itaps-parallel Confusion between BOUNDARY, INTERNAL, GHOST

[Tim Tautges]

Yes.  So, I would suggest we refer to INTERFACE rather than BOUNDARY, 
since the latter is not quite right (INTERFACE implies multiple sides, 
whereas BOUNDARY doesn't).

- tim

Carl Ollivier-Gooch wrote:
> Tim Tautges wrote:
>> Hi all,
>>   I'm in the process of implementing at least part of this interface, 
>> and I think there's ambiguity about what BOUNDARY, INTERNAL, and GHOST 
>> really mean.  Namely, are these referring to processor sharing, or the 
>> relation to the skin?  That is, if an entity is on the skin of a part 
>> but not shared with another processor, is its status INTERNAL?  If so, 
>> then I think these values are mutually exclusive, which I think is an 
>> important requirement if the status is accessed with a single function.
> 
> I agree that the key thing here is relationship to other parts (I would 
> argue parts, not processors).  Either way, the three are mutually 
> exclusive.
> 
> Carl
> 

-- 
================================================================
"You will keep in perfect peace him whose mind is
   steadfast, because he trusts in you."               Isaiah 26:3

              Tim Tautges            Argonne National Laboratory
          (tautges at mcs.anl.gov)      (telecommuting from UW-Madison)
          phone: (608) 263-8485      1500 Engineering Dr.
            fax: (608) 263-4499      Madison, WI 53706