ompf2.com

We're hiring someone to help us work on a production path tracer.

https://apply.workable.com/tangent-animation/j/B40BB5C7FF/

Ompf got a mention during "Are we done with ray tracing?".

Since this online place is a bit silent lately, anyone up for an offline meeting at SIGGRAPH 2019?

I would think the RTX cores are exposed the same way as the rasterisation hardware - through graphics APIs, but not general compute APIs. Note how there's no access to ROPs from CUDA or OpenCL, I guess the same goes for RT.

Can't say anything about this group in particular. But I'm expecting RTRT on mobile at some point, as Apple's current public betas have an API to do ray tracing on mobile via Metal.

Here's another similar incarnation: http://cgg.mff.cuni.cz/~jaroslav/papers ... stract.pdf
I'd have to search, but I saw the iRay team also describing a light BVH with probabilistic traversal that seemed to also go off the same idea.

Obviously, some parts of the scene benefit more from lights than the skydome. So, I want to change the probability of sampling the light or the sky depending on potential contribution. So I evaluate a random point on the skydome (importance sampled) and a random point on a random light. Based on th...

Presentation video and slides are here:
http://on-demand-gtc.gputechconf.com/gt ... t=&select=

Lesson learnt: When you want all threads in a warp to participate in a memory fetch (see Tony Scudiero's GTC presentation "Memory boot camp III"), first make sure all threads are active.

How to not optimise CUDA BVH traversal.