<div dir="ltr"><div>I think what you propose is in principles feasible, but I am afraid that it affects so much code that it is not going to happen anytime soon</div><div><br></div><div>Paolo<br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Apr 25, 2019 at 1:05 PM Thomas Brumme <<a href="mailto:thomas.brumme@uni-leipzig.de">thomas.brumme@uni-leipzig.de</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Dear all,<br>
<br>
I understand that the standard parallelization in QE is done via the FFTs<br>
which also results in a quite good speed up AND memory reduction.<br>
Of course, the communication between CPUs needs to be fast.<br>
<br>
Yet, why is the most important number here the 3rd dimension? Is it<br>
difficult to implement that the most important dimension is actually the<br>
largest one? Or would it be "easier" to (internally) rotate the system such<br>
that the 3rd dimension is the largest and then do the computations and<br>
rotate back?<br>
<br>
I'm asking since I have a large slab system in which z ist not the largest<br>
dimension and thus I get memory problems on the cluster. Rotating<br>
the system such that the slab is not in xy but in yz I can reduce the<br>
memory needed per task... So, I can do this manually but it would be<br>
easier if this is automatically taken care of ;)<br>
<br>
Kind regards<br>
<br>
Thomas<br>
<br>
-- <br>
Dr. rer. nat. Thomas Brumme<br>
Wilhelm-Ostwald-Institute for Physical and Theoretical Chemistry<br>
Leipzig University<br>
Phillipp-Rosenthal-Strasse 31<br>
04103 Leipzig<br>
<br>
Tel: +49 (0)341 97 36456<br>
<br>
email: <a href="mailto:thomas.brumme@uni-leipzig.de" target="_blank">thomas.brumme@uni-leipzig.de</a><br>
<br>
_______________________________________________<br>
developers mailing list<br>
<a href="mailto:developers@lists.quantum-espresso.org" target="_blank">developers@lists.quantum-espresso.org</a><br>
<a href="https://lists.quantum-espresso.org/mailman/listinfo/developers" rel="noreferrer" target="_blank">https://lists.quantum-espresso.org/mailman/listinfo/developers</a><br>
</blockquote></div><br clear="all"><br>-- <br><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div>Paolo Giannozzi, Dip. Scienze Matematiche Informatiche e Fisiche,<br>Univ. Udine, via delle Scienze 208, 33100 Udine, Italy<br>Phone +39-0432-558216, fax +39-0432-558222<br><br></div></div></div></div></div>