Re: 14.9 and higher OpenCL performance
Thanks for sharing the link. However, only kernel code is available there. A corresponding host code that calls the kernel is required to run and analyze it. I'm not familiar with the code. Can you...
View ArticleRe: passing SVM pointers in struct?
I guess, I've found the problem of getting wrong result on GPU devices. We must pass the information about those SVM pointers to the kernel via clSetKernelExecInfo API. Because OpenCL spec says:...
View ArticleRe: Bug? CL_MEM_COPY_HOST_PTR is not thread safe
You missed a quite important step: freeing the cl::Buffer: cl::CommandQueue queue = cl::CommandQueue::getDefault();cl::Context context = cl::Context::getDefault(); void run() { cl_int value = 0;...
View ArticleRe: Bug? CL_MEM_COPY_HOST_PTR is not thread safe
Yes, its crashing after adding the clReleaseMemObject(buff). However, I don't see any reason for this segfault.Another point is, it is working fine for following case:cl_mem buff =...
View Articlesegfault at clBuildProgram
Hi, after modifying a number of variable declarations fromdouble to single precision in a (working) .cl file, I now have a systematic segmentation fault at the clBuildProgram call.It does not seem to...
View ArticleRe: Suggest Feature you want in AMD APP
1. Async compute (execute different kernels simultaneously)2. Smaller latencies for small data transfers and / or compute simultaneously 3. Make OpenCL 2.0 beta available to Win7 (8 makes me so angry)...
View ArticleClik here to view.
Re: 14.9 and higher OpenCL performance
Sorry, that code is for SGMiner 5 - an altcoin mining application. The host code is on GitHub, here: https://github.com/sgminer-dev/sgminer - the file shown should replace kernel/groestlcoin.cl in the...
View Articlerequest for DOPP edge blending sample code
Hi AMD, is there any edge blending sample code available for sharing? thanks.
View ArticleRe: 14.9 and higher OpenCL performance
Hi,I'm just curious. Does the Groest algo has big memory footprint (just like Litecoin)?
View ArticleRe: 14.9 and higher OpenCL performance
No, not in the same way. Litecoin's algorithm uses a scratchpad that cannot fit in LDS, so it goes in global memory - Groestl, at least these implementations, use rather large lookup tables, but they...
View ArticleRe: FirePro DOPP SDK is Here!
The official DOPP SDK Archive DOPPSDK_1.0.zip does not contain the DOPPenable.exe, but only a DOPPenable.txt with the following content:FILE QUARANTINED Microsoft Forefront Protection for Exchange...
View ArticleHow to use OpenCL via SSH for normal users?
I've been trying to find some way to let remote users run OpenCL programs via SSH without them having to start up a local X session. The closest I've found is here but it still requires an X session...
View ArticleRe: FirePro DOPP SDK is Here!
The download is now fixed, and I have removed the .exe from Chris's post, to avoid confusion. Please get the download from the website. THANKS for reporting it.
View ArticleRe: Re: FirePro DOPP SDK is Here!
Hi,thanks for reporting this problem. We will update the package. In the meantime, please find the DOPPEnable.exe attached.Chris (.exe file now removed, problem fixed!)
View ArticleDOPP PresentTextureToVideo not working
Hi, I'm trying to get the DOPPEfectOpenGL from the DOPP SDK 1.0 working. Using the capture window works nicely, but I never get the effect applied to the full output. I've added some debug outputs to...
View ArticleRe: DOPP PresentTextureToVideo not working
Hi, do you have DWM/Aero turned on? If not please turn it on and check if the desktop texture gets replaced. Chris
View ArticleClik here to view.
Re: DOPP PresentTextureToVideo not working
Hi, do you have DWM/Aero turned on? If not please turn it on and check if the desktop texture gets replaced. That was it. Thank you! I thought that I had even tested with both areo on and off before,...
View ArticleRe: segfault at clBuildProgram
Thanks for the heads up, Wolf; did you have an "automated" or at least tolerable way of identifying which kernel the problem was in?
View ArticleWhat's the type of SVM cache supported?
SVM logically extends global memory into host address space, and the cache support for global memory on Kaveri is CL_READ_WRITE_CACHE.Does it mean that SVM will be cached as read and write type? Does...
View ArticleForce high performance GPU programmatically on Switchable Graphics
Hi, I am searching how to force my OpenGL application to use of the AMD GPU rather than the integrated Intel HD on Switchable Graphics laptops.Is there an equivalent to NVIDIA's NvOptimusEnablement...
View Article