Mateusz Kielan

> Note that in Vulkan's Perspective you cannot bind BLAS directly as a descriptor, you should always create a TLAS. Potatoe, potato I presume there's an option to create a...

hmm but I've seen and heard of people tracing just the BLAS for maximum gains in static scenes in DXR/OptiX. So what do we do then, TLAS with a single...

> that lots of optimisations already done and tested That's a rather bold assumption ;)

> you no need to be rude. That's not me being rude ;) > I genuinely curious how current solution in Nabla better in terms of testing and optimisation compared...

@3d4m-vladimir we'll be moving to HLSL2021 in the near future. Do you have any suggestions for a GLM-like library but which has an identical syntax/type names to HLSL ?

# Spotlight Culling Basically you need Cone and Sphere vs. AABB culling first. The cases split into 2 In both cases you first want to test the sphere. Cone culling...

https://www.intel.com/content/www/us/en/developer/articles/technical/forward-clustered-shading.html

https://www.jonmanatee.com/blog/2015/1/20/improved-spotlight-culling-for-clustered-forward-shading.html

# Old idea for constructing the Light AS Start by dispatching a NumLights invocations, then test each light against 2x2 frustums (each with its own custom far value), add the...

# Newer idea for Light AS We frustum cull and then sort the lights by importance, scratch memory needed to do this is O(numLights) we then take the first min(K*TileCount,LightCount)...