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

* master: (593 commits)
Bib: Added Top500 and fixed entry
fun3d: update PetscMallocValidate() usage
bib: rename ref with duplicate key

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

* master: (593 commits)
Bib: Added Top500 and fixed entry
fun3d: update PetscMallocValidate() usage
bib: rename ref with duplicate key
Webpage: Corrected '-dm_mat_type cusp' to 'dm_mat_type aijcusp'.
Allow calling MatGetBlockSize[s]() before matrix preallocation
SNESLINESEARCHBT: Set the norms when exiting early due to negligible step.
SNESQN: only monitor real part of dot product (fails with C++ complex)
Corrected the #include statement in the man pages for the PetscObjectComposedDataSet/Getwhatever routines.
DMPlex: Added doc for DMPlexGetHybridBounds()
winzip: detect if winzip is used to extract petsc.tar.gz and error out.
configure: remove self.archIndependent as its not being used. [it is used to create externalpackages/package/arch dir which is unused]
configure: fix packages using package-dir/PETSC_ARCH as out-of-source-build location Perhaps this should be changed to package-dir/build?
configure: remove dead code previously used to download BuildSystem
configure: check if compilerDefines [and compilerFixes] exist in framework before using them
configure: save/restore reconfigure.py when --with-clean is used
configure: add --with-clean option to delete buildfiles/externalpackages in PETSC_DIR/PETSC_ARCH and potential externalpackages in --with-external-package-dir/PETSC_ARCH
configure: With --with-externalpackages-dir=dir store/build packages in dir/PETSC_ARCH
Add MatSeqSBAIJSetPreallocationCSR()
configure: switch to using PETSC_DIR/PETSC_ARCH/externalpackages by updating package.py to use externalpackages.py as the externalPackagesDirProvider
configure: move dead code configureExternalPackagesDir() from petscdir.py to externalpackagesdir.py Also set PETSC_DIR/PETSC_ARCH/externalpackages as the externalpackagesdir
...

show more ...

Merge branch 'master' into barry/saws

Conflicts:
src/ksp/pc/impls/gamg/gamg.c
src/sys/classes/viewer/impls/ams/ams.c
src/sys/objects/pinit.c

Merge branch 'master' into knepley/feature-dmda-section

* master: (397 commits)
PetscSynchronizedFGets: fix deadlock at EOF
Compiler: Fix warnings from MPI impls which do not initialize outputs

Merge branch 'master' into knepley/feature-dmda-section

* master: (397 commits)
PetscSynchronizedFGets: fix deadlock at EOF
Compiler: Fix warnings from MPI impls which do not initialize outputs
Increase patchlevel to 3.4.3
SNES: Now work vectors come from the DM
SNES ex62: Remove code generation
SNES: Move setup involving snes->vec_sol from SNESSetUp() to SNESolve()
Compiler: Fix warnings from MPI impls which do not initialize outputs
DMPlex ex7: Added missing test output
SNES ex52: Removed old Jacobian stuff, and fixed call to DMPlexProjectFunction() - Fixed calls for new element handling
SNES ex12: Added a performance profiling mode
DMPlex ex8: Fixed leak
PetscSection: Must reset the section when changing the number of fields
DMPlex ex7: Fixed test output - Corrected orientations in interpolation
DMPlex ex1: Fixed test output - Uniform refinement for quads changed
DMPlex: Fix overagressive checks
PC: Removed support graph PC
configure: both downloadonWindows and worksonWindows refer to MS compilers. Also fix isWindows() -> isWindows(CC).
MatXAIJSetPreallocation: use array[] notation to help out Fortran
__float128: when blas/lapack is not found instruct using f2cblaslapack
Configure: Package.downloadonWindows is supposed to mean that Windows compilers work. not Cygwin - Also changed doc for Package.worksonWindows, which does refer to Cygwin
...

Conflicts:
src/dm/impls/da/dalocal.c

show more ...

Merge branch 'master' into prbrune/mat-matcolor

Conflicts:
src/snes/interface/snesj2.c

Merge branch 'barry/dmvecmattypes' into shri/feature-dm-circuit

Conflicts:
src/dm/impls/makefile
src/dm/interface/dmregall.c

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

* master: (149 commits)
Bib: Added papers referencing PETSc from ResearchGate
Bib: Fixed urls for some refs Suggested-by: Michele De Ste

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

* master: (149 commits)
Bib: Added papers referencing PETSc from ResearchGate
Bib: Fixed urls for some refs Suggested-by: Michele De Stefano
fixed bug that has appeared recently of false positive errors when there are zero local equations on coarse grids in gamg-agg.
MatSchurComplement: Must initialize KSP package
bib: fix inbook citation
Bib: Updated some refs
SNES: fix copy/paste in man page
fortran: fix KSPCONVERGEDDEFAULT and SNESCONVERGEDSKIP in fortran includes
Mat SBAIJ: avoid invalid memory read in MatSOR_SBAIJ
Revert "MatMPIBAIJSetPreallocationCSR() handled the input matrix entries incorrectly, it treated them as if each row of values"
PCGAMG: fix corruption for multiple solves when MatSetNearNullSpace is used
PCGAMG: remove distracting comment
KSP ex49: restrict near-null space for elasticity example with sym BC
MatMPIBAIJSetPreallocationCSR() handled the input matrix entries incorrectly, it treated them as if each row of values was provided ordered by row within the block rows instead of by block as it was originally designed to be. Also added more discussion to the manual pages on the expected order of the values
Fix accidental creation of the matrices in SNESNCG used for linear analogue LS.
PCGAMG: add man page for PCGAMGType
fortran: fix snesconvergedskip_() kspconvergedskip_() kspconvergeddefault*_()
rm //
Sys: new_ir changed from PetscInt to PetscObjectState - so fix mallocs to use the new type
SNES: Fixed package init in SNESLineSearchCreate()
...

Conflicts:
include/petscdmplex.h
src/dm/impls/plex/examples/tests/ex5.c
src/dm/impls/plex/plex.c
src/dm/interface/dm.c

show more ...

Merge branch 'jed/remove-dynamic-loading-option'

Option --with-dynamic-loading has been removed. Similar functionality
is available via the run-time option -dynamic_library_preload.

* jed/remove-d

Merge branch 'jed/remove-dynamic-loading-option'

Option --with-dynamic-loading has been removed. Similar functionality
is available via the run-time option -dynamic_library_preload.

* jed/remove-dynamic-loading-option:
Sys: PetscContainerCreate must call PetscSysInitializePackage
Remove --with-dynamic-loading / PETSC_USE_DYNAMIC_LIBRARIES

Conflicts:
src/dm/impls/mesh/mesh.c
src/dm/interface/dlregisdmdm.c
src/docs/website/documentation/changes/dev.html

show more ...

Merge branch 'hzhang/snes-jacobiancoloropt' of bitbucket.org:petsc/petsc into hzhang/snes-jacobiancoloropt

Merge branch 'hzhang/snes-jacobiancoloropt' of bitbucket.org:petsc/petsc into hzhang/snes-jacobiancoloropt

Merge branch 'master' into barry/dmvecmattypes
possible some messed up manual merges!

Conflicts:
src/dm/impls/mesh/examples/tutorials/ex4f90.F
src/dm/impls/mesh/mesh.c
src/dm/impls/mesh/meshcreat

Merge branch 'master' into barry/dmvecmattypes
possible some messed up manual merges!

Conflicts:
src/dm/impls/mesh/examples/tutorials/ex4f90.F
src/dm/impls/mesh/mesh.c
src/dm/impls/mesh/meshcreate.c
src/dm/impls/mesh/section.c
src/snes/examples/tutorials/ex10.c
src/snes/examples/tutorials/ex12.c
src/snes/examples/tutorials/ex52.c
src/snes/examples/tutorials/ex62.c
src/snes/utils/mesh/dmmeshsnes.c

show more ...

Merge branch 'knepley/remove-sieve'

Conflicts:
src/dm/impls/mesh/examples/tests/output/ex10_0.out
src/dm/impls/mesh/examples/tests/output/ex10_1.out
src/dm/impls/mesh/examples/tests/output/ex11f9

Merge branch 'knepley/remove-sieve'

Conflicts:
src/dm/impls/mesh/examples/tests/output/ex10_0.out
src/dm/impls/mesh/examples/tests/output/ex10_1.out
src/dm/impls/mesh/examples/tests/output/ex11f90_0.out
src/dm/impls/mesh/examples/tests/output/ex11f90_1.out
src/dm/impls/mesh/examples/tests/output/ex3_0.out
src/dm/impls/mesh/examples/tests/output/ex3_1.out
src/dm/impls/mesh/examples/tests/output/ex3_2.out
src/dm/impls/mesh/examples/tests/output/ex3_3.out
src/dm/impls/mesh/examples/tests/output/ex8_0.out
src/dm/impls/mesh/examples/tests/output/ex9f90_0.out
src/dm/impls/mesh/examples/tests/output/ex9f90_1.out
src/dm/impls/mesh/mesh.c
src/dm/interface/dlregisdmdm.c
src/vec/vec/interface/vecregall.c

show more ...

Merge branch 'master' into barry/wirth-fusion-materials

Conflicts:
src/ts/examples/tutorials/advection-diffusion-reaction/ex10.c

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

* master: (124 commits)
SNES ex12: Fix buggy checkin
add missing output file src/snes/examples/tutorials/output/ex14_3.out
fixed bunch

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

* master: (124 commits)
SNES ex12: Fix buggy checkin
add missing output file src/snes/examples/tutorials/output/ex14_3.out
fixed bunch of bibtex items that should ahve used abbreviations only
PetscDualSpace: Pointer check barfs for function pointer
Sys: Add ability to turn off CUBLAS initialization - This continually SEGVs on my Air
SNES ex62: Updated test output - Matrix now prints attached nullspace indicator - 3D tests are wierdly different, they need to be verified by hand
SNES ex12: Updated test output - Mostly for completed labels
SNES ex12/62: Changed to new DMPlexProjectFunction() interface - Took DM out of main struct
SNES ex12/62: Complete boundary label - Puts in edges in 3D - Perhaps should be moved to the creation routine
PetscDualSpace: Fixed orientation of reference tetrahedron - Now this does not match FIAT
PetscDualSpace: Fixed numDof for P0
PetscDualSpace: Added PetscDualSpaceApply() for the action of a functional - Declared PetscDualSpaceGetFunctional()
DMPlex: Updated ProjectFunction() to use PetscDualSpace for generic projection - Has not been tested with moment dofs - Accommodates vector functions
DMPlex: Added support for INSERT_BC_VALUES in VecSetClosure()
DMPlex: Fixed missing RestoreTransitiveClosure()
DMPlex: Fixed optimized portion of VecGetClosure() for NULL input array
DMPlex: Allow NULL array as input to DMPlexVecGetClosure()
DMPlex: Fix VecGetClosure() when the array is input
PetscFE: OpenCL is hardcoded for P0 coefficients right now
SNES ex12: Added test cases for variable coefficient Laplace - The P1 tests reproduce the analytic linear coefficient
...

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

show more ...

Merge branch 'knepley/feature-dt-fem'

* knepley/feature-dt-fem: (122 commits)
SNES ex12: Fix buggy checkin
PetscDualSpace: Pointer check barfs for function pointer
Sys: Add ability to turn off

Merge branch 'knepley/feature-dt-fem'

* knepley/feature-dt-fem: (122 commits)
SNES ex12: Fix buggy checkin
PetscDualSpace: Pointer check barfs for function pointer
Sys: Add ability to turn off CUBLAS initialization - This continually SEGVs on my Air
SNES ex62: Updated test output - Matrix now prints attached nullspace indicator - 3D tests are wierdly different, they need to be verified by hand
SNES ex12: Updated test output - Mostly for completed labels
SNES ex12/62: Changed to new DMPlexProjectFunction() interface - Took DM out of main struct
SNES ex12/62: Complete boundary label - Puts in edges in 3D - Perhaps should be moved to the creation routine
PetscDualSpace: Fixed orientation of reference tetrahedron - Now this does not match FIAT
PetscDualSpace: Fixed numDof for P0
PetscDualSpace: Added PetscDualSpaceApply() for the action of a functional - Declared PetscDualSpaceGetFunctional()
DMPlex: Updated ProjectFunction() to use PetscDualSpace for generic projection - Has not been tested with moment dofs - Accommodates vector functions
DMPlex: Added support for INSERT_BC_VALUES in VecSetClosure()
DMPlex: Fixed missing RestoreTransitiveClosure()
DMPlex: Fixed optimized portion of VecGetClosure() for NULL input array
DMPlex: Allow NULL array as input to DMPlexVecGetClosure()
DMPlex: Fix VecGetClosure() when the array is input
PetscFE: OpenCL is hardcoded for P0 coefficients right now
SNES ex12: Added test cases for variable coefficient Laplace - The P1 tests reproduce the analytic linear coefficient
PetscFE: Added auxiliary fields to PetscFEIntegrateJacobian() - Hooked it up to DMPlexComputeJacobian()
SNES ex12: Removed code generation
...

show more ...

Merge branch 'barry/dmvecmattypes' into barry/saws

Needed to work with version of PETSc that did not have constant calls to VecSetFromOptions() etc

Conflicts:
src/ksp/ksp/interface/ams/kspams.c
s

Merge branch 'barry/dmvecmattypes' into barry/saws

Needed to work with version of PETSc that did not have constant calls to VecSetFromOptions() etc

Conflicts:
src/ksp/ksp/interface/ams/kspams.c
src/snes/impls/composite/snescomposite.c
src/snes/impls/gs/snesgs.c
src/snes/impls/nasm/nasm.c
src/snes/impls/ngmres/snesngmres.c

show more ...

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

* knepley/feature-dt-fem: (123 commits)
SNES ex12: Fix buggy checkin
Builder: strip test output before comparing
PetscDua

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

* knepley/feature-dt-fem: (123 commits)
SNES ex12: Fix buggy checkin
Builder: strip test output before comparing
PetscDualSpace: Pointer check barfs for function pointer
Sys: Add ability to turn off CUBLAS initialization - This continually SEGVs on my Air
SNES ex62: Updated test output - Matrix now prints attached nullspace indicator - 3D tests are wierdly different, they need to be verified by hand
SNES ex12: Updated test output - Mostly for completed labels
SNES ex12/62: Changed to new DMPlexProjectFunction() interface - Took DM out of main struct
SNES ex12/62: Complete boundary label - Puts in edges in 3D - Perhaps should be moved to the creation routine
PetscDualSpace: Fixed orientation of reference tetrahedron - Now this does not match FIAT
PetscDualSpace: Fixed numDof for P0
PetscDualSpace: Added PetscDualSpaceApply() for the action of a functional - Declared PetscDualSpaceGetFunctional()
DMPlex: Updated ProjectFunction() to use PetscDualSpace for generic projection - Has not been tested with moment dofs - Accommodates vector functions
DMPlex: Added support for INSERT_BC_VALUES in VecSetClosure()
DMPlex: Fixed missing RestoreTransitiveClosure()
DMPlex: Fixed optimized portion of VecGetClosure() for NULL input array
DMPlex: Allow NULL array as input to DMPlexVecGetClosure()
DMPlex: Fix VecGetClosure() when the array is input
PetscFE: OpenCL is hardcoded for P0 coefficients right now
SNES ex12: Added test cases for variable coefficient Laplace - The P1 tests reproduce the analytic linear coefficient
PetscFE: Added auxiliary fields to PetscFEIntegrateJacobian() - Hooked it up to DMPlexComputeJacobian()
...

show more ...

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/plex-profile-distribution'

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

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+PetscFE: Moved integration functions from DMPlex to PetscFE
- Now PetscFE type indicates the integration method
- Added all machinery for PetscFE types

PetscFE: FEM Jacobian computation working, and now cache default tabulation
- Added PetscFEIntegratJacobianChunk()
- Changed interface in DMPlexComputeJacobianFEM()
- Changed signature of integrateJa

PetscFE: FEM Jacobian computation working, and now cache default tabulation
- Added PetscFEIntegratJacobianChunk()
- Changed interface in DMPlexComputeJacobianFEM()
- Changed signature of integrateJacobianFEM in DMPlex
- Added DMPLEX_JacobianFEM event
- Now PetscFE caches default tabulation

show more ...

PetscFE: Large reorganization of FEM dispatch
- WARNING: Now DMPlex and PetscFE have a circular dependence. We need to move the FEM methods to PetscFE
- Changed FEMIntegrateResidualBatch() from to Pe

PetscFE: Large reorganization of FEM dispatch
- WARNING: Now DMPlex and PetscFE have a circular dependence. We need to move the FEM methods to PetscFE
- Changed FEMIntegrateResidualBatch() from to PetscFEIntegrateResidualChunk()
- Changed DMPlexComputeResidualFEM() to use new interface
- Changed signature of f_k and g_kl functions
- Added DMPlexResidualFEM event
- Put PetscQuadrature and PetscCellGeometry
- Moved and changed PetscFEM structure

show more ...

PetscFE: Added package initialization to DM, register classes

DMPlex: Added new events for distribution