<div dir="ltr">On Mon, Jul 8, 2013 at 4:16 PM, Richard Tran Mills <span dir="ltr"><<a href="mailto:rtm@eecs.utk.edu" target="_blank">rtm@eecs.utk.edu</a>></span> wrote:<br><div class="gmail_extra"><div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Hi Jed,<br>
<br>
Revisiting this now; thanks for your help so far. I understand that I can use PetscSFBcast() for this, but it is not clear to me whether there is a good way that I can make use of the "default" SF that exists (or the "default" PetscSection used to construct this). Should I just construct some other "default" for local-to-local, or is there a good way to remap the "global" vector layout onto a local one?<br>
</blockquote><div><br></div><div style>The section stuff will not help you much, because you would still need to create a mesh point SF. Its useful if you want to manage all data that way.</div><div style><br></div><div style>
Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
--Richard<br>
<br>
On 6/12/13 11:25 AM, Jed Brown wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Richard Tran Mills <<a href="mailto:rtm@eecs.utk.edu" target="_blank">rtm@eecs.utk.edu</a>> writes:<br>
<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
PETSc developers,<br>
<br>
I am finally getting around to adding the DMLocalToLocalBegin/End routines<br>
that I had mentioned several months ago. Looking at<br>
DMGlobalToLocalBegin() in src/interface/dm/dm.c, I see that a little over<br>
a year ago, Matt added the use of a default 'PetscSF' ("star forest") if<br>
present to handle the global-to-local and local-to-global operations. I<br>
am not familiar with PetscSF, but I assume that it should be possible to<br>
use these somehow (maybe needing to add a little bit of code) for<br>
local-to-local operations, since the communication pattern is the same as<br>
for a global-to-local. Could someone who is familiar with PetscSF comment<br>
on this?<br>
</blockquote>
You can use PetscSFBcast for this. For each point (which will be a leaf<br>
in star-forest terminology), set the (rank, offset) of the owner<br>
("root"). Use PetscSFSetGraph rather than PetscSFSetGraphLayout,<br>
because you don't have a global ordering/PetscLayout to use the latter.<span class="HOEnZb"><font color="#888888"><br>
</font></span></blockquote><span class="HOEnZb"><font color="#888888">
<br>
<br>
-- <br>
Richard Tran Mills, Ph.D.<br>
Computational Earth Scientist | Joint Assistant Professor<br>
Hydrogeochemical Dynamics Team | EECS and Earth & Planetary Sciences<br>
Oak Ridge National Laboratory | University of Tennessee, Knoxville<br>
E-mail: <a href="mailto:rmills@ornl.gov" target="_blank">rmills@ornl.gov</a> V: <a href="tel:865-241-3198" value="+18652413198" target="_blank">865-241-3198</a> <a href="http://climate.ornl.gov/~rmills" target="_blank">http://climate.ornl.gov/~<u></u>rmills</a><br>
<br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br>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>