On Thu, Feb 23, 2012 at 12:51 PM, Bojan Niceno <span dir="ltr">&lt;<a href="mailto:bojan.niceno@psi.ch">bojan.niceno@psi.ch</a>&gt;</span> wrote:<br><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">
    Dear Matt, <br>
    <br>
    <br>
    are you sure?  It is almost 4000 lines long!  Shall I send only the
    function which bother me?<br>
    <br>
    If the entire code is what you need, shall I make a tarball and
    attach it?<br></div></blockquote><div><br></div><div>Send something the builds and runs. Don&#39;t care how long it is.</div><div><br></div><div>   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">
        Kind regards,<br>
    <br>
    <br>
        Bojan<br>
    <br>
    On 2/23/2012 7:44 PM, Matthew Knepley wrote:
    <blockquote type="cite">On Thu, Feb 23, 2012 at 12:28 PM, Bojan Niceno <span dir="ltr">&lt;<a href="mailto:bojan.niceno@psi.ch" target="_blank">bojan.niceno@psi.ch</a>&gt;</span>
      wrote:<br>
      <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"> On 2/23/2012 7:24 PM,
            Matthew Knepley wrote:
            <blockquote type="cite">On Thu, Feb 23, 2012 at 12:05 PM,
              Bojan Niceno <span dir="ltr">&lt;<a href="mailto:bojan.niceno@psi.ch" target="_blank">bojan.niceno@psi.ch</a>&gt;</span>
              wrote:<br>
              <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"> Dear Matthew,<br>
                    <br>
                    <br>
                    thank you for your response.  When I use
                    VecCreateGhost, I get the following:<br>
                  </div>
                </blockquote>
                <div><br>
                </div>
                <div>It appears that you passed a bad communicator. Did
                  you not initialize a &#39;comm&#39; variable?</div>
              </div>
            </blockquote>
            <br>
            I pass PETSC_COMM_WORLD to VecCreateGhost.  <br>
            <br>
            I don&#39;t know what you mean by &#39;comm&#39; variable :-(  I called
            all the routines to initialize PETSc.</div>
        </blockquote>
        <div><br>
        </div>
        <div>Send your code to <a href="mailto:petsc-maint@mcs.anl.gov" target="_blank">petsc-maint@mcs.anl.gov</a>.</div>
        <div><br>
        </div>
        <div>   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">    <br>
                Cheers,<br>
            <br>
                <br>
                Bojan<br>
            <br>
            <blockquote type="cite">
              <div class="gmail_quote">
                <div><br>
                </div>
                <div>   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"> [0]PETSC ERROR:
------------------------------------------------------------------------<br>
                    [0]PETSC ERROR: Caught signal number 11 SEGV:
                    Segmentation Violation, probably memory access out
                    of range<br>
                    [0]PETSC ERROR: Try option -start_in_debugger or
                    -on_error_attach_debugger<br>
                    [0]PETSC ERROR: or see <a href="http://www.mcs.anl.gov/petsc/petsc-as/documentation/faq.html#valgrind" target="_blank">http://www.mcs.anl.gov/petsc/petsc-as/documentation/faq.html#valgrind</a>[0]PETSC


                    ERROR: or try <a href="http://valgrind.org" target="_blank">http://valgrind.org</a>
                    on GNU/linux and Apple Mac OS X to find memory
                    corruption errors<br>
                    [0]PETSC ERROR: likely location of problem given in
                    stack below<br>
                    [0]PETSC ERROR: ---------------------  Stack Frames
                    ------------------------------------<br>
                    [0]PETSC ERROR: Note: The EXACT line numbers in the
                    stack are not available,<br>
                    [0]PETSC ERROR:       INSTEAD the line number of the
                    start of the function<br>
                    [0]PETSC ERROR:       is given.<br>
                    [0]PETSC ERROR: [0] PetscCommDuplicate line 140
                    src/sys/objects/tagm.c<br>
                    [0]PETSC ERROR: [0] PetscHeaderCreate_Private line
                    30 src/sys/objects/inherit.c<br>
                    [0]PETSC ERROR: [0] VecCreate line 32
                    src/vec/vec/interface/veccreate.c<br>
                    [0]PETSC ERROR: [0] VecCreateGhostWithArray line 567
                    src/vec/vec/impls/mpi/pbvec.c<br>
                    [0]PETSC ERROR: [0] VecCreateGhost line 647
                    src/vec/vec/impls/mpi/pbvec.c<br>
                    [0]PETSC ERROR: --------------------- Error Message
                    ------------------------------------<br>
                    [0]PETSC ERROR: Signal received!<br>
                    [0]PETSC ERROR:
                    ------------------------------------------------------------------------<br>
                    [0]PETSC ERROR: Petsc Release Version 3.2.0, Patch
                    6, Wed Jan 11 09:28:45 CST 2012<br>
                    [0]PETSC ERROR: See docs/changes/index.html for
                    recent updates.<br>
                    [0]PETSC ERROR: See docs/faq.html for hints about
                    trouble shooting.<br>
                    [0]PETSC ERROR: See docs/index.html for manual
                    pages.<br>
                    [0]PETSC ERROR:
                    ------------------------------------------------------------------------<br>
                    [0]PETSC ERROR: ./PSI-Flow on a arch-linu named
                    lccfd06 by niceno Thu Feb 23 19:02:45 2012<br>
                    [0]PETSC ERROR: Libraries linked from
                    /homecfd/niceno/PETSc-3.2-p6/arch-linux2-c-debug/lib<br>
                    [0]PETSC ERROR: Configure run at Fri Feb 10 10:24:13
                    2012<br>
                    [0]PETSC ERROR: Configure options<br>
                    [0]PETSC ERROR:
                    ------------------------------------------------------------------------<br>
                    [0]PETSC ERROR: User provided function() line 0 in
                    unknown directory unknown file<br>
                    <br>
                    I don&#39;t understand what could be causing it.  I took
                    very good care to match the global numbers of ghost
                    cells when calling VecCreateGhost<br>
                    <br>
                    <br>
                        Kind regards,<br>
                    <br>
                    <br>
                        Bojan<br>
                    <br>
                    <br>
                    On 2/23/2012 5:53 PM, Matthew Knepley wrote:
                    <blockquote type="cite">On Thu, Feb 23, 2012 at
                      10:46 AM, Bojan Niceno <span dir="ltr">&lt;<a href="mailto:bojan.niceno@psi.ch" target="_blank">bojan.niceno@psi.ch</a>&gt;</span>
                      wrote:<br>
                      <div class="gmail_quote">
                        <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> Hi all,<br>
                          <br>
                          I&#39;ve never used a mailing list before, so I
                          hope this message will reach PETSc users and
                          experts and someone might be willing to help
                          me.  I am also novice in PETSc.<br>
                          <br>
                          I have developed an unstructured finite volume
                          solver on top of PETSc libraries.  In
                          sequential, it works like a charm.  For the
                          parallel version, I do domain decomposition
                          externally with Metis, and work out local and
                          global numberings, as well as communication
                          patterns between processor.  (The latter don&#39;t
                          seem to be needed for PETSc, though.)  When I
                          run my program in parallel, it also works, but
                          I miss values in vectors&#39; ghost points.<br>
                          <br>
                          I create vectors with command:
                          VecCreate(PETSC_COMM_WORLD, &amp;x);<br>
                          <br>
                          Is it possible to get the ghost values if a
                          vector is created like this?<br>
                        </blockquote>
                        <div><br>
                        </div>
                        <div>I do not understand this question. By
                          definition, &quot;ghost values&quot; are those not
                          stored in the global vector.</div>
                        <div> </div>
                        <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> I have tried to use
                          VecCreateGhost, but for some reason which is
                          beyond my comprehension, PETSc goes berserk
                          when it reaches the command:
                          VecCreateGhost(PETSC_COMM_WORLD, n,
                          PETSC_DECIDE, nghost, ifrom, &amp;x)<br>
                        </blockquote>
                        <div><br>
                        </div>
                        <div>I think you can understand that &quot;berserk&quot;
                          tells me absolutely nothing. Error message?
                          Stack trace? Did you try to run an</div>
                        <div>example which uses VecGhost?</div>
                        <div><br>
                        </div>
                        <div>  Thanks,</div>
                        <div><br>
                        </div>
                        <div>     Matt</div>
                        <div> </div>
                        <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"> Can anyone help me?
                           Either how to reach ghost values for vector
                          created by VecCreate, or how to use
                          VecCreateGhost properly?<br>
                          <br>
                          <br>
                            Kind regards,<br>
                          <br>
                            Bojan<br>
                        </blockquote>
                      </div>
                      <br>
                      <br clear="all">
                      <span><font color="#888888">
                          <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>
                        </font></span></blockquote>
                    <span><font color="#888888"> <br>
                        <br>
                        <div>-- <br>
                          <img src="cid:part1.07080600.05050800@psi.ch" border="0"></div>
                      </font></span></div>
                </blockquote>
              </div>
              <br>
              <br clear="all">
              <span><font color="#888888">
                  <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>
                </font></span></blockquote>
            <span><font color="#888888"> <br>
                <br>
                <div>-- <br>
                  <img src="cid:part2.07040807.04050702@psi.ch" border="0"></div>
              </font></span></div>
        </blockquote>
      </div>
      <br>
      <br clear="all"><span class="HOEnZb"><font color="#888888">
      <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>
    </font></span></blockquote><span class="HOEnZb"><font color="#888888">
    <br>
    <br>
    <div>-- <br>
      <img src="cid:part3.09010509.02040600@psi.ch" border="0"></div>
  </font></span></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>