[petsc-users] mumps solve with same nonzero pattern

[Wen Jiang]

Hi Hong,

Thanks for your reply. I check the attachment sent last time and I miss
some very information. I attached the complete info with this email. Sorry
for this.

I also tried other matrix ordering like mat_mumps_icntl_7 2 and I got the
similar performance. I checked the configuration log file on that cluster,
they use --download-f-blas-lapack=1 instead of using optimal BLAS. Would
this be the problem which cause the poor performance? Actually the mumps
runs quite slow, at14 Gflop/s,  which is far from the machine's peak.

Thanks.
Wen

>
> Wen :
>
> > Reply to
> >
> >> This is weird.  Try
> >> 1) increase work  space with
> >> -mat_mumps_icntl_14 50 (default is 20)
> >> 2) different matrix orderings with
> >> -mat_mumps_icntl_7 2 (or number from 0 to 6)
> >>
> >> Run your code with '-log_summary' and see which routine causes this huge
> >> difference.
> >>
> > Why your '-log_summary' only gives
> KSPSolve               4 1.0 2.2645e+03 1.0 0.00e+00 0.0 3.9e+04 3.6e+02
> 5.4e+01 96  0 27  0  9  96  0 27  0  9     0
> PCSetUp                4 1.0 2.2633e+03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00
> 3.4e+01 96  0  0  0  6  96  0  0  0  6     0
> PCApply                4 1.0 1.1641e+00 1.0 0.00e+00 0.0 3.9e+04 3.6e+02
> 2.0e+01  0  0 27  0  3   0  0 27  0  3     0
>
> I get
> petsc-dev/src/ksp/ksp/examples/tutorials>mpiexec -n 2 ./ex2 -pc_type lu
> -pc_factor_mat_solver_package mumps -log_summary
> MatMult                2 1.0 1.6904e-04 1.0 4.44e+02 1.0 4.0e+00 5.6e+01
> 0.0e+00  0 47 25 13  0   0 47 33 13  0     5
> MatSolve               2 1.0 3.8259e-03 1.0 0.00e+00 0.0 8.0e+00 1.9e+02
> 6.0e+00 10  0 50 84  7  11  0 67 87  9     0
> MatLUFactorSym         1 1.0 2.9058e-03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00
> 8.0e+00  7  0  0  0  9   8  0  0  0 11     0
> MatLUFactorNum         1 1.0 2.0120e-03 1.0 0.00e+00 0.0 0.0e+00 0.0e+00
> 2.0e+00  5  0  0  0  2   6  0  0  0  3     0
> ...
>
> I like to check these functions. In addition, have you tried other matrix
> orderings?
> Hong
>
> >
> >> Hong
> >>
> >>
> > I just tested the problem according to what you suggested. I set icntl_14
> > = 50 and icntl_7 = 5 (METIS). The problem still persisted. The first
> solve
> > took 920 second and second solve took 215 second with same nonzero
> pattern
> > pc set up. I also attached the log_summary output file. Do you have any
> > further suggestion?  Thanks.
> >
> > Regards,
> > Wen
> >
> >
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120430/a7d3d921/attachment.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: petsc_summary_info
Type: application/octet-stream
Size: 18496 bytes
Desc: not available
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120430/a7d3d921/attachment.obj>