Search found 10 matches

by keldor314
Fri Apr 19, 2013 3:00 am
Forum: GPU
Topic: Is GPU computing dead already?
Replies: 19
Views: 14187

Re: Is GPU computing dead already?

For what it's worth, both AMD and Nvidia currently use LLVM in their OpenCL toolchains (Nvidia also uses it in the Cuda toolchain). Nvidia's backend is already in the main LLVM distribution (NVPTX target), and AMD's (R600 I believe, or maybe CAL) is supposed to be incorporated in LLVM 3.3. This mean...
by keldor314
Mon Apr 08, 2013 10:44 pm
Forum: General Development
Topic: Questions about fire rendering
Replies: 4
Views: 3068

Re: Questions about fire rendering

Basically, you just have to ray march through the fire volume for every light sample, much like you would for primary rays.
by keldor314
Mon Apr 08, 2013 10:39 pm
Forum: General Development
Topic: Can't pass virtual function objects to CUDA kernel is a pain
Replies: 7
Views: 5016

Re: Can't pass virtual function objects to CUDA kernel is a

It's probably worth noting that GPUs should be able to handle function pointers more efficiently than CPUs for micro-architectural reasons (if you're interested, I can explain), so be sure to give them a try. Are you referring to the GPU's latency hiding strategies with this comment? Or something e...
by keldor314
Sat Apr 06, 2013 5:37 am
Forum: General Development
Topic: Can't pass virtual function objects to CUDA kernel is a pain
Replies: 7
Views: 5016

Re: Can't pass virtual function objects to CUDA kernel is a

A CPU will do polymorphism either through function pointers or though a big switch clause, depending on what the compiler thinks is fastest. Hence, you have to eat that cost there too. It's probably worth noting that GPUs should be able to handle function pointers more efficiently than CPUs for micr...
by keldor314
Sat Apr 06, 2013 5:24 am
Forum: General Development
Topic: Random number generator on GPU
Replies: 1
Views: 2030

Re: Random number generator on GPU

Just write your own. This is the one I use: __constant__ unsigned int shift1[4] = {6, 2, 13, 3}; __constant__ unsigned int shift2[4] = {13, 27, 21, 12}; __constant__ unsigned int shift3[4] = {18, 2, 7, 13}; __constant__ unsigned int offset[4] = {4294967294, 4294967288, 4294967280, 4294967168}; __sha...
by keldor314
Sun Oct 14, 2012 8:35 pm
Forum: Links & Papers
Topic: Vertex merging paper and SmallVCM
Replies: 33
Views: 25058

Re: Vertex merging paper and SmallVCM

PPM (and VCM) can be made to be unbiased simply by having each photon store information about the previous hit, rather than the current hit. Then when the eye path lands close to a photon, you simply shoot a ray toward the photon's source (be it directly at a light or simply the last thing the photo...
by keldor314
Wed Jan 25, 2012 8:30 am
Forum: GPU
Topic: Dissapointing building times from lbvh gpu based builder
Replies: 35
Views: 22080

Re: Dissapointing building times from lbvh gpu based builder

Optix now has a GPU based HLBVH builder, as of version 2.5. Has anyone tried to benchmark it yet?
by keldor314
Wed Jan 25, 2012 8:28 am
Forum: General Development
Topic: consistency and unbiasedness
Replies: 6
Views: 4805

Re: consistency and unbiasedness

There's one very practical difference between unbiased and merely consistent renderers. To see it, imagine that you have a render farm, and you'd like to use a large number of separate computers to render an image. With an unbiased renderer, you can simply have them each render the image, but with f...
by keldor314
Wed Jan 25, 2012 8:13 am
Forum: GPU
Topic: Dissapointing building times from lbvh gpu based builder
Replies: 35
Views: 22080

Re: Dissapointing building times from lbvh gpu based builder

All that unbiased means in practice is that, thanks to the Central Limit Theorem, an infinite sum of finite runs will converge to zero error. (it also means that each run has an expected error of zero over infinitely many realizations, but this in practical terms has no value at all - all that matt...
by keldor314
Tue Jan 10, 2012 7:15 pm
Forum: Links & Papers
Topic: Random Parameter Filtering
Replies: 4
Views: 4495

Random Parameter Filtering

This is quite spectacular: http://agl.unm.edu/rpf/ Moreover, it's very likely that it can be brought near to real time on a high end GPU or two, since it looks like a very GPU friendly algorithm, I'd expect a speed increase of 100x or more, since it's heavy on local number crunching and uses some tr...

Go to advanced search