itaps-parallel entities arg. in iMeshP_push... on non-owner side?

Onkar Sahni osahni at scorec.rpi.edu
Fri Oct 3 23:45:41 CDT 2008


Karen,

I want to make sure that I understand, so I will ask this question in a
slightly different way --- what if I want to exchange tag-data for only
one entity (e0) which has copies in two parts P0 and P1, with P0 as owner,
so I understand that I call iMeshP_push... from P0 (which sends) but do I
make iMeshP_push... call on P1 or not? If so then is entities arg. empty
and if not, then when is the counter-receive of point-to-point
communication posted on non-owner side?

Please let me know if my question is not clear.

Thanks,
Onkar

> Hi, Ting.  Sorry for my slow reply.
>
> I think the entities argument should include only owned entities being
> sent.
> So for your example, part P0 includes entity e0 in its entity list.  Part
> P1, which has a copy of e0 but does not own e0, does not include e0 in its
> entities argument.
>
> I will update the interface spec.
>
> Thank you for the good question.
> Karen
>
>
>
> On 9/30/08 11:54 AM, "owner-itaps-parallel at mcs.anl.gov"
> <owner-itaps-parallel at mcs.anl.gov> wrote:
>
>> Hi, All,
>>
>> I have a question about iMeshP tag communication functions, including
>> iMeshP_pushTagsEnt, iMeshP_pushTags and etc. I think that the
>> specification is not clear. Should the involved parts provide the same
>> entities (entity copies) in calling those functions?
>>
>> For example, the specification of iMeshP_pushTagsEnt is as follows:
>>
>>  * Send tag information for specified entities, which must
>>  * already be shared.
>>  * The tag data is "pushed" from the
>>  * owner entities to all copies.
>>
>> In some situation, mesh entity e0 is shared by part P0 and P1, and the
>> owner part is P0. In calling iMeshP_pushTagsEnt(..., entities,
>> entities_size,...), part P0 sends entity e0 (included in "entities" on
>> P0)
>> to part P1, should part P1 also provide e0' (the entity copy on P1,
>> included in "entities" on P1) to receive the message?
>>
>> Please correct me if you find any problems. Thanks,
>>
>> Ting
>>
>>
>>
>>
>>
>
>
>
>





More information about the itaps-parallel mailing list