Search found 160 matches

by graphicsMan
Thu Jun 11, 2015 5:30 pm
Forum: General Development
Topic: Float versus double
Replies: 12
Views: 12990

Re: Float versus double

You can work around most precision issues with float, but in some edge cases, you have to be fancy. Using double would probably reduce (or eliminate) your need for those workarounds, but keep in mind that when a problem exists for float, the same problem exists for double, just at a different scale.
by graphicsMan
Fri Jun 05, 2015 8:11 pm
Forum: Links & Papers
Topic: Looking for robust ray offsets
Replies: 2
Views: 6032

Re: Looking for robust ray offsets

BTW, I was talking about Carsten Wächter's thesis: http://vts.uni-ulm.de/docs/2008/6265/vts_6265_8393.pdf
by graphicsMan
Fri Jun 05, 2015 7:07 pm
Forum: Links & Papers
Topic: Looking for robust ray offsets
Replies: 2
Views: 6032

Looking for robust ray offsets

Hi all -

It's been a while, but there was a paper or dissertation that discussed how to calculate robust ray offsets by pushing the low-order bits of the floats for the vector offset. I can't recall which paper or dissertation; can anyone please post a link?
by graphicsMan
Mon Feb 02, 2015 4:23 pm
Forum: Scratchpad
Topic: A joke.
Replies: 3
Views: 6037

Re: A joke.

wah wah wah wah... Yes, I smiled in spite of myself.
by graphicsMan
Fri Jun 27, 2014 3:43 pm
Forum: General Development
Topic: Sampling Distorted Spheres
Replies: 4
Views: 3371

Re: Sampling Distorted Spheres

See if this paper will help you:

http://www.cs.utah.edu/~shirley/papers/tog94.pdf
by graphicsMan
Wed Jun 18, 2014 6:26 pm
Forum: General Development
Topic: Energy-Conserving Phong Specular Lobe
Replies: 10
Views: 7244

Re: Energy-Conserving Phong Specular Lobe

Just making sure... you've looked at Lafortune's paper on the topic? I believe it addresses sampling.
by graphicsMan
Wed Feb 05, 2014 8:32 pm
Forum: GPU
Topic: OpenCL - ray-triangle intersection
Replies: 5
Views: 6842

Re: OpenCL - ray-triangle intersection

I found "Ray-Triangle Intersection Algorithm for Modern CPU Architectures" to provide a really fast, and fairly robust ray triangle intersection. I found that MT is more robust and requires less storage, but Shevtsov's intersection test was faster for me (especially on GPU). Warning: I did...
by graphicsMan
Wed Jan 29, 2014 12:32 am
Forum: General Development
Topic: Fastest AABB-ray test today?
Replies: 7
Views: 4833

Re: Fastest AABB-ray test today?

Hi Toshiya - I found that the for loop version referenced here http://tog.acm.org/resources/RTNews/html/rtnv19n1.html#art7 (the one that Eric discussed with Solomon) was quite fast. I think I made some small tweaks to that version, but it was substantially the same. It turned out to be the fastest m...
by graphicsMan
Thu Nov 21, 2013 12:40 am
Forum: Considered Harmfull
Topic: 64 core cpu from intel
Replies: 13
Views: 14924

Re: 64 core cpu from intel

It's certainly superior in that it runs x86_64 code natively out of the box with no hoops to jump through. This will not get you great performance. You need to use the 16-wide SIMD lanes to really get the most out of this chip. This is not free, nor even easy as a programming exercise. It remains to...

Go to advanced search