[Mpi3-ft] Recoverability of MPI State Proposal Discussion
rlgraham at ornl.gov
Thu Mar 6 09:09:38 CST 2008
After thinking about this a bit, I decided to take Josh¹s suggestion one
more step. The
proposal attached to the UTK paper is a good starting point for this whole
so I obtained the permission of the primary authors to use this as a
I will upload this to the web site later today (I hope). While this does
not cover items
such as dynamic communicators, and even the original authors would do
differently, it is a very good starting point.
On 3/3/08 9:50 AM, "Richard Graham" <rlgraham at ornl.gov> wrote:
> I am no the hook to produce a first draft of a document for this. I am
> planning to do this later in the week, after I finish the 2.1 document
> reviews I need to do.
> On 3/3/08 8:45 AM, "Josh Hursey" <jjhursey at open-mpi.org> wrote:
>> > I'd like to start the discussion on the proposal for "defining
>> > communicator state with process loss", or recoverability of MPI state
>> > in the presence of process loss.
>> > To start the discussion I am suggesting that folks have a look at the
>> > following paper since I think it relates to quite a number of related
>> > topics:
>> > Fagg, G., et. al. "Extending the MPI Specification for Process Fault
>> > Tolerance on High Performance Computing Systems"
>> > http://icl.cs.utk.edu/projectsfiles/ftmpi/pubs/isc2004-FT-MPI.pdf
>> > ----
>> > Josh Hursey
>> > Graduate Student, Indiana University
>> > _______________________________________________
>> > Mpi3-ft mailing list
>> > Mpi3-ft at lists.mpi-forum.org
>> > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-ft
> Mpi3-ft mailing list
> Mpi3-ft at lists.mpi-forum.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the mpiwg-ft