<html>
  <head>
    <meta content="text/html; charset=windows-1252"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <p>Thank you very much. Using .re2 instead of .rea brought down<br>
      the time from 27 sec to 0.8 sec.<br>
    </p>
    <br>
    <div class="moz-cite-prefix">On Tuesday 16 May 2017 12:56 PM,
      <a class="moz-txt-link-abbreviated" href="mailto:nek5000-users@lists.mcs.anl.gov">nek5000-users@lists.mcs.anl.gov</a> wrote:<br>
    </div>
    <blockquote
      cite="mid:mailman.6722.1494932269.2967.nek5000-users@lists.mcs.anl.gov"
      type="cite">
      <meta http-equiv="content-type" content="text/html;
        charset=windows-1252">
      <div>For performance use .re2 and the latest master available on
        GitHub.</div>
      <div><br>
        On 16 May 2017, at 11:57, "<a moz-do-not-send="true"
          href="mailto:nek5000-users@lists.mcs.anl.gov">nek5000-users@lists.mcs.anl.gov</a>"
        <<a moz-do-not-send="true"
          href="mailto:nek5000-users@lists.mcs.anl.gov">nek5000-users@lists.mcs.anl.gov</a>>
        wrote:<br>
        <br>
      </div>
      <blockquote type="cite">
        <div>
          <meta http-equiv="Content-Type" content="text/html;
            charset=windows-1252">
          <meta name="Generator" content="Kopano HTML builder 1.0">
          <title></title>
          <!-- Converted from text/plain format -->
          <p><font style="font-family: courier" size="2">
              Hi Neks,<br>
              <br>
                We are carrying out an optimization study on IBM Blue
              Gene/Q server<br>
              of IDRIS using direct-adjoint method. The direct and
              adjoint equations<br>
              are solved using Nek5000. We have observed that for
              moderate to large <br>
              number of<br>
              processors  Nek5000 spends considerable time in reading
              the .rea file.<br>
              When we reduce the number of processors, the .rea file is
              read in lesser <br>
              time but<br>
              the time taken for solver increases. To give an idea, a 3D
              case for <br>
              incompressible flow<br>
              with 12000 elements spends 22.132 seconds in reading .rea
              file if we use<br>
              400 processors. If we increase the number of processors to
              1000, it <br>
              takes more than<br>
              90 seconds to read the same .rea file. Can someone provide
              us a solution on<br>
              how to make Nek read the rea file quickly? Would using
              .re2 file instead <br>
              of .rea increase<br>
              the performance considering the number of elements is not
              very large.?<br>
              I would like to mention that we are using PPLIST="MPIIO"
              in the makenek <br>
              file.<br>
              <br>
              Many thanks.<br>
              <br>
              <br>
              <br>
              _______________________________________________<br>
              Nek5000-users mailing list<br>
              <a moz-do-not-send="true"
                href="mailto:Nek5000-users@lists.mcs.anl.gov">Nek5000-users@lists.mcs.anl.gov</a><br>
              <a moz-do-not-send="true"
                href="https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users">https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users</a><br>
            </font>
          </p>
        </div>
      </blockquote>
      <br>
      <fieldset class="mimeAttachmentHeader"></fieldset>
      <br>
      <pre wrap="">_______________________________________________
Nek5000-users mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Nek5000-users@lists.mcs.anl.gov">Nek5000-users@lists.mcs.anl.gov</a>
<a class="moz-txt-link-freetext" href="https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users">https://lists.mcs.anl.gov/mailman/listinfo/nek5000-users</a>
</pre>
    </blockquote>
    <br>
  </body>
</html>