<html>
  <head>
    <meta content="text/html; charset=ISO-8859-1"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    I decided to go with ksp/ksp/exampeles/tutorials/ex2.c; I was unsure
    how to convert the run lines for snes/examples/ex5.c to work with a
    direct solver as I am not versed in SNES options.<br>
    <br>
    Notwithstanding something strange is happening only on select
    examples.  With ksp/ksp/exampeles/tutorials/ex2.c and the run line:<br>
    <br>
    -@${MPIEXEC} -n 2 ./ex2 -ksp_monitor_short -m 20 -n 20 -ksp_type
    preonly -pc_type lu -pc_factor_mat_solver_package superlu_dist<br>
        <br>
    I get good results (of the order):<br>
    <br>
    Norm of error 1.85464e-14 iterations 1<br>
    <br>
    using both superlu_dist and spooles.<br>
    <br>
    My BLAS/LAPACK: -llapack -lblas (so native to my machine).<br>
    <br>
    If you can guide me on a run line for the snes ex5.c I can try that
    too.  I'll also try to construct a GCC build later to see if that is
    an issue.<br>
    <br>
    -sanjay<br>
    <br>
    <br>
    <div class="moz-cite-prefix">On 12/23/12 5:58 PM, Matthew Knepley
      wrote:<br>
    </div>
    <blockquote
cite="mid:CAMYG4GmuhF7Jh7os3j9bLubuoMGnerxtN+tU=gzpeYmX+3UUXA@mail.gmail.com"
      type="cite">
      <div dir="ltr">On Sun, Dec 23, 2012 at 8:08 PM, Sanjay Govindjee <span
          dir="ltr"><<a moz-do-not-send="true"
            href="mailto:s_g@berkeley.edu" target="_blank">s_g@berkeley.edu</a>></span>
        wrote:<br>
        <div class="gmail_extra">
          <div class="gmail_quote">
            <blockquote class="gmail_quote" style="margin:0 0 0
              .8ex;border-left:1px #ccc solid;padding-left:1ex">
              <div bgcolor="#FFFFFF" text="#000000"> Not sure what you
                mean by where is your matrix?  I am simply running ex6
                in the ksp/examples/tests directory.<br>
                <br>
                The reason I ran this test is because I was seeing the
                same behavior with my finite element code (on perfectly
                benign problems).<br>
                <br>
                Is there a built-in test that you use to check that
                superlu_dist is working properly with petsc?<br>
                i.e. something you know that works with with petsc
                3.3-p5?<br>
              </div>
            </blockquote>
            <div><br>
            </div>
            <div style="">1) Run it on a SNES ex5 (or KSP ex2), which is
              a nice Laplacian</div>
            <div style=""><br>
            </div>
            <div style="">2) Compare with MUMPS</div>
            <div style=""><br>
            </div>
            <div style="">   Matt</div>
            <div> </div>
            <blockquote class="gmail_quote" style="margin:0 0 0
              .8ex;border-left:1px #ccc solid;padding-left:1ex">
              <div bgcolor="#FFFFFF" text="#000000"> -sanjay
                <div>
                  <div class="h5"><br>
                    <br>
                    <br>
                    <div>On 12/23/12 4:56 PM, Jed Brown wrote:<br>
                    </div>
                    <blockquote type="cite">
                      <div dir="ltr">Where is your matrix? It might be
                        ending up with a very bad pivot. If the problem
                        can be reproduced, it should be reported to the
                        SuperLU_DIST developers to fix. (Note that we do
                        not see this with other matrices.) You can also
                        try MUMPS.</div>
                      <div class="gmail_extra"><br>
                        <br>
                        <div class="gmail_quote">On Sun, Dec 23, 2012 at
                          6:48 PM, Sanjay Govindjee <span dir="ltr"><<a
                              moz-do-not-send="true"
                              href="mailto:s_g@berkeley.edu"
                              target="_blank">s_g@berkeley.edu</a>></span>
                          wrote:<br>
                          <blockquote class="gmail_quote"
                            style="margin:0 0 0 .8ex;border-left:1px
                            #ccc solid;padding-left:1ex">
                            <div bgcolor="#FFFFFF" text="#000000"> I
                              wanted to use SuperLU Dist to perform a
                              direct solve but seem to be encountering<br>
                              a problem.  I was wonder if this is a know
                              issue and if there is a solution for it.<br>
                              <br>
                              The problem is easily observed using ex6.c
                              in src/ksp/ksp/examples/tests.<br>
                              <br>
                              Out of the box: make runex6 produces a
                              residual error of O(1e-11), all is well.<br>
                              <br>
                              I then changed the run to run on two
                              processors and add the flag<br>
                              -pc_factor_mat_solver_package spooles 
                              this produces a residual error of
                              O(1e-11), all is still well.<br>
                              <br>
                              I then switch over to
                              -pc_factor_mat_solver_package superlu_dist
                              and the<br>
                              residual error comes back as 22.6637! 
                              Something seems very wrong.<br>
                              <br>
                              My build is perfectly vanilla:<br>
                              <br>
                              export PETSC_DIR=/Users/sg/petsc-3.3-p5/<br>
                              export PETSC_ARCH=intel<br>
                              <br>
                              ./configure --with-cc=icc --with-fc=ifort 
                              \
-download-{spooles,parmetis,superlu_dist,prometheus,mpich,ml,hypre,metis}<br>
                              <br>
                              make PETSC_DIR=/Users/sg/petsc-3.3-p5/
                              PETSC_ARCH=intel all<br>
                              make PETSC_DIR=/Users/sg/petsc-3.3-p5/
                              PETSC_ARCH=intel test<span><font
                                  color="#888888"><br>
                                  <br>
                                  -sanjay<br>
                                </font></span></div>
                          </blockquote>
                        </div>
                        <br>
                      </div>
                    </blockquote>
                    <br>
                  </div>
                </div>
                <pre cols="72">-- 
-----------------------------------------------
Sanjay Govindjee, PhD, PE
Professor of Civil Engineering
Vice Chair for Academic Affairs

779 Davis Hall
Structural Engineering, Mechanics and Materials
Department of Civil Engineering
University of California
Berkeley, CA 94720-1710

Voice:  <a moz-do-not-send="true" href="tel:%2B1%20510%20642%206060" value="+15106426060" target="_blank">+1 510 642 6060</a>
FAX:    <a moz-do-not-send="true" href="tel:%2B1%20510%20643%205264" value="+15106435264" target="_blank">+1 510 643 5264</a>
<a moz-do-not-send="true" href="mailto:s_g@berkeley.edu" target="_blank">s_g@berkeley.edu</a>
<a moz-do-not-send="true" href="http://www.ce.berkeley.edu/%7Esanjay" target="_blank">http://www.ce.berkeley.edu/~sanjay</a>
-----------------------------------------------

New Books:  

Engineering Mechanics of Deformable 
Solids: A Presentation with Exercises
<a moz-do-not-send="true" href="http://www.oup.com/us/catalog/general/subject/Physics/MaterialsScience/?view=usa&ci=9780199651641" target="_blank">http://www.oup.com/us/catalog/general/subject/Physics/MaterialsScience/?view=usa&ci=9780199651641</a>
<a moz-do-not-send="true" href="http://ukcatalogue.oup.com/product/9780199651641.do" target="_blank">http://ukcatalogue.oup.com/product/9780199651641.do</a>
<a moz-do-not-send="true" href="http://amzn.com/0199651647" target="_blank">http://amzn.com/0199651647</a>


Engineering Mechanics 3 (Dynamics)
<a moz-do-not-send="true" href="http://www.springer.com/materials/mechanics/book/978-3-642-14018-1" target="_blank">http://www.springer.com/materials/mechanics/book/978-3-642-14018-1</a>
<a moz-do-not-send="true" href="http://amzn.com/3642140181" target="_blank">http://amzn.com/3642140181</a>

-----------------------------------------------
</pre>
              </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
        </div>
      </div>
    </blockquote>
    <br>
  </body>
</html>