US 7,889,205 B1Granted

Frame buffer based transparency group computation on a GPU without context switching

AssigneeAdobe Systems Incorporated

InventorsAlexandre S. Parenteau, Cynthia W. Lau

Life of this patent

Estimating the term…

Loading patent…

Abstract

Transparency groups or other images may be rendered on graphics hardware using a GPU utilizing only a single frame buffer and without the need to switch contexts to another frame buffer. A single frame buffer may be allocated and the overall background image may be rendered to the frame buffer. In order to render a foreground image to be combined with the background image, a sub-image of the background image is copied from the frame buffer to a texture atlas. The foreground image may then be rendered to the portion of the frame buffer from which sub-image was copied. The foreground image may then be copied from the frame buffer into the texture atlas. Additionally, both the sub-image of the background image and the foreground image may be merged and copied from the texture atlas into the frame buffer.

Claims21

Dependent claims

A system, comprising:

one or more graphic processors;
and
memory coupled to the one or more graphic processors, comprising:
a frame buffer;
and
texture buffer configured as a texture atlas;
wherein the memory is configured to store program instructions executable by the one or more graphic processors to:
render a first graphic image to the frame buffer;
copy a portion of the first graphic image from the frame buffer to the texture atlas;
render a second graphic image to the frame buffer;
copy the second graphic image to the texture atlas, wherein the portion of the first graphic image and the second graphic image are independently addressable in the texture atlas;
and
merge the portion of the first graphic image and second graphic image from the texture atlas onto the frame buffer;
wherein said rendering the first graphic image, said copying the portion of the first graphic image, said rendering the second graphic image, said copying the first graphic image and said merging are performed using the same frame buffer and without performing a context switch between the frame buffer and any other frame buffer.

11 more elements

Dependencies are inferred from the claim text.