<br><font size=2 face="sans-serif">Also, the IBM-ANL collaboration won't
be limited to the MPI_Aint issue. We plan on contributing patches
to the mpich community regularly now that the dcmf software is open source.
Discussion of those (future) patches would best fit a "mpich-development"
type of mailing list.</font>
<br>
<br><font size=2 face="sans-serif">Michael Blocksome<br>
Blue Gene Messaging Team Lead<br>
Advanced Systems SW Development<br>
blocksom@us.ibm.com<br>
</font>
<br>
<br><tt><font size=2>dcmf-bounces@lists.anl-external.org wrote on 02/28/2008
11:18:26 AM:<br>
<br>
> <br>
> Unfortunately, this MPI_Aint discussion really has nothing to do <br>
> with DCMF. The entrire problem and solution is with MPICH2.
<br>
> <br>
> Is there another, less broad, mpich mailing list that we could use?
<br>
> Maybe a "mpich-development" or something like that? <br>
> <br>
> Michael Blocksome<br>
> Blue Gene Messaging Team Lead<br>
> Advanced Systems SW Development<br>
> blocksom@us.ibm.com<br>
> <br>
> <br>
> dcmf-bounces@lists.anl-external.org wrote on 02/28/2008 11:01:09 AM:<br>
> <br>
> > I'd say this mailing list is better for it right now. Posting
on the<br>
> > broader mpich-discuss might just distract us. <br>
> > <br>
> > Rajeev <br>
> > <br>
> > From: dcmf-bounces@lists.anl-external.org [mailto:dcmf-<br>
> > bounces@lists.anl-external.org] On Behalf Of Bob Cernohous<br>
> > Sent: Wednesday, February 27, 2008 4:19 PM<br>
> > To: dcmf@lists.anl-external.org<br>
> > Subject: Re: [dcmf] 32-bit ROMIO: What is the best solution?<br>
> <br>
> > <br>
> > bobc@us.ibm.com wrote on 02/08/2008 02:41:40 PM: <br>
> > <br>
> > >We all realize there are issues with MPI_Aint's in 32 bit
implementations. <br>
> > >Using signed 32 bit addresses along with 64 bit offsets can
result in <br>
> > >some pretty broken code. I've reproduced several problems
on <br>
> > >BGL/BGP/linux. The problems are most obvious with
romio files > 2G or <br>
> > >virtual addresses > 2G. <br>
> > <br>
> > Earlier this month I posted some comments to this mailing list
about <br>
> > 32-bit MPICH/ROMIO/MPI_Aint issues (see above and the archive).
<br>
> > <br>
> > We've started to work on the problem. We're (optionally)
making <br>
> > MPI_Aint a 64 bit signed value even when integers/pointers are
32 bit <br>
> > values. <br>
> > <br>
> > We'd like to start sending fix patches to the community for comment.
<br>
> > <br>
> > However, since we are (in parallel) contributing our BGP code
back <br>
> > to MPICH and trying to converge on a common code base of 1.0.7,
<br>
> > and because this problem applies to any 32-bit platform, <br>
> > we thought we should move the discussion to mpich-discuss to
get <br>
> > the larger community's comments. <br>
> > <br>
> > It's unlikely, at this point, that our patches would apply to
MPICH2, <br>
> > but that is our goal after the 1.0.7/BGP patch settles.
For now, we'd <br>
> > be sending these as RFC (request for comment) patches. <br>
> > <br>
> > Please let us know if you agree with discussing this on mpich-discuss,
<br>
> > or if there is a better place. <br>
> > <br>
> > Bob Cernohous: (T/L 553) 507-253-6093<br>
> > <br>
> > BobC@us.ibm.com<br>
> > IBM Rochester, Building 030-2(C335), Department 61L<br>
> > 3605 Hwy 52 North, Rochester, MN 55901-7829<br>
> > <br>
> > > Chaos reigns within.<br>
> > > Reflect, repent, and reboot.<br>
> > > Order shall return._______________________________________________<br>
> > dcmf mailing list<br>
> > dcmf@lists.anl-external.org<br>
> > http://lists.anl-external.org/cgi-bin/mailman/listinfo/dcmf<br>
> > http://dcmf.anl-external.org/wiki<br>
> _______________________________________________<br>
> dcmf mailing list<br>
> dcmf@lists.anl-external.org<br>
> http://lists.anl-external.org/cgi-bin/mailman/listinfo/dcmf<br>
> http://dcmf.anl-external.org/wiki</font></tt>