[mpich2-dev] MPI_UNWEIGHTED should have type "int*" ?

Supalov, Alexander alexander.supalov at intel.com
Fri Dec 18 14:19:25 CST 2009


Re https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/172 : the issue was detected a few days before MPI-2.2 became final. There was no time to get all voting done for this small correction, and so it went into the MPI-2.2 errata. As such, it stands a very good chance of being voted in soon, and thus the proposed fix should be OK.

-----Original Message-----
From: mpich2-dev-bounces at mcs.anl.gov [mailto:mpich2-dev-bounces at mcs.anl.gov] On Behalf Of Dave Goodell
Sent: Friday, December 18, 2009 7:52 PM
To: mpich2-dev at mcs.anl.gov
Subject: Re: [mpich2-dev] MPI_UNWEIGHTED should have type "int*" ?

In case anyone wants to track these issues, the relevant links are  
inline below.

On Dec 17, 2009, at 8:07 AM, Dave Goodell wrote:
> 1) We aren't testing MPI_UNWEIGHTED in test/mpi/topo/distgraph1.c.   
> I'll file a ticket to remind us to do this.

https://trac.mcs.anl.gov/projects/mpich2/ticket/976

> 2) There isn't any test in Fortran yet for the distgraph stuff.   
> I'll file a ticket to remind us to do that at some point.  There's a  
> reasonable chance that Fortran is broken because I don't recall  
> doing any of the special constant magic (MPI_UNWEIGHTED is similar  
> to MPI_STATUS_IGNORE).

https://trac.mcs.anl.gov/projects/mpich2/ticket/975

> 3) The MPI-2.2 Standard doesn't specify the type of MPI_UNWEIGHTED  
> in section A.1.1, page 523, line 35.  I'll file a ticket with the  
> MPI Forum for this one.


Someone already beat me to it: https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/172

-Dave
---------------------------------------------------------------------
Intel GmbH
Dornacher Strasse 1
85622 Feldkirchen/Muenchen Germany
Sitz der Gesellschaft: Feldkirchen bei Muenchen
Geschaeftsfuehrer: Douglas Lusk, Peter Gleissner, Hannes Schwaderer
Registergericht: Muenchen HRB 47456 Ust.-IdNr.
VAT Registration No.: DE129385895
Citibank Frankfurt (BLZ 502 109 00) 600119052

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.



More information about the mpich2-dev mailing list