Search:

Type: Posts; User: jimmyz500

Search: Search took 0.00 seconds.

  1. Replies
    3
    Views
    1,312

    Re: warp size vs # of SPs per SM

    Thanks guys!
  2. Replies
    3
    Views
    1,312

    warp size vs # of SPs per SM

    In my GPU there are 384 cores, 8 compute units (streaming multiprocessors), so there 384/8 = 48 streaming processors on each compute unit. Given that NVidia warp size is 32, which means 32 threads...
  3. Re: OpenCL Kernel Memory Optimization - Local vs. Global Mem

    I have a follow up question to this. In my GPU there are 384 cores, 8 compute units (streaming multiprocessors), so there 384/8 = 48 streaming processors on each compute unit. Given that NVidia...
  4. Replies
    7
    Views
    2,653

    Re: Running kernel on host vs device

    Dithermaster, thanks very much for the explanation.
  5. Replies
    7
    Views
    2,653

    Re: Running kernel on host vs device

    Dithermaster, thanks very much for your response.

    So only when device type is set to CL_DEVICE_TYPE_GPU, does clEnqueueWriteBuffer actually copies the data to the device over PCIe, causing the...
  6. Replies
    7
    Views
    2,653

    Running kernel on host vs device

    In the Codeproject example:

    // create data for the run
    float* data = new float[DATA_SIZE];

    // Create the device memory vectors
    input = clCreateBuffer(context, CL_MEM_READ_ONLY,...
Results 1 to 6 of 6