Using a geometry shader for variable input and output algorithms

• US 9,928,642 B2
• Filed: 01/03/2017
• Issued: 03/27/2018
• Est. Priority Date: 07/31/2007
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Diard, Franck
• Primary Examiner(s): Hoang, Phi
• Application Number:
  US15/397,528
• Publication Number:
  US 20170186224A1
• Time in Patent Office: 448 Days
• CPC Class Codes: G06T 1/20 Processor architectures; Processor configuration, e.g. pipelining
• CPC Class Codes: G06T 15/005 General purpose rendering architectures
• CPC Class Codes: G06T 15/80 Shading
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 17/005 Tree description, e.g. octree, quadtree
• CPC Class Codes: G06T 2200/28 involving image processing hardware
• CPC Class Codes: G06T 2210/21 Collision detection, intersection
• CPC Class Codes: G06T 7/13 Edge detection

Abstract

A system and method uses the capabilities of a geometry shader unit within the multi-threaded graphics processor to implement algorithms with variable input and output.

Claims

1. A method for using a geometry shader unit to process input data and produce a histogram, the method comprising:

receiving image data for an input image;

executing, on a processing core included in a parallel processor, a geometry shader program to sort the image data into multiple bins to generate the histogram, wherein each bin represents a different image data value; and

storing the histogram in an output buffer.

2. The method of claim 1, further comprising:

storing a first value in a first bin of the multiple bins;

summing a second value with the first value to produce a sum using a blend function; and

storing the sum in the first bin.

3. The method of claim 1, further comprising dividing the input image into multiple regions and generating the histogram by allocating a different execution thread to process histogram data for each one of the multiple regions in order to execute the geometry shader program in parallel.

4. The method of claim 1, further comprising computing a luminance value for each pixel of the input image to produce the image data.

5. The method of claim 1, further comprising reading out the histogram from the output buffer, by at least one of a central processing unit and a parallel processing unit (PPU) that includes the processing core, for further processing of the image data based on the histogram.

6. The method of claim 5, wherein the further processing of the image data comprises performing at least one of a contrast correction of the image data and a tone mapping of the image data.

7. The method of claim 1, wherein the image data has a first data length, and the histogram has a second data length that is different from the first data length.

8. A non-transitory computer-readable medium that, when executed by a parallel processor, causes the parallel processor to execute a geometry shader unit to process input data and produce a histogram by performing the steps of:

receiving image data for an input image;

executing, on a processing core included in the parallel processor, a geometry shader program to sort the image data into multiple bins to generate the histogram, wherein each bin represents a different image data value; and

storing the histogram in an output buffer.

9. The non-transitory computer-readable medium of claim 8, further comprising:

storing a first value in a first bin of the multiple bins;

summing a second value with the first value to produce a sum using a blend function; and

storing the sum in the first bin.

10. The non-transitory computer-readable medium of claim 8, further comprising dividing the input image into multiple regions and generating the histogram by allocating a different execution thread to process histogram data for each one of the multiple regions in order to execute the geometry shader program in parallel.

11. The non-transitory computer-readable medium of claim 8, further comprising reading out the histogram from the output buffer, by at least one of a central processing unit and a parallel processing unit (PPU) that includes the processing core, for further processing of the image data based on the histogram.

12. The non-transitory computer-readable medium of claim 11, wherein the further processing of the image data comprises performing at least one of a contrast correction of the image data and a tone mapping of the image data.

13. The non-transitory computer-readable medium of claim 8, wherein the image data has a first data length, and the histogram has a second data length that is different from the first data length.

14. A system for using a geometry shader unit to process input data and produce a histogram, the system comprising:

a parallel processor configured to;

receive image data for an input image;

execute, on a processing core included in the parallel processor, a geometry shader program to sort the image data into multiple bins to generate the histogram, wherein each bin represents a different image data value; and

store the histogram in an output buffer.

15. The system of claim 14, further comprising:

storing a first value in a first bin of the multiple bins;

summing a second value with the first value to produce a sum using a blend function; and

storing the sum in the first bin.

16. The system of claim 14, further comprising dividing the input image into multiple regions and generating the histogram by allocating a different execution thread to process histogram data for each one of the multiple regions in order to execute the geometry shader program in parallel.

17. The system of claim 14, further comprising reading out the histogram from the output buffer, by at least one of a central processing unit and a parallel processing unit (PPU) that includes the processing core, for further processing of the image data based on the histogram.

18. The system of claim 17, wherein the further processing of the image data comprises performing at least one of a contrast correction of the image data and a tone mapping of the image data.

19. The system of claim 14, wherein the image data has a first data length, and the histogram has a second data length that is different from the first data length.