公开(公告)号：US11941724B2

公开(公告)日：2024-03-26

申请号：US17665678

申请日：2022-02-07

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xindong Shi ,  Shu Wang ,  Jiangzheng Wu ,  Mingwei Lu

IPC: G06N3/04 ,  G06N3/08 ,  G06T1/20 ,  G06T1/60 ,  G06T3/40 ,  G06T7/40 ,  G06V10/82

CPC classification number: G06T1/20 ,  G06T1/60 ,  G06T3/40 ,  G06T7/40

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.

公开(公告)号：US20220156878A1

公开(公告)日：2022-05-19

申请号：US17665678

申请日：2022-02-07

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xindong Shi ,  Shu Wang ,  Jiangzheng Wu ,  Mingwei Lu

IPC: G06T1/20 ,  G06T7/40 ,  G06T1/60 ,  G06T3/40

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.