GPU Performance Testing via Multi-Scene Rendering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a lack of a complete and reliable method for accurately testing the performance of graphics processing units (GPUs) with different architectures, which hinders precise evaluation and comparison of their capabilities.
Innovation Solution
A method involving capturing and rendering 3D scenes using a main camera and script objects to execute rendering processes on the GPU, incrementing a rendering execution number, and determining performance parameters based on time taken to complete a predetermined number of rendering processes, allowing for the assessment of GPU performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional GPU performance testing methods are used, then testing can be performed, but the accuracy and reliability of performance evaluation is insufficient
Solution Approach 1:
The patent changes the testing parameters by implementing a multi-scene rendering approach where the main camera captures and renders multiple different scenes (first scene, second scene, third scene) with varying complexity levels. This varies the computational load parameters to achieve more accurate and reliable performance measurements across different operating conditions.
Solution Approach 2:
The testing method achieves universality by creating a comprehensive test framework that can evaluate GPU performance across multiple scenarios simultaneously. The system uses a unified testing architecture that handles different scene types, camera movements, and rendering configurations, making the performance evaluation applicable to various GPU architectures and use cases.
2Adaptability or versatility
If a single scene rendering test is used, then the test is simple to implement, but it cannot accurately reflect GPU performance across different scenarios
Solution Approach 1:
The patent segments the performance testing into distinct components: first scene rendering, second scene rendering, third scene rendering, and auxiliary object rendering. Each scene is tested separately with specific camera movements and rendering parameters, allowing comprehensive evaluation while maintaining organized and manageable test structures.
Solution Approach 2:
The system performs preliminary actions by pre-configuring multiple scenes with different complexity levels, pre-defining camera movement paths, and pre-establishing the rendering test framework before actual performance measurement. This preparation enables the system to efficiently execute comprehensive tests without adding excessive complexity during the actual testing phase.
Data Source
AI summary
Embodiments of the present disclosure provide a method for testing performance of GPU, a terminal device and a storage medium. The method comprises: capturing a target scene from a 3D scene model by a main camera in the 3D scene model; determining an execution sequence of functions in a script object of the target object and determining a target rendering process according to the execution sequence; obtaining a target image via the target rendering process, and incrementing a rendering execution number i by 1; moving the main camera, capturing a new scene to update the target scene and iterating the above steps until i is equal to j; obtaining a time period T for completing j target rendering processes, and determining a target performance parameter according to j and T; and determining a performance test result of the GPU according to the target performance parameter and a performance criterion parameter.