<html>
  <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
  </head>
  <body>
    <p>Hi Mark,</p>
    <p>What interconnect is on your machine?</p>
    <p>Regards,</p>
    <p>Benson<br>
    </p>
    <div class="moz-cite-prefix">On 10/4/19 3:37 PM, Mark Cunningham via
      discuss wrote:<br>
    </div>
    <blockquote type="cite"
cite="mid:CACj+-Tg3edC81W+v2Z1rTEX2PPyEKriZ8p3qpYqqktzKw9_giw@mail.gmail.com">
      <meta http-equiv="content-type" content="text/html; charset=UTF-8">
      <div dir="ltr">Oops, sorry I forgot the attachment.<br>
        <div><br>
          <div class="gmail_quote">
            <div dir="ltr" class="gmail_attr">---------- Forwarded
              message ---------<br>
              From: <b class="gmail_sendername" dir="auto">Mark
                Cunningham</b> <span dir="auto"><<a
                  href="mailto:mark.cunningham@ariacoustics.com"
                  moz-do-not-send="true">mark.cunningham@ariacoustics.com</a>></span><br>
              Date: Fri, Oct 4, 2019 at 8:35 AM<br>
              Subject: MPICH 3.3.1 tests fail<br>
              To: <<a href="mailto:discuss@mpich.org"
                moz-do-not-send="true">discuss@mpich.org</a>><br>
            </div>
            <br>
            <br>
            <div dir="ltr">
              <div dir="ltr">
                <div dir="ltr">
                  <div>I have built MPICH 3.3.1 on Ubuntu 18.04 with the
                    gcc-7 compiler suite.  (Build script is provided:
                    build_mpich.)  I have built with both
                    --with-device=ch3:nemesis and
                    --with-device=ch3:nemesis:ofi</div>
                  <div>with the same outcome in the make test.  A dozen
                    of the tests fail with timeouts.</div>
                  <div>I ran the test on an 8 processor Thinkstation but
                    what would be beneficial is some sort of sense of
                    what the test results should be.  I've browsed the
                    test results that you've posted but these appear to
                    be summaries that conclude All Tests Passed, without
                    individual timings for each test.</div>
                  <div><br>
                  </div>
                  <div>In any case, I would appreciate any guidance that
                    you might be able to provide.  I have provided the
                    config files and the summary.junit.xml file. (On my
                    machine the summary.xml file just reports that there
                    is an error on line 9562.)  The result of mpiexec
                    -info is:</div>
                  <div>~/build/mpich-3.3.1/src/pm/hydra %
                    ./mpiexec.hydra -info<br>
                    HYDRA build details:<br>
                        Version:                                 3.3.1<br>
                        Release Date:                            Wed Jun
                     5 14:57:33 CDT 2019<br>
                        CC:                              gcc    <br>
                        CXX:                             g++    <br>
                        F77:                             gfortran   <br>
                        F90:                             gfortran   <br>
                        Configure options:                      
                    '--disable-option-checking'
                    '--prefix=/home/share/mpich/mpich-3.3.1'
                    '--with-devce=ch3:nemesis' '--cache-file=/dev/null'
                    '--srcdir=.' 'CC=gcc' 'CFLAGS= -O2' 'LDFLAGS='
                    'LIBS=' 'CPPFLAGS=
                    -I/home/mark/buildmpich-3.3.1/src/mpl/include
                    -I/home/mark/build/mpich-3.3.1/src/mpl/include
                    -I/home/mark/build/mpich-3.3.1/src/openpa/src
                    -I/hme/mark/build/mpich-3.3.1/src/openpa/src
                    -D_REENTRANT
                    -I/home/mark/build/mpich-3.3.1/src/mpi/romio/include'
                    'MPLLIBNAME=mpl'<br>
                        Process Manager:                         pmi<br>
                        Launchers available:                     ssh rsh
                    fork slurm ll lsf sge manual persist<br>
                        Topology libraries available:            hwloc<br>
                        Resource management kernels available:   user
                    slurm ll lsf sge pbs cobalt<br>
                        Checkpointing libraries available:       <br>
                        Demux engines available:                 poll
                    select</div>
                  <div>---------------------------------------------------------</div>
                  <div>Thanks for your help,</div>
                  <div>Mark</div>
                  <div><br>
                  </div>
                  <div>Mark A Cunningham, PhD</div>
                  <div>Senior Scientist</div>
                  <div>Applied Research in Acoustics LLC</div>
                  <div>Culpeper VA 22701<br>
                  </div>
                  <div><br>
                  </div>
                </div>
              </div>
            </div>
          </div>
        </div>
      </div>
      <br>
      <fieldset class="mimeAttachmentHeader"></fieldset>
      <pre class="moz-quote-pre" wrap="">_______________________________________________
discuss mailing list     <a class="moz-txt-link-abbreviated" href="mailto:discuss@mpich.org">discuss@mpich.org</a>
To manage subscription options or unsubscribe:
<a class="moz-txt-link-freetext" href="https://lists.mpich.org/mailman/listinfo/discuss">https://lists.mpich.org/mailman/listinfo/discuss</a>
</pre>
    </blockquote>
  </body>
</html>