[Beignet] [PATCH] Add memory fence before barrier to support global memory barrier.

[Zhigang Gong]

On Tue, Jun 18, 2013 at 10:10:08AM +0200, Dag Lem wrote:
> Dag Lem <dag at nimrod.no> writes:
> 
> [...]
> 
> > If I understand you correctly, in order to calculate the maximum
> > allocatable local memory size, you should rather calculate the maximum
> > number of thread groups running in parallel per half-slice, and divide
> > the maximum allocatable half-slice SLM size by this number.
> 
> Hmm, or will the GPGPU walker automatically limit the number of thread
> groups running in parallel based on the requested local memory size?
Yeah, I think so.
> 
> Please bear with me, I'm learning :-)
We are all learning too. And your comments/contributions are really valuable
for us. Thanks.

But this issue still remains. Let's hold for a while to learn more about
the barrier/SLM/memory fence and find out the real reason. One interesting
thing is a memory fence can fix this failure. Maybe that's a clue.



> 
> -- 
> Dag
> _______________________________________________
> Beignet mailing list
> Beignet at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/beignet