MatDuplicate() for sequential AIJ did not copy over required field
MatDuplicate() does not copy over DM hence things like MatView() fail
Changed PCGAMGFilterGraph() to diagonally scale and use absolu

MatDuplicate() for sequential AIJ did not copy over required field
MatDuplicate() does not copy over DM hence things like MatView() fail
Changed PCGAMGFilterGraph() to diagonally scale and use absolute values of graph matrix even for negative threshold; don't know if this is needed in the algorithm or not

show more ...

added manual Fortran stubs for MatGetRowMin[Abs] to allow PETSC_NULL_INTEGER argument for idx

Allow PETSC_NULL_INTEGER arguments for MatGetRow and MatGetRowMax calls

Merge branch 'master' into stefano_zampini/pcbddc-adaptive-selection

Merge branch 'master' into knepley/feature-harmonic-advection

* master: (205 commits)
Bib: Added bio refs
Don't print SAWs URL since it disturbs all the test output
missing (double) cast in pr

Merge branch 'master' into knepley/feature-harmonic-advection

* master: (205 commits)
Bib: Added bio refs
Don't print SAWs URL since it disturbs all the test output
missing (double) cast in print statement
don't output to test file all 12 digits of values
fixes and additions to SNESQM manual pages
PetscViewerBinaryGetDescriptor() is now a collective and must be treated as such fixed some calls to PetscViewerBinarySetUseMPIIO() removed some test runs that take too long
removed dead routine
ViennaCL: Added MCS download mirror URL for version 1.6.2
shift order of processing options for TS to be compatiable with SAWs Fix options handling for SAWs to duplicate array that previously was deleted too soon for SAWs processing
remove some dead code for AD and old AMS java and Matlab utilities
add missing PetscFunctionBegin; that messed up displaying of stack
Viewer: Fixed PetscViewerBinarySetUseMPIIO() in some examples
removed unused variables, removed dead code from AMS
git is so freaking annoying I accidently made a bunch of updates in next which I pushed lets see if this diff makes the same changes in my branch Why can't git just forbid me to make changes or next or set up some utility to prevent it!
moved saws directory to proper share directory location updated source to point to it.
rm checkboxes at top of pcoptions.html (ugly and not useful) and centered display of solver
PetscOptionsObject->prefix was freed before using in SAWs post processing hence SAWs was unable to change any type which had a prefix
display URL to point to to access SAWs server
missing break in case for handling string arguments better description for Options database option handling
removed extern PC_CLASSID and KSP_CLASSID that don't belong in petscoptions.h
...

show more ...

Merge branch 'barry/saws-options-merge-master'

MatStash BTS: add MAT_SUBSET_OFF_PROC_ENTRIES, impl with neighbor-only comm

Add MatOption to imprint a communication pattern on the first assembly
and reuse on subsequent assemblies. Messages of si

MatStash BTS: add MAT_SUBSET_OFF_PROC_ENTRIES, impl with neighbor-only comm

Add MatOption to imprint a communication pattern on the first assembly
and reuse on subsequent assemblies. Messages of size 0 are sent if no
values need to be communicated to that rank. Since there are no
collectives (even Ibarrier) and no separate headers, this should be more
efficient for large process counts. The BTS implementation must
currently be activated via the -matstash_bts option.

show more ...

Merge branch 'master' into stefano_zampini/pcbddc-adaptive-selection

Conflicts:
src/ksp/pc/impls/bddc/bddcprivate.c

add missing PetscFunctionBegin; that messed up displaying of stack

Merge branch 'master' into barry/saws-options-merge-master

Totally confusing manual merge, could be wrong

Conflicts:
include/petscoptions.h
src/dm/impls/da/dacreate.c
src/sys/objects/aoptions.c

Merge branch 'master' into barry/saws-options-merge-master

Totally confusing manual merge, could be wrong

Conflicts:
include/petscoptions.h
src/dm/impls/da/dacreate.c
src/sys/objects/aoptions.c
src/sys/threadcomm/interface/threadcomm.c

show more ...

Merge branch 'master' into pr252/dmay/PetscViewerBinarySkipHeaderVecViewLoad
Manual merge of makefile

Conflicts:
src/sys/classes/viewer/examples/tutorials/makefile

Merge branch 'barry/refactor-petscsubcomm'

Merge branch 'xolotl'

Conflicts:
src/mat/impls/aij/mpi/mpiaij.c

minor cleanup of PetscSubcomm code and documentation

Merge branch 'master' into stefano_zampini/pcbddc-adaptive-selection

Merge branch 'barry/feature-vec-lock'

Added VecLockPush/Pop() around SNES callbacks etc
Added DADAVecGetArray[DOF]Read()
Added use of GetArrayRead() as needed
Added many more const as needed

Note DMDAVecGetArray[DOF]Read() does not yet

Added VecLockPush/Pop() around SNES callbacks etc
Added DADAVecGetArray[DOF]Read()
Added use of GetArrayRead() as needed
Added many more const as needed

Note DMDAVecGetArray[DOF]Read() does not yet require correctly consted argument

show more ...

Added VecLockPush() and VecLockPop() to make vector read only
Used VecLockPush() and VecLockPop() in a couple of key locations; PCApply(), KSPSolve(), MatMult()
Fixed many uses of VecGetArray() to Ve

Added VecLockPush() and VecLockPop() to make vector read only
Used VecLockPush() and VecLockPop() in a couple of key locations; PCApply(), KSPSolve(), MatMult()
Fixed many uses of VecGetArray() to VecGetArrayRead()
Added VecGet/RestoreArrayPair() for commonly occuring pattern
Added const to many locations driven by use of VecGetArrayRead()

show more ...

Merge branch 'tisaac/feature-gamg-extensible' into barry/experiment

Conflicts:
src/ksp/pc/impls/gamg/gamg.h

Merge branch 'knepley/feature-combined-tabulation' into knepley/feature-ts-fem+fvm-example

* knepley/feature-combined-tabulation: (41 commits)
Plex: Fix distribution of uninterpolated meshes - Doe

Merge branch 'knepley/feature-combined-tabulation' into knepley/feature-ts-fem+fvm-example

* knepley/feature-combined-tabulation: (41 commits)
Plex: Fix distribution of uninterpolated meshes - Does SF stratification by depth, not by dimension - The old code numbered cells after vertices
Plex+SNES: Fixes for nonzero cStart
cannot call PetscObjectGetName() on a subset of the MPI processes
MatView() with some matrix formats and ASCII_MATLAB did not print correct matrix name
Plex: Preserve periodicity when adding ghost cells
Plex: Fixed DMPlexGetGlobalFieldOffset_Private() in optimized mode
Plex+SNES: Offset should be into field components, not basis functions
Plex+SNES: Add guards for optional arrays
DS: Added PetscDSGetComponentOffset(), Added to petsc.h
Plex+TS: FVM RHS computation uses a global F
Plex+FV: Corrected accumulation of fluxes to cells and added time derivative term
Plex: Added DMPlexPointGlobalFieldRead/Ref()
Plex+SNES: Fixed DMPlexGetFaceFields() - It returns field values, not coefficients - FE evaluation is now done
FV: In PetscFVIntegrateRHSFunction(), the arguments are field values, not coefficients
FE: Added EvaluateFaceFields() to FE fields at face centroids
Plex: Added DMPlexPointLocalFieldRead()
FE: Have a standard tabulation at face centroids
Plex: Copy BC for hierarchical refinement
FE: Allow P0 over 1D cells
Plex+FV: Fixed BC with gradient calculation
...

Conflicts:
config/builder.py

show more ...

Fixed formatting in MatSetOption manual page

Reported-by: Sebastien Gilles <sebastien.gilles@inria.fr>

Merge branch 'master' of bitbucket.org:petsc/petsc into mark/gamg-crs-ksp2

mv include/finclude to include/petsc-finclude for namespacing in installs

mv include/finclude to include/petsc-finclude for namespacing in installs

Merge branch 'master' into barry/ksp-converged-reason-viewer

Conflicts:
src/sys/objects/options.c