Caitlin Bestler wrote:
[EMAIL PROTECTED] wrote:
I was under the assumption that the DAT` community defined the
APIs and semantics through an open process. Given that the
IB write immediate data facility does not break the
implementation or semantics of the currently defined RDMA
write facility, I see no reason the DAPL spec couldn't be
updated, through consensus, with the realities of existing
transport services.
I agree, but I am not sure we are any closer to consensus regarding an
**unambiguous** write with immediate. I am also not totally clear on the
rules by which we implement new API's. Regardless, it appears that there
is a strong desire to follow the IB semantics if we go with a standard
API and if we cannot come to consensus then it should be incorporated as
an extension.
I would vote for implementing the standard rdma_write_with_ immediate
API that follows IB semantics.
-arlin
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
