Lack of reproducibility points its huge foam finger at memory corruption. You can try
1. running with -fp_trap to see where the bad values are first computed 2. running in valgrind to look for memory corruption 3. linking to a different BLAS/Lapack to rule out linking problems with MKL On Sat, Nov 24, 2012 at 6:17 PM, Roc Wang <pengxwang at hotmail.com> wrote: > Hello, > > I met a wierd problem. I am trying to solve linear system by calling > KSPSolve(). But sometimes, the error information of Floating point > exception! I tried to track down the error, but unfortunately, it's > pretty random. Sometimes the executable runs fine. Other times it will > crash with floating point exceptions as below. I cannot find the exact line > causing the error. Could you please give me some suggestions or hints? > Thanks a lot! > > [0]PETSC ERROR: --------------------- Error Message > ------------------------------------ [0]PETSC ERROR: Floating point > exception! [0]PETSC ERROR: Infinite or not-a-number generated in norm! > [0]PETSC ERROR: > ------------------------------------------------------------------------ > [0]PETSC ERROR: Petsc Release Version 3.2.0, Patch 7, Thu Mar 15 09:30:51 > CDT 2012 [0]PETSC ERROR: See docs/changes/index.html for recent updates. > [0]PETSC ERROR: See docs/faq.html for hints about trouble shooting. > [0]PETSC ERROR: See docs/index.html for manual pages. [0]PETSC ERROR: > ------------------------------------------------------------------------ > [0]PETSC ERROR: /gpfs/home/pzw2/work/MLPIC03_3dCart_20121118/a.out on a > arch-linu named lionxo64.hpc.aset.psu.edu by pzw2 Sat Nov 24 11:01:49 > 2012 [0]PETSC ERROR: Libraries linked from /usr/global/petsc/3.2-p7/lib > [0]PETSC ERROR: Configure run at Thu Apr 5 10:32:29 2012 [0]PETSC ERROR: > Configure options --prefix=/usr/global/petsc/3.2-p7/ > --with-blas-lapack-dir=/usr/global/intel/mkl/10.2.6.038/lib/em64t/[0]PETSC > ERROR: > ------------------------------------------------------------------------ > [0]PETSC ERROR: VecNorm() line 167 in src/vec/vec/interface/rvector.c > [0]PETSC ERROR: VecNormalize() line 261 in src/vec/vec/interface/rvector.c > [0]PETSC ERROR: GMREScycle() line 128 in src/ksp/ksp/impls/gmres/gmres.c > [0]PETSC ERROR: KSPSolve_GMRES() line 231 in > src/ksp/ksp/impls/gmres/gmres.c [0]PETSC ERROR: KSPSolve() line 423 in > src/ksp/ksp/interface/itfunc.c > > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20121124/714eb2ee/attachment.html>