[petsc-users] Slow linear solver via MUMPS

[Matthew Knepley]

On Fri, Jan 25, 2019 at 9:06 PM Mohammad Gohardoust via petsc-users <
petsc-users at mcs.anl.gov> wrote:

> Hi,
>
> I am trying to modify a "pure MPI" code for solving water movement
> equation in soils which employs KSP iterative solvers. This code gets
> really slow in the hpc I am testing it as I increase the number of
> calculating nodes (each node has 28 cores) even from 1 to 2. I went for
> implementing "MPI-OpenMP" solutions like MUMPS. I did this inside the petsc
> by:
>

In my opinion, this is not a great strategy. You should figure out what is
happening with MUMPS first. Second, you
should consider not using LU because it is not that scalable. First, when
you run in parallel, are you having MUMPS
calculate the ordering in parallel? Second, it sounds like you are running
on a single node. Do not expect to get much
speedup with either processes or threads here because all your operations
are limited by memory bandwidth, not
compute power, and the node has a fixed bandwidth.

  Thanks,

    Matt


> KSPSetType(ksp, KSPPREONLY);
> PCSetType(pc, PCLU);
> PCFactorSetMatSolverType(pc, MATSOLVERMUMPS);
> KSPSolve(ksp, ...
>
> and I run it through:
>
> export OMP_NUM_THREADS=16 && mpirun -n 2 ~/Programs/my_programs
>
> The code is working (in my own PC) but it is too slow (maybe about 50
> times slower). Since I am not an expert, I like to know is this what I
> should expect from MUMPS!?
>
> Thanks,
> Mohammad
>
>

-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener

https://www.cse.buffalo.edu/~knepley/ <http://www.cse.buffalo.edu/~knepley/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20190126/5d3bed46/attachment.html>