I was searching a lot but couldn’t find an answer,
Is it possible to use optix as an api to analyze rays themselves instead of their interactions with meshes/planes ?
In particular i’m searching for api that would let me find shortest distance between two arbitrary chosen rays using gpu and rt-cores on it
The formula to find the shortest distance between two skew lines is basic linear algebra.
If you need that GPU accelerated because you have a huge number of these calculations, you could use a native CUDA kernel.
in my understanding rt cores would accelerate those calculations even further, does normal cuda api allows me to utilize them ?
That is not the case. The RT cores accelerate the BVH traversal through a hierarchy of axis aligned bounding boxes and the intersection between a ray and a triangle.
native cuda kernel seems like most reasonable choice for my application then, thank you for answers