Dear all,<br>
<br>
I basically use PETSc inside an existing OpenMP application. All PETSc
solves are done in serial in this application. I therefore do not need
MPI (at the moment...). The code solves finite element problems, where
the OpenMP environment is used to use various parameters for these
systems. All private variables are allocated on the stack, the OpenMP
parallel loop makes calls to PETSc.<br>
Thanks for your replies,<br>
Patrick<br>
<br>
<br><br><div><span class="gmail_quote">On 10/9/06, <b class="gmail_sendername">Barry Smith</b> <<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br> Patrick,<br><br> Are you using "user level threads", that is your code stops<br>and starts additional threads directly or are you using loop level<br>threads, that is OpenMPI manages all the threads for you. If the
<br>later you are fine, if the former make sure only one thread<br>makes PETSc calls.<br><br> Barry<br><br><br>On Mon, 9 Oct 2006, Patrick Lechner wrote:<br><br>> Dear all,<br>> I am currently writing a code and try to combine PETSc and OpenMP (where
<br>> PETSc will be used inside a parallel environment).<br>> My questions now are:<br>> 1. Is it safe to combine these libraries?<br>> 2. What will I have to consider to make my code work reliably?<br>> Thanks a lot for your help.
<br>> Best wishes,<br>> Patrick<br>><br><br></blockquote></div><br><br clear="all"><br>-- <br>=================================<br><br>Patrick Lechner<br>Numerical Analysist / Numerical Modeller<br>Flat 1<br>159 Hardgate
<br>Aberdeen, AB11 6XQ<br><br>Phone: 07815 927333<br>E-mail: <a href="mailto:patrick@lechner.com">patrick@lechner.com</a><br>Homepage: <a href="http://www.patrick.lechner.com">http://www.patrick.lechner.com</a>