Bandwidth Efficient Method for Generating an Alpha Hint Buffer

    公开(公告)号:US20170213315A1

    公开(公告)日:2017-07-27

    申请号:US15242478

    申请日:2016-08-19

    Applicant: MediaTek Inc.

    CPC classification number: G06T1/60 G06T11/40 G06T11/60

    Abstract: A graphics processing unit (GPU) renders graphical objects into a group of pixels and stores the pixels in an on-chip buffer on the same chip as the GPU. Each pixel has an alpha value that indicates transparency of the pixel. The GPU reads the alpha value of each pixel from the on-chip buffer. According to alpha values of the group of pixels, the GPU generates an alpha hint in the system memory for the group of pixels. The alpha hint represents an aggregate of the alpha values of the group of pixels. The GPU then stores the group of pixels into a frame buffer in the system memory.

    Graphic Processing Circuit With Binning Rendering And Pre-Depth Processing Method Thereof
    15.
    发明申请
    Graphic Processing Circuit With Binning Rendering And Pre-Depth Processing Method Thereof 有权
    具有分层渲染和深度处理方法的图形处理电路

    公开(公告)号:US20160180539A1

    公开(公告)日:2016-06-23

    申请号:US14582134

    申请日:2014-12-23

    Applicant: MediaTek Inc.

    CPC classification number: G06T15/005 G06T15/40

    Abstract: A graphic processing circuit with binning rendering and associated pre-depth processing method is provided. Firstly, a first depth data of a first primitive corresponding to a specified tile is received. Then, the pre-depth data corresponding to the specified tile is read from a pre-Z buffer. If the first depth data is not larger than the pre-depth data and the first primitive is an opaque primitive, the pre-depth data is updated with the first depth data. If the first depth data is not larger than the pre-depth data and the first primitive is a translucent primitive, an uncertainty ordering range is defined according to the first depth data and the pre-depth data, and the pre-depth data is updated with the uncertainty ordering range.

    Abstract translation: 提供了具有binning渲染和相关的预深度处理方法的图形处理电路。 首先,接收对应于指定瓦片的第一原语的第一深度数据。 然后,从预Z缓冲器读取对应于指定瓦片的预深度数据。 如果第一深度数据不大于预深度数据,并且第一原语是不透明原语,则用第一深度数据更新预深度数据。 如果第一深度数据不大于预深度数据,并且第一图元是半透明图元,则根据第一深度数据和预深度数据来定义不确定性排序范围,并且更新预深度数据 具有不确定性排序范围。

    METHOD FOR PERFORMING AUTOMATIC ACTIVATION CONTROL REGARDING VARIABLE RATE SHADING, AND ASSOCIATED APPARATUS

    公开(公告)号:US20240386648A1

    公开(公告)日:2024-11-21

    申请号:US18583884

    申请日:2024-02-22

    Applicant: MEDIATEK INC.

    Abstract: A method for performing automatic activation control regarding VRS and associated apparatus are provided. The method applicable to a processing circuit may include: utilizing a rendering classifier to intercept at least one set of original graphic commands on a command path to obtain at least one rendering property, for classifying rendering corresponding to the at least one set of original graphic commands; utilizing the rendering classifier to classify the rendering into at least one predetermined rendering type among multiple predetermined rendering types according to the at least one rendering property, in order to determine at least one shading rate corresponding to the at least one predetermined rendering type for the rendering; and utilizing a shading rate controller to control the processing circuit to selectively activate a VRS function of the processing circuit, for rendering at the at least one shading rate corresponding to the at least one predetermined rendering type.

Patent Agency Ranking