Search found 206 matches

by Dade
Thu Feb 27, 2014 11:08 am
Forum: General Development
Topic: Implementing a Shader System
Replies: 13
Views: 10477

Re: Implementing a Shader System

If one of your rays do something dumb, then they can crash your entire driver, making debugging a nightmare Ha-ha, I face it many times =) I even fail to make Intel OpenCL debugging, breakpoints is set, but just do not works. You should try to run GDB on Linux with AMD drivers, they can totally fre...
by Dade
Thu Feb 13, 2014 4:41 pm
Forum: General Development
Topic: Hair intersection : approaches ?
Replies: 16
Views: 13395

Re: Hair intersection : approaches ?

Blender Cycles has native support for hair/strand primitives (but it works more or less only on the CPU, not with CUDA).
by Dade
Thu Feb 13, 2014 10:09 am
Forum: General Development
Topic: Hair intersection : approaches ?
Replies: 16
Views: 13395

Re: Hair intersection : approaches ?

Having another ray/primitive intersection, aside from ray/triangle, is particularly GPU-unfriendly. In LuxRender, we use a simple open standard file format to fast export/import (http://www.cemyuksel.com/research/hairmodels/) hair/strand information. It is also quite efficient in term of disk space....
by Dade
Tue Feb 11, 2014 9:55 am
Forum: General Development
Topic: Hybrid : CPU & GPU strategies
Replies: 14
Views: 11565

Re: Hybrid : CPU & GPU strategies

Sure, but it is not the goal... any speedup is still fine ;-) Yup but a LuxRender-like hybrid rendering (i.e. where only rays are traced on the GPU) provide a very small speedup. If we assume a 50% load for shading and 50% for ray tracing, in a best case scenario (i.e. infinite GPU speed), you get ...
by Dade
Tue Feb 11, 2014 9:39 am
Forum: General Development
Topic: Hybrid : CPU & GPU strategies
Replies: 14
Views: 11565

Re: Hybrid : CPU & GPU strategies

tarlack wrote:Haha, I don't know how to reply :mrgreen: but as the the author of this paper I can only be happy you cited it... :mrgreen:
Hehe, ok :D
by Dade
Mon Feb 10, 2014 9:22 am
Forum: General Development
Topic: Hybrid : CPU & GPU strategies
Replies: 14
Views: 11565

Re: Hybrid : CPU & GPU strategies

Just for the intersection test, it is likely that the memory throughput will be your main problem while you stick to one ray produced by CPU->one GPU task, even with double buffering and async transfers. Could you find a way to build on CPU something that will be able to "explode" on GPU, even just...
by Dade
Thu Jan 09, 2014 9:22 am
Forum: General Development
Topic: Population Monte Carlo Sampling
Replies: 14
Views: 11210

Re: Population Monte Carlo Sampling

Zelcious, correct me if I'm wrong, but the short version of your post, and the answer to the original thread question, is: Metropolis is superior to PMC (because it is able to sample all the 1000 "peaks"). P.S. I have never tried PMC so I can not argue but I'm not surprised because Metropolis has al...
by Dade
Mon Jan 06, 2014 2:41 pm
Forum: General Development
Topic: Population Monte Carlo Sampling
Replies: 14
Views: 11210

Re: Population Monte Carlo Sampling

I may be wrong but Octane should currently use PMC.
by Dade
Fri Nov 22, 2013 11:07 pm
Forum: General Development
Topic: 64 core cpu from intel
Replies: 13
Views: 17220

Re: 64 core cpu from intel

Microprocessor experts outside Intel are currently puzzled how the future chip can hit the announced 3 TFLOPS double precision. Are we interested in double precision performance ? I mean, is it ever going to be a transition from FP32 to FP64 in the rendering field ? I have the feeling it is not goi...
by Dade
Fri Nov 22, 2013 10:55 pm
Forum: Links & Papers
Topic: Stackless MBVH Traversal for CPU, MIC and GPU Ray Tracing
Replies: 15
Views: 20889

Re: Stackless MBVH Traversal for CPU, MIC and GPU Ray Tracin

It is a shame AMD has dropped VLIW architecture, QBVH (aka MBVH) was very effective on that kind of GPUs too. Now, I guess, this kind of research is mostly useful for CPUs and Xeon Phi.