Search found 206 matches

by Dade
Fri Nov 22, 2013 11:06 am
Forum: General Development
Topic: 64 core cpu from intel
Replies: 13
Views: 17110

Re: 64 core cpu from intel

Of course, there is still the classical challenge of coming up with multithreaded algorithms that scale so high, while producing actual results rather than just excess heat. :-) Xeon Phi cores are _lot_ slower than today average Xeon cores, I assume that the performance will be awful if you don't u...
by Dade
Thu Nov 21, 2013 10:04 am
Forum: General Development
Topic: 64 core cpu from intel
Replies: 13
Views: 17110

Re: 64 core cpu from intel

rumors say it will be produced with 72 core instead of 64, they also need incrase IPC and maybe add some superscalar capabilities to keep the one-thread performance a bit higher than the current design. they will have both DDR4 and motherboard-soldered GDDR5 version from the new architecture, to fe...
by Dade
Sat Nov 16, 2013 4:11 pm
Forum: General Development
Topic: About volumetric caustics.
Replies: 23
Views: 18819

Re: About volumetric caustics.

Does make sense to compare VCM and a Metropolis Sampler ? I mean, aren't they orthogonal and solve different kind of problems ? I use BPT+VCM with a Metropolis Sampler; there is nothing preventing to use both. Anyway a Path racer with a Metropolis Sampler have no hope to render any no trivial SDS pa...
by Dade
Thu Nov 14, 2013 10:20 pm
Forum: General Development
Topic: About volumetric caustics.
Replies: 23
Views: 18819

Re: About volumetric caustics.

But that doesn't include all the additional mumbo-jumbo that the rest of the renderer has to support to make it "simple" like this.. The above code just generated (on demand, it implements Kelemen-style lazy evaluation) float values as the most simple Random Sampler, there isn't any particular supp...
by Dade
Thu Nov 14, 2013 3:54 pm
Forum: General Development
Topic: C++ AMP
Replies: 4
Views: 7044

Re: C++ AMP

Just out of interest, did anybody ever try to code some more or less simple ray tracing kernel with C++ AMP? BTW, I have read AMD has a recently shown C++ AMP for Linux (i.e. running over OpenCL so it is likely to be available for Apple too). However, I must admit, Microsoft hasn't really the best ...
by Dade
Thu Nov 14, 2013 3:52 pm
Forum: General Development
Topic: About volumetric caustics.
Replies: 23
Views: 18819

Re: About volumetric caustics.

I have never written a MLT before and I heard it's hard. I guess I will go with the easiest and quickest way for now... still deciding. It is quite a false myth, a Metropolis sampler require something like 150 lines of code: http://src.luxrender.net/luxrays/file/eeb8c20ef760/src/slg/sampler/sampler...
by Dade
Tue Nov 12, 2013 9:02 pm
Forum: Visuals, Tools, Demos & Sources
Topic: Arauna2 announcement video
Replies: 14
Views: 65566

Re: Arauna2 announcement video

jbikker wrote:The shading path is still 'ubershader' style, with full Phong support (including glossy), pure specualars and dielectrics.
Interesting, I guess the "ubershader" way makes a lot of sense for GPU real-time path tracing.
by Dade
Sat Sep 28, 2013 12:48 pm
Forum: Visuals, Tools, Demos & Sources
Topic: Render
Replies: 5
Views: 10582

Re: Render

jbikker wrote:Allow me to show off some recent work.
Great lighting, I love it, I assume it is off-line rendering and not real-time stuff :?:

P.S. If I have to try to criticize something, may be there is some little aliasing problem on some strong highlight ?
by Dade
Mon Sep 16, 2013 6:22 am
Forum: Visuals, Tools, Demos & Sources
Topic: giga rays on intel phi
Replies: 24
Views: 26896

Re: giga rays on intel phi

graphicsMan wrote:I think a key thing about Phi is that it has more memory than GPUs have, and going forward memory will likely be a main factor for which platform to choose.
There is a Quadro card with 12GB of ram, what is the larger memory configuration available for Xeon Phi ?
by Dade
Sat Sep 14, 2013 2:19 pm
Forum: Visuals, Tools, Demos & Sources
Topic: giga rays on intel phi
Replies: 24
Views: 26896

Re: giga rays on intel phi

yes titan (serveral) are in place. as i said above, both are more or less equal in performing diffuse bounces (around 165mray/s). for primary rays mic is 2x ahead. Strange, I would have expected exactly the opposite result :?: I mean, MIC should be less sensible to thread divergence. May be cache, ...