On Thu, Feb 23, 2012 at 1:33 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>
    I sent the code as an attached tarball.  I sent it with case I run,
    so is 2 MB big.  It is now in the cue for moderator&#39;s approval. <br></div></blockquote><div><br></div><div>No, you HAVE to send it to <a href="mailto:petsc-maint@mcs.anl.gov">petsc-maint@mcs.anl.gov</a>, as I said last time, for exactly this reason.</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">
    Thanks.<br>
    <br>
        <br>
        Kind regards,<br>
    <br>
    <br>
        Bojan<br>
    <br>
    <br>
    On 2/23/2012 8:04 PM, Matthew Knepley wrote:
    <blockquote type="cite">On Thu, Feb 23, 2012 at 12:51 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 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:part1.02040900.03040302@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:part2.02060807.05000506@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:part3.09070605.05030208@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:part4.04060304.01030403@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>