公开(公告)号：US08559733B2

公开(公告)日：2013-10-15

申请号：US12728740

申请日：2010-03-22

申请人： Julian Petrov

发明人： Julian Petrov

IPC分类号： G06K9/36

CPC分类号： G06T9/00 ,  H04N19/17 ,  H04N19/46 ,  H04N19/59

摘要： An image partitioner that executes on a local computer to vertically partition pixels of an original image into one or more non-overlapping vertical rows of image pixels, and horizontally partition the original image pixels into one or more non-overlapping horizontal rows of image pixels. The image partitioner can then separate the original image into a first sub-image that includes pixels of a first horizontal row and pixels of a first vertical row. The image partitioner can then separate the original image into a second sub-image that includes pixels of either the first horizontal row and a second vertical row, or a second horizontal row and the first vertical row. The first sub-image and second sub-image are then transmitted to a remote computer that interlaces the first sub-image with the second sub-image to create a first combined image which approximates the original image on the local computer.

摘要翻译： 图像分割器，其在本地计算机上执行以将原始图像的像素垂直分割成一个或多个不重叠的垂直行的图像像素，并且将原始图像像素水平分割成一个或多个不重叠的水平行的图像像素。 然后，图像分割器可以将原始图像分离成包括第一水平行的像素和第一垂直行的像素的第一子图像。 然后，图像分割器可以将原始图像分离成包括第一水平行和第二垂直行，或第二水平行和第一垂直行的像素的第二子图像。 然后将第一子图像和第二子图像发送到与第二子图像交错第一子图像的远程计算机，以创建近似本地计算机上的原始图像的第一组合图像。

公开(公告)号：US20090189892A1

公开(公告)日：2009-07-30

申请号：US12360842

申请日：2009-01-27

申请人： Nitin Desai ,  Julian Petrov ,  Tim Corbett

发明人： Nitin Desai ,  Julian Petrov ,  Tim Corbett

IPC分类号： G06T15/00

CPC分类号： G06T15/005 ,  G06F3/14 ,  G06F9/452 ,  G06F9/453 ,  G06F9/505 ,  G06F2209/509 ,  G06T19/00 ,  G06T2200/16 ,  G09G2340/02

摘要： Methods and systems for detecting a dirty region within a frame encompassing three dimensional graphics and three dimensional graphics primitives. The methods and systems include executing an application on a local computing machine, the application generating three dimensional graphics, and issuing at least one function call. An agent also executes on the local computing machine to intercept the issued function call; identify, in response to intercepting the function call, at least one location within a frame that contains three dimensional graphics commands generated by the application, where the identified location corresponding to a drawing region; determine a change in a portion of the three dimensional graphics commands associated with the identified location; and extract the changed portion. The agent may also identify a plurality of locations and a plurality of changed three dimensional graphics commands at those locations.

摘要翻译： 用于检测包含三维图形和三维图形图元的框架内的脏区域的方法和系统。 方法和系统包括在本地计算机上执行应用，生成三维图形的应用，以及发出至少一个功能调用。 代理还在本地计算机上执行拦截发出的函数调用; 识别响应于截取所述功能调用的框架内的至少一个位置，所述至少一个位置包含由所述应用产生的三维图形命令，其中所述标识位置对应于绘图区域; 确定与所识别的位置相关联的三维图形命令的一部分的改变; 并提取更改的部分。 代理还可以在这些位置处识别多个位置和多个改变的三维图形命令。

公开(公告)号：US09146762B2

公开(公告)日：2015-09-29

申请号：US13592891

申请日：2012-08-23

申请人： Julian Petrov ,  Sandy Stutsman

发明人： Julian Petrov ,  Sandy Stutsman

IPC分类号： G06F13/12 ,  G06F13/38 ,  G06F9/455 ,  G09G5/36

CPC分类号： G06F9/45533 ,  G09G5/363

摘要： A computing system includes a graphics processing unit (GPU) and main processing circuitry to execute computer program instructions forming a hypervisor, a control virtual machine (VM) and a specialized rendering VM for graphics processing. An application program of a guest VM generates graphics commands and data according to a graphics API such as Direct 3D. The rendering VM includes a graphics driver native to the GPU and is assigned pass-through access to the GPU by the control VM. The rendering VM receives the graphics information from the application program via an inter-VM communication channel, and it uses the graphics driver to control the GPU to perform graphics rendering. The use of the rendering VM enables native graphics performance to be achieved without constraining the control VM to use a compatible operating system. The technique is generally applicable to virtualization of hardware resources by specialized VMs.

摘要翻译： 计算系统包括图形处理单元（GPU）和用于执行形成管理程序的计算机程序指令的主处理电路，用于图形处理的控制虚拟机（VM）和专用渲染VM。 访客VM的应用程序根据诸如Direct 3D的图形API生成图形命令和数据。 渲染VM包括GPU原生的图形驱动器，并被控制VM分配给GPU的直通访问。 渲染VM经由VM通信通道从应用程序接收图形信息，并且它使用图形驱动器来控制GPU执行图形呈现。 使用渲染虚拟机可以实现本机图形性能，而不会限制控制VM使用兼容的操作系统。 该技术通常适用于专门的虚拟机的硬件资源的虚拟化。

公开(公告)号：US20100246982A1

公开(公告)日：2010-09-30

申请号：US12728740

申请日：2010-03-22

申请人： Julian Petrov

发明人： Julian Petrov

IPC分类号： G06K9/36

CPC分类号： G06T9/00 ,  H04N19/17 ,  H04N19/46 ,  H04N19/59

摘要： An image partitioner that executes on a local computer to vertically partition pixels of an original image into one or more non-overlapping vertical rows of image pixels, and horizontally partition the original image pixels into one or more non-overlapping horizontal rows of image pixels. The image partitioner can then separate the original image into a first sub-image that includes pixels of a first horizontal row and pixels of a first vertical row. The image partitioner can then separate the original image into a second sub-image that includes pixels of either the first horizontal row and a second vertical row, or a second horizontal row and the first vertical row. The first sub-image and second sub-image are then transmitted to a remote computer that interlaces the first sub-image with the second sub-image to create a first combined image which approximates the original image on the local computer.

摘要翻译： 图像分割器，其在本地计算机上执行以将原始图像的像素垂直分割成一个或多个不重叠的垂直行的图像像素，并且将原始图像像素水平分割成一个或多个不重叠的水平行的图像像素。 然后，图像分割器可以将原始图像分离成包括第一水平行的像素和第一垂直行的像素的第一子图像。 然后，图像分割器可以将原始图像分离成包括第一水平行和第二垂直行，或第二水平行和第一垂直行的像素的第二子图像。 然后将第一子图像和第二子图像发送到与第二子图像交错第一子图像的远程计算机，以创建近似本地计算机上的原始图像的第一组合图像。