| 2b5a7727 | 01-Apr-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
Merged in dalcinl/fix-info-log-exclude (pull request #914)
Consistent handling of command line options -info_exclude and -log_exclude
Approved-by: BarryFSmith <bsmith@mcs.anl.gov> |
| 6fbadf99 | 31-Mar-2018 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/hzhang/vec_node/master-rebased-v2' |
| bd3c5f74 | 31-Mar-2018 |
Satish Balay <balay@mcs.anl.gov> |
doc: fix LOCDIR in makefiles |
| 8e81d068 | 30-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
Consistent handling of command line options -info_exclude and -log_exclude |
| 16ac2964 | 30-Mar-2018 |
Matthew G. Knepley <knepley@gmail.com> |
Section: Allow global offsets for fields to be non-contiguous
- This allows the global operator to segregate fields, rather than having all fields on a point contiguous as was our default |
| 8fb6b4f5 | 29-Mar-2018 |
Hong Zhang <hzhang@mcs.anl.gov> |
add VecGetArrayRead_Node() |
| d13c9127 | 29-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
Merge branch 'karlrupp/feature-remove-cusp'
* karlrupp/feature-remove-cusp:
Removes VECCUSP vectors and AIJCUSP matrices, because they provide no added benefit over VECCUDA and AIJCUSPARSE.
Also rem
Merge branch 'karlrupp/feature-remove-cusp'
* karlrupp/feature-remove-cusp:
Removes VECCUSP vectors and AIJCUSP matrices, because they provide no added benefit over VECCUDA and AIJCUSPARSE.
Also removes the CUSP-based preconditioners for now.
SACUSP will be re-added later, after the new release is out.
show more ...
|
| 7c94e9e1 | 29-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
ViennaCL: Masked extra CUDA paths in VecGetArray()/VecGetArrayRead().
If ViennaCL is used without CUDA, then the old code still tried to use CUDA stuff. |
| 6f7079dd | 28-Mar-2018 |
Satish Balay <balay@mcs.anl.gov> |
set flag 'HAVE_MPI_WIN_CREATE_FEATURE' only for newer MPICH that has HAVE_MPI_WIN_CREATE HAVE_MPI_WIN_ALLOCATE_SHARED and HAVE_MPI_WIN_SHARED_QUERY
old mpich-3.0.4 has buggy MPI_Win_shared_query()
set flag 'HAVE_MPI_WIN_CREATE_FEATURE' only for newer MPICH that has HAVE_MPI_WIN_CREATE HAVE_MPI_WIN_ALLOCATE_SHARED and HAVE_MPI_WIN_SHARED_QUERY
old mpich-3.0.4 has buggy MPI_Win_shared_query() - does not return correct values
update vecscatter code to use PETSC_HAVE_MPI_WIN_CREATE_FEATURE flag [and remove code that handled
for PETSC_HAVE_MPI_WIN_ALLOCATE_SHARED and PETSC_HAVE_MPI_WIN_SHARED_QUERY flags - this was not clean anyway]
show more ...
|
| 48379629 | 28-Mar-2018 |
Hong Zhang <hzhang@mcs.anl.gov> |
add missing CHKERRQ |
| b8ced49e | 28-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
GPUs: Allow ViennaCL and VECCUDA to be used concurrently.
This also gets rid of the weird veccuda.py. |
| 0bbffbc0 | 27-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
Merge branch 'stefano_zampini/fix-matis-dmda-l2g' |
| e9e886b6 | 27-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
CUSP: Removed VECCUSP and AIJCUSP as well as preconditioners.
SA-AMG from CUSP will be re-added in a follow-up commit,
made to work with AIJCUSPARSE and VECCUDA. |
| 2ea74b33 | 27-Mar-2018 |
Karl Rupp <me@karlrupp.net> |
CUSP: Converted all CUSP-tests to CUDA.
This is a preparation for removing veccusp and aijcusp. |
| 8198064f | 26-Mar-2018 |
Barry Smith <bsmith@mcs.anl.gov> |
fix alignm problems from MPI_Win_allocate_shared()
fix use of printf() in examples
Reported-by: nightly tests
Thanks-to: Satish Balay <balay@mcs.anl.gv> |
| aa1c0910 | 23-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
Merged in dalcinl/fix-sf (pull request #903)
PetscSF: Various fixes and cleanups
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
Approved-by: Jed Brown <jed@59a2.org> |
| 2ad1e87f | 22-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
PetscSFSetGraph: Check and optimize for contiguous storage |
| 373e0d91 | 22-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
PetscSFGetGraph: Remove comment with dead code and add note to docs |
| 73afbf15 | 21-Mar-2018 |
Satish Balay <balay@mcs.anl.gov> |
vecnode: fix incorrect typecast used in VecGetArray() |
| 29046d53 | 20-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
PetscSF: Various fixes and cleanups
* Add missing PetscSFGetType()
* PetscSFDestroy_XXX() now calls PetscSFReset_XXX(), otherwise changing
the SF type with PetscSFSetType() may leak memory.
* Fix
PetscSF: Various fixes and cleanups
* Add missing PetscSFGetType()
* PetscSFDestroy_XXX() now calls PetscSFReset_XXX(), otherwise changing
the SF type with PetscSFSetType() may leak memory.
* Fix init/computation of {min|max}leaf and use maxleaf where required
rather than recomputing the value in a loop
* Add logging event for PetscSFSetUp()
* Add tons of missing error checking
* Enable missing Fortran wrappers that can be generated automatically
* Support for command line options -{info|log}_exclude
* Various doc fixes
* Add tests for SFs with empty graphs
show more ...
|
| 3f92d817 | 21-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
ISView: Fix MPI_SUM -> MPI_MAX to determine maximum message to arrive |
| de8a3bf8 | 19-Mar-2018 |
Lisandro Dalcin <dalcinl@gmail.com> |
MPI I/O: Support for view/load ISGENERAL |
| 6294108e | 19-Mar-2018 |
Toby Isaac <tisaac@cc.gatech.edu> |
Merge remote-tracking branch 'origin/knepley/fix-snes-ex69' into tisaac/feature-dmfield
* origin/knepley/fix-snes-ex69: (311 commits)
PetscFECreateDefault: fix custom Fortran interface to use MPI_
Merge remote-tracking branch 'origin/knepley/fix-snes-ex69' into tisaac/feature-dmfield
* origin/knepley/fix-snes-ex69: (311 commits)
PetscFECreateDefault: fix custom Fortran interface to use MPI_Comm
SNES ex69: Updated test output
SNES ex69: Removed all mantle stuff and change fields to constants - Also use dsymutil for executables
SNES ex69: Removed special partition
SNES ex69: Fixed null space creation - Null space locks its vectors
PetscFE: PetscFECreateDefault() now takes MPI_Comm instead of DM
cleanup very ugly PCGAMG manual page
minor clarifications for VecScatterCreate() manual page
gcov: PETSC_ARCH is required onlyfor -run_gcov - and not for -merge_gcov [where it doesn't exist]
make clearer in help statements what --with-external-packages-dir is for.
Website: Added news entry for PETSc User Meeting 2018 on main page.
CUDA: Further test output fixes for mat_tests-ex2
Turn off elemental test for parmetis running since this does not work on batch systems.
3.8 Changes: KSPCHEBYSHEV
CUDA: Fixed most test errors due to MatMultTranspose*
website: update urls
website: fix Jason's name to match pic. Also add Todd's pic
Dev manual: copyedit
DMPlexDistributeLabels: Propagate the output flag
cuda/cusp: update minimum supported versions of cuda to 7.5 and cusp to 0.5.0
...
show more ...
|
| 49c9c947 | 17-Mar-2018 |
Barry Smith <bsmith@mcs.anl.gov> |
Merge branch 'maint' |
| dacb1e0f | 17-Mar-2018 |
Barry Smith <bsmith@mcs.anl.gov> |
minor clarifications for VecScatterCreate() manual page
Commit-type: documentation
Reported-by: apostol <apostol.faliagas@gmail.com>
Thanks-to:
Development Tools: Vim, Emacs, Eclipse |