System and method for structuring an A-buffer to support multi-sample anti-aliasing

• US 8,130,223 B1
• Filed: 09/10/2008
• Issued: 03/06/2012
• Est. Priority Date: 09/10/2008
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Danskin, John M.
• Primary Examiner(s): Wu, Xiao M.
• Assistant Examiner(s): He, Yingchun
• Application Number:
  US12/208,204
• Time in Patent Office: 1,273 Days
• Field of Search: 345/422, 345/421, 345/428, 345611-616, 345/619, 345/543, 345/555
• US Class Current: 345/422
• CPC Class Codes: G06T 1/60 Memory management
• CPC Class Codes: G06T 11/40 Filling a planar surface by adding surface attributes, e.g. colour or texture
• CPC Class Codes: G06T 15/503 Blending, e.g. for anti-aliasing

Abstract

One embodiment of the present invention sets forth a technique for efficiently creating and accessing an A-Buffer that supports multi-sample compression techniques. The A-Buffer is organized in stacks of uniformly-sized tiles, wherein the tile size is selected to facilitate compression techniques. Each stack represents the samples included in a group of pixels. Each tile within a stack represents the set of sample data at a specific per-sample rendering order index that are associated with the group of pixels represented by the stack. Advantageously, each tile includes tile compression bits that enable the tile to maintain data using existing compression formats. As the A-Buffer is created, a corresponding stack compression buffer is also created. For each stack, the stack compression buffer includes a bit that indicates whether all of the tiles in the stack are similarly compressed and, consequently, whether the GPU may operate on the stack at an efficient per pixel granularity.

Claims

1. A method for generating an A-Buffer for storing sample information, the method comprising:

receiving an image frame comprised of a plurality of pixels, wherein each pixel is comprised of a plurality of samples;

dividing the image frame into one or more pixel groups, wherein a number of pixels in each of the one or more pixel groups is based on a tile size and a number of samples in each pixel;

generating a sample depth complexity image based on the image frame, wherein each entry in the sample depth complexity image reflects a maximum rendering order index associated with a different one of the samples in the image frame;

determining a stack height for each pixel group based on the sample depth complexity image, wherein the stack height reflects a maximum of the maximum rendering order indexes associated with the samples in the pixel group;

determining a number of tiles associated with the A-Buffer based on the stack heights for the one or more pixel groups; and

allocating memory space for the A-Buffer based on the number of tiles associated with the A-Buffer,

wherein a maximum rendering order index corresponds to the number of potentially visible surfaces associated with a different one of the samples in the image frame.

2. The method of claim 1, where the step of allocating memory space comprises determining whether the number of tiles associated with the A-Buffer is supported by a pre-allocated memory space.

3. The method of claim 1, wherein the A-Buffer includes one or more stacks, each stack corresponding to a different one of the one or more pixel groups and having a size equal to the number of tiles associated with the corresponding pixel group.

4. The method of claim 3, wherein the step of determining the number of tiles associated with the A-Buffer comprises designating a number of tiles for each pixel group equal to the stack height associated with the pixel group.

5. The method of claim 4, wherein the maximum rendering order index associated with a sample reflects a number of graphics objects associated with the image frame that intersect the sample.

6. The method of claim 4, further comprising the step of populating the A-Buffer with sample data.

7. The method of claim 6, wherein the step of populating the A-Buffer with sample data comprises:

receiving a pixel write for a target pixel;

expanding the pixel write into one or more sample writes, wherein each sample write reflects a graphics object covering a particular sample included in the target pixel; and

storing data included in each sample write in the A-Buffer.

8. The method of claim 6, wherein the step of populating the A-Buffer with sample data comprises:

receiving a compressed write that includes compressed data,

determining a target tile included in the A-Buffer associated with the compressed write;

setting tile compression bits included in the target tile to reflect a compression format; and

storing the compressed data in the target tile using the compression format.

9. The method of claim 1, wherein the step of generating the sample depth complexity image comprises:

receiving a first pixel write for a target pixel in the image frame;

incrementing a corresponding rendering order index for each covered sample within the target pixel based on the first pixel write.

10. The method of claim 9, wherein the step of generating the sample depth complexity image further comprises:

receiving a second pixel write for the target pixel, if more pixel writes exist; and

incrementing the corresponding rendering order index for each covered sample within the target pixel based on the second pixel write.

11. A computer system, comprising:

a memory;

a graphics processing unit coupled to the memory and configured to generate an A-Buffer in the memory for storing sample information by;

dividing an image frame into one or more pixel groups, wherein the image frame is comprised of a plurality of pixels, each pixel is comprised of a plurality of samples, and a number of pixels in each of the one or more pixel groups is based on a tile size and a number of samples in each pixel,

generating a sample depth complexity image based on the image frame, wherein each entry in the sample depth complexity image reflects a maximum rendering order index associated with a different one of the samples in the image frame,

determining a stack height for each pixel group, based on the sample depth complexity image, wherein the stack height reflects a maximum of the maximum rendering order indexes associated with the samples in the pixel group, a number of tiles associated with the A-Buffer is based on the stack heights for the one or more pixel groups, and memory space for the A-Buffer is allocated based on the number of tiles associated with the A-Buffer, and

populating the A-Buffer with sample data,

wherein a maximum rendering order index corresponds to the number of potentially visible surfaces associated with a different one of the samples in the image frame.

12. The computer system of claim 11, further comprising a central processing unit configured to allocate the memory space for the A-Buffer based on the number of tiles associated with the A-Buffer.

13. The computer system of claim 12, wherein the central processing unit is further configured to determine whether the number of tiles associated with the A-Buffer is supported by a pre-allocated memory space.

14. The computer system of claim 12, wherein either the graphics processing unit or the central processing unit is configured to determine the number of tiles associated with the A-Buffer.

15. The computer system of claim 11, wherein the A-Buffer includes one or more stacks, each stack corresponding to a different one of the one or more pixel groups and having a size equal to the number of tiles associated with the corresponding pixel group.

16. The computer system of claim 15, wherein the maximum rendering order index associated with a sample reflects a number of graphics objects associated with the image frame that intersect the sample.

17. The computer system of claim 11, wherein the graphics processing unit is configured to populate the A-Buffer with sample data by:

receiving a pixel write for a target pixel;

expanding the pixel write into one or more sample writes, wherein each sample write reflects a graphics object covering a particular sample included in the target pixel; and

storing data included in each sample write in the A-Buffer.

18. The computer system of claim 11, wherein the graphics processing unit is configured to populate the A-Buffer with sample data by:

receiving a compressed write that includes compressed data,

determining a target tile included in the A-Buffer associated with the compressed write;

setting tile compression bits included in the target tile to reflect a compression format; and

storing compressed data in the target tile using the compression format.

19. The computer system of claim 11, wherein the graphics processing unit includes a raster operations unit configured to generate the sample depth complexity image.

20. The computer system of claim 19, wherein the graphics processing unit includes a fragment shader configured to determine the stack height for each pixel group.

21. The computer system of claim 20, wherein either the raster operations unit or the fragment shader is configured to populate the A-Buffer with sample data.