On Sun, May 6, 2012 at 9:24 AM, Alexander Grayver <span dir="ltr"><<a href="mailto:agrayver@gfz-potsdam.de" target="_blank">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">
<u></u>
<div bgcolor="#ffffff" text="#000000">
Hm, valgrind gives a lot of output like that (see full log in
previous message):</div></blockquote><div><br></div><div>Can you run this with --download-f-blas-lapack? This sounds much more like an MKL bug.</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"><div class="im">
==20287== Invalid read of size 8<br></div>
==20287== at 0x1AE79DA1: mkl_lapack_dlasq3 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_lapack.so)<br>
==20287== by 0x5CF7AE5: mkl_lapack_dlasq3 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_thread.so)<br>
==20287== by 0x1AE79617: mkl_lapack_dlasq2 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_lapack.so)<br>
==20287== by 0x5CF7A15: mkl_lapack_dlasq2 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_thread.so)<br>
==20287== by 0x1AA3E72A: mkl_lapack_dlasq1 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_lapack.so)<br>
==20287== by 0x5CF79C7: mkl_lapack_dlasq1 (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_thread.so)<br>
==20287== by 0x1AC44D6C: mkl_lapack_zbdsqr (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_lapack.so)<br>
==20287== by 0x5CFFEF8: mkl_lapack_zbdsqr (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_thread.so)<br>
==20287== by 0x1AC7D989: mkl_lapack_zgesvd (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_lapack.so)<br>
==20287== by 0x5D021C0: mkl_lapack_zgesvd (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_thread.so)<br>
==20287== by 0x5899E43: ZGESVD (in
/opt/intel/Compiler/11.1/072/mkl/lib/em64t/libmkl_intel_lp64.so)<br>
==20287== by 0x697017: KSPComputeExtremeSingularValues_GMRES
(gmreig.c:46)<br>
==20287== by 0x69EFBA: KSPComputeExtremeSingularValues
(itfunc.c:47)<br>
==20287== by 0x4509BC: main (solveTest.c:62)<br>
==20287== Address 0x11363d48 is not stack'd, malloc'd or (recently)
free'd<div><div class="h5"><br>
<br>
On 06.05.2012 15:21, Alexander Grayver wrote:
<blockquote type="cite">
On 06.05.2012 15:07, Matthew Knepley wrote:<br>
<blockquote type="cite">
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div bgcolor="#ffffff" text="#000000">
<blockquote type="cite">
<div class="gmail_quote">
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"> Hello,<br>
<br>
I use KSP and random rhs to compute largest singular
value:<br>
</blockquote>
<div><br>
</div>
<div>1) Is this the whole program? If not, this can be
caused by memory corruption somewhere else. This is
what I suspect.</div>
</div>
</blockquote>
<br>
Matt,<br>
<br>
I can reproduce error using attached test programm and
this matrix (7 mb):<br>
<a href="http://dl.dropbox.com/u/60982984/A.dat" target="_blank">http://dl.dropbox.com/u/60982984/A.dat</a></div>
</blockquote>
<div><br>
</div>
<div>I run it fine with the latest petsc-dev:</div>
<div><br>
</div>
<div> 1.405802e+00</div>
<div><br>
</div>
<div>Can you valgrind it on your machine?</div>
</div>
<br>
</blockquote>
<br>
I did:<br>
valgrind --tool=memcheck -q --num-callers=20
--log-file=valgrind.log.%p /solveTest -ksp_monitor_true_residual
-log_summary -mat_type aij -ksp_rtol 1.0e-10 -malloc off<br>
<br>
The error is better constrained:<br>
<br>
==20287== Invalid read of size 8<br>
==20287== at 0x7874B4C: opal_os_path (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-pal.so.0.0.0)<br>
==20287== by 0x75F2E27: orte_session_dir_finalize (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-rte.so.0.0.0)<br>
==20287== by 0x76012E8: orte_errmgr_base_error_abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-rte.so.0.0.0)<br>
==20287== by 0x73396E9: ompi_mpi_abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libmpi.so.0.0.2)<br>
==20287== by 0x734F36E: PMPI_Abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libmpi.so.0.0.2)<br>
==20287== by 0x7499AB: PetscDefaultSignalHandler (signal.c:169)<br>
==20287== by 0x749267: PetscSignalHandler_Private (signal.c:53)<br>
==20287== by 0x924B9DF: ??? (in /lib64/<a href="http://libc-2.11.1.so" target="_blank">libc-2.11.1.so</a>)<br>
==20287== by 0x535D9E: VecDestroyVecs (vector.c:653)<br>
==20287== by 0x68B61D: KSPReset_GMRES (gmres.c:258)<br>
==20287== by 0x6A9D39: KSPReset (itfunc.c:733)<br>
==20287== by 0x6AA839: KSPDestroy (itfunc.c:780)<br>
==20287== by 0x4509F8: main (solveTest.c:66)<br>
==20287== Address 0xbde4860 is 0 bytes inside a block of size 2
alloc'd<br>
==20287== at 0x4C26B9B: malloc (vg_replace_malloc.c:263)<br>
==20287== by 0x92876DF: vasprintf (in /lib64/<a href="http://libc-2.11.1.so" target="_blank">libc-2.11.1.so</a>)<br>
==20287== by 0x9266C67: asprintf (in /lib64/<a href="http://libc-2.11.1.so" target="_blank">libc-2.11.1.so</a>)<br>
==20287== by 0x75F1701: orte_util_convert_vpid_to_string (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-rte.so.0.0.0)<br>
==20287== by 0x75F2D4A: orte_session_dir_finalize (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-rte.so.0.0.0)<br>
==20287== by 0x76012E8: orte_errmgr_base_error_abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libopen-rte.so.0.0.0)<br>
==20287== by 0x73396E9: ompi_mpi_abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libmpi.so.0.0.2)<br>
==20287== by 0x734F36E: PMPI_Abort (in
/opt/mpi/intel/openmpi-1.4.2/lib/libmpi.so.0.0.2)<br>
==20287== by 0x7499AB: PetscDefaultSignalHandler (signal.c:169)<br>
==20287== by 0x749267: PetscSignalHandler_Private (signal.c:53)<br>
==20287== by 0x924B9DF: ??? (in /lib64/<a href="http://libc-2.11.1.so" target="_blank">libc-2.11.1.so</a>)<br>
==20287== by 0x535D9E: VecDestroyVecs (vector.c:653)<br>
==20287== by 0x68B61D: KSPReset_GMRES (gmres.c:258)<br>
==20287== by 0x6A9D39: KSPReset (itfunc.c:733)<br>
==20287== by 0x6AA839: KSPDestroy (itfunc.c:780)<br>
==20287== by 0x4509F8: main (solveTest.c:66)<br>
<br>
Full log is attached.<br>
<br>
Important.<br>
If I comment this line:<br>
KSPComputeExtremeSingularValues(ksp, &maxx, &minx);<br>
<br>
It works. <br>
<br>
-- <br>
<pre cols="72">Regards,
Alexander</pre>
</blockquote>
<br>
<br>
</div></div><span class="HOEnZb"><font color="#888888"><pre cols="72">--
Regards,
Alexander</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<br>