<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<div class="moz-cite-prefix">Another note, there seem to be problems
using FFTW interface of MKL<br>
</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">export MKL_DEBUG_CPU_TYPE=5</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">with AMD cpus. To get around this
problem, one hast to additionally set</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">export MKL_CBWR=AUTO</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">Kind regards,</div>
<div class="moz-cite-prefix">Tobias</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">On 2/3/20 8:46 AM, Tobias Kloeffel
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:5dd716a5-520a-ee22-4ee7-d4705b638310@fau.de">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<div class="moz-cite-prefix">Recently I played around with some
AMD EPYC cpus and the bad thing is that I also saw some strange
numbers when using libflame/aocl 2.1.</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">The 'workaround' is probably to just
use Intel's MKL. Since version 2020 the MKL performs rather well
when using AMD cpus, however, if you want to get the best
performance you have to additionally set:<br>
</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">export MKL_DEBUG_CPU_TYPE=5<br>
</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">which gives an additional 10-20%
speedup with MKL 2020, while for earlier versions the speedup is
greater than 200%</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">Kind regards,</div>
<div class="moz-cite-prefix">Tobias</div>
<div class="moz-cite-prefix"><br>
</div>
<div class="moz-cite-prefix">On 2/2/20 10:57 PM, Paolo Giannozzi
wrote:<br>
</div>
<blockquote type="cite"
cite="mid:CAPMgbCsAiTK+wmcBvGxbSVLgqWpbrTnany-AO4X4cAy4j9pH1Q@mail.gmail.com">
<div dir="ltr">
<div dir="ltr">On Sun, Feb 2, 2020 at 10:23 PM Evgeny
Permyakov <<a href="mailto:permeakra@gmail.com"
moz-do-not-send="true">permeakra@gmail.com</a>> wrote:</div>
<div dir="ltr"><br>
</div>
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0px 0px 0px
0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">
<div dir="ltr">sidenote: I had to set
**orte_execute_quiet = true** in
~/.openmpi/mca-params.conf so mpi didn't mess with extra
messages<br>
</div>
</blockquote>
<div><br>
</div>
<div>thank you for this useful piece of information: I got
rid of those annoying messages<br>
</div>
<div><br>
</div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px
0.8ex;border-left:1px solid
rgb(204,204,204);padding-left:1ex">
<div dir="ltr">I don't use epw in my work and pwscf tests
work just fine, but the fact that some tests failed
bother me. Should I investigate it further and how? I'm
not versed in QE code, I'm a humble user.</div>
</blockquote>
<div> </div>
<div>investigating further would be a good thing, but it is
not easy: one has to figure out which piece of code fails,
then why. Even if one succeeds, very often the problem is
in the library itself and there is nothing that can be
done.<br>
</div>
<div><br>
</div>
<div>Frequent offenders are complex-valued routines (e.g.
zdotc) that seem to follow two different incompatible
conventions, but the symptom is a hard crash, not a wrong
number. <br>
</div>
<br clear="all">
</div>
Paolo<br>
<div>-- <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>
</div>
</div>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<pre class="moz-quote-pre" wrap="">_______________________________________________
Quantum ESPRESSO is supported by MaX (<a class="moz-txt-link-abbreviated" href="http://www.max-centre.eu/quantum-espresso" moz-do-not-send="true">www.max-centre.eu/quantum-espresso</a>)
users mailing list <a class="moz-txt-link-abbreviated" href="mailto:users@lists.quantum-espresso.org" moz-do-not-send="true">users@lists.quantum-espresso.org</a>
<a class="moz-txt-link-freetext" href="https://lists.quantum-espresso.org/mailman/listinfo/users" moz-do-not-send="true">https://lists.quantum-espresso.org/mailman/listinfo/users</a></pre>
</blockquote>
<p><br>
</p>
<pre class="moz-signature" cols="72">--
M.Sc. Tobias Klöffel
=======================================================
HPC (High Performance Computing) group
Erlangen Regional Computing Center(RRZE)
Friedrich-Alexander-Universität Erlangen-Nürnberg
Martensstr. 1
91058 Erlangen
Room: 1.133
Phone: +49 (0) 9131 / 85 - 20101
=======================================================
E-mail: <a class="moz-txt-link-abbreviated" href="mailto:tobias.kloeffel@fau.de" moz-do-not-send="true">tobias.kloeffel@fau.de</a></pre>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<pre class="moz-quote-pre" wrap="">_______________________________________________
Quantum ESPRESSO is supported by MaX (<a class="moz-txt-link-abbreviated" href="http://www.max-centre.eu/quantum-espresso">www.max-centre.eu/quantum-espresso</a>)
users mailing list <a class="moz-txt-link-abbreviated" href="mailto:users@lists.quantum-espresso.org">users@lists.quantum-espresso.org</a>
<a class="moz-txt-link-freetext" href="https://lists.quantum-espresso.org/mailman/listinfo/users">https://lists.quantum-espresso.org/mailman/listinfo/users</a></pre>
</blockquote>
<p><br>
</p>
<pre class="moz-signature" cols="72">--
M.Sc. Tobias Klöffel
=======================================================
HPC (High Performance Computing) group
Erlangen Regional Computing Center(RRZE)
Friedrich-Alexander-Universität Erlangen-Nürnberg
Martensstr. 1
91058 Erlangen
Room: 1.133
Phone: +49 (0) 9131 / 85 - 20101
=======================================================
E-mail: <a class="moz-txt-link-abbreviated" href="mailto:tobias.kloeffel@fau.de">tobias.kloeffel@fau.de</a></pre>
</body>
</html>