Azralee

Hi, Sure I will do that next week, once I'm back from my holiday. I'll also try it on a few different driver versions to make sure it's not a...

I'd suggest a squash merge to get rid of the merge commit.

This is way more complicated than the original comment stated. I need to study this more.

Yeah, I tried to use AMD's static Analyzer (RGA) yesterday, but they have not released an update with the latest SPIR-V tools. AMD's Vulkan traversal code seems under-optimized at the...

I think I figured the performance difference out.  If you take a look at the heatmap, you can see that the heatmap is relatively coarse, specifically it's batches of...

It could probably be faster to trace a single sample per shader and dispatch a bunch of samples per pixel at the same time, no idea if it's possible though.

This hypothesis seems convincing. I ran the raytracer at 5120x2880 and at 1280x720:   The 64-pixel blocks are very visible in 720p and cover a lot ot the central...

The bad performance in the Cornell box scenes make a lot of sense, since there are only very few triangles (36 if I count correctly) making up the scene. Ampere...

I did some more testing and found a way to force wave32 execution on the RT shaders on RDNA2. This improved performance by ~6%. Moving line [101](https://github.com/GPSnoopy/RayTracingInVulkan/blob/e4be305e42230ecd7a08529e88c2a1c97853b086/assets/shaders/RayTracing.rgen#L101) directly behind the...

Well the newest driver automatically defaults to wave32, so that's good. Makes the first part of my pull request unnecessary.