<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
  <head>
    <meta content="text/html; charset=ISO-8859-1"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#ffffff" text="#000000">
    I tested various combinations, for the error.
    <br>
    <br>
    It appears only in this combination:
    <br>
    <br>
    * debugging configuration
    <br>
    * MKL
    blas/lapack (but not blacs and scalapack!)<br>
    * development branch
    <br>
    <br>
    The release configuration, reference blas/lapack installation or
    petsc-3.2-p5 do not have the problem.
    <br>
    <br>
    Regards,<br>
    Alexander<br>
    <br>
    On 11.01.2012 19:55, Matthew Knepley wrote:
    <blockquote
cite="mid:CAMYG4G=wAZN7ctnpLVQZr08ivMZtoPrJGJ4pFvpw21HPP_7xAA@mail.gmail.com"
      type="cite">On Wed, Jan 11, 2012 at 11:10 AM, Alexander Grayver <span
        dir="ltr"><<a moz-do-not-send="true"
          href="mailto:agrayver@gfz-potsdam.de">agrayver@gfz-potsdam.de</a>></span>
      wrote:<br>
      <div class="gmail_quote">
        <blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt
          0.8ex; border-left: 1px solid rgb(204, 204, 204);
          padding-left: 1ex;">
          <div bgcolor="#ffffff" text="#000000"> The error still happens
            if I configure and make with the following line:<br>
            <br>
            ./configure --with-petsc-arch=openmpi-intel-complex-debug-c
            --with-mpi-dir=/opt/mpi/intel/openmpi-1.4.2
            --with-scalar-type=complex
            --with-blas-lapack-dir=/opt/intel/Compiler/11.1/072/mkl/lib/em64t
            --with-precision=double<br>
          </div>
        </blockquote>
        <div><br>
        </div>
        <div>This sounds like a problem with the MKL install. Are the
          complex routines there and not just stubs? Is that</div>
        <div>the correct set of libraries for this machine?</div>
        <div><br>
        </div>
        <div>   Matt</div>
        <div> </div>
        <blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt
          0.8ex; border-left: 1px solid rgb(204, 204, 204);
          padding-left: 1ex;">
          <div bgcolor="#ffffff" text="#000000"> And disappears with the
            following one:<br>
            <br>
            ./configure --with-petsc-arch=openmpi-intel-complex-debug-c
            --with-mpi-dir=/opt/mpi/intel/openmpi-1.4.2
            --with-scalar-type=complex --download-blas-lapack
            --with-precision=double<br>
            <br>
            What could that mean?<br>
            <br>
            Regards,<br>
            Alexander<br>
            <br>
            On 10.01.2012 20:29, Matthew Knepley wrote:
            <blockquote type="cite">On Tue, Jan 10, 2012 at 4:27 AM,
              Alexander Grayver <span dir="ltr"><<a
                  moz-do-not-send="true"
                  href="mailto:agrayver@gfz-potsdam.de" target="_blank">agrayver@gfz-potsdam.de</a>></span>
              wrote:<br>
              <div class="gmail_quote">
                <blockquote class="gmail_quote" style="margin: 0pt 0pt
                  0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204);
                  padding-left: 1ex;">
                  <div bgcolor="#ffffff" text="#000000"> Can I do
                    something about that I should I wait for patch?<br>
                  </div>
                </blockquote>
                <div><br>
                </div>
                <div>I was not being direct enough. I want you to
                  repeatedly reconfigure and run until you find the</div>
                <div>offending package. We still cannot get this to
                  fail.</div>
                <div><br>
                </div>
                <div>   Matt</div>
                <br>
              </div>
            </blockquote>
          </div>
        </blockquote>
      </div>
      <br>
      <br clear="all">
      <div><br>
      </div>
      -- <br>
      What most experimenters take for granted before they begin their
      experiments is infinitely more interesting than any results to
      which their experiments lead.<br>
      -- Norbert Wiener<br>
    </blockquote>
    <br>
  </body>
</html>