Search:

Type: Posts; User: initram

Search: Search took 0.00 seconds.

  1. opengl 3.2 core profile not compatible with cl_gl.h

    The OpenGL 3.2 core profile is not compatible with cl_gl.h

    as a workaround to use OpenCL functionality with OpenGL 3.2 core mode, you have to define __gl_h_ before including CL/cl_gl.h
    otherwise...
  2. Re: How many CUDA registers uses an OpenCL kernel

    you can try to use the compilation parameters you can set with opencl.

    but in experienced that the parameters don't work with the first 2 releases (maybe it works with the conformant release).
    i...
  3. Replies
    1
    Views
    2,900

    Re: OpenCl and Nvidia!

    opencl is not an automatic acceleration mechanism for c++ code.
    it's an api to parallel programming features for hardware which supports this.

    please read the specification for more informations:...
  4. Replies
    2
    Views
    3,233

    Re: Newbie question

    yes. the information you find on the khronos website is the api specification.

    nvidia already provides a pre-release of the opencl implementation for registered developers.
  5. Replies
    5
    Views
    3,957

    Re: offline compilation ?

    please have a look at the function clGetProgramInfo with the parameter CL_PROGRAM_BINARIES.

    just use your program as usual, read out the kernel binaries after compilation (clBuildProgram) using...
  6. Replies
    5
    Views
    5,582

    Re: kernel execution returns CL_INVALID_VALUE

    i assume, you talk about the current nVidia sdk.
    try to use less threads (128 or 64).

    if that does not help, you can try to post the code.
  7. Replies
    4
    Views
    3,103

    Re: Passing arrays of complex structures

    this doesnt seem to work on current sdk implementations.

    you have to copy the whole array to the gpu memory instead of passing it as a kernel parameter.
    (this also makes sense because of the...
  8. Replies
    5
    Views
    3,957

    Re: offline compilation ?

    you can compile offline by calling the builtin compiler and store the binaries.
    (compilation makes it necessary to specify the graphic card for which you want to create the binaries).

    afaik the...
  9. Replies
    99
    Views
    67,946

    Re: OpenCL C++ Bindings

    1) yes
    2) probably more than x10 if the problem is well suited. this is usually the case if you have a lot of vector operations and coalesced memory access. but a concretely answer to this question...
  10. Thread: setArg

    by initram
    Replies
    2
    Views
    3,074

    Re: setArg

    hi affie,

    thx for your reply. you're right that setting the value of an kernel argument with a string would take more cycles but this makes to difference if the values are set while another kernel...
  11. Thread: setArg

    by initram
    Replies
    2
    Views
    3,074

    setArg

    Does anyone know the reason, why the clSetKernelArg uses only the argument index to specify the argument instead of the argument parameter name?

    i think that the specification (maybe the OpenCL...
Results 1 to 11 of 11