[mpiwg-ft] FTWG Con Call

[Aurélien Bouteiller]

--
          ~~~ Aurélien Bouteiller, Ph.D. ~~~
             ~ Research Scientist @ ICL ~
The University of Tennessee, Innovative Computing Laboratory
1122 Volunteer Blvd, suite 309, Knoxville, TN 37996
tel: +1 (865) 974-9375       fax: +1 (865) 974-8296
https://icl.cs.utk.edu/~bouteill/




> Le 7 janv. 2015 à 14:46, Jeff Hammond <jeff.science at gmail.com> a écrit :
> 
> I'm sorry I missed the telecon.  It landed right in the middle of my
> lunch hour and my calendar notification was missed.
> 
> I am reading through the proposal now and will try to provide some
> content related to RMA soon.
> 
> One small comment on the current document (ticket 323 ft.pdf):
> 
> "If process 0 in 6 MPI_COMM_WORLD has failed, it is possible that no
> process returns from MPI_FINALIZE."
> 
> This is assuming the process 0 hosts MPI.  Does MPI-3 specify that
> hosted MPI is hosted by rank 0?  

Yes page 361, line 28. 


> If not, then I think that text should
> be generalized to:
> 
> "If any process in MPI_COMM_WORLD has failed, it is possible that no
> process returns from MPI_FINALIZE."
> 
> Jeff
> 
> On Wed, Jan 7, 2015 at 8:38 AM, Wesley Bland <wbland at anl.gov> wrote:
>> The notes from yesterday's call are now available on the wiki:
>> 
>> https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/2015-01-06
>> 
>> On Tue, Jan 6, 2015 at 10:42 AM, Wesley Bland <wbland at anl.gov> wrote:
>>> 
>>> As a reminder, we have our usual con call today at 3:00 EST.
>>> 
>>> We’ll be discussing:
>>> 
>>> - Summary of December Face-to-Face
>>> - What's left to do?
>>> 
>>> Dial-in information:
>>> Phone: 712-432-0360
>>> Code: 623998#
>>> 
>>> Thanks,
>>> Wesley
>> 
>> 
>> 
>> _______________________________________________
>> mpiwg-ft mailing list
>> mpiwg-ft at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-ft
> 
> 
> 
> -- 
> Jeff Hammond
> jeff.science at gmail.com
> http://jeffhammond.github.io/
> _______________________________________________
> mpiwg-ft mailing list
> mpiwg-ft at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-ft