On Sun, Oct 27, 2013 at 6:47 PM, Matthew Knepley knep...@gmail.com wrote:
On Sun, Oct 27, 2013 at 10:04 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Sun, Oct 27, 2013 at 2:53 PM, Matthew Knepley knep...@gmail.comwrote:
On Sat, Oct 26, 2013 at 8:27 AM, Bishesh Khanal
On Fri, Oct 25, 2013 at 10:04 PM, Jed Brown jedbr...@mcs.anl.gov wrote:
Christophe Ortiz christophe.or...@ciemat.es writes:
After playing around, I found something interesting, an option that I
have
never seen in any example: TSSetEquationType. I did a TSGetEquationType
and
I got
Hello,
I need to use DMPlexDistribute in a parallel finite element code.
I would like to know which partitioner can be used with this function.
I saw in an example that chaco is a possibility.
I tried to use parmetis instead but I did not manage to do it.
Furthermore, I do not see where the
For comparison, 3.4.2 gives (from the previous email): 354 MiB for 1
rank, 141 for 2 ranks and 81 for 4 ranks, which is a LOT less. I
suspect this might have something to do with the DA - DMDA change?
Hmm, I wonder where you're getting your numbers from.
From /proc/self/stat, which (for me
On Fri, Oct 25, 2013 at 10:21 PM, Matthew Knepley knep...@gmail.com wrote:
On Fri, Oct 25, 2013 at 2:55 PM, Bishesh Khanal bishes...@gmail.comwrote:
On Fri, Oct 25, 2013 at 8:18 PM, Matthew Knepley knep...@gmail.comwrote:
On Fri, Oct 25, 2013 at 12:09 PM, Bishesh Khanal
I was not looking at the latest version of the code (it seems online
documentation has not been updated yet).
Now, I can see that partitioner is used as an argument of
DMPlexCreatePartition.
However, there is a new argument: a PetscSF.
I have two questions about this new implementation:
1.
Hi there,
I am trying to familiarize myself with unstructured grids. For this I
started with the example given in the petsc-manual (mesh of 2 triangles)
and tried to modify it according to my needs.
However, the example seems to be incomplete. At least I was not able to
create a matrix
I've just seen in DMPlexCreatePartition that only 'chaco' and 'metis' can be
used.
- Mail original -
De: Cedric Doucet cedric.dou...@inria.fr
À: petsc-users@mcs.anl.gov
Envoyé: Lundi 28 Octobre 2013 12:17:22
Objet: Re: [petsc-users] Partitioner in DMPlexDistribute
I was not
The 64 bit integers would at most double the memory usage. It should
actually be a bit less than doubling the memory usages since some of the memory
allocated in DMSetUp_DA() are doubles whose size would remain unchanged. Note
that switching to 64 bit indices would not increase the Vec
On Mon, Oct 28, 2013 at 5:30 AM, Bishesh Khanal bishes...@gmail.com wrote:
On Fri, Oct 25, 2013 at 10:21 PM, Matthew Knepley knep...@gmail.comwrote:
On Fri, Oct 25, 2013 at 2:55 PM, Bishesh Khanal bishes...@gmail.comwrote:
On Fri, Oct 25, 2013 at 8:18 PM, Matthew Knepley
On Mon, Oct 28, 2013 at 6:17 AM, Cedric Doucet cedric.dou...@inria.frwrote:
I was not looking at the latest version of the code (it seems online
documentation has not been updated yet).
Now, I can see that partitioner is used as an argument of
DMPlexCreatePartition.
However, there is a new
Well, when dealing with Fortran I also often encounter software which
cannot be changed or upgraded to a more modern style.
What was in my mind is to create an interface additional to what is already
there in petsc. So this should be compiled along with anyone's code if the
used ocmpiler supports
Hossein Talebi talebi.hoss...@gmail.com writes:
What was in my mind is to create an interface additional to what is already
there in petsc. So this should be compiled along with anyone's code if the
used ocmpiler supports F03 or the necessary features of F03.
I don't think anyone will want to
Exactly, I personally look for:
1) type checking during the function calls. This helps also not looking
into the manual for every single petsc function call.
2) low level access to petsc data structure. For example in my own code I
already have my own hadnling of parallel vectors and matrices.
Christophe Ortiz christophe.or...@ciemat.es writes:
But just to understand what I'm doing, what does TSSetEquationType do
internally ?
It tells the method what is necessary to evaluate stage derivatives, and
affects the starting method and (possibly) what can be carried over from
the last step.
On Mon, Oct 28, 2013 at 1:40 PM, Matthew Knepley knep...@gmail.com wrote:
On Mon, Oct 28, 2013 at 5:30 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Fri, Oct 25, 2013 at 10:21 PM, Matthew Knepley knep...@gmail.comwrote:
On Fri, Oct 25, 2013 at 2:55 PM, Bishesh Khanal
Hossein Talebi talebi.hoss...@gmail.com writes:
Exactly, I personally look for:
1) type checking during the function calls. This helps also not looking
into the manual for every single petsc function call.
2) low level access to petsc data structure. For example in my own code I
already
On Mon, Oct 28, 2013 at 9:06 AM, Bishesh Khanal bishes...@gmail.com wrote:
On Mon, Oct 28, 2013 at 1:40 PM, Matthew Knepley knep...@gmail.comwrote:
On Mon, Oct 28, 2013 at 5:30 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Fri, Oct 25, 2013 at 10:21 PM, Matthew Knepley
On Mon, Oct 28, 2013 at 3:49 PM, Matthew Knepley knep...@gmail.com wrote:
On Mon, Oct 28, 2013 at 9:06 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Mon, Oct 28, 2013 at 1:40 PM, Matthew Knepley knep...@gmail.comwrote:
On Mon, Oct 28, 2013 at 5:30 AM, Bishesh Khanal
On Mon, Oct 28, 2013 at 6:17 AM, Bernhard Reinhardt
b.reinha...@physik.uni-muenchen.de wrote:
Hi there,
I am trying to familiarize myself with unstructured grids. For this I
started with the example given in the petsc-manual (mesh of 2 triangles)
and tried to modify it according to my
1. You really need to profile. Copying a vector is cheap.
You are right. Maybe I make a big thing for this copy in/out and it is
not that problematic or slow even for the whole 2D matrix. I have to test
it with a large one to see.
2. If you make your functions (to evaluate residuals, etc)
/cygdrive/c/Windows/SUA/common/rm -f -rf
/cygdrive/c/cygwin_cache/petsc-3.4.3/arch-mswin-c-opt/lib/libpetsc*.*
You appear to have non cygwin stuff in your PATH. Can you remove these
things from your PATH - make sure grep in PATH is from cygwin - and
rerun configure make
Satish
On Mon, 28
Satish,
As far as I know, cygwin reads the Windows enviromental variable PATH. Can I
not change the the setting in in the Windows enviromental variables (since
other programs need them), but change the PATH used by cygwin only? Which file
should I change?
Thanks,
Qin
On Monday, October
cygwin should have already setup PATH correctly so that its listed first
What do you have for:
echo $PATH
which make
which rm
which grep
export PATH=/usr/bin:$PATH
which make
which rm
which grep
Satish
On Mon, 28 Oct 2013, Qin Lu wrote:
Satish,
As far as I know, cygwin reads the Windows
On Mon, Oct 28, 2013 at 10:13 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Mon, Oct 28, 2013 at 3:49 PM, Matthew Knepley knep...@gmail.comwrote:
On Mon, Oct 28, 2013 at 9:06 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Mon, Oct 28, 2013 at 1:40 PM, Matthew Knepley
Hi all,
Does Petsc provide any support to export and view a petsc vector/mat ?
Thanks.
Shiyuan
Shiyuan Gu shiyua...@gmail.com writes:
Hi all,
Does Petsc provide any support to export and view a petsc vector/mat ?
See $PETSC_DIR/bin/pythonscripts/PetscBinaryIO.py. You can read or
write the PETSc format as Numpy matrices.
pgpQnnLkTL8Pg.pgp
Description: PGP signature
Thanks Jed.
Is there an convenient way to save petsc objects to a binary file in gdb?
On Mon, Oct 28, 2013 at 1:18 PM, Jed Brown jedbr...@mcs.anl.gov wrote:
Shiyuan Gu shiyua...@gmail.com writes:
Hi all,
Does Petsc provide any support to export and view a petsc
vector/mat ?
See
Shiyuan Gu shiyua...@gmail.com writes:
Thanks Jed.
Is there an convenient way to save petsc objects to a binary file in gdb?
call VecView(X,PETSC_VIEWER_BINARY_WORLD)?
pgp70A1bxgewT.pgp
Description: PGP signature
On Mon, Oct 28, 2013 at 1:57 PM, Jed Brown jedbr...@mcs.anl.gov wrote:
Shiyuan Gu shiyua...@gmail.com writes:
Thanks Jed.
Is there an convenient way to save petsc objects to a binary file in gdb?
call VecView(X,PETSC_VIEWER_BINARY_WORLD)?
That never works for me. I use
call
Matthew Knepley knep...@gmail.com writes:
That never works for me. I use
call VecView(X, PETSC_VIEWER_BINARY_(PETSC_COMM_WORLD))
Oh, right. The debugger doesn't see macros to expand them automatically.
pgpTcJudhMIKQ.pgp
Description: PGP signature
On Mon, Oct 28, 2013 at 6:19 PM, Matthew Knepley knep...@gmail.com wrote:
On Mon, Oct 28, 2013 at 10:13 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Mon, Oct 28, 2013 at 3:49 PM, Matthew Knepley knep...@gmail.comwrote:
On Mon, Oct 28, 2013 at 9:06 AM, Bishesh Khanal
On Mon, Oct 28, 2013 at 2:51 PM, Bishesh Khanal bishes...@gmail.com wrote:
On Mon, Oct 28, 2013 at 6:19 PM, Matthew Knepley knep...@gmail.comwrote:
On Mon, Oct 28, 2013 at 10:13 AM, Bishesh Khanal bishes...@gmail.comwrote:
On Mon, Oct 28, 2013 at 3:49 PM, Matthew Knepley
You appear to have 2 issues:
fp.c^M
C:\CYGWIN~1\PETSC-~1.2\src\sys\error\fp.c(425): error: expression must have
arithmetic or pointer type^M
if (feclearexcept(FE_ALL_EXCEPT))
SETERRQ(PETSC_COMM_SELF,PETSC_ERR_LIB,Cannot clear floating point exception
flags\n);^M
^^M
^M
34 matches
Mail list logo