Abstract: A server and methods for performing an ultra-high resolution pan-scan on displays connected across multiple client GPUs are provided. In one embodiment, one of the methods includes: 1) rendering a surface that exceeds resolutions of displays connected to multiple client GPUs; 2) receiving viewport coordinates of one of the displays that is connected to one of the multiple client GPUs; 3) encoding only a portion of the surface that corresponds to the viewport coordinates; 4) sending the portion to the one of the multiple client GPUs.

Abstract: A server and methods for performing an ultra-high resolution pan-scan on displays connected across multiple client GPUs are provided. In one embodiment, one of the methods includes: 1) rendering a surface that exceeds resolutions of displays connected to multiple client GPUs; 2) receiving viewport coordinates of one of the displays that is connected to one of the multiple client GPUs; 3) encoding only a portion of the surface that corresponds to the viewport coordinates; 4) sending the portion to the one of the multiple client GPUs.

Abstract: A method includes providing a memory unit in a computing device already including a number of processors communicatively coupled to a memory through a system bus, and providing a non-system bus based dedicated channel between the number of processors and the memory unit. The method also includes rendering a different video frame and/or a surface on each processor of the number of processors, and leveraging the memory unit to store a video frame and/or a surface rendered on a processor therein through the non-system bus based dedicated channel. Further, the method includes copying, to other processors, the stored video frame and/or the surface rendered on the processor from the memory unit through the non-system bus based dedicated channel, and scanning out, through the number of processors, the video frame and/or the surface rendered on the processor following the copying to enable display thereof on a corresponding number of displays.

Abstract: A computing system and method for automatically making a display configuration persistent. One embodiment of the computing system includes: (1) a video adapter coupled to a data bus and operable to interface a display configuration associated with extended display identification data (EDID), (2) a cache configured to store the EDID, and (3) a central processing unit (CPU) coupled to the data bus and the cache, and operable to execute a driver associated with the video adapter and configured to detect the display configuration and cause the EDID to be written to the cache.

Abstract: A method includes providing a memory unit in a computing device already including a number of processors communicatively coupled to a memory through a system bus, and providing a non-system bus based dedicated channel between the number of processors and the memory unit. The method also includes rendering a different video frame and/or a surface on each processor of the number of processors, and leveraging the memory unit to store a video frame and/or a surface rendered on a processor therein through the non-system bus based dedicated channel. Further, the method includes copying, to other processors, the stored video frame and/or the surface rendered on the processor from the memory unit through the non-system bus based dedicated channel, and scanning out, through the number of processors, the video frame and/or the surface rendered on the processor following the copying to enable display thereof on a corresponding number of displays.

Abstract: A method includes defining, through a graphics driver component of a graphics processor of a computing device, a custom mode of displaying pixel data from the graphics processor on a display communicatively coupled to the computing device, and receiving, as an input through the custom mode, dimensional parameters of the display through the graphics processor. The custom mode is interpretable through an operating system executing on the computing device. The method also includes providing a virtual representation of the display through the operating system based on the received dimensional parameters of the display, and scaling, through the graphics processor, the pixel data corresponding to a scanout of the graphics processor to fit within the virtual representation of the display to provide a one-on-one mapping between a virtual display canvas corresponding to the scanout of the graphics processor and dimensions of the display.