<html><body>
<p>Hi Bronis <br>
<br>
To the best of my knowledge, none of the signatories involved in asking that Ticket 140 not become part of MPI 2.2 consider it inappropriate for consideration in MPI 3.0<br>
<br>
This proposal generated real interest among Forum members and I see no reason for it to be withdrawn entirely. <br>
<br>
Thank you Erez for agreeing to defer this to 3.0. It is a relief to a number of MPI implementors that if (or when) this becomes part of the MPI standard, we will have the lead time to do it properly and test it rigorously.<br>
<br>
Dick Treumann<br>
<br>
Dick Treumann - MPI Team <br>
IBM Systems & Technology Group<br>
Dept X2ZA / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601<br>
Tele (845) 433-7846 Fax (845) 433-8363<br>
<br>
<br>
<tt>mpi-forum-bounces@lists.mpi-forum.org wrote on 06/01/2009 06:28:29 PM:<br>
<br>
> [image removed] </tt><br>
<tt>> <br>
> Re: [Mpi-forum] [Mpi-22] The const proposal - Ticket 140</tt><br>
<tt>> <br>
> Bronis R. de Supinski </tt><br>
<tt>> <br>
> to:</tt><br>
<tt>> <br>
> Main MPI Forum mailing list</tt><br>
<tt>> <br>
> 06/01/2009 06:32 PM</tt><br>
<tt>> <br>
> Sent by:</tt><br>
<tt>> <br>
> mpi-forum-bounces@lists.mpi-forum.org</tt><br>
<tt>> <br>
> Cc:</tt><br>
<tt>> <br>
> "MPI 2.2"</tt><br>
<tt>> <br>
> Please respond to "Bronis R. de Supinski", Main MPI Forum mailing list</tt><br>
<tt>> <br>
> <br>
> Erez:<br>
> <br>
> Please do not simply withdraw it. There are a substantial<br>
> portion of us who you convinced this was a good idea and<br>
> what I saw in the feedback was that some found that it<br>
> was outside the scope of 2.2. I think some of those people<br>
> still feel it is a good idea even if that is the case.<br>
> I hope you will press for 3.0.<br>
> <br>
> Bronis<br>
> <br>
> <br>
> On Mon, 1 Jun 2009, Erez Haba wrote:<br>
> <br>
> > With this feedback of my distinguish colleagues, I don't see any <br>
> point of perusing this proposal and I will be withdrawing this <br>
> ticket in the next mpi forum meeting.<br>
> ><br>
> > Thanks,<br>
> > .Erez<br>
> ><br>
> > From: mpi-22-bounces@lists.mpi-forum.org [<a href="mailto:mpi-22-">mailto:mpi-22-</a><br>
> bounces@lists.mpi-forum.org] On Behalf Of William Gropp<br>
> > Sent: Wednesday, May 27, 2009 11:37 AM<br>
> > To: MPI 2.2<br>
> > Cc: Main MPI Forum mailing list<br>
> > Subject: Re: [Mpi-22] [Mpi-forum] The const proposal - Ticket 140<br>
> ><br>
> > This is an example of why we have two votes - to give everyone a <br>
> chance to take a second look at the issues. I'll note that the <br>
> 17-10 (counting no's and abstains together) is worrisome; while a <br>
> majority vote is the rule, a good standard will make a compelling <br>
> argument for each feature.<br>
> ><br>
> > The process here would normally be to have a debate and then the <br>
> second vote. However, for MPI 2.2, we have the additional <br>
> requirements of limited scope of change to implementations - we <br>
> didn't define what that meant precisely (and that is a good thing), <br>
> but there is a strong argument that limited scope of change would <br>
> require at least a majority of implementations to agree that the <br>
> change is minor.<br>
> ><br>
> > Bill<br>
> ><br>
> > On May 27, 2009, at 12:48 PM, Erez Haba wrote:<br>
> ><br>
> ><br>
> > Hi all, I'm not really sure how to respond to this email. I will <br>
> just note that this proposal has passed 1st vote last September with<br>
> the following results.<br>
> ><br>
> > 4. Vote topic: MPI-2.2 const for C bindings, 1st vote:<br>
> > YES:<br>
> ><br>
> > 17<br>
> ><br>
> > NO:<br>
> ><br>
> > 4<br>
> ><br>
> > ABSTAIN:<br>
> ><br>
> > 6<br>
> ><br>
> > MISSED:<br>
> ><br>
> > 0<br>
> ><br>
> > Result:<br>
> ><br>
> > Ballot passed<br>
> ><br>
> ><br>
> > <a href="http://meetings.mpi-forum.org/secretary/2008/09/votes.php">http://meetings.mpi-forum.org/secretary/2008/09/votes.php</a><br>
> ><br>
> > since then we decided to postpone the 1st vote to add very few <br>
> minor correction to ticket #46 (the original proposal) and thus <br>
> created ticket #140.<br>
> ><br>
> > I believe that all the points you mention below have been <br>
> discussed in the forum meeting(s).<br>
> ><br>
> > Thanks,<br>
> > .Erez<br>
> ><br>
> > From: mpi-forum-bounces@lists.mpi-forum.org<<a href="mailto:mpi-forum-">mailto:mpi-forum-</a><br>
> bounces@lists.mpi-forum.org> [<a href="mailto:mpi-forum-bounces@lists.mpi-forum.org">mailto:mpi-forum-bounces@lists.mpi-forum.org</a><br>
> ] On Behalf Of Richard Treumann<br>
> > Sent: Wednesday, May 27, 2009 6:53 AM<br>
> > To: Main MPI Forum mailing list<br>
> > Cc: mpi-22@lists.mpi-forum.org<<a href="mailto:mpi-22@lists.mpi-forum.org">mailto:mpi-22@lists.mpi-forum.org</a>><br>
> > Subject: [Mpi-forum] The const proposal - Ticket 140<br>
> ><br>
> ><br>
> > All -<br>
> ><br>
> > The signatories of this letter represent the majority of MPI <br>
> implementors participating in the MPI Forum. We are concerned that <br>
> proposal #140 ("Add const Keyword to the C bindings") has a number <br>
> of issues which suggest delaying to MPI-3 would be appropriate.<br>
> ><br>
> > In particular, the proposal:<br>
> ><br>
> > - Is likely to pass a simple majority vote, but does not carry the<br>
> support of the majority of MPI implementors, suggesting consensus <br>
> has not been reached.<br>
> > - Changes 90+ MPI API interfaces, which is not a "trivial" change <br>
> and therefore does not meet the intent of the MPI-2.2 process.<br>
> > - Is not needed to fix any serious bug in the standard text or to <br>
> solve an issue that cannot easily be avoided by the MPI application.<br>
> > - Does not offer any demonstrable optimization opportunities for <br>
> implementation or application, but may constrain future <br>
> implementation opportunities.<br>
> ><br>
> > Therefore, we ask for your assistance in deferring proposal #140 <br>
> to the MPI-3 process, where more time can be spent assessing its impact.<br>
> ><br>
> > Thank you,<br>
> ><br>
> > - Cisco: Jeff Squires<br>
> > - Intel: Alexander Supalov & Keith Underwood<br>
> > - Sandia: Brian Barrett<br>
> > - IBM: Richard Treumann<br>
> > - QLogic: Avneesh Pant<br>
> > - UTenn: George Bosilca<br>
> > - HP: David George Solt<br>
> > - UHouston: Edgar Gabriel<br>
> > - Myricom: Patrick Geoffray<br>
> > - ORNL: Richard Graham<br>
> > - Sun: Terry Dontje<br>
> > - NEC: Hubert Ritzdorf & Jesper Traeff<br>
> ><br>
> ><br>
> ><br>
> > Dick Treumann - MPI Team<br>
> > IBM Systems & Technology Group<br>
> > Dept X2ZA / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601<br>
> > Tele (845) 433-7846 Fax (845) 433-8363<br>
> > <ATT00001.txt><br>
> ><br>
> > William Gropp<br>
> > Deputy Director for Research<br>
> > Institute for Advanced Computing Applications and Technologies<br>
> > Paul and Cynthia Saylor Professor of Computer Science<br>
> > University of Illinois Urbana-Champaign<br>
> ><br>
> ><br>
> ><br>
> ><br>
> ><br>
> ><br>
> _______________________________________________<br>
> mpi-forum mailing list<br>
> mpi-forum@lists.mpi-forum.org<br>
> <a href="http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum">http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum</a><br>
</tt></body></html>