NVIDIA OptiX SDK is a scalable framework designed for building ray tracing based applications.
The application enables the assignment of CUDA functions and allows efficient sharing of data between OptiX and other CUDA applications.
The OptiX engine is composed of two parts:
· a host-based API
· a programming system based on CUDA C
Together, these components provide users with low-level support for "raw ray tracing".
Moreover, the OptiX engine enables software developers to accelerate as many ray tracing tasks as they want.
Requirements:
· System Memory: matches graphics board recommendations
· GPU: CUDA-capable, G80 or later.
· GPU memory: varies with data complexity
· NVIDIA Driver R300or later
· Development Environment: C/C++ Compiler, CUDA Toolkit 2.3 or newer, CMake (only for rebuilding SDK samples)
· CUDA toolkit 2.3 or later
What's New in This Release: [ read full changelog ]
Callable Programs:
· Enables the assignment of arbitrary CUDA functions to OptiX variables enabling shade trees, referenced procedurals, and a far more diverse set of shading and rendering algorithms.
OptiX-CUDA Interop:
· Allows efficient sharing of data between OptiX and other CUDA applications.
Bindless Textures:
· Textures now have indirect access by using CUDA RT_TEXTURE and storing this handle within OptiX variables and buffers.
Improved Performance:
· Better performance when using GL interop input buffers with multiple GPUs.
· Far Faster Times for SBVH - our highest Performance acceleration Structure Type
· The build times for SBVH are now far faster for assemblies, and general compile times are over 2X faster.
Better Multi-GPU Load Balancing:
· The algorithm for partitioning work across multiple GPUs has improved, increasing multi-GPU scalability.
More Efficient Compilation:
· The need to compile when the scene changes is far less frequent than in previous releases.
...
Find us on Google+
