Hi,

On 2/2/13 11:09 AM, "Carlos Sánchez de La Lama" wrote:
> IIRC the main difference was WFV did not take into account the need for all 
> WIs to reach the same barriers. That is, your "trampolines" only need to 
> choose which continuation to run for the first WI on each WG, then they could 
> use the same continuation unconditionally. I remember finding it surprising 
> that you did not apply such optimization, after a significant part of the 
> paper was dedicated to de-conditionalizing intra-WI branches to create longer 
> vectorizable regions.

I am not sure I understand what you mean. The OpenCL specification says 
that if work items of the same work group hit different barriers, the 
behavior is undefined. So you only need to store the ID of the barrier 
that was hit by any of the items, e.g. the last. That is what I 
implemented - does it differ from what you said?

Cheers,
Ralf

------------------------------------------------------------------------------
Free Next-Gen Firewall Hardware Offer
Buy your Sophos next-gen firewall before the end March 2013 
and get the hardware for free! Learn more.
http://p.sf.net/sfu/sophos-d2d-feb
_______________________________________________
pocl-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/pocl-devel

Reply via email to