Search:

Type: Posts; User: daveh19

Search: Search took 0.00 seconds.

  1. Thanks for the follow-up Dithermaster. Sorry I...

    Thanks for the follow-up Dithermaster. Sorry I didn't get an email alerting me to the reply so I'm only checking back now.

    Your advice is all perfect, unfortunately at present I don't have much...
  2. By the way, this guy...

    By the way, this guy appears to be having the exact same problem as me.

    Dave
  3. Hi Dithermaster, thanks for the response, I...

    Hi Dithermaster, thanks for the response,

    I don't have access to a task manager type program as this simulation is running on a university provided compute cluster. I submit batch jobs and they...
  4. Does Nvidia API grow an unbounded command queue unless clFinish() is called?

    Hi all,

    I have a simulator which runs under all of the major OpenCL APIs but if I run it for a long time under Nvidia it eventually runs out of memory. My code involves repeatedly calling the same...
  5. Re: Putting a space in path supplied to clBuildProgram()

    I'm feeling a little stupid for not having thought of that! ;-)

    Thank you
  6. Putting a space in path supplied to clBuildProgram()

    Hi,

    I am trying to use #include within a kernel. And despite what I originally read on many internet pages it does work. But now I am having trouble with the locations searched for the included...
  7. Re: Low level behaviour of clEnqueueWriteBuffer() - spec vs

    Just for the sake of the public record, I've been playing with this issue a little more and it seems to be a transitory effect. By that I mean it doesn't always happen. It's reproducable, but not...
  8. Re: Kernel with >8 float3 parameters fail on Intel device

    Call clGetDeviceInfo() with CL_DEVICE_MAX_CONSTANT_ARGS as the second argument. It will tell you how many constant arguments your device can support (the min in the spec is 8!)

    Dave.
  9. Re: Low level behaviour of clEnqueueWriteBuffer() - spec vs

    It's OpenCL 1.0 (unfortunately, that's the one that comes with the OS), the Apple version of the OpenCL framework is 12.3.6 dated 18/05/2011.

    The device is an AMD Radeon HD 6750M with driver...
  10. Re: Low level behaviour of clEnqueueWriteBuffer() - spec vs

    Thanks Notzed. You've given me a reply which corresponds with my own understanding of the spec. The catch is that's not how it's working on my computer ! :)

    I am, as you asked, modifying the data...
  11. Re: problem passing struct kernel arguments (Apple)

    I can confirm that I came across this problem previously on a Mac (OS 10.6.8). I never found a solution, so thanks for filing the bug report. I presume that you're getting the same error number as me...
  12. Replies
    2
    Views
    1,026

    Re: How to display error code

    I think I saw elsewhere that you're using Nvidia, but MacOS implementation has a header file called util_opencl.h with the following function in it
    static char *print_cl_errstring(cl_int err)...
  13. Low level behaviour of clEnqueueWriteBuffer() - spec vs impl

    Hi,

    Can somebody please clarify for me how clEnqueueWriteBuffer() operates at a hardware/OS level? And how much is in the specification versus implementation specific.

    The reason I ask, is that...
Results 1 to 13 of 23