Search found 6 matches

by tstanev
Sun Jul 28, 2013 11:38 pm
Forum: General Development
Topic: Is it still worth it to do CPU SIMD ray tracing?
Replies: 12
Views: 11615

Re: Is it still worth it to do CPU SIMD ray tracing?

i dont think its worth doing by-hand assembly optimisations for special instructions. for me, the formula is more simple: what the compiler compiles on maximal optimisation on the system, is the maximum speed what the architecture can reach. a general purpose cpu should be able to execute the gener...
by tstanev
Sun Jul 28, 2013 3:01 am
Forum: General Development
Topic: Is it still worth it to do CPU SIMD ray tracing?
Replies: 12
Views: 11615

Re: Is it still worth it to do CPU SIMD ray tracing?

Recently I have been reading about doing ray tracing with SSE intrinsics. And I felt that it's really troublesome to pack data into ray packets and use SSE. Now that we have GPU, is it still worth doing it?? Timo Alia has their fastest ray tracer written in CUDA, right? Do they also pack their ray ...
by tstanev
Sun Feb 26, 2012 3:43 pm
Forum: General Development
Topic: Speeding up OpenCL BVH
Replies: 6
Views: 7602

Re: Speeding up OpenCL BVH

I guess for a completely balanced tree, step 2 is sufficient. But, if you make more optimal one (SAH) then after step 2 you will have incomplete node filling at the leaf level, so you will need some post-processing. For example, check out section 4 of this Wald paper: http://www.sci.utah.edu/~wald/P...
by tstanev
Sat Jan 07, 2012 4:11 am
Forum: General Development
Topic: Preetham Sun, spectral rendering
Replies: 15
Views: 11737

Re: Preetham Sun, spectral rendering

Where does this factor of 10 come from? Is this because of the 10nm wavelength data interval that we need to take in to account when integrating? Also, when the sun is at zenith, I get an undesirable pink shade around the horizon. I have seen this in some implementations, and not in others. (Mine d...
by tstanev
Sat Dec 31, 2011 2:51 am
Forum: General Development
Topic: Preetham Sun, spectral rendering
Replies: 15
Views: 11737

Re: Preetham Sun, spectral rendering

I think it's a factor of 10 overall as someone stated previously, and it is to convert the cm^2 to m^2 and the um to nm: /* from W/cm^2/um/sr to W/m^2/nm/sr */ double unit_factor = 1.0e4 * 1.0e-3; /* 1/cm^2 to 1/m^2 and 1/um to 1/nm */ Confusingly, the attenuation factors still need um wavelength in...
by tstanev
Tue Dec 27, 2011 12:21 am
Forum: General Development
Topic: How to deal with mesh emitters?
Replies: 3
Views: 4098

Re: How to deal with mesh emitters?

If the visual angle covered by the light sources is on average very small (regardless of number of triangles), you are probably better off sampling them explicitly (using importance sampling), in order to avoid noise. Another option may be to approximate each mesh emitter by a series of point lights...