[mpiwg-sessions] Sessions WG - meet today

Rolf Rabenseifner rabenseifner at hlrs.de
Tue Mar 2 11:17:57 CST 2021


Hi Dan and all,

in the moment, it is not clear for me, what Bill and Wesley 
will do with the revert of the 7 PRs (445, 258, 484, 434, 444, 455+425).

Yes, mainly all what is not in

https://github.com/mpi-forum/mpi-issues/files/6050186/mpi40-rc-feb-21_rab.pdf
or
https://github.com/mpi-forum/mpi-issues/files/6051904/mpi40-issue435-PR547-sessions-2021-FEB-26-v1.pdf
or
the first three commits in PR540

is not a errata-style-vote, i.e., would be a no-no-vote.
 
The remaining three changes in PR519 are such after-the-meeting no-no-votes.
But they seem to be correct and the last the middle one also necessary. 

Best regards
Rolf




----- Original Message -----
> From: "Dan Holmes, MPI" <danholmes at chi.scot>
> To: "Rolf Rabenseifner" <rabenseifner at hlrs.de>
> Cc: "mpiwg-sessions" <mpiwg-sessions at lists.mpi-forum.org>
> Sent: Tuesday, March 2, 2021 5:38:28 PM
> Subject: Re: [mpiwg-sessions] Sessions WG - meet today

> HI Rolf (et al),
> 
> We should be very careful, from a procedural point-of-view, about creating new
> issues now that we are properly past the end of the voting meeting. Any issue
> created before the end of the voting meeting can be treated like an errata
> (i.e. a single vote with a majority in favour carrying the day), but all issues
> created after the voting meeting has ended must be treated as no-no-votes (i.e.
> a single vote where every voting member has a unilateral veto).
> 
> Thus: let us keep the existing crop of issues and fiddle only with the pull
> requests.
> 
> On a different note, there should be no reason to replace the existing PR either
> - we merely need to fix the branch on which it is based. I have merged the
> current mpi-4-rc branch into the branch behind PR519 and it now shows a much
> small list of changes - things that are, I guess, really not in mpi-4-rc.
> 
> Please re-check PR519 now does something we do want, nothing we don’t want, and
> addresses the issue 424 with which it is 1-to-1 associated.
> 
> Cheers,
> Dan.
>> Dr Daniel Holmes PhD
> Executive Director
> Chief Technology Officer
> CHI Ltd
> danholmes at chi.scot
> 
> 
> 
>> On 1 Mar 2021, at 21:44, Rolf Rabenseifner via mpiwg-sessions
>> <mpiwg-sessions at lists.mpi-forum.org> wrote:
>> 
>> Dear Howard and all,
>> 
>> sorry, but I saw your email too late.
>> 
>> I wrote on PR519 the same comment that I gave during the MPI Forum meeting.
>> If there are still not merged portions of PR519, then I recommend to
>> close PR519 and to start a new small PR with exactly the not yet merged
>> portions.
>> 
>> And to add a new issue for that because it is outside of the
>> PR435 + PR547 which is already read at the Feb. 2021 meeting
>> and only requires a errata-style vote on next forum meeting.
>> 
>> Best regards
>> Rolf
>> 
>> ----- Original Message -----
>>> From: "mpiwg-sessions" <mpiwg-sessions at lists.mpi-forum.org>
>>> To: "mpiwg-sessions" <mpiwg-sessions at lists.mpi-forum.org>
>>> Cc: "Pritchard" <howardp at lanl.gov>
>>> Sent: Monday, March 1, 2021 5:02:18 PM
>>> Subject: [mpiwg-sessions] Sessions WG - meet today
>> 
>>> HI All,
>>> 
>>> 
>>> 
>>> Let’s try to meet today. Items I have on the agenda:
>>> 
>>> 
>>> 
>>>   * Sort out where we are wrt issue 435 and the next release candidate
>>>   * What happened to these PRs
>>>       * [ https://github.com/mpi-forum/mpi-standard/pull/519 |
>>>       https://github.com/mpi-forum/mpi-standard/pull/519
>>>       <https://github.com/mpi-forum/mpi-standard/pull/519> ]
>>>       * [ https://github.com/mpi-forum/mpi-standard/pull/538
>>>       <https://github.com/mpi-forum/mpi-standard/pull/538> |
>>>       https://github.com/mpi-forum/mpi-standard/pull/538 ]
>>>   * MPI thread level and Sessions discussion – something for 4.1
>>>   * MPI and dynamic process model (spawn), and what about connect/accept –
>>>   something for 4.1
>>>   * Open MPI prototype update
>>>   * Other
>>> 
>>> 
>>> 
>>> 
>>> Howard
>>> 
>>> 
>>> 
>>> --
>>> 
>>> 
>>> 
>>> 
>>> Howard Pritchard
>>> 
>>> HPC-ENV
>>> 
>>> Los Alamos National Laboratory
>>> 
>>> 
>>> 
>>> 
>>> _______________________________________________
>>> mpiwg-sessions mailing list
>>> mpiwg-sessions at lists.mpi-forum.org
>>> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions
>> 
>> --
>> Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner at hlrs.de
>> <mailto: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
>> <http://www.hlrs.de/people/rabenseifner> .
>> Nobelstr. 19, D-70550 Stuttgart, Germany . . . . (Office: Room 1.307) .
>> _______________________________________________
>> mpiwg-sessions mailing list
>> mpiwg-sessions at lists.mpi-forum.org <mailto:mpiwg-sessions at lists.mpi-forum.org>
>> https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions
> > <https://lists.mpi-forum.org/mailman/listinfo/mpiwg-sessions>

-- 
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: Room 1.307) .


More information about the mpiwg-sessions mailing list