On Fri, Apr 20, 2012 at 6:07 AM, Alexander Grayver <span dir="ltr"><<a href="mailto:agrayver@gfz-potsdam.de">agrayver@gfz-potsdam.de</a>></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">
Hello,<br>
<br>
Calling MatAYPX with MatStructure == DIFFERENT_NONZERO_PATTERN produces following errors:<br>
<br>
[30]PETSC ERROR: --------------------- Error Message ------------------------------<u></u>------<br>
[30]PETSC ERROR: Argument out of range!<br>
[30]PETSC ERROR: New nonzero at (0,8486) caused a malloc!<br>
[30]PETSC ERROR: ------------------------------<u></u>------------------------------<u></u>------------<br>
[30]PETSC ERROR: Petsc Development HG revision: 7c3c3f8c0d65b793aea33c138419de<u></u>755b591ca7 HG Date: Thu Feb 09 14:42:30 2012 -0600<br>
[30]PETSC ERROR: See docs/changes/index.html for recent updates.<br>
[30]PETSC ERROR: See docs/faq.html for hints about trouble shooting.<br>
[30]PETSC ERROR: See docs/index.html for manual pages.<br>
[30]PETSC ERROR: ------------------------------<u></u>------------------------------<u></u>------------<br>
[30]PETSC ERROR: /home/prog on a openmpi-i named node229 by agrayver Fri Apr 20 11:33:55 2012<br>
[30]PETSC ERROR: Libraries linked from /home/lib/petsc-dev/openmpi-<u></u>intel-complex-debug-f/lib<br>
[30]PETSC ERROR: Configure run at Fri Feb 10 09:28:34 2012<br>
[30]PETSC ERROR: Configure options --with-petsc-arch=openmpi-<u></u>intel-complex-debug-f --with-fortran-interfaces=1 --with-scalapack-lib=/opt/<u></u>intel/Compiler/11.1/072/mkl/<u></u>lib/em64t/libmkl_scalapack_<u></u>lp64.a --with-scalapack-include=/opt/<u></u>intel/Compiler/11.1/072/mkl/<u></u>include --with-blacs-lib=/opt/intel/<u></u>Compiler/11.1/072/mkl/lib/<u></u>em64t/libmkl_blacs_openmpi_<u></u>lp64.a --with-blacs-include=/opt/<u></u>intel/Compiler/11.1/072/mkl/<u></u>include --with-mpi-dir=/opt/mpi/intel/<u></u>openmpi-1.4.2 --with-scalar-type=complex --with-blas-lapack-lib="[/opt/<u></u>intel/Compiler/11.1/072/mkl/<u></u>lib/em64t/libmkl_intel_lp64.a,<u></u>/opt/intel/Compiler/11.1/072/<u></u>mkl/lib/em64t/libmkl_intel_<u></u>thread.a,/opt/intel/Compiler/<u></u>11.1/072/mkl/lib/em64t/libmkl_<u></u>core.a,/opt/intel/Compiler/11.<u></u>1/072/lib/intel64/libiomp5.a]" --with-precision=double --with-x=0<br>
[30]PETSC ERROR: ------------------------------<u></u>------------------------------<u></u>------------<br>
[30]PETSC ERROR: MatSetValues_MPIAIJ() line 538 in /home/lib/petsc-dev/src/mat/<u></u>impls/aij/mpi/mpiaij.c<br>
[30]PETSC ERROR: MatSetValues() line 1129 in /home/lib/petsc-dev/src/mat/<u></u>interface/matrix.c<br>
[30]PETSC ERROR: MatAXPY_<u></u>BasicWithPreallocation() line 108 in /home/lib/petsc-dev/src/mat/<u></u>utils/axpy.c<br>
[30]PETSC ERROR: MatAXPY_MPIAIJ() line 2235 in /home/lib/petsc-dev/src/mat/<u></u>impls/aij/mpi/mpiaij.c<br>
[30]PETSC ERROR: MatAXPY() line 39 in /home/lib/petsc-dev/src/mat/<u></u>utils/axpy.c<br>
[30]PETSC ERROR: MatAYPX() line 272 in /home/lib/petsc-dev/src/mat/<u></u>utils/axpy.c<br>
<br>
<br>
I guess it has something to do with recent changes in mataij implementation, doesn't it?</blockquote><div><br></div><div>Yes, we started to require that everything be correctly allocated, rather than have hidden performance problems.</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"><span class="HOEnZb"><font color="#888888">
-- <br>
Regards,<br>
Alexander<br></font></span></blockquote></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>