CUGAR, the CUDA Graphics AcceleratoR, is a library of reusable components designed to accelerate CUDA based graphics applications. Though it is specifically designed to unleash the power of NVIDIA GPUs, most of its components are completely cross-platform and can be used both from host C++ and device CUDA code.
Introduction
Modules
- CUGAR includes the following modules:
- Basic Module
- Bits Module
- Linear Algebra Module
- Binary Trees Module
- Radix Trees Module
- BVH Module
- K-d Trees Module
- BSDF Module
- Sampling Module
- Spherical Functions Module
- tree_page
Dependencies
- CUGAR depends on the following external libraries:
- CUB
- a modification of Nathaniel McClatchey's priority_deque
Licensing
- CUGAR has been developed by NVIDIA Corporation and is licensed under BSD.
Contributors
- CUGAR is made and mantained by Jacopo Pantaleoni.
