• Execution of OpenCL Kernel on more than one GPU

    Hello,   i want to execute different instances of the same kernel on 2 AMD Radeon HD 6870 at the same time. Every kernel instance is called by one instance of the host program. I have a AMD Sempron(tm) 140 Pro...
    last modified by w00
  • Right cache size in AMD A10 7850K?

    Recently I query the device info of AMD APU A10 7850K in OpenCL by "clinfo", as the results show, both the integrated CPU and the GPU has "16384" Bytes "Cache size". I am confused with the results because of two thing...
    last modified by acekiller
  • W600 3x3 video wall

    Hi I tried to setup a 3x3 video wall using w600. I used 3 startech MSTMDP123DP mini display port to display port splitters to split 3 of the w600 ports in to 6 display and tried to use rest of the 3 ports directly. U...
    last modified by kworld
  • AMD FirePro D.O.P.P API - Where to Find Detailed Document

    Dear Friends,   I want to develop applications of post-processing the content of framebuffer  before it is presented.  The manual of FirePro card, such as W9000, lists one feature 'D.O.P.P' which is m...
    last modified by zdjiang
  • DOPP & Windows 8

    Hi,   I was wondering which versions of windows are supported by DOPP.   Perhaps the question is different: which windows version is the best fit for DOPP i.e. which windows would be more stable with DOPP...
    last modified by aldero
  • CodeXL truncate float on when profiling openCL

    Hello,   I have a problem when using the "Application Timeline Trace" tool in profile mode. Float constants are truncated   Here an example: __kernel void useFloats(__global float* in,   &nb...
    last modified by festi
  • CodeXL causing blue screen

    Hello, I just started using CodeXL a few weeks ago, and it is great.  However, when I try to use it on my heavily multi-threaded app, it chugs for a while and then my machine blue screens and reboots.  I am...
    last modified by kornely
  • GPUPerfAPI Library for GPU Graphics Memory Usage info?

    Hi All,   Is it possible to use GPUPerfAPI for retrieving the graphics memory utilization at run time? I am trying to use OpenGL's glGetIntegerv(GL_TEXTURE_FREE_MEMORY_ATI, param) but new AMD drivers do not seem...
    last modified by piyushm1
  • HSA Motherboard

    On the page HSA Platforms & Installation · HSAFoundation/HSA-Docs-AMD Wiki · GitHub the only target platforms mentioned are based on Asus motherboards. The page states "Note that some System BIOS ver...
    last modified by sarobi
  • Is Kaveri a HSA-compliant processor?

    Hello everyone,   I have survey lots of HSA introduction and find that GPU should be preemptible and support context switch. But the wiki AMD Accelerated Processing Unit - Wikipedia, the free encyclopedia says...
    last modified by gic4107
  • Blender Cycles(Opencl on AMD GPUS)

    Dear Opencl Developer Why doesn't the AMD opencl compiler work with blender cycles? whenever i compile the blender cycles kernel, the system either crashes due to lack of memory, or takes too long to compile the ble...
    nazim mer
    last modified by nazim mer
  • HSA Linux kernel driver v0.8 released

    AMD Releases HSA Linux kernel driver v0.8 at HSAFoundation/HSA-Drivers-Linux-AMD · GitHub. What's New in kfd v0.8 Based on kernel 3.14.11 Supports HSA signals (kfd events) Enable allocating memory from GPU l...
    last modified by gabbayo
  • Does the OpenCL2.0 SVM support allocate memory for images?

    Does the OpenCL2.0 SVM support allocate memory for images? We can test the SVM performance like:   d_a=(float*)clSVMAlloc(context,(CL_MEM_READ_WRITE|CL_MEM_SVM_FINE_GRAIN_BUFFER|CL_MEM_SVM_ATOMICS),size,0); d_...
    last modified by sky3551211
  • IL support for FirePro W9100

    Hi,   I understand CAL/IL is not officially supported anymore in recent OpenCL SDKs. However, If I link my old CAL/IL programs with an old version of ATI Stream SDK, I can still run my code on Cayman and Tah...
    last modified by nnsan
  • Does CodeXl step into a Kernel built by clBuildProgramWithBinary?

    I can step into the Kernel built by clBuildProgramWithSource, which is good. However, the clBuildProgramWithSource took me 2+ mins (with 100+ Kernels) to wait for the compilation finish, which is bad since I need de...
    last modified by digbug
  • clBuildProgram had an unhandled exception

    The kernel below succeeds to compile in some devices, but gives an unhandled exception in others. I've put it through CodeXL in Analyze Mode, and got the error below. Minor changes to the code tend to hide the problem...
    last modified by danval
  • How to set ATI MPEG Video Encoder Properties?

    Hi, I'm application developers. I set RADEON R280X to my pc, and install Catalyst 14.4. Open the GraphEdit, I saw ATI MPEG Video Encoder. Connect Filter Graph, Change Codec Properties MPEG2 to H.264, and so on. an...
    last modified by lhs9647
  • Disappointing real-time performance OpenCL and HSA

    Hi All,   We have build an test application where we use OpenCL in combination with an AMD A10-7850K APU. The platform is Linux based and the uses a Ubuntu 11.04 distribution with an Xenomai 2.6 patch. The test ...
    last modified by klopwa
  • R9 M290X - Problem with OpenCL

    HI! First post here, and of course, I need your help   Here is my computer:   GX60 3CC-294XES (Destroyer) - OS Windows 7 Home Premium SP1 AMD Quad-Core A10-5750M (2,50 GHz) Integrated GPU - AMD Radeon H...
    last modified by legi0nario
  • 2 Landscape Flipped monitors in 2x2 wall?

    Hi Is it possible to have a 2x2 wall with the top 2 monitors working in Landscape flipped mode in Eyefinity?   We want to try this so we can run a large 2x2 wall using cheap HDTVs.  Problem is these TVs us...
    last modified by bobh