[Mpi3-rma] RMA examples
balaji at mcs.anl.gov
Fri Nov 12 17:07:23 CST 2010
On 11/11/2010 10:02 PM, Torsten Hoefler wrote:
> Also, it seems like we need to allow conflicting accesses in such an
> epoch (which would be undefined). To allow this, we would need to change
> the definition of shared lock, which right now reads: "Updates to the
> window are protected by exclusive locks if they may conflict.
> Nonconflicting accesses (such as read-only accesses or accumulate
> accesses) are protected by shared locks, both for local accesses and for
> RMA accesses.". Changing this would obviously be possible but seems to
> conflict with the literature on shared/exclusive locks, which suggests
> to use shared locks for non-conflicting accesses and upgrade to
> exclusive locks if conflicts might occur. MPI-2.2 is in line with this
> definition if we relax "lock" to "transaction" and assume that the
> granularity of a "lock" is a whole window.
Conflicting access to overlapping regions is already changed to
"undefined" from "not allowed" in the proposal 1. What additional change
are you suggesting? The above text seems to contradict the change to
"undefined" for overlapping regions, which needs to be fixed anyway.
More information about the mpiwg-rma