<div dir="ltr">Hi Philipp,<div><br></div><div>gop is a thin wrapper around mpi_allreduce:</div><div><a href="https://github.com/maxhutch/Nek5000/blob/master/comm_mpi.f#L97">https://github.com/maxhutch/Nek5000/blob/master/comm_mpi.f#L97</a><br></div><div>so it is unlikely to be causing side-effects outside of its arguments. If you post some code (better: a link to some posted code) I can take a look.</div><div><br></div><div>Max</div></div><br><div class="gmail_quote"><div dir="ltr">On Mon, Apr 18, 2016 at 8:48 AM <<a href="mailto:nek5000-users@lists.mcs.anl.gov">nek5000-users@lists.mcs.anl.gov</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div>
<div style="direction:ltr;font-family:Tahoma;color:#000000;font-size:10pt"><span style="font-size:10pt">Hi Neks,</span><br>
<div style="font-family:'Times New Roman';font-size:16px">
<div style="direction:ltr;font-family:Tahoma;font-size:10pt">
<div><br>
</div>
<div>We try to extend Nek5000 for the simulation of turbulent flows laden with evaporating droplets. We use the Nek5000-subroutine gop() for the parallel communication of our additional dispersed-phase data. However, the parallel communication with gop() causes <span style="font-size:10pt">flow
field</span><span style="font-size:10pt"> disturbances. What are the possible reasons for these disturbances? How can we avoid them?</span></div>
<div><br>
</div>
<div>Best regards, Philipp Weiss</div>
</div>
</div>
</div>
</div>
_______________________________________________<br>
Nek5000-users mailing list<br>
<a href="mailto:Nek5000-users@lists.mcs.anl.gov" target="_blank">Nek5000-users@lists.mcs.anl.gov</a><br>
<a href="https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users" rel="noreferrer" target="_blank">https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users</a><br>
</blockquote></div>