<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Tue, Apr 3, 2018 at 6:06 PM, Jed Brown <span dir="ltr"><<a href="mailto:jed@jedbrown.org" target="_blank">jed@jedbrown.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Derek Gaston <<a href="mailto:friedmud@gmail.com">friedmud@gmail.com</a>> writes:<br>
<br>
> Sounds great to me - what library do I download that we're all going to use<br>
> for managing the memory pool?  :-)<br>
><br>
> Seriously though: why doesn't MPI give us an ability to get unique tag IDs<br>
> for a given communicator?<br>
<br>
It's called a dup'd communicator.<br>
<br>
> I like the way libMesh deals with this:<br>
> <a href="https://github.com/libMesh/libmesh/blob/master/include/parallel/parallel_implementation.h#L1343" rel="noreferrer" target="_blank">https://github.com/libMesh/<wbr>libmesh/blob/master/include/<wbr>parallel/parallel_<wbr>implementation.h#L1343</a><br>
<br>
PETSc does something similar, but using attributes inside the MPI_Comm<br>
instead of as a wrapper that goes around the communicator.<br>
<br>
<a href="https://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Sys/PetscCommGetNewTag.html" rel="noreferrer" target="_blank">https://www.mcs.anl.gov/petsc/<wbr>petsc-current/docs/<wbr>manualpages/Sys/<wbr>PetscCommGetNewTag.html</a><br>
<br>
> I would definitely sign on for all of us to use the same library for<br>
> getting unique tag IDs... and then we would need a lot less communicators...<br>
<br>
Communicators should be cheap.  One per library per "size" isn't a huge<br>
number of communicators.<br>
</blockquote></div><br>And this <a href="https://experts.illinois.edu/en/publications/mpi-on-millions-of-cores">https://experts.illinois.edu/en/publications/mpi-on-millions-of-cores</a> still got published? I guess</div><div class="gmail_extra">the reviewers never wanted any more than 2K communicators ;)</div><div class="gmail_extra"><br></div><div class="gmail_extra">   Matt<br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener</div><div><br></div><div><a href="http://www.caam.rice.edu/~mk51/" target="_blank">https://www.cse.buffalo.edu/~knepley/</a><br></div></div></div></div></div>
</div></div>