Exploring different methods of optimizing a raytracing algorithm.
- simple parallelization
- parallelization with queue
- flattening the data structure representing the scene
- bounding volume hierarchy
- parallelization of the BVH construction
The application of all this methods achieved a combined speed-up of over 291x. Reducing the execution time from 99933ms to 343ms.
Al the performance analysis where performed on the SeARCH cluster @ UMinho while rendering a Cornell Box scene filled with water.
This project is licensed under the MIT License - see the LICENSE file for details