Search:

Type: Posts; User: acolubri

Search: Search took 0.00 seconds.

  1. Replies
    5
    Views
    5,735

    Re: mapping buffers vs using host pointers

    Many thanks for bringing the clEnqueueReadBuffer() function to my attention. It seems it is exactly what I was looking for.

    So, the proper order to call the all these functions should be as...
  2. Replies
    5
    Views
    5,735

    Re: mapping buffers vs using host pointers

    I managed to run my distance calculation kernel which uses a host pointer. Basically, I create the CL memory object by doing:

    cldistances = clCreateBuffer(clcontext, CL_MEM_WRITE_ONLY |...
  3. Replies
    5
    Views
    5,735

    Re: mapping buffers vs using host pointers

    Hello,

    Thanks for your response. Since my experience with OpenCL is very limited at the moment, I was drawing these conclusions from some OpenGL coding I did recently where I used Vertex Buffer...
  4. Replies
    5
    Views
    5,202

    Re: kernel execution returns CL_INVALID_VALUE

    Yes, that's correct. I'm using the opencl 1.0 conformant release for Linux (on top of cudadriver_2.2_linux_32_185.18.08-beta).

    I didn't set the number of threads, so I must be using the default...
  5. Replies
    5
    Views
    5,202

    kernel execution returns CL_INVALID_VALUE

    Hello,

    I implemented an OpenCL calculation, and all of the stages seem to be running ok (context creation, device variable allocation, kernel building, etc). However, the execution of the kernel...
  6. Re: input and output having different dimensions

    Thanks, I just figured out the logic of the ND ranges, work elements, memory objects, etc.
  7. input and output having different dimensions

    Is is possible to have a ocl kernel taking as input two float arrays of length N and writing the results to one output array of dimension NxN? Thanks!
  8. Replies
    5
    Views
    5,735

    mapping buffers vs using host pointers

    Hello,

    I'm currently considering to write an application that would use OpenCL to offload atom distance calculations to the GPU (the specific situation being Monte Carlo simulations of protein...
Results 1 to 8 of 9