<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
  </head>
  <body text="#000000" bgcolor="#FFFFFF">
    <p>Hi Erik,</p>
    <p>thanks for your quick reply. I'm not so worried about the error,
      it actually seems to be an MPI issue, even though MPI worked fine
      on the smaller cluster. Hopefully it isn't a pain to fix.<br>
    </p>
    <p>What I really want to know is the difference between the standard
      lapacke and intel's mkl one. Is the only difference between the
      two, if all I used before was functions defined in lapacke.h, to
      replace this with mkl_lapacke.h? The code seems to run fine with
      only this change, but I remember seeing somewhere standard lapack
      function calls but with mkl__ appended at the front. I want to
      know if I should also modify these function calls as well to make
      proper use of the mkl. The mkl_lapacke.h header file itself
      doesn't seem very insightful.<br>
    </p>
    <p>I can't seem to find much useful documentation on this through
      google...</p>
    <p>Cheers,</p>
    <p>Chris<br>
    </p>
    <br>
    <div class="moz-cite-prefix">On 03/24/2018 04:50 PM, Erik Schnetter
      wrote:<br>
    </div>
    <blockquote type="cite"
cite="mid:CADKQjjf6YF_uh=iWk0-u+=ULVHxBSkuK9WMg_wjV979Bem74jQ@mail.gmail.com">
      <div>
        <div dir="auto">Chris</div>
        <div dir="auto"><br>
        </div>
        <div dir="auto">Can you say what is actually going wrong? We
          need to see an error message or similar to help out.</div>
        <div dir="auto"><br>
        </div>
        <div dir="auto">-erik</div>
        <br>
        <div class="gmail_quote">
          <div>On Sat, Mar 24, 2018 at 03:38 Chris Stevens &lt;<a
              href="mailto:c.stevens@ru.ac.za" moz-do-not-send="true">c.stevens@ru.ac.za</a>&gt;
            wrote:<br>
          </div>
          <blockquote class="gmail_quote" style="margin:0 0 0
            .8ex;border-left:1px #ccc solid;padding-left:1ex">
            <div text="#000000" bgcolor="#FFFFFF">
              <p>Hi everyone,</p>
              <p>I have just ported my code from a local cluster to
                larger one which uses intel mkl and wanted to clarify
                the changes I've made are the correct ones wrt the
                lapacke library:</p>
              <p>-- In the local cluster, I had the option <br>
              </p>
              <p>LAPACK_LIBS = lapack lapacke in my .ini file</p>
              <p>and used #include "lapacke.h" in the code.<br>
              </p>
              <p>-- In the bigger cluster, I now have to use intel mkl,
                and I have the following options in my .cfg<br>
              </p>
              <p>LAPACK_DIRĀ  =
                /apps/compilers/intel/parallel_studio_xe_2016/mkl/lib/intel64</p>
              <p>LAPACK_LIBS = -mkl</p>
              <p>which will only compile my code if I replace #include
                "lapacke.h" with #include "mkl_lapacke.h".</p>
              <p>Question: Is this the right way to generalise to mkl
                lapacke?<br>
              </p>
              <p>Problem: The code runs fine on the local cluster, but
                breaks (not obvious where) on the larger one with the
                above changes. The lapacke functions seem to work OK at
                a glance, but seeing as this is the only thing that has
                changed this may still be the culprit. <br>
              </p>
              <p>Question: Do I perhaps need to change the lapacke
                function calls also? The mkl_lapacke.h header file
                doesn't seem to give much insight... I think I remember
                seeing somewhere calls replaced something like <br>
              </p>
              <p>LAPACKE_dgels -&gt; MKL_LAPACKE_dgels</p>
              <p>Thanks!</p>
              <p>Chris<br>
              </p>
              <div class="m_6846868189903482482moz-signature">-- <br>
                <font color="#666666" face="Cantarell" size="-1">Dr
                  Chris Stevens<br>
                  <br>
                  Claude Leon Postdoctoral Fellow<br>
                </font>
                <div class="m_6846868189903482482moz-signature">
                  <div class="m_6846868189903482482moz-signature">
                    <div class="m_6846868189903482482moz-signature"> <font
                        color="#666666" face="Cantarell" size="-1"> </font>
                      <p><font color="#666666" face="Cantarell"
                          size="-1">Department of Mathematics</font></p>
                      <font color="#666666" face="Cantarell" size="-1">
                      </font>
                      <p><font color="#666666" face="Cantarell"
                          size="-1">Rhodes University</font></p>
                      <p><font color="#666666"><font size="-1"><font
                              face="Cantarell">Room 5</font></font></font></p>
                      <p><font color="#666666"><font size="-1"><font
                              face="Cantarell"> Ph: +27 46 603 8932</font></font></font></p>
                      <p><font color="#666666"><font size="-1"><font
                              face="Cantarell">Web: <a
                                href="http://www.chrisdoesmaths.com"
                                target="_blank" moz-do-not-send="true">www.chrisdoesmaths.com</a></font></font></font></p>
                    </div>
                  </div>
                </div>
              </div>
            </div>
            _______________________________________________<br>
            Users mailing list<br>
            <a href="mailto:Users@einsteintoolkit.org" target="_blank"
              moz-do-not-send="true">Users@einsteintoolkit.org</a><br>
            <a
              href="http://lists.einsteintoolkit.org/mailman/listinfo/users"
              rel="noreferrer" target="_blank" moz-do-not-send="true">http://lists.einsteintoolkit.org/mailman/listinfo/users</a><br>
          </blockquote>
        </div>
      </div>
      -- <br>
      <div dir="ltr" class="gmail_signature"
        data-smartmail="gmail_signature">
        <div dir="ltr">
          <div>Erik Schnetter &lt;<a href="mailto:schnetter@cct.lsu.edu"
              target="_blank" moz-do-not-send="true">schnetter@cct.lsu.edu</a>&gt;<br>
            <a
              href="http://www.perimeterinstitute.ca/personal/eschnetter/"
              target="_blank" moz-do-not-send="true">http://www.perimeterinstitute.ca/personal/eschnetter/</a></div>
          <div><br>
          </div>
        </div>
      </div>
    </blockquote>
    <br>
    <div class="moz-signature">-- <br>
      <font color="#666666" face="Cantarell" size="-1">Dr Chris Stevens<br>
        <br>
        Claude Leon Postdoctoral Fellow<br>
      </font>
      <div class="moz-signature">
        <div class="moz-signature">
          <div class="moz-signature"> <font color="#666666"
              face="Cantarell" size="-1"> </font>
            <p><font color="#666666" face="Cantarell" size="-1">Department
                of Mathematics</font></p>
            <font color="#666666" face="Cantarell" size="-1"> </font>
            <p><font color="#666666" face="Cantarell" size="-1">Rhodes
                University</font></p>
            <p><font color="#666666"><font size="-1"><font
                    face="Cantarell">Room 5</font></font></font></p>
            <p><font color="#666666"><font size="-1"><font
                    face="Cantarell"> Ph: +27 46 603 8932</font></font></font></p>
            <p><font color="#666666"><font size="-1"><font
                    face="Cantarell">Web: <a moz-do-not-send="true"
                      href="http://www.chrisdoesmaths.com">www.chrisdoesmaths.com</a></font></font></font></p>
          </div>
        </div>
      </div>
    </div>
  </body>
</html>