<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body dir="auto">
<div>Hi</div>
<div><br>
</div>
<div>The pre-compiled CP2K binaries including all the linked in libraries were compiled without any architecture specific optimisations which allows running them on most Linux boxes. The price to pay for that compatibility is an inferior performance. These
binaries are provided primarily for testing but not production purposes.</div>
<div>Moreover, depending on the case, a larger number of threads does not result necessarily in any speed-up and 16 threads may run slower than 4 threads.</div>
<div><br>
<div>Matthias</div>
</div>
<div><br>
Am 29.08.2017 um 21:35 schrieb Faraz H <<a href="mailto:fa...@squashclub.org">fa...@squashclub.org</a>>:<br>
<br>
</div>
<blockquote type="cite">
<div>
<div dir="ltr">I am comparing the pre-compiled binary, cp2k-4.1-Linux-x86_64.ssmp with a version that was compiled with Intel 2015 compiler. The pre-compiled one seems to take 3-4X as long per iteration. I did the whole export OMP_NUM_THREADS and a top does
show the cpu usage go to 1600% ( the machine has 16 cpus ). <br>
<br>
Is it a known issue that the pre-compiled binary will be this much slower? Or is there likely something else going on?<br>
</div>
<p></p>
-- <br>
You received this message because you are subscribed to the Google Groups "cp2k" group.<br>
To unsubscribe from this group and stop receiving emails from it, send an email to
<a href="mailto:cp2k+unsu...@googlegroups.com">cp2k+unsu...@googlegroups.com</a>.<br>
To post to this group, send email to <a href="mailto:cp...@googlegroups.com">cp...@googlegroups.com</a>.<br>
Visit this group at <a href="https://groups.google.com/group/cp2k">https://groups.google.com/group/cp2k</a>.<br>
For more options, visit <a href="https://groups.google.com/d/optout">https://groups.google.com/d/optout</a>.<br>
</div>
</blockquote>
</body>
</html>