[omolobo]

It's a mega-kernel, so you'll get poor occupancy past the first bounce. A better strategy is to shoot, sort, and repeat, which then also allows you to squeeze in an adaptive sampler in the middle.

> // No idea where negative values come from :(

I don't know, but:

> newRay.origin += sign(dot(newRay.direction, geometryNormal)) * geometryNormal * 1e-4;

The new origin should be along the reflected ray, not along the direction of the normal. This line basically adds the normal (with a sign) to the origin (intersection point), which seems odd.

Poor's man way to find where the negatives come from is to max(0,...) stuff until you find it.

[TomClabault]

> A better strategy is to shoot, sort, and repeat

Do we have good sorting strategy whose costs are amortized yet? Meister 2020 (https://meistdan.github.io/publications/raysorting/paper.pdf) shows that the hard part is actually to hide the cost of the sorting.

> squeeze in an adaptive sampler in the middle. Can you expand on that? How does that work? I only know of adaptive sampling in screen space where you shoot more or less rays to certain pixels based on their estimated variance so far.

[TomClabault]

After reading this paper a bit more it seems that the it focuses on simple scenes and simple materials only, which a bit unfortunate. This is exactly where ray reordering overhead is going to be the most problematic.

They also do talk about the potential of ray reordering for complex scenes and complex materials in the paper (because reordering helps with shading divergence since "all" reordered rays are pretty much going to hit the same material).

So maybe ray reordering isn't dead just yet. Probably would have to try that at some point...

[lisyarus]

> It's a mega-kernel, so you'll get poor occupancy past the first bounce

Sure! If you look into the to-do list, there's a "wavefront path tracer" entry :)

> new origin should be along the reflected ray

I've found that doing it the way I'm doing it works better for preventing self-intersections. Might be worth investigating, though.

[omolobo]

It probably works better when the reflected ray is almost tangent to the surface. But that should be an epsilon case.