July 2012 - petsc-dev - mailman3.cels.anl.gov

Re: [petsc-dev] Fwd: Request for information for Energy Workshop
by Matthew Knepley 14 Jul '12

14 Jul '12

On Fri, Jul 13, 2012 at 4:12 PM, Barry Smith <bsmith(a)mcs.anl.gov> wrote: > > This workshop gives us a chance to show DOE and industrial folks that > we are serious about moving PETSc technology towards industry. Please find > attached some slides I've prepared with the Tech-X folks to be used at this > meeting. > > I'd appreciate any feedback on improving the presentation etc (we > don't have room for many more slides). > I liked your slides. Do you want to mention anything about 24-7 support by a team of qualified people? Industry is usually very big on support, and maybe that PETSc can now drink (21 yrs old)? Matt > Thanks > > Barry > > > [see attached file: PetscIndustry-1.pptx] > > > Begin forwarded message: > > *From: *"Diachin, Lori A." <diachin2(a)llnl.gov> > *Date: *July 12, 2012 12:02:31 PM CDT > *To: *"fastmath-team(a)lists.llnl.gov" <fastmath-team(a)lists.llnl.gov> > *Subject: **Request for information for Energy Workshop* > *Reply-To: *"Diachin, Lori A." <diachin2(a)llnl.gov> > > Hi All, > > As I mentioned in the web page content request, I am giving a FASTMath > presentation at the end of July to a workshop focused on HPC use for > industry and applied energy applications. I only 15-20 minutes for my > portion of the 'tutorial' on HPC resources, including software, at DOE, but > in that time I'd like to highlight use of FASTMath software in industrial > or applied energy settings. > > If you have example of use of your algorithms/technologies/software in > this way, please let me know. I'd appreciate a ppt single slide that > covered the following: > > - goal of the project > - technology/approach used (1-2 bullets) > - impact or expected benefit > - a pretty picture > - notes that I can use when I'm speaking to the slide. > > If you could send me any such examples by the end of next week, July 20, > that would be great. > > Thanks in advance, > Lori > > > -- 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

1 0

parallel GPU implementation
by Olga Tramontano 14 Jul '12

14 Jul '12

Hi all I was trying to study Petsc for GPUs... I don't understand this: in the sequential implementation there's one process that uses a signle GPU... and that's ok! What about the parallel implementation for GPUs? Are there multiple processes using the same GPU, or each proess uses a separate GPU like its own...? Thanks

1 0

--with-precision=__float128 tells me to use --download-f-blas-lapack, but I really need --download-f2cblaslapack
by Jed Brown 13 Jul '12

13 Jul '12

******************************************************************************* UNABLE to CONFIGURE with GIVEN OPTIONS (see configure.log for details): ------------------------------------------------------------------------------- Could not use downloaded f-blas-lapack? ******************************************************************************* What is the intent here? Make f-blas-lapack work or tell the user about f2cblaslapack?

1 0

helping PETSc user get started the right way!
by Barry Smith 13 Jul '12

13 Jul '12

We should consider a system that helps PETSc users auto-magically set up bitbucket (or similar but better place) repository for their PETSc derived code. Now we tell people to copy a PETSc example and its make file and start developing from that. Perhaps we could provide a python script that 1) made a directory 2) hg init it 3) copy over the makefile and example 4) hg add them 5) hg commit them 6) hg clone up to somewhere (bitbucket or elsewhere, PETSc machine?) and fix the .hg/hgrc location Then they need only do hg commit; hg push to share their latest work anytime. Barry Begin forwarded message: > From: Jed Brown <jedbrown(a)mcs.anl.gov> > Date: July 13, 2012 5:53:54 PM CDT > To: Barry Smith <bsmith(a)mcs.anl.gov> > Cc: Lulu Liu <lulu.liu(a)kaust.edu.sa>, Satish Balay <balay(a)mcs.anl.gov>, Hong Zhang <hzhang(a)mcs.anl.gov> > Subject: Re: null space in Lulu's model > > On Fri, Jul 13, 2012 at 5:45 PM, Barry Smith <bsmith(a)mcs.anl.gov> wrote: > I am talking about NOW at this stage, regardless we need a good robust Newton style approach and it takes like 10 minutes to test with fieldsplit. Come on Jed, you're sounding like a usual brain-dead PETSc user "jump to the hard-stuff before doing the needed background work". > > Sure. > > Lulu, where is your source repository? If it's not somewhere yet, create an account at bitbucket.org and put it there. You can make it private if you like, but give "jedbrown", "prbrune", and "barrysmith" access. Then we can quickly experiment and give you feedback.

1 0

Re: [petsc-dev] Assertion at agg.c:514 tripped
by Mark F. Adams 13 Jul '12

13 Jul '12

I have added this code: if(sgid != -1 ) { SETERRQ(PETSC_COMM_SELF,PETSC_ERR_PLIB,"Have un-symmetric graph (apparently). Use '-pc_gamg_sym_graph true' to symetrize the graph or '-pc_gamg_threshold 0.0' if the matrix is structurally symmetric."); } I'm trying to build now. LuLu: I've changed the defaults so it looks like you want to add '-pc_gamg_sym_graph true' to get back to the old semantics. Mark On Jul 13, 2012, at 6:20 PM, Jed Brown wrote: > Mark, in a nonsymmetric (but structurally symmetric) bs=2 problem from Lulu, we are tripping this assertion. > > else{ /* I'm stealing this local, owned by a ghost */ > assert(sgid==-1); > > > What does this mean? Can't we at least always use SETERRQ for errors? > > > Also from that section of code, I notice you are using PETSC_ERR_LIB for internal PETSc logic/corruption errors. They look like they should be PETSC_ERR_PLIB.

1 0

Assertion at agg.c:514 tripped
by Jed Brown 13 Jul '12

13 Jul '12

Mark, in a nonsymmetric (but structurally symmetric) bs=2 problem from Lulu, we are tripping this assertion. else{ /* I'm stealing this local, owned by a ghost */ assert(sgid==-1); What does this mean? Can't we at least always use SETERRQ for errors? Also from that section of code, I notice you are using PETSC_ERR_LIB for internal PETSc logic/corruption errors. They look like they should be PETSC_ERR_PLIB.

1 0

Fwd: Request for information for Energy Workshop
by Barry Smith 13 Jul '12

13 Jul '12

This workshop gives us a chance to show DOE and industrial folks that we are serious about moving PETSc technology towards industry. Please find attached some slides I've prepared with the Tech-X folks to be used at this meeting. I'd appreciate any feedback on improving the presentation etc (we don't have room for many more slides). Thanks Barry Begin forwarded message: > From: "Diachin, Lori A." <diachin2(a)llnl.gov> > Date: July 12, 2012 12:02:31 PM CDT > To: "fastmath-team(a)lists.llnl.gov" <fastmath-team(a)lists.llnl.gov> > Subject: Request for information for Energy Workshop > Reply-To: "Diachin, Lori A." <diachin2(a)llnl.gov> > > Hi All, > > As I mentioned in the web page content request, I am giving a FASTMath presentation at the end of July to a workshop focused on HPC use for industry and applied energy applications. I only 15-20 minutes for my portion of the 'tutorial' on HPC resources, including software, at DOE, but in that time I'd like to highlight use of FASTMath software in industrial or applied energy settings. > > If you have example of use of your algorithms/technologies/software in this way, please let me know. I'd appreciate a ppt single slide that covered the following: > > - goal of the project > - technology/approach used (1-2 bullets) > - impact or expected benefit > - a pretty picture > - notes that I can use when I'm speaking to the slide. > > If you could send me any such examples by the end of next week, July 20, that would be great. > > Thanks in advance, > Lori

1 0

Re: [petsc-dev] patch: fortran binding for PetscOptionsView
by Jed Brown 13 Jul '12

13 Jul '12

On Fri, Jul 13, 2012 at 7:45 AM, Blaise Bourdin <bourdin(a)lsu.edu> wrote: > Hi, > > Here is a trivial patch that adds fortran binding for PetscOptionsView. Is > it possible to apply it to petsc-3.3 and petsc-dev? > Thanks. http://petsc.cs.iit.edu/petsc/releases/petsc-3.3/rev/cbd93afde6b9 > > Blaise > > > -- > Department of Mathematics and Center for Computation & Technology > Louisiana State University, Baton Rouge, LA 70803, USA > Tel. +1 (225) 578 1612, Fax +1 (225) 578 4276 > http://www.math.lsu.edu/~bourdin > > > > > > > > >

1 0

patch: fortran binding for PetscOptionsView
by Blaise Bourdin 13 Jul '12

13 Jul '12

Hi, Here is a trivial patch that adds fortran binding for PetscOptionsView. Is it possible to apply it to petsc-3.3 and petsc-dev? Blaise -- Department of Mathematics and Center for Computation & Technology Louisiana State University, Baton Rouge, LA 70803, USA Tel. +1 (225) 578 1612, Fax +1 (225) 578 4276 http://www.math.lsu.edu/~bourdin

1 0

Re: [petsc-dev] PetscSegv_sigaction / PetscCheckPointer don't build using visual studio
by Chetan Jhurani 12 Jul '12

12 Jul '12

Thanks! Chetan > -----Original Message----- > From: petsc-dev-bounces(a)mcs.anl.gov [mailto:[email protected]] On Behalf Of Satish Balay > Sent: Thursday, July 12, 2012 4:36 PM > To: For users of the development version of PETSc > Subject: Re: [petsc-dev] PetscSegv_sigaction / PetscCheckPointer don't build using visual studio > > On Wed, 11 Jul 2012, Chetan Jhurani wrote: > > > Hi, > > > > The recent changes to PetscCheckPointer in petsc-dev > > don't build on windows when using Visual Studio 2005 and 2010. > > > > They have a very bare-bones signal implementation. > > http://msdn.microsoft.com/en-us/library/xdkz3x12.aspx > > > > The first error encountered is due to this new code in > > petsc-private/petscimpl.h > > > > #if defined(PETSC_HAVE_SETJMP_H) > > #include <signal.h> > > #include <setjmp.h> > > PETSC_EXTERN jmp_buf PetscSegvJumpBuf; > > PETSC_EXTERN void PetscSegv_sigaction(int, siginfo_t*, void *); > > > > PETSC_HAVE_SETJMP_H is 1 and both signal.h and setjmp.h > > are found but they don't define siginfo_t. I'm sure there > > the compiler doesn't implement a lot of other stuff in > > PetscCheckPointer. > > fixed now. > > http://petsc.cs.iit.edu/petsc/petsc-dev/rev/68976e0f458f > http://petsc.cs.iit.edu/petsc/BuildSystem/rev/71be541c881b > > Satish

1 0