[Mpi-forum] [EXTERNAL] July meeting

Thu Jun 21 11:20:15 CDT 2012

It's a step in the right direction, I suppose.  But I still firmly believe
we should be able to schedule this thing to be business hours, starting at
1:00 on the first day, ending at noon on the last day, which is
essentially what we all signed up for.  We've gotten to the point where
everyone's so tired by the end of the day that little useful work gets
done.  The final chapter edits are going to be mind-numbing, particularly
after the first 10 hours...

Brian

On 6/21/12 7:46 AM, "Jeff Hammond" <jhammond at alcf.anl.gov> wrote:

>The schedule has been adjusted (this morning) to go until 7:15 PM
>every night and it ends at 1 PM on Thursday.  You might want to check
>it now.
>
>Jeff
>
>On Thu, Jun 21, 2012 at 8:29 AM, Rolf Rabenseifner <rabenseifner at hlrs.de>
>wrote:
>> Rich,
>>
>> When I booked my flights many weeks ago,
>> of course, I expected that the meeting finishes at noon,
>> which is 2h30 less than you scheduled.
>>
>> Additionally, I had to take a flight that I must leave on 11:00 am.
>>
>> I hope we can do all relevant to me before 11:00 am.
>>
>> And the other days can be scheduled until 6 pm, which adds in total
>>1h45.
>>
>> If we see that we need more time, we should use on Wednesday the
>> after-dinner slot.
>>
>> Best regards
>> Rolf
>>
>> ----- Original Message -----
>>> From: "Brian W Barrett" <bwbarre at sandia.gov>
>>> To: "Main MPI Forum mailing list" <mpi-forum at lists.mpi-forum.org>
>>> Sent: Wednesday, June 20, 2012 4:03:05 PM
>>> Subject: Re: [Mpi-forum] [EXTERNAL] July meeting
>>> But that's not what we agreed to do. If we need to be more efficient
>>> with
>>> our time, then let's figure out how to. But every meeting we have an
>>> agenda that goes late in the afternoon on the last day, we had a long
>>> discussion about how we wouldn't do that when we went to four day
>>> meetings, and now we're going to 2:30 again. Which wouldn't be so bad,
>>> except that we rarely go anywhere near as late as scheduled on the
>>> last
>>> day, but I'm not willing to "guess' on that and miss the final
>>> logistics /
>>> MPI next discussions.
>>>
>>> The fact that chapter edits 1) are largely serialized and 2) have time
>>> which in no way reflects the number of changes (for example, I/O needs
>>> as
>>> much time as one-sided) suggests that either we've done something
>>> terribly
>>> wrong with the process or are bad at guessing time allocations.
>>>
>>> Either way, we should rework the schedule to conform to the meeting
>>> schedule we all agreed to when we decided to do these 4 day
>>> marathons...
>>>
>>> Brian
>>>
>>> On 6/19/12 11:34 PM, "Richard Graham" <richardg at mellanox.com> wrote:
>>>
>>> >We need to give time for all the chapter wg's to finish their work.
>>> >We
>>> >can always be flexible, and consider moving around items on the
>>> >agenda to
>>> >meet travel needs - and hope we can meet all of them.
>>> >
>>> >Rich
>>> >
>>> >-----Original Message-----
>>> >From: mpi-forum-bounces at lists.mpi-forum.org
>>> >[mailto:mpi-forum-bounces at lists.mpi-forum.org] On Behalf Of Barrett,
>>> >Brian W
>>> >Sent: Monday, June 18, 2012 4:44 PM
>>> >To: Main MPI Forum mailing list
>>> >Subject: Re: [Mpi-forum] [EXTERNAL] July meeting
>>> >
>>> >On 6/16/12 9:30 AM, "Richard Graham" <richardg at mellanox.com> wrote:
>>> >
>>> >>The first cut at the agenda for the July meeting of the Forum is
>>> >>on-line.
>>> >> As I mentioned at the last meeting, the goal of this meeting is to
>>> >> get
>>> >>the 3.0 standard ready to be released as a draft standard - all but
>>> >>the
>>> >>last vote, and perhaps a few ticket-0 minor edits before the final
>>> >>vote in Sept.
>>> >>
>>> >>PLEASE NOTE: we will start as usual at 1pm on Monday, and go through
>>> >>2:30 on THURSDAY this is the first of the meetings where we shift to
>>> >>a quarterly meeting schedule.
>>> >>
>>> >>The registration page and hotel information should also be available
>>> >>very soon final logistics are being handled.
>>> >
>>> >Is there a reason we are continuing to go until 2:30 on the last day?
>>> >Historically, we have gone until 12:00 on the final day and have only
>>> >pushed out further into Wednesday recently in order to cover the rush
>>> >for
>>> >3.0. With the extension to four days, it would be nice to return to
>>> >our
>>> >normal final day schedule so that people can attend for the full
>>> >session
>>> >and make it home that night.
>>> >
>>> >Brian
>>> >
>>> >--
>>> >  Brian W. Barrett
>>> >  Dept. 1423: Scalable System Software
>>> >  Sandia National Laboratories
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >
>>> >_______________________________________________
>>> >mpi-forum mailing list
>>> >mpi-forum at lists.mpi-forum.org
>>> >http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>>> >
>>> >_______________________________________________
>>> >mpi-forum mailing list
>>> >mpi-forum at lists.mpi-forum.org
>>> >http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>>> >
>>> >
>>>
>>>
>>> --
>>> Brian W. Barrett
>>> Dept. 1423: Scalable System Software
>>> Sandia National Laboratories
>>>
>>>
>>>
>>>
>>>
>>>
>>> _______________________________________________
>>> mpi-forum mailing list
>>> mpi-forum at lists.mpi-forum.org
>>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>>
>> --
>> Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner at hlrs.de
>> High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530
>> University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832
>> Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner
>> Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30)
>> _______________________________________________
>> mpi-forum mailing list
>> mpi-forum at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>
>
>
>-- 
>Jeff Hammond
>Argonne Leadership Computing Facility
>University of Chicago Computation Institute
>jhammond at alcf.anl.gov / (630) 252-5381
>http://www.linkedin.com/in/jeffhammond
>https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
>
>_______________________________________________
>mpi-forum mailing list
>mpi-forum at lists.mpi-forum.org
>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>
>

-- 
  Brian W. Barrett
  Dept. 1423: Scalable System Software
  Sandia National Laboratories