https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/483

On Mon, Aug 24, 2015 at 8:03 AM, Jim Dinan <james.dinan@gmail.com> wrote:
IIRC, per-window ordering was the intent of the working group and it also seems like the only sensible reading of the chapter, given that we allow each window to provide a different value for the ordering info key.  This might just be an erratum, but it would be helpful to create a ticket for it.

On Mon, Aug 10, 2015 at 10:04 AM, Jeff Hammond <jeff.science@gmail.com> wrote:

"11.7.2 Ordering" says: 

"MPI specifies ordering between accumulate operations from one process to the same (or overlapping) memory locations at another process on a per-datatype granularity."

This seems to say that ordering is required between overlapping windows, which is a horrible semantic.  We need to add a "per-window" caveat here.

Later, we talk about overlapping memory regions, rather than locations, which is confusing:

"MPI does not provide any guarantees for accesses or updates from different origin processes to overlapping target memory regions."

What is a memory region anyways?  Is it a window?  Is it a set of memory locations?

And to be clear, I think I know what we mean in the RMA chapter, but others may not.

Jeff

--

_______________________________________________
mpiwg-rma mailing list
mpiwg-rma@lists.mpi-forum.org
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma


_______________________________________________
mpiwg-rma mailing list
mpiwg-rma@lists.mpi-forum.org
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma



--