|
|
| Line 1: |
Line 1: |
| − | Hello. I am interested in ray-tracing, and GPGPU. I plan to work on OpenCL acceleration of the BRL-CAD librt rendering pipeline.
| |
| | | | |
| − | =Preliminary Schedule=
| |
| − | * 1 week - ellipsoid (ell), arb8 (arbitrary polyhedron) shot routines in OCL
| |
| − | * 1 week - to refactor dispatcher, shoot, optical renderer to process many rays in parallel in C when rendering an image or block
| |
| − | * 3 weeks - grid spatial partitioning in OCL
| |
| − | * 2 weeks - to code for GPU side database storage of OCL implemented primitives
| |
| − | * 3 weeks - to port the compute intensive or critical parts of the dispatcher, boolean evaluator, optical renderer to OCL
| |
| − | * 1 week - torus (tor), truncated general cone (tgc) shot routines in OCL
| |
| − | * 2 weeks - bot (bag o' triangles) shot routine in OCL
| |
| − |
| |
| − | Code should be implemented in C and OpenCL. The boolean weaving should be implemented in the 3 week segment where the boolean evaluator will be reimplemented in OCL. bot implementation is near the end because it might be possible to reuse some of the spatial partitioning code in it.
| |
