Merge branch 'knepley/fix-plex-parmetis'

* knepley/fix-plex-parmetis:
DMPlex: ParMetis now working - Ridiculous stub partition up front removed - Metis does not return 0 on success, so fixed call

Merge branch 'knepley/fix-plex-parmetis'

* knepley/fix-plex-parmetis:
DMPlex: ParMetis now working - Ridiculous stub partition up front removed - Metis does not return 0 on success, so fixed call
DMPlex: Changed DMPlexCreatePartition() to take the partitioner name
DMPlex: remove unused variable
DMPlex: Put in METIS support

show more ...

DMPlex: Added support for INSERT_BC_VALUES in VecSetClosure()

Merge branch 'knepley/fix-plex-closure' into knepley/feature-dt-fem

* knepley/fix-plex-closure:
DMPlex: Fixed missing RestoreTransitiveClosure()

DMPlex: Fixed missing RestoreTransitiveClosure()

Merge branch 'knepley/fix-plex-closure' into knepley/feature-dt-fem

* knepley/fix-plex-closure:
DMPlex: Fixed optimized portion of VecGetClosure() for NULL input array

DMPlex: Fixed optimized portion of VecGetClosure() for NULL input array

Merge branch 'knepley/fix-plex-closure' into knepley/feature-dt-fem

* knepley/fix-plex-closure:
DMPlex: Allow NULL array as input to DMPlexVecGetClosure()
DMPlex: Fix VecGetClosure() when the ar

Merge branch 'knepley/fix-plex-closure' into knepley/feature-dt-fem

* knepley/fix-plex-closure:
DMPlex: Allow NULL array as input to DMPlexVecGetClosure()
DMPlex: Fix VecGetClosure() when the array is input

show more ...

DMPlex: Allow NULL array as input to DMPlexVecGetClosure()

DMPlex: Fix VecGetClosure() when the array is input

Merge branch 'master' into knepley/feature-plex-refine-3d

* master: (71 commits)
Sys: revert packed PetscMalloc to PetscMallocN in PetscCommBuildTwoSided_Allreduce
SNESMonitorCancel: enable fort

Merge branch 'master' into knepley/feature-plex-refine-3d

* master: (71 commits)
Sys: revert packed PetscMalloc to PetscMallocN in PetscCommBuildTwoSided_Allreduce
SNESMonitorCancel: enable fortran interface
PetscSection: Added docs for Fortran binding for VecSetValuesSection()
Vec: Removed old F90 binding for PetscSection
bgq: fix deadlock on bgq due to inconsistant values returned by getpwuid(getuid()) on runs with 256nodes [or 4096 cores]. This fix removes the reliance on PetscGetHomeDirectory() returning 'same' value across nodes. [using the fact that PetscOptionsInsertFile() uses HOMEDIR from node-0 only]
DMPlex: change order of assignment to appease -Wmaybe-initialized (gcc-4.8.1)
DMPlex: Fix 64-bit int problem in VTK
Mat: Fix for PetscSparseDenseMaxDot() for complex
Vec: Correct VecUniqueEntries() for 64-bit indices
MatSeqAIJGetArrayF90: add man pages and fix typo in MatDense version
SF docs: add link to summary page and fix title
Doc: Fixed DM code in manual
metis/parmetis: update to metis-5.1.0/parmetis-4.0.3 Also update the test output as the partitioning appears to have changed.
DMPlex: remove unused variables
blaslapack: update f,f2c tarballs to 3.4.2 version
DMPlex ex5: Added test for 2 face cohesive submesh - Fixed old tests for cohesive cell orientation
DMPlex: Put in depth label optimization
DMPlex: Fix flipping of fault normal
DMPlex: We label cells with only vertices on the fault, but they have no cone replacement
DMPlex: Fix translation to cohesive edges in 3D - They are labeled by the vertices they connect
...

Conflicts:
include/petscdmplex.h

show more ...

Merge branch 'master' into knepley/feature-dt-fem

* master: (51 commits)
Sys: revert packed PetscMalloc to PetscMallocN in PetscCommBuildTwoSided_Allreduce
SNESMonitorCancel: enable fortran inte

Merge branch 'master' into knepley/feature-dt-fem

* master: (51 commits)
Sys: revert packed PetscMalloc to PetscMallocN in PetscCommBuildTwoSided_Allreduce
SNESMonitorCancel: enable fortran interface
PetscSection: Added docs for Fortran binding for VecSetValuesSection()
Vec: Removed old F90 binding for PetscSection
bgq: fix deadlock on bgq due to inconsistant values returned by getpwuid(getuid()) on runs with 256nodes [or 4096 cores]. This fix removes the reliance on PetscGetHomeDirectory() returning 'same' value across nodes. [using the fact that PetscOptionsInsertFile() uses HOMEDIR from node-0 only]
DMPlex: change order of assignment to appease -Wmaybe-initialized (gcc-4.8.1)
metis/parmetis: update to metis-5.1.0/parmetis-4.0.3 Also update the test output as the partitioning appears to have changed.
DMPlex: remove unused variables
blaslapack: update f,f2c tarballs to 3.4.2 version
DMPlex ex5: Added test for 2 face cohesive submesh - Fixed old tests for cohesive cell orientation
DMPlex: Put in depth label optimization
DMPlex: Fix flipping of fault normal
DMPlex: We label cells with only vertices on the fault, but they have no cone replacement
DMPlex: Fix translation to cohesive edges in 3D - They are labeled by the vertices they connect
DMPlex: Added flip argument to DMPlexLabelCohesiveComplete() to reverse submesh normal - Fixed ex5 test
DMPlex ex5: Fixed existing tests and added two cohesive cell test - Fixed tests for new cohesive cell orientation
DMPlex: Propagate orientation information to the submesh properly
DMPlex: Orientation of cohesive cell should come from face to which it is attached
DMPlex: Added subdm argument to DMPlexLabelCohesiveComplete() - Use the subdm for orientation information so we replace vertices all on the same side
DMPlex: Fix DMPlexOrient() for submeshes - Need to also reverse cone orientation of cells attached to fault faces when we flip them
...

Conflicts:
config/builder.py
include/petsc-private/dmpleximpl.h
include/petscdm.h
src/dm/impls/plex/plex.c
src/dm/impls/plex/plexfem.c
src/dm/interface/dlregisdmdm.c
src/snes/examples/tutorials/ex52.c
src/snes/examples/tutorials/output/ex12_10.out
src/snes/examples/tutorials/output/ex12_11.out
src/snes/examples/tutorials/output/ex12_5.out
src/snes/examples/tutorials/output/ex12_6.out
src/snes/examples/tutorials/output/ex12_7.out
src/snes/examples/tutorials/output/ex12_8.out
src/snes/examples/tutorials/output/ex12_9.out

show more ...

Merge branch 'knepley/fix-plex-orient'

* knepley/fix-plex-orient:
DMPlex: Fixed bug with mesh orientation - flipped marker must be a boolean for ^ operation - Final check needs a mismatch as well

Merge branch 'knepley/fix-plex-orient'

* knepley/fix-plex-orient:
DMPlex: Fixed bug with mesh orientation - flipped marker must be a boolean for ^ operation - Final check needs a mismatch as well
DMInterpolation: Fixed declarations
DMPlex: Added declaration

show more ...

Merge branch 'knepley/fix-plex-matclosure'

* knepley/fix-plex-matclosure:
DMPlex: Update calls to DMPlexMatSetClosure() to eliminate default arguments
DMPlex: Do not allow default sections in DM

Merge branch 'knepley/fix-plex-matclosure'

* knepley/fix-plex-matclosure:
DMPlex: Update calls to DMPlexMatSetClosure() to eliminate default arguments
DMPlex: Do not allow default sections in DMPlexMatSetClosure() - This makes the call collective

show more ...

Merge branch 'knepley/fix-plex-matrix-sbaij'

* knepley/fix-plex-matrix-sbaij:
DMPlex: Move Mat option set after preallocation - SEGV on SBAIJ if we do not do this

Merge branch 'knepley/fix-plex-submesh-orient'

* knepley/fix-plex-submesh-orient:
DMPlex ex5: Added test for 2 face cohesive submesh - Fixed old tests for cohesive cell orientation
DMPlex: Put i

Merge branch 'knepley/fix-plex-submesh-orient'

* knepley/fix-plex-submesh-orient:
DMPlex ex5: Added test for 2 face cohesive submesh - Fixed old tests for cohesive cell orientation
DMPlex: Put in depth label optimization
DMPlex: Fix flipping of fault normal
DMPlex: We label cells with only vertices on the fault, but they have no cone replacement
DMPlex: Fix translation to cohesive edges in 3D - They are labeled by the vertices they connect
DMPlex: Added flip argument to DMPlexLabelCohesiveComplete() to reverse submesh normal - Fixed ex5 test
DMPlex ex5: Fixed existing tests and added two cohesive cell test - Fixed tests for new cohesive cell orientation
DMPlex: Propagate orientation information to the submesh properly
DMPlex: Orientation of cohesive cell should come from face to which it is attached
DMPlex: Added subdm argument to DMPlexLabelCohesiveComplete() - Use the subdm for orientation information so we replace vertices all on the same side
DMPlex: Fix DMPlexOrient() for submeshes - Need to also reverse cone orientation of cells attached to fault faces when we flip them
DMPlex: Propagate orientations in cohesive cell creation - Also fix hybrid bounds

Conflicts:
src/dm/impls/plex/plexsubmesh.c

show more ...

Merge branch 'knepley/plex-depth-label'

* knepley/plex-depth-label:
DMPlex: remove unused variables
DMPlex: Use BFS to calculate depth rather than crazy recursive scheme
DMPlex: Now use DMPlex

Merge branch 'knepley/plex-depth-label'

* knepley/plex-depth-label:
DMPlex: remove unused variables
DMPlex: Use BFS to calculate depth rather than crazy recursive scheme
DMPlex: Now use DMPlexGetDepthLabel() to interrogate point depths
DMPlex: Optimize depth retrieval by storing a pointer to the label - This is a little unsafe since someone could go in and create a new "depth" label out from under you

show more ...

Merge branch 'knepley/plex-profile-distribution'

* knepley/plex-profile-distribution:
DMPlex: Added new events for distribution

Merge branch 'knepley/fix-plex-parallel'

* knepley/fix-plex-parallel:
DMPlex: Fixed creation of global sections - The size of neg[] must be all of nroots instead of pEnd-pStart
DMPlex: Fixed coh

Merge branch 'knepley/fix-plex-parallel'

* knepley/fix-plex-parallel:
DMPlex: Fixed creation of global sections - The size of neg[] must be all of nroots instead of pEnd-pStart
DMPlex: Fixed cohesive submesh SF - I misclassified points which were not owned in the original mesh, but are owned in the submesh
DMPlex: Fixed bug with cohesive submesh SF - Needed to put in owned subpoints since they do not come from leaves OR from the original mesh
DMPlex: Fix out of bounds access for empty mesh
DMPlex: Fixed creation of PetscSF in DMPlexCreateCohesiveSubmesh_Uninterpolated() - Could not assume that original owner of subvertex owned it in submesh because it might have no subcells - Needed to redetermine ownership of subpoints
Plex VTK: Handle missing submesh pieces in parallel
DMPlex: Initializeremote locations when calculating SF for submesh
DMPlex: FIxed hang in DMPlexCreateCohesiveSubmesh()
DMPlex: Added PetscSF creation to DMPlexCreateCohesiveSubmesh_Uninterpolated() - Added DMPlexFilterPoint_Internal() - Still need this for the interpolated variant
DMPlex: Remove dead code
DMPlex: Removed aggressive checks for cohesive cells - How should we handle extraction in parallel?
PetscSection: PetscSectionCreateSubmeshSection() now can take an empty IS
DMPlex: Allow submesh creation with empty mesh and empty label
DMPlex: Allow DMPlexOrient() of empty mesh

Conflicts:
src/dm/impls/plex/plexsubmesh.c

show more ...

Merge branch 'knepley/plex-speed-tests'

* knepley/plex-speed-tests:
DMPlex: Remove unused variables
DMPlex: Fixed bug in special case for DMPlexVecGetClosure() - Need to set outgoing size if arr

Merge branch 'knepley/plex-speed-tests'

* knepley/plex-speed-tests:
DMPlex: Remove unused variables
DMPlex: Fixed bug in special case for DMPlexVecGetClosure() - Need to set outgoing size if array is passed in
DMPlex: Added special case for DMPlexVecSetClosure() - Could add more modes
DMPlex: Optimizations for DMPlexVecGetClosure() - Removed branch (seems to have little effect) - Removed calculation of size when array is provided (profiled for 20% effect)
DMPlex: Forgot one init for DMPlexVecGetClosure()
DMPlex: Must initialize argument to DMPlexVecGetClosure()
DMPlex ex9: Added ability to reuse array in VecGetClosure()
DMPlex: Allow DMPlexVecGetClosure() to take an input array
DMPlex: Fix bug in specialization of DMPlexVecGetClosure()
DMPlex: Bug fix for special case in DMPlexVecGetClosure()
DMPlex: Added optimization for depth 1 DMPlexVecGetClosure()
DMPlex ex9: Does not fail by default - Will turn back on failure once we calculate variance
SNES ex12: Cleaning up in preparation for speed testing
DMPlex: Added ex9 to test performance, put in depth 1 special case for TransitiveClosure

Conflicts:
config/builder.py
src/dm/impls/plex/plexgeometry.c
src/snes/examples/tutorials/output/ex12_5.out

show more ...

Remove --with-dynamic-loading / PETSC_USE_DYNAMIC_LIBRARIES

This option was mostly redundant because normal shared libraries satisfy
all the same needs. This commit adds the run-time option
-dynami

Remove --with-dynamic-loading / PETSC_USE_DYNAMIC_LIBRARIES

This option was mostly redundant because normal shared libraries satisfy
all the same needs. This commit adds the run-time option
-dynamic_library_preload that can be used to load/initialize all the
packages in advance, as used to be done when --with-dynamic-loading.

The PetscDLLibraryRegister_petscxxx functions have been kept, but are
not called unless -dynamic_library_preload is used. The petsc-dev
discussion, "Why --with-dynamic-loading?" did not reach consensus about
whether this was ever useful, so it may also be removable.

show more ...

DMPlex: ParMetis now working
- Ridiculous stub partition up front removed
- Metis does not return 0 on success, so fixed call

Merge remote-tracking branch 'origin/knepley/feature-plex-metis' into knepley/fix-plex-parmetis

* origin/knepley/feature-plex-metis:
DMPlex: remove unused variable
DMPlex: Put in METIS support

DMPlex: Changed DMPlexCreatePartition() to take the partitioner name

DMPlex: remove unused variable

Merge branch 'master' into knepley/feature-dt-fem

* master: (211 commits)
Mat ex170: Comments
VTK: Small fix to error message (.vts to .vtu)
VTK: Small fix to error message
Fixed bib entries

Merge branch 'master' into knepley/feature-dt-fem

* master: (211 commits)
Mat ex170: Comments
VTK: Small fix to error message (.vts to .vtu)
VTK: Small fix to error message
Fixed bib entries
Bib: Updates
AO: fix erroneous processing of -ao_view and factor into AOViewFromOptions
doc: fix named argument in {Vec,Mat,DM}ViewFromOptions
Sys: add PetscDataTypeFromString() and test code
Mat: Should say that it has a nullspace in MatView()
parms: update tarball with fix for namespace conflict with metis
fix citation 'Golub_Varga_1961'
parmetis: update tarball to parmetis-4.0.2-p5 which fixes an install issue with cygwin
Sys Logging: revert parent traversal
fixed hdf5.py so that if self.libraries.compression is None the code still runs correctly
DMDA: fix bad cast of DM_DA to PetscObject
MatClique: follow DistMultiVec API changes
MatClique: remove unused variables
config cmakeboot: add C++ flags any time compiler is available
config OpenMP: check for C++ flag any time the compiler is available
replaced all left-over uses of a single PetscMalloc() to allocated multiple arrays: replaced with PetscMallocN() The only ones left are when the second array is set into the first array and one ugly usage in the MUMPS interface that cannot be easily fixed
...

Conflicts:
config/builder.py
src/dm/impls/plex/plexgeometry.c

show more ...