<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Dear <span lang="EN-US">Matthias,</span></p>
<p><span lang="EN-US">I'm really appreciate for your valuable
comments. Your help is very fruitful, thank you!</span></p>
<p><span lang="EN-US">Actually, where is nothing special in output
file the calculations simple freeze after the message"<br>
</span></p>
<div
class="highlight highlight-source-shell notranslate position-relative overflow-auto"
dir="auto"
style="box-sizing: border-box; position: relative !important; overflow: visible !important; margin-bottom: 16px; background-color: rgb(255, 255, 255); color: rgb(31, 35, 40); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Noto Sans", Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji"; font-size: 14px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">
<pre class="notranslate"
style="box-sizing: border-box; font-family: var(--fontStack-monospace, ui-monospace, SFMono-Regular, SF Mono, Menlo, Consolas, Liberation Mono, monospace); font-size: 11.9px; margin-top: 0px; margin-bottom: 0px; overflow-wrap: normal; padding: 16px; overflow: auto; line-height: 1.45; color: var(--fgColor-default, var(--color-fg-default)); background-color: var(--bgColor-muted, var(--color-canvas-subtle)); border-radius: 6px; word-break: normal; min-height: 52px;">HFX_MEM_INFO<span
class="pl-k"
style="box-sizing: border-box; color: var(--color-prettylights-syntax-keyword);">|</span> Est. max. program size before HFX [MiB]: 1283</pre>
<div
class="zeroclipboard-container position-absolute right-0 top-0"
style="box-sizing: border-box; position: absolute !important; top: 0px !important; right: 0px !important;"><svg
aria-hidden="true" height="16" viewBox="0 0 16 16" width="16"
data-view-component="true"
class="octicon octicon-copy js-clipboard-copy-icon m-2"><path
d="M0 6.75C0 5.784.784 5 1.75 5h1.5a.75.75 0 0 1 0 1.5h-1.5a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-1.5a.75.75 0 0 1 1.5 0v1.5A1.75 1.75 0 0 1 9.25 16h-7.5A1.75 1.75 0 0 1 0 14.25Z"></path><path
d="M5 1.75C5 .784 5.784 0 6.75 0h7.5C15.216 0 16 .784 16 1.75v7.5A1.75 1.75 0 0 1 14.25 11h-7.5A1.75 1.75 0 0 1 5 9.25Zm1.75-.25a.25.25 0 0 0-.25.25v7.5c0 .138.112.25.25.25h7.5a.25.25 0 0 0 .25-.25v-7.5a.25.25 0 0 0-.25-.25Z"></path></svg></div>
</div>
<p><span lang="EN-US">There is already a mess in different CP2K
versions and supporting libraries installed, but I'm trying to
control the situation...</span></p>
<p><span lang="EN-US">So before sending a proper output I emerged a
test using only MPI parallelization and it was always failed
when hybrid functional is used. But I swear it worked before. So
I grabbed dependency libraries form version 8 set and feed them
to version 2024. I found libint cause the problem. According to
toolchain scripts the 2.6.0 version is recommended with LMAX=5.
I took the source from libint-v2.6.0-cp2k-lmax-4.tgz traball and
compiled with options --enable-fortran --with-pic
--enable-shared and this combination seems to work in hybrid
MPI+OMP mode. Although </span><span lang="EN-US">OMP_STACKSIZE
requires to be 4 times as much with respect to version 8.</span></p>
<p><span lang="EN-US">Why CP2K is so sensitive to libint in Hybrid
functional calculations?<br>
</span></p>
<p><span lang="EN-US"><br>
</span></p>
<p><span lang="EN-US">Thank you in advance,<br>
Eugene<br>
</span></p>
<p><span lang="EN-US"><br>
</span></p>
<div class="moz-cite-prefix">On 3/20/24 16:49, Krack Matthias wrote:<br>
</div>
<blockquote type="cite"
cite="mid:ZRAP278MB0827C82560F5067265202C0BF4332@ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM">
<meta name="Generator"
content="Microsoft Word 15 (filtered medium)">
<div class="WordSection1">
<p class="MsoNormal"><span lang="DE-CH">Dear Eugene</span></p>
<p class="MsoNormal"><span lang="DE-CH"> </span></p>
<p class="MsoNormal"><span lang="EN-US">The cp2k code has been
increasingly functionalized with OpenMP directives since
version 8 including the loops in the PW part operating with
large arrays. By contrast to the GNU compiler, the Intel
compiler requires now in most cases an explicit increase of
the OMP_STACKSIZE. Your problem with the PBE0 run could have
also other reasons. Without an input/output example showing
the problem, it is difficult to provide further hints.</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">Best</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<p class="MsoNormal"><span lang="EN-US">Matthias</span></p>
<p class="MsoNormal"><span lang="EN-US"> </span></p>
<div id="mail-editor-reference-message-container">
<div>
<div>
<p class="MsoNormal">
<b><span>From: </span></b><span><a class="moz-txt-link-abbreviated" href="mailto:cp2k@googlegroups.com">cp2k@googlegroups.com</a>
<a class="moz-txt-link-rfc2396E" href="mailto:cp2k@googlegroups.com"><cp2k@googlegroups.com></a> on behalf of Eugene
<a class="moz-txt-link-rfc2396E" href="mailto:roginovicci@gmail.com"><roginovicci@gmail.com></a><br>
<b>Date: </b>Wednesday, 20 March 2024 at 13:16<br>
<b>To: </b><a class="moz-txt-link-abbreviated" href="mailto:cp2k@googlegroups.com">cp2k@googlegroups.com</a>
<a class="moz-txt-link-rfc2396E" href="mailto:cp2k@googlegroups.com"><cp2k@googlegroups.com></a><br>
<b>Subject: </b>Re: [CP2K:20045] Hybrid MPI+OpenMP is
broken in v2024.1?</span></p>
</div>
<p>Dear Matthias,</p>
<p>Thank you for advice. This guide me towards localization
of the problem.
</p>
<p>I have two testing system with the same atomic structure
but different functionals, namely common PBE and hybrid
PBE0. Both works in hybrid mode in CP2K v8 without
changing
<span lang="EN-US">OMP_STACKSIZE. In new version of CP2K
v2024.1 it become very important to set
OMP_STACKSIZE=44m.</span> for PBE model. value below 44m
will rise segfault. But for PBE0 model there is no
reasonable value to finish calculations even 1024m rise
segfault.</p>
<p>According to htop statistics I found that new 2024.1
version took more SHM (amount of shared memory used by a
task) per process -- approx 1.3 times more ~ 135 M.</p>
<p>At the same time in case of old v8 CP2K there is no
influence of
<span lang="EN-US">OMP_STACKSIZE at all. Even very small
values doesn't rise error and calculations finished
normally.</span></p>
<p><span lang="EN-US">Is there something related to
OMP_STACKSIZE in configuration of CP2K source code. Some
kind of limit or -D parameter?</span></p>
<p><span lang="EN-US">I found related unresolved issue in
mailing list:</span></p>
<p><span lang="EN-US"><a
href="https://groups.google.com/g/cp2k/c/40Ods3HYW5g"
moz-do-not-send="true" class="moz-txt-link-freetext">https://groups.google.com/g/cp2k/c/40Ods3HYW5g</a></span></p>
<p><span lang="EN-US">I made some test with different
cutoffs as well and in new 2024.1 it always crashed in
PBE0.</span></p>
<p><span lang="EN-US">Best regards,<br>
Eugene</span></p>
<div>
<p class="MsoNormal">On 3/19/24 17:02, Krack Matthias
wrote:</p>
</div>
<blockquote>
<div>
<p class="MsoNormal">
<span lang="DE-CH">HI Eugene</span></p>
<p class="MsoNormal">
<span lang="DE-CH"> </span></p>
<p class="MsoNormal">
<span lang="EN-US">If you haven’t tried yet, you can
set the environment variable OMP_STACKSIZE=64m.</span></p>
<p class="MsoNormal">
<span lang="EN-US"> </span></p>
<p class="MsoNormal">
<span lang="EN-US">HTH</span></p>
<p class="MsoNormal">
<span lang="EN-US"> </span></p>
<p class="MsoNormal">
<span lang="EN-US">Matthias</span></p>
<p class="MsoNormal">
<span lang="EN-US"> </span></p>
<div id="mail-editor-reference-message-container">
<div>
<div>
<p class="MsoNormal">
<b>From: </b><a
href="mailto:cp2k@googlegroups.com"
moz-do-not-send="true"
class="moz-txt-link-freetext">cp2k@googlegroups.com</a>
<a href="mailto:cp2k@googlegroups.com"
moz-do-not-send="true">
<cp2k@googlegroups.com></a> on behalf of
Eugene <a href="mailto:roginovicci@gmail.com"
moz-do-not-send="true">
<roginovicci@gmail.com></a><br>
<b>Date: </b>Tuesday, 19 March 2024 at 13:43<br>
<b>To: </b>cp2k <a
href="mailto:cp2k@googlegroups.com"
moz-do-not-send="true"><cp2k@googlegroups.com></a><br>
<b>Subject: </b>[CP2K:20043] Hybrid MPI+OpenMP
is broken in v2024.1?</p>
</div>
<p class="MsoNormal">
Hi, I've finally compiled CP2K v2024.1 using cmake
build system (which was a long story accompanied
with cmake modules fixing). Anyway I have two
nodes for testing based on xeon 2011 v4 processors
(-march=broadwell) running on Almalinux 9. I have
the following library compiled and installed:</p>
<div>
<p class="MsoNormal">
1. linint 2.6.0 (options are --enable-fortran
--with-pic --enable-shared as suggested in
toolchain build script)</p>
</div>
<div>
<p class="MsoNormal">
2. libxsmm-1.17 (with option INTRINSICS=1)</p>
</div>
<div>
<p class="MsoNormal">
3. libxc-6.1.0</p>
</div>
<div>
<p class="MsoNormal">
4. dbcsr-2.6.0</p>
</div>
<div>
<p class="MsoNormal">
5. Elpa </p>
</div>
<div>
<p class="MsoNormal">
</p>
</div>
<div>
<p class="MsoNormal">
Everything was build with Intel oneAPI 2023.0.0
compilator using MKL and intel MPI libraries. <br>
The compiled binary cp2k.psmp works quite well
in MPI mode (OMP_NUM_THREADS=1), but hybrid mode
filed to run properly. A can see the general MPI
processe do fire up OMP threads as necessary at
the beginning, the calculations run and make
initialization unless "SCF WAVEFUNCTION
OPTIMIZATION" starts. There is no debug
information except message about Segmentation
fault which rise termination of mpi process on
child node. I spent hours to localize the
problem but I'm pretty sure this is not due to
node configuration since old v8.2 version do
works in hybrid mode even being compiled with
older intel compilator.</p>
</div>
<div>
<p class="MsoNormal">
</p>
</div>
<div>
<p class="MsoNormal">
Any hints are very welcome,<br>
Eugene</p>
</div>
<div>
<p class="MsoNormal">
</p>
</div>
<p class="MsoNormal">
-- <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+unsubscribe@googlegroups.com"
moz-do-not-send="true"
class="moz-txt-link-freetext">cp2k+unsubscribe@googlegroups.com</a>.<br>
To view this discussion on the web visit <a
href="https://groups.google.com/d/msgid/cp2k/52bbc3d3-e857-4f21-a33f-aa42e30d106an%40googlegroups.com?utm_medium=email&utm_source=footer"
moz-do-not-send="true">
https://groups.google.com/d/msgid/cp2k/52bbc3d3-e857-4f21-a33f-aa42e30d106an%40googlegroups.com</a>.</p>
</div>
</div>
</div>
<p class="MsoNormal">-- <br>
You received this message because you are subscribed to
a topic in the Google Groups "cp2k" group.<br>
To unsubscribe from this topic, visit <a
href="https://groups.google.com/d/topic/cp2k/TFgAsWkpnW0/unsubscribe"
moz-do-not-send="true" class="moz-txt-link-freetext">
https://groups.google.com/d/topic/cp2k/TFgAsWkpnW0/unsubscribe</a>.<br>
To unsubscribe from this group and all its topics, send
an email to <a
href="mailto:cp2k+unsubscribe@googlegroups.com"
moz-do-not-send="true" class="moz-txt-link-freetext">
cp2k+unsubscribe@googlegroups.com</a>.<br>
To view this discussion on the web visit <a
href="https://groups.google.com/d/msgid/cp2k/ZRAP278MB08278F9087D15079913994C1F42C2%40ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM?utm_medium=email&utm_source=footer"
moz-do-not-send="true">
https://groups.google.com/d/msgid/cp2k/ZRAP278MB08278F9087D15079913994C1F42C2%40ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM</a>.</p>
</blockquote>
<p class="MsoNormal">-- <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+unsubscribe@googlegroups.com"
moz-do-not-send="true" class="moz-txt-link-freetext">cp2k+unsubscribe@googlegroups.com</a>.<br>
To view this discussion on the web visit <a
href="https://groups.google.com/d/msgid/cp2k/b7c23615-29ca-474d-884e-f861eef46093%40gmail.com?utm_medium=email&utm_source=footer"
moz-do-not-send="true">
https://groups.google.com/d/msgid/cp2k/b7c23615-29ca-474d-884e-f861eef46093%40gmail.com</a>.</p>
</div>
</div>
</div>
-- <br>
You received this message because you are subscribed to a topic in
the Google Groups "cp2k" group.<br>
To unsubscribe from this topic, visit <a
href="https://groups.google.com/d/topic/cp2k/TFgAsWkpnW0/unsubscribe"
moz-do-not-send="true" class="moz-txt-link-freetext">https://groups.google.com/d/topic/cp2k/TFgAsWkpnW0/unsubscribe</a>.<br>
To unsubscribe from this group and all its topics, send an email
to <a href="mailto:cp2k+unsubscribe@googlegroups.com"
moz-do-not-send="true" class="moz-txt-link-freetext">cp2k+unsubscribe@googlegroups.com</a>.<br>
To view this discussion on the web visit <a
href="https://groups.google.com/d/msgid/cp2k/ZRAP278MB0827C82560F5067265202C0BF4332%40ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM?utm_medium=email&utm_source=footer"
moz-do-not-send="true">https://groups.google.com/d/msgid/cp2k/ZRAP278MB0827C82560F5067265202C0BF4332%40ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM</a>.<br>
</blockquote>
</body>
</html>
<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+unsubscribe@googlegroups.com">cp2k+unsubscribe@googlegroups.com</a>.<br />
To view this discussion on the web visit <a href="https://groups.google.com/d/msgid/cp2k/7cdacb12-cb1e-4f56-9c1f-268b98e7b77c%40gmail.com?utm_medium=email&utm_source=footer">https://groups.google.com/d/msgid/cp2k/7cdacb12-cb1e-4f56-9c1f-268b98e7b77c%40gmail.com</a>.<br />