Abstract: Aspects include API interfaces for interfacing shaders with other components and/or code modules that provide ray tracing functionality. For example, API calls may allow direct contribution of light energy to a buffer for an identified pixel, and allow emission of new rays for intersection testing alone or in bundles. The API also can provide a mechanism for associating arbitrary data with ray definition data defining a ray to be tested through a shader using the emit ray call. The arbitrary data is provided to a shader associated with an object that is identified subsequently as having been intersected by the ray. The data can include code, or a pointer to code, that can be used by or run after the shader. The data also can be propagated through a series of shaders, and associated with rays instantiated in each shader.

Abstract: Systems and methods include high throughput and/or parallelized ray/geometric shape intersection testing using intersection testing resources accepting and operating with block floating point data. Block floating point data sacrifices precision of scene location in ways that maintain precision where more beneficial, and allow reduced precision where beneficial. In particular, rays, acceleration structures, and primitives can be represented in a variety of block floating point formats, such that storage requirements for storing such data can be reduced. Hardware accelerated intersection testing can be provided with reduced sized math units, with reduced routing requirements. A driver for hardware accelerators can maintain full-precision versions of rays and primitives to allow reduced communication requirements for high throughput intersection testing in loosely coupled systems. Embodiments also can include using BFP formatted data in programmable test cells or more general purpose processing elements.

Abstract: A system which utilizes the processing capabilities of the graphics processing unit (GPU) in the graphics controller. Each frame of each video stream is decoded. After decoding the compressed image is separated into an image representing the luminance and an image representing the chroma. The chroma image is resampled as appropriate using the GPU to provide chroma values corresponding to each luminance value at the proper locations. The resampled chroma image and the luminance image are properly combined to produce a 4:4:4 image, preferably in the RGB color space, and provided to the frame buffer for final display. Each of these operations is done in real time for each frame of the video.

Abstract: A system which utilizes the processing capabilities of the graphics processing unit (GPU) in the graphics controller. Each frame of each video stream or track is decoded into a buffer and a color profile indicating parameters of the color space of the video source is associated with the buffer. The compositor uses the color profile to convert each buffer to a defined working color space from the source color space. This conversion and rendering of the buffer is performed using the fragment processing capabilities of the GPU. The compositor then instructs the GPU to convert the buffer to the final color space of the display device and the frame is rendered to the frame buffer for final display. Each of these operations is done in real time for each frame of the video.

Abstract: Techniques are described for creating and storing data describing a pixel aspect ratio and specifications of the clean aperture of video data. This data may be used to determine parameters of one or more modes of display which may be selected for an individual track based upon the rendering intent, and the parameters may be stored with the video data.