PetscSection: Fix View() to use viewer with right communicator

Removed crumbs from previous support of Netcdf. Support was removed in 2010

Time: .2 hours

Merge branch 'barry/add-matfdcoloring-ghosted-example'

Refactored ./configures handling of package requirements for precision. Now each package indicates
what it supports with
self.precisions = ['single','double','__float128']
Updated the package files t

Refactored ./configures handling of package requirements for precision. Now each package indicates
what it supports with
self.precisions = ['single','double','__float128']
Updated the package files to indicate what they support
Removed unneeded #requires arguments from makefiles for external packages.

Time: 2 hours
Reported-by: Patrick Sanan <patrick.sanan@gmail.com>

show more ...

Changed IS_COLORING_GHOSTED to IS_COLORING_LOCAL, added test case, fixed code to work properly

Time: 5 hours
Reported-by: Hong Zhang <hzhang@mcs.anl.gov>

Merge branch 'maint'

Some Fortran stubs that returned strings could produce garbage

Some Fortran stubs that returned strings did not properly use FIXRETURNCHAR() to blank out the end of the Fortran string. Thus the Fort

Some Fortran stubs that returned strings could produce garbage

Some Fortran stubs that returned strings did not properly use FIXRETURNCHAR() to blank out the end of the Fortran string. Thus the Fortran string would contain "garbage".

Time: .2 hours
Reported-by: Mark Filipiak <m.filipiak@epcc.ed.ac.uk>

show more ...

Merge branch 'maint'

Merge branch 'tisaac/dualspace-feature-symmetry'

In finite element assembly, to compute a residual or assemble a Jacobian
on an element, the dual space functionals of a reference finite element are

Merge branch 'tisaac/dualspace-feature-symmetry'

In finite element assembly, to compute a residual or assemble a Jacobian
on an element, the dual space functionals of a reference finite element are related
(i.e., pushed forward) to the functionals that make of the degrees of
freedom of the discretized system.

In doing so, we have to draw a correspondence between the boundary
points of the reference element (its edges and vertices) and the
boundary points of each cell in the mesh. Sometimes, this
correspondence is not perfect, because the orientations of the boundary
points of a cell may be different than the orientations of the boundary
points of the reference element. For example, an edge that runs
clockwise around the reference element may map onto an edge that runs
counter-clockwise around the real cell.

For some finite elements (such as the most common P1 Lagrange finite
elements) this doesn't matter. But for others---high-order elements,
H-div and H-curl conforming elements---a difference in orientation
affects the mapping between reference functionals and degrees of
freedom.

The simplest example is a high-order nodal Lagrange finite element in
2D: the degrees of freedom on an edge of the reference element are
numbered left-to-right, but if the orientation of the real edge is
reverse, then we must read/write degrees of freedom right-to-left.

Things get more complicated in 3D: a quadrilateral face between
hexahedra may have any of 8 different orientations (that make of the
dihedral symmetries), and each one corresponds to a different reordering
of the 2D grid of nodes supported on that quadrilateral.

Things also get more complicated for H-div elements. Functionals on the
interfaces between cells represent the flux from one cell to another,
and thus have direction. Reversing the orientation of an edge changes
the sign of the mapping between the reference functional and the degree
of freedom.

To assemble generic finite elements, we thus need to accommodate
transforms between reference functionals and degrees of freedom that
encompass (1) permutations, and (2) scalar multipliers.

This branch accomplishes this in two steps:

- We add PetscDualSpaceGetSymmetries() to the interface, to allow a dual
space to describe how symmetries of the mesh points affect
referent-to-real maps of functionals.

- We add PetscSectionSym, an object that encapsulates symmetries of the
degrees of freedom whose layout is described by a PetscSection.

When a section is created from a DM that has a finite element
discretization in its PetscDS, it will automatically construct the
appropriate PetscSectionSym when it creates a PetscSection to describe a
discretized function space.

If a PetsFE finite element discretization is not used, the user can
create a PetscSectionSym for their degrees of freedom for themselves.
We give an example of this for spectal elements in
src/dm/impls/plex/examples/tutoerials/ex6.c.

* tisaac/dualspace-feature-symmetry: (22 commits)
cast memzeros to void to avoid compiler complaints about const qualifiers
DMPlex: fix stray PetscScalar to PetscReal
DMPlex: fix stray PetscScalar to PetscReal
Plex tutorials ex6: use symmetries in SEM example
Plex tests ex3: added high order tests
Plex tests ex3: add matrix-free near null space test
DMPlex: fix PetscInt %D PetscPrintf character
DMPlexTree: use symmetries when computing constraint matrices
DMPlex: use symmetries in DMPlexGetIndicesPoint{Fields}_Internal() and DMPlexAnchorsModifyMat()
DMPlex: use PetscSectionGet/RestorePointSyms() in DMPlexVecGet/SetClosure()
DMPlex: added DMPlexGet/RestoreCompressedClosure()
DMPlex: added DMPlexGetPointDualSpaceFEM()
DMPlex: set PetscSectionSym in DMPlexCreateSectionInitial()
DMLabel: added PETSCSECTIONSYMLABEL
PetscSection: add PetscSectionSym
PetscDualSpace: added PetscDualSpaceGetSymmetries()
PetscDualSpace_Lagrange: setup recursively on dimension
PetscDualSpace_Lagrange: order functions now go after tuple used
PetscDualSpace_Lagrange: use lexicographic order for nodes
DMPlex: added DMPlexComputePointGeometry_Internal()
...

show more ...

cast memzeros to void to avoid compiler complaints about const qualifiers

VecScatter: add custom fortran stub, cribbed from ISColoringView stub

PetscSection: add PetscSectionSym

This object's is essentially a Petsc-idiom way of letting the user
specify implementations of

PetscSectionGetPointSyms()
PetscSectionRestorePointSyms()
PetscSectio

PetscSection: add PetscSectionSym

This object's is essentially a Petsc-idiom way of letting the user
specify implementations of

PetscSectionGetPointSyms()
PetscSectionRestorePointSyms()
PetscSectionGetFieldPointSyms()
PetscSectionRestoreFieldPointSyms()

Like PetscDualSpaceGetSymmetries(), the symmetries are descibed by R *
P, where R is a flip (or rotation with complex scalars). I had thought
about a more managed approach, like PetscSectionGet/SetValues, which
entirely hid the existence of symmetries to begin with, but:

- then you have to differentiate between different PetscDataTypes (e.g.,
for indices, just perform the permutation, not the flips/rotations),
and
- what about inserting an element matrix? When inserting an element
matrix, it makes the most sense to apply flips/rotations to the
element matrix, and the permutations to the indices where the matrix
is to be inserted with MatSetValues().

so in the end I decided to just provide a simple interface to pass the
symmetries to the users and let them figure out how they want to use
them.

show more ...

Merge branch 'tisaac/is-fix-min-max'

* tisaac/is-fix-min-max:
IS: for an empty index set, we should have max < min

IS: for an empty index set, we should have max < min

We might want min = PETSC_MAX_INT and max = PETSC_MIN_INT, but I think
it's convenient to have (max + 1 - min) = (-2 + 1 - -1) = 0 for an empty
s

IS: for an empty index set, we should have max < min

We might want min = PETSC_MAX_INT and max = PETSC_MIN_INT, but I think
it's convenient to have (max + 1 - min) = (-2 + 1 - -1) = 0 for an empty
set.

show more ...

Merge branch 'jose/veccuda-tests'

Conflicts:
config/PETSc/Regression.py

* jose/veccuda-tests:
This is an attempt to modify configure to run regression tests with VECCUDA.
The tests for CUSP ar

Merge branch 'jose/veccuda-tests'

Conflicts:
config/PETSc/Regression.py

* jose/veccuda-tests:
This is an attempt to modify configure to run regression tests with VECCUDA.
The tests for CUSP are left unchanged.
The new tests include CUSPARSE and work with real and complex scalars.
See PR #490 for discussion.

show more ...

Merge branch 'karlrupp/feature-viennacl-hybrid'

Conflicts:
src/mat/impls/aij/mpi/makefile

* karlrupp/feature-viennacl-hybrid:
Added hybrid capabilities (CUDA, OpenCL, OpenMP) for ViennaCL bindi

Merge branch 'karlrupp/feature-viennacl-hybrid'

Conflicts:
src/mat/impls/aij/mpi/makefile

* karlrupp/feature-viennacl-hybrid:
Added hybrid capabilities (CUDA, OpenCL, OpenMP) for ViennaCL bindings.
Depending on whether the user configures with CUDA, OpenCL, or OpenMP,
the respective backends will be available in ViennaCL.
Available options:
- viennacl_view: Lists available and selected backends
- viennacl_backed: One out of CUDA, OpenCL, OpenMP (if enabled in configure)
- viennacl_opencl_device_type: cpu, gpu, accelerator (OpenCL device type selection)

show more ...

Merge branch 'maint'

Vec: enable Fortran interfaces for VecGetLocalVectorRead and VecRestoreLocalVectorRead

fix typo in isltog comment

Merge branch 'stefano_zampini/fix-matis'

Conflicts:
src/mat/examples/tests/makefile

Merge branch 'maint'

fortran: enable interface for VecGetLocalVector(), VecRestoreLocalVector()

Reported-by: Patrick Sanan <patrick.sanan@gmail.com>

Merge remote-tracking branch 'origin/maint'

Fix warnings from gfortran 6.1 (OS X, Homebrew build)

gfortran 6.1 seems to include -Wconversion in -Wall. When configuring
with 64bit indices, the compiler emit warnings about conversions from
INTE

Fix warnings from gfortran 6.1 (OS X, Homebrew build)

gfortran 6.1 seems to include -Wconversion in -Wall. When configuring
with 64bit indices, the compiler emit warnings about conversions from
INTEGER(8) to REAL(4). Use REAL() intrinsic to silence the warnings.

show more ...

PetscSF: test Bcast with dupped input datatype