Methods and graphics processing units for determining differential data for rays of a ray bundle
Graphics processing system configured to perform ray tracing. Rays are bundled together and processed together. When differential data is needed by a shader, the data of a true ray in the bundle can be used rather than processing separate tracker rays.
1. A computer-implemented method of processing rays in a ray bundle in a graphics processing system, the method comprising:
executing a plurality of instances of a shader program, an instance corresponding to a ray of the ray bundle;
wherein the shader program is operable to utilize data determined by the execution of an instance of the shader program corresponding to a first ray of the ray bundle in the execution of an instance of the shader program for a further ray of the ray bundle.
2. The method of claim 1 , further comprising:
emitting a secondary ray from each of two or more instances of the shader program; and
grouping the secondary rays into another ray bundle.
3. The method of claim 2 , wherein said two or more instances of the shader program correspond to rays of the ray bundle.
4. The method of claim 1 , further comprising performing intersection testing on the rays of the ray bundle.
5. The method of claim 4 , wherein said executing a plurality of instances of a shader program is performed in response to results of said performing intersection testing on the rays of the ray bundle.
6. The method of claim 4 , further comprising using results of the intersection testing for the rays of the ray bundle to determine whether the rays are to be maintained in the ray bundle, wherein rays are maintained in the ray bundle if they have matching intersection testing results, wherein rays are considered to have matching intersection testing results if:
the rays intersect with the same primitive;
the rays intersect with the same mesh;
the rays intersect with the same object;
the intersections invoke the same one or more shader programs to be executed;
the difference between surface normals at the intersection points is below an angular threshold; or
the difference between the ray depths in the intersection points is below a depth threshold.
7. The method of claim 1 , further comprising receiving an indication via an API to indicate that a plurality of rays are intended to be coherent, wherein the method further comprises grouping said plurality of rays together into the ray bundle on the basis of the received indication.
8. The method of claim 1 , further comprising constructing a data structure representing the rays in the ray bundle, wherein full precision ray data is stored in the data structure, and wherein difference data is stored in the data structure for one or more of the rays of the ray bundle representing differences in the ray data compared to the full precision ray data stored in the data structure.
9. The method of claim 8 , wherein said full precision ray data is stored in the data structure for one of the rays of the ray bundle, and wherein said difference data is stored in the data structure for the other rays of the ray bundle.
10. The method of claim 1 , wherein the execution of an instance of the shader program for said further ray of the ray bundle comprises determining differential data for said further ray of the ray bundle using data for said first ray of the ray bundle.
11. The method of claim 10 , wherein the differential data is indicative of a gradient for the further ray.
12. The method of claim 1 , wherein the instances of the shader program are executed in parallel for different rays of the ray bundle.
13. The method of claim 1 , further comprising splitting a ray from the ray bundle if the ray does not have matching intersection testing results with other rays in the ray bundle.
14. The method of claim 1 , further comprising, if a ray of the ray bundle does not have matching intersection testing results with other rays in the ray bundle, marking the ray as a tracker ray in the ray bundle, wherein tracker rays are used to determine differential data for other rays in the bundle.
15. The method of claim 1 , wherein the rays to be grouped together are emitted due to the execution of a shader program, wherein a decision as to which rays to group together into a ray bundle is defined in the shader program causing the rays to be emitted.
16. The method of claim 1 , wherein a ray bundle comprises:
four rays corresponding to a 2×2 block of fragments; or
sixteen rays corresponding to a 4×4 block of fragments, wherein only a 3×3 block of the rays are valid rays and the remaining rays are tracker rays.
17. A graphics processing unit configured to process rays in a ray bundle, the graphics processing unit comprising processing logic configured to execute a plurality of instances of a shader program, an instance corresponding to a ray of the ray bundle, wherein the shader program is operable to utilize data determined by the execution of an instance of the shader program corresponding to a first ray of the ray bundle in the execution of an instance of the shader program for a further ray of the ray bundle.
18. The graphics processing unit of claim 17 , further comprising ray memory for storing ray data for the rays of the ray bundle, wherein the ray memory is configured to store data for the rays of a ray bundle in a data structure, wherein the data structure for the ray bundle comprises:
full precision ray data for one of the rays of the ray bundle; and
difference data for the other rays of the ray bundle representing differences in the ray data compared to the full precision ray data stored in the data structure.
19. The graphics processing unit of claim 17 ,
wherein the full precision ray data comprises: (i) a floating point 3-component vector to represent a ray origin, and (ii) a floating point 3-component vector to represent a ray direction; and
wherein the difference data comprises, for each of said one or more of the rays of the ray bundle: (i) three limited precision delta vectors for a ray origin, and (ii) three limited precision delta vectors for a ray direction.
20. A non-transitory computer readable storage medium having stored thereon computer readable instructions that, when executed at a computer system, cause the computer system to perform a method of processing rays in a ray bundle in a graphics processing system, the method comprising:
executing a plurality of instances of a shader program, an instance corresponding to a ray of the ray bundle;
wherein the shader program is operable to utilize data determined by the execution of an instance of the shader program corresponding to a first ray of the ray bundle in the execution of an instance of the shader program for a further ray of the ray bundle.