[mpiwg-hybridpm] Process -> MPI process change

Steven Oyanagi sko at cray.com
Wed Jun 8 18:05:55 CDT 2016


Hi,

Please see the branch fix_hybrid-process-clarification which should be a
branch off of hybrid-process-clarification that can be fast-forward merged
on to the hybrid-process-clarification branch.  I fixed my 100 pages, Jeff
Hammond’s commit, and part of Dan Holems’ commit.  Dan’s commit affected
two files, but oddly the second of the two files was already fixed for
“MPI” -> “\MPI/“.

Note also that I do not have the capability at this time to convert the
Tex source into a final document (not installed on my macbook) so there
might be some issues in this branch and my original commit that a format
would uncover.

Let me know if anything else needs to be done.
	- Steve

-----Original Message-----
From: Steve Oyanagi <sko at cray.com>
Date: Wednesday, June 8, 2016 at 5:04 PM
To: "mpiwg-hybridpm at lists.mpi-forum.org"
<mpiwg-hybridpm at lists.mpi-forum.org>
Subject: Re: [mpiwg-hybridpm] Process -> MPI process change

>Hi,
>
>I may have a simple way of fixing my changes which, if it works, could be
>used to fix Dan’s changes.  Let me see what I can do.
>	- Steve
>
>-----Original Message-----
>From: mpiwg-hybridpm <mpiwg-hybridpm-bounces at mpi-forum.org> on behalf of
>Jeff Hammond <jeff.science at gmail.com>
>Reply-To: "mpiwg-hybridpm at mpi-forum.org" <mpiwg-hybridpm at mpi-forum.org>
>Date: Wednesday, June 8, 2016 at 5:00 PM
>To: "mpiwg-hybridpm at mpi-forum.org" <mpiwg-hybridpm at mpi-forum.org>
>Cc: "mpiwg-hybridpm at lists.mpi-forum.org"
><mpiwg-hybridpm at lists.mpi-forum.org>
>Subject: Re: [mpiwg-hybridpm] Process -> MPI process change
>
>>mea culpa
>>
>>
>>i'll provide free coffee to whoever fixes my bug.  you can collect your
>>free coffee at any Intel campus ;-)
>>
>>
>>jeff
>>
>>
>>On Wed, Jun 8, 2016 at 2:47 PM, Steven Oyanagi
>><sko at cray.com> wrote:
>>
>>Hi,
>>
>>First off, sorry, but I probably won’t be able to get the changes done
>>today.  At this point I suspect you don’t need them for this meeting.  If
>>you do, let me know and I will try to get them done quick.
>>
>>I do note we have not be consistent about putting things in as \MPI/.  I
>>note that Jeff Hammond’s change on Mar 1 (7c911456d - change process to
>>MPI process) did not use \MPI/.  Pavan’s mod is right, it did use \MPI/.
>>Dan’s mod (12aa5e1c -  Clarification of word 'process', pages 101-200
>>from
>>Feb 5th does *not* use \MPI/, it inserts “MPI “.  It may be I looked at
>>Dan’s mod and thought it was Pavan’s.
>>        - Steve
>>
>>
>>-----Original Message-----
>>From: Pavan Balaji <balaji at anl.gov>
>>Date: Wednesday, June 8, 2016 at 2:28 PM
>>To: "mpiwg-hybridpm at lists.mpi-forum.org"
>><mpiwg-hybridpm at lists.mpi-forum.org>
>>Cc: Pavan Balaji <balaji at anl.gov>, Steve Oyanagi <sko at cray.com>
>>Subject: Re: [mpiwg-hybridpm] Process -> MPI process change
>>
>>>Steve,
>>>
>>>You should use \MPI/ in latex.
>>>
>>>  -- Pavan
>>>
>>>> On Jun 8, 2016, at 11:33 AM, Steven Oyanagi <sko at cray.com> wrote:
>>>>
>>>> Hi,
>>>>
>>>> Sorry, I was unclear in my last message.  Changes were made per the
>>>>review
>>>> of changes for pages 201-300 in previous working group meetings.  My
>>>> inquiry was about the changes to the TEX source of the MPI standard.
>>>>Did I
>>>> have to do anything unusual in the case where “MPI “ was inserted?  I
>>>>just
>>>> inserted the string “MPI “ in those cases.  MPI isn’t some special tag
>>>> that has be denoted in an different way, is it?
>>>>      - Steve
>>>>
>>>> -----Original Message-----
>>>> From: Steve Oyanagi <sko at cray.com>
>>>> Date: Wednesday, June 8, 2016 at 11:27 AM
>>>> To: "mpiwg-hybridpm at lists.mpi-forum.org"
>>>> <mpiwg-hybridpm at lists.mpi-forum.org>
>>>> Subject: Re: [mpiwg-hybridpm] Process -> MPI process change
>>>>
>>>>> Hi,
>>>>>
>>>>> I think I have the changes for 201-300 done and correctly committed
>>>>>to
>>>>>the
>>>>> branch.  Please check that I got the git stuff correct, and take a
>>>>>glance
>>>>> at my commit to make sure I didn’t forget to do something.  I assume
>>>>>in
>>>>> most cases I just had to insert “MPI “ before process.  Was I suppose
>>>>>to
>>>>> do anything else?
>>>>>
>>>>> Please let me know if further changes are needed.
>>>>>     - Steve
>>>>>
>>>>> -----Original Message-----
>>>>> From: Steve Oyanagi <sko at cray.com>
>>>>> Date: Tuesday, June 7, 2016 at 6:12 PM
>>>>> To: "mpiwg-hybridpm at lists.mpi-forum.org"
>>>>> <mpiwg-hybridpm at lists.mpi-forum.org>
>>>>> Subject: Re: [mpiwg-hybridpm] Process -> MPI process change
>>>>>
>>>>>> Hello,
>>>>>>
>>>>>> FYI - I have the changes done, just need to proof-read a bit and
>>>>>>then
>>>>>> will
>>>>>> commit, probably tonight or tomorrow morning.  Hope that’s soon
>>>>>>enough
>>>>>> for
>>>>>> you folks.
>>>>>>    - Steve
>>>>>>
>>>>>> -----Original Message-----
>>>>>> From: mpiwg-hybridpm <mpiwg-hybridpm-bounces at mpi-forum.org> on
>>>>>>behalf
>>>>>>of
>>>>>> Pavan Balaji <balaji at anl.gov>
>>>>>> Reply-To: "mpiwg-hybridpm at mpi-forum.org"
>>>>>><mpiwg-hybridpm at mpi-forum.org>
>>>>>> Date: Tuesday, June 7, 2016 at 1:46 PM
>>>>>> To: "mpiwg-hybridpm at lists.mpi-forum.org"
>>>>>> <mpiwg-hybridpm at lists.mpi-forum.org>
>>>>>> Subject: Re: [mpiwg-hybridpm] Process -> MPI process change
>>>>>>
>>>>>>> Steve,
>>>>>>>
>>>>>>> Thanks.  If you are unable to push the changes in due to access
>>>>>>>regions,
>>>>>>> you can send your patch to me.  I'll apply it.
>>>>>>>
>>>>>>> I'll try to figure out who can make the change to the reply-to
>>>>>>>field.
>>>>>>>
>>>>>>> -- Pavan
>>>>>>>
>>>>>>>> On Jun 7, 2016, at 1:38 PM, Steven Oyanagi <sko at cray.com> wrote:
>>>>>>>>
>>>>>>>> Hi Pavan,
>>>>>>>>
>>>>>>>> Sorry, I never got around to actually making the changes.  I had
>>>>>>>> problems
>>>>>>>> finding the repositories until I
>>>>>>>> discovered that I had never gotten access to them.  Since then I
>>>>>>>>ran
>>>>>>>> out
>>>>>>>> of time to work on the changes.
>>>>>>>>
>>>>>>>> Now that they are a priority, I will try to get this done quickly.
>>>>>>>> Most
>>>>>>>> of the changes are straight-forward.
>>>>>>>>
>>>>>>>> Also - E-mail from he mailing list comes with the wrong “Reply-To”
>>>>>>>> field.
>>>>>>>> I got burned by this once before (Jim Dinan graciously pointed me
>>>>>>>>to
>>>>>>>> the
>>>>>>>> right address) but I didn’t realize the issue was in the message.
>>>>>>>>I
>>>>>>>> think
>>>>>>>> the “Reply-to” field below should be
>>>>>>>> "mpiwg-hybridpm at lists.mpi-forum.org”.
>>>>>>>> Note that the address in the Reply-to field is missing the
>>>>>>>>“lists.”
>>>>>>>> part.
>>>>>>>>  - Steve
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> -----Original Message-----
>>>>>>>> From: mpiwg-hybridpm <mpiwg-hybridpm-bounces at mpi-forum.org> on
>>>>>>>>behalf
>>>>>>>> of
>>>>>>>> Pavan Balaji <balaji at anl.gov>
>>>>>>>> Reply-To: "mpiwg-hybridpm at mpi-forum.org"
>>>>>>>> <mpiwg-hybridpm at mpi-forum.org>
>>>>>>>> Date: Tuesday, June 7, 2016 at 1:19 PM
>>>>>>>> To: "mpiwg-hybridpm at lists.mpi-forum.org"
>>>>>>>> <mpiwg-hybridpm at lists.mpi-forum.org>
>>>>>>>> Subject: [mpiwg-hybridpm] Process -> MPI process change
>>>>>>>>
>>>>>>>>> Hi Steve,
>>>>>>>>>
>>>>>>>>> We had gone over your changes from "process" to "MPI process" for
>>>>>>>>> pages
>>>>>>>>> 201-300 in one of the previous telecons, but we don't see your
>>>>>>>>> changes
>>>>>>>>> in
>>>>>>>>> git.  Did you commit your changes in?  If not, can you please
>>>>>>>>>commit
>>>>>>>>> them
>>>>>>>>> as soon as possible into the
>>>>>>>>>`origin/hybrid-process-clarification`
>>>>>>>>> branch
>>>>>>>>> on git at github.com:mpiwg-hybrid/mpi-standard.git?
>>>>>>>>>
>>>>>>>>> Thanks,
>>>>>>>>>
>>>>>>>>> -- Pavan
>>>>>>>>>
>>>>>>>>> _______________________________________________
>>>>>>>>> mpiwg-hybridpm mailing list
>>>>>>>>> mpiwg-hybridpm at mpi-forum.org
>>>>>>>>> 
>>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm
>><http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm>
>>>>>>>>
>>>>>>>> _______________________________________________
>>>>>>>> mpiwg-hybridpm mailing list
>>>>>>>> mpiwg-hybridpm at mpi-forum.org
>>>>>>>> 
>>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm
>><http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm>
>>>>>>>
>>>>>>> _______________________________________________
>>>>>>> mpiwg-hybridpm mailing list
>>>>>>> mpiwg-hybridpm at mpi-forum.org
>>>>>>> 
>>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm
>><http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm>
>>>>>>
>>>>>
>>>>
>>>> _______________________________________________
>>>> mpiwg-hybridpm mailing list
>>>> mpiwg-hybridpm at mpi-forum.org
>>>> 
>>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm
>><http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm>
>>>
>>
>>_______________________________________________
>>mpiwg-hybridpm mailing list
>>mpiwg-hybridpm at mpi-forum.org
>>http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-hybridpm
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>-- 
>>Jeff Hammond
>>jeff.science at gmail.com
>>http://jeffhammond.github.io/
>>
>




More information about the mpiwg-hybridpm mailing list