itaps-parallel Notes from today's meeting

[Devine, Karen D]

>From the iMeshP header file:
   A "process" can be thought of as an MPI process. The
   number of processes can be considered to be the result of MPI_Comm_size.
   The rank of a process can be thought of as the result of MPI_Comm_rank.
   We will think in terms of processes rather than processors.  Initial
   implementations of the parallel interface will likely use MPI terminology
   directly; future implementations may accommodate other communication
   paradigms and libraries.



On 4/19/10 8:16 AM, "Tim Tautges" <tautges at mcs.anl.gov> wrote:

> I think we mean one part per rank in a communicator, which is
> inherently bound to an mpi model.
> 
> - tim
> 
> 
> On Apr 19, 2010, at 8:47 AM, Mark Beall <mbeall at simmetrix.com> wrote:
> 
>> After reading the various emails here I have a terminology question:
>> when people are referring to a "process" in the context where there
>> may be multiple threads are they saying "thread"="process" or a
>> single "process" may have multiple threads.
>> 
>> The reason for the question is that we do support multiple parts per
>> process, however we really only use this in a multithreaded context
>> where each thread gets a part, thus this could be the same as saying
>> "one part per process" in the case where "process"="thread".
>> 
>> mark
>> 
> 
>