Abstract: Reordering workloads to improve concurrency across threads in processor-based devices is disclosed herein. In this regard, in some exemplary aspects, a processor-based device receives a plurality of workloads from a requestor, and constructs a weighted dependency graph based on the plurality of workloads. The weighted dependency graph comprises a plurality of vertices that each correspond to a workload of the plurality of workloads, and further comprises one or more directed edges that each connects two vertices of the plurality of vertices and indicates a dependency between a corresponding two workloads of the plurality of workloads. After generating the weighted dependency graph, the processor-based device performs a topological sort of the weighted dependency graph, and generates a workload execution order based on the topological sort.

Abstract: The present disclosure relates to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may process at least one frame including frame content associated with a grid including a plurality of grid sections, each of a plurality of portions of the frame content being aligned with at least a portion of at least one of the plurality of grid sections. The apparatus may also shift the frame content with respect to the grid, such that at least one portion of the plurality of portions of the frame content is aligned with at least a portion of at least one distinct grid section of the plurality of grid sections. Additionally, the apparatus may store the shifted frame content including the at least one portion of the frame content that is aligned with at least a portion of the at least one distinct grid section.

Abstract: The present disclosure relates to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may process at least one frame including frame content associated with a grid including a plurality of grid sections, each of a plurality of portions of the frame content being aligned with at least a portion of at least one of the plurality of grid sections. The apparatus may also shift the frame content with respect to the grid, such that at least one portion of the plurality of portions of the frame content is aligned with at least a portion of at least one distinct grid section of the plurality of grid sections. Additionally, the apparatus may store the shifted frame content including the at least one portion of the frame content that is aligned with at least a portion of the at least one distinct grid section.

Abstract: Example techniques are described for generating graphics content by obtaining a rendering command for a frame of the graphics content, obtaining an eye position of a user after obtaining the rendering command, determining a foveation parameter for a region of the graphics content based on the eye position; and rendering a tile, of the frame, corresponding to the region of the graphics content using the foveation parameter and the rendering command.

Abstract: A method, a computer-readable medium, and an apparatus are provided. The apparatus may be configured to receive information indicative of a fovea region. The apparatus may be configured to identify, based on the information indicative of the fovea region, high priority bins and low priority bins. The apparatus may be configured to determine a rendering time allotment for the frame. The apparatus may be configured to determine that the rendering time allotment for the frame will be exceeded, based on an amount of time used to render the high priority bins and the low priority bins. The apparatus may be configured to render, based on the determination that the rendering time allotment for the frame will be exceeded, at least one of the low priority bins at a first quality instead of a second quality.

Abstract: Example techniques are described for generating graphics content by assigning a first region of the graphics content to a first tile, assigning a second region of the graphics content to a second tile, determining, at the first tile and at a first resolution, a first set of samples of the graphics content for each pixel of multiple pixels associated with the first region, determining, at the second tile and at a second resolution that is lower than the first resolution, a second set of samples of the graphics content for each pixel of multiple pixels associated with the second region, downsampling the first set of samples into a combined set of samples, preserving samples of the second set of samples to generate a third set of samples with preserved samples, storing the combined set of samples, and storing the third set of samples with preserved samples.

Abstract: This disclosure describes examples for foveated rendering. A graphics processing unit (GPU) may render image content for portions of an image at different sizes such as at sizes smaller than the size of the portions, and store the smaller-sized image content in system memory. The GPU or some other processing circuitry may retrieve the smaller-sized image content from the system memory, and perform resizing operations to resize the image content to its actual size.

Abstract: A method, a computer-readable medium, and an apparatus are provided. The apparatus may be configured to receive information indicative of a fovea region. The apparatus may be configured to identify, based on the information indicative of the fovea region, high priority bins and low priority bins. The apparatus may be configured to determine a rendering time allotment for the frame. The apparatus may be configured to determine that the rendering time allotment for the frame will be exceeded, based on an amount of time used to render the high priority bins and the low priority bins. The apparatus may be configured to render, based on the determination that the rendering time allotment for the frame will be exceeded, at least one of the low priority bins at a first quality instead of a second quality.

Abstract: A method, a computer-readable medium, and an apparatus are provided. The apparatus may be configured to receive information indicative of a fovea region. The apparatus may be configured to identify, based on the information indicative of the fovea region, high priority bins and low priority bins. The apparatus may be configured to determine a rendering time allotment for the frame. The apparatus may be configured to determine that the rendering time allotment for the frame will be exceeded, based on an amount of time used to render the high priority bins and the low priority bins. The apparatus may be configured to render, based on the determination that the rendering time allotment for the frame will be exceeded, at least one of the low priority bins at a first quality instead of a second quality.

Abstract: A method, a computer-readable medium, and an apparatus are provided. The apparatus may be configured to receive information indicative of a fovea region. The apparatus may be configured to identify, based on the information indicative of the fovea region, high priority bins and low priority bins. The apparatus may be configured to determine a rendering time allotment for the frame. The apparatus may be configured to determine that the rendering time allotment for the frame will be exceeded, based on an amount of time used to render the high priority bins and the low priority bins. The apparatus may be configured to render, based on the determination that the rendering time allotment for the frame will be exceeded, at least one of the low priority bins at a first quality instead of a second quality.

Abstract: Techniques are described for generating, with a graphics processing unit (GPU), depth values for pixels of a tile. The tile is one of a plurality of tiles of a frame. The GPU may store a first number of the depth values for the pixels in a tile memory internal to the GPU. The tile memory is configured to store image content for the tile of the frame. The GPU may write a second number of the depth values stored in the tile memory to a system memory. The second number is less than the first number.

Abstract: This disclosure proposes utilizing user movement and virtual object movements to correct a displayed frame in a field-sequential display in a display system. Temporal delay of each color channel is corrected by re-sampling rendered frames before display so each color channel is offset appropriately based on the motion of the rendered content and/or the motion of the user. The correction can be applied during a timewarp rendering pass. A user's physical movement can be corrected using the user's change in pose/position to apply a color channel correction to the entire rendered frame. In-frame content movement can be corrected using the motion of the rendered content to apply focused color channel correction to targeted regions of the rendered frame.

Abstract: Example techniques are described for generating graphics content by obtaining a rendering command for a frame of the graphics content, obtaining an eye position of a user after obtaining the rendering command, determining a foveation parameter for a region of the graphics content based on the eye position; and rendering a tile, of the frame, corresponding to the region of the graphics content using the foveation parameter and the rendering command.

Abstract: Example techniques are described for generating graphics content by assigning a first region of the graphics content to a first tile, assigning a second region of the graphics content to a second tile, determining, at the first tile and at a first resolution, a first set of samples of the graphics content for each pixel of multiple pixels associated with the first region, determining, at the second tile and at a second resolution that is lower than the first resolution, a second set of samples of the graphics content for each pixel of multiple pixels associated with the second region, downsampling the first set of samples into a combined set of samples, preserving samples of the second set of samples to generate a third set of samples with preserved samples, storing the combined set of samples, and storing the third set of samples with preserved samples.

Abstract: Techniques are described for generating, with a graphics processing unit (GPU), depth values for pixels of a tile. The tile is one of a plurality of tiles of a frame. The GPU may store a first number of the depth values for the pixels in a tile memory internal to the GPU. The tile memory is configured to store image content for the tile of the frame. The GPU may write a second number of the depth values stored in the tile memory to a system memory. The second number is less than the first number.

Abstract: This disclosure describes examples for foveated rendering. A graphics processing unit (GPU) may render image content for portions of an image at different sizes such as at sizes smaller than the size of the portions, and store the smaller-sized image content in system memory. The GPU or some other processing circuitry may retrieve the smaller-sized image content from the system memory, and perform resizing operations to resize the image content to its actual size.