| #
b3b5d266
|
| 16-Feb-2010 |
Matthew G Knepley <knepley@gmail.com> |
Merge
Hg-commit: e58ca2d7c30994afcc347cea28d361f7ffd1c0ba
|
| #
9505b675
|
| 14-Feb-2010 |
Barry Smith <bsmith@mcs.anl.gov> |
improvements to PetscOpenMPMerge() to allow it to be run inside the program and an example of its use
updates to lsqr.c with preconditioning to more stable form
Hg-commit: 2d51898f92e225dc9c39f6963f
improvements to PetscOpenMPMerge() to allow it to be run inside the program and an example of its use
updates to lsqr.c with preconditioning to more stable form
Hg-commit: 2d51898f92e225dc9c39f6963fd52521b394fa6f
show more ...
|
| #
46edd32f
|
| 03-Feb-2010 |
Matthew Knepley <knepley@mcs.anl.gov> |
Merge
Hg-commit: 877396bee467d11706fe4bd6e7dd710925967c05
|
| #
06a205a8
|
| 29-Jan-2010 |
Barry Smith <bsmith@mcs.anl.gov> |
changed PetscSum_Op to MPIU_SUM to match the style we have for extra MPI stuff
Hg-commit: 6f826cf21d32c05c8a481b7d8be71073e672cf40
|
| #
2c876bd9
|
| 29-Jan-2010 |
Barry Smith <bsmith@mcs.anl.gov> |
added support to us MPI_C_DOUBLE_COMPLEX if it exists.
Hg-commit: c1dd1aecbb58a31cdf6a75e069e3e092253f12cb
|
| #
87843682
|
| 30-Nov-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge
Hg-commit: 88dece74cfbfd056afd52d9c6c93ea90a2af64a9
|
| #
ec50a509
|
| 30-Nov-2009 |
Jed Brown <jed@59A2.org> |
merge
Hg-commit: 4e55bf04cc3e6bd9dfaa5b08c2e382f61f54310a
|
| #
afa5c859
|
| 30-Nov-2009 |
Jed Brown <jed@59A2.org> |
Backed out changeset 4990e0f34444
I goofed wrt. where the unused options are actually printed. This is in
fact required.
Hg-commit: 2bdfd9b27ba11585b490f835e2e047d628a30bb8
|
| #
5a63da67
|
| 30-Nov-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge
Hg-commit: 2969531575bbe0c172ba5beddc62a04aac021215
|
| #
459c3c8d
|
| 29-Nov-2009 |
Jed Brown <jed@59A2.org> |
Remove unused options query for -malloc_dump in PetscFinalize()
This option is processed unconditionally later in this function. There
are no non-error early exits so this removal cannot cause spur
Remove unused options query for -malloc_dump in PetscFinalize()
This option is processed unconditionally later in this function. There
are no non-error early exits so this removal cannot cause spurious
-options_left output.
Hg-commit: 4990e0f34444df319a07ba4ba49eca38dc880cc8
show more ...
|
| #
07e8cd54
|
| 18-Nov-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge
Hg-commit: 4074ba38782c264e0ac4ed45ee2400193128e393
|
| #
480cf27a
|
| 18-Nov-2009 |
Jed Brown <jed@59A2.org> |
Use a per-communicator counter for PetscObjectName()
New struct PetscCommCounter which includes name counter replaces
raw PetscMPIInt[2] for tagvalp.
Move creation of the following keyvals to Petsc
Use a per-communicator counter for PetscObjectName()
New struct PetscCommCounter which includes name counter replaces
raw PetscMPIInt[2] for tagvalp.
Move creation of the following keyvals to PetscInitialize(), they
are freed in PetscFinalize()
Petsc_Counter_keyval (tag, namecount, refcount)
Petsc_InnerComm_keyval
Petsc_OuterComm_keyval
Note the prototype
int MPI_Attr_get(MPI_Comm comm,int keyval,void *attribute_val,int *flag)
attribute_val would logically have type void**, but the standard
made it void* so that (void**) casting would not be required.
Since C++ implicitly converts to void*, I have removed the casts
from this argument.
Also, enums are not guarateed to have size equivalent to int,
therefore the type of flag has been changed to PetscMPIInt.
Hg-commit: ecbd2dcad71aeafadd024effc66fb92f2819f4b6
show more ...
|
| #
cd621086
|
| 19-Sep-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge
Hg-commit: 148339b0d1e2fac081864ec646f45ac0937e058a
|
| #
e8373e55
|
| 17-Sep-2009 |
Matthew Knepley <knepley@mcs.anl.gov> |
Fixed problem with PETSC_COMM_WORLD initialization
Hg-commit: f081bfbc95e46d67942ff1f19b91ca1755593abf
|
| #
b022a5c1
|
| 07-Aug-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
fixed output files to have additional line for norm type PRECONDITIONED
now allows PetscInitialize() and PetscFinalize() to be called multiple times
Hg-commit: 2a35ab2c090ec4b625e988497846f530aaa67b
fixed output files to have additional line for norm type PRECONDITIONED
now allows PetscInitialize() and PetscFinalize() to be called multiple times
Hg-commit: 2a35ab2c090ec4b625e988497846f530aaa67b2c
show more ...
|
| #
fe36e6c7
|
| 13-Apr-2009 |
Matthew Knepley <knepley@mcs.anl.gov> |
Merge
- Watch out for SNES ex45, I think the merge was bad
Hg-commit: 04bc4bca24f51d95f00a035b6b5fb2e5990fd8a8
|
| #
90d69ab7
|
| 28-Mar-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
changed PetscOptionsName() and PetscOptionsHasName() to return true if option is set, regardless of the value it is set to, include 0 and false
changed most uses of these routines to the Truth vari
changed PetscOptionsName() and PetscOptionsHasName() to return true if option is set, regardless of the value it is set to, include 0 and false
changed most uses of these routines to the Truth varient
Hg-commit: fd6366abd7eb1f3ec925faa0ecd078d5cc025eb2
show more ...
|
| #
efe6c3a7
|
| 16-Feb-2009 |
Matthew Knepley <knepley@mcs.anl.gov> |
Merge
Hg-commit: c24770da2f7a4ec6d2c54d0774691ec6c5dd493c
|
| #
62f4b9a8
|
| 12-Feb-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge from petsc-3.0.0
Hg-commit: fe2b1d4a209804427bebd09014d0a5ddc55788dc
|
| #
dbf0e21d
|
| 08-Feb-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
fixes to mpibaij.c found in nightly build
fixes to wrong use of CHKERRQ() throughout code
Hg-commit: 733dea1e39d18170feab68a0e7a269e3248a628a
|
| #
05827820
|
| 07-Feb-2009 |
Barry Smith <bsmith@mcs.anl.gov> |
Fixed up HDF5 support for PetscViewer() for VecView() and VecLoadIntoVector() for DA created vectors.
Tested in src/dm/da/examples/tutorials/ex9.c
Hg-commit: 09470055899d2d5bee51dded92f5d92042b54d
Fixed up HDF5 support for PetscViewer() for VecView() and VecLoadIntoVector() for DA created vectors.
Tested in src/dm/da/examples/tutorials/ex9.c
Hg-commit: 09470055899d2d5bee51dded92f5d92042b54d6c
show more ...
|
| #
fe20df21
|
| 18-Dec-2008 |
Barry Smith <bsmith@mcs.anl.gov> |
commit after merge
Hg-commit: 1667a1330eff9f2943bbc157888ed46ec6a73cc3
|
| #
99f316e7
|
| 17-Dec-2008 |
Matthew Knepley <knepley@mcs.anl.gov> |
Added Fortran wrappers for PetscGlobalSum/Max/Min()
Hg-commit: 1f20c9217e7237a05e0a32075f1c9ff5b8b1f109
|
| #
6ae9a8a6
|
| 16-Dec-2008 |
Barry Smith <bsmith@mcs.anl.gov> |
PetscGetArgs() is now supported even if main program is Fortran
Hg-commit: d4e668c9a0506d1e9e86bb96d015f9b160729313
|
| #
717030ee
|
| 15-Dec-2008 |
Lisandro Dalcin <dalcinl@gmail.com> |
fixes for make working Fortran+Python
Hg-commit: bae17ac1b9daadd37f802b3060487532ffa6a584
|