clMAGMA with HD5850 gpu, WinXP32, VS2008 + MKL
Any suggestion is appreciated to help solve this problem I'm having trying to resolve some bugs with my clMAGMA build using HD5850 gpus: 1) Compiling and running with AMD Sempron CPU:...
View ArticleHow long does it take to get an answer for an OpenCL ticket?
Does anyone have any idea how long one should wait for an answer for an OpenCL ticket? It's been almost two weeks since submitting the ticket and I still have no answer. Moreover, trying to reply to...
View ArticleOpenCL 1.2 "cl_khr_dx9_media_sharing" bugs
Hey guys, trying to make the "cl_khr_dx9_media_sharing" OpenCL 1.2 extension work. The latest AMD drivers (12.11 beta) generally support this extension and it works ok, but there are a couple of bugs:...
View ArticleRe-create OpenCL-OpenGL interop
Problem when create, release and re-create OpenCL-OpenGL context.Hi everyone,I have a problem when I create, release and re-create OpenCL-OpenGL context. I have isolated this issue in the program...
View ArticleInterleaving data transfers and execution in Linux
I've seen in another thread about how to data transfers and execution. Basically, you create two command queues, issue copies and kernels into both queues, and flush them both. When you set...
View ArticleHelp: Catalyst 12.11 clBuildProgram crash
I've recently updated to Catalyst 12.11 Beta 8 from 12.9 and now my code which compiled & run perfectly now causes the compiler to crash.This also happens using KernelAnalyzer. I get this debug...
View ArticleConcurrent execution on multiple GPUs
Hi, everyone! I found a problem about concurrent kernels execution on multiple GPUs. There are two AMD Radeon HD 7850 GPUs on my computer, and the OS is Ubuntu 12.04 LTS.I installed the AMD APP SDK and...
View ArticleTransfer from host to GPU via DMA parallel to kernel execution
My application runs the same sequence of kernels several times for different chunks of data.I'm trying to overlap transfer with running kernels, specifically, I want to transfer the next piece of data...
View ArticlePossible compiler bug with Catalyst 12.10
Tested with a Radeon HD 7970 on Windows 7 64 bits. Driver updated to Catalyst 12.10 The relevant code: #define PIXELS 20 for(int dy=0;dy<PIXELS;dy++) { (...) if(dy>0)...
View ArticleAPP SDK v2.7 in Windows 8 Pro x64 does not work. Why?
Hi everyone, This is my system:AMD Phenom II X4 9558 GB DDR3Chipset = AMD 785G / SB710Video Card 1 (PCI Express) = Radeon HD 5670 (Catalyst 12.10)Video Card 2 (onboard) = Radeon HD 4250 (Catalyst 12.6...
View ArticleWide memory access
Hello, is it possible to have wide memory access without declaring the buffer as float4? Does anybody know? I have a kernel similar to this: __kernel void test(__global float* uav0){ int r =...
View ArticleAMD SDK & the ATI Theater HD 750 card.
Does anyone know if the AMD SDK supports the ATI Theater HD 750 card, and would it allow apps access to access and collect video data from the HD 750 card?
View ArticleUsing Open CL to implement serval applications.
We would like to use OPEN CL to implement the following applications.1) Direct volume Rending2) Diffusion 3) NLD (non-linear diffusion) 4) Edge detection5) AnisotropicIn AMD...
View ArticleClik here to view.
Tahiti ISA assembler
Hi All!I have a really simple question:Is it really possible tho assemble my ISA code on my 7970? I know that CodeXl provides things like dissassembling code and showing me the ISAbut is it possible to...
View ArticleRecommended way to overlap Ocl kernels on HD7970 Catalyst 12.10
Hi, I've just downloaded the new driver and noticed, that my program is became 3.7% slower than before. I have figured out that the problem is that the new driver wont allow to execute 2 kernels...
View ArticleUsing a single CPU core without pinning the process to a specific core
I am running my OpenCL program on a cluster. The cluster software prefers jobs to use a single CPU core so it can utilize the nodes effectively. I tried using device fission to restrict my code to run...
View ArticleLinux x64 floats are buggy, caused by 12.8 driver?
Hi there. I have a really strange problem and i hope you can help me. I have a shrinked kernel to my problem: __kernelvoid softwareRender(){ __private float zeroDotFive; zeroDotFive =...
View ArticleStandard Portable Intermediate Representation (SPIR)
What are your plans for the Standard Portable Intermediate Representation SPIR ( OpenCL portable and vendor-independent IL ).Do you plan to update your SKA tool with it+ Just curious. If you don-t know...
View ArticleQuestions about OpenVideo Encode
I have recently started working on a project involving the use of the AMD OpenVideo Encode which is re-written from the example titled openEncode.zip found here. I have a Radeon HD7970 and am running...
View ArticleGPU passthrough with vmware
I'm stuck since 2 days trying to have my Graphic card working in a Vmware host. Specifications: - Vvmware ESXi 5.0.0 running on Windows- Ubuntu 10.04 running on host- Graphic card: AMD Radeon 6900...
View Article
