Qualcomm Incorporated

Angus Dorbie

Guofang Jiao

Chun Yu

Baback Elmieh

James P Ritts

Yun Du

Alexei Vladimirovich Bourd

Jay Chunsup Yun

Thomas Fortier

In general, this disclosure relates to techniques for optimizing a graphics scene, such as a three-dimensional (3D) scene, by allowing application developers and/or graphics artists to identify which graphics instructions and associated graphics data (e.g., polygonal data, texture data) may be associated with identified performance issues. One example method comprises receiving mapping information from the external device, wherein the mapping information includes information to map the graphics instructions to primitive graphics data that is used to render one or more graphics images during execution of the graphics instructions, and identifying a performance issue associated with execution of at least one graphics instruction within the graphics instructions. The method further comprises using the mapping information to identify a portion of the primitive graphics data that is associated with the performance issue based upon execution of the at least one graphics instruction.

Mapping graphics instructions to associated graphics data during performance analysis

In general, this disclosure relates to techniques for using graphics instructions and state information received from a graphics device to visually create a graphics image. Performance analysis may also be conducted to identify potential bottlenecks during instruction execution on the graphics device. One example device includes a display device and one or more processors. The one or more processors are configured to receive a plurality of graphics instructions from an external graphics device, wherein the graphics instructions are executed by the external graphics device to display a graphics image, and to receive state information from the external graphics device, wherein the state information is associated with execution of the graphics instructions on the external graphics device. The one or more processors are further configured to display, on the display device, a representation of the graphics image according to the graphics instructions and the state information.

Performance analysis during visual creation of graphics images

Scissoring for any number of scissoring regions is performed in a sequential order by drawing one scissoring region at a time on a drawing surface and updating scissor values for pixels within each scissoring region. A scissor value for a pixel may indicate the number of scissoring regions covering the pixel and may be incremented for each scissoring region covering the pixel. A scissor value for a pixel may also be a bitmap, and a bit for a scissoring region may be set to one if the pixel is within the scissoring region. Pixels within a region of interest are passed and rendered, and pixels outside of the region are discarded. This region may be defined by a reference value, which may be set to (a) one for the union of all scissoring regions, for a scissoring UNION operation, or (b) larger than one for the intersection of multiple (e.g., all) scissoring regions, for a scissoring AND operation.

Efficient scissoring for graphics application

Methods and computing devices enable optimized triangle strip generation using forward looking game tree evaluation methods with node evaluation of strip options based on desired performance criteria. The evaluation of possible triangle paths is performed using metrics which may be weighted for each desirable criteria at each move depth. A recursive algorithm may be used to recursively descend through alternative triangle paths and accumulates a score for the path. The final score for each evaluated triangle path at a dead end or maximum depth of evaluation provides a basis for selecting the best alternative path from the base or root triangle for graphic processing. This evaluation or alternative triangle paths may be repeated to select each subsequent triangle for processing or may be repeated after a number of triangles within the selected path have been processed.

Method and apparatus for optimizing triangles into triangle strips according to a variety of criteria

Techniques for supporting both 2-D and 3-D graphics are described. A graphics processing unit (GPU) may perform 3-D graphics processing in accordance with a 3-D graphics pipeline to render 3-D images and may also perform 2-D graphics processing in accordance with a 2-D graphics pipeline to render 2-D images. Each stage of the 2-D graphics pipeline may be mapped to at least one stage of the 3-D graphics pipeline. For example, a clipping, masking and scissoring stage in 2-D graphics may be mapped to a depth test stage in 3-D graphics. Coverage values for pixels within paths in 2-D graphics may be determined using rasterization and depth test stages in 3-D graphics. A paint generation stage and an image interpolation stage in 2-D graphics may be mapped to a fragment shader stage in 3-D graphics. A blending stage in 2-D graphics may be mapped to a blending stage in 3-D graphics.

Efficient 2-D and 3-D graphics processing

Methods and computing devices enable the generation of contiguous triangle patches for use in generating triangle strips for processing in a computer graphics engine. A seed triangle is selected and a patch of contiguous triangles is formed by incrementally adding adjacent triangles to the patch at equal steps from the seed triangle until a limit is reached or no more triangles can be added to the patch. Triangles whose vertices are already included in the patch are also added to the patch. If no more triangles can be added to the patch before the vertex limit is reached, a new seed triangle may be selected and another patch generated until the vertex limit is reached. Forming patches of contiguous triangles before generating triangle strips improves memory utilization can speed the processing of computer graphic objects.

Method and apparatus for organizing object geometry for spatial and memory coherency and optimal rendering

The system includes a shape buffer manager configured to store coverage data in the shape buffer. The coverage data indicates whether each mask pixel is a covered pixel or an uncovered pixel. A mask pixel is a covered pixel when a shape to be rendered on a screen covers the mask pixel such that one or more coverage criteria is satisfied and is an uncovered pixel when the shape does not cover the mask pixel such that the one or more coverage criteria are satisfied. A bounds primitive rasterizer is configured to rasterize a bounds primitive that bounds the shape. The bounds primitive is rasterized into primitive pixels that each corresponds to one of the mask pixels. A pixel screener is configured to employ the coverage data from the shape buffer to screen the primitive pixels into retained pixels and discarded pixels. The retained pixels each corresponds to a mask pixel that the coverage data indicates is a covered pixel and the discarded pixels each correspond to a mask pixels that the coverage data indicates is an uncovered pixel. The system also includes an attribute generator configured to generate pixel attributes for the retained primitive pixels and also configured not to generate pixel attributes for the discarded primitive pixels.

Graphics system employing shape buffer

The system includes a bounds primitive rasterizer that rasterizes a bounds primitive into a selection of primitive pixels. The selection of primitive pixels bounds a shape to be rendered to a screen. The system also includes a pixel mask generator that generates a pixel mask for the shape. The pixel mask includes mask pixels that each corresponds to one of the primitive pixels. A mask pixel is a covered pixel when the shape covers at least a threshold portion of the mask pixel and is an uncovered pixel when the shape does not cover the mask pixel. The system also includes a pixel screener configured to retain primitive pixels that correspond to covered mask pixels and to discard primitive pixels that correspond to uncovered mask pixels.

Growing community of inventors

San Diego, CA, United States of America

Angus Dorbie