Search:

Type: Posts; User: samuelbferraz

Search: Search took 0.00 seconds.

  1. Replies
    1
    Views
    2,843

    OpenCL on CUDA architecture

    Hello,

    I'm implementing a problem using OpenCL 1.0 on a NVIDIA Fermi Architecture GPU. How is NVIDIA's driver version going to influence the performance of my kernel? I couldn't really get how...
  2. Re: How to configure cache and shared memory on Fermi

    Ok David, thank you.

    Sincerely,
    Samuel
  3. How to configure cache and shared memory on Fermi

    Hello,

    I've been searching about Fermi Architecture and one of the great things about it is that you can configure how much shared memory and cache you want, up to 64kb. Using CUDA, it's possible...
  4. Replies
    4
    Views
    1,917

    Re: Constant memory execution error

    I still haven't found the solution for my issue and searching on OpenCL reference guide I've found the following:

    "A pointer to address space A can only be assigned to a pointer to the same...
  5. Replies
    4
    Views
    1,917

    Re: Constant memory execution error

    Unfortunately this problem happens even if I put Rt as the only constant argument. You may be right, it looks like a bug in the compiler, but I'll keep trying to find a way to solve this. Thanks.
    ...
  6. Replies
    8
    Views
    3,268

    Re: OpenCL weird error from clBuildProgram

    Are you reading your .cl file and loading the prog source correctly?
  7. Replies
    4
    Views
    1,917

    Constant memory execution error

    Hello everybody,

    I've been facing a strange problem with constant memory. Look at the header of my kernel:



    __kernel void Lvo
    (
    __global int* Rt,
    __constant int* St,
  8. Replies
    8
    Views
    3,268

    Re: OpenCL weird error from clBuildProgram

    Hello,

    I don't know what kind of calls you have before the clBuildProgram, but here follows an example of how I use to compile my OpenCL codes:



    oclGetPlatformID(&cpPlatform);...
Results 1 to 8 of 9