Re: segmentation fault inside clBuildProgram (bug demonstration attached)
Are you sure you're using the kernel code in my second message? The code attached to my first message was supposed to work.
View ArticleRe: Blender Cycles(Opencl on AMD GPUS)
In my case too, as I have the money for the asus gtx 970. Amd stayed with the party games and more intel that ta is not engaged in gross gpus are improving much more than amd. So amd "the great...
View ArticleClik here to view.
Re: Blender Cycles(Opencl on AMD GPUS)
cusa123 wrote: You do not try to think that amd fix the problem.You yourself mentioned, 3 years is already more than enough.To make clear to all OpenCL 2.0 (will not be the solution).Amd cpu now also...
View ArticleList of platforms supported by OpenCL 2.0 driver
We have updated the list of AMD products supported by the early release of the OpenCL 2.0 driver. You can find that list here: The original page listed supported product families, but in some cases...
View ArticleRe: List of platforms supported by OpenCL 2.0 driver
Thank you for this list. I have a few questionsWill AMD be supporting Fine Grain Shared Virtual Memory on existing or future graphics cards (perhaps only on AMD based motherboards) Will Multi GPU...
View ArticleClik here to view.
Re: Blender Cycles(Opencl on AMD GPUS)
@mrdriftmeyer I agree - tired of hearing all the moaning and groaning. Not all of the blame can be pinned on AMD..If it is such a big problem for some people, just fork over $400 for a 970, and use the...
View ArticleRe: About INTR intercept in the XEN HVM with SVM
GIF is implicitly cleared (interrupts are unmasked) by vmrun and implicitly set with #VMEXIT.AMD64 Architecture Programmer's Manual Volume 2: System Programming, 15.5.1, Loading Guest State, p....
View ArticleRe: SVM virtualization problem ( intercepting CPUID )
Just keep silence if you can't help rather than spamming with such messages.
View ArticleRe: Blender Cycles(Opencl on AMD GPUS)
Sorry I do not understand your answer. You say the problem is with Blender and developers ?. What I do not understand is because amd does not generate a rendering engine base. LuxRender is terribly...
View ArticleRe: segmentation fault inside clBuildProgram (bug demonstration attached)
Yes the kernel code in your second post runs fine with me. No segmentation fault.
View ArticleRe: Opengl interop / clCreateContextFromType segfault
I found the problem ... or at least a workaround: Obviously the wrong libGL was used for the case that OpenGL interoperability is made use of. I changed the following symlink:...
View ArticleMaths in double precision gives me different results on AMD and NVIDIA
Hi everyone, I made a porting a Cellular Automaton from CPU to GPU, I'm using OpenCL and I have the following hardware:CPU Xeon 8 coreGPU NVIDIA k20cGPU AMD R9 280x The porting is completed but there...
View ArticleRe: How to use GpuPerfStudio 3 to get gpu info from Chrome running a WebGL...
Hi, It all depends on how Chrome implements its double buffering in WebGL. The PerfStudio OpenGL server intercepts the wglSwapBuffers (or glXSwapBuffers on Linux) and this is where it does its...
View ArticleClik here to view.
Re: PerfStudio 3.0 with 3DMark11/3DMark ?
Hi, One thing you could try is to make a shortcut to the application and its command line arguments. Verify that this works by launching the shortcut. You should then be able to drag the shortcut onto...
View ArticleRe: Maths in double precision gives me different results on AMD and NVIDIA
Don't you think that there would be race conditions when multiple work[items/groups] write to same memory location simultaneously? Try to use atomic add for the div_kernel and see if it gives same...
View ArticleRe: Metro: Last Light freezes system maybe because of fog effect
I also have this problem, just tried playing Metro LL for the first time and it hangs at that press any key screen.Please fix and let me know if I can help debug in anyway. Arch Linux...
View ArticleRe: Problem with parallel calls of dgemm
Hi, I am currently facing the same problem with the latest 6.0.6 version.I was using Visual Studio 2013, and I downloaded acml-6.0.6.17-ifort64.zip. I used single threaded version of the library. I ran...
View ArticleRe: Maths in double precision gives me different results on AMD and NVIDIA
Sorry i didn't understand your problem correctly. But the built in pow function often gave me very different result and thats why i avoid it by either explicitly coding it (e.g double myPow(arg,arg))...
View ArticleRe: Maths in double precision gives me different results on AMD and NVIDIA
Hi bilal,this code is just an example to highlights the problem I know that using NDRange with size 1 is not a good choice, but I put 1 just to have only one workitem Your results are correct because...
View ArticleRe: Maths in double precision gives me different results on AMD and NVIDIA
The solution (suggested by an user of GPGPU group on linkedIn) was to made my own pow() function like this: double my_pow(double x, double a) { return exp(x * log(a)); } It works very well and the...
View Article