[Trilinos-Users] [EXTERNAL] RE: Teuchos::TimeMonitor::summarize problem with local communicators
Dicharry, Will
wdichar at sandia.gov
Thu Dec 8 16:24:32 MST 2011
On 12/8/11 1:52 PM, "Mark Hoemmen" <mhoemme at sandia.gov> wrote:
>On Dec 8, 2011, at 1:30 PM, Bartlett, Roscoe A. wrote:
>> Question below ...
>>
>>>> Is there a special reason why the summarize method takes more or less
>>>> automatically the MPI_COMM_WORLD communicator.
>>>
>>> 1. Because it was a legacy interface which I got stuck supporting ;-)
>>>
>>> 2. So that summarize() works in packages that have no communicator
>>> concept (e.g., Anasazi and Belos).
>>>
>>>> I'm working with a split communicator and not all of my processes
>>>> call the summarize. Hence, some of my processes wait in front of
>>>>several
>>>> "barrier (*pComm)" calls within the summarize but the remaining
>>>> processes will never reach these barriers and my whole simulation
>>>>stops.
>>>>
>>>> An alternative would be to add a further argument to the summarize
>>>> method that includes a potential local communicator. The default can
>>>>of
>>>> course be the MPI_COMM_WORLD.
>>>
>>> This is not very hard for us to do. We may have to give the new
>>>method a
>>> different name or otherwise change the interface so as to retain
>>>backwards
>>> compatibility.
>>>
>>> I'm the person who would likely have to implement this. You are
>>>welcome to
>>> communicate with me directly regarding the urgency of this request, so
>>>that I
>>> can prioritize tasks.
>>
>> [Bartlett, Roscoe A.]
>>
>> Can you use Teuchos::Comm instead of raw MPI for this?
>
>Of course! :-) I would only use Teuchos::Comm and not raw MPI
>communicators. I just want to give the question-asker a chance to let me
>know how urgent this is and provide some interface input.
I'm not sure if it's relevant, but the question-asker mentioned using a
split communicator, which is not available in the Teuchos::Comm interface
in the 10.8 release, but *is* available in master right now (it was
implemented at the beginning of October). Without that change, you have to
go through some minor contortions to use a split communicator via
Teuchos::Comm.
-- Will
>
>mfh
>
>
>
>_______________________________________________
>Trilinos-Users mailing list
>Trilinos-Users at software.sandia.gov
>http://software.sandia.gov/mailman/listinfo/trilinos-users
More information about the Trilinos-Users
mailing list