[mpi3-coll] [Mpi-forum] MPI_Comm_create_group Meeting

Bronis R. de Supinski bronis at llnl.gov
Thu Dec 8 19:32:24 CST 2011


Jim:

The new ticket looks fine to me. I suggest we move it
forward so we can have a reading in January (maybe some
others can review it before the telecon). The updated
PDF also looks fine. I was wondering if we have strong
enough language on ordering requirements but I have
convinced myself that the words with the tags discussion
are sufficient.

Bronis



On Thu, 8 Dec 2011, Jim Dinan wrote:

> Hi Bronis,
>
> Thanks very much for the feedback.  I've created a ticket (#305) with
> some initial text for MPI_Intercomm_create:
>
> https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/305
>
> I updated the MPI_Comm_create_group text with your corrections and also
> made some additional updates to the tags paragraph (page 228, line 12)
> to hopefully address a few other questions I got off-list.  A new PDF is
> attached.  I'd appreciate a second look if you have time.
>
> Thanks,
>  ~Jim.
>
> On 12/7/11 9:00 PM, Bronis R. de Supinski wrote:
>>
>> Jim:
>>
>> I think it would be good to create a companion ticket to make
>> MPI_Intercomm_create use the tag space. We should get that
>> ticket ready now (I expect it is just a few lines of change)
>> so that it will be in MPI 3.0, assuming ticket 286 passes.
>>
>> Anyway, please change:
>>
>> "new intracommunicator, newcomm, whose communication group is defined by
>> the group argument."
>>
>> to:
>>
>> "new intracommunicator, newcomm, for which the group argument defines
>> the communication group."
>>
>> Also, please change:
>>
>> "to order calls and/or use different tag arguments"
>>
>> to
>>
>> "to order calls and/or to use differenttag arguments"
>>
>> Bronis
>>
>>
>>
>> On Wed, 7 Dec 2011, Jim Dinan wrote:
>>
>>> Hi All,
>>>
>>> I've updated the text with feedback from the last meeting, adding text
>>> to define a collective tag space. Please take a look at the ticket286
>>> edits in the attached PDF and send any feedback.
>>>
>>> Also, I'd like to have another conference call early next week to
>>> discuss and get ready for a reading in January. Please fill in your
>>> availability on the doodle poll:
>>>
>>> http://www.doodle.com/yx5b2f5f5hwc2qzq
>>>
>>> Thanks,
>>> ~Jim.
>>>
>>> On 11/8/11 3:57 PM, James Dinan wrote:
>>>> Hi All,
>>>>
>>>> Notes from yesterday's meeting are attached. Please note that we are
>>>> moving all future discussion of this ticket to the mpi3-coll mailing
>>>> list.
>>>>
>>>> Best,
>>>> ~Jim.
>>>>
>>>> In attendance:
>>>>
>>>> Adam Moody, David Goodell, Jim Dinan, Pavan Balaji, Fab Tiller, Bronis
>>>> de Supinski, Jeff Hammond
>>>>
>>>> Item 1: Name of the routine.
>>>>
>>>> We decided to stick with MPI_Comm_create group as the best way of
>>>> matching the MPI_CLASS_ACTION_SUBSET naming convention.
>>>>
>>>> Item 2: Tag versus color.
>>>>
>>>> We decided to use a tag, which is defined to be in a collective tag
>>>> space that is distinct from the point-to-point tag space. The collective
>>>> tag will follow all MPI tag semantics, however it will not conflict with
>>>> any point-to-point tags (including MPI_ANY_TAG). This essentially
>>>> exposes the expected implementation in the standard, providing more
>>>> flexible semantics to the user. In addition, it allows an implementation
>>>> to make more efficient use of the tag space by defining tag conflicts
>>>> across tagged collective operations (currently only MPI_Intercomm_create
>>>> and MPI_Comm_create_group, but we could define others in the future).
>>>>
>>>> In a separate ticket, we can update MPI_Intercomm_create to specify that
>>>> its tag is also in the collective tag space. This will be backward
>>>> compatible, but will make MPI_Intercomm_create considerably easier to
>>>> use because its tags will no longer conflict with point-to-point
>>>> operations.
>>>>
>>>> Tasks:
>>>>
>>>> * Jim will work on a revision of the text that follows the above
>>>> semantics.
>>>>
>>>> * The group will reconvene after Thanksgiving to review new text.
>>>>
>>>> * The group will move discussion to the collectives mailing list.
>>>>
>>>>
>>>> On 11/4/11 11:07 AM, James Dinan wrote:
>>>>> Based on the doodle poll, it looks like Monday at 3pm CT will be the
>>>>> best time to meet. We'll use the hybrid WG telecon bridge:
>>>>>
>>>>> Domestic dial number: 866-654-6744
>>>>> International dial number: 517-308-8226
>>>>> Passcode: 6086006
>>>>>
>>>>> See you then,
>>>>> ~Jim.
>>>>>
>>>>> On 11/1/11 2:33 PM, James Dinan wrote:
>>>>>> Hi All,
>>>>>>
>>>>>> I would like to form a group to review the MPI_Comm_create_group()
>>>>>> proposal (#286) for a formal reading at the next Forum meeting. If you
>>>>>> are interested in joining the discussion, could you please fill in
>>>>>> your
>>>>>> availability for a one hour conference call next week:
>>>>>>
>>>>>> http://www.doodle.com/9tganzq2hqiqy7kt
>>>>>>
>>>>>> We have a couple issues to discuss:
>>>>>>
>>>>>> 1.) The name of the function: MPI_Comm_create_group,
>>>>>> MPI_Group_comm_create, MPI_Comm_create_from_group, ...
>>>>>>
>>>>>> 2.) The tag argument: Should we use a tag or a "color" to establish a
>>>>>> safe communication conduit on the parent communicator. As discussed at
>>>>>> the Forum, using a tag could conflict with the use of MPI_ANY_TAG
>>>>>> on the
>>>>>> parent communicator. A color would avoid this issue, however it could
>>>>>> complicate tag matching.
>>>>>>
>>>>>> 3.) Changes to the text.
>>>>>>
>>>>>> Thanks,
>>>>>> ~Jim.
>>>>>>
>>>>>> PS- I've attached a copy of the current text with comments from the
>>>>>> formal reading at the last Forum meeting (in Acrobat: Comments ->
>>>>>> Comments View -> Show Comments List for the full list).
>>>>>>
>>>>>>
>>>>>> _______________________________________________
>>>>>> 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
>>>> _______________________________________________
>>>> mpi-forum mailing list
>>>> mpi-forum at lists.mpi-forum.org
>>>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>>>
>>
>>
>> _______________________________________________
>> mpi3-coll mailing list
>> mpi3-coll at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-coll
>


More information about the mpiwg-coll mailing list