公开(公告)号：US09183610B2

公开(公告)日：2015-11-10

申请号：US13745350

申请日：2013-01-18

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G06T1/00 ,  G06T15/00 ,  G06F15/00 ,  G06T1/20 ,  G09G5/36

CPC classification number: G06T1/20 ,  G09G5/363 ,  G09G2340/0407 ,  G09G2340/10

Abstract: The invention provides a method for driving a graphic processing unit (GPU), where a driver applies two threads to drive one ore more GPUs. The method includes the steps of: (a) activating a rendering thread and a displaying thread in response to invoking by an application thread of a graphics application; (b) sending according to the rendering thread a plurality of rendering instructions for enabling generation of at least a first rendered frame and a second rendered frame; and (c) sending according to the displaying thread one or more interpolating instructions and one or more displaying instructions, the one or more interpolating instructions enabling execution of interpolation according to the at least a first rendered frame and the second rendered frame to create one or more interpolated frames, and the one or more displaying instructions enabling display of the one or more interpolated frames.

Abstract translation: 本发明提供了一种用于驱动图形处理单元（GPU）的方法，其中驱动程序应用两个线程来驱动一个或多个GPU。 该方法包括以下步骤：（a）响应于图形应用程序的应用程序线程的调用激活呈现线程和显示线程; （b）根据呈现线程发送多个渲染指令，以便能够生成至少第一渲染帧和第二渲染帧; 以及（c）根据显示线程发送一个或多个内插指令和一个或多个显示指令，所述一个或多个内插指令使得能够根据至少第一渲染帧和第二渲染帧来执行内插以创建一个或多个内插指令 更多的内插帧，以及一个或多个显示指令，使得能够显示一个或多个内插帧。

公开(公告)号：US10459873B2

公开(公告)日：2019-10-29

申请号：US13754256

申请日：2013-01-30

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters ,  Ratin Kumar ,  Lieven Leroy

IPC: G06F15/00 ,  G06F1/20 ,  G06F1/3215 ,  G06F1/3234

Abstract: The invention provides a method for adaptively adjusting a framerate of a graphic processing unit (GPU). For example, when the GPU workload is high and the temperature of the GPU is close to high temperature, the framerate can be decreased to reduce the workload; when the GPU workload is low, the framerate can be permitted to increase to raise the workload. By the present invention, the GPU is permitted to operate at maximum temperature. The method comprises the steps of: (a) receiving an execution parameter associated with at least one GPU; (b) comparing if the execution parameter is greater than a first reference value; and (c) in the event the execution parameter is greater than the first reference value, increasing a sleep time and power-gating the at least one GPU based on the sleep time to adjust the framerate.

公开(公告)号：US20140125670A1

公开(公告)日：2014-05-08

申请号：US13730441

申请日：2012-12-28

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G06T15/80

CPC classification number: G06T5/002 ,  G06T13/80 ,  G06T15/005 ,  G06T2207/10016 ,  G06T2207/20201

Abstract: The invention provides a method for approximating motion blur in rendered frame from within a graphics driver. For example, the method includes the steps of: (a) obtaining by the graphics driver values of a frame transformation matrix for a current rendered frame and a previous rendered frame respectively; (b) obtaining by the graphics driver depth values of the current rendered frame; and (c) loading by the graphics driver a shader onto a GPU, in order to enable the GPU to adjust color values of one or more sample areas on the current rendered frame, based on at least the values of the frame transformation matrix for the current rendered frame and the previous rendered frame and the depth values of the current rendered frame, whereby a motion blur effect is created in the current rendered frame.

Abstract translation: 本发明提供了一种用于在图形驱动器内从渲染帧近似运动模糊的方法。 例如，该方法包括以下步骤：（a）分别通过图形驱动程序获取当前渲染帧和先前渲染帧的帧变换矩阵的值; （b）通过图形驱动程序获取当前渲染帧的深度值; 以及（c）由图形驱动器将着色器加载到GPU上，以便使得GPU能够基于至少对于当前渲染帧的帧变换矩阵的值来调整当前渲染帧上的一个或多个采样区域的颜色值 当前渲染帧和先前渲染的帧以及当前渲染帧的深度值，由此在当前渲染帧中创建运动模糊效果。

公开(公告)号：US09576340B2

公开(公告)日：2017-02-21

申请号：US13727216

申请日：2012-12-26

Applicant: NVIDIA CORPORATION

Inventor： Dawid Stanislaw Pajak ,  David Luebke ,  Scott Saulters

IPC: G06T5/00 ,  G06T11/00 ,  G06T1/20 ,  G06T9/00 ,  H04N19/46 ,  H04N19/61

CPC classification number: G06T5/00 ,  G06T1/20 ,  G06T9/004 ,  G06T11/00 ,  H04N19/46 ,  H04N19/61

Abstract: A technique for efficiently compressing rendered three-dimensional images in a remote rendering system adds a novel render-assisted prediction function to an existing video compression framework, such as the standard H.264/5 framework. Auxiliary rendering information is separated from rendering information used to describe a reference image by a server system. A client system may alter the auxiliary data and generate a new image based on the reference image and rendered scene information from the auxiliary data without creating additional network bandwidth or server workload.

Abstract translation: 用于在远程渲染系统中有效压缩渲染的三维图像的技术将新颖的渲染辅助预测功能添加到诸如标准H.264 / 5框架的现有视频压缩框架中。 辅助渲染信息与用于由服务器系统描述参考图像的渲染信息分离。 客户端系统可以改变辅助数据，并且从辅助数据基于参考图像和呈现的场景信息生成新图像，而不产生额外的网络带宽或服务器工作负载。

公开(公告)号：US20140125687A1

公开(公告)日：2014-05-08

申请号：US13730378

申请日：2012-12-28

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G06T15/04

CPC classification number: G06T15/04

Abstract: A method for sub-pixel texture mapping and filtering is provided. The method includes the steps of: dividing an area on a source image into a red (R) sub-area, a green (G) sub-area, and a blue (B) sub-area, where the area on the source image is corresponding to a pixel of a destination image presented by a display device; sampling the R sub-area to obtain a R color value, sampling the G sub-area to obtain a G color value, and sampling the B sub-area to obtain a B color value; and rendering R, G, B color components of the pixel of the destination image according to the R color value, the G color value, and the B color value.

Abstract translation: 提供了一种亚像素纹理映射和滤波的方法。 该方法包括以下步骤：将源图像上的区域划分为红色（R）子区域，绿色（G）子区域和蓝色（B）子区域，其中源图像上的区域 对应于由显示装置呈现的目的地图像的像素; 对R子区域进行采样以获得R颜色值，对G子区域进行采样以获得G色值，并对B子区域进行采样以获得B色值; 以及根据R颜色值，G颜色值和B颜色值呈现目的地图像的像素的R，G，B颜色分量。

公开(公告)号：US20140028679A1

公开(公告)日：2014-01-30

申请号：US13727265

申请日：2012-12-26

Applicant: NVIDIA CORPORATION

Inventor： Dawid Stanislaw Pajak ,  David Luebke ,  Scott Saulters

IPC: G06T5/00

CPC classification number: G06T5/00 ,  G06T1/20 ,  G06T9/004 ,  G06T11/00 ,  H04N19/46 ,  H04N19/61

Abstract: A technique for efficiently compressing rendered three-dimensional images in a remote rendering system adds a novel render-assisted prediction function to an existing video compression framework, such as the standard H.264/5 framework. Auxiliary rendering information is separated from rendering information used to describe a reference image by a server system. A client system may alter the auxiliary data and generate a new image based on the reference image and rendered scene information from the auxiliary data without creating additional network bandwidth or server workload.

公开(公告)号：US09412194B2

公开(公告)日：2016-08-09

申请号：US13730378

申请日：2012-12-28

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G09G5/00 ,  G06T15/04

CPC classification number: G06T15/04

Abstract: A method for sub-pixel texture mapping and filtering is provided. The method includes the steps of: dividing an area on a source image into a red (R) sub-area, a green (G) sub-area, and a blue (B) sub-area, where the area on the source image is corresponding to a pixel of a destination image presented by a display device; sampling the R sub-area to obtain a R color value, sampling the G sub-area to obtain a G color value, and sampling the B sub-area to obtain a B color value; and rendering R, G, B color components of the pixel of the destination image according to the R color value, the G color value, and the B color value.

Abstract translation: 提供了一种亚像素纹理映射和滤波的方法。 该方法包括以下步骤：将源图像上的区域划分为红色（R）子区域，绿色（G）子区域和蓝色（B）子区域，其中源图像上的区域 对应于由显示装置呈现的目的地图像的像素; 对R子区域进行采样以获得R颜色值，对G子区域进行采样以获得G色值，并对B子区域进行采样以获得B色值; 以及根据R颜色值，G颜色值和B颜色值呈现目的地图像的像素的R，G，B颜色分量。

公开(公告)号：US20140125680A1

公开(公告)日：2014-05-08

申请号：US13745350

申请日：2013-01-18

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G06F9/30

CPC classification number: G06T1/20 ,  G09G5/363 ,  G09G2340/0407 ,  G09G2340/10

Abstract: The invention provides a method for driving a graphic processing unit (GPU), where a driver applies two threads to drive one ore more GPUs. The method includes the steps of: (a) activating a rendering thread and a displaying thread in response to invoking by an application thread of a graphics application; (b) sending according to the rendering thread a plurality of rendering instructions for enabling generation of at least a first rendered frame and a second rendered frame; and (c) sending according to the displaying thread one or more interpolating instructions and one or more displaying instructions, the one or more interpolating instructions enabling execution of interpolation according to the at least a first rendered frame and the second rendered frame to create one or more interpolated frames, and the one or more displaying instructions enabling display of the one or more interpolated frames.

Abstract translation: 本发明提供了一种用于驱动图形处理单元（GPU）的方法，其中驱动程序应用两个线程来驱动一个或多个GPU。 该方法包括以下步骤：（a）响应于图形应用程序的应用程序线程的调用激活呈现线程和显示线程; （b）根据呈现线程发送多个渲染指令，以便能够生成至少第一渲染帧和第二渲染帧; 以及（c）根据显示线程发送一个或多个内插指令和一个或多个显示指令，所述一个或多个内插指令使得能够根据至少第一渲染帧和第二渲染帧来执行内插以创建一个或多个内插指令 更多的内插帧，以及一个或多个显示指令，使得能够显示一个或多个内插帧。

公开(公告)号：US20140092109A1

公开(公告)日：2014-04-03

申请号：US13730473

申请日：2012-12-28

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters

IPC: G06T1/20

CPC classification number: G06T1/20 ,  G09G5/363 ,  G09G5/395 ,  G09G2320/0209 ,  G09G2330/021 ,  G09G2340/0435 ,  G09G2340/16

Abstract: The invention provides a method for driving a graphic processing unit (GPU). The method comprises the steps of: (a) receiving a plurality of requests for processing a first frame, a second frame and a third frame; (b) sequentially rendering the first frame and the third frame; (c) performing an interpolation to generate the second frame according to the rendered first frame and the rendered third frame; and, (d) sequentially displaying the rendered first frame, the second frame generated by interpolation and the rendered third frame.

Abstract translation: 本发明提供了一种用于驱动图形处理单元（GPU）的方法。 该方法包括以下步骤：（a）接收多个处理第一帧，第二帧和第三帧的请求; （b）顺序渲染第一帧和第三帧; （c）根据所渲染的第一帧和渲染的第三帧执行内插以产生第二帧; 和（d）依次显示所渲染的第一帧，通过插值和渲染的第三帧产生的第二帧。

公开(公告)号：US20140092103A1

公开(公告)日：2014-04-03

申请号：US13754256

申请日：2013-01-30

Applicant: NVIDIA CORPORATION

Inventor： Scott Saulters ,  Ratin Kumar ,  Lieven Leroy

IPC: G06F15/00

CPC classification number: G06F15/00 ,  G06F1/206 ,  G06F1/3215 ,  G06F1/325

Abstract: The invention provides a method for adaptively adjusting a framerate of a graphic processing unit (GPU). For example, when the GPU workload is high and the temperature of the GPU is close to high temperature, the framerate can be decreased to reduce the workload; when the GPU workload is low, the framerate can be permitted to increase to raise the workload. By the present invention, the GPU is permitted to operate at maximum temperature. The method comprises the steps of: (a) receiving an execution parameter associated with at least one GPU; (b) comparing if the execution parameter is greater than a first reference value; and (c) in the event the execution parameter is greater than the first reference value, increasing a sleep time and power-gating the at least one GPU based on the sleep time to adjust the framerate.

Abstract translation: 本发明提供一种用于自适应地调整图形处理单元（GPU）的帧率的方法。 例如，当GPU工作负载高并且GPU的温度接近高温时，可以减小帧率以减少工作量; 当GPU工作负载低时，可以允许帧率增加以提高工作负载。 通过本发明，允许GPU在最高温度下工作。 该方法包括以下步骤：（a）接收与至少一个GPU相关联的执行参数; （b）比较执行参数是否大于第一参考值; 以及（c）在所述执行参数大于所述第一参考值的情况下，基于所述睡眠时间增加睡眠时间并对所述至少一个GPU进行选通以调整所述帧率。