- petsc-dev - mailman3.cels.anl.gov

Looking to hire more PETSc team developers
by Barry Smith 04 May '07

04 May '07

PETSc Users, We are looking to try to hire one or more PETSc developers who would work on PETSc and one or two large application codes that use PETSc. So experience with PETSc and C or C++ programming would be a must. There would be a possibility of working at Argonne as an Argonne employee or possibly with a sub-contract. If you are interested, please let me know directly bsmith(a)mcs.anl.gov and send a CV and some indications of your experience with PETSc. Thanks Barry

1 0

changes to Matrix free Mat
by Barry Smith 20 Apr '07

20 Apr '07

I have refactored the SNESMF code into MFFD code that now goes in src/mat/impls and a tiny child class that incorporates SNES. See src/docs/website/documentation/changes/dev.html Please let me know quickly if this breaks anything. Barry

1 0

Re: MUMPS
by Hong Zhang 17 Apr '07

17 Apr '07

Dirk, Thanks for the info. I'll update petsc-dev interface. The mumps developers have promised me to notify me whenever there is a new release :-) Hong On Wed, 18 Apr 2007, Dirk Clasen wrote: > Hi everyone, > > will there be an upgrade to MUMPS 4.7.1 soon? I've updated my petsc-dev > an PETSc still uses 4.6.4 > > Best regards, > Dirk > >

1 0

MUMPS
by Dirk Clasen 17 Apr '07

17 Apr '07

Hi everyone, will there be an upgrade to MUMPS 4.7.1 soon? I've updated my petsc-dev an PETSc still uses 4.6.4 Best regards, Dirk

1 0

Re: DDM with PETSc
by Matthew Knepley 31 Mar '07

31 Mar '07

I would look at some PETSc examples, for instance http://www-unix.mcs.anl.gov/petsc/petsc-as/snapshots/petsc-current/src/ksp/… Matt On 3/31/07, Waad Subber <wsubber(a)connect.carleton.ca> wrote: > Hello everyone: > > I am new to PETSC. Reading the tutorials, I understand that PETSC > supports domain decomposition with additive Schwartz and iterative > substructuring (balancing Neumann-Neumann). I am looking for some > example codes involving these domain decomposition methods for 1D and > 2D PDE (preferable linear PDE) so that I can get started. Can anyone > kindly point me to the right place where I can find them. > > Thanks :) > > waad > > -- One trouble is that despite this system, anyone who reads journals widely and critically is forced to realize that there are scarcely any bars to eventual publication. There seems to be no study too fragmented, no hypothesis too trivial, no literature citation too biased or too egotistical, no design too warped, no methodology too bungled, no presentation of results too inaccurate, too obscure, and too contradictory, no analysis too self-serving, no argument too circular, no conclusions too trifling or too unjustified, and no grammar and syntax too offensive for a paper to end up in print. -- Drummond Rennie

1 0

DDM with PETSc
by Waad Subber 31 Mar '07

31 Mar '07

Hello everyone: I am new to PETSC. Reading the tutorials, I understand that PETSC supports domain decomposition with additive Schwartz and iterative substructuring (balancing Neumann-Neumann). I am looking for some example codes involving these domain decomposition methods for 1D and 2D PDE (preferable linear PDE) so that I can get started. Can anyone kindly point me to the right place where I can find them. Thanks :) waad

1 0

mpirun --> mpiexec in petsc-dev
by Barry Smith 06 Mar '07

06 Mar '07

I have updated the PETSc-dev src/bin/configure.py to use mpiexec/MPIEXEC instead of mpirun/MPIRUN as the variable names. program names etc. Let us know if this introduces any problems. Barry

1 0

recompile all after next pull to petsc-dev
by Barry Smith 25 Feb '07

25 Feb '07

petsc-dev users, After your next petsc-dev pull please rerun make in the root directory to rebuild all the libraries. Barry

1 0

Re: update to BuildSystem-dev for parmetis on Apple
by Victor Eijkhout 28 Jan '07

28 Jan '07

On Jan 28, 2007, at 1:12 PM, Satish Balay wrote: > Are you sure you have the correct sources? I don't get > such errors with current petsc-dev > > Things to check. [with both petsc-dev & BuildSystem] > > - do you have any edited fies? > hg status > > - did you update the sources after pull? > hg update > > > If you have no local edits - then use the following to > make sure the workingdir sources are uptodate > cd petsc-dev > make pull PETSC_ARCH=docsonly [albook:~/Software/petsc/petsc-dev] %% hg status ? 1 [albook:~/Software/petsc/petsc-dev] %% less ../Makefile [albook:~/Software/petsc/petsc-dev] %% hg update 0 files updated, 0 files merged, 0 files removed, 0 files unresolved [albook:~/Software/petsc/petsc-dev] %% less ../Makefile [albook:~/Software/petsc/petsc-dev] %% (cd python/BuildSystem/ ; hg update) 0 files updated, 0 files merged, 0 files removed, 0 files unresolved [albook:~/Software/petsc/petsc-dev] %% make pull PETSC_ARCH=docsonly pulling from http://mercurial.mcs.anl.gov/petsc/petsc-dev searching for changes no changes found 0 files updated, 0 files merged, 0 files removed, 0 files unresolved pulling from http://mercurial.mcs.anl.gov/petsc/BuildSystem searching for changes no changes found 0 files updated, 0 files merged, 0 files removed, 0 files unresolved Anyway, fresh clone and it worked. Victor. > > Satish > > On Sun, 28 Jan 2007, Victor Eijkhout wrote: > >> No module named Fiat. >> >> I did a pull of the source and buildsystem. >> >> Victor. >> >> > -- Victor Eijkhout, 512 471 5809 (w), 512 499 0504 (h) Texas Advanced Computing Center, The University of Texas at Austin

1 0

Re: update to BuildSystem-dev for parmetis on Apple
by Satish Balay 28 Jan '07

28 Jan '07

Are you sure you have the correct sources? I don't get such errors with current petsc-dev Things to check. [with both petsc-dev & BuildSystem] - do you have any edited fies? hg status - did you update the sources after pull? hg update If you have no local edits - then use the following to make sure the workingdir sources are uptodate cd petsc-dev make pull PETSC_ARCH=docsonly Satish On Sun, 28 Jan 2007, Victor Eijkhout wrote: > No module named Fiat. > > I did a pull of the source and buildsystem. > > Victor. > >

1 0