<html>
  <head>
    <meta content="text/html; charset=ISO-8859-1"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#FFFFFF" text="#000000">
    <div class="moz-cite-prefix"><br>
      Le 2013-10-30 17:45, Matthew Knepley a écrit :<br>
    </div>
    <blockquote
cite="mid:CAMYG4Gkx=oUe9B=7L7Bhxp16VVmDYc730YY9FxFkwOj27CduCw@mail.gmail.com"
      type="cite">
      <div dir="ltr">On Wed, Oct 30, 2013 at 4:41 PM, Maxime
        Boissonneault <span dir="ltr"><<a moz-do-not-send="true"
            href="mailto:maxime.boissonneault@calculquebec.ca"
            target="_blank">maxime.boissonneault@calculquebec.ca</a>></span>
        wrote:<br>
        <div class="gmail_extra">
          <div class="gmail_quote">
            <blockquote class="gmail_quote" style="margin:0px 0px 0px
0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
              <div bgcolor="#FFFFFF" text="#000000">
                <div>Hi,<br>
                  Here is the attached configure.log file.<br>
                  <br>
                  I will try the flag --with-debugging tomorrow.<br>
                </div>
              </div>
            </blockquote>
            <div><br>
            </div>
            Get rid of -O2: CFLAGS="-O2 -xHost -mkl -fPIC -m64"
            FFLAGS="-O2 -xHost -mkl -fPIC -m64"
            --prefix=/software6/libs/petsc/3.4.3_intel</div>
        </div>
      </div>
    </blockquote>
    I had -O3 earlier. The error was the same. It is overwritten by the
    makefile anyway if you look in the details. This is not the source
    of the problem.<br>
    <blockquote
cite="mid:CAMYG4Gkx=oUe9B=7L7Bhxp16VVmDYc730YY9FxFkwOj27CduCw@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div class="gmail_extra">
          <div class="gmail_quote">--with-dynamic-loading</div>
          <div class="gmail_quote">--with-x=0 --with-mpi-compilers=1</div>
          <div class="gmail_quote">--with-mpi-dir=/software6/mpi/openmpi/1.6.5_intel</div>
          <div class="gmail_quote">
            --known-mpi-shared-libraries=1</div>
          <div class="gmail_quote">--with-debugging=no</div>
          <div class="gmail_quote">--with-shared-libraries=1</div>
          <div class="gmail_quote">--with-blas-lapack-dir=/software6/compilers/intel/composer_xe_2013_sp1/lib/intel64</div>
          <div class="gmail_quote">Don't need this --with-scalapack=1</div>
          <div class="gmail_quote">--with-scalapack-include=/software6/compilers/intel/composer_xe_2013_sp1/include</div>
          <div class="gmail_quote">--with-scalapack-lib=/software6/compilers/intel/composer_xe_2013_sp1/lib/intel64/libmkl_scalapack_lp64.a</div>
          <div class="gmail_quote">Don't need this --with-blacs=1</div>
          <div class="gmail_quote">--with-blacs-include=/software6/compilers/intel/composer_xe_2013_sp1/include</div>
          <div class="gmail_quote">--with-blacs-lib=/software6/compilers/intel/composer_xe_2013_sp1/lib/intel64/libmkl_blacs_openmpi_lp64.a</div>
          <div class="gmail_quote">--download-mumps=yes</div>
          <div class="gmail_quote">--download-ptscotch=1</div>
          <div class="gmail_quote">--download-superlu=yes</div>
          <div class="gmail_quote">--download-superlu_dist=yes</div>
          <div class="gmail_quote">
            --download-parmetis=yes</div>
          <div class="gmail_quote">--download-metis=yes</div>
          <div class="gmail_quote">--download-ml=yes</div>
          <div class="gmail_quote">This is deprecated. Use -pc_type gamg
            --download-prometheus=yes</div>
        </div>
      </div>
    </blockquote>
    Which part is, download-ml ? or download-hypre ? Again, this is not
    the module that fails compiling however.<br>
    <br>
    Maxime<br>
    <blockquote
cite="mid:CAMYG4Gkx=oUe9B=7L7Bhxp16VVmDYc730YY9FxFkwOj27CduCw@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div class="gmail_extra">
          <div class="gmail_quote">--download-hypre=yes</div>
          <div class="gmail_quote"><br>
          </div>
          <div class="gmail_quote">  Matt<br>
             
            <blockquote class="gmail_quote" style="margin:0px 0px 0px
0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
              <div bgcolor="#FFFFFF" text="#000000">
                <div> Maxime<br>
                  <br>
                  Le 2013-10-30 16:49, Matthew Knepley a écrit :<br>
                </div>
                <blockquote type="cite">
                  <div dir="ltr">On Wed, Oct 30, 2013 at 3:39 PM, Maxime
                    Boissonneault <span dir="ltr"><<a
                        moz-do-not-send="true"
                        href="mailto:maxime.boissonneault@calculquebec.ca"
                        target="_blank">maxime.boissonneault@calculquebec.ca</a>></span>
                    wrote:<br>
                    <div class="gmail_extra">
                      <div class="gmail_quote">
                        <blockquote class="gmail_quote"
                          style="margin:0px 0px 0px
0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
                          <div bgcolor="#FFFFFF" text="#000000">
                            <div
                              style="font-family:-moz-fixed;font-size:12px"
                              lang="x-western">Hi, <br>
                              I am currently trying to compile PETSc
                              3.4.3 with ICC 14.0 and OpenMPI 1.6.5 and
                              it fails SuperLU_Dist.<br>
                              <br>
                              I am getting the following error : <br>
                              <br>
                              68303
                              /software6/mpi/openmpi/1.6.5_intel/bin/mpicc
                              -I/software6/mpi/openmpi/1.6.5_intel/include

                              -I/software6/mpi/openmpi/1.6.5_intel/include
                              -O2 -xHost -mkl -fPIC -m64 -fPIC -O3 
                              -DAdd_ -DUSE_VENDOR_BLAS -c pdgstrf.c <br>
                              68304 make[1]: Leaving directory
`/software6/src/petsc-3.4.3-intel-try/externalpackages/SuperLU_DIST_3.3/SRC'<br>
                              68305 error #13002: unexpected CFE message
                              argument:  e. The staggered cosine
                              transform may be <br>
                              68306 warning #13003: message verification
                              failed for: 556; reverting to internal
                              message <br>
                              68307 pdgstrf.c(2672): warning #556: a
                              value of type "int" cannot be assigned to
                              an entity of type "MPI_Request" <br>
                              68308            
                              U_diag_blk_send_req[krow] = 1; /* flag
                              outstanding Isend */ <br>
                              68309                                      
                              ^ <br>
                              68310 <br>
                              68311 pdgstrf.c(2672): warning #152: Fatal
                              error: Trigonometric Transform has failed
                              to release the memory. <br>
                              68312            
                              U_diag_blk_send_req[krow] = 1; /* flag
                              outstanding Isend */ <br>
                              68313                                        
                              ^ <br>
                              68314 <br>
                              68315 compilation aborted for pdgstrf.c
                              (code 1) <br>
                              68316 make[1]: *** [pdgstrf.o] Error 1 <br>
                              <br>
                              Anyone has a clue on to what might be
                              going on ? </div>
                          </div>
                        </blockquote>
                        <div><br>
                        </div>
                        <div>1) Always send configure.log</div>
                        <div><br>
                        </div>
                        <div>2) It looks like an Intel compiler bug. Try
                          building with --with-debugging first</div>
                        <div><br>
                        </div>
                        <div>  Matt</div>
                        <div>  </div>
                        <blockquote class="gmail_quote"
                          style="margin:0px 0px 0px
0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
                          <div bgcolor="#FFFFFF" text="#000000">
                            <div
                              style="font-family:-moz-fixed;font-size:12px"
                              lang="x-western"><span><font
                                  color="#888888"><br>
                                  <div><span>-- <br>
                                    </span>---------------------------------
                                    <br>
                                    Maxime Boissonneault <br>
                                    Analyste de calcul - Calcul Québec,
                                    Université Laval <br>
                                    Ph. D. en physique <br>
                                    <br>
                                  </div>
                                </font></span></div>
                          </div>
                        </blockquote>
                      </div>
                      <br>
                      <br clear="all">
                      <span class=""><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 </font></span></div>
                    <span class=""><font color="#888888"> </font></span></div>
                  <span class=""><font color="#888888"> </font></span></blockquote>
                <span class=""><font color="#888888"> <br>
                    <br>
                    <pre cols="72">-- 
---------------------------------
Maxime Boissonneault
Analyste de calcul - Calcul Québec, Université Laval
Ph. D. en physique</pre>
                  </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
        </div>
      </div>
    </blockquote>
    <br>
    <br>
    <pre class="moz-signature" cols="72">-- 
---------------------------------
Maxime Boissonneault
Analyste de calcul - Calcul Québec, Université Laval
Ph. D. en physique</pre>
  </body>
</html>