<div dir="ltr">Thank you Axel,<br>I can avoid this warning with linking to espresso's self lapack package. But it seems too slow than mkl library<br>I am trying to upgrade my mkl library to the latest, and test whether it will give this warning .<br>
<br>Thank you again for this long explanation .<br><br><div class="gmail_quote">On Mon, Jul 28, 2008 at 4:33 AM, Axel Kohlmeyer <span dir="ltr"><<a href="mailto:akohlmey@cmm.chem.upenn.edu">akohlmey@cmm.chem.upenn.edu</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">On Sun, 27 Jul 2008, Stefano Baroni wrote:<br>
<br>
SB> Ian haping:<br>
SB><br>
SB> >this warning originates from MKL. you have to check out intel's support<br>
SB> >forums for MKL or contact intel support to get help or an explanation<br>
SB> >for that.<br>
SB><br>
SB> probably, people in this mailing list will like to learn about the<br>
SB> information you get<br>
<br>
hi stefano,<br>
<br>
i stuffed the warning into google and it looks as if this<br>
originates from incorrect linking, e.g. by trying to link<br>
a static library as dynamic. without digging too deep into<br>
the technical details it looks as if this would happen when<br>
an old x86_64 compiler executable would be used on a too<br>
new installation or similarly related software that may mess<br>
with dynamic and static linkage of libraries (e.g. MPI).<br>
the error shows up on a large number of quite unrelated<br>
software packages.<br>
<br>
it is essentially a user error... and it has to be taken seriously<br>
since the affected functionality will not work. with large libraries<br>
like MKL it is impossible to predict whether some low level<br>
function is needed or not. if the calculation continues it would<br>
be worse than getting a straight crash as one cannot know whether<br>
there is some data corrupted or operations not performed and thus<br>
the resulting data dependable or not.<br>
<br>
cheers,<br>
axel.<br>
<br>
<br>
<br>
SB><br>
SB> cheers - SB<br>
SB><br>
SB> ><br>
SB><br>
SB> ---<br>
<div class="Ih2E3d">SB> Stefano Baroni - SISSA & DEMOCRITOS National Simulation Center - Trieste<br>
</div>SB> <a href="http://www.sissa.it/%7Ebaroni" target="_blank">http://www.sissa.it/~baroni</a> / [+39] 040 3787 406 (tel) -528 (fax) /<br>
SB> stefanobaroni (skype)<br>
SB><br>
SB> La morale est une logique de l'action comme la logique est une morale de la<br>
SB> pensée - Jean Piaget<br>
SB><br>
SB> Please, if possible, don't send me MS Word or PowerPoint attachments<br>
SB> Why? See: <a href="http://www.gnu.org/philosophy/no-word-attachments.html" target="_blank">http://www.gnu.org/philosophy/no-word-attachments.html</a><br>
SB><br>
SB><br>
SB><br>
SB><br>
SB><br>
SB><br>
SB><br>
<div><div></div><div class="Wj3C7c"><br>
--<br>
=======================================================================<br>
Axel Kohlmeyer <a href="mailto:akohlmey@cmm.chem.upenn.edu">akohlmey@cmm.chem.upenn.edu</a> <a href="http://www.cmm.upenn.edu" target="_blank">http://www.cmm.upenn.edu</a><br>
Center for Molecular Modeling -- University of Pennsylvania<br>
Department of Chemistry, 231 S.34th Street, Philadelphia, PA 19104-6323<br>
tel: 1-215-898-1582, fax: 1-215-573-6233, office-tel: 1-215-898-5425<br>
=======================================================================<br>
If you make something idiot-proof, the universe creates a better idiot.</div></div><br>_______________________________________________<br>
Pw_forum mailing list<br>
<a href="mailto:Pw_forum@pwscf.org">Pw_forum@pwscf.org</a><br>
<a href="http://www.democritos.it/mailman/listinfo/pw_forum" target="_blank">http://www.democritos.it/mailman/listinfo/pw_forum</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>Hai-Ping Lan <br>Department of Electronics ,<br>Peking University , Bejing, 100871<br><a href="mailto:lanhaiping@gmail.com">lanhaiping@gmail.com</a>, <a href="mailto:hplan@pku.edu.cn">hplan@pku.edu.cn</a><br>
</div>