<html><body>
<p><font size="4">I do not see a need for clarification.<br>
<br>
As long as somewhere in the standard the following points are clear enough:</font>
<p><font size="4"><br>
1) Only MPI_BARRIER promises barrier behavior<br>
2) Any collective may be implemented with barrier behavior as a side effect<br>
<br>
(performance issues make some collectives (eg. MPI_Bcast) unlikely to be barrier like. An MPI_Allreduce will always be barrier like. Either way though, the standard does not stipulate)<br>
</font><br>
Dick Treumann - MPI Team/TCEM <br>
IBM Systems & Technology Group<br>
Dept 0lva / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601<br>
Tele (845) 433-7846 Fax (845) 433-8363<br>
<br>
<br>
<tt>mpi-21-bounces@cs.uiuc.edu wrote on 01/28/2008 12:52:54 PM:<br>
<br>
> Mainly to Jeff Squyres, Hubert Ritzdorf, Rolf Rabenseifner, Nicholas Nevin,<br>
> Bill Gropp, Dick Treumann <br>
> <br>
> This is a follow up to:<br>
> MPI_FINALIZE in MPI-2 (with spawn) <br>
> in <a href="http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-">http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-</a><br>
> errata/index.html<br>
> with mail discussion in<br>
> <a href="http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-">http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-</a><br>
> errata/discuss/finalize/<br>
> _________________________________________<br>
> <br>
> When I understand correctly, then a clarification is not needed<br>
> because the MPI standard expresses all, i.e.<br>
> - MPI_Finalize need not to behave like a barrier <br>
> - but is allowed to have a barrier inside.<br>
> - If the user wants to exit one spawned process while<br>
> the others still continue to work, he/she must<br>
> disconnect this process before calling MPI_Finalize on it.<br>
> <br>
> If somebody wants a clarification to be included into the standard<br>
> and therefore in Ballot 4, please send me your wording<br>
> with the page and line references included.<br>
> <br>
> If all agree, that no clarification is needed, then I would finish <br>
> this track.<br>
> <br>
> Best regards<br>
> Rolf<br>
> <br>
> <br>
> Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner@hlrs.de<br>
> High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530<br>
> University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832<br>
> Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner<br>
> Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30)<br>
> _______________________________________________<br>
> mpi-21 mailing list<br>
> mpi-21@cs.uiuc.edu<br>
> <a href="http://lists.cs.uiuc.edu/mailman/listinfo/mpi-21">http://lists.cs.uiuc.edu/mailman/listinfo/mpi-21</a><br>
</tt></body></html>