Abstract: This application provides a model inference method and apparatus based on a graphics rendering pipeline, and a storage medium for model inference based on a graphics rendering pipeline. The method includes: obtaining an instruction stream in a render thread; extracting and saving texture data information from the instruction stream, where the texture data information includes texture data; and inputting the texture data information to a graphics processing unit (GPU) rendering pipeline, where the GPU rendering pipeline is used to perform GPU model-based inference on the texture data based on a GPU model to obtain an inference result of the texture data, and the GPU model is a model running in a GPU. This implements model inference on the texture data, and avoids conversion of the texture data into another data type, thereby reducing I/O memory overheads.

Abstract: A graphics rendering method includes obtaining, by a central processing unit (CPU), to-be-processed vertex data. The to-be-processed vertex data is vertex data used by a graphics processing unit (GPU) for graphics rendering processing. The method also includes processing, by the CPU, the to-be-processed vertex data to obtain vertex data within a field of view of a user. The method additionally includes sending, by the CPU, the vertex data within the field of view of the user to the GPU for the graphics rendering processing.

Abstract: An image rendering method and a related device thereof are disclosed. The method includes: performing ray tracing based on rendering information of a reflecting object, and storing an obtained image of a reflection in the reflecting object in a first frame buffer, where the first frame buffer is used for storing an image that does not need to be displayed temporarily; performing rasterization separately based on the rendering information of the reflecting object and rendering information of a reflected object, and storing an obtained image of the reflecting object and an obtained image of the reflected object in a second frame buffer, where the second frame buffer is used for storing an image to be displayed; and obtaining, from the first frame buffer, the image of the reflection in the reflecting object, and storing the image of the reflection in the reflecting object in the second frame buffer.

Abstract: This application provides a model inference method and apparatus based on a graphics rendering pipeline, and a storage medium for model inference based on a graphics rendering pipeline. The method includes: obtaining an instruction stream in a render thread; extracting and saving texture data information from the instruction stream, where the texture data information includes texture data; and inputting the texture data information to a graphics processing unit (GPU) rendering pipeline, where the GPU rendering pipeline is used to perform GPU model-based inference on the texture data based on a GPU model to obtain an inference result of the texture data, and the GPU model is a model running in a GPU. This implements model inference on the texture data, and avoids conversion of the texture data into another data type, thereby reducing I/O memory overheads.

Abstract: This application relates to the field of graphics rendering technologies, and specifically discloses a graphics rendering method and a related apparatus. A central processing unit CPU captures an instruction stream of a graphics processing unit GPU to obtain vertex data required by the GPU for graphics rendering; the CPU performs primitive processing such as coordinate transformation and clipping on the obtained vertex data to obtain vertex data within a field of view of a user; and the CPU sends the vertex data within the field of view of the user to the graphics processing unit GPU, so that the GPU performs graphics rendering processing based on the vertex data processed by the CPU. In technical solutions provided in this application, load of the GPU can be reduced during graphics rendering.