• segmentation fault inside clBuildProgram (bug demonstration attached)

    I have a particular OpenCL program that is revealing a bug with clBuildProgam for AMD CPU device.  After several recent code changes, my OpenCL kernel/program will compile just fine on Apple and NVIDIA platforms,...
    last modified by noah_r
  • GPUPerfAPI 2.14 will not work with 7970 and OpenGL

    I am trying to use GPUPerfAPI 2.14 in an OpenGL application with a 7970 card.  I have tried both the Catalyst 12.8 and Catalyst 14.7 drivers.  It acts the same on both.  After calling GPA_Initialize(), ...
    last modified by laynec
  • Opengl interop / clCreateContextFromType segfault

    Hi,   i recently did an ill advised updated of my Debian (sid) installation. This caused my OpenCL/OpenGL interoperability to be broken, and i wonder if anyone else is experiencing this ...   The call to c...
    last modified by fesc2000
  • OpenCL™ 2.0 is here!

    Unfortunately, it is from Intel. When will AMD release OpenCL 2.0 support for AMD APU?   OpenCL™ 2.0 is here! Download the Release 2 of Intel® SDK for OpenCL™ Applications 2014
    last modified by bsp2020
  • Black screen TF2

    On October 1, 2014, and update had been added to Team Fortress 2. I believe there are compatibility issues for Linux users using AMD drivers because that is what most are claiming they have. There may have been an upd...
    last modified by kaboom9530
  • possible OpenCl compiler bug

    Hi,   I have come across a possible compiler issue which is present in the attached kernels. The two kernels differ how work is mapped to the threads. Requiring a work group size of 256; the difference in the ke...
    last modified by martinb
  • How can I force a workgroup to be swapped out for another?

    I am working on partially ordering work group execution order using atomics and need a way to instruct one work group to wait on another workgroup. To achieve this, the waiting work group busy waits on an atomic value...
    last modified by coordz
  • How can I run a kernel with cpu device ?

    Hiiii, I'm trying  to run a OpenCL code on multi2sim . I can run a kernel on gnu, like this : ret = clGetDeviceIDs(platform_id, CL_DEVICE_TYPE_GPU, 1, &device_id, &ret_num_devices); But when I run a k...
    last modified by angelko
  • Thermal Specifications and security measures

    Hello, I'm starting to develop some tools for monitoring hardware components stability and I have some doubts I would like to clear. First, does all amd graphic card implement some security measures to avoid overheat...
    last modified by caezar.jc
  • How to get the status of multi-monitor by W600 video card / SDK?

      Dear All   Hello.   I would like to ask some questions from you, I need you your help.   Thanks a lot.     Background: We have a lot of monitors was placed each garage. ...
    last modified by hayashi
  • HSA + flags for clEnqueueMapBuffer

    With Kaveri out, we now have HSA in our hands. Great, but what flags do I need to use for clEnqueueMapBuffer to avoid data-copying? I have my guesses, but I'd like to hear from you.   For the normal map/unmap-pr...
    last modified by VincentSC
  • suggested user driver update policy

    Hi,   What is AMDs 'general' recommendation regarding OpenCL driver updates? Stay at the current driver if working, or updating to newest? To give more specific reasoning for that question I have a scientific a...
    last modified by firespot
  • Problem about modifying overlap value of Eyefinity setting using Firepro W5000 GPU

    I’m developing an application which runs in multi-display mode using Eyefinity's multi-display group of Firepro GPU. The settings of Eyefinity must be manipluated using c++ code for user’s convenience.&nbs...
    last modified by hellosword
  • can not download app sdk 2.9.1

    because my driver version is 14.10,  I need this version of sdk and try many times to download it failed .
    last modified by heaven
  • PerfStudio 3.0 with 3DMark11/3DMark ?

    Does Perfstudio 3.0 not work with 3dmark11/3dmark/vantage? I am trying to launch those applications to capture some frames but always ending up with "Failed to launch application" error.   Attached Screenshots o...
    last modified by shabby26
  • Using GPUPerfStudio client under wine

    Realizing that GPUPerfStudio is meant for windows, I decided to try it out under wine. It works great! Use winetricks to get the .NET runtime 4.0.   Well, I wouldn't be posting if I didn't have a question. I can...
    last modified by sounds
  • How to make GPU PerfStudio & GLEW play nicely?

    I have a basic application which runs just fine, uses OpenGL 4.3 core profile & GLEW 1.11.0. However, when I run it through GPU PerfStudio, it crashes right on glewInit, yielding an error saying "Missing GL versi...
    last modified by pokiaka
  • PerfStudio command line parameters

    How can I pass command line arguments when starting PerfStudio server?   For example, I have an application that takes the following options.   app.exe -x_size 1024 -y_size 768 -config test.cfg   Ho...
    last modified by joohoon
  • Problems 4k monitor on Linux (Ubuntu)

    When showing the desktop (by minimalising or closing all windows) the computer becomes unresponsive for a few minutes: the mouse moves, but clicking doesn't work. The work-around is to not close all programs when shut...
    last modified by VincentSC
  • GL_ARB_shader_storage_buffer_object ".length()" for unsized arrays returns erroneous value

    I am using OpenGL 4.3 core profile to do various things in OpenGL under Linux.  I am having trouble when using shader storage buffers where the last component of a shader storage block is an unsized array.  ...
    last modified by fletcheb