Hi,<br>Yes I've experience something similar, altough the compiler version is 9.1.036 and MKL version is 9.0. The machine is an Itanium 2.<br>Marius<br><br><div class="gmail_quote">On Wed, Sep 23, 2009 at 7:23 PM, Ondrej Marsalek <span dir="ltr"><<a href="mailto:ondrej....@gmail.com">ondrej....@gmail.com</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;"><br>
Dear all,<br>
<br>
I have found that my build of CP2K with the Intel Fortran Compiler<br>
10.1.018 and MKL 10.0.4.023 has trouble passing the tests (NaNs appear<br>
and so on). Apparently, it is miscompiled. The same setup has worked<br>
(passed all the tests) about a year. I have only updated CP2K from CVS<br>
and used a recent OpenMPI (1.3.3). I have intentionally kept the<br>
versions the same as before, to have something that is known to work.<br>
I have two questions related to that.<br>
<br>
Has anyone else experienced a similar problem?<br>
<br>
Does anyone have a tested combination of recent Intel compiler and MKL<br>
versions, perhaps together with an arch file that I could use as<br>
inspiration?<br>
<br>
Thanks for any replies,<br>
Ondrej<br>
<br>
<br>
</blockquote></div><br>