On Tue, Jul 10, 2012 at 11:59 AM, Thomas Hisch t.hisch at gmail.com wrote:
Thx for the hint.
Should PETSc-dev in principle work with gcc-4.7, because I get the
following error while building petsc:
Jed is fixing that now. C++ compilers are extraordinarily dumb, and cannot
cast
a 'volatile
On Thu, Jul 12, 2012 at 10:42 AM, Olga Tramontano
tramontanoolga at yahoo.itwrote:
Hi all
I am very new to PETSc. I just learnt its class structure and I just
understood that the interface Vec has been reimplemented with the class
VecCUSP that is able to support GPU. My question is: if I have
On Fri, Jul 13, 2012 at 4:12 PM, Barry Smith bsmith at 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
On Sat, Jul 14, 2012 at 2:43 AM, Olga Tramontano tramontanoolga at
yahoo.itwrote:
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
I saw a good talk by Chris Baker at SIAM about multiprecision solvers, and
was suitably embarrassed that we cannot do
this. I still strongly believe that templates are the wrong solution, and
mucking up perfectly good interfaces with a
bunch of types we do not care about is wrong. I now have a
On Sun, Jul 15, 2012 at 4:12 AM, ??? 330358508 at qq.com wrote:
Hello?
I get the information that you run pflotran on GPU and test it, these days
I?m trying to find the GPU version of pflotran, could you send me a copy of
your GPU version?
PFLOTRAN, as I understand, only uses the GPU
On Mon, Jul 16, 2012 at 9:35 AM, Olga Tramontano tramontanoolga at
yahoo.itwrote:
Hi all
I need to know which part of PETSc has been suited to gpus.
I think that only Vec and Mat classes have been extended for GPUs. Am I
wrong?
Please read the paper:
PM, Barry Smith bsmith at mcs.anl.gov
wrote:
On Jul 7, 2012, at 3:23 AM, Dmitry Karpeev wrote:
On Fri, Jul 6, 2012 at 9:56 PM, Barry Smith bsmith at mcs.anl.gov
wrote:
On Jul 6, 2012, at 9:35 PM, Matthew Knepley wrote:
On Fri, Jul 6, 2012
On Sun, Jul 22, 2012 at 1:19 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
We recommend to people that they just call MatSetNullSpace() and solve the
singular system. What if reductions are very expensive? Are there Krylov
methods that accommodate a pipelined or deferred null space removal?
I think we just need a small converter from AIJ:
https://bitbucket.org/poulson/clique/src/dc417c7e9403/tests/DistSparseMatrix.cpp
Matt
--
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments
On Mon, Jul 23, 2012 at 10:12 AM, Hong Zhang hzhang at mcs.anl.gov wrote:
Xuan will take a look at this.
He has added nice variables for the build as well
http://poulson.github.com/Elemental/build.html#testing-the-installation
Matt
Hong
On Mon, Jul 23, 2012 at 9:47 AM, Matthew
On Thu, Jul 26, 2012 at 11:08 AM, Satish Balay balay at mcs.anl.gov wrote:
On Thu, 26 Jul 2012, Jed Brown wrote:
On Thu, Jul 26, 2012 at 10:41 AM, Satish Balay balay at mcs.anl.gov
wrote:
The naming/clasification is not perfect.
Looks like Barry tried to fix this - by adding a
On Thu, Jul 26, 2012 at 11:32 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 11:08 AM, Satish Balay balay at mcs.anl.gov wrote:
I think python is fine - as long as the run targets still remain in
the makefile.
Are you saying each 'run' target in the makefile will be
locally.
On Thu, Jul 26, 2012 at 11:37 AM, Matthew Knepley knepley at gmail.comwrote:
./test.py build ex19
$ config/builder2.py buildExample src/snes/examples/tutorials/ex19.c
Namespace(files=['src/snes/examples/tutorials/ex19.c'], func=function
buildExample at 0x1fa56e0)
Building ['/home/jed
On Thu, Jul 26, 2012 at 1:52 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 1:30 PM, Matthew Knepley knepley at gmail.comwrote:
On Thu, Jul 26, 2012 at 12:21 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
Builder does some of this, but I think not all, and I don't think
On Thu, Jul 26, 2012 at 2:31 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 2:17 PM, Matthew Knepley knepley at gmail.comwrote:
You can tell from the primary key what it is. If the primary key is
wrong, it does not help you in your scenario as it could be
misspelled
On Thu, Jul 26, 2012 at 2:31 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 2:17 PM, Matthew Knepley knepley at gmail.comwrote:
You can tell from the primary key what it is. If the primary key is
wrong, it does not help you in your scenario as it could be
misspelled
On Thu, Jul 26, 2012 at 2:39 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 2:34 PM, Matthew Knepley knepley at gmail.comwrote:
Well, that's an interesting (and confusing) idea for how it *could* work
some day, but it's not how it currently works.
How the fuck
On Thu, Jul 26, 2012 at 2:49 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 26, 2012 at 2:44 PM, Matthew Knepley knepley at gmail.comwrote:
You do not read it correctly. It operates exactly as everything else. You
move make.log to make.log.bkp, which is what we do now, and
write
I like it.
Matt
On Fri, Jul 27, 2012 at 2:35 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
I'm sick of truncated PETSC_ARCH in log_summary. Does anyone object to my
pushing the following to petsc-3.3? Should we just make all the fields huge
so we're guaranteed to get everything? Since pname
On Sat, Jul 28, 2012 at 6:53 AM, Gerard Gorman g.gorman at
imperial.ac.ukwrote:
Slightly off topic - but I have Buildbot set up locally to keep an eye
on petsc-dev and various branches of petsc that I care about (if you are
curious see http://stereolab.ese.ic.ac.uk:8080/waterfall - knock
On Sat, Jul 28, 2012 at 4:00 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Jul 19, 2012 at 2:07 PM, Barry Smith bsmith at mcs.anl.gov wrote:
I agree, but I could not find an easy way.
Can you find a difficult way ?
We chose to make the DM both a factory for creating stuff and a
On Sun, Jul 29, 2012 at 3:56 PM, Barry Smith bsmith at mcs.anl.gov wrote:
The problem with the programming model they propose, namely unroll the
entire
task graph and schedule, is that it has been proposed at least 20 times
before
by smart, well-funded people. These slides just tell us how the
On Mon, Aug 13, 2012 at 11:57 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Aug 13, 2012 at 10:45 AM, Barry Smith bsmith at mcs.anl.gov wrote:
I propose to remove MatGetArray() from PETSc and insert
MatSeqDenseGetArray()for all the uses with in that case (where it
appears often
On Mon, Aug 13, 2012 at 12:07 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Aug 13, 2012, at 12:05 PM, Hong Zhang hzhang at mcs.anl.gov wrote:
Barry,
Elemental interface is not well tested yet.
I would wait for few months to remove PLAPACK stuff.
PLAPACK stuff is (and never was)
On Tue, Aug 14, 2012 at 4:28 PM, Peter Brune prbrune at gmail.com wrote:
This is a problem I've been harping on but should harp on more; It is
IMPOSSIBLE to reset the context on a lot of things to null after it's been
set. What's happening is that the context is being set as the TS object in
On Tue, Aug 14, 2012 at 4:40 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Aug 14, 2012 at 3:35 PM, Matthew Knepley knepley at gmail.comwrote:
I guess I do not understand. What is the context set API? Why can't you
pass NULL?
You can, but the setter routines interpret NULL as ignore
On Tue, Aug 14, 2012 at 4:47 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Aug 14, 2012 at 3:44 PM, Matthew Knepley knepley at gmail.comwrote:
You can, but the setter routines interpret NULL as ignore, i.e.
if (func) ctx-func = func;
Does this make sense to anyone? Can we remove
On Fri, Aug 17, 2012 at 1:21 PM, Chris Eldred chris.eldred at gmail.comwrote:
I was wondering how ghost values were handled when creating a
distributed (global) vector from a specific PetscSection over a
DMComplex object- ie what defines the stencils used to figure out
which values need to be
On Fri, Aug 17, 2012 at 1:24 PM, Matthew Knepley knepley at gmail.com
wrote:
On Fri, Aug 17, 2012 at 1:21 PM, Chris Eldred chris.eldred at gmail.com
wrote:
I was wondering how ghost values were handled when creating a
distributed (global) vector from a specific PetscSection over
On Sun, Aug 19, 2012 at 2:31 AM, Dmitry Karpeev karpeev at mcs.anl.gov wrote:
I just pushed a couple of fixes to PCFIELDSPLIT in petsc-3.3 (
http://petsc.cs.iit.edu/petsc/releases/petsc-3.3/rev/943dde820f7f,
http://petsc.cs.iit.edu/petsc/releases/petsc-3.3/rev/5a9ebf885615) In
particular,
Wolfgang is not wrong here. I was against the name change :)
Matt
-- Forwarded message --
From: Wolfgang Bangerth bange...@math.tamu.edu
Date: Mon, Aug 20, 2012 at 10:30 PM
Subject: Changes in PETSc
To: Matthew Knepley knepley at ci.uchicago.edu, Toby D. Young
tyoung
On Tue, Aug 21, 2012 at 11:24 AM, Barry Smith bsmith at mcs.anl.gov wrote:
On Aug 21, 2012, at 10:53 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Aug 21, 2012 at 10:39 AM, Matthew Knepley
knepley at ci.uchicago.edu wrote:
Wolfgang is not wrong here. I was against the name change
On Tue, Aug 21, 2012 at 8:46 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Aug 21, 2012 at 2:53 AM, Dmitry Karpeev karpeev at mcs.anl.govwrote:
On Mon, Aug 20, 2012 at 8:36 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Aug 20, 2012 at 4:02 AM, Dmitry Karpeev karpeev at
On Tue, Aug 21, 2012 at 8:59 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Aug 21, 2012 at 8:51 PM, Matthew Knepley knepley at gmail.comwrote:
I thought we agreed in this thread that we were (for now) going with
Matt's bastardized model of attaching the Schur null space to A11. Doesn't
On Thu, Aug 23, 2012 at 12:19 PM, Chris Eldred chris.eldred at gmail.comwrote:
I am working with a 2D unstructured mesh using sieve and I wanted to
get some advice on how to determine adjacency relations using the
topological operators provided by Sieve (cone, support, closure,
star). I have
.
Okay, then for parallelism, I think you need nothing more than the SF we get
from Jacobian preallocation.
Thanks,
Matt
On Thu, Aug 23, 2012 at 12:17 PM, Matthew Knepley knepley at gmail.com
wrote:
On Thu, Aug 23, 2012 at 12:26 PM, Chris Eldred chris.eldred at gmail.com
wrote
On Thu, Aug 23, 2012 at 2:08 PM, Chris Eldred chris.eldred at gmail.comwrote:
Awesome- that is easy. How do I access that SF?
I destroy it inside DMComplexPreallocateOperator(), but we can preserve it.
Matt
On Thu, Aug 23, 2012 at 12:54 PM, Matthew Knepley knepley at gmail.com
wrote
/run into
issues!
-Chris
On Thu, Aug 23, 2012 at 12:22 PM, Matthew Knepley knepley at gmail.com
wrote:
On Thu, Aug 23, 2012 at 12:19 PM, Chris Eldred chris.eldred at gmail.com
wrote:
I am working with a 2D unstructured mesh using sieve and I wanted to
get some advice on how
On Fri, Aug 24, 2012 at 2:16 PM, Chris Eldred chris.eldred at gmail.comwrote:
The following code snippet does not appear to be working:
1) I hate Fortran. A lot. It is not debuggable.
2) Here is my code that should work, but the do loop somehow does not work:
program main
On Fri, Aug 24, 2012 at 3:48 PM, Blaise Bourdin bourdin at lsu.edu wrote:
I am attaching a debugged version.
Checked in as DMComplex ex1f90.F
Matt
Blaise
On Aug 24, 2012, at 3:30 PM, Matthew Knepley knepley at gmail.com wrote:
On Fri, Aug 24, 2012 at 2:16 PM, Chris Eldred
That depends on what the meaning of IS is.
Matt
On Mon, Aug 27, 2012 at 3:38 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
As the recent petsc-maint pointed out, IS is now a Fortran keyword. Is
petsc-3.4 time to namespace more types? Just PetscIS or also PetscVec,
PetscMat, etc?
--
On Mon, Aug 27, 2012 at 5:45 PM, Barry Smith bsmith at mcs.anl.gov wrote:
Does Fortran2008 have Vec Mat etc also as keywords?
If you are going to change IS - PetscIS then you should change every
stinking non-name-spaced thing in PETSc and boy Matt will be happy. Doesn't
this change
On Tue, Aug 28, 2012 at 4:39 PM, Chris Eldred chris.eldred at gmail.comwrote:
DMComplexGetTransitiveClosure does not appear to have the calling
sequence (DM dm, PetscInt p, PetscBool useCone, PetscInt *numPoints,
PetscInt *points[]) indicated in the documentation- instead it has DM
dm,
On Tue, Aug 28, 2012 at 4:49 PM, Chris Eldred chris.eldred at gmail.comwrote:
I am getting a segmentation fault when calling PetscSectionCreate. The
error is:
[0]PETSC ERROR:
[0]PETSC ERROR: Caught signal number 11
On Tue, Aug 28, 2012 at 5:01 PM, Chris Eldred chris.eldred at gmail.comwrote:
On Tue, Aug 28, 2012 at 3:49 PM, Matthew Knepley knepley at gmail.com
wrote:
On Tue, Aug 28, 2012 at 4:39 PM, Chris Eldred chris.eldred at gmail.com
wrote:
DMComplexGetTransitiveClosure does not appear to have
On Tue, Aug 28, 2012 at 4:58 PM, Chris Eldred chris.eldred at gmail.comwrote:
Building on the previous example code (for the Doublet mesh), I am
getting an error when trying to set Cone orientations:
[0]PETSC ERROR: - Error Message
debugging.
Matt
On Tue, Aug 28, 2012 at 8:16 PM, Matthew Knepley knepley at gmail.com
wrote:
On Tue, Aug 28, 2012 at 5:01 PM, Chris Eldred chris.eldred at gmail.com
wrote:
On Tue, Aug 28, 2012 at 3:49 PM, Matthew Knepley knepley at gmail.com
wrote:
On Tue, Aug 28, 2012 at 4:39 PM
)
edge: Complex of dimension 1
face:Complex of co-dimension 1 (notice it can also be an edge in 2D)
Thanks,
Matt
On Wed, Aug 29, 2012 at 8:51 PM, Matthew Knepley knepley at gmail.com
wrote:
On Wed, Aug 29, 2012 at 1:35 PM, Chris Eldred chris.eldred at gmail.com
wrote
On Thu, Aug 30, 2012 at 5:10 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Aug 30, 2012 at 5:06 PM, Chris Eldred chris.eldred at
gmail.comwrote:
The code for DMSetDefaultSection is:
3016: PetscSectionDestroy(dm-defaultSection);
3017:
at 5:12 PM, Matthew Knepley knepley at gmail.com
wrote:
Its not wrong. This is the way I wanted it. You set the PetscSection and
give up control. If you
do not want to give up control, then call PetscObjectReference() before
passing it in.
Since this is (a) different from everything
On Fri, Aug 31, 2012 at 1:04 PM, Chris Eldred chris.eldred at gmail.comwrote:
I was wondering how components were treated in PetscSection- my
understanding is that a field with multiple components and multiple
dofs would have those dofs duplicated for each component, but that
does not appear
have 4 dofs defined, not 2. Num components just serves to give
additional info about the field but it is not used in defining or
manipulating the PetscSection.
Yes.
Matt
On Fri, Aug 31, 2012 at 2:29 PM, Matthew Knepley knepley at gmail.com
wrote:
On Fri, Aug 31, 2012 at 1:04 PM, Chris
On Fri, Aug 31, 2012 at 4:49 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Fri, Aug 31, 2012 at 4:17 PM, Jack Poulson jack.poulson at
gmail.comwrote:
In these cases, it sounds like the current best option is then to avoid
using the CMake build system and manually link Elemental and
On Fri, Aug 31, 2012 at 10:00 PM, Barry Smith bsmith at mcs.anl.gov wrote:
I put a couple patches in petsc-3.3 can a skilled person (Satish?)
please push them up to petsc-dev ?
We are in deep shit if this takes skill. What is wrong with
hg pull
On Fri, Aug 31, 2012 at 10:06 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Fri, Aug 31, 2012 at 10:04 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Aug 31, 2012, at 10:02 PM, Matthew Knepley knepley at gmail.com wrote:
On Fri, Aug 31, 2012 at 10:00 PM, Barry Smith bsmith at mcs.anl.gov
On Fri, Sep 7, 2012 at 9:46 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Sep 6, 2012 at 10:37 PM, Barry Smith bsmith at mcs.anl.gov wrote:
The allure of Powerpoint is I can just start it up and poke around the
menus to put together a few slides that look ok very quickly. If I want
On Fri, Sep 7, 2012 at 11:08 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 7, 2012, at 9:46 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Thu, Sep 6, 2012 at 10:37 PM, Barry Smith bsmith at mcs.anl.gov wrote:
The allure of Powerpoint is I can just start it up and poke around
On Fri, Sep 7, 2012 at 11:21 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 7, 2012, at 11:10 PM, Matthew Knepley knepley at gmail.com wrote:
On Fri, Sep 7, 2012 at 11:08 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 7, 2012, at 9:46 PM, Jed Brown jedbrown at mcs.anl.gov wrote
On Fri, Sep 7, 2012 at 11:32 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 7, 2012, at 11:24 PM, Matthew Knepley knepley at gmail.com wrote:
On Fri, Sep 7, 2012 at 11:21 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 7, 2012, at 11:10 PM, Matthew Knepley knepley at gmail.com
On Sat, Sep 8, 2012 at 5:39 AM, Barry Smith bsmith at mcs.anl.gov wrote:
Some discussion came up today about the use of factories in C++ (and
other OO languages) code and I thought it would be useful to related it to
how PETSc handles the same issue since some numerical libraries (the next
On Sat, Sep 8, 2012 at 2:18 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Sat, Sep 8, 2012 at 1:32 PM, Barry Smith bsmith at mcs.anl.gov wrote:
So you guys are programming in Java-fake^?, so good luck with that :-)
Clojure and Scala are pretty good languages. Java being a terrible
On Sat, Sep 8, 2012 at 2:45 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Sat, Sep 8, 2012 at 2:24 PM, Matthew Knepley knepley at gmail.com wrote:
JVM definitely sucks (stack machine with builtin slowness), but who cares
about performance on these things.
You are confusing interface
On Sat, Sep 8, 2012 at 4:53 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Sep 8, 2012, at 2:09 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Sat, Sep 8, 2012 at 12:38 PM, Barry Smith bsmith at mcs.anl.gov wrote:
Yes, because this is how people prepare talks. They grab slides and
On Mon, Sep 10, 2012 at 3:00 AM, Aron Ahmadia aron at ahmadia.net wrote:
Hey guys,
I'm running somebody else's petsc4py application script and I'm seeing a
segmentation fault in __pyx_module_cleanup ().
I'll spend some time debugging this later, but has anybody run into this
before and
On Mon, Sep 10, 2012 at 11:19 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
I would like to use complex arithmetic in some code that does polynomial
optimization in the complex plane (for adaptive smoothers), even when
PetscScalar is real. I'd like to push something like the attached, but
On Tue, Sep 11, 2012 at 7:50 AM, Aron Ahmadia aron at ahmadia.net wrote:
There was a massive purge where Barry renamed a bunch of the DA commands
to either DMDA or moved them over to DM, causing much wailing and gnashing
of teeth, but eventual grudging acceptance that he probably did the right
On Sun, Sep 16, 2012 at 10:46 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Sun, Sep 16, 2012 at 10:13 PM, Barry Smith bsmith at mcs.anl.gov wrote:
What are the various plans for running the test cases on examples?
As I've said before I'd really like each example to be
On Mon, Sep 17, 2012 at 9:36 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 9:08 AM, Barry Smith bsmith at mcs.anl.gov wrote:
How do you map the loops in some of the shell scripts in the makefiles?
Not all the loop constructs are parsed now, but I can add that in an
On Mon, Sep 17, 2012 at 10:01 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 9:48 AM, Matthew Knepley knepley at gmail.comwrote:
On Mon, Sep 17, 2012 at 9:36 AM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 9:08 AM, Barry Smith bsmith at mcs.anl.gov
http://petsc.cs.iit.edu/petsc/petsc-dev/rev/b74991ae4579
Matt
--
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
-- next part --
An HTML
On Sep 17, 2012, at 7:56 PM, Matthew Knepley knepley at gmail.com wrote:
http://petsc.cs.iit.edu/petsc/petsc-dev/rev/b74991ae4579
Matt
--
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which
remote: adding changesets
remote: adding manifests
remote: adding file changes
remote: added 2 changesets with 5 changes to 5 files
remote: pushing to ssh://hg at bitbucket.org/petsc/petsc-dev
remote: searching for changes
remote: remote: adding changesets
remote: remote: adding manifests
remote:
On Mon, Sep 17, 2012 at 8:14 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 8:10 PM, Matthew Knepley knepley at gmail.comwrote:
This is bad design. We should setup CHKERRQ structs first. If they fail
during setup we should MPI_Abort.
It is never okay
On Mon, Sep 17, 2012 at 8:18 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 8:15 PM, Matthew Knepley knepley at gmail.comwrote:
What do you think we do when that Petsc Exception bottoms out?
Return an error code and let the caller deal with it.
If a caller does
On Mon, Sep 17, 2012 at 8:19 PM, Sean Farley sean at mcs.anl.gov wrote:
On Mon, Sep 17, 2012 at 8:14 PM, Matthew Knepley knepley at gmail.com
wrote:
remote: remote: File
/opt/python/domains/
bitbucket.org/2012-08-14/bitbucket/local/env/lib/python2.7/site-packages/django/conf/__init__.py
On Tue, Sep 18, 2012 at 11:24 AM, Barry Smith bsmith at mcs.anl.gov wrote:
Begin forwarded message:
From: Satish Balay petsc-maint at mcs.anl.gov
Subject: Re: [petsc-maint #132779] Error while installing Petsc3-3p3
Date: September 18, 2012 11:22:18 AM CDT
To: petsc-maint at mcs.anl.gov,
On Tue, Sep 18, 2012 at 8:54 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Tue, Sep 18, 2012 at 8:45 PM, Matthew Knepley knepley at gmail.comwrote:
But it is nasty because it changes the convergence tests, the monitor
routines (they report the residual norms in the scale system
On Sat, Sep 22, 2012 at 3:47 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
http://petsc.cs.iit.edu/petsc/petsc-dev/rev/6eccf13462a8
Since when did we start using assert()?
Its commented out.
When we discussed this in chat, I specifically asked you to use
PetscInt imid = imin + (imax -
On Sat, Sep 22, 2012 at 5:06 PM, Jed Brown jedbrown at mcs.anl.gov wrote:
On Sat, Sep 22, 2012 at 3:56 PM, Matthew Knepley knepley at gmail.comwrote:
I was not sure that would work, but of course I tried it before pushing:
Try a C compiler or clang++. It's working for you due to a g++ bug
Since this graphic is from a paper, I suppose I can reshare.
Matt
-- Forwarded message --
From: Robert van de Geijn r...@cs.utexas.edu
Date: Sun, Sep 23, 2012 at 11:16 PM
Subject: How badly Elemental beats ScaLAPACK
To: FLAME mailing list flame_cs at cs.utexas.edu
Folks,
We
On Wed, Sep 26, 2012 at 10:18 AM, Chris Eldred chris.eldred at gmail.comwrote:
I have a vector (created from a PetscSection) that holds a set of
values distributed over various points in my mesh. It represents
multiple fields with different dofs. I was wondering which approach
for modifying
Objections?
Matt
--
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
-- next part --
An HTML attachment was scrubbed...
URL:
26, 2012 at 1:43 PM, Matthew Knepley knepley at gmail.comwrote:
Objections?
Matt
--
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
--
What most
On Wed, Sep 26, 2012 at 5:24 PM, Chris Eldred chris.eldred at gmail.comwrote:
On the subject:
How do coordinates work for user-defined DMComplex objects? What
determines the Coordinate section (and which points does it contain?)?
How is the coordinate vector set?
I am just rewriting this.
On Wed, Sep 26, 2012 at 3:34 PM, Matthew Knepley knepley at gmail.com
wrote:
On Wed, Sep 26, 2012 at 5:24 PM, Chris Eldred chris.eldred at gmail.com
wrote:
On the subject:
How do coordinates work for user-defined DMComplex objects? What
determines the Coordinate section (and which points
On Fri, Sep 28, 2012 at 12:25 PM, Karl Rupp rupp at mcs.anl.gov wrote:
Hi guys,
a long time ago, I stumbled upon one thing that caused a lot of headaches
when interfacing my code with PETSc. Stripping away all the details, my
solver interface looked about like this:
template typename
On Sep 28, 2012 2:13 PM, Barry Smith bsmith at mcs.anl.gov wrote:
Karl,
1)
The reason we use a #define instead of typedef is because of
ch-uni/include -I/usr/X11R6/include -I/opt/local/include
-I/Users/barrysmith/Src/petsc-dev/include/mpiuni-o
On Fri, Sep 28, 2012 at 3:17 PM, Karl Rupp rupp at mcs.anl.gov wrote:
Hi,
The reason we use a #define instead of typedef is because of
(...)
We really want to be able to const the beast in many places and I
couldn't get it to work with typedefs in a way natural for users. If you
http://en.wikipedia.org/wiki/Composability
http://en.wikipedia.org/wiki/Levels_of_Conceptual_Interoperability
I think we can take it to Level 7!
Matt
--
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which
On Wed, Oct 3, 2012 at 5:24 PM, Satish Balay balay at mcs.anl.gov wrote:
I think the attached patch should fix this issue. But I'll let Matt
confirm - before comitting to repo
Yes, this is right.
Thanks,
Matt
Satish
On Wed, 3 Oct 2012, Chris Eldred wrote:
I am having issues
On Fri, Oct 5, 2012 at 6:50 PM, Karl Rupp rupp at mcs.anl.gov wrote:
Dear petsc-dev'ers,
I'll start my undertaking of a common infrastructure for linear algebra
operations with a first look at managing memory. Even though this is
presumably the part with smaller complexity compared to the
On Sat, Oct 6, 2012 at 9:15 PM, Karl Rupp rupp at mcs.anl.gov wrote:
Hi again,
Hmm, I thought that spptr is some 'special pointer' as commented in
Mat, but not supposed to be a generic pointer to a derived class'
datastructure (spptr is only injected with #define
On Sat, Oct 6, 2012 at 10:52 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Oct 6, 2012, at 9:16 PM, Karl Rupp rupp at mcs.anl.gov wrote:
Hi Barry,
Let's see if we can lift this discussion up another level and
treat multi-core threading more specifically in the discussion (though
On Sun, Oct 7, 2012 at 12:48 PM, Satish Balay petsc-maint at mcs.anl.govwrote:
My test ran fine again.
Perhaps you can run the example manually in a debugger to get a better
trace.
Yes, I can't reproduce this either.
Matt
Satish
On Sun, 7 Oct 2012, Satish Balay wrote:
ok - then
PURPOSE.
Matt
A
Sent from my iPhone
On Oct 7, 2012, at 7:49 PM, Matthew Knepley petsc-maint at mcs.anl.gov
wrote:
On Sun, Oct 7, 2012 at 12:48 PM, Satish Balay petsc-maint at mcs.anl.gov
wrote:
My test ran fine again.
Perhaps you can run the example manually in a debugger to get
. However, the fastest way to debug
this is
to run with the debugger and see what the SEGV is actually coming from.
Matt
A
On Sun, Oct 7, 2012 at 10:16 PM, Matthew Knepley petsc-maint at mcs.anl.gov
wrote:
On Sun, Oct 7, 2012 at 2:36 PM, Aron Ahmadia aron.ahmadia at gmail.com
wrote:
Please
I don't know if you guys have seen this:
https://bitbucket.org/dalcinl/petiga
I remove DMIGA today, because this completely supersedes it. The demos are
really cool, and the efficiency blows traditional FEM out of the water on
problems
with smoothness.
Matt
--
What most experimenters
On Tue, Oct 16, 2012 at 3:24 PM, Barry Smith bsmith at mcs.anl.gov wrote:
It is seriously misleading that TSType rosw uses SNES as the solver
since it is only using SNESKSP and the algorithm really is built around
only linear solves. Are you sure that using SNES is the right model for
On Tue, Oct 16, 2012 at 3:52 PM, Barry Smith bsmith at mcs.anl.gov wrote:
On Oct 15, 2012, at 11:48 PM, Matthew Knepley knepley at gmail.com wrote:
On Tue, Oct 16, 2012 at 3:24 PM, Barry Smith bsmith at mcs.anl.gov wrote:
It is seriously misleading that TSType rosw uses SNES
301 - 400 of 2694 matches
Mail list logo