Hi,

You've just bumped into an unimplemented built-in.
I added a ticket of it:
https://github.com/pocl/pocl/issues/294

If you want to make sure it's fixed soon, please implement
it, and send a merge request. This is a no-op for x86_64,
so the default implementation is trivial.

BR,
Pekka

On 23.01.2016 12:50, Gunnar Wüllrich wrote:
> Hi,
>
> when running the OpenCL HiddenMarkovModel example from NVIDIA's CUDA
> toolkit v4.2 (https://developer.nvidia.com/cuda-toolkit-42-archive), the
> execution fails with an undefined symbol: mem_fence error.
> This example runs well with other OpenCL runtimes, and other examples
> also run fine with pocl.
>
> Is this an issue on my end, or a known problem with pocl?
>
> Regards,
>       Gunnar Wüllrich


------------------------------------------------------------------------------
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take corrective actions now
Troubleshoot faster and improve end-user experience. Signup Now!
http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140
_______________________________________________
pocl-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/pocl-devel

Reply via email to