Search:

Type: Posts; User: ffelagund

Page 1 of 2 1 2

Search: Search took 0.00 seconds.

  1. Replies
    4
    Views
    1,694

    Re: clEnqueueWriteBuffer crash with error -38

    Without more info, I can't say much more, but I'l almost sure you don't need more than one CL context. Could you provide us more info?
  2. Replies
    4
    Views
    1,694

    Re: clEnqueueWriteBuffer crash with error -38

    Sorry for the question, but why do you need so many different opencl contexts? Couldn't your app work in a single CL context environment?
  3. Replies
    9
    Views
    2,185

    Re: OpenCL Failing At Conditionals

    Your problem seems caused by the NV driver. NV drivers presented those kind of weird behaviours.

    The underlaying message is: if you want GPGPU in our cards, use CUDA

    PD: Seek for my messages...
  4. Replies
    3
    Views
    3,340

    Re: Problems mixing GTX 680 and GTX 590

    I can't really help you with your problem.

    I only can tell you that you shouldn't be surprised if:
    -you find unexpected kernel numerical results
    -non related CL errors
    -CL errors that belong...
  5. Replies
    0
    Views
    1,884

    OpenCL + Python

    Hello,

    I know this is not a proper OpenCL question but a python one, but because Iím getting this error only with this .lib, its highly propable that another OpenCL programmer could faced this...
  6. Replies
    2
    Views
    1,250

    Re: More bugs on NV compiler

    Ok, for all those bugs, NV was able to reproduce them. They told me that the bugs are routed for investigation.

    Hope they will fix that soon.
  7. Add the option to chose the OpenCL version to instance

    Hello,

    Its pretty anoying have prepared an application that works well with a certail OpenCL version, and when the new driver comes, with support for the next OpenCL version, some things of the...
  8. Replies
    2
    Views
    1,250

    Re: More bugs on NV compiler

    Well, still playing with structs and it seems that NV din't implemented very well the structs. The driver crashes with standard C99 initializators like:

    struct DispMapPixel maxDispPixel = {-1.0f,...
  9. Replies
    2
    Views
    1,250

    More bugs on NV compiler

    Hello,

    We are reaching a hit. In two weeks we've found 3 bugs in the OpenCL NV compiler. I'm starting to thinking if it would be better switch back to GLSL again...

    First one is described...
  10. Replies
    5
    Views
    2,133

    Re: Bug in NV OpenCL compiler

    @vci, try disabling OpenCL compiler optimizations in the clBuildProgram, using a line like this: clBuildProgram(program, 0, NULL, "-cl-opt-disable", NULL, NULL);

    @notzed, my company has always...
  11. Replies
    5
    Views
    2,133

    Re: Bug in NV OpenCL compiler

    david.garcia, please, dont assume that everybody is a noob. I started to send bug reports to cards manufactureds since OpenGL 1.1 ages. The Visual Studio project I've prepared is the result of a...
  12. Replies
    5
    Views
    2,133

    Bug in NV OpenCL compiler

    Hello,

    I already posted this information in nv forums, but it seems that NV people dont read them.

    We've found a bug in the NV Compiler. Here is the text I'd wrote in the NV forums, and the...
  13. Replies
    2
    Views
    1,539

    Re: clBuildProgram crashes in Intel platform - SOLVED

    Ok, problem solved. Internally, the Intel's OpenCL driver uses TBB, and in our project we was using TBB too, but an older version. Our TBB dll's was being copied to our bin folder, so when the...
  14. Replies
    2
    Views
    1,539

    Re: clBuildProgram crashes in Intel platform

    Only as clarification: the crash that happens is:
    Unhandled exception at 0x00000000 in PublicLayer_Debug.MetriaApps.PublicLayerSample.exe: 0xC0000005: Access violation.
    in this line:

    error =...
  15. Replies
    2
    Views
    1,539

    clBuildProgram crashes in Intel platform

    Hello,

    I have an application that runs fine in GPU, but when I chose the Intel CPU as platform, clBuildProgram crashes. clCreateProgramWithSource returns what appears to be a valid cl_program and...
  16. Replies
    0
    Views
    1,175

    Force to an OpenCL version

    Hello,

    I would like to know if there is possible, like in OpenGL, to create a context for a specific OpenCL version. We really don't want our program to change it's behaviour depending on the CL...
  17. Replies
    7
    Views
    2,381

    Re: Problem with normalized image coordinates

    I've found the problem. You two were right. The problem was caused by using floating point increments and comparisions. I've checked the loops control variables and, in many cases the number of...
  18. Replies
    7
    Views
    2,381

    Re: Problem with normalized image coordinates

    We tried a lot of tests. With bigger convolutions, the deffect is bigger. With bigger images the effect is bigger (for instance, with a 512x512 source image, the break happens exactly at the middle...
  19. Replies
    7
    Views
    2,381

    Problem with normalized image coordinates

    Hello,

    I'm learning OpenCL (I come from the GLSL world) and I'm playing with normalized image coordinates (this is the way I am used, so I would like know how they work in OpenCL) but I'm having...
  20. Replies
    1
    Views
    912

    Re: Naive problem with Images and Kernels

    As said, it was a naive problem. I was checking incorrectly the bounds of the image, sorry for bothering you with tons of code.
  21. Replies
    1
    Views
    912

    Naive problem with Images and Kernels

    Hello,

    I'm starting with OpenCL and I'm having some troubles understanding the work items and work groups stuff (and probably also images format)
    I'm not new with OpenGL, so I'm a little...
  22. Replies
    0
    Views
    1,306

    OpenCL on FPGAs

    Hello,

    We are building a heavy image processing based application. We are in the point where we must choose the technology to use for this. I would like to use OpenCL, because it makes us easier...
  23. Replies
    6
    Views
    7,388

    Re: Problems converting to fixed point

    GLfixed is a typedef of int, and C++ doesn't allow to overload any operator (even the casts) of basic types (like int, chat, float, etc) :)
  24. Replies
    6
    Views
    7,388

    Re: Problems converting to fixed point

    Could you post some lines of your code? Another thing, the first texel of your texture is black? I say this because if you forgot convert texcoord '1' to '1<<16', you probably will get only the first...
  25. Re: How to get current MODELVIEW MATRIX and PROJECTION MATRI

    Currently, in OpenGL|ES, you must track the matrices, because OpenGL|ES doesn't allow glGetxxx for dynamic states, but if your OpenGL|ES implementation supports the GL_OES_matrix_get (read this...
Results 1 to 25 of 35
Page 1 of 2 1 2