Search:

Type: Posts; User: grabner

Search: Search took 0.00 seconds.

  1. Re: how to declare a constant array of float2 vectors?

    I did run into the same issue (with driver 306.94) and did some further investigations, see https://devtalk.nvidia.com/default/topic/524095.

    Kind regards,
    Markus
  2. Replies
    0
    Views
    1,288

    PCI address of mapped OpenCL buffer object?

    Hi!

    Is it possible to query the PCI bus address of an OpenCL buffer object mapped into host address space? I would like a frame grabber card to directly grab into GPU memory, which, according to...
  3. Replies
    9
    Views
    7,701

    Re: non-blocking call to clEnqueueNDRangeKernel?

    [/quote]
    Since I currently don't have access to Nvidia hardware, I did not further investigate this. However, I'm looking forward to receiving a Fermi card as soon as it becomes available (whenever...
  4. Replies
    99
    Views
    67,970

    Re: OpenCL C++ Bindings

    Thanks for your proposals, I slightly modified them and came up with an approach that works for me. Basically it does the following:
    *) define a template function "fixReferenceCount()" which does...
  5. Replies
    99
    Views
    67,970

    Re: OpenCL C++ Bindings

    cl::CommandQueue::getInfo<CL_QUEUE_CONTEXT>() doesn't increase the reference count of the cl::Context object returned by this method. This results in a program crash when the destructur is called for...
  6. Re: #include headers from memory, not from filesystem?

    This could be a solution if I could tell the preprocessor to only process "#include" statements and not to touch the "#ifdef USE_SOME_FEATURE" in the above example. Do you know if this is possible?
    ...
  7. #include headers from memory, not from filesystem?

    Hi!

    In a commercial environment, we have the requirement that no OpenCL source code can be stored in the file system as plain text. Is it still possible under this restriction to use #include...
  8. Replies
    9
    Views
    7,701

    Re: non-blocking call to clEnqueueNDRangeKernel?

    That's what I expected (although for example the read/write/map buffer funtions have an explicit blocking option), therefore I was surprised to see that the clEnqueueNDRangeKernel function returns...
  9. Replies
    9
    Views
    7,701

    non-blocking call to clEnqueueNDRangeKernel?

    Hi!

    With Nvidia's current OpenCL release, the clEnqueueNDRangeKernel function blocks the calling process until the kernel has completed. The OpenCL specification is not explicit about the...
Results 1 to 9 of 11