System for primary ray shooting having geometrical stencils
Aspects comprise ray shooting system based on the data structure of a uniform grid of cells, and on local stencils in cells. The high traversal and construction costs of accelerating structures are cut down. The object's visibility from the viewpoint and from light sources, as well as the primary workload and its distribution among cells, are gained in the preprocessing stage and cached in stencils for runtime use. In runtime, the use of stencils allows a complete locality at each cell, for load balanced parallel processing.
1. A ray tracing system having stencil based primary ray shooting, comprising:
one or more processors with memory,
a data structure of a scene, based on a grid of cells,
wherein stencils are generated in data filled cells prior to primary ray shooting, while during the primary ray shooting local ray segments are generated in cells for only those shooting rays that hit the cell stencils, and intersection tests are conducted between said local ray segments and between local objects, generating primary intersection points.
2. The system of claim 1 , wherein said grid of cells comprises uniform cells.
3. The system of claim 1 , wherein said grid of cells is generated in a preprocessing stage.
4. The system of claim 1 , wherein said stencils are generated in a preprocessing stage.
5. The system of claim 1 , wherein the object data of a scene are represented by a polygon model.
6. The system of claim 1 , wherein per each primary shooting ray, at most one of its local ray segments is tested.
7. The system of claim 1 , wherein the cells of a grid are processed in an arbitrary order for a primary ray shooting.
8. The system of claim 1 , wherein the stencils at cells are generated as a combined result of projections cast by external objects and projections cast by local objects.
9. The system of claim 1 , wherein the said processors are selected from the group of general purpose processors, special purpose processors, multicore processors and GPUs.
10. The system of claim 1 , wherein each of the shooting rays comprises multiple local ray segments, and each segment belongs to a different cell.
11. The system of claim 1 , wherein the said processors are incorporated in one or more computers selected from the group consisting of a PC-level computer, information server computer, cloud server computer, parallel computer, laptop, portable processing system, tablet, smartphone, and any computational-based machine.
12. The system of claim 1 , wherein the shooting workload in a cell can be pre-calculated based on the surface area of the stencil.
13. The system of claim 12 , wherein load balancing of the system is achievable, and such load balancing is assisted by pre-calculating the distribution of shooting workloads among cells.
14. The system of claim 1 , wherein the said memory is shared by multiple processors.
15. The method of claim 1 , wherein each processor has its private memory.
16. The system of claim 1 , wherein for each shooting ray, at most one of its segments is tested for intersections.
17. The system of claim 1 , wherein shooting rays that hit no objects are not tested for intersection.
18. The system of claim 1 , wherein empty cells are determined prior to the primary ray shooting.
19. The system of claim 1 , wherein the object data of a scene is represented by a geometric model.
20. The system of claim 1 , wherein the primary ray shooting has the characteristics of static process locality.