Search:

Type: Posts; User: ofer_rose

Search: Search took 0.00 seconds.

  1. Replies
    1
    Views
    2,574

    Re: Running openCL on CPU

    You need to have Intel OpenCL installed.

    Open this link: http://software.intel.com/en-us/vcsourc ... opencl-sdk
    On the right side you'll see "OpenCL* CPU Only Runtime 2012" - click it, and it...
  2. Re: when to use get_global id and get_local id in opencl?

    get_global_id(0) returns the global ID of the workitem in the first dimension. For 1D problems, this is enough for the algorithm to work. The kernel will still be launched in parallel many times.
    ...
  3. Replies
    6
    Views
    2,235

    Re: Do I need atomic_add in that case?

    In theory you're right - but the "problem" is that GPUs are vector machines (also CPUs, if you use SSE/AVX).

    The meaning is that threads are not executed solely, but in SIMD fashion (SIMT, if you...
  4. Replies
    1
    Views
    1,156

    Re: Asynchrouous call to program build

    Hi Manish,

    It might - if enough time had passed between calling to clBuildProgram and clCreateKernel - but I wouldn't count on it.

    In order to enqueue the kernel, you need a kernel handler -...
  5. Replies
    6
    Views
    2,235

    Re: Do I need atomic_add in that case?

    No. you have to use some atomic mechanism to sync the reads and writes to histo[].

    The operation of "histo[arr[id]]++;" (or any increment of global memory) is actually composed of three...
Results 1 to 5 of 8