Provided by: python-petsc4py-doc_3.22.4-1ubuntu1_all 
NAME
petsc4py - PETSc for Python
Author Lisandro Dalcin
Contact
dalcinl@gmail.com
Web Site
https://gitlab.com/petsc/petsc
Date Mar 12, 2025
Abstract
This document describes petsc4py, a Python wrapper to the PETSc libraries.
PETSc (the Portable, Extensible Toolkit for Scientific Computation) is a suite of data structures and
routines for the scalable (parallel) solution of scientific applications modeled by partial differential
equations. It employs the MPI standard for all message-passing communication.
This package provides an important subset of PETSc functionalities and uses NumPy to efficiently manage
input and output of array data.
A good friend of petsc4py is:
• mpi4py: Python bindings for MPI, the Message Passing Interface.
Other projects depend on petsc4py:
• slepc4py: Python bindings for SLEPc, the Scalable Library for Eigenvalue Problem Computations.
PETSC OVERVIEW
PETSc is a suite of data structures and routines for the scalable (parallel) solution of scientific
applications modeled by partial differential equations. It employs the MPI standard for all
message-passing communication.
PETSc is intended for use in large-scale application projects [petsc-efficient], and several ongoing
computational science projects are built around the PETSc libraries. With strict attention to component
interoperability, PETSc facilitates the integration of independently developed application modules, which
often most naturally employ different coding styles and data structures.
PETSc is easy to use for beginners [petsc-user-ref]. Moreover, its careful design allows advanced users
to have detailed control over the solution process. PETSc includes an expanding suite of parallel linear
and nonlinear equation solvers that are easily used in application codes written in C, C++, and Fortran.
PETSc provides many of the mechanisms needed within parallel application codes, such as simple parallel
matrix and vector assembly routines that allow the overlap of communication and computation.
[petsc-user-ref]
S. Balay, S. Abhyankar, M. Adams, S. Benson, J. Brown, P. Brune, K. Buschelman, E. Constantinescu,
L. Dalcin, A. Dener, V. Eijkhout, J. Faibussowitsch, W. Gropp, V. Hapla, T. Isaac, P. Jolivet, D.
Karpeyev, D. Kaushik, M. Knepley, F. Kong, S. Kruger, D. May, L. Curfman McInnes, R. Mills, L.
Mitchell, T. Munson, J. Roman, K. Rupp, P. Sanan, J Sarich, B. Smith, H. Suh, S. Zampini, H. Zhang,
and H. Zhang, J. Zhang, PETSc/TAO Users Manual, ANL-21/39 - Revision 3.22, 2024. ‐
http://dx.doi.org/10.2172/2205494, https://petsc.org/release/docs/manual/manual.pdf
[petsc-efficient]
Satish Balay, Victor Eijkhout, William D. Gropp, Lois Curfman McInnes and Barry F. Smith. Efficient
Management of Parallelism in Object Oriented Numerical Software Libraries. Modern Software Tools in
Scientific Computing. E. Arge, A. M. Bruaset and H. P. Langtangen, editors. 163--202. Birkhauser
Press. 1997.
Components
PETSc is designed with an object-oriented style. Almost all user-visible types are abstract interfaces
with implementations that may be chosen at runtime. Those objects are managed through handles to opaque
data structures which are created, accessed and destroyed by calling appropriate library routines.
PETSc consists of a variety of components. Each component manipulates a particular family of objects and
the operations one would like to perform on these objects. These components provide the functionality
required for many parallel solutions of PDEs.
Vec Provides the vector operations required for setting up and solving large-scale linear and
nonlinear problems. Includes easy-to-use parallel scatter and gather operations, as well as
special-purpose code for handling ghost points for regular data structures.
Mat A large suite of data structures and code for the manipulation of parallel sparse matrices.
Includes several different parallel matrix data structures, each appropriate for a different class
of problems.
PC A collection of sequential and parallel preconditioners, including (sequential) ILU(k), LU, and
(both sequential and parallel) block Jacobi, overlapping additive Schwarz methods.
KSP Parallel implementations of many popular Krylov subspace iterative methods, including GMRES, CG,
CGS, Bi-CG-Stab, two variants of TFQMR, CR, and LSQR. All are coded so that they are immediately
usable with any preconditioners and any matrix data structures, including matrix-free methods.
SNES Data-structure-neutral implementations of Newton-like methods for nonlinear systems. Includes both
line search and trust region techniques with a single interface. Employs by default the above data
structures and linear solvers. Users can set custom monitoring routines, convergence criteria,
etc.
TS Code for the time evolution of solutions of PDEs. In addition, provides pseudo-transient
continuation techniques for computing steady-state solutions.
INSTALLATION
Install from PyPI using pip
You can use pip to install petsc4py and its dependencies (mpi4py is optional but highly recommended):
$ python -m pip install mpi4py petsc petsc4py
Install from the PETSc source tree
First build PETSc. Next cd to the top of the PETSc source tree and set the PETSC_DIR and PETSC_ARCH
environment variables. Run:
$ python -m pip install src/binding/petsc4py
The installation of petsc4py supports multiple PETSC_ARCH in the form of colon separated list:
$ PETSC_ARCH='arch-0:...:arch-N' python -m pip install src/binding/petsc4py
If you are cross-compiling, and the numpy module cannot be loaded on your build host, then before
invoking pip, set the NUMPY_INCLUDE environment variable to the path that would be returned by import
numpy; numpy.get_include():
$ export NUMPY_INCLUDE=/usr/lib/pythonX/site-packages/numpy/core/include
Running the testing suite
When installing from source, the petsc4py complete testsuite can be run as:
$ cd src/binding/petsc4py
$ python test/runtests.py
or via the makefile rule test:
$ make test -C src/binding/petsc4py
Specific tests can be run using the command-line option -k, e.g.:
$ python test/runtests.py -k test_optdb
to run all the tests provided in tests/test_optdb.py.
For other command-line options, run:
$ python test/runtests.py --help
If not otherwise specified, all tests will be run in sequential mode. To run all the tests with the same
number of MPI processes, for example 4, run:
$ mpiexec -n 4 python test/runtests.py
or:
$ make test-4 -C src/binding/petsc4py
Building the documentation
Install the documentation dependencies:
$ python -m pip install -r ${PETSC_DIR/doc/requirements.txt
Then:
$ cd src/binding/petsc4py/docs/source
$ make html
The resulting HTML files will be in _build/html.
NOTE:
Building the documentation requires Python 3.11 or later.
CONTRIBUTING
Contributions from the user community are welcome. See the PETSc developers documentation for general
information on contributions.
New contributions to petsc4py must adhere with the coding standards. We use cython-lint for Cython and ‐
ruff for Python source codes. These can be installed using:
$ python -m pip install -r src/binding/petsc4py/conf/requirements-lint.txt
If you are contributing Cython code, you can check compliance with:
$ make cython-lint -C src/binding/petsc4py
For Python code, run:
$ make ruff-lint -C src/binding/petsc4py
Python code can be auto-formatted using:
$ make ruff-lint RUFF_OPTS='format' -C src/binding/petsc4py
New contributions to petsc4py must be tested. Tests are located in the src/binding/petsc4py/test folder.
To add a new test, either add a new test_xxx.py or modify a pre-existing file according to the unittest
specifications.
If you add a new test_xxx.py, you can run the tests using:
$ cd src/binding/petsc4py
$ python test/runtests.py -k test_xxx
If instead you are modifying an existing test_xxx.py, you can test your additions by using the fully
qualified name of the Python class or method you are modifying, e.g.:
$ python test/runtests.py -k test_xxx.class_name.method_name
All new code must include documentation in accordance with the documentation standard. To check for
compliance, run:
$ make html SPHINXOPTS='-W' -C src/binding/petsc4py/docs/source
WARNING:
The docstrings must not cause Sphinx warnings.
CITATIONS
If PETSc for Python has been significant to a project that leads to an academic publication, please
acknowledge that fact by citing the project.
• L. Dalcin, P. Kler, R. Paz, and A. Cosimo, Parallel Distributed Computing using Python, Advances in
Water Resources, 34(9):1124-1139, 2011. https://doi.org/10.1016/j.advwatres.2011.04.013
• S. Balay, S. Abhyankar, M. Adams, S. Benson, J. Brown, P. Brune, K. Buschelman, E. Constantinescu, L.
Dalcin, A. Dener, V. Eijkhout, J. Faibussowitsch, W. Gropp, V. Hapla, T. Isaac, P. Jolivet, D.
Karpeyev, D. Kaushik, M. Knepley, F. Kong, S. Kruger, D. May, L. Curfman McInnes, R. Mills, L.
Mitchell, T. Munson, J. Roman, K. Rupp, P. Sanan, J Sarich, B. Smith, H. Suh, S. Zampini, H. Zhang, and
H. Zhang, J. Zhang, PETSc/TAO Users Manual, ANL-21/39 - Revision 3.22, 2024. ‐
https://doi.org/10.2172/2205494, https://petsc.org/release/docs/manual/manual.pdf
REFERENCE
┌─────────────────┬───────────────────────────────────────┐
│ petsc4py │ The PETSc for Python package. │
├─────────────────┼───────────────────────────────────────┤
│ petsc4py.typing │ Typing support. │
├─────────────────┼───────────────────────────────────────┤
│ petsc4py.PETSc │ Portable, Extensible Toolkit for │
│ │ Scientific Computation. │
└─────────────────┴───────────────────────────────────────┘
petsc4py
The PETSc for Python package.
This package is an interface to PETSc libraries.
PETSc (the Portable, Extensible Toolkit for Scientific Computation) is a suite of data structures and
routines for the scalable (parallel) solution of scientific applications modeled by partial differential
equations. It employs the MPI standard for all message-passing communications.
Functions
┌──────────────────────────┬───────────────────────────────────────┐
│ get_config() │ Return a dictionary with information │
│ │ about PETSc. │
├──────────────────────────┼───────────────────────────────────────┤
│ get_include() │ Return the directory in the package │
│ │ that contains header files. │
├──────────────────────────┼───────────────────────────────────────┤
│ init([args, arch, comm]) │ Initialize PETSc. │
└──────────────────────────┴───────────────────────────────────────┘
petsc4py.get_config
petsc4py.get_config()
Return a dictionary with information about PETSc.
Return type
dict[str, str]
petsc4py.get_include
petsc4py.get_include()
Return the directory in the package that contains header files.
Extension modules that need to compile against petsc4py should use this function to locate the
appropriate include directory.
Example
Using Python distutils or NumPy distutils:
import petsc4py
Extension('extension_name', ...
include_dirs=[..., petsc4py.get_include()])
Return type
str
petsc4py.init
petsc4py.init(args=None, arch=None, comm=None)
Initialize PETSc.
Parameters
• args (str | list[str] | None) -- Command-line arguments, usually the sys.argv list
• arch (str | None) -- Specific configuration to use
• comm (Intracomm | None) -- MPI commmunicator
Return type
None
Notes
This function should be called only once, typically at the very beginning of the bootstrap script
of an application.
petsc4py.typing
Typing support.
Attributes
┌────────────────────────────────┬───────────────────────────────────────┐
│ Scalar │ Scalar type. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ArrayBool │ Array of bool. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ArrayInt │ Array of int. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ArrayReal │ Array of float. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ArrayComplex │ Array of complex. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ArrayScalar │ Array of Scalar numbers. │
├────────────────────────────────┼───────────────────────────────────────┤
│ DimsSpec │ Dimensions specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ AccessModeSpec │ Access mode specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ InsertModeSpec │ Insertion mode specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ ScatterModeSpec │ Scatter mode specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ LayoutSizeSpec │ int or 2-tuple of int describing the │
│ │ layout sizes. │
├────────────────────────────────┼───────────────────────────────────────┤
│ NormTypeSpec │ Norm type specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ PetscOptionsHandlerFunction │ Callback for processing extra │
│ │ options. │
├────────────────────────────────┼───────────────────────────────────────┤
│ MatAssemblySpec │ Matrix assembly specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ MatSizeSpec │ int or (nested) tuple of int │
│ │ describing the matrix sizes. │
├────────────────────────────────┼───────────────────────────────────────┤
│ MatBlockSizeSpec │ The row and column block sizes. │
├────────────────────────────────┼───────────────────────────────────────┤
│ CSRIndicesSpec │ CSR indices format specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ CSRSpec │ CSR format specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ NNZSpec │ Nonzero pattern specification. │
├────────────────────────────────┼───────────────────────────────────────┤
│ MatNullFunction │ PETSc.NullSpace callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ DMCoarsenHookFunction │ PETSc.DM coarsening hook callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ DMRestrictHookFunction │ PETSc.DM restriction hook callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPRHSFunction │ PETSc.KSP right-hand side function │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPOperatorsFunction │ PETSc.KSP operators function │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPConvergenceTestFunction │ PETSc.KSP convergence test callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPMonitorFunction │ PETSc.KSP monitor callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPPreSolveFunction │ PETSc.KSP pre solve callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ KSPPostSolveFunction │ PETSc.KSP post solve callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESMonitorFunction │ SNES monitor callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESObjFunction │ SNES objective function callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESFunction │ SNES residual function callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESJacobianFunction │ SNES Jacobian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESGuessFunction │ SNES initial guess callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESUpdateFunction │ SNES step update callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESLSPreFunction │ SNES linesearch pre-check update │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESNGSFunction │ SNES nonlinear Gauss-Seidel callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ SNESConvergedFunction │ SNES convergence test callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSRHSFunction │ TS right-hand side function callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSRHSJacobian │ TS right-hand side Jacobian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSRHSJacobianP │ TS right-hand side parameter Jacobian │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSIFunction │ TS implicit function callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSIJacobian │ TS implicit Jacobian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSIJacobianP │ TS implicit parameter Jacobian │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSI2Function │ TS implicit 2nd order function │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSI2Jacobian │ TS implicit 2nd order Jacobian │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSI2JacobianP │ TS implicit 2nd order parameter │
│ │ Jacobian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSMonitorFunction │ TS monitor callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSPreStepFunction │ TS pre-step callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSPostStepFunction │ TS post-step callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSIndicatorFunction │ TS event indicator callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TSPostEventFunction │ TS post-event callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOObjectiveFunction │ TAO objective function callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOGradientFunction │ TAO objective gradient callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOObjectiveGradientFunction │ TAO objective function and gradient │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOHessianFunction │ TAO objective Hessian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOUpdateFunction │ TAO update callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOMonitorFunction │ TAO monitor callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOConvergedFunction │ TAO convergence test callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOJacobianFunction │ TAO Jacobian callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOResidualFunction │ TAO residual callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOJacobianResidualFunction │ TAO Jacobian residual callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOVariableBoundsFunction │ TAO variable bounds callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOConstraintsFunction │ TAO constraints callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOLSObjectiveFunction │ TAOLineSearch objective function │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOLSGradientFunction │ TAOLineSearch objective gradient │
│ │ callback. │
├────────────────────────────────┼───────────────────────────────────────┤
│ TAOLSObjectiveGradientFunction │ TAOLineSearch objective function and │
│ │ gradient callback. │
└────────────────────────────────┴───────────────────────────────────────┘
petsc4py.typing.Scalar
petsc4py.typing.Scalar = float | complex
Scalar type.
Scalars can be either float or complex (but not both) depending on how PETSc was configured
(./configure --with-scalar-type=real|complex).
petsc4py.typing.ArrayBool
petsc4py.typing.ArrayBool
Array of bool.
alias of ndarray[tuple[int, ...], dtype[bool]]
petsc4py.typing.ArrayInt
petsc4py.typing.ArrayInt
Array of int.
alias of ndarray[tuple[int, ...], dtype[int]]
petsc4py.typing.ArrayReal
petsc4py.typing.ArrayReal
Array of float.
alias of ndarray[tuple[int, ...], dtype[float]]
petsc4py.typing.ArrayComplex
petsc4py.typing.ArrayComplex
Array of complex.
alias of ndarray[tuple[int, ...], dtype[complex]]
petsc4py.typing.ArrayScalar
petsc4py.typing.ArrayScalar
Array of Scalar numbers.
alias of ndarray[tuple[int, ...], dtype[float | complex]]
petsc4py.typing.DimsSpec
petsc4py.typing.DimsSpec
Dimensions specification.
N-tuples indicates N-dimensional grid sizes.
alias of tuple[int, ...]
petsc4py.typing.AccessModeSpec
petsc4py.typing.AccessModeSpec
Access mode specification.
Possible values are:
• 'rw' Read-Write mode.
• 'r' Read-only mode.
• 'w' Write-only mode.
• None as 'rw'.
alias of Literal['rw', 'r', 'w'] | None
petsc4py.typing.InsertModeSpec
petsc4py.typing.InsertModeSpec = petsc4py.PETSc.InsertMode | bool | None
Insertion mode specification.
Possible values are:
• InsertMode.ADD_VALUES Add new value to existing one.
• InsertMode.INSERT_VALUES Replace existing entry with new value.
• None as InsertMode.INSERT_VALUES.
• False as InsertMode.INSERT_VALUES.
• True as InsertMode.ADD_VALUES.
SEE ALSO:
InsertMode
petsc4py.typing.ScatterModeSpec
petsc4py.typing.ScatterModeSpec = petsc4py.PETSc.ScatterMode | bool | str | None
Scatter mode specification.
Possible values are:
• ScatterMode.FORWARD Forward mode.
• ScatterMode.REVERSE Reverse mode.
• None as ScatterMode.FORWARD.
• False as ScatterMode.FORWARD.
• True as ScatterMode.REVERSE.
• 'forward' as ScatterMode.FORWARD.
• 'reverse' as ScatterMode.REVERSE.
SEE ALSO:
ScatterMode
petsc4py.typing.LayoutSizeSpec
petsc4py.typing.LayoutSizeSpec = int | tuple[int, int]
int or 2-tuple of int describing the layout sizes.
A single int indicates global size. A tuple of int indicates (local_size, global_size).
SEE ALSO:
Sys.splitOwnership
petsc4py.typing.NormTypeSpec
petsc4py.typing.NormTypeSpec = petsc4py.PETSc.NormType | None
Norm type specification.
Possible values include:
• NormType.NORM_1 The 1-norm: Σₙ abs(xₙ) for vectors, maxₙ (Σᵢ abs(xₙᵢ)) for matrices.
• NormType.NORM_2 The 2-norm: √(Σₙ xₙ²) for vectors, largest singular values for matrices.
• NormType.NORM_INFINITY The ∞-norm: maxₙ abs(xₙ) for vectors, maxᵢ (Σₙ abs(xₙᵢ)) for matrices.
• NormType.NORM_FROBENIUS The Frobenius norm: same as 2-norm for vectors, √(Σₙᵢ xₙᵢ²) for
matrices.
• NormType.NORM_1_AND_2 Compute both NormType.NORM_1 and NormType.NORM_2.
• None as NormType.NORM_2 for vectors, NormType.NORM_FROBENIUS for matrices.
SEE ALSO:
PETSc.NormType, NormType
petsc4py.typing.PetscOptionsHandlerFunction
petsc4py.typing.PetscOptionsHandlerFunction
Callback for processing extra options.
alias of Callable[[Object], None]
petsc4py.typing.MatAssemblySpec
petsc4py.typing.MatAssemblySpec = petsc4py.PETSc.Mat.AssemblyType | bool | None
Matrix assembly specification.
Possible values are:
• Mat.AssemblyType.FINAL
• Mat.AssemblyType.FLUSH
• None as Mat.AssemblyType.FINAL
• False as Mat.AssemblyType.FINAL
• True as Mat.AssemblyType.FLUSH
SEE ALSO:
MatAssemblyType
petsc4py.typing.MatSizeSpec
petsc4py.typing.MatSizeSpec = int | tuple[int, int] | tuple[tuple[int, int], tuple[int, int]]
int or (nested) tuple of int describing the matrix sizes.
If int then rows = columns. A single tuple of int indicates (rows, columns). A nested tuple of ‐
int indicates ((local_rows, rows), (local_columns, columns)).
SEE ALSO:
Sys.splitOwnership
petsc4py.typing.MatBlockSizeSpec
petsc4py.typing.MatBlockSizeSpec = int | tuple[int, int]
The row and column block sizes.
If a single int is provided then rows and columns share the same block size.
petsc4py.typing.CSRIndicesSpec
petsc4py.typing.CSRIndicesSpec
CSR indices format specification.
A 2-tuple carrying the (row_start, col_indices) information.
alias of tuple[Sequence[int], Sequence[int]]
petsc4py.typing.CSRSpec
petsc4py.typing.CSRSpec
CSR format specification.
A 3-tuple carrying the (row_start, col_indices, values) information.
alias of tuple[Sequence[int], Sequence[int], Sequence[float | complex]]
petsc4py.typing.NNZSpec
petsc4py.typing.NNZSpec
Nonzero pattern specification.
A single int corresponds to fixed number of non-zeros per row. A Sequence of int indicates
different non-zeros per row. If a 2-tuple is used, the elements of the tuple corresponds to the
on-process and off-process parts of the matrix.
SEE ALSO:
MatSeqAIJSetPreallocation, MatMPIAIJSetPreallocation
alias of int | Sequence[int] | tuple[Sequence[int], Sequence[int]]
petsc4py.typing.MatNullFunction
petsc4py.typing.MatNullFunction
PETSc.NullSpace callback.
alias of Callable[[NullSpace, Vec], None]
petsc4py.typing.DMCoarsenHookFunction
petsc4py.typing.DMCoarsenHookFunction
PETSc.DM coarsening hook callback.
alias of Callable[[DM, DM], None]
petsc4py.typing.DMRestrictHookFunction
petsc4py.typing.DMRestrictHookFunction
PETSc.DM restriction hook callback.
alias of Callable[[DM, Mat, Vec, Mat, DM], None]
petsc4py.typing.KSPRHSFunction
petsc4py.typing.KSPRHSFunction
PETSc.KSP right-hand side function callback.
alias of Callable[[KSP, Vec], None]
petsc4py.typing.KSPOperatorsFunction
petsc4py.typing.KSPOperatorsFunction
PETSc.KSP operators function callback.
alias of Callable[[KSP, Mat, Mat], None]
petsc4py.typing.KSPConvergenceTestFunction
petsc4py.typing.KSPConvergenceTestFunction
PETSc.KSP convergence test callback.
alias of Callable[[KSP, int, float], ConvergedReason]
petsc4py.typing.KSPMonitorFunction
petsc4py.typing.KSPMonitorFunction
PETSc.KSP monitor callback.
alias of Callable[[KSP, int, float], None]
petsc4py.typing.KSPPreSolveFunction
petsc4py.typing.KSPPreSolveFunction
PETSc.KSP pre solve callback.
alias of Callable[[KSP, Vec, Vec], None]
petsc4py.typing.KSPPostSolveFunction
petsc4py.typing.KSPPostSolveFunction
PETSc.KSP post solve callback.
alias of Callable[[KSP, Vec, Vec], None]
petsc4py.typing.SNESMonitorFunction
petsc4py.typing.SNESMonitorFunction
SNES monitor callback.
alias of Callable[[SNES, int, float], None]
petsc4py.typing.SNESObjFunction
petsc4py.typing.SNESObjFunction
SNES objective function callback.
alias of Callable[[SNES, Vec], None]
petsc4py.typing.SNESFunction
petsc4py.typing.SNESFunction
SNES residual function callback.
alias of Callable[[SNES, Vec, Vec], None]
petsc4py.typing.SNESJacobianFunction
petsc4py.typing.SNESJacobianFunction
SNES Jacobian callback.
alias of Callable[[SNES, Vec, Mat, Mat], None]
petsc4py.typing.SNESGuessFunction
petsc4py.typing.SNESGuessFunction
SNES initial guess callback.
alias of Callable[[SNES, Vec], None]
petsc4py.typing.SNESUpdateFunction
petsc4py.typing.SNESUpdateFunction
SNES step update callback.
alias of Callable[[SNES, int], None]
petsc4py.typing.SNESLSPreFunction
petsc4py.typing.SNESLSPreFunction
SNES linesearch pre-check update callback.
alias of Callable[[Vec, Vec], None]
petsc4py.typing.SNESNGSFunction
petsc4py.typing.SNESNGSFunction
SNES nonlinear Gauss-Seidel callback.
alias of Callable[[SNES, Vec, Vec], None]
petsc4py.typing.SNESConvergedFunction
petsc4py.typing.SNESConvergedFunction
SNES convergence test callback.
alias of Callable[[SNES, int, tuple[float, float, float]], ConvergedReason]
petsc4py.typing.TSRHSFunction
petsc4py.typing.TSRHSFunction
TS right-hand side function callback.
alias of Callable[[TS, float, Vec, Vec], None]
petsc4py.typing.TSRHSJacobian
petsc4py.typing.TSRHSJacobian
TS right-hand side Jacobian callback.
alias of Callable[[TS, float, Vec, Mat, Mat], None]
petsc4py.typing.TSRHSJacobianP
petsc4py.typing.TSRHSJacobianP
TS right-hand side parameter Jacobian callback.
alias of Callable[[TS, float, Vec, Mat], None]
petsc4py.typing.TSIFunction
petsc4py.typing.TSIFunction
TS implicit function callback.
alias of Callable[[TS, float, Vec, Vec, Vec], None]
petsc4py.typing.TSIJacobian
petsc4py.typing.TSIJacobian
TS implicit Jacobian callback.
alias of Callable[[TS, float, Vec, Vec, float, Mat, Mat], None]
petsc4py.typing.TSIJacobianP
petsc4py.typing.TSIJacobianP
TS implicit parameter Jacobian callback.
alias of Callable[[TS, float, Vec, Vec, float, Mat], None]
petsc4py.typing.TSI2Function
petsc4py.typing.TSI2Function
TS implicit 2nd order function callback.
alias of Callable[[TS, float, Vec, Vec, Vec, Vec], None]
petsc4py.typing.TSI2Jacobian
petsc4py.typing.TSI2Jacobian
TS implicit 2nd order Jacobian callback.
alias of Callable[[TS, float, Vec, Vec, Vec, float, float, Mat, Mat], None]
petsc4py.typing.TSI2JacobianP
petsc4py.typing.TSI2JacobianP
TS implicit 2nd order parameter Jacobian callback.
alias of Callable[[TS, float, Vec, Vec, Vec, float, float, Mat], None]
petsc4py.typing.TSMonitorFunction
petsc4py.typing.TSMonitorFunction
TS monitor callback.
alias of Callable[[TS, int, float, Vec], None]
petsc4py.typing.TSPreStepFunction
petsc4py.typing.TSPreStepFunction
TS pre-step callback.
alias of Callable[[TS], None]
petsc4py.typing.TSPostStepFunction
petsc4py.typing.TSPostStepFunction
TS post-step callback.
alias of Callable[[TS], None]
petsc4py.typing.TSIndicatorFunction
petsc4py.typing.TSIndicatorFunction
TS event indicator callback.
alias of Callable[[TS, float, Vec, ndarray[tuple[int, ...], dtype[float]]], None]
petsc4py.typing.TSPostEventFunction
petsc4py.typing.TSPostEventFunction
TS post-event callback.
alias of Callable[[TS, ndarray[tuple[int, ...], dtype[int]], float, Vec, bool], None]
petsc4py.typing.TAOObjectiveFunction
petsc4py.typing.TAOObjectiveFunction
TAO objective function callback.
alias of Callable[[TAO, Vec], float]
petsc4py.typing.TAOGradientFunction
petsc4py.typing.TAOGradientFunction
TAO objective gradient callback.
alias of Callable[[TAO, Vec, Vec], None]
petsc4py.typing.TAOObjectiveGradientFunction
petsc4py.typing.TAOObjectiveGradientFunction
TAO objective function and gradient callback.
alias of Callable[[TAO, Vec, Vec], float]
petsc4py.typing.TAOHessianFunction
petsc4py.typing.TAOHessianFunction
TAO objective Hessian callback.
alias of Callable[[TAO, Vec, Mat, Mat], None]
petsc4py.typing.TAOUpdateFunction
petsc4py.typing.TAOUpdateFunction
TAO update callback.
alias of Callable[[TAO, int], None]
petsc4py.typing.TAOMonitorFunction
petsc4py.typing.TAOMonitorFunction
TAO monitor callback.
alias of Callable[[TAO], None]
petsc4py.typing.TAOConvergedFunction
petsc4py.typing.TAOConvergedFunction
TAO convergence test callback.
alias of Callable[[TAO], None]
petsc4py.typing.TAOJacobianFunction
petsc4py.typing.TAOJacobianFunction
TAO Jacobian callback.
alias of Callable[[TAO, Vec, Mat, Mat], None]
petsc4py.typing.TAOResidualFunction
petsc4py.typing.TAOResidualFunction
TAO residual callback.
alias of Callable[[TAO, Vec, Vec], None]
petsc4py.typing.TAOJacobianResidualFunction
petsc4py.typing.TAOJacobianResidualFunction
TAO Jacobian residual callback.
alias of Callable[[TAO, Vec, Mat, Mat], None]
petsc4py.typing.TAOVariableBoundsFunction
petsc4py.typing.TAOVariableBoundsFunction
TAO variable bounds callback.
alias of Callable[[TAO, Vec, Vec], None]
petsc4py.typing.TAOConstraintsFunction
petsc4py.typing.TAOConstraintsFunction
TAO constraints callback.
alias of Callable[[TAO, Vec, Vec], None]
petsc4py.typing.TAOLSObjectiveFunction
petsc4py.typing.TAOLSObjectiveFunction
TAOLineSearch objective function callback.
alias of Callable[[TAOLineSearch, Vec], float]
petsc4py.typing.TAOLSGradientFunction
petsc4py.typing.TAOLSGradientFunction
TAOLineSearch objective gradient callback.
alias of Callable[[TAOLineSearch, Vec, Vec], None]
petsc4py.typing.TAOLSObjectiveGradientFunction
petsc4py.typing.TAOLSObjectiveGradientFunction
TAOLineSearch objective function and gradient callback.
alias of Callable[[TAOLineSearch, Vec, Vec], float]
petsc4py.PETSc
Portable, Extensible Toolkit for Scientific Computation.
Basic constants:
DECIDE Use a default value for an int or float parameter.
DEFAULT
Use a default value chosen by PETSc.
DETERMINE
Compute a default value for an int or float parameter. For tolerances this uses the default value
from when the object's type was set.
CURRENT
Do not change the current value that is set.
UNLIMITED
For a parameter that is a bound, such as the maximum number of iterations, do not bound the value.
More constants:
INFINITY
Very large real value.
NINFINITY
Very large negative real value.
PINFINITY
Very large positive real value, same as INFINITY.
Classes
┌─────────────────────┬───────────────────────────────────────┐
│ AO │ Application ordering object. │
├─────────────────────┼───────────────────────────────────────┤
│ Comm │ Communicator object. │
├─────────────────────┼───────────────────────────────────────┤
│ DM │ An object describing a computational │
│ │ grid or mesh. │
├─────────────────────┼───────────────────────────────────────┤
│ DMComposite │ A DM object that is used to manage │
│ │ data for a collection of DMs. │
├─────────────────────┼───────────────────────────────────────┤
│ DMDA │ A DM object that is used to manage │
│ │ data for a structured grid. │
├─────────────────────┼───────────────────────────────────────┤
│ DMInterpolation │ Interpolation on a mesh. │
├─────────────────────┼───────────────────────────────────────┤
│ DMLabel │ An object representing a subset of │
│ │ mesh entities from a DM. │
├─────────────────────┼───────────────────────────────────────┤
│ DMPlex │ Encapsulate an unstructured mesh. │
├─────────────────────┼───────────────────────────────────────┤
│ DMPlexTransform │ Mesh transformations. │
├─────────────────────┼───────────────────────────────────────┤
│ DMPlexTransformType │ Transformation types. │
├─────────────────────┼───────────────────────────────────────┤
│ DMShell │ A shell DM object, used to manage │
│ │ user-defined problem data. │
├─────────────────────┼───────────────────────────────────────┤
│ DMStag │ A DM object representing a "staggered │
│ │ grid" or a structured cell complex. │
├─────────────────────┼───────────────────────────────────────┤
│ DMSwarm │ A DM object used to represent arrays │
│ │ of data (fields) of arbitrary type. │
├─────────────────────┼───────────────────────────────────────┤
│ DS │ Discrete System object. │
├─────────────────────┼───────────────────────────────────────┤
│ Device │ The device object. │
├─────────────────────┼───────────────────────────────────────┤
│ DeviceContext │ DeviceContext object. │
├─────────────────────┼───────────────────────────────────────┤
│ DualSpace │ Dual space to a linear space. │
├─────────────────────┼───────────────────────────────────────┤
│ FE │ A PETSc object that manages a finite │
│ │ element space. │
├─────────────────────┼───────────────────────────────────────┤
│ IS │ A collection of indices. │
├─────────────────────┼───────────────────────────────────────┤
│ InsertMode │ Insertion mode. │
├─────────────────────┼───────────────────────────────────────┤
│ KSP │ Abstract PETSc object that manages │
│ │ all Krylov methods. │
├─────────────────────┼───────────────────────────────────────┤
│ LGMap │ Mapping from a local to a global │
│ │ ordering. │
├─────────────────────┼───────────────────────────────────────┤
│ Log │ Logging support. │
├─────────────────────┼───────────────────────────────────────┤
│ LogClass │ Logging support. │
├─────────────────────┼───────────────────────────────────────┤
│ LogEvent │ Logging support. │
├─────────────────────┼───────────────────────────────────────┤
│ LogStage │ Logging support for different stages. │
├─────────────────────┼───────────────────────────────────────┤
│ Mat │ Matrix object. │
├─────────────────────┼───────────────────────────────────────┤
│ MatPartitioning │ Object for managing the partitioning │
│ │ of a matrix or graph. │
├─────────────────────┼───────────────────────────────────────┤
│ NormType │ Norm type. │
├─────────────────────┼───────────────────────────────────────┤
│ NullSpace │ Nullspace object. │
├─────────────────────┼───────────────────────────────────────┤
│ Object │ Base class wrapping a PETSc object. │
├─────────────────────┼───────────────────────────────────────┤
│ Options │ The options database object. │
├─────────────────────┼───────────────────────────────────────┤
│ PC │ Preconditioners. │
├─────────────────────┼───────────────────────────────────────┤
│ Partitioner │ A graph partitioner. │
├─────────────────────┼───────────────────────────────────────┤
│ Quad │ Quadrature rule for integration. │
├─────────────────────┼───────────────────────────────────────┤
│ Random │ The random number generator object. │
├─────────────────────┼───────────────────────────────────────┤
│ SF │ Star Forest object for communication. │
├─────────────────────┼───────────────────────────────────────┤
│ SNES │ Nonlinear equations solver. │
├─────────────────────┼───────────────────────────────────────┤
│ Scatter │ Scatter object. │
├─────────────────────┼───────────────────────────────────────┤
│ ScatterMode │ Scatter mode. │
├─────────────────────┼───────────────────────────────────────┤
│ Section │ Mapping from integers in a range to │
│ │ unstructured set of integers. │
├─────────────────────┼───────────────────────────────────────┤
│ Space │ Function space object. │
├─────────────────────┼───────────────────────────────────────┤
│ Sys │ System utilities. │
├─────────────────────┼───────────────────────────────────────┤
│ TAO │ Optimization solver. │
├─────────────────────┼───────────────────────────────────────┤
│ TAOLineSearch │ TAO Line Search. │
├─────────────────────┼───────────────────────────────────────┤
│ TS │ ODE integrator. │
├─────────────────────┼───────────────────────────────────────┤
│ Vec │ A vector object. │
├─────────────────────┼───────────────────────────────────────┤
│ Viewer │ Viewer object. │
├─────────────────────┼───────────────────────────────────────┤
│ ViewerHDF5 │ Viewer object for HDF5 file formats. │
└─────────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.AO
class petsc4py.PETSc.AO
Bases: Object
Application ordering object.
Enumerations
┌──────┬─────────────────────────────────┐
│ Type │ The application ordering types. │
└──────┴─────────────────────────────────┘
petsc4py.PETSc.AO.Type
class petsc4py.PETSc.AO.Type
Bases: object
The application ordering types.
Attributes Summary
┌────────────────┬───────────────────────────────────┐
│ ADVANCED │ Object ADVANCED of type str │
├────────────────┼───────────────────────────────────┤
│ BASIC │ Object BASIC of type str │
├────────────────┼───────────────────────────────────┤
│ MAPPING │ Object MAPPING of type str │
├────────────────┼───────────────────────────────────┤
│ MEMORYSCALABLE │ Object MEMORYSCALABLE of type str │
└────────────────┴───────────────────────────────────┘
Attributes Documentation
ADVANCED: str = ADVANCED
Object ADVANCED of type str
BASIC: str = BASIC
Object BASIC of type str
MAPPING: str = MAPPING
Object MAPPING of type str
MEMORYSCALABLE: str = MEMORYSCALABLE
Object MEMORYSCALABLE of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ app2petsc(indices) │ Map an application-defined ordering │
│ │ to the PETSc ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createBasic(app[, petsc, comm]) │ Return a basic application ordering │
│ │ using two orderings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMapping(app[, petsc, comm]) │ Return an application mapping using │
│ │ two orderings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMemoryScalable(app[, petsc, │ Return a memory scalable application │
│ comm]) │ ordering using two orderings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the application ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the application ordering type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ petsc2app(indices) │ Map a PETSc ordering to the │
│ │ application-defined ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Display the application ordering. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
app2petsc(indices)
Map an application-defined ordering to the PETSc ordering.
Collective.
Any integers in indices that are negative are left unchanged. This allows one to convert,
for example, neighbor lists that use negative entries to indicate nonexistent neighbors due
to boundary conditions, etc.
Integers that are out of range are mapped to -1.
If IS is used, it cannot be of type stride or block.
Parameters
indices (Sequence[int] | IS) -- The indices; to be replaced with their mapped
values.
Return type
Sequence[int] | IS
SEE ALSO:
petsc2app, AOApplicationToPetscIS, AOApplicationToPetsc
Source code at petsc4py/PETSc/AO.pyx:214
createBasic(app, petsc=None, comm=None)
Return a basic application ordering using two orderings.
Collective.
The arrays/indices app and petsc must contain all the integers 0 to len(app)-1 with no
duplicates; that is there cannot be any "holes" in the indices. Use createMapping if you
wish to have "holes" in the indices.
Parameters
• app (Sequence[int] | IS) -- The application ordering.
• petsc (Sequence[int] | IS | None) -- Another ordering (may be None to indicate the
natural ordering, that is 0, 1, 2, 3, ...).
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createMemoryScalable, createMapping, AOCreateBasicIS, AOCreateBasic
Source code at petsc4py/PETSc/AO.pyx:53
createMapping(app, petsc=None, comm=None)
Return an application mapping using two orderings.
Collective.
The arrays app and petsc need NOT contain all the integers 0 to len(app)-1, that is there
CAN be "holes" in the indices. Use createBasic if they do not have holes for better
performance.
Parameters
• app (Sequence[int] | IS) -- The application ordering.
• petsc (Sequence[int] | IS | None) -- Another ordering. May be None to indicate the
identity ordering.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createBasic, AOCreateMappingIS, AOCreateMapping
Source code at petsc4py/PETSc/AO.pyx:154
createMemoryScalable(app, petsc=None, comm=None)
Return a memory scalable application ordering using two orderings.
Collective.
The arrays/indices app and petsc must contain all the integers 0 to len(app)-1 with no
duplicates; that is there cannot be any "holes" in the indices. Use createMapping if you
wish to have "holes" in the indices.
Comparing with createBasic, this routine trades memory with message communication.
Parameters
• app (Sequence[int] | IS) -- The application ordering.
• petsc (Sequence[int] | IS | None) -- Another ordering (may be None to indicate the
natural ordering, that is 0, 1, 2, 3, ...).
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createBasic, createMapping, AOCreateMemoryScalableIS, AOCreateMemoryScalable
Source code at petsc4py/PETSc/AO.pyx:102
destroy()
Destroy the application ordering.
Collective.
SEE ALSO:
AODestroy
Source code at petsc4py/PETSc/AO.pyx:40
Return type
Self
getType()
Return the application ordering type.
Not collective.
SEE ALSO:
AOGetType
Source code at petsc4py/PETSc/AO.pyx:200
Return type
str
petsc2app(indices)
Map a PETSc ordering to the application-defined ordering.
Collective.
Any integers in indices that are negative are left unchanged. This allows one to convert,
for example, neighbor lists that use negative entries to indicate nonexistent neighbors due
to boundary conditions, etc.
Integers that are out of range are mapped to -1.
If IS is used, it cannot be of type stride or block.
Parameters
indices (Sequence[int] | IS) -- The indices; to be replaced with their mapped
values.
Return type
Sequence[int] | IS
SEE ALSO:
app2petsc, AOPetscToApplicationIS, AOPetscToApplication
Source code at petsc4py/PETSc/AO.pyx:248
view(viewer=None)
Display the application ordering.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the ordering.
Return type
None
SEE ALSO:
AOView
Source code at petsc4py/PETSc/AO.pyx:21
petsc4py.PETSc.Comm
class petsc4py.PETSc.Comm
Bases: object
Communicator object.
Predefined instances:
COMM_NULL
The null (or invalid) communicator.
COMM_SELF
The self communicator.
COMM_WORLD
The world communicator.
SEE ALSO:
Sys.setDefaultComm, Sys.getDefaultComm
Methods Summary
┌─────────────┬───────────────────────────────────────┐
│ barrier() │ Barrier synchronization. │
├─────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the communicator. │
├─────────────┼───────────────────────────────────────┤
│ duplicate() │ Duplicate the communicator. │
├─────────────┼───────────────────────────────────────┤
│ getRank() │ Return the rank of the calling │
│ │ processes in the communicator. │
├─────────────┼───────────────────────────────────────┤
│ getSize() │ Return the number of processes in the │
│ │ communicator. │
├─────────────┼───────────────────────────────────────┤
│ tompi4py() │ Convert communicator to mpi4py. │
└─────────────┴───────────────────────────────────────┘
Attributes Summary
┌─────────┬────────────────────┐
│ fortran │ Fortran handle. │
├─────────┼────────────────────┤
│ rank │ Communicator rank. │
├─────────┼────────────────────┤
│ size │ Communicator size. │
└─────────┴────────────────────┘
Methods Documentation
barrier()
Barrier synchronization.
Collective.
Source code at petsc4py/PETSc/Comm.pyx:123
Return type
None
destroy()
Destroy the communicator.
Collective.
SEE ALSO:
PetscCommDestroy
Source code at petsc4py/PETSc/Comm.pyx:61
Return type
None
duplicate()
Duplicate the communicator.
Collective.
SEE ALSO:
PetscCommDuplicate
Source code at petsc4py/PETSc/Comm.pyx:79
Return type
Self
getRank()
Return the rank of the calling processes in the communicator.
Not collective.
Source code at petsc4py/PETSc/Comm.pyx:111
Return type
int
getSize()
Return the number of processes in the communicator.
Not collective.
Source code at petsc4py/PETSc/Comm.pyx:99
Return type
int
tompi4py()
Convert communicator to mpi4py.
Not collective.
SEE ALSO:
mpi4py.MPI.Comm, mpi4py.MPI.Intracomm
Source code at petsc4py/PETSc/Comm.pyx:155
Return type
Intracomm
Attributes Documentation
fortran
Fortran handle.
Source code at petsc4py/PETSc/Comm.pyx:147
rank Communicator rank.
Source code at petsc4py/PETSc/Comm.pyx:140
size Communicator size.
Source code at petsc4py/PETSc/Comm.pyx:135
petsc4py.PETSc.DM
class petsc4py.PETSc.DM
Bases: Object
An object describing a computational grid or mesh.
Enumerations
┌────────────────────┬──────────────────────────────────┐
│ BoundaryType │ DM Boundary types. │
├────────────────────┼──────────────────────────────────┤
│ PolytopeType │ The DM cell types. │
├────────────────────┼──────────────────────────────────┤
│ ReorderDefaultFlag │ The DM reordering default flags. │
├────────────────────┼──────────────────────────────────┤
│ Type │ DM types. │
└────────────────────┴──────────────────────────────────┘
petsc4py.PETSc.DM.BoundaryType
class petsc4py.PETSc.DM.BoundaryType
Bases: object
DM Boundary types.
Attributes Summary
┌──────────┬───────────────────────────────┐
│ GHOSTED │ Constant GHOSTED of type int │
├──────────┼───────────────────────────────┤
│ MIRROR │ Constant MIRROR of type int │
├──────────┼───────────────────────────────┤
│ NONE │ Constant NONE of type int │
├──────────┼───────────────────────────────┤
│ PERIODIC │ Constant PERIODIC of type int │
├──────────┼───────────────────────────────┤
│ TWIST │ Constant TWIST of type int │
└──────────┴───────────────────────────────┘
Attributes Documentation
GHOSTED: int = GHOSTED
Constant GHOSTED of type int
MIRROR: int = MIRROR
Constant MIRROR of type int
NONE: int = NONE
Constant NONE of type int
PERIODIC: int = PERIODIC
Constant PERIODIC of type int
TWIST: int = TWIST
Constant TWIST of type int
petsc4py.PETSc.DM.PolytopeType
class petsc4py.PETSc.DM.PolytopeType
Bases: object
The DM cell types.
Attributes Summary
┌────────────────────┬───────────────────────────────────────┐
│ FV_GHOST │ Constant FV_GHOST of type int │
├────────────────────┼───────────────────────────────────────┤
│ HEXAHEDRON │ Constant HEXAHEDRON of type int │
├────────────────────┼───────────────────────────────────────┤
│ INTERIOR_GHOST │ Constant INTERIOR_GHOST of type int │
├────────────────────┼───────────────────────────────────────┤
│ POINT │ Constant POINT of type int │
├────────────────────┼───────────────────────────────────────┤
│ POINT_PRISM_TENSOR │ Constant POINT_PRISM_TENSOR of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ PYRAMID │ Constant PYRAMID of type int │
├────────────────────┼───────────────────────────────────────┤
│ QUADRILATERAL │ Constant QUADRILATERAL of type int │
├────────────────────┼───────────────────────────────────────┤
│ QUAD_PRISM_TENSOR │ Constant QUAD_PRISM_TENSOR of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ SEGMENT │ Constant SEGMENT of type int │
├────────────────────┼───────────────────────────────────────┤
│ SEG_PRISM_TENSOR │ Constant SEG_PRISM_TENSOR of type int │
├────────────────────┼───────────────────────────────────────┤
│ TETRAHEDRON │ Constant TETRAHEDRON of type int │
├────────────────────┼───────────────────────────────────────┤
│ TRIANGLE │ Constant TRIANGLE of type int │
├────────────────────┼───────────────────────────────────────┤
│ TRI_PRISM │ Constant TRI_PRISM of type int │
├────────────────────┼───────────────────────────────────────┤
│ TRI_PRISM_TENSOR │ Constant TRI_PRISM_TENSOR of type int │
├────────────────────┼───────────────────────────────────────┤
│ UNKNOWN │ Constant UNKNOWN of type int │
├────────────────────┼───────────────────────────────────────┤
│ UNKNOWN_CELL │ Constant UNKNOWN_CELL of type int │
├────────────────────┼───────────────────────────────────────┤
│ UNKNOWN_FACE │ Constant UNKNOWN_FACE of type int │
└────────────────────┴───────────────────────────────────────┘
Attributes Documentation
FV_GHOST: int = FV_GHOST
Constant FV_GHOST of type int
HEXAHEDRON: int = HEXAHEDRON
Constant HEXAHEDRON of type int
INTERIOR_GHOST: int = INTERIOR_GHOST
Constant INTERIOR_GHOST of type int
POINT: int = POINT
Constant POINT of type int
POINT_PRISM_TENSOR: int = POINT_PRISM_TENSOR
Constant POINT_PRISM_TENSOR of type int
PYRAMID: int = PYRAMID
Constant PYRAMID of type int
QUADRILATERAL: int = QUADRILATERAL
Constant QUADRILATERAL of type int
QUAD_PRISM_TENSOR: int = QUAD_PRISM_TENSOR
Constant QUAD_PRISM_TENSOR of type int
SEGMENT: int = SEGMENT
Constant SEGMENT of type int
SEG_PRISM_TENSOR: int = SEG_PRISM_TENSOR
Constant SEG_PRISM_TENSOR of type int
TETRAHEDRON: int = TETRAHEDRON
Constant TETRAHEDRON of type int
TRIANGLE: int = TRIANGLE
Constant TRIANGLE of type int
TRI_PRISM: int = TRI_PRISM
Constant TRI_PRISM of type int
TRI_PRISM_TENSOR: int = TRI_PRISM_TENSOR
Constant TRI_PRISM_TENSOR of type int
UNKNOWN: int = UNKNOWN
Constant UNKNOWN of type int
UNKNOWN_CELL: int = UNKNOWN_CELL
Constant UNKNOWN_CELL of type int
UNKNOWN_FACE: int = UNKNOWN_FACE
Constant UNKNOWN_FACE of type int
petsc4py.PETSc.DM.ReorderDefaultFlag
class petsc4py.PETSc.DM.ReorderDefaultFlag
Bases: object
The DM reordering default flags.
Attributes Summary
┌────────┬─────────────────────────────┐
│ FALSE │ Constant FALSE of type int │
├────────┼─────────────────────────────┤
│ NOTSET │ Constant NOTSET of type int │
├────────┼─────────────────────────────┤
│ TRUE │ Constant TRUE of type int │
└────────┴─────────────────────────────┘
Attributes Documentation
FALSE: int = FALSE
Constant FALSE of type int
NOTSET: int = NOTSET
Constant NOTSET of type int
TRUE: int = TRUE
Constant TRUE of type int
petsc4py.PETSc.DM.Type
class petsc4py.PETSc.DM.Type
Bases: object
DM types.
Attributes Summary
┌───────────┬──────────────────────────────┐
│ COMPOSITE │ Object COMPOSITE of type str │
├───────────┼──────────────────────────────┤
│ DA │ Object DA of type str │
├───────────┼──────────────────────────────┤
│ FOREST │ Object FOREST of type str │
├───────────┼──────────────────────────────┤
│ MOAB │ Object MOAB of type str │
├───────────┼──────────────────────────────┤
│ NETWORK │ Object NETWORK of type str │
├───────────┼──────────────────────────────┤
│ P4EST │ Object P4EST of type str │
├───────────┼──────────────────────────────┤
│ P8EST │ Object P8EST of type str │
├───────────┼──────────────────────────────┤
│ PATCH │ Object PATCH of type str │
├───────────┼──────────────────────────────┤
│ PLEX │ Object PLEX of type str │
├───────────┼──────────────────────────────┤
│ PRODUCT │ Object PRODUCT of type str │
├───────────┼──────────────────────────────┤
│ REDUNDANT │ Object REDUNDANT of type str │
├───────────┼──────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├───────────┼──────────────────────────────┤
│ SLICED │ Object SLICED of type str │
├───────────┼──────────────────────────────┤
│ STAG │ Object STAG of type str │
├───────────┼──────────────────────────────┤
│ SWARM │ Object SWARM of type str │
└───────────┴──────────────────────────────┘
Attributes Documentation
COMPOSITE: str = COMPOSITE
Object COMPOSITE of type str
DA: str = DA
Object DA of type str
FOREST: str = FOREST
Object FOREST of type str
MOAB: str = MOAB
Object MOAB of type str
NETWORK: str = NETWORK
Object NETWORK of type str
P4EST: str = P4EST
Object P4EST of type str
P8EST: str = P8EST
Object P8EST of type str
PATCH: str = PATCH
Object PATCH of type str
PLEX: str = PLEX
Object PLEX of type str
PRODUCT: str = PRODUCT
Object PRODUCT of type str
REDUNDANT: str = REDUNDANT
Object REDUNDANT of type str
SHELL: str = SHELL
Object SHELL of type str
SLICED: str = SLICED
Object SLICED of type str
STAG: str = STAG
Object STAG of type str
SWARM: str = SWARM
Object SWARM of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ adaptLabel(label) │ Adapt a DM based on a DMLabel. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ adaptMetric(metric[, bdLabel, │ Return a mesh adapted to the │
│ rgLabel]) │ specified metric field. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addCoarsenHook(coarsenhook, │ Add a callback to be executed when │
│ restricthook[, ...]) │ restricting to a coarser grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addField(field[, label]) │ Add a field to a DM object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix(prefix) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearDS() │ Remove all discrete systems from the │
│ │ DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearFields() │ Remove all fields from the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearLabelStratum(name, value) │ Remove all points from a stratum. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearLabelValue(name, point, value) │ Remove a point from a DMLabel with │
│ │ given value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clone() │ Return the cloned DM . │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ coarsen([comm]) │ Return a coarsened DM object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ coarsenHierarchy(nlevels) │ Coarsen this DM and return the │
│ │ coarsened DM hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ convert(dm_type) │ Return a DM converted to another DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copyDS(dm[, minDegree, maxDegree]) │ Copy the discrete systems for this DM │
│ │ into another DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copyDisc(dm) │ Copy fields and discrete systems of a │
│ │ DM into another DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copyFields(dm[, minDegree, │ Copy the discretizations of this DM │
│ maxDegree]) │ into another DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Return an empty DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDS() │ Create discrete systems. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createFieldDecomposition() │ Return a list of IS objects. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createGlobalVec() │ Return a global vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createInjection(dm) │ Return the injection matrix into a │
│ │ finer DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createInterpolation(dm) │ Return the interpolation matrix to a │
│ │ finer DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createLabel(name) │ Create a label of the given name if │
│ │ it does not already exist. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createLocalVec() │ Return a local vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMassMatrix(dmf) │ Return the mass matrix between this │
│ │ DM and the given DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMat() │ Return an empty matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createRestriction(dm) │ Return the restriction matrix between │
│ │ this DM and the given DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSectionSF(localsec, globalsec) │ Create the SF encoding the parallel │
│ │ DOF overlap for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSubDM(fields) │ Return IS and DM encapsulating a │
│ │ subproblem. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAppCtx() │ Return the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAuxiliaryVec([label, value, part]) │ Return an auxiliary vector for │
│ │ region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBasicAdjacency() │ Return the flags for determining │
│ │ variable influence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSize() │ Return the inherent block size │
│ │ associated with a DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBoundingBox() │ Return the dimension of embedding │
│ │ space for coordinates values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCellCoordinateDM() │ Return the cell coordinate DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCellCoordinateSection() │ Return the cell coordinate layout │
│ │ over the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCellCoordinates() │ Return a global vector with the │
│ │ cellwise coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCellCoordinatesLocal() │ Return a local vector with the │
│ │ cellwise coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoarseDM() │ Return the coarse DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoarsenLevel() │ Return the number of coarsenings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinateDM() │ Return the coordinate DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinateDim() │ Return the dimension of embedding │
│ │ space for coordinates values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinateSection() │ Return coordinate values layout over │
│ │ the mesh. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinates() │ Return a global vector with the │
│ │ coordinates associated. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinatesLocal() │ Return a local vector with the │
│ │ coordinates associated. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinatesLocalized() │ Check if the coordinates have been │
│ │ localized for cells. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDS() │ Return default DS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDimension() │ Return the topological dimension of │
│ │ the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getField(index) │ Return the discretization object for │
│ │ a given DM field. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldAdjacency(field) │ Return the flags for determining │
│ │ variable influence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGlobalSection() │ Return the Section encoding the │
│ │ global data layout for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGlobalVec([name]) │ Return a global vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLGMap() │ Return local mapping to global │
│ │ mapping. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabel(name) │ Return the label of a given name. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabelIdIS(name) │ Return an IS of all values that the │
│ │ DMLabel takes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabelName(index) │ Return the name of nth label. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabelOutput(name) │ Return the output flag for a given │
│ │ label. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabelSize(name) │ Return the number of values that the │
│ │ DMLabel takes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLabelValue(name, point) │ Return the value in DMLabel for the │
│ │ given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalBoundingBox() │ Return the bounding box for the piece │
│ │ of the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSection() │ Return the Section encoding the local │
│ │ data layout for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalVec([name]) │ Return a local vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumFields() │ Return the number of fields in the │
│ │ DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumLabels() │ Return the number of labels defined │
│ │ by on the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPointSF() │ Return the SF encoding the parallel │
│ │ DOF overlap for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRefineLevel() │ Return the refinement level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSectionSF() │ Return the Section encoding the │
│ │ parallel DOF overlap. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStratumIS(name, value) │ Return the points in a label stratum. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStratumSize(name, value) │ Return the number of points in a │
│ │ label stratum. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the DM type name. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ globalToLocal(vg, vl[, addv]) │ Update local vectors from global │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ hasLabel(name) │ Determine whether the DM has a label. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ load(viewer) │ Return a DM stored in binary. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ localToGlobal(vl, vg[, addv]) │ Update global vectors from local │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ localToLocal(vl, vlg[, addv]) │ Map the values from a local vector to │
│ │ another local vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ localizeCoordinates() │ Create local coordinates for cells │
│ │ having periodic faces. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ refine([comm]) │ Return a refined DM object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ refineHierarchy(nlevels) │ Refine this DM and return the refined │
│ │ DM hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ removeLabel(name) │ Remove and destroy the label by name. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreGlobalVec(vg[, name]) │ Restore a global vector obtained with │
│ │ getGlobalVec. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreLocalVec(vl[, name]) │ Restore a local vector obtained with │
│ │ getLocalVec. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAppCtx(appctx) │ Set the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAuxiliaryVec(aux, label[, value, │ Set an auxiliary vector for a │
│ part]) │ specific region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBasicAdjacency(useCone, │ Set the flags for determining │
│ useClosure) │ variable influence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCellCoordinateDM(dm) │ Set the cell coordinate DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCellCoordinateSection(dim, sec) │ Set the cell coordinate layout over │
│ │ the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCellCoordinates(c) │ Set a global vector with the cellwise │
│ │ coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCellCoordinatesLocal(c) │ Set a local vector with the cellwise │
│ │ coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoarseDM(dm) │ Set the coarse DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinateDim(dim) │ Set the dimension of embedding space │
│ │ for coordinates values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinateDisc(disc, project) │ Project coordinates to a different │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinates(c) │ Set a global vector that holds the │
│ │ coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinatesLocal(c) │ Set a local vector with the ghost │
│ │ point holding the coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDimension(dim) │ Set the topological dimension of the │
│ │ DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setField(index, field[, label]) │ Set the discretization object for a │
│ │ given DM field. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldAdjacency(field, useCone, │ Set the flags for determining │
│ useClosure) │ variable influence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the object from the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setGlobalSection(sec) │ Set the Section encoding the global │
│ │ data layout for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setKSPComputeOperators(operators[, │ Matrix associated with the linear │
│ args, kargs]) │ system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLabelOutput(name, output) │ Set if a given label should be saved │
│ │ to a view. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLabelValue(name, point, value) │ Set a point to a DMLabel with a given │
│ │ value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalSection(sec) │ Set the Section encoding the local │
│ │ data layout for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMatType(mat_type) │ Set matrix type to be used by │
│ │ DM.createMat. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNumFields(numFields) │ Set the number of fields in the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for searching for │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPointSF(sf) │ Set the SF encoding the parallel DOF │
│ │ overlap for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRefineLevel(level) │ Set the number of refinements. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSNESFunction(function[, args, │ Set SNES residual evaluation │
│ kargs]) │ function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSNESJacobian(jacobian[, args, │ Set the SNES Jacobian evaluation │
│ kargs]) │ function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSectionSF(sf) │ Set the Section encoding the parallel │
│ │ DOF overlap for the DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(dm_type) │ Build a DM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Return the data structure. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setVecType(vec_type) │ Set the type of vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the DM. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌────────┬──────────────────────┐
│ appctx │ Application context. │
├────────┼──────────────────────┤
│ ds │ Discrete space. │
└────────┴──────────────────────┘
Methods Documentation
adaptLabel(label)
Adapt a DM based on a DMLabel.
Collective.
Parameters
label (str) -- The name of the DMLabel.
Return type
DM
SEE ALSO:
DMAdaptLabel
Source code at petsc4py/PETSc/DM.pyx:1645
adaptMetric(metric, bdLabel=None, rgLabel=None)
Return a mesh adapted to the specified metric field.
Collective.
Parameters
• metric (Vec) -- The metric to which the mesh is adapted, defined vertex-wise.
• bdLabel (str | None) -- Label for boundary tags.
• rgLabel (str | None) -- Label for cell tag.
Return type
DM
SEE ALSO:
DMAdaptMetric
Source code at petsc4py/PETSc/DM.pyx:1668
addCoarsenHook(coarsenhook, restricthook, args=None, kargs=None)
Add a callback to be executed when restricting to a coarser grid.
Logically collective.
Parameters
• coarsenhook (DMCoarsenHookFunction) -- The coarsen hook function.
• restricthook (DMRestrictHookFunction) -- The restrict hook function.
• args (tuple[Any, ...] | None) -- Positional arguments for the hooks.
• kargs (dict[str, Any] | None) -- Keyword arguments for the hooks.
Return type
None
SEE ALSO:
DMCoarsenHookAdd
Source code at petsc4py/PETSc/DM.pyx:2333
addField(field, label=None)
Add a field to a DM object.
Logically collective.
Parameters
• field (Object) -- The discretization object.
• label (str | None) -- The name of the label indicating the support of the field,
or None for the entire mesh.
Return type
None
SEE ALSO:
DMAddField
Source code at petsc4py/PETSc/DM.pyx:611
appendOptionsPrefix(prefix)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, DMAppendOptionsPrefix
Source code at petsc4py/PETSc/DM.pyx:298
Parameters
prefix (str | None)
Return type
None
clearDS()
Remove all discrete systems from the DM.
Logically collective.
SEE ALSO:
DMClearDS
Source code at petsc4py/PETSc/DM.pyx:691
Return type
None
clearFields()
Remove all fields from the DM.
Logically collective.
SEE ALSO:
DMClearFields
Source code at petsc4py/PETSc/DM.pyx:634
Return type
None
clearLabelStratum(name, value)
Remove all points from a stratum.
Not collective.
Parameters
• name (str) -- The label name.
• value (int) -- The stratum value.
Return type
None
SEE ALSO:
DMClearLabelStratum
Source code at petsc4py/PETSc/DM.pyx:2124
clearLabelValue(name, point, value)
Remove a point from a DMLabel with given value.
Not collective.
Parameters
• name (str) -- The label name.
• point (int) -- The mesh point.
• value (int) -- The label value for the point.
Return type
None
SEE ALSO:
DMClearLabelValue
Source code at petsc4py/PETSc/DM.pyx:2010
clone()
Return the cloned DM .
Collective.
SEE ALSO:
DMClone
Source code at petsc4py/PETSc/DM.pyx:155
Return type
DM
coarsen(comm=None)
Return a coarsened DM object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
DM
SEE ALSO:
DMCoarsen
Source code at petsc4py/PETSc/DM.pyx:1519
coarsenHierarchy(nlevels)
Coarsen this DM and return the coarsened DM hierarchy.
Collective.
Parameters
nlevels (int) -- The number of levels of coarsening.
Return type
list
SEE ALSO:
DMCoarsenHierarchy
Source code at petsc4py/PETSc/DM.pyx:1570
convert(dm_type)
Return a DM converted to another DM.
Collective.
Parameters
dm_type (Type | str) -- The new DM.Type, use “same” for the same type.
Return type
DM
SEE ALSO:
DM.Type, DMConvert
Source code at petsc4py/PETSc/DM.pyx:1472
copyDS(dm, minDegree=None, maxDegree=None)
Copy the discrete systems for this DM into another DM.
Collective.
Parameters
• dm (DM) -- The DM that the discrete fields are copied into.
• minDegree -- The minimum polynommial degree for the discretization, or None for no
limit
• maxDegree -- The maximum polynommial degree for the discretization, or None for no
limit
Return type
None
SEE ALSO:
DMCopyDS
Source code at petsc4py/PETSc/DM.pyx:718
copyDisc(dm)
Copy fields and discrete systems of a DM into another DM.
Collective.
Parameters
dm (DM) -- The DM that the fields and discrete systems are copied into.
Return type
None
SEE ALSO:
DMCopyDisc
Source code at petsc4py/PETSc/DM.pyx:751
copyFields(dm, minDegree=None, maxDegree=None)
Copy the discretizations of this DM into another DM.
Collective.
Parameters
• dm (DM) -- The DM that the fields are copied into.
• minDegree -- The minimum polynommial degree for the discretization, or None for no
limit
• maxDegree -- The maximum polynommial degree for the discretization, or None for no
limit
Return type
None
SEE ALSO:
DMCopyFields
Source code at petsc4py/PETSc/DM.pyx:646
create(comm=None)
Return an empty DM.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DMCreate
Source code at petsc4py/PETSc/DM.pyx:134
createDS()
Create discrete systems.
Collective.
SEE ALSO:
DMCreateDS
Source code at petsc4py/PETSc/DM.pyx:679
Return type
None
createFieldDecomposition()
Return a list of IS objects.
Not collective.
Notes
The user is responsible for freeing all requested arrays.
SEE ALSO:
DMCreateFieldDecomposition
Source code at petsc4py/PETSc/DM.pyx:2222
Return type
tuple[list, list, list]
createGlobalVec()
Return a global vector.
Collective.
SEE ALSO:
DMCreateGlobalVector
Source code at petsc4py/PETSc/DM.pyx:798
Return type
Vec
createInjection(dm)
Return the injection matrix into a finer DM.
Collective.
Parameters
dm (DM) -- The second, finer DM object.
Return type
Mat
SEE ALSO:
DMCreateInjection
Source code at petsc4py/PETSc/DM.pyx:1434
createInterpolation(dm)
Return the interpolation matrix to a finer DM.
Collective.
Parameters
dm (DM) -- The second, finer DM.
Return type
tuple[Mat, Vec]
SEE ALSO:
DMCreateInterpolation
Source code at petsc4py/PETSc/DM.pyx:1413
createLabel(name)
Create a label of the given name if it does not already exist.
Not collective.
Parameters
name (str) -- The label name.
Return type
None
SEE ALSO:
DMCreateLabel
Source code at petsc4py/PETSc/DM.pyx:1922
createLocalVec()
Return a local vector.
Not collective.
SEE ALSO:
DMCreateLocalVector
Source code at petsc4py/PETSc/DM.pyx:812
Return type
Vec
createMassMatrix(dmf)
Return the mass matrix between this DM and the given DM.
Collective.
Parameters
dmf (DM) -- The second DM.
Return type
Mat
SEE ALSO:
DMCreateMassMatrix
Source code at petsc4py/PETSc/DM.pyx:1394
createMat()
Return an empty matrix.
Collective.
SEE ALSO:
DMCreateMatrix
Source code at petsc4py/PETSc/DM.pyx:1380
Return type
Mat
createRestriction(dm)
Return the restriction matrix between this DM and the given DM.
Collective.
Parameters
dm (DM) -- The second, finer DM object.
Return type
Mat
SEE ALSO:
DMCreateRestriction
Source code at petsc4py/PETSc/DM.pyx:1453
createSectionSF(localsec, globalsec)
Create the SF encoding the parallel DOF overlap for the DM.
Collective.
Parameters
• localsec (Section) -- Describe the local data layout.
• globalsec (Section) -- Describe the global data layout.
Return type
None
Notes
Encoding based on the Section describing the data layout.
SEE ALSO:
DM.getSectionSF, DMCreateSectionSF
Source code at petsc4py/PETSc/DM.pyx:1786
createSubDM(fields)
Return IS and DM encapsulating a subproblem.
Not collective.
Returns
• iset (IS) -- The global indices for all the degrees of freedom.
• subdm (DM) -- The DM for the subproblem.
Parameters
fields (Sequence[int])
Return type
tuple[IS, DM]
SEE ALSO:
DMCreateSubDM
Source code at petsc4py/PETSc/DM.pyx:446
destroy()
Destroy the object.
Collective.
SEE ALSO:
DMDestroy
Source code at petsc4py/PETSc/DM.pyx:121
Return type
Self
getAppCtx()
Return the application context.
Source code at petsc4py/PETSc/DM.pyx:343
Return type
Any
getAuxiliaryVec(label=None, value=0, part=0)
Return an auxiliary vector for region.
Not collective.
Parameters
• label (str | None) -- The name of the DMLabel.
• value (int | None) -- Indicate the region.
• part (int | None) -- The equation part, or 0 is unused.
Return type
Vec
SEE ALSO:
DM.getLabel, DMGetAuxiliaryVec
Source code at petsc4py/PETSc/DM.pyx:503
getBasicAdjacency()
Return the flags for determining variable influence.
Not collective.
Returns
• useCone (bool) -- Whether adjacency uses cone information.
• useClosure (bool) -- Whether adjacency is computed using full closure information.
Return type
tuple[bool, bool]
SEE ALSO:
DMGetBasicAdjacency
Source code at petsc4py/PETSc/DM.pyx:370
getBlockSize()
Return the inherent block size associated with a DM.
Not collective.
SEE ALSO:
DMGetBlockSize
Source code at petsc4py/PETSc/DM.pyx:770
Return type
int
getBoundingBox()
Return the dimension of embedding space for coordinates values.
Not collective.
SEE ALSO:
DMGetBoundingBox
Source code at petsc4py/PETSc/DM.pyx:1306
Return type
tuple[tuple[float, float], ...]
getCellCoordinateDM()
Return the cell coordinate DM.
Collective.
SEE ALSO:
DMGetCellCoordinateDM
Source code at petsc4py/PETSc/DM.pyx:1159
Return type
DM
getCellCoordinateSection()
Return the cell coordinate layout over the DM.
Collective.
SEE ALSO:
DMGetCellCoordinateSection
Source code at petsc4py/PETSc/DM.pyx:1194
Return type
Section
getCellCoordinates()
Return a global vector with the cellwise coordinates.
Collective.
SEE ALSO:
DMGetCellCoordinates
Source code at petsc4py/PETSc/DM.pyx:1226
Return type
Vec
getCellCoordinatesLocal()
Return a local vector with the cellwise coordinates.
Collective.
SEE ALSO:
DMGetCellCoordinatesLocal
Source code at petsc4py/PETSc/DM.pyx:1258
Return type
Vec
getCoarseDM()
Return the coarse DM.
Collective.
SEE ALSO:
DMGetCoarseDM
Source code at petsc4py/PETSc/DM.pyx:1020
Return type
DM
getCoarsenLevel()
Return the number of coarsenings.
Not collective.
SEE ALSO:
DMGetCoarsenLevel
Source code at petsc4py/PETSc/DM.pyx:1629
Return type
int
getCoordinateDM()
Return the coordinate DM.
Collective.
SEE ALSO:
DMGetCoordinateDM
Source code at petsc4py/PETSc/DM.pyx:1048
Return type
DM
getCoordinateDim()
Return the dimension of embedding space for coordinates values.
Not collective.
SEE ALSO:
DMGetCoordinateDim
Source code at petsc4py/PETSc/DM.pyx:238
Return type
int
getCoordinateSection()
Return coordinate values layout over the mesh.
Collective.
SEE ALSO:
DMGetCoordinateSection
Source code at petsc4py/PETSc/DM.pyx:1063
Return type
Section
getCoordinates()
Return a global vector with the coordinates associated.
Collective.
SEE ALSO:
DMGetCoordinates
Source code at petsc4py/PETSc/DM.pyx:1095
Return type
Vec
getCoordinatesLocal()
Return a local vector with the coordinates associated.
Collective the first time it is called.
SEE ALSO:
DMGetCoordinatesLocal
Source code at petsc4py/PETSc/DM.pyx:1127
Return type
Vec
getCoordinatesLocalized()
Check if the coordinates have been localized for cells.
Not collective.
SEE ALSO:
DMGetCoordinatesLocalized
Source code at petsc4py/PETSc/DM.pyx:1292
Return type
bool
getDS()
Return default DS.
Not collective.
SEE ALSO:
DMGetDS
Source code at petsc4py/PETSc/DM.pyx:703
Return type
DS
getDimension()
Return the topological dimension of the DM.
Not collective.
SEE ALSO:
DMGetDimension
Source code at petsc4py/PETSc/DM.pyx:206
Return type
int
getField(index)
Return the discretization object for a given DM field.
Not collective.
Parameters
index (int) -- The field number.
Return type
tuple[Object, None]
SEE ALSO:
DMGetField
Source code at petsc4py/PETSc/DM.pyx:586
getFieldAdjacency(field)
Return the flags for determining variable influence.
Not collective.
Parameters
field (int) -- The field number.
Returns
• useCone (bool) -- Whether adjacency uses cone information.
• useClosure (bool) -- Whether adjacency is computed using full closure information.
Return type
tuple[bool, bool]
SEE ALSO:
DMGetAdjacency
Source code at petsc4py/PETSc/DM.pyx:416
getGlobalSection()
Return the Section encoding the global data layout for the DM.
Collective the first time it is called.
SEE ALSO:
DMGetGlobalSection
Source code at petsc4py/PETSc/DM.pyx:1762
Return type
Section
getGlobalVec(name=None)
Return a global vector.
Collective.
Parameters
name (str | None) -- The optional name to retrieve a persistent vector.
Return type
Vec
Notes
When done with the vector, it must be restored using restoreGlobalVec.
SEE ALSO:
restoreGlobalVec, DMGetGlobalVector, DMGetNamedGlobalVector
Source code at petsc4py/PETSc/DM.pyx:826
getLGMap()
Return local mapping to global mapping.
Collective.
SEE ALSO:
DMGetLocalToGlobalMapping
Source code at petsc4py/PETSc/DM.pyx:1003
Return type
LGMap
getLabel(name)
Return the label of a given name.
Not collective.
SEE ALSO:
DMGetLabel
Source code at petsc4py/PETSc/DM.pyx:1704
Parameters
name (str)
Return type
DMLabel
getLabelIdIS(name)
Return an IS of all values that the DMLabel takes.
Not collective.
Parameters
name (str) -- The label name.
Return type
IS
SEE ALSO:
DMLabelGetValueIS, DMGetLabelIdIS
Source code at petsc4py/PETSc/DM.pyx:2055
getLabelName(index)
Return the name of nth label.
Not collective.
Parameters
index (int) -- The label number.
Return type
str
SEE ALSO:
DMGetLabelName
Source code at petsc4py/PETSc/DM.pyx:1881
getLabelOutput(name)
Return the output flag for a given label.
Not collective.
Parameters
name (str) -- The label name.
Return type
bool
SEE ALSO:
DMGetLabelOutput
Source code at petsc4py/PETSc/DM.pyx:2168
getLabelSize(name)
Return the number of values that the DMLabel takes.
Not collective.
Parameters
name (str) -- The label name.
Return type
int
SEE ALSO:
DMLabelGetNumValues, DMGetLabelSize
Source code at petsc4py/PETSc/DM.pyx:2034
getLabelValue(name, point)
Return the value in DMLabel for the given point.
Not collective.
Parameters
• name (str) -- The label name.
• point (int) -- The mesh point
Return type
int
SEE ALSO:
DMGetLabelValue
Source code at petsc4py/PETSc/DM.pyx:1963
getLocalBoundingBox()
Return the bounding box for the piece of the DM.
Not collective.
SEE ALSO:
DMGetLocalBoundingBox
Source code at petsc4py/PETSc/DM.pyx:1323
Return type
tuple[tuple[float, float], ...]
getLocalSection()
Return the Section encoding the local data layout for the DM.
Not collective.
SEE ALSO:
DMGetGlobalSection
Source code at petsc4py/PETSc/DM.pyx:1735
Return type
Section
getLocalVec(name=None)
Return a local vector.
Not collective.
Parameters
name (str | None) -- The optional name to retrieve a persistent vector.
Return type
Vec
Notes
When done with the vector, it must be restored using restoreLocalVec.
SEE ALSO:
restoreLocalVec, DMGetLocalVector, DMGetNamedLocalVector
Source code at petsc4py/PETSc/DM.pyx:880
getNumFields()
Return the number of fields in the DM.
Not collective.
SEE ALSO:
DMGetNumFields
Source code at petsc4py/PETSc/DM.pyx:546
Return type
int
getNumLabels()
Return the number of labels defined by on the DM.
Not collective.
SEE ALSO:
DMGetNumLabels
Source code at petsc4py/PETSc/DM.pyx:1867
Return type
int
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, DMGetOptionsPrefix
Source code at petsc4py/PETSc/DM.pyx:284
Return type
str
getPointSF()
Return the SF encoding the parallel DOF overlap for the DM.
Not collective.
SEE ALSO:
DMGetPointSF
Source code at petsc4py/PETSc/DM.pyx:1840
Return type
SF
getRefineLevel()
Return the refinement level.
Not collective.
SEE ALSO:
DMGetRefineLevel
Source code at petsc4py/PETSc/DM.pyx:1597
Return type
int
getSectionSF()
Return the Section encoding the parallel DOF overlap.
Collective the first time it is called.
SEE ALSO:
DMGetSectionSF
Source code at petsc4py/PETSc/DM.pyx:1809
Return type
SF
getStratumIS(name, value)
Return the points in a label stratum.
Not collective.
Parameters
• name (str) -- The label name.
• value (int) -- The stratum value.
Return type
IS
SEE ALSO:
DMGetStratumIS
Source code at petsc4py/PETSc/DM.pyx:2100
getStratumSize(name, value)
Return the number of points in a label stratum.
Not collective.
Parameters
• name (str) -- The label name.
• value (int) -- The stratum value.
Return type
int
SEE ALSO:
DMGetStratumSize
Source code at petsc4py/PETSc/DM.pyx:2076
getType()
Return the DM type name.
Not collective.
SEE ALSO:
DMGetType
Source code at petsc4py/PETSc/DM.pyx:192
Return type
str
globalToLocal(vg, vl, addv=None)
Update local vectors from global vector.
Neighborwise collective.
Parameters
• vg (Vec) -- The global vector.
• vl (Vec) -- The local vector.
• addv (InsertModeSpec | None) -- Insertion mode.
Return type
None
SEE ALSO:
DMGlobalToLocalBegin, DMGlobalToLocalEnd
Source code at petsc4py/PETSc/DM.pyx:934
hasLabel(name)
Determine whether the DM has a label.
Not collective.
Parameters
name (str) -- The label name.
Return type
bool
SEE ALSO:
DMHasLabel
Source code at petsc4py/PETSc/DM.pyx:1901
load(viewer)
Return a DM stored in binary.
Collective.
Parameters
viewer (Viewer) -- Viewer used to store the DM, like Viewer.Type.BINARY or
Viewer.Type.HDF5.
Return type
Self
Notes
When using Viewer.Type.HDF5 format, one can save multiple DMPlex meshes in a single HDF5
files. This in turn requires one to name the DMPlex object with Object.setName before
saving it with DM.view and before loading it with DM.load for identification of the mesh
object.
SEE ALSO:
DM.view, DM.load, Object.setName, DMLoad
Source code at petsc4py/PETSc/DM.pyx:95
localToGlobal(vl, vg, addv=None)
Update global vectors from local vector.
Neighborwise collective.
Parameters
• vl (Vec) -- The local vector.
• vg (Vec) -- The global vector.
• addv (InsertModeSpec | None) -- Insertion mode.
Return type
None
SEE ALSO:
DMLocalToGlobalBegin, DMLocalToGlobalEnd
Source code at petsc4py/PETSc/DM.pyx:957
localToLocal(vl, vlg, addv=None)
Map the values from a local vector to another local vector.
Neighborwise collective.
Parameters
• vl (Vec) -- The local vector.
• vlg (Vec) -- The global vector.
• addv (InsertModeSpec | None) -- Insertion mode.
Return type
None
SEE ALSO:
DMLocalToLocalBegin, DMLocalToLocalEnd
Source code at petsc4py/PETSc/DM.pyx:980
localizeCoordinates()
Create local coordinates for cells having periodic faces.
Collective.
Notes
Used if the mesh is periodic.
SEE ALSO:
DMLocalizeCoordinates
Source code at petsc4py/PETSc/DM.pyx:1340
Return type
None
refine(comm=None)
Return a refined DM object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
DM
SEE ALSO:
DMRefine
Source code at petsc4py/PETSc/DM.pyx:1495
refineHierarchy(nlevels)
Refine this DM and return the refined DM hierarchy.
Collective.
Parameters
nlevels (int) -- The number of levels of refinement.
Return type
list
SEE ALSO:
DMRefineHierarchy
Source code at petsc4py/PETSc/DM.pyx:1543
removeLabel(name)
Remove and destroy the label by name.
Not collective.
Parameters
name (str) -- The label name.
Return type
None
SEE ALSO:
DMRemoveLabel
Source code at petsc4py/PETSc/DM.pyx:1941
restoreGlobalVec(vg, name=None)
Restore a global vector obtained with getGlobalVec.
Logically collective.
Parameters
• vg (Vec) -- The global vector.
• name (str | None) -- The name used to retrieve the persistent vector, if any.
Return type
None
SEE ALSO:
getGlobalVec, DMRestoreGlobalVector, DMRestoreNamedGlobalVector
Source code at petsc4py/PETSc/DM.pyx:855
restoreLocalVec(vl, name=None)
Restore a local vector obtained with getLocalVec.
Not collective.
Parameters
• vl (Vec) -- The local vector.
• name (str | None) -- The name used to retrieve the persistent vector, if any.
Return type
None
SEE ALSO:
getLocalVec, DMRestoreLocalVector, DMRestoreNamedLocalVector
Source code at petsc4py/PETSc/DM.pyx:909
setAppCtx(appctx)
Set the application context.
Source code at petsc4py/PETSc/DM.pyx:339
Parameters
appctx (Any)
Return type
None
setAuxiliaryVec(aux, label, value=0, part=0)
Set an auxiliary vector for a specific region.
Not collective.
Parameters
• aux (Vec) -- The auxiliary vector.
• label (DMLabel | None) -- The name of the DMLabel.
• value -- Indicate the region.
• part -- The equation part, or 0 is unused.
Return type
None
SEE ALSO:
DMGetLabel, DMSetAuxiliaryVec
Source code at petsc4py/PETSc/DM.pyx:473
setBasicAdjacency(useCone, useClosure)
Set the flags for determining variable influence.
Not collective.
Parameters
• useCone (bool) -- Whether adjacency uses cone information.
• useClosure (bool) -- Whether adjacency is computed using full closure information.
Return type
None
SEE ALSO:
DMSetBasicAdjacency
Source code at petsc4py/PETSc/DM.pyx:349
setCellCoordinateDM(dm)
Set the cell coordinate DM.
Collective.
Parameters
dm (DM) -- The cell coordinate DM.
Return type
None
SEE ALSO:
DMSetCellCoordinateDM
Source code at petsc4py/PETSc/DM.pyx:1142
setCellCoordinateSection(dim, sec)
Set the cell coordinate layout over the DM.
Collective.
Parameters
• dim (int) -- The embedding dimension, or DETERMINE.
• sec (Section) -- The cell coordinate Section.
Return type
None
SEE ALSO:
DMSetCellCoordinateSection
Source code at petsc4py/PETSc/DM.pyx:1174
setCellCoordinates(c)
Set a global vector with the cellwise coordinates.
Collective.
Parameters
c (Vec) -- The global cell coordinate vector.
Return type
None
SEE ALSO:
DMSetCellCoordinates
Source code at petsc4py/PETSc/DM.pyx:1209
setCellCoordinatesLocal(c)
Set a local vector with the cellwise coordinates.
Not collective.
Parameters
c (Vec) -- The local cell coordinate vector.
Return type
None
SEE ALSO:
DMSetCellCoordinatesLocal
Source code at petsc4py/PETSc/DM.pyx:1241
setCoarseDM(dm)
Set the coarse DM.
Collective.
SEE ALSO:
DMSetCoarseDM
Source code at petsc4py/PETSc/DM.pyx:1035
Parameters
dm (DM)
Return type
None
setCoordinateDim(dim)
Set the dimension of embedding space for coordinates values.
Not collective.
Parameters
dim (int) -- The embedding dimension.
Return type
None
SEE ALSO:
DMSetCoordinateDim
Source code at petsc4py/PETSc/DM.pyx:252
setCoordinateDisc(disc, project)
Project coordinates to a different space.
Collective.
Parameters
• disc (FE) -- The new coordinates discretization.
• project (bool)
Return type
Self
SEE ALSO:
DMSetCoordinateDisc
Source code at petsc4py/PETSc/DM.pyx:1273
setCoordinates(c)
Set a global vector that holds the coordinates.
Collective.
Parameters
c (Vec) -- Coordinate Vector.
Return type
None
SEE ALSO:
DMSetCoordinates
Source code at petsc4py/PETSc/DM.pyx:1078
setCoordinatesLocal(c)
Set a local vector with the ghost point holding the coordinates.
Not collective.
Parameters
c (Vec) -- Coordinate Vector.
Return type
None
SEE ALSO:
DMSetCoordinatesLocal
Source code at petsc4py/PETSc/DM.pyx:1110
setDimension(dim)
Set the topological dimension of the DM.
Collective.
Parameters
dim (int) -- Topological dimension.
Return type
None
SEE ALSO:
DMSetDimension
Source code at petsc4py/PETSc/DM.pyx:220
setField(index, field, label=None)
Set the discretization object for a given DM field.
Logically collective.
Parameters
• index (int) -- The field number.
• field (Object) -- The discretization object.
• label (str | None) -- The name of the label indicating the support of the field,
or None for the entire mesh.
Return type
None
SEE ALSO:
DMSetField
Source code at petsc4py/PETSc/DM.pyx:560
setFieldAdjacency(field, useCone, useClosure)
Set the flags for determining variable influence.
Not collective.
Parameters
• field (int) -- The field number.
• useCone (bool) -- Whether adjacency uses cone information.
• useClosure (bool) -- Whether adjacency is computed using full closure information.
Return type
None
SEE ALSO:
DMSetAdjacency
Source code at petsc4py/PETSc/DM.pyx:392
setFromOptions()
Configure the object from the options database.
Collective.
SEE ALSO:
Working with PETSc options, DMSetFromOptions
Source code at petsc4py/PETSc/DM.pyx:312
Return type
None
setGlobalSection(sec)
Set the Section encoding the global data layout for the DM.
Collective.
SEE ALSO:
DMSetGlobalSection
Source code at petsc4py/PETSc/DM.pyx:1750
Parameters
sec (Section)
Return type
None
setKSPComputeOperators(operators, args=None, kargs=None)
Matrix associated with the linear system.
Collective.
Parameters
• operator -- Callback function to compute the operators.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
DMKSPSetComputeOperators
Source code at petsc4py/PETSc/DM.pyx:2194
setLabelOutput(name, output)
Set if a given label should be saved to a view.
Not collective.
Parameters
• name (str) -- The label name.
• output (bool) -- If True, the label is saved to the viewer.
Return type
None
SEE ALSO:
DMSetLabelOutput
Source code at petsc4py/PETSc/DM.pyx:2146
setLabelValue(name, point, value)
Set a point to a DMLabel with a given value.
Not collective.
Parameters
• name (str) -- The label name.
• point (int) -- The mesh point.
• value (int) -- The label value for the point.
Return type
None
SEE ALSO:
DMSetLabelValue
Source code at petsc4py/PETSc/DM.pyx:1986
setLocalSection(sec)
Set the Section encoding the local data layout for the DM.
Collective.
SEE ALSO:
DMSetLocalSection
Source code at petsc4py/PETSc/DM.pyx:1723
Parameters
sec (Section)
Return type
None
setMatType(mat_type)
Set matrix type to be used by DM.createMat.
Logically collective.
Parameters
mat_type (Type | str) -- The matrix type.
Return type
None
Notes
The option -dm_mat_type is used to set the matrix type.
SEE ALSO:
Working with PETSc options, DMSetMatType
Source code at petsc4py/PETSc/DM.pyx:1357
setNumFields(numFields)
Set the number of fields in the DM.
Logically collective.
SEE ALSO:
DMSetNumFields
Source code at petsc4py/PETSc/DM.pyx:533
Parameters
numFields (int)
Return type
None
setOptionsPrefix(prefix)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, getOptionsPrefix, DMSetOptionsPrefix
Source code at petsc4py/PETSc/DM.pyx:270
Parameters
prefix (str | None)
Return type
None
setPointSF(sf)
Set the SF encoding the parallel DOF overlap for the DM.
Logically collective.
SEE ALSO:
DMSetPointSF
Source code at petsc4py/PETSc/DM.pyx:1855
Parameters
sf (SF)
Return type
None
setRefineLevel(level)
Set the number of refinements.
Not collective.
Parameters
• nlevels -- The number of refinement.
• level (int)
Return type
None
SEE ALSO:
DMSetRefineLevel
Source code at petsc4py/PETSc/DM.pyx:1611
setSNESFunction(function, args=None, kargs=None)
Set SNES residual evaluation function.
Not collective.
Parameters
• function (SNESFunction) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
SNES.setFunction, DMSNESSetFunction
Source code at petsc4py/PETSc/DM.pyx:2270
setSNESJacobian(jacobian, args=None, kargs=None)
Set the SNES Jacobian evaluation function.
Not collective.
Parameters
• jacobian (SNESJacobianFunction) -- The Jacobian callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
SNES.setJacobian, DMSNESSetJacobian
Source code at petsc4py/PETSc/DM.pyx:2302
setSectionSF(sf)
Set the Section encoding the parallel DOF overlap for the DM.
Logically collective.
SEE ALSO:
DMSetSectionSF
Source code at petsc4py/PETSc/DM.pyx:1824
Parameters
sf (SF)
Return type
None
setType(dm_type)
Build a DM.
Collective.
Parameters
dm_type (Type | str) -- The type of DM.
Return type
None
Notes
DM types are available in DM.Type class.
SEE ALSO:
DM.Type, DMSetType
Source code at petsc4py/PETSc/DM.pyx:169
setUp()
Return the data structure.
Collective.
SEE ALSO:
DMSetUp
Source code at petsc4py/PETSc/DM.pyx:324
Return type
Self
setVecType(vec_type)
Set the type of vector.
Logically collective.
SEE ALSO:
Vec.Type, DMSetVecType
Source code at petsc4py/PETSc/DM.pyx:784
Parameters
vec_type (Type | str)
Return type
None
view(viewer=None)
View the DM.
Collective.
Parameters
viewer (Viewer | None) -- The DM viewer.
Return type
None
SEE ALSO:
DMView
Source code at petsc4py/PETSc/DM.pyx:76
Attributes Documentation
appctx Application context.
Source code at petsc4py/PETSc/DM.pyx:2386
ds Discrete space.
Source code at petsc4py/PETSc/DM.pyx:2396
petsc4py.PETSc.DMComposite
class petsc4py.PETSc.DMComposite
Bases: DM
A DM object that is used to manage data for a collection of DMs.
Methods Summary
┌────────────────────────────┬───────────────────────────────────────┐
│ addDM(dm, *args) │ Add a DM vector to the composite. │
├────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a composite object. │
├────────────────────────────┼───────────────────────────────────────┤
│ gather(gvec, imode, lvecs) │ Gather split local vectors into a │
│ │ coupled global vector. │
├────────────────────────────┼───────────────────────────────────────┤
│ getAccess(gvec[, locs]) │ Get access to the individual vectors │
│ │ from the global vector. │
├────────────────────────────┼───────────────────────────────────────┤
│ getEntries() │ Return sub-DMs contained in the │
│ │ composite. │
├────────────────────────────┼───────────────────────────────────────┤
│ getGlobalISs() │ Return the index sets for each │
│ │ composed object in the composite. │
├────────────────────────────┼───────────────────────────────────────┤
│ getLGMaps() │ Return a local-to-global mapping for │
│ │ each DM in the composite. │
├────────────────────────────┼───────────────────────────────────────┤
│ getLocalISs() │ Return index sets for each component │
│ │ of a composite local vector. │
├────────────────────────────┼───────────────────────────────────────┤
│ getNumber() │ Get number of sub-DMs contained in │
│ │ the composite. │
├────────────────────────────┼───────────────────────────────────────┤
│ scatter(gvec, lvecs) │ Scatter coupled global vector into │
│ │ split local vectors. │
└────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
addDM(dm, *args)
Add a DM vector to the composite.
Collective.
Parameters
• dm (DM) -- The DM object.
• *args (DM) -- Additional DM objects.
Return type
None
SEE ALSO:
DMCompositeAddDM
Source code at petsc4py/PETSc/DMComposite.pyx:28
create(comm=None)
Create a composite object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DMCompositeCreate
Source code at petsc4py/PETSc/DMComposite.pyx:6
gather(gvec, imode, lvecs)
Gather split local vectors into a coupled global vector.
Collective.
Parameters
• gvec (Vec) -- The global vector.
• imode (InsertModeSpec) -- The insertion mode.
• lvecs (Sequence[Vec]) -- The individual sequential vectors.
Return type
None
SEE ALSO:
scatter, DMCompositeGatherArray
Source code at petsc4py/PETSc/DMComposite.pyx:115
getAccess(gvec, locs=None)
Get access to the individual vectors from the global vector.
Not collective.
Use via The with statement context manager (PEP 343).
Parameters
• gvec (Vec) -- The global vector.
• locs (Sequence[int] | None) -- Indices of vectors wanted, or None to get all
vectors.
Return type
Any
Source code at petsc4py/PETSc/DMComposite.pyx:219
getEntries()
Return sub-DMs contained in the composite.
Not collective.
SEE ALSO:
DMCompositeGetEntriesArray
Source code at petsc4py/PETSc/DMComposite.pyx:66
Return type
list[DM]
getGlobalISs()
Return the index sets for each composed object in the composite.
Collective.
These could be used to extract a subset of vector entries for a "multi-physics"
preconditioner.
Use getLocalISs for index sets in the packed local numbering, and getLGMaps for to map
local sub-DM (including ghost) indices to packed global indices.
SEE ALSO:
DMCompositeGetGlobalISs
Source code at petsc4py/PETSc/DMComposite.pyx:143
Return type
list[IS]
getLGMaps()
Return a local-to-global mapping for each DM in the composite.
Collective.
Note that this includes all the ghost points that individual ghosted DMDA may have.
SEE ALSO:
DMCompositeGetISLocalToGlobalMappings
Source code at petsc4py/PETSc/DMComposite.pyx:196
Return type
list[LGMap]
getLocalISs()
Return index sets for each component of a composite local vector.
Not collective.
To get the composite global indices at all local points (including ghosts), use getLGMaps.
To get index sets for pieces of the composite global vector, use getGlobalISs.
SEE ALSO:
DMCompositeGetLocalISs
Source code at petsc4py/PETSc/DMComposite.pyx:170
Return type
list[IS]
getNumber()
Get number of sub-DMs contained in the composite.
Not collective.
SEE ALSO:
DMCompositeGetNumberDM
Source code at petsc4py/PETSc/DMComposite.pyx:51
Return type
int
scatter(gvec, lvecs)
Scatter coupled global vector into split local vectors.
Collective.
Parameters
• gvec (Vec) -- The global vector.
• lvecs (Sequence[Vec]) -- Array of local vectors.
Return type
None
SEE ALSO:
gather, DMCompositeScatterArray
Source code at petsc4py/PETSc/DMComposite.pyx:90
petsc4py.PETSc.DMDA
class petsc4py.PETSc.DMDA
Bases: DM
A DM object that is used to manage data for a structured grid.
Enumerations
┌───────────────────┬──────────────────────┐
│ ElementType │ Element types. │
├───────────────────┼──────────────────────┤
│ InterpolationType │ Interpolation types. │
├───────────────────┼──────────────────────┤
│ StencilType │ Stencil types. │
└───────────────────┴──────────────────────┘
petsc4py.PETSc.DMDA.ElementType
class petsc4py.PETSc.DMDA.ElementType
Bases: object
Element types.
Attributes Summary
┌────┬─────────────────────────┐
│ P1 │ Constant P1 of type int │
├────┼─────────────────────────┤
│ Q1 │ Constant Q1 of type int │
└────┴─────────────────────────┘
Attributes Documentation
P1: int = P1
Constant P1 of type int
Q1: int = Q1
Constant Q1 of type int
petsc4py.PETSc.DMDA.InterpolationType
class petsc4py.PETSc.DMDA.InterpolationType
Bases: object
Interpolation types.
Attributes Summary
┌────┬─────────────────────────┐
│ Q0 │ Constant Q0 of type int │
├────┼─────────────────────────┤
│ Q1 │ Constant Q1 of type int │
└────┴─────────────────────────┘
Attributes Documentation
Q0: int = Q0
Constant Q0 of type int
Q1: int = Q1
Constant Q1 of type int
petsc4py.PETSc.DMDA.StencilType
class petsc4py.PETSc.DMDA.StencilType
Bases: object
Stencil types.
Attributes Summary
┌──────┬───────────────────────────┐
│ BOX │ Constant BOX of type int │
├──────┼───────────────────────────┤
│ STAR │ Constant STAR of type int │
└──────┴───────────────────────────┘
Attributes Documentation
BOX: int = BOX
Constant BOX of type int
STAR: int = STAR
Constant STAR of type int
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ create([dim, dof, sizes, proc_sizes, │ Create a DMDA object. │
│ ...]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createNaturalVec() │ Create a vector that will hold values │
│ │ in the natural numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ duplicate([dof, boundary_type, ...]) │ Duplicate a DMDA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAO() │ Return the application ordering │
│ │ context for a distributed array. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBoundaryType() │ Return the type of ghost nodes at │
│ │ boundary in each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinateName(index) │ Return the name of a coordinate │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCorners() │ Return the lower left corner and the │
│ │ sizes of the owned local region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDim() │ Return the topological dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDof() │ Return the number of degrees of │
│ │ freedom per node. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getElementType() │ Return the element type to be │
│ │ returned by getElements. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getElements([elem_type]) │ Return an array containing the │
│ │ indices of all the local elements. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldName(field) │ Return the name of an individual │
│ │ field component. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGhostCorners() │ Return the lower left corner and the │
│ │ size of the ghosted local region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGhostRanges() │ Return the ranges of the local region │
│ │ in each dimension, including ghost │
│ │ nodes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInterpolationType() │ Return the type of interpolation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRanges() │ Return the ranges of indices in each │
│ │ dimension owned by each process. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getProcSizes() │ Return the number of processes in │
│ │ each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRanges() │ Return the ranges of the owned local │
│ │ region in each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRefinementFactor() │ Return the ratios that the DMDA grid │
│ │ is refined in each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getScatter() │ Return the global-to-local, and │
│ │ local-to-local scatter contexts. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSizes() │ Return the number of grid points in │
│ │ each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStencil() │ Return the stencil type and width. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStencilType() │ Return the stencil type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStencilWidth() │ Return the stencil width. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVecArray(vec[, readonly]) │ Get access to the vector as laid out │
│ │ on a N-d grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ globalToNatural(vg, vn[, addv]) │ Map values to the "natural" grid │
│ │ ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ naturalToGlobal(vn, vg[, addv]) │ Map values the to grid ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBoundaryType(boundary_type) │ Set the type of ghost nodes on domain │
│ │ boundaries. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinateName(index, name) │ Set the name of the coordinate │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDim(dim) │ Set the topological dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDof(dof) │ Set the number of degrees of freedom │
│ │ per vertex. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setElementType(elem_type) │ Set the element type to be returned │
│ │ by getElements. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldName(field, name) │ Set the name of individual field │
│ │ components. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setInterpolationType(interp_type) │ Set the type of interpolation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setProcSizes(proc_sizes) │ Set the number of processes in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRefinementFactor([refine_x, │ Set the ratios for the DMDA grid │
│ refine_y, ...]) │ refinement. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSizes(sizes) │ Set the number of grid points in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencil(stencil_type, │ Set the stencil type and width. │
│ stencil_width) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencilType(stencil_type) │ Set the stencil type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencilWidth(stencil_width) │ Set the stencil width. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUniformCoordinates([xmin, xmax, │ Set the DMDA coordinates to be a │
│ ymin, ...]) │ uniform grid. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────────┬───────────────────────────────────────┐
│ boundary_type │ Boundary types in each dimension. │
├───────────────┼───────────────────────────────────────┤
│ corners │ The lower left corner and size of │
│ │ local region in each dimension. │
├───────────────┼───────────────────────────────────────┤
│ dim │ The grid dimension. │
├───────────────┼───────────────────────────────────────┤
│ dof │ The number of DOFs associated with │
│ │ each stratum of the grid. │
├───────────────┼───────────────────────────────────────┤
│ ghost_corners │ The lower left corner and size of │
│ │ local region in each dimension. │
├───────────────┼───────────────────────────────────────┤
│ ghost_ranges │ Ranges of local region, including │
│ │ ghost nodes. │
├───────────────┼───────────────────────────────────────┤
│ proc_sizes │ The number of processes in each │
│ │ dimension in the global │
│ │ decomposition. │
├───────────────┼───────────────────────────────────────┤
│ ranges │ Ranges of the local region in each │
│ │ dimension. │
├───────────────┼───────────────────────────────────────┤
│ sizes │ The global dimension. │
├───────────────┼───────────────────────────────────────┤
│ stencil │ Stencil type and width. │
├───────────────┼───────────────────────────────────────┤
│ stencil_type │ Stencil type. │
├───────────────┼───────────────────────────────────────┤
│ stencil_width │ Elementwise stencil width. │
└───────────────┴───────────────────────────────────────┘
Methods Documentation
create(dim=None, dof=None, sizes=None, proc_sizes=None, boundary_type=None, stencil_type=None,
stencil_width=None, setup=True, ownership_ranges=None, comm=None)
Create a DMDA object.
Collective.
This routine performs the following steps of the C API: - petsc.DMDACreate -
petsc.DMSetDimension - petsc.DMDASetDof - petsc.DMDASetSizes - petsc.DMDASetNumProcs -
petsc.DMDASetOwnershipRanges - petsc.DMDASetBoundaryType - petsc.DMDASetStencilType -
petsc.DMDASetStencilWidth - petsc.DMSetUp (optionally)
Parameters
• dim (int | None) -- The number of dimensions.
• dof (int | None) -- The number of degrees of freedom.
• sizes (DimsSpec | None) -- The number of elements in each dimension.
• proc_sizes (DimsSpec | None) -- The number of processes in x, y, z dimensions.
• boundary_type (tuple[DM.BoundaryType | int | str | bool, ...] | None) -- The
boundary types.
• stencil_type (StencilType | None) -- The ghost/halo stencil type.
• stencil_width (int | None) -- The width of the ghost/halo region.
• setup (bool) -- Whether to call the setup routine after creating the object.
• ownership_ranges (tuple[Sequence[int], ...] | None) -- Local x, y, z element
counts, of length equal to proc_sizes, summing to sizes.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DMDACreate, DMSetDimension, DMDASetDof, DMDASetSizes, DMDASetNumProcs, ‐
DMDASetOwnershipRanges, DMDASetBoundaryType, DMDASetStencilType, DMDASetStencilWidth, ‐
DMSetUp
Source code at petsc4py/PETSc/DMDA.pyx:32
createNaturalVec()
Create a vector that will hold values in the natural numbering.
Collective.
The number of local entries in the vector on each process is the same as in a vector
created with DM.createGlobalVec.
SEE ALSO:
DMDACreateNaturalVector
Source code at petsc4py/PETSc/DMDA.pyx:832
Return type
Vec
duplicate(dof=None, boundary_type=None, stencil_type=None, stencil_width=None)
Duplicate a DMDA.
Collective.
This routine retrieves the information from the DMDA and recreates it. Parameters dof,
boundary_type, stencil_type, stencil_width will be overwritten, if provided.
Parameters
• dof (int | None) -- The number of degrees of freedom.
• boundary_type (tuple[DM.BoundaryType | int | str | bool, ...] | None) -- Boundary
types.
• stencil_type (StencilType | None) -- The ghost/halo stencil type.
• stencil_width (int | None) -- The width of the ghost/halo region.
Return type
DMDA
SEE ALSO:
create, DMDAGetInfo, DMSetUp
Source code at petsc4py/PETSc/DMDA.pyx:148
getAO()
Return the application ordering context for a distributed array.
Collective.
The returned AO maps to the natural grid ordering that would be used for the DMDA if only 1
processor were employed (ordering most rapidly in the x-dimension, then y, then z).
Multiple degrees of freedom are numbered for each node (rather than 1 component for the
whole grid, then the next component, etc.).
SEE ALSO:
DMDAGetAO
Source code at petsc4py/PETSc/DMDA.pyx:909
Return type
AO
getBoundaryType()
Return the type of ghost nodes at boundary in each dimension.
Not collective.
SEE ALSO:
setBoundaryType
Source code at petsc4py/PETSc/DMDA.pyx:407
Return type
tuple[BoundaryType, ...]
getCoordinateName(index)
Return the name of a coordinate dimension.
Not collective.
Parameters
index (int) -- The coordinate number for the DMDA (0, 1, ..., dim-1).
Return type
str
SEE ALSO:
setCoordinateName, DMDAGetCoordinateName
Source code at petsc4py/PETSc/DMDA.pyx:810
getCorners()
Return the lower left corner and the sizes of the owned local region.
Not collective.
Returns the global (x,y,z) indices of the lower left corner (first tuple) and size of the
local region (second tuple).
Excluding ghost points.
The corner information is independent of the number of degrees of freedom per node. Thus
the returned values can be thought of as coordinates on a logical grid, where each grid
point has (potentially) several degrees of freedom.
SEE ALSO:
getRanges, getGhostRanges, getOwnershipRanges, getGhostCorners, DMDAGetCorners
Source code at petsc4py/PETSc/DMDA.pyx:622
Return type
tuple[tuple[int, ...], tuple[int, ...]]
getDim()
Return the topological dimension.
Not collective.
SEE ALSO:
setDim, DMGetDimension
Source code at petsc4py/PETSc/DMDA.pyx:234
Return type
int
getDof()
Return the number of degrees of freedom per node.
Not collective.
SEE ALSO:
setDof, DMDAGetInfo
Source code at petsc4py/PETSc/DMDA.pyx:264
Return type
int
getElementType()
Return the element type to be returned by getElements.
Not collective.
SEE ALSO:
setElementType, DMDAGetElementType
Source code at petsc4py/PETSc/DMDA.pyx:1050
Return type
ElementType
getElements(elem_type=None)
Return an array containing the indices of all the local elements.
Not collective.
The elements are in local coordinates.
Each process uniquely owns a subset of the elements. That is, no element is owned by two or
more processes.
Parameters
elem_type (ElementType | None) -- The element type.
Return type
ArrayInt
SEE ALSO:
DMDAGetElements
Source code at petsc4py/PETSc/DMDA.pyx:1064
getFieldName(field)
Return the name of an individual field component.
Not collective.
Parameters
field (int) -- The field number for the DMDA (0, 1, ..., dof-1), where dof indicates
the number of degrees of freedom per node within the DMDA.
Return type
str
SEE ALSO:
setFieldName, DMDAGetFieldName
Source code at petsc4py/PETSc/DMDA.pyx:699
getGhostCorners()
Return the lower left corner and the size of the ghosted local region.
Not collective.
Returns the global (x,y,z) indices of the lower left corner (first tuple) and size of the
local region (second tuple).
SEE ALSO:
getRanges, getGhostRanges, getOwnershipRanges, getCorners, DMDAGetGhostCorners
Source code at petsc4py/PETSc/DMDA.pyx:651
Return type
tuple[tuple[int, ...], tuple[int, ...]]
getGhostRanges()
Return the ranges of the local region in each dimension, including ghost nodes.
Not collective.
SEE ALSO:
getRanges, getOwnershipRanges, getCorners, getGhostCorners, DMDAGetGhostCorners
Source code at petsc4py/PETSc/DMDA.pyx:577
Return type
tuple[tuple[int, int], ...]
getInterpolationType()
Return the type of interpolation.
Not collective.
SEE ALSO:
setInterpolationType, DMDAGetInterpolationType
Source code at petsc4py/PETSc/DMDA.pyx:1020
Return type
InterpolationType
getOwnershipRanges()
Return the ranges of indices in each dimension owned by each process.
Not collective.
These numbers are not multiplied by the number of DOFs per node.
SEE ALSO:
getRanges, getGhostRanges, getCorners, getGhostCorners, DMDAGetOwnershipRanges
Source code at petsc4py/PETSc/DMDA.pyx:597
Return type
tuple[ArrayInt, ...]
getProcSizes()
Return the number of processes in each dimension.
Not collective.
SEE ALSO:
setProcSizes, DMDAGetInfo
Source code at petsc4py/PETSc/DMDA.pyx:361
Return type
tuple[int, ...]
getRanges()
Return the ranges of the owned local region in each dimension.
Not collective.
Excluding ghost nodes.
SEE ALSO:
getGhostRanges, getOwnershipRanges, getCorners, getGhostCorners, DMDAGetCorners
Source code at petsc4py/PETSc/DMDA.pyx:555
Return type
tuple[tuple[int, int], ...]
getRefinementFactor()
Return the ratios that the DMDA grid is refined in each dimension.
Not collective.
SEE ALSO:
setRefinementFactor, DMDAGetRefinementFactor
Source code at petsc4py/PETSc/DMDA.pyx:981
Return type
tuple[int, ...]
getScatter()
Return the global-to-local, and local-to-local scatter contexts.
Collective.
SEE ALSO:
DMDAGetScatter
Source code at petsc4py/PETSc/DMDA.pyx:930
Return type
tuple[Scatter, Scatter]
getSizes()
Return the number of grid points in each dimension.
Not collective.
SEE ALSO:
setSizes, DMDAGetInfo
Source code at petsc4py/PETSc/DMDA.pyx:311
Return type
tuple[int, ...]
getStencil()
Return the stencil type and width.
Not collective.
SEE ALSO:
getStencilType, getStencilWidth
Source code at petsc4py/PETSc/DMDA.pyx:532
Return type
tuple[StencilType, int]
getStencilType()
Return the stencil type.
Not collective.
SEE ALSO:
setStencilType, DMDAGetInfo
Source code at petsc4py/PETSc/DMDA.pyx:448
Return type
StencilType
getStencilWidth()
Return the stencil width.
Not collective.
SEE ALSO:
setStencilWidth
Source code at petsc4py/PETSc/DMDA.pyx:486
Return type
int
getVecArray(vec, readonly=False)
Get access to the vector as laid out on a N-d grid.
Logically collective.
Parameters
• vec (Vec) -- The vector to which access is being requested.
• readonly (bool) -- Request read-only access.
Return type
Any
SEE ALSO:
Vec.getArray, DMDAVecGetArray, DMDAVecGetArrayDOF
Source code at petsc4py/PETSc/DMDA.pyx:723
globalToNatural(vg, vn, addv=None)
Map values to the "natural" grid ordering.
Neighborwise collective.
You must call createNaturalVec before using this routine.
Parameters
• vg (Vec) -- The global vector in a grid ordering.
• vn (Vec) -- The global vector in a "natural" ordering.
• addv (InsertMode | None) -- The insertion mode.
Return type
None
SEE ALSO:
naturalToGlobal, DMDAGlobalToNaturalBegin, DMDAGlobalToNaturalEnd
Source code at petsc4py/PETSc/DMDA.pyx:849
naturalToGlobal(vn, vg, addv=None)
Map values the to grid ordering.
Neighborwise collective.
Parameters
• vn (Vec) -- The global vector in a natural ordering.
• vg (Vec) -- the global vector in a grid ordering.
• addv (InsertMode | None) -- The insertion mode.
Return type
None
SEE ALSO:
globalToNatural, DMDANaturalToGlobalBegin, DMDANaturalToGlobalEnd
Source code at petsc4py/PETSc/DMDA.pyx:879
setBoundaryType(boundary_type)
Set the type of ghost nodes on domain boundaries.
Not collective.
Parameters
boundary_type (tuple[BoundaryType | int | str | bool, ...]) -- The boundary type in
(x), (x, y), or (x, y, z) dimensions.
Return type
None
SEE ALSO:
getBoundaryType, DMDASetBoundaryType
Source code at petsc4py/PETSc/DMDA.pyx:384
setCoordinateName(index, name)
Set the name of the coordinate dimension.
Logically collective.
Parameters
• index (int) -- The coordinate number for the DMDA (0, 1, ..., dim-1).
• name (str) -- The name of the coordinate.
Return type
None
SEE ALSO:
getCoordinateName, DMDASetCoordinateName
Source code at petsc4py/PETSc/DMDA.pyx:788
setDim(dim)
Set the topological dimension.
Collective.
Parameters
dim (int) -- Topological dimension.
Return type
None
SEE ALSO:
getDim, DMSetDimension
Source code at petsc4py/PETSc/DMDA.pyx:217
setDof(dof)
Set the number of degrees of freedom per vertex.
Not collective.
Parameters
dof (int) -- The number of degrees of freedom.
Return type
None
SEE ALSO:
getDof, DMDASetDof
Source code at petsc4py/PETSc/DMDA.pyx:246
setElementType(elem_type)
Set the element type to be returned by getElements.
Not collective.
SEE ALSO:
getElementType, DMDASetElementType
Source code at petsc4py/PETSc/DMDA.pyx:1036
Parameters
elem_type (ElementType | str)
Return type
None
setFieldName(field, name)
Set the name of individual field components.
Logically collective.
Parameters
• field (int) -- The field number for the DMDA (0, 1, ..., dof-1), where dof
indicates the number of degrees of freedom per node within the DMDA.
• name (str) -- The name of the field (component).
Return type
None
SEE ALSO:
getFieldName, DMDASetFieldName
Source code at petsc4py/PETSc/DMDA.pyx:675
setInterpolationType(interp_type)
Set the type of interpolation.
Logically collective.
You should call this on the coarser of the two DMDAs you pass to DM.createInterpolation.
Parameters
interp_type (InterpolationType) -- The interpolation type.
Return type
None
SEE ALSO:
getInterpolationType, DMDASetInterpolationType
Source code at petsc4py/PETSc/DMDA.pyx:999
setProcSizes(proc_sizes)
Set the number of processes in each dimension.
Logically collective.
Parameters
proc_sizes (DimsSpec) -- The number of processes in (x,), (x, y), or (x, y, z)
dimensions.
Return type
None
SEE ALSO:
getProcSizes, DMDASetNumProcs
Source code at petsc4py/PETSc/DMDA.pyx:334
setRefinementFactor(refine_x=2, refine_y=2, refine_z=2)
Set the ratios for the DMDA grid refinement.
Logically collective.
Parameters
• refine_x (int) -- Ratio of fine grid to coarse in x dimension.
• refine_y (int) -- Ratio of fine grid to coarse in y dimension.
• refine_z (int) -- Ratio of fine grid to coarse in z dimension.
Return type
None
SEE ALSO:
getRefinementFactor, DMDASetRefinementFactor
Source code at petsc4py/PETSc/DMDA.pyx:949
setSizes(sizes)
Set the number of grid points in each dimension.
Logically collective.
Parameters
sizes (DimsSpec) -- The global (x,), (x, y), or (x, y, z) size.
Return type
None
SEE ALSO:
getSizes, DMDASetSizes
Source code at petsc4py/PETSc/DMDA.pyx:284
setStencil(stencil_type, stencil_width)
Set the stencil type and width.
Not collective.
Parameters
• stencil_type (StencilType) -- The stencil type.
• stencil_width (int) -- The stencil width.
Return type
None
SEE ALSO:
setStencilWidth, setStencilType, DMDASetStencilType, DMDASetStencilWidth
Source code at petsc4py/PETSc/DMDA.pyx:506
setStencilType(stencil_type)
Set the stencil type.
Logically collective.
Parameters
• stype -- The stencil type.
• stencil_type (StencilType)
Return type
None
SEE ALSO:
getStencilType, setStencil, DMDASetStencilType
Source code at petsc4py/PETSc/DMDA.pyx:430
setStencilWidth(stencil_width)
Set the stencil width.
Logically collective.
Parameters
stencil_width (int) -- The stencil width.
Return type
None
SEE ALSO:
getStencilWidth, setStencil, DMDASetStencilWidth
Source code at petsc4py/PETSc/DMDA.pyx:468
setUniformCoordinates(xmin=0, xmax=1, ymin=0, ymax=1, zmin=0, zmax=1)
Set the DMDA coordinates to be a uniform grid.
Collective.
Parameters
• xmin (float) -- The minimum in the x dimension.
• xmax (float) -- The maximum in the x dimension.
• ymin (float) -- The minimum in the y dimension (value ignored for 1 dimensional
problems).
• ymax (float) -- The maximum in the y dimension (value ignored for 1 dimensional
problems).
• zmin (float) -- The minimum in the z dimension (value ignored for 1 or 2
dimensional problems).
• zmax (float) -- The maximum in the z dimension (value ignored for 1 or 2
dimensional problems).
Return type
None
SEE ALSO:
DMDASetUniformCoordinates
Source code at petsc4py/PETSc/DMDA.pyx:744
Attributes Documentation
boundary_type
Boundary types in each dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1123
corners
The lower left corner and size of local region in each dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1153
dim The grid dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1103
dof The number of DOFs associated with each stratum of the grid.
Source code at petsc4py/PETSc/DMDA.pyx:1108
ghost_corners
The lower left corner and size of local region in each dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1158
ghost_ranges
Ranges of local region, including ghost nodes.
Source code at petsc4py/PETSc/DMDA.pyx:1148
proc_sizes
The number of processes in each dimension in the global decomposition.
Source code at petsc4py/PETSc/DMDA.pyx:1118
ranges Ranges of the local region in each dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1143
sizes The global dimension.
Source code at petsc4py/PETSc/DMDA.pyx:1113
stencil
Stencil type and width.
Source code at petsc4py/PETSc/DMDA.pyx:1128
stencil_type
Stencil type.
Source code at petsc4py/PETSc/DMDA.pyx:1133
stencil_width
Elementwise stencil width.
Source code at petsc4py/PETSc/DMDA.pyx:1138
petsc4py.PETSc.DMInterpolation
class petsc4py.PETSc.DMInterpolation
Bases: object
Interpolation on a mesh.
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create a DMInterpolation context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the DMInterpolation context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ evaluate(dm, x[, v]) │ Calculate interpolated field values │
│ │ at the interpolation points. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCoordinates() │ Return the coordinates of each │
│ │ interpolation point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDim() │ Return the spatial dimension of the │
│ │ interpolation context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDof() │ Return the number of fields │
│ │ interpolated at a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVector() │ Return a Vec which can hold all the │
│ │ interpolated field values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreVector(vec) │ Restore a Vec which can hold all the │
│ │ interpolated field values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDim(dim) │ Set the spatial dimension for the │
│ │ interpolation context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDof(dof) │ Set the number of fields interpolated │
│ │ at a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp(dm[, redundantPoints, │ Compute spatial indices for point │
│ ignoreOutsideDomain]) │ location during interpolation. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create a DMInterpolation context.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to COMM_SELF.
Return type
Self
SEE ALSO:
destroy, DMInterpolationCreate
Source code at petsc4py/PETSc/DMUtils.pyx:13
destroy()
Destroy the DMInterpolation context.
Collective.
SEE ALSO:
create, DMInterpolationDestroy
Source code at petsc4py/PETSc/DMUtils.pyx:35
Return type
Self
evaluate(dm, x, v=None)
Calculate interpolated field values at the interpolation points.
Collective.
Parameters
• dm (DM) -- The DM.
• x (Vec) -- The local vector containing the field to be interpolated.
• v (Vec | None) -- A vector capable of holding the interpolated field values.
Return type
Vec
SEE ALSO:
DMInterpolationEvaluate
Source code at petsc4py/PETSc/DMUtils.pyx:48
getCoordinates()
Return the coordinates of each interpolation point.
Collective.
The local vector entries correspond to interpolation points lying on this process,
according to the associated DM.
SEE ALSO:
DMInterpolationGetCoordinates
Source code at petsc4py/PETSc/DMUtils.pyx:74
Return type
Vec
getDim()
Return the spatial dimension of the interpolation context.
Not collective.
SEE ALSO:
setDim, DMInterpolationGetDim
Source code at petsc4py/PETSc/DMUtils.pyx:92
Return type
int
getDof()
Return the number of fields interpolated at a point.
Not collective.
SEE ALSO:
setDof, DMInterpolationGetDof
Source code at petsc4py/PETSc/DMUtils.pyx:106
Return type
int
getVector()
Return a Vec which can hold all the interpolated field values.
Collective.
This vector should be returned using restoreVector.
SEE ALSO:
restoreVector, DMInterpolationGetVector
Source code at petsc4py/PETSc/DMUtils.pyx:185
Return type
Vec
restoreVector(vec)
Restore a Vec which can hold all the interpolated field values.
Collective.
Parameters
vec (Vec) -- A vector capable of holding the interpolated field values.
Return type
None
SEE ALSO:
getVector, DMInterpolationRestoreVector
Source code at petsc4py/PETSc/DMUtils.pyx:201
setDim(dim)
Set the spatial dimension for the interpolation context.
Not collective.
Parameters
dim (int) -- The spatial dimension.
Return type
None
SEE ALSO:
getDim, DMInterpolationSetDim
Source code at petsc4py/PETSc/DMUtils.pyx:120
setDof(dof)
Set the number of fields interpolated at a point.
Not collective.
Parameters
dof (int) -- The number of fields.
Return type
None
SEE ALSO:
getDof, DMInterpolationSetDof
Source code at petsc4py/PETSc/DMUtils.pyx:138
setUp(dm, redundantPoints=False, ignoreOutsideDomain=False)
Compute spatial indices for point location during interpolation.
Collective.
Parameters
• dm (DM) -- The DM for the function space used for interpolation.
• redundantPoints (bool) -- If True, all processes are passing in the same array of
points. Otherwise, points need to be communicated among processes.
• ignoreOutsideDomain (bool) -- Ignore points outside of the domain if True;
otherwise, return an error.
Return type
None
SEE ALSO:
DMInterpolationSetUp
Source code at petsc4py/PETSc/DMUtils.pyx:156
petsc4py.PETSc.DMLabel
class petsc4py.PETSc.DMLabel
Bases: Object
An object representing a subset of mesh entities from a DM.
Methods Summary
┌───────────────────────────────┬───────────────────────────────────────┐
│ addStrata(strata) │ Add new stratum values in a DMLabel. │
├───────────────────────────────┼───────────────────────────────────────┤
│ addStrataIS(iset) │ Add new stratum values in a DMLabel. │
├───────────────────────────────┼───────────────────────────────────────┤
│ addStratum(value) │ Add a new stratum value in a DMLabel. │
├───────────────────────────────┼───────────────────────────────────────┤
│ clearStratum(stratum) │ Remove a stratum. │
├───────────────────────────────┼───────────────────────────────────────┤
│ clearValue(point, value) │ Clear the value a label assigns to a │
│ │ point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ computeIndex() │ Create an index structure for │
│ │ membership determination. │
├───────────────────────────────┼───────────────────────────────────────┤
│ convertToSection() │ Return a Section and IS that encode │
│ │ the label. │
├───────────────────────────────┼───────────────────────────────────────┤
│ create(name[, comm]) │ Create a DMLabel object, which is a │
│ │ multimap. │
├───────────────────────────────┼───────────────────────────────────────┤
│ createIndex(pStart, pEnd) │ Create an index structure for │
│ │ membership determination. │
├───────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the label. │
├───────────────────────────────┼───────────────────────────────────────┤
│ destroyIndex() │ Destroy the index structure. │
├───────────────────────────────┼───────────────────────────────────────┤
│ distribute(sf) │ Create a new label pushed forward │
│ │ over the SF. │
├───────────────────────────────┼───────────────────────────────────────┤
│ duplicate() │ Duplicate the DMLabel. │
├───────────────────────────────┼───────────────────────────────────────┤
│ filter(start, end) │ Remove all points outside of [start, │
│ │ end). │
├───────────────────────────────┼───────────────────────────────────────┤
│ gather(sf) │ Gather all label values from leaves │
│ │ into roots. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getBounds() │ Return the smallest and largest point │
│ │ in the label. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getDefaultValue() │ Return the default value returned by │
│ │ getValue. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getNonEmptyStratumValuesIS() │ Return an IS of all values that the │
│ │ DMLabel takes. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getNumValues() │ Return the number of values that the │
│ │ DMLabel takes. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getStratumIS(stratum) │ Return an IS with the stratum points. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getStratumSize(stratum) │ Return the size of a stratum. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getValue(point) │ Return the value a label assigns to a │
│ │ point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getValueIS() │ Return an IS of all values that the │
│ │ DMLabel takes. │
├───────────────────────────────┼───────────────────────────────────────┤
│ hasPoint(point) │ Determine whether the label contains │
│ │ a point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ hasStratum(value) │ Determine whether points exist with │
│ │ the given value. │
├───────────────────────────────┼───────────────────────────────────────┤
│ hasValue(value) │ Determine whether a label assigns the │
│ │ value to any point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ insertIS(iset, value) │ Set all points in the IS to a value. │
├───────────────────────────────┼───────────────────────────────────────┤
│ permute(permutation) │ Create a new label with permuted │
│ │ points. │
├───────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Destroy internal data structures in │
│ │ the DMLabel. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setDefaultValue(value) │ Set the default value returned by │
│ │ getValue. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setStratumIS(stratum, iset) │ Set the stratum points using an IS. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setValue(point, value) │ Set the value a label assigns to a │
│ │ point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ stratumHasPoint(value, point) │ Return whether the stratum contains a │
│ │ point. │
├───────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the label. │
└───────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
addStrata(strata)
Add new stratum values in a DMLabel.
Not collective.
Parameters
strata (Sequence[int]) -- The stratum values.
Return type
None
SEE ALSO:
addStrataIS, addStratum, DMLabelAddStrata
Source code at petsc4py/PETSc/DMLabel.pyx:238
addStrataIS(iset)
Add new stratum values in a DMLabel.
Not collective.
Parameters
iset (IS) -- Index set with stratum values.
Return type
None
SEE ALSO:
addStrata, addStratum, DMLabelAddStrataIS
Source code at petsc4py/PETSc/DMLabel.pyx:258
addStratum(value)
Add a new stratum value in a DMLabel.
Not collective.
Parameters
value (int) -- The stratum value.
Return type
None
SEE ALSO:
addStrata, addStrataIS, DMLabelAddStratum
Source code at petsc4py/PETSc/DMLabel.pyx:220
clearStratum(stratum)
Remove a stratum.
Not collective.
Parameters
stratum (int) -- The stratum value.
Return type
None
SEE ALSO:
DMLabelClearStratum
Source code at petsc4py/PETSc/DMLabel.pyx:406
clearValue(point, value)
Clear the value a label assigns to a point.
Not collective.
Parameters
• point (int) -- The point.
• value (int) -- The point value.
Return type
None
SEE ALSO:
DMLabelClearValue
Source code at petsc4py/PETSc/DMLabel.pyx:199
computeIndex()
Create an index structure for membership determination.
Not collective.
Automatically determines the bounds.
SEE ALSO:
DMLabelComputeIndex
Source code at petsc4py/PETSc/DMLabel.pyx:424
Return type
None
convertToSection()
Return a Section and IS that encode the label.
Not collective.
SEE ALSO:
DMLabelConvertToSection
Source code at petsc4py/PETSc/DMLabel.pyx:607
Return type
tuple[Section, IS]
create(name, comm=None)
Create a DMLabel object, which is a multimap.
Collective.
Parameters
• name (str) -- The label name.
• comm (Comm | None) -- MPI communicator, defaults to COMM_SELF.
Return type
Self
SEE ALSO:
DMLabelCreate
Source code at petsc4py/PETSc/DMLabel.pyx:40
createIndex(pStart, pEnd)
Create an index structure for membership determination.
Not collective.
Parameters
• pStart (int) -- The smallest point.
• pEnd (int) -- The largest point + 1.
Return type
None
SEE ALSO:
destroyIndex, DMLabelCreateIndex
Source code at petsc4py/PETSc/DMLabel.pyx:438
destroy()
Destroy the label.
Collective.
SEE ALSO:
DMLabelDestroy
Source code at petsc4py/PETSc/DMLabel.pyx:8
Return type
Self
destroyIndex()
Destroy the index structure.
Not collective.
SEE ALSO:
createIndex, DMLabelDestroyIndex
Source code at petsc4py/PETSc/DMLabel.pyx:458
Return type
None
distribute(sf)
Create a new label pushed forward over the SF.
Collective.
Parameters
sf (SF) -- The map from old to new distribution.
Return type
DMLabel
SEE ALSO:
gather, DMLabelDistribute
Source code at petsc4py/PETSc/DMLabel.pyx:567
duplicate()
Duplicate the DMLabel.
Collective.
SEE ALSO:
DMLabelDuplicate
Source code at petsc4py/PETSc/DMLabel.pyx:65
Return type
DMLabel
filter(start, end)
Remove all points outside of [start, end).
Not collective.
Parameters
• start (int) -- The first point kept.
• end (int) -- One more than the last point kept.
Return type
None
SEE ALSO:
DMLabelFilter
Source code at petsc4py/PETSc/DMLabel.pyx:528
gather(sf)
Gather all label values from leaves into roots.
Collective.
This is the inverse operation to distribute.
Parameters
sf (SF) -- The SF communication map.
Return type
DMLabel
SEE ALSO:
distribute, DMLabelGather
Source code at petsc4py/PETSc/DMLabel.pyx:586
getBounds()
Return the smallest and largest point in the label.
Not collective.
The returned values are the smallest point and the largest point + 1.
SEE ALSO:
DMLabelGetBounds
Source code at petsc4py/PETSc/DMLabel.pyx:512
Return type
tuple[int, int]
getDefaultValue()
Return the default value returned by getValue.
Not collective.
The default value is returned if a point has not been explicitly given a value. When a
label is created, it is initialized to -1.
SEE ALSO:
setDefaultValue, DMLabelGetDefaultValue
Source code at petsc4py/PETSc/DMLabel.pyx:161
Return type
int
getNonEmptyStratumValuesIS()
Return an IS of all values that the DMLabel takes.
Not collective.
SEE ALSO:
DMLabelGetNonEmptyStratumValuesIS
Source code at petsc4py/PETSc/DMLabel.pyx:622
Return type
IS
getNumValues()
Return the number of values that the DMLabel takes.
Not collective.
SEE ALSO:
DMLabelGetNumValues
Source code at petsc4py/PETSc/DMLabel.pyx:275
Return type
int
getStratumIS(stratum)
Return an IS with the stratum points.
Not collective.
Parameters
stratum (int) -- The stratum value.
Return type
IS
SEE ALSO:
setStratumIS, DMLabelGetStratumIS
Source code at petsc4py/PETSc/DMLabel.pyx:366
getStratumSize(stratum)
Return the size of a stratum.
Not collective.
Parameters
stratum (int) -- The stratum value.
Return type
int
SEE ALSO:
DMLabelGetStratumSize
Source code at petsc4py/PETSc/DMLabel.pyx:346
getValue(point)
Return the value a label assigns to a point.
Not collective.
If no value was assigned, a default value will be returned The default value, initially -1,
can be changed with setDefaultValue.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
setValue, setDefaultValue, DMLabelGetValue
Source code at petsc4py/PETSc/DMLabel.pyx:137
getValueIS()
Return an IS of all values that the DMLabel takes.
Not collective.
SEE ALSO:
DMLabelGetValueIS
Source code at petsc4py/PETSc/DMLabel.pyx:289
Return type
IS
hasPoint(point)
Determine whether the label contains a point.
Not collective.
The user must call createIndex before this function.
Parameters
point (int) -- The point.
Return type
bool
SEE ALSO:
hasValue, DMLabelHasPoint
Source code at petsc4py/PETSc/DMLabel.pyx:490
hasStratum(value)
Determine whether points exist with the given value.
Not collective.
Parameters
value (int) -- The stratum value.
Return type
bool
SEE ALSO:
DMLabelHasStratum
Source code at petsc4py/PETSc/DMLabel.pyx:326
hasValue(value)
Determine whether a label assigns the value to any point.
Not collective.
Parameters
value (int) -- The value.
Return type
bool
SEE ALSO:
hasPoint, DMLabelHasValue
Source code at petsc4py/PETSc/DMLabel.pyx:470
insertIS(iset, value)
Set all points in the IS to a value.
Not collective.
Parameters
• iset (IS) -- The point IS.
• value (int) -- The point value.
Return type
Self
SEE ALSO:
DMLabelInsertIS
Source code at petsc4py/PETSc/DMLabel.pyx:91
permute(permutation)
Create a new label with permuted points.
Not collective.
Parameters
permutation (IS) -- The point permutation.
Return type
DMLabel
SEE ALSO:
DMLabelPermute
Source code at petsc4py/PETSc/DMLabel.pyx:548
reset()
Destroy internal data structures in the DMLabel.
Not collective.
SEE ALSO:
DMLabelReset
Source code at petsc4py/PETSc/DMLabel.pyx:79
Return type
None
setDefaultValue(value)
Set the default value returned by getValue.
Not collective.
The value is used if a point has not been explicitly given a value. When a label is
created, the default value is initialized to -1.
Parameters
value (int) -- The default value.
Return type
None
SEE ALSO:
getDefaultValue, DMLabelSetDefaultValue
Source code at petsc4py/PETSc/DMLabel.pyx:178
setStratumIS(stratum, iset)
Set the stratum points using an IS.
Not collective.
Parameters
• stratum (int) -- The stratum value.
• iset (IS) -- The stratum points.
Return type
None
SEE ALSO:
getStratumIS, DMLabelSetStratumIS
Source code at petsc4py/PETSc/DMLabel.pyx:386
setValue(point, value)
Set the value a label assigns to a point.
Not collective.
If the value is the same as the label's default value (which is initially -1, and can be
changed with setDefaultValue), this function will do nothing.
Parameters
• point (int) -- The point.
• value (int) -- The point value.
Return type
None
SEE ALSO:
getValue, setDefaultValue, DMLabelSetValue
Source code at petsc4py/PETSc/DMLabel.pyx:112
stratumHasPoint(value, point)
Return whether the stratum contains a point.
Not collective.
Parameters
• value (int) -- The stratum value.
• point (int) -- The point.
Return type
bool
SEE ALSO:
DMLabelStratumHasPoint
Source code at petsc4py/PETSc/DMLabel.pyx:303
view(viewer=None)
View the label.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
DMLabelView
Source code at petsc4py/PETSc/DMLabel.pyx:21
petsc4py.PETSc.DMPlex
class petsc4py.PETSc.DMPlex
Bases: DM
Encapsulate an unstructured mesh.
DMPlex encapsulates both topology and geometry. It is capable of parallel refinement and
coarsening (using Pragmatic or ParMmg) and parallel redistribution for load balancing.
Methods Summary
┌─────────────────────────────────────────────┬───────────────────────────────────────┐
│ computeCellGeometryFVM(cell) │ Compute the volume for a given cell. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeGradientClementInterpolant(locX, │ Return the L2 projection of the │
│ locC) │ cellwise gradient of a function onto │
│ │ P1. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ constructGhostCells([labelName]) │ Construct ghost cells which connect │
│ │ to every boundary face. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ coordinatesLoad(viewer, sfxc) │ Load coordinates into this DMPlex │
│ │ object. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ coordinatesView(viewer) │ Save DMPlex coordinates into a file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a DMPlex object, which │
│ │ encapsulates an unstructured mesh. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createBoxMesh(faces[, lower, upper, │ Create a mesh on the tensor product │
│ ...]) │ of intervals. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createBoxSurfaceMesh(faces[, lower, │ Create a mesh on the surface of a box │
│ upper, ...]) │ mesh using tensor cells. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createCGNS(cgid[, interpolate, comm]) │ Create a DMPlex mesh from a CGNS │
│ │ file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createCGNSFromFile(filename[, │ "Create a DMPlex mesh from a CGNS │
│ interpolate, comm]) │ file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createClosureIndex(sec) │ Calculate an index for sec for the │
│ │ closure operation. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createCoarsePointIS() │ Create an IS covering the coarse │
│ │ DMPlex chart with the fine points as │
│ │ data. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createCohesiveSubmesh(hasLagrange, │ Extract the hypersurface defined by │
│ value) │ one face of the cohesive cells. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createExodus(exoid[, interpolate, │ Create a DMPlex mesh from an ExodusII │
│ comm]) │ file ID. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createExodusFromFile(filename[, ...]) │ Create a DMPlex mesh from an ExodusII │
│ │ file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createFromCellList(dim, cells, coords[, │ Create a DMPlex from a list of │
│ ...]) │ vertices for each cell on process 0. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createFromFile(filename[, plexname, │ Create DMPlex from a file. │
│ ...]) │ │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createGmsh(viewer[, interpolate, comm]) │ Create a DMPlex mesh from a Gmsh file │
│ │ viewer. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createPointNumbering() │ Create a global numbering for all │
│ │ points. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ createSection(numComp, numDof[, │ Create a Section based upon the DOF │
│ bcField, ...]) │ layout specification provided. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distribute([overlap]) │ Distribute the mesh and any │
│ │ associated sections. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributeField(sf, sec, vec[, newsec, │ Distribute field data with a with a │
│ newvec]) │ given SF. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributeGetDefault() │ Return a flag indicating whether the │
│ │ DM should be distributed by default. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributeOverlap([overlap]) │ Add partition overlap to a │
│ │ distributed non-overlapping DMPlex. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributeSetDefault(flag) │ Set flag indicating whether the │
│ │ DMPlex should be distributed by │
│ │ default. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributionGetName() │ Retrieve the name of the specific │
│ │ parallel distribution. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ distributionSetName(name) │ Set the name of the specific parallel │
│ │ distribution. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ generate(boundary[, name, interpolate]) │ Generate a mesh. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getAdjacency(p) │ Return all points adjacent to the │
│ │ given point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getAdjacencyUseAnchors() │ Query whether adjacency in the mesh │
│ │ uses the point-to-point constraints. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getCellNumbering() │ Return a global cell numbering for │
│ │ all cells on this process. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getCellType(p) │ Return the polytope type of a given │
│ │ cell. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getCellTypeLabel() │ Return the DMLabel recording the │
│ │ polytope type of each cell. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getChart() │ Return the interval for all mesh │
│ │ points [pStart, pEnd). │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getCone(p) │ Return the points on the in-edges for │
│ │ this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getConeOrientation(p) │ Return the orientations on the │
│ │ in-edges for this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getConeSize(p) │ Return the number of in-edges for │
│ │ this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getDepth() │ Return the depth of the DAG │
│ │ representing this mesh. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getDepthStratum(svalue) │ Return the bounds [start, end) for │
│ │ all points at a certain depth. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFullJoin(points) │ Return an array for the join of the │
│ │ set of points. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHeightStratum(svalue) │ Return the bounds [start, end) for │
│ │ all points at a certain height. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getJoin(points) │ Return an array for the join of the │
│ │ set of points. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxSizes() │ Return the maximum number of in-edges │
│ │ and out-edges of the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMeet(points) │ Return an array for the meet of the │
│ │ set of points. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMinRadius() │ Return the minimum distance from any │
│ │ cell centroid to a face. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getOrdering(otype) │ Calculate a reordering of the mesh. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPartitioner() │ Return the mesh partitioner. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointDepth(point) │ Return the depth of a given point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointGlobal(point) │ Return location of point data in │
│ │ global Vec. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointGlobalField(point, field) │ Return location of point field data │
│ │ in global Vec. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointHeight(point) │ Return the height of a given point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointLocal(point) │ Return location of point data in │
│ │ local Vec. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPointLocalField(point, field) │ Return location of point field data │
│ │ in local Vec. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getRefinementLimit() │ Retrieve the maximum cell volume for │
│ │ refinement. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getRefinementUniform() │ Retrieve the flag for uniform │
│ │ refinement. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSubpointIS() │ Return an IS covering the entire │
│ │ subdm chart. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSubpointMap() │ Return a DMLabel with point dimension │
│ │ as values. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSupport(p) │ Return the points on the out-edges │
│ │ for this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSupportSize(p) │ Return the number of out-edges for │
│ │ this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getTransitiveClosure(p[, useCone]) │ Return the points and orientations on │
│ │ the transitive closure of this point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getVecClosure(sec, vec, point) │ Return an array of the values on the │
│ │ closure of a point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ getVertexNumbering() │ Return a global vertex numbering for │
│ │ all vertices on this process. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ globalVectorLoad(viewer, sectiondm, sf, │ Load on-disk vector data into a │
│ vec) │ global vector. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ globalVectorView(viewer, sectiondm, │ Save a global vector. │
│ vec) │ │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ insertCone(p, conePos, conePoint) │ DMPlexInsertCone - Insert a point │
│ │ into the in-edges for the point p in │
│ │ the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ insertConeOrientation(p, conePos, ...) │ Insert a point orientation for the │
│ │ in-edge for the point p in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ interpolate() │ Convert to a mesh with all │
│ │ intermediate faces, edges, etc. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ isDistributed() │ Return the flag indicating if the │
│ │ mesh is distributed. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ isSimplex() │ Return the flag indicating if the │
│ │ first cell is a simplex. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ labelCohesiveComplete(label, bdlabel, │ Add all other mesh pieces to complete │
│ ...) │ the surface. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ labelComplete(label) │ Add the transitive closure to the │
│ │ surface. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ labelsLoad(viewer, sfxc) │ Load labels into this DMPlex object. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ labelsView(viewer) │ Save DMPlex labels into a file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ localVectorLoad(viewer, sectiondm, sf, │ Load on-disk vector data into a local │
│ vec) │ vector. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ localVectorView(viewer, sectiondm, vec) │ Save a local vector. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ markBoundaryFaces(label[, value]) │ Mark all faces on the boundary. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricAverage2(metric1, metric2, │ Compute and return the unweighted │
│ metricAvg) │ average of two metrics. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricAverage3(metric1, metric2, │ Compute and return the unweighted │
│ metric3, ...) │ average of three metrics. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricCreate([field]) │ Create a Riemannian metric field. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricCreateIsotropic(indicator[, │ Construct an isotropic metric from an │
│ field]) │ error indicator. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricCreateUniform(alpha[, field]) │ Construct a uniform isotropic metric. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricDeterminantCreate([field]) │ Create the determinant field for a │
│ │ Riemannian metric. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricEnforceSPD(metric, ometric, │ Enforce symmetric │
│ determinant) │ positive-definiteness of a metric. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetGradationFactor() │ Return the metric gradation factor. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetHausdorffNumber() │ Return the metric Hausdorff number. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetMaximumAnisotropy() │ Return the maximum tolerated metric │
│ │ anisotropy. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetMaximumMagnitude() │ Return the maximum tolerated metric │
│ │ magnitude. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetMinimumMagnitude() │ Return the minimum tolerated metric │
│ │ magnitude. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetNormalizationOrder() │ Return the order p for L-p │
│ │ normalization. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetNumIterations() │ Return the number of parallel │
│ │ adaptation iterations. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetTargetComplexity() │ Return the target metric complexity. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricGetVerbosity() │ Return the verbosity of the mesh │
│ │ adaptation package. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricIntersection2(metric1, metric2, │ Compute and return the intersection │
│ metricInt) │ of two metrics. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricIntersection3(metric1, metric2, │ Compute the intersection of three │
│ ...) │ metrics. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricIsIsotropic() │ Return the flag indicating whether │
│ │ the metric is isotropic or not. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricIsUniform() │ Return the flag indicating whether │
│ │ the metric is uniform or not. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricNoInsertion() │ Return the flag indicating whether │
│ │ node insertion and deletion are │
│ │ turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricNoMovement() │ Return the flag indicating whether │
│ │ node movement is turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricNoSurf() │ Return the flag indicating whether │
│ │ surface modification is turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricNoSwapping() │ Return the flag indicating whether │
│ │ facet swapping is turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricNormalize(metric, ometric, │ Apply L-p normalization to a metric. │
│ determinant) │ │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricRestrictAnisotropyFirst() │ Return true if anisotropy is │
│ │ restricted before normalization. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetFromOptions() │ Configure the object from the options │
│ │ database. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetGradationFactor(beta) │ Set the metric gradation factor. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetHausdorffNumber(hausd) │ Set the metric Hausdorff number. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetIsotropic(isotropic) │ Record whether the metric is │
│ │ isotropic or not. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetMaximumAnisotropy(a_max) │ Set the maximum tolerated metric │
│ │ anisotropy. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetMaximumMagnitude(h_max) │ Set the maximum tolerated metric │
│ │ magnitude. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetMinimumMagnitude(h_min) │ Set the minimum tolerated metric │
│ │ magnitude. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNoInsertion(noInsert) │ Set the flag indicating whether node │
│ │ insertion should be turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNoMovement(noMove) │ Set the flag indicating whether node │
│ │ movement should be turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNoSurf(noSurf) │ Set the flag indicating whether │
│ │ surface modification should be turned │
│ │ off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNoSwapping(noSwap) │ Set the flag indicating whether facet │
│ │ swapping should be turned off. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNormalizationOrder(p) │ Set the order p for L-p │
│ │ normalization. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetNumIterations(numIter) │ Set the number of parallel adaptation │
│ │ iterations. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetRestrictAnisotropyFirst(...) │ Record whether anisotropy is be │
│ │ restricted before normalization or │
│ │ after. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetTargetComplexity(targetComplexity) │ Set the target metric complexity. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetUniform(uniform) │ Record whether the metric is uniform │
│ │ or not. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ metricSetVerbosity(verbosity) │ Set the verbosity of the mesh │
│ │ adaptation package. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ orient() │ Give a consistent orientation to the │
│ │ input mesh. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ permute(perm) │ Reorder the mesh according to the │
│ │ input permutation. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ rebalanceSharedPoints([entityDepth, ...]) │ Redistribute shared points in order │
│ │ to achieve better balancing. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ reorderGetDefault() │ Return flag indicating whether the │
│ │ DMPlex should be reordered by │
│ │ default. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ reorderSetDefault(flag) │ Set flag indicating whether the DM │
│ │ should be reordered by default. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ sectionLoad(viewer, sectiondm, sfxc) │ Load section into a DM. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ sectionView(viewer, sectiondm) │ Save a section associated with a │
│ │ DMPlex. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setAdjacencyUseAnchors([useAnchors]) │ Define adjacency in the mesh using │
│ │ the point-to-point constraints. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCellType(p, ctype) │ Set the polytope type of a given │
│ │ cell. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setChart(pStart, pEnd) │ Set the interval for all mesh points │
│ │ [pStart, pEnd). │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCone(p, cone[, orientation]) │ Set the points on the in-edges for │
│ │ this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConeOrientation(p, orientation) │ Set the orientations on the in-edges │
│ │ for this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConeSize(p, size) │ Set the number of in-edges for this │
│ │ point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMatClosure(sec, gsec, mat, point, │ Set an array of the values on the │
│ values) │ closure of point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPartitioner(part) │ Set the mesh partitioner. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setRefinementLimit(refinementLimit) │ Set the maximum cell volume for │
│ │ refinement. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setRefinementUniform([refinementUniform]) │ Set the flag for uniform refinement. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSupport(p, supp) │ Set the points on the out-edges for │
│ │ this point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSupportSize(p, size) │ Set the number of out-edges for this │
│ │ point in the DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setTetGenOptions(opts) │ Set the options used for the Tetgen │
│ │ mesh generator. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setTriangleOptions(opts) │ Set the options used for the Triangle │
│ │ mesh generator. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ setVecClosure(sec, vec, point, values[, │ Set an array of the values on the │
│ addv]) │ closure of point. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ stratify() │ Calculate the strata of DAG. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ symmetrize() │ Create support (out-edge) information │
│ │ from cone (in-edge) information. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ topologyLoad(viewer) │ Load a topology into this DMPlex │
│ │ object. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ topologyView(viewer) │ Save a DMPlex topology into a file. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ uninterpolate() │ Convert to a mesh with only cells and │
│ │ vertices. │
├─────────────────────────────────────────────┼───────────────────────────────────────┤
│ vecGetClosure(sec, vec, p) │ Return an array of values on the │
│ │ closure of p. │
└─────────────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
computeCellGeometryFVM(cell)
Compute the volume for a given cell.
Not collective.
Parameters
cell (int) -- The cell.
Returns
• volume (float) -- The cell volume.
• centroid (ArrayReal) -- The cell centroid.
• normal (ArrayReal) -- The cell normal, if appropriate.
Return type
tuple[float, ArrayReal, ArrayReal]
SEE ALSO:
DMPlex, DM.getCoordinateSection, DM.getCoordinates, DMPlexComputeCellGeometryFVM
Source code at petsc4py/PETSc/DMPlex.pyx:2217
computeGradientClementInterpolant(locX, locC)
Return the L2 projection of the cellwise gradient of a function onto P1.
Collective.
Parameters
• locX (Vec) -- The coefficient vector of the function.
• locC (Vec) -- The output Vec which holds the Clement interpolant of the gradient.
Return type
Vec
SEE ALSO:
DM, DMPlex, DMPlexComputeGradientClementInterpolant
Source code at petsc4py/PETSc/DMPlex.pyx:3151
constructGhostCells(labelName=None)
Construct ghost cells which connect to every boundary face.
Collective.
Parameters
labelName (str | None) -- The name of the label specifying the boundary faces.
Defaults to "Face Sets".
Returns
numGhostCells -- The number of ghost cells added to the DMPlex.
Return type
int
SEE ALSO:
DM, DMPlex, DM.create, DMPlexConstructGhostCells
Source code at petsc4py/PETSc/DMPlex.pyx:2249
coordinatesLoad(viewer, sfxc)
Load coordinates into this DMPlex object.
Collective.
Parameters
• viewer (Viewer) -- The Viewer for the saved coordinates.
• sfxc (SF) -- The SF returned by topologyLoad.
Return type
None
SEE ALSO:
DM, DMPlex, DM.load, DMPlex.topologyLoad, DMPlex.labelsLoad, DM.view, SF, Viewer, ‐
DMPlexCoordinatesLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3324
coordinatesView(viewer)
Save DMPlex coordinates into a file.
Collective.
Parameters
viewer (Viewer) -- The Viewer for saving.
Return type
None
SEE ALSO:
DM, DMPlex, DM.view, DMPlex.topologyView, DMPlex.labelsView, DMPlex.coordinatesLoad,
Viewer, DMPlexCoordinatesView
Source code at petsc4py/PETSc/DMPlex.pyx:3191
create(comm=None)
Create a DMPlex object, which encapsulates an unstructured mesh.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DM.create, DM.setType, DMPlexCreate
Source code at petsc4py/PETSc/DMPlex.pyx:14
createBoxMesh(faces, lower=(0, 0, 0), upper=(1, 1, 1), simplex=True, periodic=False,
interpolate=True, localizationHeight=0, sparseLocalize=True, comm=None)
Create a mesh on the tensor product of intervals.
Collective.
Parameters
• faces (Sequence[int]) -- Number of faces per dimension, or None for the default.
• lower (Sequence[float] | None) -- The lower left corner.
• upper (Sequence[float] | None) -- The upper right corner.
• simplex (bool | None) -- True for simplices, False for tensor cells.
• periodic (Sequence | str | int | bool | None) -- The boundary type for the X, Y, Z
direction, or None for DM.BoundaryType.NONE.
• interpolate (bool | None) -- Flag to create intermediate mesh entities (edges,
faces).
• localizationHeight (int | None) -- Flag to localize edges and faces in addition to
cells; only significant for periodic meshes.
• sparseLocalize (bool | None) -- Flag to localize coordinates only for cells near
the periodic boundary; only significant for periodic meshes.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DM.setFromOptions, DMPlex.createFromFile, DM.setType, DM.create, ‐
DMPlexCreateBoxMesh
Source code at petsc4py/PETSc/DMPlex.pyx:90
createBoxSurfaceMesh(faces, lower=(0, 0, 0), upper=(1, 1, 1), interpolate=True, comm=None)
Create a mesh on the surface of a box mesh using tensor cells.
Collective.
Parameters
• faces (Sequence[int]) -- Number of faces per dimension, or None for the default.
• lower (Sequence[float] | None) -- The lower left corner.
• upper (Sequence[float] | None) -- The upper right corner.
• interpolate (bool | None) -- Flag to create intermediate mesh pieces (edges,
faces).
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DM.setFromOptions, DMPlex.createBoxMesh, DMPlex.createFromFile, DM.setType,
DM.create, DMPlexCreateBoxSurfaceMesh
Source code at petsc4py/PETSc/DMPlex.pyx:149
createCGNS(cgid, interpolate=True, comm=None)
Create a DMPlex mesh from a CGNS file.
Collective.
Parameters
• cgid (int) -- The CG id associated with a file and obtained using cg_open.
• interpolate (bool | None) -- Create faces and edges in the mesh.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.createCGNSFromFile, DMPlex.createExodus, ‐
DMPlexCreateCGNS
Source code at petsc4py/PETSc/DMPlex.pyx:226
createCGNSFromFile(filename, interpolate=True, comm=None)
"Create a DMPlex mesh from a CGNS file.
Collective.
Parameters
• filename (str) -- The name of the CGNS file.
• interpolate (bool | None) -- Create faces and edges in the mesh.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.createCGNS, DMPlex.createExodus, DMPlexCreateCGNS
Source code at petsc4py/PETSc/DMPlex.pyx:254
createClosureIndex(sec)
Calculate an index for sec for the closure operation.
Not collective.
Parameters
sec (Section) -- The Section describing the layout in the local vector, or None to
use the default section.
Return type
None
SEE ALSO:
DM, DMPlex, Section, DMPlex.vecGetClosure, DMPlexCreateClosureIndex
Source code at petsc4py/PETSc/DMPlex.pyx:2031
createCoarsePointIS()
Create an IS covering the coarse DMPlex chart with the fine points as data.
Collective.
Returns
fpointIS -- The IS of all the fine points which exist in the original coarse mesh.
Return type
IS
SEE ALSO:
DM, DMPlex, IS, DM.refine, DMPlex.setRefinementUniform, DMPlexCreateCoarsePointIS
Source code at petsc4py/PETSc/DMPlex.pyx:1817
createCohesiveSubmesh(hasLagrange, value)
Extract the hypersurface defined by one face of the cohesive cells.
Collective.
Parameters
• hasLagrange (bool) -- Flag indicating whether the mesh has Lagrange dofs in the
cohesive cells.
• value (int) -- A label value.
Return type
DMPlex
SEE ALSO:
DM, DMPlex, DMPlexCreateCohesiveSubmesh
Source code at petsc4py/PETSc/DMPlex.pyx:377
createExodus(exoid, interpolate=True, comm=None)
Create a DMPlex mesh from an ExodusII file ID.
Collective.
Parameters
• exoid (int) -- The ExodusII id associated with a file obtained using ex_open.
• interpolate (bool | None) -- Create faces and edges in the mesh,
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DM.create, DMPlexCreateExodus
Source code at petsc4py/PETSc/DMPlex.pyx:312
createExodusFromFile(filename, interpolate=True, comm=None)
Create a DMPlex mesh from an ExodusII file.
Collective.
Parameters
• filename (str) -- The name of the ExodusII file.
• interpolate (bool | None) -- Create faces and edges in the mesh.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DM.create, DMPlex.createExodus, DMPlexCreateExodusFromFile
Source code at petsc4py/PETSc/DMPlex.pyx:283
createFromCellList(dim, cells, coords, interpolate=True, comm=None)
Create a DMPlex from a list of vertices for each cell on process 0.
Collective.
Parameters
• dim (int) -- The topological dimension of the mesh.
• cells (Sequence[int]) -- An array of number of cells times number of vertices on
each cell.
• coords (Sequence[float]) -- An array of number of vertices times spatial dimension
for coordinates.
• interpolate (bool | None) -- Flag to interpolate the mesh.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.interpolate, DMPlexCreateFromCellListPetsc
Source code at petsc4py/PETSc/DMPlex.pyx:35
createFromFile(filename, plexname='unnamed', interpolate=True, comm=None)
Create DMPlex from a file.
Collective.
Parameters
• filename (str) -- A file name.
• plexname (str | None) -- The name of the resulting DMPlex, also used for
intra-datafile lookup by some formats.
• interpolate (bool | None) -- Flag to create intermediate mesh pieces (edges,
faces).
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DM, DMPlex, DMPlex.createFromCellList, DMPlex.create, Object.setName, DM.view, DM.load,
Working with PETSc options, DMPlexCreateFromFile
Source code at petsc4py/PETSc/DMPlex.pyx:192
createGmsh(viewer, interpolate=True, comm=None)
Create a DMPlex mesh from a Gmsh file viewer.
Collective.
Parameters
• viewer (Viewer) -- The Viewer associated with a Gmsh file.
• interpolate (bool | None) -- Create faces and edges in the mesh.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
Notes
-dm_plex_gmsh_hybrid forces triangular prisms to use tensor order.
-dm_plex_gmsh_periodic allows for reading Gmsh periodic section.
-dm_plex_gmsh_highorder allows for generating high-order coordinates.
-dm_plex_gmsh_project projects high-order coordinates to a different space, use the prefix
-dm_plex_gmsh_project_ to define the space.
-dm_plex_gmsh_use_regions generates labels with region names.
-dm_plex_gmsh_mark_vertices adds vertices to generated labels.
-dm_plex_gmsh_multiple_tags allows multiple tags for default labels.
-dm_plex_gmsh_spacedim <d> embedding space dimension.
SEE ALSO:
DM, DMPlex, DM.create, Working with PETSc options, DMPlexCreateGmsh
Source code at petsc4py/PETSc/DMPlex.pyx:339
createPointNumbering()
Create a global numbering for all points.
Collective.
SEE ALSO:
DM, DMPlex, DMPlex.getCellNumbering, DMPlexCreatePointNumbering
Source code at petsc4py/PETSc/DMPlex.pyx:915
Return type
IS
createSection(numComp, numDof, bcField=None, bcComps=None, bcPoints=None, perm=None)
Create a Section based upon the DOF layout specification provided.
Not collective.
Parameters
• numComp (Sequence[int]) -- An array of size numFields holding the number of
components per field.
• numDof (Sequence[int]) -- An array of size numFields*(dim+1) holding the number of
DOFs per field on a mesh piece of dimension dim.
• bcField (Sequence[int] | None) -- An array of size numBC giving the field number
for each boundary condition, where numBC is the number of boundary conditions.
• bcComps (Sequence[IS] | None) -- An array of size numBC giving an IS holding the
field components to which each boundary condition applies.
• bcPoints (Sequence[IS] | None) -- An array of size numBC giving an IS holding the
DMPlex points to which each boundary condition applies.
• perm (IS | None) -- Permutation of the chart.
Return type
Section
SEE ALSO:
DM, DMPlex, DMPlex.create, Section.create, Section.setPermutation, DMPlexCreateSection
Source code at petsc4py/PETSc/DMPlex.pyx:1837
distribute(overlap=0)
Distribute the mesh and any associated sections.
Collective.
Parameters
overlap (int | None) -- The overlap of partitions.
Returns
sf -- The SF used for point distribution, or None if not distributed.
Return type
SF or None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlexDistribute
Source code at petsc4py/PETSc/DMPlex.pyx:1561
distributeField(sf, sec, vec, newsec=None, newvec=None)
Distribute field data with a with a given SF.
Collective.
Parameters
• sf (SF) -- The SF describing the communication pattern.
• sec (Section) -- The Section for existing data layout.
• vec (Vec) -- The existing data in a local vector.
• newsec (Section | None) -- The SF describing the new data layout.
• newvec (Vec | None) -- The new data in a local vector.
Returns
• newSection (Section) -- The SF describing the new data layout.
• newVec (Vec) -- The new data in a local vector.
Return type
tuple[Section, Vec]
SEE ALSO:
DMPlex, DMPlex.distribute, DMPlexDistributeField
Source code at petsc4py/PETSc/DMPlex.pyx:1758
distributeGetDefault()
Return a flag indicating whether the DM should be distributed by default.
Not collective.
Returns
dist -- Flag indicating whether the DMPlex should be distributed by default.
Return type
bool
SEE ALSO:
DM, DMPlex, DMPlex.distributeSetDefault, DMPlex.distribute, DMPlexDistributeGetDefault
Source code at petsc4py/PETSc/DMPlex.pyx:1647
distributeOverlap(overlap=0)
Add partition overlap to a distributed non-overlapping DMPlex.
Collective.
Parameters
overlap (int | None) -- The overlap of partitions (the same on all ranks).
Returns
sf -- The SF used for point distribution.
Return type
SF
SEE ALSO:
DM, DMPlex, SF, DMPlex.create, DMPlex.distribute, DMPlexDistributeOverlap
Source code at petsc4py/PETSc/DMPlex.pyx:1589
distributeSetDefault(flag)
Set flag indicating whether the DMPlex should be distributed by default.
Logically collective.
Parameters
flag (bool) -- Flag indicating whether the DMPlex should be distributed by default.
Return type
None
SEE ALSO:
DMPlex, DMPlex.distributeGetDefault, DMPlex.distribute, DMPlexDistributeSetDefault
Source code at petsc4py/PETSc/DMPlex.pyx:1667
distributionGetName()
Retrieve the name of the specific parallel distribution.
Not collective.
Returns
name -- The name of the specific parallel distribution.
Return type
str
SEE ALSO:
DMPlex, DMPlex.distributionSetName, DMPlex.topologyView, DMPlex.topologyLoad, ‐
DMPlexDistributionGetName
Source code at petsc4py/PETSc/DMPlex.pyx:1708
distributionSetName(name)
Set the name of the specific parallel distribution.
Logically collective.
Parameters
name (str) -- The name of the specific parallel distribution.
Return type
None
SEE ALSO:
DMPlex, DMPlex.distributionGetName, DMPlex.topologyView, DMPlex.topologyLoad, ‐
DMPlexDistributionSetName
Source code at petsc4py/PETSc/DMPlex.pyx:1687
generate(boundary, name=None, interpolate=True)
Generate a mesh.
Not collective.
Parameters
• boundary (DMPlex) -- The DMPlex boundary object.
• name (str | None) -- The mesh generation package name.
• interpolate (bool | None) -- Flag to create intermediate mesh elements.
Return type
Self
SEE ALSO:
DM, DMPlex, DMPlex.create, DM.refine, Working with PETSc options, DMPlexGenerate
Source code at petsc4py/PETSc/DMPlex.pyx:1284
getAdjacency(p)
Return all points adjacent to the given point.
Not collective.
Parameters
p (int) -- The point.
Return type
ArrayInt
SEE ALSO:
DMPlex, DMPlex.distribute, DMPlexGetAdjacency
Source code at petsc4py/PETSc/DMPlex.pyx:1467
getAdjacencyUseAnchors()
Query whether adjacency in the mesh uses the point-to-point constraints.
Not collective.
SEE ALSO:
DMPlex, DMPlex.getAdjacency, DMPlex.distribute, DMPlexGetAdjacencyUseAnchors
Source code at petsc4py/PETSc/DMPlex.pyx:1452
Return type
bool
getCellNumbering()
Return a global cell numbering for all cells on this process.
Collective the first time it is called.
SEE ALSO:
DM, DMPlex, DMPlex.getVertexNumbering, DMPlexGetCellNumbering
Source code at petsc4py/PETSc/DMPlex.pyx:885
Return type
IS
getCellType(p)
Return the polytope type of a given cell.
Not collective.
Parameters
p (int) -- The cell.
Return type
PolytopeType
SEE ALSO:
DM, DMPlex, DM.PolytopeType, DMPlex.getCellTypeLabel, DMPlex.getDepth, DMPlexGetCellType
Source code at petsc4py/PETSc/DMPlex.pyx:685
getCellTypeLabel()
Return the DMLabel recording the polytope type of each cell.
Not collective.
SEE ALSO:
DM, DMPlex, DMPlex.getCellType, DM.createLabel, DMPlexGetCellTypeLabel
Source code at petsc4py/PETSc/DMPlex.pyx:706
Return type
DMLabel
getChart()
Return the interval for all mesh points [pStart, pEnd).
Not collective.
Returns
• pStart (int) -- The first mesh point.
• pEnd (int) -- The upper bound for mesh points.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setChart, DMPlexGetChart
Source code at petsc4py/PETSc/DMPlex.pyx:400
getCone(p)
Return the points on the in-edges for this point in the DAG.
Not collective.
Parameters
p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.getConeSize, DMPlex.setCone, DMPlex.setChart, DMPlexGetCone
Source code at petsc4py/PETSc/DMPlex.pyx:491
getConeOrientation(p)
Return the orientations on the in-edges for this point in the DAG.
Not collective.
Parameters
p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getCone, DMPlex.setCone, DMPlex.setChart, ‐
DMPlexGetConeOrientation
Source code at petsc4py/PETSc/DMPlex.pyx:606
getConeSize(p)
Return the number of in-edges for this point in the DAG.
Not collective.
Parameters
p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
Return type
int
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setConeSize, DMPlex.setChart, DMPlexGetConeSize
Source code at petsc4py/PETSc/DMPlex.pyx:442
getDepth()
Return the depth of the DAG representing this mesh.
Not collective.
SEE ALSO:
DM, DMPlex, DMPlex.getDepthStratum, DMPlex.symmetrize, DMPlexGetDepth
Source code at petsc4py/PETSc/DMPlex.pyx:929
Return type
int
getDepthStratum(svalue)
Return the bounds [start, end) for all points at a certain depth.
Not collective.
Parameters
svalue (int) -- The requested depth.
Returns
• pStart (int) -- The first stratum point.
• pEnd (int) -- The upper bound for stratum points.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getHeightStratum, DMPlex.getDepth, DMPlex.symmetrize,
DMPlex.interpolate, DMPlexGetDepthStratum
Source code at petsc4py/PETSc/DMPlex.pyx:944
getFullJoin(points)
Return an array for the join of the set of points.
Not collective.
Parameters
points (Sequence[int]) -- The input points.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.getJoin, DMPlex.getMeet, DMPlexGetFullJoin
Source code at petsc4py/PETSc/DMPlex.pyx:1092
getHeightStratum(svalue)
Return the bounds [start, end) for all points at a certain height.
Not collective.
Parameters
svalue (int) -- The requested height.
Returns
• pStart (int) -- The first stratum point.
• pEnd (int) -- The upper bound for stratum points.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getDepthStratum, DMPlex.getDepth, DMPlexGetHeightStratum
Source code at petsc4py/PETSc/DMPlex.pyx:971
getJoin(points)
Return an array for the join of the set of points.
Not collective.
Parameters
points (Sequence[int]) -- The input points.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.getMeet, DMPlexGetJoin
Source code at petsc4py/PETSc/DMPlex.pyx:1066
getMaxSizes()
Return the maximum number of in-edges and out-edges of the DAG.
Not collective.
Returns
• maxConeSize (int) -- The maximum number of in-edges.
• maxSupportSize (int) -- The maximum number of out-edges.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setConeSize, DMPlex.setChart, DMPlexGetMaxSizes
Source code at petsc4py/PETSc/DMPlex.pyx:826
getMeet(points)
Return an array for the meet of the set of points.
Not collective.
Parameters
points (Sequence[int]) -- The input points.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.getJoin, DMPlexGetMeet
Source code at petsc4py/PETSc/DMPlex.pyx:1040
getMinRadius()
Return the minimum distance from any cell centroid to a face.
Not collective.
SEE ALSO:
DMPlex, DM.getCoordinates, DMPlexGetMinRadius
Source code at petsc4py/PETSc/DMPlex.pyx:1803
Return type
float
getOrdering(otype)
Calculate a reordering of the mesh.
Collective.
Parameters
otype (OrderingType) -- Type of reordering, see Mat.OrderingType.
Returns
perm -- The point permutation.
Return type
IS
SEE ALSO:
DMPlex, DMPlex.permute, Mat.OrderingType, Mat.getOrdering, DMPlexGetOrdering
Source code at petsc4py/PETSc/DMPlex.pyx:2130
getPartitioner()
Return the mesh partitioner.
Not collective.
SEE ALSO:
DM, DMPlex, Partitioner, Section, DMPlex.distribute, DMPlex.setPartitioner,
Partitioner.create, PetscPartitionerDMPlexPartition, DMPlexGetPartitioner
Source code at petsc4py/PETSc/DMPlex.pyx:1510
Return type
Partitioner
getPointDepth(point)
Return the depth of a given point.
Not collective.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
DM, DMPlex, DMPlex.getDepthStratum, DMPlex.getDepth, DMPlexGetPointDepth
Source code at petsc4py/PETSc/DMPlex.pyx:998
getPointGlobal(point)
Return location of point data in global Vec.
Not collective.
Parameters
point (int) -- The topological point.
Returns
• start (int) -- Start of point data; returns -(globalStart+1) if point is not
owned.
• end (int) -- End of point data; returns -(globalEnd+1) if point is not owned.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getPointGlobalField, Section.getOffset, Section.getDof,
DMPlex.getPointLocal, DMPlexGetPointGlobal
Source code at petsc4py/PETSc/DMPlex.pyx:1972
getPointGlobalField(point, field)
Return location of point field data in global Vec.
Not collective.
Parameters
• point (int) -- The topological point.
• field (int) -- The field number.
Returns
• start (int) -- Start of point data; returns -(globalStart+1) if point is not
owned.
• end (int) -- End of point data; returns -(globalEnd+1) if point is not owned.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getPointGlobal, Section.getOffset, Section.getDof,
DMPlex.getPointLocal, DMPlexGetPointGlobalField
Source code at petsc4py/PETSc/DMPlex.pyx:2000
getPointHeight(point)
Return the height of a given point.
Not collective.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
DM, DMPlex, DMPlex.getHeightStratum, DMPlexGetPointHeight
Source code at petsc4py/PETSc/DMPlex.pyx:1019
getPointLocal(point)
Return location of point data in local Vec.
Not collective.
Parameters
point (int) -- The topological point.
Returns
• start (int) -- Start of point data.
• end (int) -- End of point data.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getPointLocalField, Section.getOffset, Section.getDof, ‐
DMPlexGetPointLocal
Source code at petsc4py/PETSc/DMPlex.pyx:1913
getPointLocalField(point, field)
Return location of point field data in local Vec.
Not collective.
Parameters
• point (int) -- The topological point.
• field (int) -- The field number.
Returns
• start (int) -- Start of point data.
• end (int) -- End of point data.
Return type
tuple[int, int]
SEE ALSO:
DM, DMPlex, DMPlex.getPointLocal, Section.getOffset, DMPlexGetPointLocalField
Source code at petsc4py/PETSc/DMPlex.pyx:1941
getRefinementLimit()
Retrieve the maximum cell volume for refinement.
Not collective.
SEE ALSO:
DM, DMPlex, DM.refine, DMPlex.setRefinementLimit, DMPlex.getRefinementUniform,
DMPlex.setRefinementUniform, DMPlexGetRefinementLimit
Source code at petsc4py/PETSc/DMPlex.pyx:2114
Return type
float
getRefinementUniform()
Retrieve the flag for uniform refinement.
Not collective.
Returns
refinementUniform -- The flag for uniform refinement.
Return type
bool
SEE ALSO:
DM, DMPlex, DM.refine, DMPlex.setRefinementUniform, DMPlex.getRefinementLimit,
DMPlex.setRefinementLimit, DMPlexGetRefinementUniform
Source code at petsc4py/PETSc/DMPlex.pyx:2073
getSubpointIS()
Return an IS covering the entire subdm chart.
Not collective.
Returns
iset -- The IS containing subdm's parent's points.
Return type
IS
SEE ALSO:
DM, DMPlex, DMPlexGetSubpointIS
Source code at petsc4py/PETSc/DMPlex.pyx:2278
getSubpointMap()
Return a DMLabel with point dimension as values.
Not collective.
Returns
label -- The DMLabel whose values are subdm's point dimensions.
Return type
DMLabel
SEE ALSO:
DM, DMPlex, DMPlexGetSubpointMap
Source code at petsc4py/PETSc/DMPlex.pyx:2298
getSupport(p)
Return the points on the out-edges for this point in the DAG.
Not collective.
Parameters
p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
Return type
ArrayInt
SEE ALSO:
DM, DMPlex, DMPlex.getSupportSize, DMPlex.setSupport, DMPlex.getCone, DMPlex.setChart, ‐
DMPlexGetSupport
Source code at petsc4py/PETSc/DMPlex.pyx:771
getSupportSize(p)
Return the number of out-edges for this point in the DAG.
Not collective.
Parameters
p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
Return type
int
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setConeSize, DMPlex.setChart, DMPlex.getConeSize, ‐
DMPlexGetSupportSize
Source code at petsc4py/PETSc/DMPlex.pyx:722
getTransitiveClosure(p, useCone=True)
Return the points and orientations on the transitive closure of this point.
Not collective.
Parameters
• p (int) -- The mesh point.
• useCone (bool | None) -- True for the closure, otherwise return the star.
Returns
• points (ArrayInt) -- The points.
• orientations (ArrayInt) -- The orientations.
Return type
tuple[ArrayInt, ArrayInt]
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setCone, DMPlex.setChart, DMPlex.getCone, ‐
DMPlexGetTransitiveClosure
Source code at petsc4py/PETSc/DMPlex.pyx:1118
getVecClosure(sec, vec, point)
Return an array of the values on the closure of a point.
Not collective.
Parameters
• sec (Section) -- The Section describing the layout in vec or None to use the
default section.
• vec (Vec) -- The local vector.
• point (int) -- The point in the DMPlex.
Return type
ArrayScalar
SEE ALSO:
DM, DMPlex, DMPlexVecRestoreClosure
Source code at petsc4py/PETSc/DMPlex.pyx:1185
getVertexNumbering()
Return a global vertex numbering for all vertices on this process.
Collective the first time it is called.
SEE ALSO:
DM, DMPlex, DMPlex.getCellNumbering, DMPlexGetVertexNumbering
Source code at petsc4py/PETSc/DMPlex.pyx:900
Return type
IS
globalVectorLoad(viewer, sectiondm, sf, vec)
Load on-disk vector data into a global vector.
Collective.
Parameters
• viewer (Viewer) -- The Viewer that represents the on-disk vector data.
• sectiondm (DM) -- The DM that contains the global section on which vec is defined.
• sf (SF) -- The SF that migrates the on-disk vector data into vec.
• vec (Vec) -- The global vector to set values of.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.topologyLoad, DMPlex.sectionLoad, DMPlex.localVectorLoad,
DMPlex.globalVectorView, DMPlex.localVectorView, SF, Viewer, DMPlexGlobalVectorLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3401
globalVectorView(viewer, sectiondm, vec)
Save a global vector.
Collective.
Parameters
• viewer (Viewer) -- The Viewer to save data with.
• sectiondm (DM) -- The DM containing the global section on which vec is defined;
may be the same as this DMPlex object.
• vec (Vec) -- The global vector to be saved.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.topologyView, DMPlex.sectionView, DMPlex.localVectorView,
DMPlex.globalVectorLoad, DMPlex.localVectorLoad, DMPlexGlobalVectorView
Source code at petsc4py/PETSc/DMPlex.pyx:3248
insertCone(p, conePos, conePoint)
DMPlexInsertCone - Insert a point into the in-edges for the point p in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• conePos (int) -- The local index in the cone where the point should be put.
• conePoint (int) -- The mesh point to insert.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getCone, DMPlex.setChart, DMPlex.setConeSize,
DM.setUp, DMPlexInsertCone
Source code at petsc4py/PETSc/DMPlex.pyx:556
insertConeOrientation(p, conePos, coneOrientation)
Insert a point orientation for the in-edge for the point p in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart
• conePos (int) -- The local index in the cone where the point should be put.
• coneOrientation (int) -- The point orientation to insert.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getCone, DMPlex.setChart, DMPlex.setConeSize,
DM.setUp, DMPlexInsertConeOrientation
Source code at petsc4py/PETSc/DMPlex.pyx:581
interpolate()
Convert to a mesh with all intermediate faces, edges, etc.
Collective.
SEE ALSO:
DMPlex, DMPlex.uninterpolate, DMPlex.createFromCellList, DMPlexInterpolate
Source code at petsc4py/PETSc/DMPlex.pyx:1728
Return type
None
isDistributed()
Return the flag indicating if the mesh is distributed.
Collective.
SEE ALSO:
DM, DMPlex, DMPlex.distribute, DMPlexIsDistributed
Source code at petsc4py/PETSc/DMPlex.pyx:1618
Return type
bool
isSimplex()
Return the flag indicating if the first cell is a simplex.
Not collective.
SEE ALSO:
DM, DMPlex, DMPlex.getCellType, DMPlex.getHeightStratum, DMPlexIsSimplex
Source code at petsc4py/PETSc/DMPlex.pyx:1632
Return type
bool
labelCohesiveComplete(label, bdlabel, bdvalue, flip, split, subdm)
Add all other mesh pieces to complete the surface.
Not collective.
Parameters
• label (DMLabel) -- A DMLabel marking the surface.
• bdlabel (DMLabel) -- A DMLabel marking the vertices on the boundary which will not
be duplicated.
• bdvalue (int) -- Value of DMLabel marking the vertices on the boundary.
• flip (bool) -- Flag to flip the submesh normal and replace points on the other
side.
• split (bool) -- Flag to split faces incident on the surface boundary, rather than
clamping those faces to the boundary
• subdm (DMPlex) -- The DMPlex associated with the label.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.labelComplete, DMPlexLabelCohesiveComplete
Source code at petsc4py/PETSc/DMPlex.pyx:1396
labelComplete(label)
Add the transitive closure to the surface.
Not collective.
Parameters
label (DMLabel) -- A DMLabel marking the surface points.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.labelCohesiveComplete, DMPlexLabelComplete
Source code at petsc4py/PETSc/DMPlex.pyx:1379
labelsLoad(viewer, sfxc)
Load labels into this DMPlex object.
Collective.
Parameters
• viewer (Viewer) -- The Viewer for the saved labels.
• sfxc (SF) -- The SF returned by topologyLoad.
Return type
None
SEE ALSO:
DM, DMPlex, DM.load, DMPlex.topologyLoad, DMPlex.coordinatesLoad, DM.view, SF, Viewer, ‐
DMPlexLabelsLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3344
labelsView(viewer)
Save DMPlex labels into a file.
Collective.
Parameters
viewer (Viewer) -- The Viewer for saving.
Return type
None
SEE ALSO:
DM, DMPlex, DM.view, DMPlex.topologyView, DMPlex.coordinatesView, DMPlex.labelsLoad,
Viewer, DMPlexLabelsView
Source code at petsc4py/PETSc/DMPlex.pyx:3209
localVectorLoad(viewer, sectiondm, sf, vec)
Load on-disk vector data into a local vector.
Collective.
Parameters
• viewer (Viewer) -- The Viewer that represents the on-disk vector data.
• sectiondm (DM) -- The DM that contains the local section on which vec is defined.
• sf (SF) -- The SF that migrates the on-disk vector data into vec.
• vec (Vec) -- The local vector to set values of.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.topologyLoad, DMPlex.sectionLoad, DMPlex.globalVectorLoad,
DMPlex.globalVectorView, DMPlex.localVectorView, SF, Viewer, DMPlexLocalVectorLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3426
localVectorView(viewer, sectiondm, vec)
Save a local vector.
Collective.
Parameters
• viewer (Viewer) -- The Viewer to save data with.
• sectiondm (DM) -- The DM that contains the local section on which vec is defined;
may be the same as this DMPlex object.
• vec (Vec) -- The local vector to be saved.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.topologyView, DMPlex.sectionView, DMPlex.globalVectorView,
DMPlex.globalVectorLoad, DMPlex.localVectorLoad, DMPlexLocalVectorView
Source code at petsc4py/PETSc/DMPlex.pyx:3272
markBoundaryFaces(label, value=None)
Mark all faces on the boundary.
Not collective.
Parameters
• value (int | None) -- The marker value, or DETERMINE or None to use some value in
the closure (or 1 if none are found).
• label (str)
Return type
DMLabel
SEE ALSO:
DM, DMPlex, DMLabel.create, DM.createLabel, DMPlexMarkBoundaryFaces
Source code at petsc4py/PETSc/DMPlex.pyx:1352
metricAverage2(metric1, metric2, metricAvg)
Compute and return the unweighted average of two metrics.
Collective.
Parameters
• metric1 (Vec) -- The first metric to be averaged.
• metric2 (Vec) -- The second metric to be averaged.
• metricAvg (Vec) -- The output averaged metric.
Return type
Vec
SEE ALSO:
DMPlex.metricAverage3, DMPlexMetricAverage2
Source code at petsc4py/PETSc/DMPlex.pyx:3059
metricAverage3(metric1, metric2, metric3, metricAvg)
Compute and return the unweighted average of three metrics.
Collective.
Parameters
• metric1 (Vec) -- The first metric to be averaged.
• metric2 (Vec) -- The second metric to be averaged.
• metric3 (Vec) -- The third metric to be averaged.
• metricAvg (Vec) -- The output averaged metric.
Return type
Vec
SEE ALSO:
DMPlex.metricAverage2, DMPlexMetricAverage3
Source code at petsc4py/PETSc/DMPlex.pyx:3081
metricCreate(field=0)
Create a Riemannian metric field.
Collective.
Parameters
field (int | None) -- The field number to use.
Return type
Vec
SEE ALSO:
DMPlex.metricCreateUniform, DMPlex.metricCreateIsotropic, Working with PETSc options, ‐
DMPlexMetricCreate
Source code at petsc4py/PETSc/DMPlex.pyx:2890
metricCreateIsotropic(indicator, field=0)
Construct an isotropic metric from an error indicator.
Collective.
Parameters
• indicator (Vec) -- The error indicator.
• field (int | None) -- The field number to use.
Return type
Vec
SEE ALSO:
DMPlex.metricCreate, DMPlex.metricCreateUniform, DMPlexMetricCreateIsotropic
Source code at petsc4py/PETSc/DMPlex.pyx:2935
metricCreateUniform(alpha, field=0)
Construct a uniform isotropic metric.
Collective.
Parameters
• alpha (float) -- Scaling parameter for the diagonal.
• field (int | None) -- The field number to use.
Return type
Vec
SEE ALSO:
DMPlex.metricCreate, DMPlex.metricCreateIsotropic, DMPlexMetricCreateUniform
Source code at petsc4py/PETSc/DMPlex.pyx:2911
metricDeterminantCreate(field=0)
Create the determinant field for a Riemannian metric.
Collective.
Parameters
field (int | None) -- The field number to use.
Returns
• determinant (Vec) -- The determinant field.
• dmDet (DM) -- The corresponding DM
Return type
tuple[Vec, DM]
SEE ALSO:
DMPlex.metricCreateUniform, DMPlex.metricCreateIsotropic, DMPlex.metricCreate, ‐
DMPlexMetricDeterminantCreate
Source code at petsc4py/PETSc/DMPlex.pyx:2958
metricEnforceSPD(metric, ometric, determinant, restrictSizes=False, restrictAnisotropy=False)
Enforce symmetric positive-definiteness of a metric.
Collective.
Parameters
• metric (Vec) -- The metric.
• ometric (Vec) -- The output metric.
• determinant (Vec) -- The output determinant.
• restrictSizes (bool | None) -- Flag indicating whether maximum/minimum magnitudes
should be enforced.
• restrictAnisotropy (bool | None) -- Flag indicating whether maximum anisotropy
should be enforced.
Returns
• ometric (Vec) -- The output metric.
• determinant (Vec) -- The output determinant.
Return type
tuple[Vec, Vec]
SEE ALSO:
DMPlex.metricNormalize, DMPlex.metricIntersection2, DMPlex.metricIntersection3, Working
with PETSc options, DMPlexMetricEnforceSPD
Source code at petsc4py/PETSc/DMPlex.pyx:2987
metricGetGradationFactor()
Return the metric gradation factor.
Not collective.
SEE ALSO:
DMPlex.metricSetGradationFactor, DMPlex.metricGetHausdorffNumber, ‐
DMPlexMetricGetGradationFactor
Source code at petsc4py/PETSc/DMPlex.pyx:2841
Return type
float
metricGetHausdorffNumber()
Return the metric Hausdorff number.
Not collective.
SEE ALSO:
DMPlex.metricGetGradationFactor, DMPlex.metricSetHausdorffNumber, ‐
DMPlexMetricGetHausdorffNumber
Source code at petsc4py/PETSc/DMPlex.pyx:2875
Return type
float
metricGetMaximumAnisotropy()
Return the maximum tolerated metric anisotropy.
Not collective.
SEE ALSO:
DMPlex.metricSetMaximumAnisotropy, DMPlex.metricGetMaximumMagnitude, ‐
DMPlexMetricGetMaximumAnisotropy
Source code at petsc4py/PETSc/DMPlex.pyx:2739
Return type
float
metricGetMaximumMagnitude()
Return the maximum tolerated metric magnitude.
Not collective.
SEE ALSO:
DMPlex.metricSetMaximumMagnitude, DMPlex.metricGetMinimumMagnitude, ‐
DMPlexMetricGetMaximumMagnitude
Source code at petsc4py/PETSc/DMPlex.pyx:2705
Return type
float
metricGetMinimumMagnitude()
Return the minimum tolerated metric magnitude.
Not collective.
SEE ALSO:
DMPlex.metricSetMinimumMagnitude, DMPlex.metricGetMaximumMagnitude, ‐
DMPlexMetricGetMinimumMagnitude
Source code at petsc4py/PETSc/DMPlex.pyx:2671
Return type
float
metricGetNormalizationOrder()
Return the order p for L-p normalization.
Not collective.
SEE ALSO:
DMPlex.metricSetNormalizationOrder, DMPlex.metricGetTargetComplexity, ‐
DMPlexMetricGetNormalizationOrder
Source code at petsc4py/PETSc/DMPlex.pyx:2807
Return type
float
metricGetNumIterations()
Return the number of parallel adaptation iterations.
Not collective.
SEE ALSO:
DMPlex.metricSetNumIterations, DMPlex.metricGetVerbosity, DMPlexMetricGetNumIterations
Source code at petsc4py/PETSc/DMPlex.pyx:2637
Return type
int
metricGetTargetComplexity()
Return the target metric complexity.
Not collective.
SEE ALSO:
DMPlex.metricSetTargetComplexity, DMPlex.metricGetNormalizationOrder, ‐
DMPlexMetricGetTargetComplexity
Source code at petsc4py/PETSc/DMPlex.pyx:2773
Return type
float
metricGetVerbosity()
Return the verbosity of the mesh adaptation package.
Not collective.
Returns
verbosity -- The verbosity, where -1 is silent and 10 is maximum.
Return type
int
SEE ALSO:
DMPlex.metricSetVerbosity, DMPlex.metricGetNumIterations, DMPlexMetricGetVerbosity
Source code at petsc4py/PETSc/DMPlex.pyx:2598
metricIntersection2(metric1, metric2, metricInt)
Compute and return the intersection of two metrics.
Collective.
Parameters
• metric1 (Vec) -- The first metric to be intersected.
• metric2 (Vec) -- The second metric to be intersected.
• metricInt (Vec) -- The output intersected metric.
Return type
Vec
SEE ALSO:
DMPlex.metricIntersection3, DMPlexMetricIntersection2
Source code at petsc4py/PETSc/DMPlex.pyx:3105
metricIntersection3(metric1, metric2, metric3, metricInt)
Compute the intersection of three metrics.
Collective.
Parameters
• metric1 (Vec) -- The first metric to be intersected.
• metric2 (Vec) -- The second metric to be intersected.
• metric3 (Vec) -- The third metric to be intersected.
• metricInt (Vec) -- The output intersected metric.
Return type
Vec
SEE ALSO:
DMPlex.metricIntersection2, DMPlexMetricIntersection3
Source code at petsc4py/PETSc/DMPlex.pyx:3127
metricIsIsotropic()
Return the flag indicating whether the metric is isotropic or not.
Not collective.
SEE ALSO:
DMPlex.metricSetIsotropic, DMPlex.metricIsUniform, DMPlex.metricRestrictAnisotropyFirst,
DMPlexMetricIsIsotropic
Source code at petsc4py/PETSc/DMPlex.pyx:2386
Return type
bool
metricIsUniform()
Return the flag indicating whether the metric is uniform or not.
Not collective.
SEE ALSO:
DMPlex.metricSetUniform, DMPlex.metricRestrictAnisotropyFirst, DMPlexMetricIsUniform
Source code at petsc4py/PETSc/DMPlex.pyx:2352
Return type
bool
metricNoInsertion()
Return the flag indicating whether node insertion and deletion are turned off.
Not collective.
SEE ALSO:
DMPlex.metricSetNoInsertion, DMPlex.metricNoSwapping, DMPlex.metricNoMovement,
DMPlex.metricNoSurf, DMPlexMetricNoInsertion
Source code at petsc4py/PETSc/DMPlex.pyx:2455
Return type
bool
metricNoMovement()
Return the flag indicating whether node movement is turned off.
Not collective.
SEE ALSO:
DMPlex.metricSetNoMovement, DMPlex.metricNoInsertion, DMPlex.metricNoSwapping,
DMPlex.metricNoSurf, DMPlexMetricNoMovement
Source code at petsc4py/PETSc/DMPlex.pyx:2527
Return type
bool
metricNoSurf()
Return the flag indicating whether surface modification is turned off.
Not collective.
SEE ALSO:
DMPlex.metricSetNoSurf, DMPlex.metricNoMovement, DMPlex.metricNoInsertion,
DMPlex.metricNoSwapping, DMPlexMetricNoSurf
Source code at petsc4py/PETSc/DMPlex.pyx:2563
Return type
bool
metricNoSwapping()
Return the flag indicating whether facet swapping is turned off.
Not collective.
SEE ALSO:
DMPlex.metricSetNoSwapping, DMPlex.metricNoInsertion, DMPlex.metricNoMovement,
DMPlex.metricNoSurf, DMPlexMetricNoSwapping
Source code at petsc4py/PETSc/DMPlex.pyx:2491
Return type
bool
metricNormalize(metric, ometric, determinant, restrictSizes=True, restrictAnisotropy=True)
Apply L-p normalization to a metric.
Collective.
Parameters
• metric (Vec) -- The metric.
• ometric (Vec) -- The output metric.
• determinant (Vec) -- The output determinant.
• restrictSizes (bool | None) -- Flag indicating whether maximum/minimum magnitudes
should be enforced.
• restrictAnisotropy (bool | None) -- Flag indicating whether maximum anisotropy
should be enforced.
Returns
• ometric (Vec) -- The output normalized metric.
• determinant (Vec) -- The output determinant.
Return type
tuple[Vec, Vec]
SEE ALSO:
DMPlex.metricEnforceSPD, DMPlex.metricIntersection2, DMPlex.metricIntersection3, Working
with PETSc options, DMPlexMetricNormalize
Source code at petsc4py/PETSc/DMPlex.pyx:3023
metricRestrictAnisotropyFirst()
Return true if anisotropy is restricted before normalization.
Not collective.
SEE ALSO:
DMPlex.metricIsIsotropic, DMPlex.metricSetRestrictAnisotropyFirst, ‐
DMPlexMetricRestrictAnisotropyFirst
Source code at petsc4py/PETSc/DMPlex.pyx:2420
Return type
bool
metricSetFromOptions()
Configure the object from the options database.
Collective.
SEE ALSO:
Working with PETSc options
Source code at petsc4py/PETSc/DMPlex.pyx:2320
Return type
None
metricSetGradationFactor(beta)
Set the metric gradation factor.
Logically collective.
Parameters
beta (float) -- The metric gradation factor.
Return type
None
SEE ALSO:
DMPlex.metricGetGradationFactor, DMPlex.metricSetHausdorffNumber, ‐
DMPlexMetricSetGradationFactor
Source code at petsc4py/PETSc/DMPlex.pyx:2822
metricSetHausdorffNumber(hausd)
Set the metric Hausdorff number.
Logically collective.
Parameters
hausd (float) -- The metric Hausdorff number.
Return type
None
SEE ALSO:
DMPlex.metricSetGradationFactor, DMPlex.metricGetHausdorffNumber, ‐
DMPlexMetricSetHausdorffNumber
Source code at petsc4py/PETSc/DMPlex.pyx:2856
metricSetIsotropic(isotropic)
Record whether the metric is isotropic or not.
Logically collective.
Parameters
isotropic (bool) -- Flag indicating whether the metric is isotropic or not.
Return type
None
SEE ALSO:
DMPlex.metricIsIsotropic, DMPlex.metricSetUniform,
DMPlex.metricSetRestrictAnisotropyFirst, DMPlexMetricSetIsotropic
Source code at petsc4py/PETSc/DMPlex.pyx:2367
metricSetMaximumAnisotropy(a_max)
Set the maximum tolerated metric anisotropy.
Logically collective.
Parameters
a_max (float) -- The maximum tolerated metric anisotropy.
Return type
None
SEE ALSO:
DMPlex.metricGetMaximumAnisotropy, DMPlex.metricSetMaximumMagnitude, ‐
DMPlexMetricSetMaximumAnisotropy
Source code at petsc4py/PETSc/DMPlex.pyx:2720
metricSetMaximumMagnitude(h_max)
Set the maximum tolerated metric magnitude.
Logically collective.
Parameters
h_max (float) -- The maximum tolerated metric magnitude.
Return type
None
SEE ALSO:
DMPlex.metricGetMaximumMagnitude, DMPlex.metricSetMinimumMagnitude, ‐
DMPlexMetricSetMaximumMagnitude
Source code at petsc4py/PETSc/DMPlex.pyx:2686
metricSetMinimumMagnitude(h_min)
Set the minimum tolerated metric magnitude.
Logically collective.
Parameters
h_min (float) -- The minimum tolerated metric magnitude.
Return type
None
SEE ALSO:
DMPlex.metricGetMinimumMagnitude, DMPlex.metricSetMaximumMagnitude, ‐
DMPlexMetricSetMinimumMagnitude
Source code at petsc4py/PETSc/DMPlex.pyx:2652
metricSetNoInsertion(noInsert)
Set the flag indicating whether node insertion should be turned off.
Logically collective.
Parameters
noInsert (bool) -- Flag indicating whether node insertion and deletion should be
turned off.
Return type
None
SEE ALSO:
DMPlex.metricNoInsertion, DMPlex.metricSetNoSwapping, DMPlex.metricSetNoMovement,
DMPlex.metricSetNoSurf, DMPlexMetricSetNoInsertion
Source code at petsc4py/PETSc/DMPlex.pyx:2435
metricSetNoMovement(noMove)
Set the flag indicating whether node movement should be turned off.
Logically collective.
Parameters
noMove (bool) -- Flag indicating whether node movement should be turned off.
Return type
None
SEE ALSO:
DMPlex.metricNoMovement, DMPlex.metricSetNoInsertion, DMPlex.metricSetNoSwapping,
DMPlex.metricSetNoSurf, DMPlexMetricSetNoMovement
Source code at petsc4py/PETSc/DMPlex.pyx:2507
metricSetNoSurf(noSurf)
Set the flag indicating whether surface modification should be turned off.
Logically collective.
Parameters
noSurf (bool) -- Flag indicating whether surface modification should be turned off.
Return type
None
SEE ALSO:
DMPlex.metricNoSurf, DMPlex.metricSetNoMovement, DMPlex.metricSetNoInsertion,
DMPlex.metricSetNoSwapping, DMPlexMetricSetNoSurf
Source code at petsc4py/PETSc/DMPlex.pyx:2543
metricSetNoSwapping(noSwap)
Set the flag indicating whether facet swapping should be turned off.
Logically collective.
Parameters
noSwap (bool) -- Flag indicating whether facet swapping should be turned off.
Return type
None
SEE ALSO:
DMPlex.metricNoSwapping, DMPlex.metricSetNoInsertion, DMPlex.metricSetNoMovement,
DMPlex.metricSetNoSurf, DMPlexMetricSetNoSwapping
Source code at petsc4py/PETSc/DMPlex.pyx:2471
metricSetNormalizationOrder(p)
Set the order p for L-p normalization.
Logically collective.
Parameters
p (float) -- The normalization order.
Return type
None
SEE ALSO:
DMPlex.metricGetNormalizationOrder, DMPlex.metricSetTargetComplexity, ‐
DMPlexMetricSetNormalizationOrder
Source code at petsc4py/PETSc/DMPlex.pyx:2788
metricSetNumIterations(numIter)
Set the number of parallel adaptation iterations.
Logically collective.
Parameters
numIter (int) -- The number of parallel adaptation iterations.
Return type
None
SEE ALSO:
DMPlex.metricSetVerbosity, DMPlex.metricGetNumIterations, DMPlexMetricSetNumIterations
Source code at petsc4py/PETSc/DMPlex.pyx:2618
metricSetRestrictAnisotropyFirst(restrictAnisotropyFirst)
Record whether anisotropy is be restricted before normalization or after.
Logically collective.
Parameters
restrictAnisotropyFirst (bool) -- Flag indicating if anisotropy is restricted before
normalization or after.
Return type
None
SEE ALSO:
DMPlex.metricSetIsotropic, DMPlex.metricRestrictAnisotropyFirst, ‐
DMPlexMetricSetRestrictAnisotropyFirst
Source code at petsc4py/PETSc/DMPlex.pyx:2401
metricSetTargetComplexity(targetComplexity)
Set the target metric complexity.
Logically collective.
Parameters
targetComplexity (float) -- The target metric complexity.
Return type
None
SEE ALSO:
DMPlex.metricGetTargetComplexity, DMPlex.metricSetNormalizationOrder, ‐
DMPlexMetricSetTargetComplexity
Source code at petsc4py/PETSc/DMPlex.pyx:2754
metricSetUniform(uniform)
Record whether the metric is uniform or not.
Logically collective.
Parameters
uniform (bool) -- Flag indicating whether the metric is uniform or not.
Return type
None
SEE ALSO:
DMPlex.metricIsUniform, DMPlex.metricSetIsotropic,
DMPlex.metricSetRestrictAnisotropyFirst, DMPlexMetricSetUniform
Source code at petsc4py/PETSc/DMPlex.pyx:2333
metricSetVerbosity(verbosity)
Set the verbosity of the mesh adaptation package.
Logically collective.
Parameters
verbosity (int) -- The verbosity, where -1 is silent and 10 is maximum.
Return type
None
SEE ALSO:
DMPlex.metricGetVerbosity, DMPlex.metricSetNumIterations, DMPlexMetricSetVerbosity
Source code at petsc4py/PETSc/DMPlex.pyx:2579
orient()
Give a consistent orientation to the input mesh.
Collective.
SEE ALSO:
DM, DMPlex, DM.create, DMPlexOrient
Source code at petsc4py/PETSc/DMPlex.pyx:873
Return type
None
permute(perm)
Reorder the mesh according to the input permutation.
Collective.
Parameters
perm (IS) -- The point permutation, perm[old point number] = new point number.
Returns
pdm -- The permuted DMPlex.
Return type
DMPlex
SEE ALSO:
DMPlex, Mat.permute, DMPlexPermute
Source code at petsc4py/PETSc/DMPlex.pyx:2158
rebalanceSharedPoints(entityDepth=0, useInitialGuess=True, parallel=True)
Redistribute shared points in order to achieve better balancing.
Collective.
Parameters
• entityDepth (int | None) -- Depth of the entity to balance (e.g., 0 -> balance
vertices).
• useInitialGuess (bool | None) -- Whether to use the current distribution as
initial guess.
• parallel (bool | None) -- Whether to use ParMETIS and do the partition in parallel
or gather the graph onto a single process.
Returns
success -- Whether the graph partitioning was successful or not. Unsuccessful
simply means no change to the partitioning.
Return type
bool
SEE ALSO:
DM, DMPlex, DMPlex.distribute, Working with PETSc options, DMPlexRebalanceSharedPoints
Source code at petsc4py/PETSc/DMPlex.pyx:1527
reorderGetDefault()
Return flag indicating whether the DMPlex should be reordered by default.
Not collective.
SEE ALSO:
None, DMPlexReorderGetDefault
Source code at petsc4py/PETSc/DMPlex.pyx:2182
Return type
ReorderDefaultFlag
reorderSetDefault(flag)
Set flag indicating whether the DM should be reordered by default.
Logically collective.
Parameters
• reorder -- Flag for reordering.
• flag (ReorderDefaultFlag)
Return type
None
SEE ALSO:
DMPlex.reorderGetDefault, DMPlexReorderSetDefault
Source code at petsc4py/PETSc/DMPlex.pyx:2196
sectionLoad(viewer, sectiondm, sfxc)
Load section into a DM.
Collective.
Parameters
• viewer (Viewer) -- The Viewer that represents the on-disk section (sectionA).
• sectiondm (DM) -- The DM into which the on-disk section (sectionA) is migrated.
• sfxc (SF) -- The SF returned by topologyLoad.
Returns
• gsf (SF) -- The SF that migrates any on-disk Vec data associated with sectionA
into a global Vec associated with the sectiondm's global section (None if not
needed).
• lsf (SF) -- The SF that migrates any on-disk Vec data associated with sectionA
into a local Vec associated with the sectiondm's local section (None if not
needed).
Return type
tuple[SF, SF]
SEE ALSO:
DM, DMPlex, DM.load, DMPlex.topologyLoad, DMPlex.coordinatesLoad, DMPlex.labelsLoad,
DMPlex.globalVectorLoad, DMPlex.localVectorLoad, DMPlex.sectionView, SF, Viewer, ‐
DMPlexSectionLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3364
sectionView(viewer, sectiondm)
Save a section associated with a DMPlex.
Collective.
Parameters
• viewer (Viewer) -- The Viewer for saving.
• sectiondm (DM) -- The DM that contains the section to be saved.
Return type
None
SEE ALSO:
DM, DMPlex, DM.view, DMPlex.topologyView, DMPlex.coordinatesView, DMPlex.labelsView,
DMPlex.globalVectorView, DMPlex.localVectorView, DMPlex.sectionLoad, Viewer, ‐
DMPlexSectionView
Source code at petsc4py/PETSc/DMPlex.pyx:3227
setAdjacencyUseAnchors(useAnchors=True)
Define adjacency in the mesh using the point-to-point constraints.
Logically collective.
Parameters
useAnchors (bool) -- Flag to use the constraints. If True, then constrained points
are omitted from DMPlex.getAdjacency, and their anchor points appear in their place.
Return type
None
SEE ALSO:
DMPlex, DMPlex.getAdjacency, DMPlex.distribute, DMPlexSetAdjacencyUseAnchors
Source code at petsc4py/PETSc/DMPlex.pyx:1431
setCellType(p, ctype)
Set the polytope type of a given cell.
Not collective.
Parameters
• p (int) -- The cell.
• ctype (PolytopeType) -- The polytope type of the cell.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.getCellTypeLabel, DMPlex.getDepth, DM.createLabel, DMPlexSetCellType
Source code at petsc4py/PETSc/DMPlex.pyx:663
setChart(pStart, pEnd)
Set the interval for all mesh points [pStart, pEnd).
Not collective.
Parameters
• pStart (int) -- The first mesh point.
• pEnd (int) -- The upper bound for mesh points.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getChart, DMPlexSetChart
Source code at petsc4py/PETSc/DMPlex.pyx:421
setCone(p, cone, orientation=None)
Set the points on the in-edges for this point in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• cone (Sequence[int]) -- An array of points which are on the in-edges for point p.
• orientation (Sequence[int] | None) -- An array of orientations, defaults to None.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getCone, DMPlex.setChart, DMPlex.setConeSize,
DM.setUp, DMPlex.setSupport, DMPlex.setSupportSize, DMPlexSetCone
Source code at petsc4py/PETSc/DMPlex.pyx:517
setConeOrientation(p, orientation)
Set the orientations on the in-edges for this point in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• orientation (Sequence[int]) -- An array of orientations.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getConeOrientation, DMPlex.setCone, DMPlex.setChart,
DMPlex.setConeSize, DM.setUp, DMPlexSetConeOrientation
Source code at petsc4py/PETSc/DMPlex.pyx:632
setConeSize(p, size)
Set the number of in-edges for this point in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• size (int) -- The cone size for point p.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getConeSize, DMPlex.setChart, DMPlexSetConeSize
Source code at petsc4py/PETSc/DMPlex.pyx:466
setMatClosure(sec, gsec, mat, point, values, addv=None)
Set an array of the values on the closure of point.
Not collective.
Parameters
• sec (Section) -- The section describing the layout in mat, or None to use the
default section.
• gsec (Section) -- The section describing the layout in mat, or None to use the
default global section.
• mat (Mat) -- The matrix.
• point (int) -- The point in the DMPlex.
• values (Sequence[Scalar]) -- The array of values.
• mode -- The insertion mode.
• addv (InsertModeSpec | None)
Return type
None
SEE ALSO:
DM, DMPlex, DMPlexMatSetClosure
Source code at petsc4py/PETSc/DMPlex.pyx:1247
setPartitioner(part)
Set the mesh partitioner.
Logically collective.
Parameters
part (Partitioner) -- The partitioner.
Return type
None
SEE ALSO:
DM, DMPlex, Partitioner, DMPlex.distribute, DMPlex.getPartitioner, Partitioner.create, ‐
DMPlexSetPartitioner
Source code at petsc4py/PETSc/DMPlex.pyx:1492
setRefinementLimit(refinementLimit)
Set the maximum cell volume for refinement.
Logically collective.
Parameters
refinementLimit (float) -- The maximum cell volume in the refined mesh.
Return type
None
SEE ALSO:
DM, DMPlex, DM.refine, DMPlex.getRefinementLimit, DMPlex.getRefinementUniform,
DMPlex.setRefinementUniform, DMPlexSetRefinementLimit
Source code at petsc4py/PETSc/DMPlex.pyx:2094
setRefinementUniform(refinementUniform=True)
Set the flag for uniform refinement.
Logically collective.
Parameters
refinementUniform (bool | None) -- The flag for uniform refinement.
Return type
None
SEE ALSO:
DM, DMPlex, DM.refine, DMPlex.getRefinementUniform, DMPlex.getRefinementLimit,
DMPlex.setRefinementLimit, DMPlexSetRefinementUniform
Source code at petsc4py/PETSc/DMPlex.pyx:2053
setSupport(p, supp)
Set the points on the out-edges for this point in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• supp (Sequence[int]) -- An array of points which are on the out-edges for point p.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.setCone, DMPlex.setConeSize, DMPlex.create, DMPlex.getSupport,
DMPlex.setChart, DMPlex.setSupportSize, DM.setUp, DMPlexSetSupport
Source code at petsc4py/PETSc/DMPlex.pyx:797
setSupportSize(p, size)
Set the number of out-edges for this point in the DAG.
Not collective.
Parameters
• p (int) -- The point, which must lie in the chart set with DMPlex.setChart.
• size (int) -- The support size for point p.
Return type
None
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.getSupportSize, DMPlex.setChart, DMPlexSetSupportSize
Source code at petsc4py/PETSc/DMPlex.pyx:746
setTetGenOptions(opts)
Set the options used for the Tetgen mesh generator.
Not collective.
Parameters
opts (str) -- The command line options.
Return type
None
SEE ALSO:
Working with PETSc options, DM, DMPlex, DMPlex.setTriangleOptions, DMPlex.generate, ‐
DMPlexTetgenSetOptions
Source code at petsc4py/PETSc/DMPlex.pyx:1332
setTriangleOptions(opts)
Set the options used for the Triangle mesh generator.
Not collective.
Parameters
opts (str) -- The command line options.
Return type
None
SEE ALSO:
Working with PETSc options, DM, DMPlex, DMPlex.setTetGenOptions, DMPlex.generate, ‐
DMPlexTriangleSetOptions
Source code at petsc4py/PETSc/DMPlex.pyx:1312
setVecClosure(sec, vec, point, values, addv=None)
Set an array of the values on the closure of point.
Not collective.
Parameters
• sec (Section) -- The section describing the layout in vec, or None to use the
default section.
• vec (Vec) -- The local vector.
• point (int) -- The point in the DMPlex.
• values (Sequence[Scalar]) -- The array of values.
• mode -- The insertion mode.
• addv (InsertModeSpec | None)
Return type
None
SEE ALSO:
DM, DMPlex, DMPlexVecSetClosure
Source code at petsc4py/PETSc/DMPlex.pyx:1215
stratify()
Calculate the strata of DAG.
Collective.
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.symmetrize, DMPlexStratify
Source code at petsc4py/PETSc/DMPlex.pyx:861
Return type
None
symmetrize()
Create support (out-edge) information from cone (in-edge) information.
Not collective.
SEE ALSO:
DM, DMPlex, DMPlex.create, DMPlex.setChart, DMPlex.setConeSize, DMPlex.setCone, ‐
DMPlexSymmetrize
Source code at petsc4py/PETSc/DMPlex.pyx:848
Return type
None
topologyLoad(viewer)
Load a topology into this DMPlex object.
Collective.
Parameters
viewer (Viewer) -- The Viewer for the saved topology
Returns
sfxc -- The SF that pushes points in [0, N) to the associated points in the loaded
DMPlex, where N is the global number of points.
Return type
SF
SEE ALSO:
DM, DMPlex, DM.load, DMPlex.coordinatesLoad, DMPlex.labelsLoad, DM.view, SF, Viewer, ‐
DMPlexTopologyLoad
Source code at petsc4py/PETSc/DMPlex.pyx:3298
topologyView(viewer)
Save a DMPlex topology into a file.
Collective.
Parameters
viewer (Viewer) -- The Viewer for saving.
Return type
None
SEE ALSO:
DM, DMPlex, DM.view, DMPlex.coordinatesView, DMPlex.labelsView, DMPlex.topologyLoad,
Viewer, DMPlexTopologyView
Source code at petsc4py/PETSc/DMPlex.pyx:3173
uninterpolate()
Convert to a mesh with only cells and vertices.
Collective.
SEE ALSO:
DMPlex, DMPlex.interpolate, DMPlex.createFromCellList, DMPlexUninterpolate
Source code at petsc4py/PETSc/DMPlex.pyx:1743
Return type
None
vecGetClosure(sec, vec, p)
Return an array of values on the closure of p.
Not collective.
Parameters
• sec (Section) -- The section describing the layout in vec.
• vec (Vec) -- The local vector.
• p (int) -- The point in the DMPlex.
Return type
ArrayScalar
SEE ALSO:
DM, DMPlex, DMPlexVecRestoreClosure
Source code at petsc4py/PETSc/DMPlex.pyx:1157
petsc4py.PETSc.DMPlexTransform
class petsc4py.PETSc.DMPlexTransform
Bases: Object
Mesh transformations.
Methods Summary
┌──────────────────┬───────────────────────────────────────┐
│ apply(dm) │ Apply a mesh transformation. │
├──────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a mesh transformation. │
├──────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy a mesh transformation. │
├──────────────────┼───────────────────────────────────────┤
│ getType() │ Return the transformation type name. │
├──────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM for the transformation. │
├──────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the transformation from the │
│ │ options database. │
├──────────────────┼───────────────────────────────────────┤
│ setType(tr_type) │ Set the transformation type. │
├──────────────────┼───────────────────────────────────────┤
│ setUp() │ Setup a mesh transformation. │
├──────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the mesh transformation. │
└──────────────────┴───────────────────────────────────────┘
Methods Documentation
apply(dm)
Apply a mesh transformation.
Collective.
Source code at petsc4py/PETSc/DMPlex.pyx:3475
Parameters
dm (DM)
Return type
DM
create(comm=None)
Create a mesh transformation.
Collective.
SEE ALSO:
DMPlexTransformCreate
Source code at petsc4py/PETSc/DMPlex.pyx:3486
Parameters
comm (Comm | None)
Return type
Self
destroy()
Destroy a mesh transformation.
Collective.
SEE ALSO:
DMPlexTransformDestroy
Source code at petsc4py/PETSc/DMPlex.pyx:3503
Return type
Self
getType()
Return the transformation type name.
Not collective.
SEE ALSO:
DMPlexTransformGetType
Source code at petsc4py/PETSc/DMPlex.pyx:3516
Return type
str
setDM(dm)
Set the DM for the transformation.
Logically collective.
Source code at petsc4py/PETSc/DMPlex.pyx:3554
Parameters
dm (DM)
Return type
None
setFromOptions()
Configure the transformation from the options database.
Collective.
SEE ALSO:
Working with PETSc options, DMPlexTransformSetFromOptions
Source code at petsc4py/PETSc/DMPlex.pyx:3563
Return type
None
setType(tr_type)
Set the transformation type.
Collective.
SEE ALSO:
DMPlexTransformSetType
Source code at petsc4py/PETSc/DMPlex.pyx:3540
Parameters
tr_type (DMPlexTransformType | str)
Return type
None
setUp()
Setup a mesh transformation.
Collective.
Source code at petsc4py/PETSc/DMPlex.pyx:3530
Return type
Self
view(viewer=None)
View the mesh transformation.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
Viewer, DMPlexTransformView
Source code at petsc4py/PETSc/DMPlex.pyx:3575
petsc4py.PETSc.DMPlexTransformType
class petsc4py.PETSc.DMPlexTransformType
Bases: object
Transformation types.
Attributes Summary
┌─────────────────────┬───────────────────────────────────────┐
│ EXTRUDE │ Object EXTRUDE of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINE1D │ Object REFINE1D of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINEALFELD │ Object REFINEALFELD of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINEBOUNDARYLAYER │ Object REFINEBOUNDARYLAYER of type ‐ │
│ │ str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINEPOWELLSABIN │ Object REFINEPOWELLSABIN of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINEREGULAR │ Object REFINEREGULAR of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINESBR │ Object REFINESBR of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINETOBOX │ Object REFINETOBOX of type str │
├─────────────────────┼───────────────────────────────────────┤
│ REFINETOSIMPLEX │ Object REFINETOSIMPLEX of type str │
├─────────────────────┼───────────────────────────────────────┤
│ TRANSFORMFILTER │ Object TRANSFORMFILTER of type str │
└─────────────────────┴───────────────────────────────────────┘
Attributes Documentation
EXTRUDE: str = EXTRUDE
Object EXTRUDE of type str
REFINE1D: str = REFINE1D
Object REFINE1D of type str
REFINEALFELD: str = REFINEALFELD
Object REFINEALFELD of type str
REFINEBOUNDARYLAYER: str = REFINEBOUNDARYLAYER
Object REFINEBOUNDARYLAYER of type str
REFINEPOWELLSABIN: str = REFINEPOWELLSABIN
Object REFINEPOWELLSABIN of type str
REFINEREGULAR: str = REFINEREGULAR
Object REFINEREGULAR of type str
REFINESBR: str = REFINESBR
Object REFINESBR of type str
REFINETOBOX: str = REFINETOBOX
Object REFINETOBOX of type str
REFINETOSIMPLEX: str = REFINETOSIMPLEX
Object REFINETOSIMPLEX of type str
TRANSFORMFILTER: str = TRANSFORMFILTER
Object TRANSFORMFILTER of type str
petsc4py.PETSc.DMShell
class petsc4py.PETSc.DMShell
Bases: DM
A shell DM object, used to manage user-defined problem data.
Methods Summary
┌───────────────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Creates a shell DM object. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCoarsen(coarsen[, args, kargs]) │ Set the routine used to coarsen the │
│ │ DMShell. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateDomainDecomposition(decomp[, │ Set the routine used to create a │
│ args, ...]) │ domain decomposition. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateDomainDecompositionScatters(scatter) │ Set the routine used to create the │
│ │ scatter contexts for domain │
│ │ decomposition. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateFieldDecomposition(decomp[, args, │ Set the routine used to create a │
│ ...]) │ field decomposition. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateGlobalVector(create_gvec[, args, │ Set the routine to create a global │
│ kargs]) │ vector. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateInjection(create_injection[, args, │ Set the routine used to create the │
│ ...]) │ injection operator. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateInterpolation(create_interpolation) │ Set the routine used to create the │
│ │ interpolation operator. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateLocalVector(create_lvec[, args, │ Set the routine to create a local │
│ kargs]) │ vector. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateMatrix(create_matrix[, args, kargs]) │ Set the routine to create a matrix. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateRestriction(create_restriction[, │ Set the routine used to create the │
│ ...]) │ restriction operator. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCreateSubDM(create_subdm[, args, kargs]) │ Set the routine used to create a sub │
│ │ DM from the DMShell. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGlobalToLocal(begin, end[, begin_args, │ Set the routines used to perform a │
│ ...]) │ global to local scatter. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGlobalToLocalVecScatter(gtol) │ Set a Scatter context for global to │
│ │ local communication. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGlobalVector(gv) │ Set a template global vector. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalToGlobal(begin, end[, begin_args, │ Set the routines used to perform a │
│ ...]) │ local to global scatter. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalToGlobalVecScatter(ltog) │ Set a Scatter context for local to │
│ │ global communication. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalToLocal(begin, end[, begin_args, │ Set the routines used to perform a │
│ ...]) │ local to local scatter. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalToLocalVecScatter(ltol) │ Set a Scatter context for local to │
│ │ local communication. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalVector(lv) │ Set a template local vector. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMatrix(mat) │ Set a template matrix. │
├───────────────────────────────────────────────┼───────────────────────────────────────┤
│ setRefine(refine[, args, kargs]) │ Set the routine used to refine the │
│ │ DMShell. │
└───────────────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Creates a shell DM object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DMShellCreate
Source code at petsc4py/PETSc/DMShell.pyx:4
setCoarsen(coarsen, args=None, kargs=None)
Set the routine used to coarsen the DMShell.
Logically collective.
Parameters
• coarsen (Callable[[DM, Comm], DM] | None) -- The routine which coarsens the DM.
• args (tuple[Any, ...] | None) -- Additional positional arguments for coarsen.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for coarsen.
Return type
None
SEE ALSO:
setRefine, DMShellSetCoarsen
Source code at petsc4py/PETSc/DMShell.pyx:368
setCreateDomainDecomposition(decomp, args=None, kargs=None)
Set the routine used to create a domain decomposition.
Logically collective.
Parameters
• decomp (Callable[[DM], tuple[list[str] | None, list[IS] | None, list[IS] | None, ‐
list[DM] | None]] | None) -- The routine to create the decomposition.
• args (tuple[Any, ...] | None) -- Additional positional arguments for decomp.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for decomp.
Return type
None
SEE ALSO:
DMShellSetCreateDomainDecomposition
Source code at petsc4py/PETSc/DMShell.pyx:560
setCreateDomainDecompositionScatters(scatter, args=None, kargs=None)
Set the routine used to create the scatter contexts for domain decomposition.
Logically collective.
Parameters
• scatter (Callable[[DM, list[DM]], tuple[list[Scatter], list[Scatter], list[‐
Scatter]]] | None) -- The routine to create the scatters.
• args (tuple[Any, ...] | None) -- Additional positional arguments for scatter.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for scatter.
Return type
None
SEE ALSO:
DMShellSetCreateDomainDecompositionScatters
Source code at petsc4py/PETSc/DMShell.pyx:592
setCreateFieldDecomposition(decomp, args=None, kargs=None)
Set the routine used to create a field decomposition.
Logically collective.
Parameters
• decomp (Callable[[DM], tuple[list[str] | None, list[IS] | None, list[DM] | None]]
| None) -- The routine to create the decomposition.
• args (tuple[Any, ...] | None) -- Additional positional arguments for decomp.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for decomp.
Return type
None
SEE ALSO:
DMShellSetCreateFieldDecomposition
Source code at petsc4py/PETSc/DMShell.pyx:528
setCreateGlobalVector(create_gvec, args=None, kargs=None)
Set the routine to create a global vector.
Logically collective.
Parameters
• create_gvec (Callable[[DM], Vec] | None) -- The creation routine.
• args (tuple[Any, ...] | None) -- Additional positional arguments for create_gvec.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for create_gvec.
Return type
None
SEE ALSO:
setCreateLocalVector, DMShellSetCreateGlobalVector
Source code at petsc4py/PETSc/DMShell.pyx:76
setCreateInjection(create_injection, args=None, kargs=None)
Set the routine used to create the injection operator.
Logically collective.
Parameters
• create_injection (Callable[[DM, DM], Mat] | None) -- The routine to create the
injection.
• args (tuple[Any, ...] | None) -- Additional positional arguments for
create_injection.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for
create_injection.
Return type
None
SEE ALSO:
DMShellSetCreateInjection
Source code at petsc4py/PETSc/DMShell.pyx:464
setCreateInterpolation(create_interpolation, args=None, kargs=None)
Set the routine used to create the interpolation operator.
Logically collective.
Parameters
• create_interpolation (Callable[[DM, DM], tuple[Mat, Vec]] | None) -- The routine
to create the interpolation.
• args (tuple[Any, ...] | None) -- Additional positional arguments for
create_interpolation.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for
create_interpolation.
Return type
None
SEE ALSO:
DMShellSetCreateInterpolation
Source code at petsc4py/PETSc/DMShell.pyx:432
setCreateLocalVector(create_lvec, args=None, kargs=None)
Set the routine to create a local vector.
Logically collective.
Parameters
• create_lvec (Callable[[DM], Vec] | None) -- The creation routine.
• args (tuple[Any, ...] | None) -- Additional positional arguments for create_lvec.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for create_lvec.
Return type
None
SEE ALSO:
setCreateGlobalVector, DMShellSetCreateLocalVector
Source code at petsc4py/PETSc/DMShell.pyx:108
setCreateMatrix(create_matrix, args=None, kargs=None)
Set the routine to create a matrix.
Logically collective.
Parameters
• create_matrix (Callable[[DM], Mat] | None) -- The function to create a matrix.
• args (tuple[Any, ...] | None) -- Additional positional arguments for
create_matrix.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for create_matrix.
Return type
None
SEE ALSO:
DMShellSetCreateMatrix
Source code at petsc4py/PETSc/DMShell.pyx:336
setCreateRestriction(create_restriction, args=None, kargs=None)
Set the routine used to create the restriction operator.
Logically collective.
Parameters
• create_restriction (Callable[[DM, DM], Mat] | None) -- The routine to create the
restriction
• args (tuple[Any, ...] | None) -- Additional positional arguments for
create_restriction.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for
create_restriction.
Return type
None
SEE ALSO:
DMShellSetCreateRestriction
Source code at petsc4py/PETSc/DMShell.pyx:496
setCreateSubDM(create_subdm, args=None, kargs=None)
Set the routine used to create a sub DM from the DMShell.
Logically collective.
Parameters
• subdm -- The routine to create the decomposition.
• args (tuple[Any, ...] | None) -- Additional positional arguments for subdm.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for subdm.
• create_subdm (Callable[[DM, Sequence[int]], tuple[IS, DM]] | None)
Return type
None
SEE ALSO:
DMShellSetCreateSubDM
Source code at petsc4py/PETSc/DMShell.pyx:624
setGlobalToLocal(begin, end, begin_args=None, begin_kargs=None, end_args=None, end_kargs=None)
Set the routines used to perform a global to local scatter.
Logically collective.
Parameters
• dm -- The DMShell.
• begin (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which
begins the global to local scatter.
• end (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which ends
the global to local scatter.
• begin_args (tuple[Any, ...] | None) -- Additional positional arguments for begin.
• begin_kargs (dict[str, Any] | None) -- Additional keyword arguments for begin.
• end_args (tuple[Any, ...] | None) -- Additional positional arguments for end.
• end_kargs (dict[str, Any] | None) -- Additional keyword arguments for end.
Return type
None
SEE ALSO:
DMShellSetGlobalToLocal
Source code at petsc4py/PETSc/DMShell.pyx:140
setGlobalToLocalVecScatter(gtol)
Set a Scatter context for global to local communication.
Logically collective.
Parameters
gtol (Scatter) -- The global to local Scatter context.
Return type
None
SEE ALSO:
DMShellSetGlobalToLocalVecScatter
Source code at petsc4py/PETSc/DMShell.pyx:189
setGlobalVector(gv)
Set a template global vector.
Logically collective.
Parameters
gv (Vec) -- Template vector.
Return type
None
SEE ALSO:
setLocalVector, DMShellSetGlobalVector
Source code at petsc4py/PETSc/DMShell.pyx:42
setLocalToGlobal(begin, end, begin_args=None, begin_kargs=None, end_args=None, end_kargs=None)
Set the routines used to perform a local to global scatter.
Logically collective.
Parameters
• begin (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which
begins the local to global scatter.
• end (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which ends
the local to global scatter.
• begin_args (tuple[Any, ...] | None) -- Additional positional arguments for begin.
• begin_kargs (dict[str, Any] | None) -- Additional keyword arguments for begin.
• end_args (tuple[Any, ...] | None) -- Additional positional arguments for end.
• end_kargs (dict[str, Any] | None) -- Additional keyword arguments for end.
Return type
None
SEE ALSO:
DMShellSetLocalToGlobal
Source code at petsc4py/PETSc/DMShell.pyx:206
setLocalToGlobalVecScatter(ltog)
Set a Scatter context for local to global communication.
Logically collective.
Parameters
ltog (Scatter) -- The local to global Scatter context.
Return type
None
SEE ALSO:
DMShellSetLocalToGlobalVecScatter
Source code at petsc4py/PETSc/DMShell.pyx:253
setLocalToLocal(begin, end, begin_args=None, begin_kargs=None, end_args=None, end_kargs=None)
Set the routines used to perform a local to local scatter.
Logically collective.
Parameters
• begin (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which
begins the local to local scatter.
• end (Callable[[DM, Vec, InsertMode, Vec], None] | None) -- The routine which ends
the local to local scatter.
• begin_args (tuple[Any, ...] | None) -- Additional positional arguments for begin.
• begin_kargs (dict[str, Any] | None) -- Additional keyword arguments for begin.
• end_args (tuple[Any, ...] | None) -- Additional positional arguments for end.
• end_kargs (dict[str, Any] | None) -- Additional keyword arguments for end.
Return type
None
SEE ALSO:
DMShellSetLocalToLocal
Source code at petsc4py/PETSc/DMShell.pyx:270
setLocalToLocalVecScatter(ltol)
Set a Scatter context for local to local communication.
Logically collective.
Parameters
ltol (Scatter) -- The local to local Scatter context.
Return type
None
SEE ALSO:
DMShellSetLocalToLocalVecScatter
Source code at petsc4py/PETSc/DMShell.pyx:319
setLocalVector(lv)
Set a template local vector.
Logically collective.
Parameters
lv (Vec) -- Template vector.
Return type
None
SEE ALSO:
setGlobalVector, DMShellSetLocalVector
Source code at petsc4py/PETSc/DMShell.pyx:59
setMatrix(mat)
Set a template matrix.
Collective.
Parameters
mat (Mat) -- The template matrix.
Return type
None
SEE ALSO:
DMShellSetMatrix
Source code at petsc4py/PETSc/DMShell.pyx:25
setRefine(refine, args=None, kargs=None)
Set the routine used to refine the DMShell.
Logically collective.
Parameters
• refine (Callable[[DM, Comm], DM] | None) -- The routine which refines the DM.
• args (tuple[Any, ...] | None) -- Additional positional arguments for refine.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for refine.
Return type
None
SEE ALSO:
setCoarsen, DMShellSetRefine
Source code at petsc4py/PETSc/DMShell.pyx:400
petsc4py.PETSc.DMStag
class petsc4py.PETSc.DMStag
Bases: DM
A DM object representing a "staggered grid" or a structured cell complex.
Enumerations
┌─────────────────┬─────────────────────────┐
│ StencilLocation │ Stencil location types. │
├─────────────────┼─────────────────────────┤
│ StencilType │ Stencil types. │
└─────────────────┴─────────────────────────┘
petsc4py.PETSc.DMStag.StencilLocation
class petsc4py.PETSc.DMStag.StencilLocation
Bases: object
Stencil location types.
Attributes Summary
┌──────────────────┬───────────────────────────────────────┐
│ BACK │ Constant BACK of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_DOWN │ Constant BACK_DOWN of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_DOWN_LEFT │ Constant BACK_DOWN_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_DOWN_RIGHT │ Constant BACK_DOWN_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_LEFT │ Constant BACK_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_RIGHT │ Constant BACK_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_UP │ Constant BACK_UP of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_UP_LEFT │ Constant BACK_UP_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ BACK_UP_RIGHT │ Constant BACK_UP_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ DOWN │ Constant DOWN of type int │
├──────────────────┼───────────────────────────────────────┤
│ DOWN_LEFT │ Constant DOWN_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ DOWN_RIGHT │ Constant DOWN_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ ELEMENT │ Constant ELEMENT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT │ Constant FRONT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_DOWN │ Constant FRONT_DOWN of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_DOWN_LEFT │ Constant FRONT_DOWN_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_DOWN_RIGHT │ Constant FRONT_DOWN_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_LEFT │ Constant FRONT_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_RIGHT │ Constant FRONT_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_UP │ Constant FRONT_UP of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_UP_LEFT │ Constant FRONT_UP_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ FRONT_UP_RIGHT │ Constant FRONT_UP_RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ LEFT │ Constant LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ NULLLOC │ Constant NULLLOC of type int │
├──────────────────┼───────────────────────────────────────┤
│ RIGHT │ Constant RIGHT of type int │
├──────────────────┼───────────────────────────────────────┤
│ UP │ Constant UP of type int │
├──────────────────┼───────────────────────────────────────┤
│ UP_LEFT │ Constant UP_LEFT of type int │
├──────────────────┼───────────────────────────────────────┤
│ UP_RIGHT │ Constant UP_RIGHT of type int │
└──────────────────┴───────────────────────────────────────┘
Attributes Documentation
BACK: int = BACK
Constant BACK of type int
BACK_DOWN: int = BACK_DOWN
Constant BACK_DOWN of type int
BACK_DOWN_LEFT: int = BACK_DOWN_LEFT
Constant BACK_DOWN_LEFT of type int
BACK_DOWN_RIGHT: int = BACK_DOWN_RIGHT
Constant BACK_DOWN_RIGHT of type int
BACK_LEFT: int = BACK_LEFT
Constant BACK_LEFT of type int
BACK_RIGHT: int = BACK_RIGHT
Constant BACK_RIGHT of type int
BACK_UP: int = BACK_UP
Constant BACK_UP of type int
BACK_UP_LEFT: int = BACK_UP_LEFT
Constant BACK_UP_LEFT of type int
BACK_UP_RIGHT: int = BACK_UP_RIGHT
Constant BACK_UP_RIGHT of type int
DOWN: int = DOWN
Constant DOWN of type int
DOWN_LEFT: int = DOWN_LEFT
Constant DOWN_LEFT of type int
DOWN_RIGHT: int = DOWN_RIGHT
Constant DOWN_RIGHT of type int
ELEMENT: int = ELEMENT
Constant ELEMENT of type int
FRONT: int = FRONT
Constant FRONT of type int
FRONT_DOWN: int = FRONT_DOWN
Constant FRONT_DOWN of type int
FRONT_DOWN_LEFT: int = FRONT_DOWN_LEFT
Constant FRONT_DOWN_LEFT of type int
FRONT_DOWN_RIGHT: int = FRONT_DOWN_RIGHT
Constant FRONT_DOWN_RIGHT of type int
FRONT_LEFT: int = FRONT_LEFT
Constant FRONT_LEFT of type int
FRONT_RIGHT: int = FRONT_RIGHT
Constant FRONT_RIGHT of type int
FRONT_UP: int = FRONT_UP
Constant FRONT_UP of type int
FRONT_UP_LEFT: int = FRONT_UP_LEFT
Constant FRONT_UP_LEFT of type int
FRONT_UP_RIGHT: int = FRONT_UP_RIGHT
Constant FRONT_UP_RIGHT of type int
LEFT: int = LEFT
Constant LEFT of type int
NULLLOC: int = NULLLOC
Constant NULLLOC of type int
RIGHT: int = RIGHT
Constant RIGHT of type int
UP: int = UP
Constant UP of type int
UP_LEFT: int = UP_LEFT
Constant UP_LEFT of type int
UP_RIGHT: int = UP_RIGHT
Constant UP_RIGHT of type int
petsc4py.PETSc.DMStag.StencilType
class petsc4py.PETSc.DMStag.StencilType
Bases: object
Stencil types.
Attributes Summary
┌──────┬───────────────────────────┐
│ BOX │ Constant BOX of type int │
├──────┼───────────────────────────┤
│ NONE │ Constant NONE of type int │
├──────┼───────────────────────────┤
│ STAR │ Constant STAR of type int │
└──────┴───────────────────────────┘
Attributes Documentation
BOX: int = BOX
Constant BOX of type int
NONE: int = NONE
Constant NONE of type int
STAR: int = STAR
Constant STAR of type int
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ VecSplitToDMDA(vec, loc, c) │ Return DMDA, Vec from a subgrid of a │
│ │ DMStag, its Vec. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create(dim[, dofs, sizes, │ Create a DMDA object. │
│ boundary_types, ...]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createCompatibleDMStag(dofs) │ Create a compatible DMStag with │
│ │ different DOFs/stratum. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ get1dCoordinatecArrays() │ Not implemented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBoundaryTypes() │ Return boundary types in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCorners() │ Return starting element index, width │
│ │ and number of partial elements. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDim() │ Return the number of dimensions. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDof() │ Get number of DOFs associated with │
│ │ each stratum of the grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getEntriesPerElement() │ Return the number of entries per │
│ │ element in the local representation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGhostCorners() │ Return starting element index and │
│ │ width of local region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGlobalSizes() │ Return global element counts in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIsFirstRank() │ Return whether this process is first │
│ │ in each dimension in the process │
│ │ grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIsLastRank() │ Return whether this process is last │
│ │ in each dimension in the process │
│ │ grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSizes() │ Return local elementwise sizes in │
│ │ each dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocationDof(loc) │ Return number of DOFs associated with │
│ │ a given point on the grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocationSlot(loc, c) │ Return index to use in accessing raw │
│ │ local arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRanges() │ Return elements per process in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getProcSizes() │ Return number of processes in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getProductCoordinateLocationSlot(loc) │ Return slot for use with local │
│ │ product coordinate arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStencilType() │ Return elementwise ghost/halo stencil │
│ │ type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStencilWidth() │ Return elementwise stencil width. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVecArray(vec) │ Not implemented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ migrateVec(vec, dmTo, vecTo) │ Transfer a vector between two DMStag │
│ │ objects. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBoundaryTypes(boundary_types) │ Set the boundary types. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinateDMType(dmtype) │ Set the type to store coordinates. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDof(dofs) │ Set DOFs/stratum. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setGlobalSizes(sizes) │ Set global element counts in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOwnershipRanges(ranges) │ Set elements per process in each │
│ │ dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setProcSizes(sizes) │ Set the number of processes in each │
│ │ dimension in the global process grid. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencilType(stenciltype) │ Set elementwise ghost/halo stencil │
│ │ type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencilWidth(swidth) │ Set elementwise stencil width. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUniformCoordinates([xmin, xmax, │ Set the coordinates to be a uniform │
│ ymin, ...]) │ grid.. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUniformCoordinatesExplicit([xmin, │ Set coordinates to be a uniform grid, │
│ xmax, ...]) │ storing all values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUniformCoordinatesProduct([xmin, │ Create uniform coordinates, as a │
│ xmax, ...]) │ product of 1D arrays. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌─────────────────────┬───────────────────────────────────────┐
│ boundary_types │ Boundary types in each dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ corners │ The lower left corner and size of │
│ │ local region in each dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ dim │ The dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ dofs │ The number of DOFs associated with │
│ │ each stratum of the grid. │
├─────────────────────┼───────────────────────────────────────┤
│ entries_per_element │ The number of entries per element in │
│ │ the local representation. │
├─────────────────────┼───────────────────────────────────────┤
│ ghost_corners │ The lower left corner and size of │
│ │ local region in each dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ global_sizes │ Global element counts in each │
│ │ dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ local_sizes │ Local elementwise sizes in each │
│ │ dimension. │
├─────────────────────┼───────────────────────────────────────┤
│ proc_sizes │ The number of processes in each │
│ │ dimension in the global │
│ │ decomposition. │
├─────────────────────┼───────────────────────────────────────┤
│ stencil_type │ Stencil type. │
├─────────────────────┼───────────────────────────────────────┤
│ stencil_width │ Elementwise stencil width. │
└─────────────────────┴───────────────────────────────────────┘
Methods Documentation
VecSplitToDMDA(vec, loc, c)
Return DMDA, Vec from a subgrid of a DMStag, its Vec.
Collective.
If a c value of -k is provided, the first k DOFs for that position are extracted, padding
with zero values if needed. If a non-negative value is provided, a single DOF is extracted.
Parameters
• vec (Vec) -- The Vec object.
• loc (StencilLocation) -- Which subgrid to extract.
• c (int) -- Which component to extract.
Return type
tuple[DMDA, Vec]
SEE ALSO:
DMStagVecSplitToDMDA
Source code at petsc4py/PETSc/DMStag.pyx:790
create(dim, dofs=None, sizes=None, boundary_types=None, stencil_type=None, stencil_width=None,
proc_sizes=None, ownership_ranges=None, comm=None, setUp=False)
Create a DMDA object.
Collective.
Creates an object to manage data living on the elements and vertices / the elements, faces,
and vertices / the elements, faces, edges, and vertices of a parallelized regular 1D / 2D /
3D grid.
Parameters
• dim (int) -- The number of dimensions.
• dofs (tuple[int, ...] | None) -- The number of degrees of freedom per vertex,
element (1D); vertex, face, element (2D); or vertex, edge, face, element (3D).
• sizes (tuple[int, ...] | None) -- The number of elements in each dimension.
• boundary_types (tuple[DM.BoundaryType | int | str | bool, ...] | None) -- The
boundary types.
• stencil_type (StencilType | None) -- The ghost/halo stencil type.
• stencil_width (int | None) -- The width of the ghost/halo region.
• proc_sizes (tuple[int, ...] | None) -- The number of processes in x, y, z
dimensions.
• ownership_ranges (tuple[Sequence[int], ...] | None) -- Local x, y, z element
counts, of length equal to proc_sizes, summing to sizes.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
• setUp (bool | None) -- Whether to call the setup routine after creating the
object.
Return type
Self
SEE ALSO:
DMStagCreate1d, DMStagCreate2d, DMStagCreate3d, DMSetUp
Source code at petsc4py/PETSc/DMStag.pyx:50
createCompatibleDMStag(dofs)
Create a compatible DMStag with different DOFs/stratum.
Collective.
Parameters
dofs (tuple[int, ...]) -- The number of DOFs on the strata in the new DMStag.
Return type
DM
SEE ALSO:
DMStagCreateCompatibleDMStag
Source code at petsc4py/PETSc/DMStag.pyx:766
get1dCoordinatecArrays()
Not implemented.
Source code at petsc4py/PETSc/DMStag.pyx:832
Return type
None
getBoundaryTypes()
Return boundary types in each dimension.
Not collective.
SEE ALSO:
setBoundaryTypes, DMStagGetBoundaryTypes
Source code at petsc4py/PETSc/DMStag.pyx:478
Return type
tuple[str, ...]
getCorners()
Return starting element index, width and number of partial elements.
Not collective.
The returned value is calculated excluding ghost points.
The number of extra partial elements is either 1 or 0. The value is 1 on right, top, and
front non-periodic domain ("physical") boundaries, in the x, y, and z dimensions
respectively, and otherwise 0.
SEE ALSO:
getGhostCorners, DMStagGetCorners, DMGetDimension
Source code at petsc4py/PETSc/DMStag.pyx:363
Return type
tuple[tuple[int, ...], tuple[int, ...], tuple[int, ...]]
getDim()
Return the number of dimensions.
Not collective.
Source code at petsc4py/PETSc/DMStag.pyx:310
Return type
int
getDof()
Get number of DOFs associated with each stratum of the grid.
Not collective.
SEE ALSO:
DMStagGetDOF
Source code at petsc4py/PETSc/DMStag.pyx:348
Return type
tuple[int, ...]
getEntriesPerElement()
Return the number of entries per element in the local representation.
Not collective.
This is the natural block size for most local operations.
SEE ALSO:
DMStagGetEntriesPerElement
Source code at petsc4py/PETSc/DMStag.pyx:318
Return type
int
getGhostCorners()
Return starting element index and width of local region.
Not collective.
SEE ALSO:
getCorners, DMStagGetGhostCorners
Source code at petsc4py/PETSc/DMStag.pyx:385
Return type
tuple[tuple[int, ...], tuple[int, ...]]
getGlobalSizes()
Return global element counts in each dimension.
Not collective.
SEE ALSO:
getLocalSizes, DMStagGetGlobalSizes
Source code at petsc4py/PETSc/DMStag.pyx:417
Return type
tuple[int, ...]
getIsFirstRank()
Return whether this process is first in each dimension in the process grid.
Not collective.
SEE ALSO:
DMStagGetIsFirstRank
Source code at petsc4py/PETSc/DMStag.pyx:496
Return type
tuple[int, ...]
getIsLastRank()
Return whether this process is last in each dimension in the process grid.
Not collective.
SEE ALSO:
DMStagGetIsLastRank
Source code at petsc4py/PETSc/DMStag.pyx:512
Return type
tuple[int, ...]
getLocalSizes()
Return local elementwise sizes in each dimension.
Not collective.
The returned value is calculated excluding ghost points.
SEE ALSO:
getGlobalSizes, DMStagGetLocalSizes
Source code at petsc4py/PETSc/DMStag.pyx:400
Return type
tuple[int, ...]
getLocationDof(loc)
Return number of DOFs associated with a given point on the grid.
Not collective.
Parameters
loc (StencilLocation) -- The grid point.
Return type
int
SEE ALSO:
DMStagGetLocationDOF
Source code at petsc4py/PETSc/DMStag.pyx:721
getLocationSlot(loc, c)
Return index to use in accessing raw local arrays.
Not collective.
Parameters
• loc (StencilLocation) -- Location relative to an element.
• c (int) -- Component.
Return type
int
SEE ALSO:
DMStagGetLocationSlot
Source code at petsc4py/PETSc/DMStag.pyx:678
getOwnershipRanges()
Return elements per process in each dimension.
Not collective.
SEE ALSO:
setOwnershipRanges, DMStagGetOwnershipRanges
Source code at petsc4py/PETSc/DMStag.pyx:461
Return type
tuple[Sequence[int], ...]
getProcSizes()
Return number of processes in each dimension.
Not collective.
SEE ALSO:
DMStagGetNumRanks
Source code at petsc4py/PETSc/DMStag.pyx:432
Return type
tuple[int, ...]
getProductCoordinateLocationSlot(loc)
Return slot for use with local product coordinate arrays.
Not collective.
Parameters
loc (StencilLocation) -- The grid location.
Return type
None
SEE ALSO:
DMStagGetProductCoordinateLocationSlot
Source code at petsc4py/PETSc/DMStag.pyx:701
getStencilType()
Return elementwise ghost/halo stencil type.
Not collective.
SEE ALSO:
setStencilType, DMStagGetStencilType
Source code at petsc4py/PETSc/DMStag.pyx:447
Return type
str
getStencilWidth()
Return elementwise stencil width.
Not collective.
SEE ALSO:
DMStagGetStencilWidth
Source code at petsc4py/PETSc/DMStag.pyx:334
Return type
int
getVecArray(vec)
Not implemented.
Source code at petsc4py/PETSc/DMStag.pyx:828
Parameters
vec (Vec)
Return type
None
migrateVec(vec, dmTo, vecTo)
Transfer a vector between two DMStag objects.
Collective.
Currently only implemented to migrate global vectors to global vectors.
Parameters
• vec (Vec) -- The source vector.
• dmTo (DM) -- The compatible destination object.
• vecTo (Vec) -- The destination vector.
Return type
None
SEE ALSO:
DMStagMigrateVec
Source code at petsc4py/PETSc/DMStag.pyx:743
setBoundaryTypes(boundary_types)
Set the boundary types.
Logically collective.
Parameters
boundary_types (tuple[BoundaryType | int | str | bool, ...]) -- Boundary types for
one/two/three dimensions.
Return type
None
SEE ALSO:
getBoundaryTypes, DMStagSetBoundaryTypes
Source code at petsc4py/PETSc/DMStag.pyx:201
setCoordinateDMType(dmtype)
Set the type to store coordinates.
Logically collective.
Parameters
dmtype (Type) -- The type to store coordinates.
Return type
None
SEE ALSO:
DMStagSetCoordinateDMType
Source code at petsc4py/PETSc/DMStag.pyx:657
setDof(dofs)
Set DOFs/stratum.
Logically collective.
Parameters
dofs (tuple[int, ...]) -- The number of points per 0-cell (vertex/node), 1-cell
(element in 1D, edge in 2D and 3D), 2-cell (element in 2D, face in 3D), or 3-cell
(element in 3D).
Return type
None
SEE ALSO:
DMStagSetDOF
Source code at petsc4py/PETSc/DMStag.pyx:224
setGlobalSizes(sizes)
Set global element counts in each dimension.
Logically collective.
Parameters
sizes (tuple[int, ...]) -- Global elementwise size in the one/two/three dimensions.
Return type
None
SEE ALSO:
DMStagSetGlobalSizes
Source code at petsc4py/PETSc/DMStag.pyx:246
setOwnershipRanges(ranges)
Set elements per process in each dimension.
Logically collective.
Parameters
ranges (tuple[Sequence[int], ...]) -- Element counts for each process in
one/two/three dimensions.
Return type
None
SEE ALSO:
getOwnershipRanges, DMStagSetOwnershipRanges
Source code at petsc4py/PETSc/DMStag.pyx:286
setProcSizes(sizes)
Set the number of processes in each dimension in the global process grid.
Logically collective.
Parameters
sizes (tuple[int, ...]) -- Number of processes in one/two/three dimensions.
Return type
None
SEE ALSO:
DMStagSetNumRanks
Source code at petsc4py/PETSc/DMStag.pyx:266
setStencilType(stenciltype)
Set elementwise ghost/halo stencil type.
Logically collective.
Parameters
stenciltype (StencilType | str) -- The elementwise ghost stencil type.
Return type
None
SEE ALSO:
getStencilType, DMStagSetStencilType
Source code at petsc4py/PETSc/DMStag.pyx:183
setStencilWidth(swidth)
Set elementwise stencil width.
Logically collective.
The width value is not used when StencilType.NONE is specified.
Parameters
swidth (int) -- Stencil/halo/ghost width in elements.
Return type
None
SEE ALSO:
DMStagSetStencilWidth
Source code at petsc4py/PETSc/DMStag.pyx:163
setUniformCoordinates(xmin=0, xmax=1, ymin=0, ymax=1, zmin=0, zmax=1)
Set the coordinates to be a uniform grid..
Collective.
Local coordinates are populated, linearly extrapolated to ghost cells, including those
outside the physical domain. This is also done in case of periodic boundaries, meaning that
the same global point may have different coordinates in different local representations,
which are equivalent assuming a periodicity implied by the arguments to this function,
i.e., two points are equivalent if their difference is a multiple of xmax-xmin in the x
dimension, ymax-ymin in the y dimension, and zmax-zmin in the z dimension.
Parameters
• xmin (float) -- The minimum global coordinate value in the x dimension.
• xmax (float) -- The maximum global coordinate value in the x dimension.
• ymin (float) -- The minimum global coordinate value in the y dimension.
• ymax (float) -- The maximum global coordinate value in the y dimension.
• zmin (float) -- The minimum global coordinate value in the z dimension.
• zmax (float) -- The maximum global coordinate value in the z dimension.
Return type
None
SEE ALSO:
setUniformCoordinatesExplicit, setUniformCoordinatesProduct, DMStagSetUniformCoordinates
Source code at petsc4py/PETSc/DMStag.pyx:610
setUniformCoordinatesExplicit(xmin=0, xmax=1, ymin=0, ymax=1, zmin=0, zmax=1)
Set coordinates to be a uniform grid, storing all values.
Collective.
Parameters
• xmin (float) -- The minimum global coordinate value in the x dimension.
• xmax (float) -- The maximum global coordinate value in the x dimension.
• ymin (float) -- The minimum global coordinate value in the y dimension.
• ymax (float) -- The maximum global coordinate value in the y dimension.
• zmin (float) -- The minimum global coordinate value in the z dimension.
• zmax (float) -- The maximum global coordinate value in the z dimension.
Return type
None
SEE ALSO:
setUniformCoordinatesProduct, setUniformCoordinates, DMStagSetUniformCoordinatesExplicit
Source code at petsc4py/PETSc/DMStag.pyx:530
setUniformCoordinatesProduct(xmin=0, xmax=1, ymin=0, ymax=1, zmin=0, zmax=1)
Create uniform coordinates, as a product of 1D arrays.
Collective.
The per-dimension 1-dimensional DMStag objects that comprise the product always have active
0-cells (vertices, element boundaries) and 1-cells (element centers).
Parameters
• xmin (float) -- The minimum global coordinate value in the x dimension.
• xmax (float) -- The maximum global coordinate value in the x dimension.
• ymin (float) -- The minimum global coordinate value in the y dimension.
• ymax (float) -- The maximum global coordinate value in the y dimension.
• zmin (float) -- The minimum global coordinate value in the z dimension.
• zmax (float) -- The maximum global coordinate value in the z dimension.
Return type
None
SEE ALSO:
setUniformCoordinatesExplicit, setUniformCoordinates, DMStagSetUniformCoordinatesProduct
Source code at petsc4py/PETSc/DMStag.pyx:568
Attributes Documentation
boundary_types
Boundary types in each dimension.
Source code at petsc4py/PETSc/DMStag.pyx:866
corners
The lower left corner and size of local region in each dimension.
Source code at petsc4py/PETSc/DMStag.pyx:881
dim The dimension.
Source code at petsc4py/PETSc/DMStag.pyx:836
dofs The number of DOFs associated with each stratum of the grid.
Source code at petsc4py/PETSc/DMStag.pyx:841
entries_per_element
The number of entries per element in the local representation.
Source code at petsc4py/PETSc/DMStag.pyx:846
ghost_corners
The lower left corner and size of local region in each dimension.
Source code at petsc4py/PETSc/DMStag.pyx:886
global_sizes
Global element counts in each dimension.
Source code at petsc4py/PETSc/DMStag.pyx:851
local_sizes
Local elementwise sizes in each dimension.
Source code at petsc4py/PETSc/DMStag.pyx:856
proc_sizes
The number of processes in each dimension in the global decomposition.
Source code at petsc4py/PETSc/DMStag.pyx:861
stencil_type
Stencil type.
Source code at petsc4py/PETSc/DMStag.pyx:871
stencil_width
Elementwise stencil width.
Source code at petsc4py/PETSc/DMStag.pyx:876
petsc4py.PETSc.DMSwarm
class petsc4py.PETSc.DMSwarm
Bases: DM
A DM object used to represent arrays of data (fields) of arbitrary type.
Enumerations
┌───────────────┬─────────────────────────┐
│ CollectType │ Swarm collection types. │
├───────────────┼─────────────────────────┤
│ MigrateType │ Swarm migration types. │
├───────────────┼─────────────────────────┤
│ PICLayoutType │ Swarm PIC layout types. │
├───────────────┼─────────────────────────┤
│ Type │ Swarm types. │
└───────────────┴─────────────────────────┘
petsc4py.PETSc.DMSwarm.CollectType
class petsc4py.PETSc.DMSwarm.CollectType
Bases: object
Swarm collection types.
Attributes Summary
┌─────────────────────────┬───────────────────────────────────────┐
│ COLLECT_BASIC │ Constant COLLECT_BASIC of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ COLLECT_DMDABOUNDINGBOX │ Constant COLLECT_DMDABOUNDINGBOX of │
│ │ type int │
├─────────────────────────┼───────────────────────────────────────┤
│ COLLECT_GENERAL │ Constant COLLECT_GENERAL of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ COLLECT_USER │ Constant COLLECT_USER of type int │
└─────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
COLLECT_BASIC: int = COLLECT_BASIC
Constant COLLECT_BASIC of type int
COLLECT_DMDABOUNDINGBOX: int = COLLECT_DMDABOUNDINGBOX
Constant COLLECT_DMDABOUNDINGBOX of type int
COLLECT_GENERAL: int = COLLECT_GENERAL
Constant COLLECT_GENERAL of type int
COLLECT_USER: int = COLLECT_USER
Constant COLLECT_USER of type int
petsc4py.PETSc.DMSwarm.MigrateType
class petsc4py.PETSc.DMSwarm.MigrateType
Bases: object
Swarm migration types.
Attributes Summary
┌────────────────────────┬───────────────────────────────────────┐
│ MIGRATE_BASIC │ Constant MIGRATE_BASIC of type int │
├────────────────────────┼───────────────────────────────────────┤
│ MIGRATE_DMCELLEXACT │ Constant MIGRATE_DMCELLEXACT of type │
│ │ int │
├────────────────────────┼───────────────────────────────────────┤
│ MIGRATE_DMCELLNSCATTER │ Constant MIGRATE_DMCELLNSCATTER of │
│ │ type int │
├────────────────────────┼───────────────────────────────────────┤
│ MIGRATE_USER │ Constant MIGRATE_USER of type int │
└────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
MIGRATE_BASIC: int = MIGRATE_BASIC
Constant MIGRATE_BASIC of type int
MIGRATE_DMCELLEXACT: int = MIGRATE_DMCELLEXACT
Constant MIGRATE_DMCELLEXACT of type int
MIGRATE_DMCELLNSCATTER: int = MIGRATE_DMCELLNSCATTER
Constant MIGRATE_DMCELLNSCATTER of type int
MIGRATE_USER: int = MIGRATE_USER
Constant MIGRATE_USER of type int
petsc4py.PETSc.DMSwarm.PICLayoutType
class petsc4py.PETSc.DMSwarm.PICLayoutType
Bases: object
Swarm PIC layout types.
Attributes Summary
┌────────────────────┬───────────────────────────────────────┐
│ LAYOUT_GAUSS │ Constant LAYOUT_GAUSS of type int │
├────────────────────┼───────────────────────────────────────┤
│ LAYOUT_REGULAR │ Constant LAYOUT_REGULAR of type int │
├────────────────────┼───────────────────────────────────────┤
│ LAYOUT_SUBDIVISION │ Constant LAYOUT_SUBDIVISION of type ‐ │
│ │ int │
└────────────────────┴───────────────────────────────────────┘
Attributes Documentation
LAYOUT_GAUSS: int = LAYOUT_GAUSS
Constant LAYOUT_GAUSS of type int
LAYOUT_REGULAR: int = LAYOUT_REGULAR
Constant LAYOUT_REGULAR of type int
LAYOUT_SUBDIVISION: int = LAYOUT_SUBDIVISION
Constant LAYOUT_SUBDIVISION of type int
petsc4py.PETSc.DMSwarm.Type
class petsc4py.PETSc.DMSwarm.Type
Bases: object
Swarm types.
Attributes Summary
┌───────┬────────────────────────────┐
│ BASIC │ Constant BASIC of type int │
├───────┼────────────────────────────┤
│ PIC │ Constant PIC of type int │
└───────┴────────────────────────────┘
Attributes Documentation
BASIC: int = BASIC
Constant BASIC of type int
PIC: int = PIC
Constant PIC of type int
Methods Summary
┌──────────────────────────────────────────┬───────────────────────────────────────┐
│ addNPoints(npoints) │ Add space for a number of new points │
│ │ in the DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ addPoint() │ Add space for one new point in the │
│ │ DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ collectViewCreate() │ Apply a collection method and gather │
│ │ points in neighbor ranks. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ collectViewDestroy() │ Reset the DMSwarm to the size prior │
│ │ to calling collectViewCreate. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ copyPoint(pi, pj) │ Copy point pi to point pj in the │
│ │ DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create an empty DM object and set its │
│ │ type to DM.Type.SWARM. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ createGlobalVectorFromField(fieldname) │ Create a global Vec object associated │
│ │ with a given field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ createLocalVectorFromField(fieldname) │ Create a local Vec object associated │
│ │ with a given field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ destroyGlobalVectorFromField(fieldname) │ Destroy the global Vec object │
│ │ associated with a given field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ destroyLocalVectorFromField(fieldname) │ Destroy the local Vec object │
│ │ associated with a given field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ finalizeFieldRegister() │ Finalize the registration of fields │
│ │ to a DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ getCellDM() │ Return DM cell attached to DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ getField(fieldname) │ Return arrays storing all entries │
│ │ associated with a field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSize() │ Return the local length of fields │
│ │ registered. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ getSize() │ Return the total length of fields │
│ │ registered. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ initializeFieldRegister() │ Initiate the registration of fields │
│ │ to a DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ insertPointUsingCellDM(layoutType, │ Insert point coordinates within each │
│ fill_param) │ cell. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ migrate([remove_sent_points]) │ Relocate points defined in the │
│ │ DMSwarm to other MPI ranks. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ projectFields(dm, fieldnames, vecs[, │ Project a set of DMSwarm fields onto │
│ mode]) │ the cell DM. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ registerField(fieldname, blocksize[, │ Register a field to a DMSwarm with a │
│ dtype]) │ native PETSc data type. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ removePoint() │ Remove the last point from the │
│ │ DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ removePointAtIndex(index) │ Remove a specific point from the │
│ │ DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ restoreField(fieldname) │ Restore accesses associated with a │
│ │ registered field. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setCellDM(dm) │ Attach a DM to a DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setLocalSizes(nlocal, buffer) │ Set the length of all registered │
│ │ fields on the DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setPointCoordinates(coordinates[, ...]) │ Set point coordinates in a DMSwarm │
│ │ from a user-defined list. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setPointCoordinatesCellwise(coordinates) │ Insert point coordinates within each │
│ │ cell. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setPointsUniformCoordinates(min, max, │ Set point coordinates in a DMSwarm on │
│ npoints) │ a regular (ijk) grid. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ setType(dmswarm_type) │ Set particular flavor of DMSwarm. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortGetAccess() │ Setup up a DMSwarm point sort │
│ │ context. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortGetIsValid() │ Return whether the sort context is │
│ │ up-to-date. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortGetNumberOfPointsPerCell(e) │ Return the number of points in a │
│ │ cell. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortGetPointsPerCell(e) │ Create an array of point indices for │
│ │ all points in a cell. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortGetSizes() │ Return the sizes associated with a │
│ │ DMSwarm point sorting context. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ sortRestoreAccess() │ Invalidate the DMSwarm point sorting │
│ │ context. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ vectorDefineField(fieldname) │ Set the field from which to define a │
│ │ Vec object. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ viewFieldsXDMF(filename, fieldnames) │ Write a selection of DMSwarm fields │
│ │ to an XDMF3 file. │
├──────────────────────────────────────────┼───────────────────────────────────────┤
│ viewXDMF(filename) │ Write this DMSwarm fields to an XDMF3 │
│ │ file. │
└──────────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
addNPoints(npoints)
Add space for a number of new points in the DMSwarm.
Not collective.
Parameters
npoints (int) -- The number of new points to add.
Return type
None
SEE ALSO:
DMSwarmAddNPoints
Source code at petsc4py/PETSc/DMSwarm.pyx:329
addPoint()
Add space for one new point in the DMSwarm.
Not collective.
SEE ALSO:
DMSwarmAddPoint
Source code at petsc4py/PETSc/DMSwarm.pyx:317
Return type
None
collectViewCreate()
Apply a collection method and gather points in neighbor ranks.
Collective.
SEE ALSO:
collectViewDestroy, DMSwarmCollectViewCreate
Source code at petsc4py/PETSc/DMSwarm.pyx:445
Return type
None
collectViewDestroy()
Reset the DMSwarm to the size prior to calling collectViewCreate.
Collective.
SEE ALSO:
collectViewCreate, DMSwarmCollectViewDestroy
Source code at petsc4py/PETSc/DMSwarm.pyx:457
Return type
None
copyPoint(pi, pj)
Copy point pi to point pj in the DMSwarm.
Not collective.
Parameters
• pi (int) -- The index of the point to copy (source).
• pj (int) -- The point index where the copy should be located (destination).
Return type
None
SEE ALSO:
DMSwarmCopyPoint
Source code at petsc4py/PETSc/DMSwarm.pyx:377
create(comm=None)
Create an empty DM object and set its type to DM.Type.SWARM.
Collective.
DMs are the abstract objects in PETSc that mediate between meshes and discretizations and
the algebraic solvers, time integrators, and optimization algorithms.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
DMCreate, DMSetType
Source code at petsc4py/PETSc/DMSwarm.pyx:39
createGlobalVectorFromField(fieldname)
Create a global Vec object associated with a given field.
Collective.
The vector must be returned to the DMSwarm using a matching call to
destroyGlobalVectorFromField.
Parameters
fieldname (str) -- The textual name given to a registered field.
Return type
Vec
SEE ALSO:
destroyGlobalVectorFromField, DMSwarmCreateGlobalVectorFromField
Source code at petsc4py/PETSc/DMSwarm.pyx:65
createLocalVectorFromField(fieldname)
Create a local Vec object associated with a given field.
Collective.
The vector must be returned to the DMSwarm using a matching call to
destroyLocalVectorFromField.
Parameters
fieldname (str) -- The textual name given to a registered field.
Return type
Vec
SEE ALSO:
destroyLocalVectorFromField, DMSwarmCreateLocalVectorFromField
Source code at petsc4py/PETSc/DMSwarm.pyx:109
destroyGlobalVectorFromField(fieldname)
Destroy the global Vec object associated with a given field.
Collective.
Parameters
fieldname (str) -- The textual name given to a registered field.
Return type
None
SEE ALSO:
createGlobalVectorFromField, DMSwarmDestroyGlobalVectorFromField
Source code at petsc4py/PETSc/DMSwarm.pyx:89
destroyLocalVectorFromField(fieldname)
Destroy the local Vec object associated with a given field.
Collective.
Parameters
fieldname (str) -- The textual name given to a registered field.
Return type
None
SEE ALSO:
createLocalVectorFromField, DMSwarmDestroyLocalVectorFromField
Source code at petsc4py/PETSc/DMSwarm.pyx:133
finalizeFieldRegister()
Finalize the registration of fields to a DMSwarm.
Collective.
SEE ALSO:
initializeFieldRegister, DMSwarmFinalizeFieldRegister
Source code at petsc4py/PETSc/DMSwarm.pyx:167
Return type
None
getCellDM()
Return DM cell attached to DMSwarm.
Collective.
SEE ALSO:
setCellDM, DMSwarmGetCellDM
Source code at petsc4py/PETSc/DMSwarm.pyx:486
Return type
DM
getField(fieldname)
Return arrays storing all entries associated with a field.
Not collective.
The returned array contains underlying values of the field.
The array must be returned to the DMSwarm using a matching call to restoreField.
Parameters
fieldname (str) -- The textual name to identify this field.
Returns
The type of the entries in the array will match the type of the field.
Return type
numpy.ndarray
SEE ALSO:
restoreField, DMSwarmGetField
Source code at petsc4py/PETSc/DMSwarm.pyx:231
getLocalSize()
Return the local length of fields registered.
Not collective.
SEE ALSO:
DMSwarmGetLocalSize
Source code at petsc4py/PETSc/DMSwarm.pyx:398
Return type
int
getSize()
Return the total length of fields registered.
Collective.
SEE ALSO:
DMSwarmGetSize
Source code at petsc4py/PETSc/DMSwarm.pyx:412
Return type
int
initializeFieldRegister()
Initiate the registration of fields to a DMSwarm.
Collective.
After all fields have been registered, you must call finalizeFieldRegister.
SEE ALSO:
finalizeFieldRegister, DMSwarmInitializeFieldRegister
Source code at petsc4py/PETSc/DMSwarm.pyx:153
Return type
None
insertPointUsingCellDM(layoutType, fill_param)
Insert point coordinates within each cell.
Not collective.
Parameters
• layout_type -- Method used to fill each cell with the cell DM.
• fill_param (int) -- Parameter controlling how many points per cell are added (the
meaning of this parameter is dependent on the layout type).
• layoutType (PICLayoutType)
Return type
None
SEE ALSO:
DMSwarmInsertPointsUsingCellDM
Source code at petsc4py/PETSc/DMSwarm.pyx:601
migrate(remove_sent_points=False)
Relocate points defined in the DMSwarm to other MPI ranks.
Collective.
Parameters
remove_sent_points (bool) -- Flag indicating if sent points should be removed from
the current MPI rank.
Return type
None
SEE ALSO:
DMSwarmMigrate
Source code at petsc4py/PETSc/DMSwarm.pyx:426
projectFields(dm, fieldnames, vecs, mode=None)
Project a set of DMSwarm fields onto the cell DM.
Collective.
Parameters
• dm (DM) -- The continuum DM.
• fieldnames (Sequence[str]) -- The textual names of the swarm fields to project.
• vecs (Sequence[Vec])
• mode (ScatterModeSpec)
Return type
None
SEE ALSO:
DMSwarmProjectFields
Source code at petsc4py/PETSc/DMSwarm.pyx:810
registerField(fieldname, blocksize, dtype=ScalarType)
Register a field to a DMSwarm with a native PETSc data type.
Collective.
Parameters
• fieldname (str) -- The textual name to identify this field.
• blocksize (int) -- The number of each data type.
• dtype (dtype) -- A valid PETSc data type.
Return type
None
SEE ALSO:
DMSwarmRegisterPetscDatatypeField
Source code at petsc4py/PETSc/DMSwarm.pyx:201
removePoint()
Remove the last point from the DMSwarm.
Not collective.
SEE ALSO:
DMSwarmRemovePoint
Source code at petsc4py/PETSc/DMSwarm.pyx:347
Return type
None
removePointAtIndex(index)
Remove a specific point from the DMSwarm.
Not collective.
Parameters
index (int) -- Index of point to remove
Return type
None
SEE ALSO:
DMSwarmRemovePointAtIndex
Source code at petsc4py/PETSc/DMSwarm.pyx:359
restoreField(fieldname)
Restore accesses associated with a registered field.
Not collective.
Parameters
fieldname (str) -- The textual name to identify this field.
Return type
None
SEE ALSO:
getField, DMSwarmRestoreField
Source code at petsc4py/PETSc/DMSwarm.pyx:274
setCellDM(dm)
Attach a DM to a DMSwarm.
Collective.
Parameters
dm (DM) -- The DM to attach to the DMSwarm.
Return type
None
SEE ALSO:
getCellDM, DMSwarmSetCellDM
Source code at petsc4py/PETSc/DMSwarm.pyx:469
setLocalSizes(nlocal, buffer)
Set the length of all registered fields on the DMSwarm.
Not collective.
Parameters
• nlocal (int) -- The length of each registered field.
• buffer (int) -- The length of the buffer used for efficient dynamic resizing.
Return type
Self
SEE ALSO:
DMSwarmSetLocalSizes
Source code at petsc4py/PETSc/DMSwarm.pyx:179
setPointCoordinates(coordinates, redundant=False, mode=None)
Set point coordinates in a DMSwarm from a user-defined list.
Collective.
Parameters
• coordinates (Sequence[float]) -- The coordinate values.
• redundant (bool) -- If set to True, it is assumed that coordinates are only valid
on rank 0 and should be broadcast to other ranks.
• mode (InsertMode | None) -- Indicates whether to append points to the swarm (‐
InsertMode.ADD), or override existing points (InsertMode.INSERT).
Return type
None
SEE ALSO:
DMSwarmSetPointCoordinates
Source code at petsc4py/PETSc/DMSwarm.pyx:565
setPointCoordinatesCellwise(coordinates)
Insert point coordinates within each cell.
Not collective.
Point coordinates are defined over the reference cell.
Parameters
coordinates (Sequence[float]) -- The coordinates (defined in the local coordinate
system for each cell) to insert.
Return type
None
SEE ALSO:
DMSwarmSetPointCoordinatesCellwise
Source code at petsc4py/PETSc/DMSwarm.pyx:623
setPointsUniformCoordinates(min, max, npoints, mode=None)
Set point coordinates in a DMSwarm on a regular (ijk) grid.
Collective.
Parameters
• min (Sequence[float]) -- Minimum coordinate values in the x, y, z directions
(array of length dim).
• max (Sequence[float]) -- Maximum coordinate values in the x, y, z directions
(array of length dim).
• npoints (Sequence[int]) -- Number of points in each spatial direction (array of
length dim).
• mode (InsertMode | None) -- Indicates whether to append points to the swarm (‐
InsertMode.ADD), or override existing points (InsertMode.INSERT).
Return type
Self
SEE ALSO:
DMSwarmSetPointsUniformCoordinates
Source code at petsc4py/PETSc/DMSwarm.pyx:521
setType(dmswarm_type)
Set particular flavor of DMSwarm.
Collective.
Parameters
dmswarm_type (Type | str) -- The DMSwarm type.
Return type
None
SEE ALSO:
DMSwarmSetType
Source code at petsc4py/PETSc/DMSwarm.pyx:503
sortGetAccess()
Setup up a DMSwarm point sort context.
Not collective.
The point sort context is used for efficient traversal of points within a cell.
You must call sortRestoreAccess when you no longer need access to the sort context.
SEE ALSO:
sortRestoreAccess, DMSwarmSortGetAccess
Source code at petsc4py/PETSc/DMSwarm.pyx:698
Return type
None
sortGetIsValid()
Return whether the sort context is up-to-date.
Not collective.
Returns the flag associated with a DMSwarm point sorting context.
SEE ALSO:
DMSwarmSortGetIsValid
Source code at petsc4py/PETSc/DMSwarm.pyx:772
Return type
bool
sortGetNumberOfPointsPerCell(e)
Return the number of points in a cell.
Not collective.
Parameters
e (int) -- The index of the cell.
Return type
int
SEE ALSO:
DMSwarmSortGetNumberOfPointsPerCell
Source code at petsc4py/PETSc/DMSwarm.pyx:752
sortGetPointsPerCell(e)
Create an array of point indices for all points in a cell.
Not collective.
Parameters
e (int) -- The index of the cell.
Return type
list[int]
SEE ALSO:
DMSwarmSortGetPointsPerCell
Source code at petsc4py/PETSc/DMSwarm.pyx:728
sortGetSizes()
Return the sizes associated with a DMSwarm point sorting context.
Not collective.
Returns
• ncells (int) -- Number of cells within the sort context.
• npoints (int) -- Number of points used to create the sort context.
Return type
tuple[int, int]
SEE ALSO:
DMSwarmSortGetSizes
Source code at petsc4py/PETSc/DMSwarm.pyx:788
sortRestoreAccess()
Invalidate the DMSwarm point sorting context.
Not collective.
SEE ALSO:
sortGetAccess, DMSwarmSortRestoreAccess
Source code at petsc4py/PETSc/DMSwarm.pyx:716
Return type
None
vectorDefineField(fieldname)
Set the field from which to define a Vec object.
Collective.
The field will be used when DM.createLocalVec, or DM.createGlobalVec is called.
Parameters
fieldname (str) -- The textual name given to a registered field.
Return type
None
SEE ALSO:
DMSwarmVectorDefineField
Source code at petsc4py/PETSc/DMSwarm.pyx:295
viewFieldsXDMF(filename, fieldnames)
Write a selection of DMSwarm fields to an XDMF3 file.
Collective.
Parameters
• filename (str) -- The file name of the XDMF file (must have the extension .xmf).
• fieldnames (Sequence[str]) -- Array containing the textual names of fields to
write.
Return type
None
SEE ALSO:
DMSwarmViewFieldsXDMF
Source code at petsc4py/PETSc/DMSwarm.pyx:650
viewXDMF(filename)
Write this DMSwarm fields to an XDMF3 file.
Collective.
Parameters
filename (str) -- The file name of the XDMF file (must have the extension .xmf).
Return type
None
SEE ALSO:
DMSwarmViewXDMF
Source code at petsc4py/PETSc/DMSwarm.pyx:679
petsc4py.PETSc.DS
class petsc4py.PETSc.DS
Bases: Object
Discrete System object.
Enumerations
┌──────┬────────────────────────────┐
│ Type │ The Discrete System types. │
└──────┴────────────────────────────┘
petsc4py.PETSc.DS.Type
class petsc4py.PETSc.DS.Type
Bases: object
The Discrete System types.
Attributes Summary
┌───────┬──────────────────────────┐
│ BASIC │ Object BASIC of type str │
└───────┴──────────────────────────┘
Attributes Documentation
BASIC: str = BASIC
Object BASIC of type str
Methods Summary
┌────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create an empty DS. │
├────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the discrete system. │
├────────────────────────────┼───────────────────────────────────────┤
│ getComponents() │ Return the number of components for │
│ │ each field on an evaluation point. │
├────────────────────────────┼───────────────────────────────────────┤
│ getCoordinateDimension() │ Return the coordinate dimension of │
│ │ the DS. │
├────────────────────────────┼───────────────────────────────────────┤
│ getDimensions() │ Return the size of the space for each │
│ │ field on an evaluation point. │
├────────────────────────────┼───────────────────────────────────────┤
│ getFieldIndex(disc) │ Return the index of the given field. │
├────────────────────────────┼───────────────────────────────────────┤
│ getNumFields() │ Return the number of fields in the │
│ │ DS. │
├────────────────────────────┼───────────────────────────────────────┤
│ getSpatialDimension() │ Return the spatial dimension of the │
│ │ DS. │
├────────────────────────────┼───────────────────────────────────────┤
│ getTotalComponents() │ Return the total number of components │
│ │ in this system. │
├────────────────────────────┼───────────────────────────────────────┤
│ getTotalDimensions() │ Return the total size of the │
│ │ approximation space for this system. │
├────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the discrete │
│ │ system. │
├────────────────────────────┼───────────────────────────────────────┤
│ setDiscretisation(f, disc) │ Set the discretization object for the │
│ │ given field. │
├────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set parameters in a DS from the │
│ │ options database. │
├────────────────────────────┼───────────────────────────────────────┤
│ setType(ds_type) │ Build a particular type of a discrete │
│ │ system. │
├────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Construct data structures for the │
│ │ discrete system. │
├────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a discrete system. │
└────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create an empty DS.
Collective.
The type can then be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
setType, destroy, PetscDSCreate
Source code at petsc4py/PETSc/DS.pyx:53
destroy()
Destroy the discrete system.
Collective.
SEE ALSO:
create, PetscDSDestroy
Source code at petsc4py/PETSc/DS.pyx:40
Return type
Self
getComponents()
Return the number of components for each field on an evaluation point.
Not collective.
SEE ALSO:
PetscDSGetComponents
Source code at petsc4py/PETSc/DS.pyx:246
Return type
ArrayInt
getCoordinateDimension()
Return the coordinate dimension of the DS.
Not collective.
The coordinate dimension of the DS is the dimension of the space into which the
discretiaztions are embedded.
SEE ALSO:
PetscDSGetCoordinateDimension
Source code at petsc4py/PETSc/DS.pyx:153
Return type
int
getDimensions()
Return the size of the space for each field on an evaluation point.
Not collective.
SEE ALSO:
PetscDSGetDimensions
Source code at petsc4py/PETSc/DS.pyx:231
Return type
ArrayInt
getFieldIndex(disc)
Return the index of the given field.
Not collective.
Parameters
disc (Object) -- The discretization object.
Return type
int
SEE ALSO:
PetscDSGetFieldIndex
Source code at petsc4py/PETSc/DS.pyx:184
getNumFields()
Return the number of fields in the DS.
Not collective.
SEE ALSO:
PetscDSGetNumFields
Source code at petsc4py/PETSc/DS.pyx:170
Return type
int
getSpatialDimension()
Return the spatial dimension of the DS.
Not collective.
The spatial dimension of the DS is the topological dimension of the discretizations.
SEE ALSO:
PetscDSGetSpatialDimension
Source code at petsc4py/PETSc/DS.pyx:136
Return type
int
getTotalComponents()
Return the total number of components in this system.
Not collective.
SEE ALSO:
PetscDSGetTotalComponents
Source code at petsc4py/PETSc/DS.pyx:217
Return type
int
getTotalDimensions()
Return the total size of the approximation space for this system.
Not collective.
SEE ALSO:
PetscDSGetTotalDimension
Source code at petsc4py/PETSc/DS.pyx:203
Return type
int
getType()
Return the type of the discrete system.
Not collective.
SEE ALSO:
setType, PetscDSGetType
Source code at petsc4py/PETSc/DS.pyx:95
Return type
str
setDiscretisation(f, disc)
Set the discretization object for the given field.
Not collective.
Parameters
• f (int) -- The field number.
• disc (Object) -- The discretization object.
Return type
None
SEE ALSO:
PetscDSSetDiscretization
Source code at petsc4py/PETSc/DS.pyx:261
setFromOptions()
Set parameters in a DS from the options database.
Collective.
SEE ALSO:
Working with PETSc options, PetscDSSetFromOptions
Source code at petsc4py/PETSc/DS.pyx:109
Return type
None
setType(ds_type)
Build a particular type of a discrete system.
Collective.
Parameters
ds_type (Type | str) -- The type of the discrete system.
Return type
None
SEE ALSO:
getType, PetscDSSetType
Source code at petsc4py/PETSc/DS.pyx:76
setUp()
Construct data structures for the discrete system.
Collective.
SEE ALSO:
PetscDSSetUp
Source code at petsc4py/PETSc/DS.pyx:121
Return type
Self
view(viewer=None)
View a discrete system.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the system.
Return type
None
SEE ALSO:
PetscDSView
Source code at petsc4py/PETSc/DS.pyx:21
petsc4py.PETSc.Device
class petsc4py.PETSc.Device
Bases: object
The device object.
Represents a handle to an accelerator (which may be the host).
SEE ALSO:
DeviceContext, PetscDevice
Enumerations
┌──────┬─────────────────────┐
│ Type │ The type of device. │
└──────┴─────────────────────┘
petsc4py.PETSc.Device.Type
class petsc4py.PETSc.Device.Type
Bases: object
The type of device.
SEE ALSO:
Device, Device.create, Device.getDeviceType, Device.type, PetscDeviceType
Attributes Summary
┌─────────┬──────────────────────────────┐
│ CUDA │ Constant CUDA of type int │
├─────────┼──────────────────────────────┤
│ DEFAULT │ Constant DEFAULT of type int │
├─────────┼──────────────────────────────┤
│ HIP │ Constant HIP of type int │
├─────────┼──────────────────────────────┤
│ HOST │ Constant HOST of type int │
├─────────┼──────────────────────────────┤
│ SYCL │ Constant SYCL of type int │
└─────────┴──────────────────────────────┘
Attributes Documentation
CUDA: int = CUDA
Constant CUDA of type int
DEFAULT: int = DEFAULT
Constant DEFAULT of type int
HIP: int = HIP
Constant HIP of type int
HOST: int = HOST
Constant HOST of type int
SYCL: int = SYCL
Constant SYCL of type int
Methods Summary
┌─────────────────────────────┬───────────────────────────────────────┐
│ configure() │ Configure and setup a device object. │
├─────────────────────────────┼───────────────────────────────────────┤
│ create([dtype, device_id]) │ Create a device object. │
├─────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy a device object. │
├─────────────────────────────┼───────────────────────────────────────┤
│ getDeviceId() │ Return the device id. │
├─────────────────────────────┼───────────────────────────────────────┤
│ getDeviceType() │ Return the type of the device. │
├─────────────────────────────┼───────────────────────────────────────┤
│ setDefaultType(device_type) │ Set the device type to be used as the │
│ │ default in subsequent calls to │
│ │ create. │
├─────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a device object. │
└─────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────┬──────────────────┐
│ device_id │ The device id. │
├───────────┼──────────────────┤
│ type │ The device type. │
└───────────┴──────────────────┘
Methods Documentation
configure()
Configure and setup a device object.
Not collective.
SEE ALSO:
create, PetscDeviceConfigure
Source code at petsc4py/PETSc/Device.pyx:132
Return type
None
classmethod create(dtype=None, device_id=DECIDE)
Create a device object.
Not collective.
Parameters
• dtype (Type | None) -- The type of device to create (or None for the default).
• device_id (int) -- The numeric id of the device to create.
Return type
Device
SEE ALSO:
destroy, PetscDeviceCreate
Source code at petsc4py/PETSc/Device.pyx:94
destroy()
Destroy a device object.
Not collective.
SEE ALSO:
create, PetscDeviceDestroy
Source code at petsc4py/PETSc/Device.pyx:120
Return type
None
getDeviceId()
Return the device id.
Not collective.
SEE ALSO:
create, PetscDeviceGetDeviceId
Source code at petsc4py/PETSc/Device.pyx:180
Return type
int
getDeviceType()
Return the type of the device.
Not collective.
SEE ALSO:
type, PetscDeviceGetType
Source code at petsc4py/PETSc/Device.pyx:165
Return type
str
static setDefaultType(device_type)
Set the device type to be used as the default in subsequent calls to create.
Not collective.
SEE ALSO:
create, PetscDeviceSetDefaultDeviceType
Source code at petsc4py/PETSc/Device.pyx:195
Parameters
device_type (Type | str)
Return type
None
view(viewer=None)
View a device object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
PetscDeviceView
Source code at petsc4py/PETSc/Device.pyx:144
Attributes Documentation
device_id
The device id.
Source code at petsc4py/PETSc/Device.pyx:215
type The device type.
Source code at petsc4py/PETSc/Device.pyx:210
petsc4py.PETSc.DeviceContext
class petsc4py.PETSc.DeviceContext
Bases: Object
DeviceContext object.
Represents an abstract handle to a device context.
SEE ALSO:
Device, PetscDeviceContext
Enumerations
┌────────────────┬──────────────────────────────┐
│ DeviceJoinMode │ The type of join to perform. │
├────────────────┼──────────────────────────────┤
│ StreamType │ The type of stream. │
└────────────────┴──────────────────────────────┘
petsc4py.PETSc.DeviceContext.DeviceJoinMode
class petsc4py.PETSc.DeviceContext.DeviceJoinMode
Bases: object
The type of join to perform.
SEE ALSO:
DeviceContext, DeviceContext.join, DeviceContext.fork, PetscDeviceContextJoinMode
Attributes Summary
┌─────────┬──────────────────────────────┐
│ DESTROY │ Constant DESTROY of type int │
├─────────┼──────────────────────────────┤
│ NO_SYNC │ Constant NO_SYNC of type int │
├─────────┼──────────────────────────────┤
│ SYNC │ Constant SYNC of type int │
└─────────┴──────────────────────────────┘
Attributes Documentation
DESTROY: int = DESTROY
Constant DESTROY of type int
NO_SYNC: int = NO_SYNC
Constant NO_SYNC of type int
SYNC: int = SYNC
Constant SYNC of type int
petsc4py.PETSc.DeviceContext.StreamType
class petsc4py.PETSc.DeviceContext.StreamType
Bases: object
The type of stream.
SEE ALSO:
DeviceContext, DeviceContext.getStreamType, DeviceContext.setStreamType, PetscStreamType
Attributes Summary
┌──────────────────────────┬───────────────────────────────────────┐
│ DEFAULT │ Constant DEFAULT of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DEFAULT_WITH_BARRIER │ Constant DEFAULT_WITH_BARRIER of type │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ NONBLOCKING │ Constant NONBLOCKING of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ NONBLOCKING_WITH_BARRIER │ Constant NONBLOCKING_WITH_BARRIER of │
│ │ type int │
└──────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
DEFAULT: int = DEFAULT
Constant DEFAULT of type int
DEFAULT_WITH_BARRIER: int = DEFAULT_WITH_BARRIER
Constant DEFAULT_WITH_BARRIER of type int
NONBLOCKING: int = NONBLOCKING
Constant NONBLOCKING of type int
NONBLOCKING_WITH_BARRIER: int = NONBLOCKING_WITH_BARRIER
Constant NONBLOCKING_WITH_BARRIER of type int
Methods Summary
┌──────────────────────────────┬───────────────────────────────────────┐
│ create() │ Create an empty DeviceContext. │
├──────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy a device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ duplicate() │ Duplicate a the device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ fork(n[, stream_type]) │ Create multiple device contexts which │
│ │ are all logically dependent on this │
│ │ one. │
├──────────────────────────────┼───────────────────────────────────────┤
│ getCurrent() │ Return the current device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ getDevice() │ Get the Device which this instance is │
│ │ attached to. │
├──────────────────────────────┼───────────────────────────────────────┤
│ getStreamType() │ Return the StreamType. │
├──────────────────────────────┼───────────────────────────────────────┤
│ idle() │ Return whether the underlying stream │
│ │ for the device context is idle. │
├──────────────────────────────┼───────────────────────────────────────┤
│ join(join_mode, py_sub_ctxs) │ Join a set of device contexts on this │
│ │ one. │
├──────────────────────────────┼───────────────────────────────────────┤
│ setCurrent(dctx) │ Set the current device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ setDevice(device) │ Set the Device which this │
│ │ DeviceContext is attached to. │
├──────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions([comm]) │ Configure the DeviceContext from the │
│ │ options database. │
├──────────────────────────────┼───────────────────────────────────────┤
│ setStreamType(stream_type) │ Set the StreamType. │
├──────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ synchronize() │ Synchronize a device context. │
├──────────────────────────────┼───────────────────────────────────────┤
│ waitFor(other) │ Make this instance wait for other. │
└──────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌─────────────┬───────────────────────────────────────┐
│ current │ The current global device context. │
├─────────────┼───────────────────────────────────────┤
│ device │ The device associated to the device │
│ │ context. │
├─────────────┼───────────────────────────────────────┤
│ stream_type │ The stream type. │
└─────────────┴───────────────────────────────────────┘
Methods Documentation
create()
Create an empty DeviceContext.
Not collective.
SEE ALSO:
destroy, Device, PetscDeviceContextCreate
Source code at petsc4py/PETSc/Device.pyx:240
Return type
Self
destroy()
Destroy a device context.
Not collective.
SEE ALSO:
create, PetscDeviceContextDestroy
Source code at petsc4py/PETSc/Device.pyx:255
Return type
Self
duplicate()
Duplicate a the device context.
Not collective.
SEE ALSO:
create, PetscDeviceContextDuplicate
Source code at petsc4py/PETSc/Device.pyx:348
Return type
DeviceContext
fork(n, stream_type=None)
Create multiple device contexts which are all logically dependent on this one.
Not collective.
Parameters
• n (int) -- The number of device contexts to create.
• stream_type (StreamType | str | None) -- The type of stream of the forked device
context.
Return type
list[DeviceContext]
Examples
The device contexts created must be destroyed using join.
>>> dctx = PETSc.DeviceContext().getCurrent()
>>> dctxs = dctx.fork(4)
>>> ... # perform computations
>>> # we can mix various join modes
>>> dctx.join(PETSc.DeviceContext.JoinMode.SYNC, dctxs[0:2])
>>> dctx.join(PETSc.DeviceContext.JoinMode.SYNC, dctxs[2:])
>>> ... # some more computations and joins
>>> # dctxs must be all destroyed with joinMode.DESTROY
>>> dctx.join(PETSc.DeviceContext.JoinMode.DESTROY, dctxs)
SEE ALSO:
join, waitFor, PetscDeviceContextFork
Source code at petsc4py/PETSc/Device.pyx:399
static getCurrent()
Return the current device context.
Not collective.
SEE ALSO:
current, setCurrent, PetscDeviceContextGetCurrentContext
Source code at petsc4py/PETSc/Device.pyx:519
Return type
DeviceContext
getDevice()
Get the Device which this instance is attached to.
Not collective.
SEE ALSO:
setDevice, device, Device, PetscDeviceContextGetDevice
Source code at petsc4py/PETSc/Device.pyx:302
Return type
Device
getStreamType()
Return the StreamType.
Not collective.
SEE ALSO:
stream_type, setStreamType, PetscDeviceContextGetStreamType
Source code at petsc4py/PETSc/Device.pyx:268
Return type
str
idle() Return whether the underlying stream for the device context is idle.
Not collective.
SEE ALSO:
synchronize, PetscDeviceContextQueryIdle
Source code at petsc4py/PETSc/Device.pyx:363
Return type
bool
join(join_mode, py_sub_ctxs)
Join a set of device contexts on this one.
Not collective.
Parameters
• join_mode (DeviceJoinMode | str) -- The type of join to perform.
• py_sub_ctxs (list[DeviceContext]) -- The list of device contexts to join.
Return type
None
SEE ALSO:
fork, waitFor, PetscDeviceContextJoin
Source code at petsc4py/PETSc/Device.pyx:448
static setCurrent(dctx)
Set the current device context.
Not collective.
Parameters
dctx (DeviceContext | None) -- The DeviceContext to set as current (or None to use
the default context).
Return type
None
SEE ALSO:
current, getCurrent, PetscDeviceContextSetCurrentContext
Source code at petsc4py/PETSc/Device.pyx:535
setDevice(device)
Set the Device which this DeviceContext is attached to.
Collective.
Parameters
device (Device) -- The Device to which this instance is attached to.
Return type
None
SEE ALSO:
getDevice, device, Device, PetscDeviceContextSetDevice
Source code at petsc4py/PETSc/Device.pyx:317
setFromOptions(comm=None)
Configure the DeviceContext from the options database.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
None
SEE ALSO:
Sys.getDefaultComm, PetscDeviceContextSetFromOptions
Source code at petsc4py/PETSc/Device.pyx:500
setStreamType(stream_type)
Set the StreamType.
Not collective.
Parameters
stream_type (StreamType | str) -- The type of stream to set
Return type
None
SEE ALSO:
stream_type, getStreamType, PetscDeviceContextSetStreamType
Source code at petsc4py/PETSc/Device.pyx:283
setUp()
Set up the internal data structures for using the device context.
Not collective.
SEE ALSO:
create, PetscDeviceContextSetUp
Source code at petsc4py/PETSc/Device.pyx:336
Return type
None
synchronize()
Synchronize a device context.
Not collective.
Notes
The underlying stream is considered idle after this routine returns, i.e. idle will return
True.
SEE ALSO:
idle, PetscDeviceContextSynchronize
Source code at petsc4py/PETSc/Device.pyx:483
Return type
None
waitFor(other)
Make this instance wait for other.
Not collective.
Parameters
other (DeviceContext | None) -- The other DeviceContext to wait for
Return type
None
SEE ALSO:
fork, join, PetscDeviceContextWaitForContext
Source code at petsc4py/PETSc/Device.pyx:378
Attributes Documentation
current
The current global device context.
Source code at petsc4py/PETSc/Device.pyx:574
device The device associated to the device context.
Source code at petsc4py/PETSc/Device.pyx:566
stream_type
The stream type.
Source code at petsc4py/PETSc/Device.pyx:558
petsc4py.PETSc.DualSpace
class petsc4py.PETSc.DualSpace
Bases: Object
Dual space to a linear space.
Enumerations
┌──────┬───────────────────────┐
│ Type │ The dual space types. │
└──────┴───────────────────────┘
petsc4py.PETSc.DualSpace.Type
class petsc4py.PETSc.DualSpace.Type
Bases: object
The dual space types.
Attributes Summary
┌──────────┬─────────────────────────────┐
│ BDM │ Object BDM of type str │
├──────────┼─────────────────────────────┤
│ LAGRANGE │ Object LAGRANGE of type str │
├──────────┼─────────────────────────────┤
│ REFINED │ Object REFINED of type str │
├──────────┼─────────────────────────────┤
│ SIMPLE │ Object SIMPLE of type str │
└──────────┴─────────────────────────────┘
Attributes Documentation
BDM: str = BDM
Object BDM of type str
LAGRANGE: str = LAGRANGE
Object LAGRANGE of type str
REFINED: str = REFINED
Object REFINED of type str
SIMPLE: str = SIMPLE
Object SIMPLE of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create an empty DualSpace object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the DualSpace object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ duplicate() │ Create a duplicate DualSpace object │
│ │ that is not set up. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM representing the │
│ │ reference cell of a DualSpace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDimension() │ Return the dimension of the dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFunctional(i) │ Return the i-th basis functional in │
│ │ the dual space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInteriorDimension() │ Return the interior dimension of the │
│ │ dual space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLagrangeContinuity() │ Return whether the element is │
│ │ continuous. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLagrangeTensor() │ Return the tensor nature of the dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLagrangeTrimmed() │ Return the trimmed nature of the dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumComponents() │ Return the number of components for │
│ │ this space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumDof() │ Return the number of degrees of │
│ │ freedom for each spatial dimension. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOrder() │ Return the order of the dual space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the dual space │
│ │ object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM representing the reference │
│ │ cell. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLagrangeContinuity(continuous) │ Indicate whether the element is │
│ │ continuous. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLagrangeTensor(tensor) │ Set the tensor nature of the dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLagrangeTrimmed(trimmed) │ Set the trimmed nature of the dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNumComponents(nc) │ Set the number of components for this │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOrder(order) │ Set the order of the dual space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSimpleDimension(dim) │ Set the number of functionals in the │
│ │ dual space basis. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSimpleFunctional(func, functional) │ Set the given basis element for this │
│ │ dual space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(dualspace_type) │ Build a particular type of dual │
│ │ space. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Construct a basis for a DualSpace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a DualSpace. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create an empty DualSpace object.
Collective.
The type can then be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscDualSpaceCreate
Source code at petsc4py/PETSc/Space.pyx:594
destroy()
Destroy the DualSpace object.
Collective.
SEE ALSO:
PetscDualSpaceDestroy
Source code at petsc4py/PETSc/Space.pyx:636
Return type
Self
duplicate()
Create a duplicate DualSpace object that is not set up.
Collective.
SEE ALSO:
PetscDualSpaceDuplicate
Source code at petsc4py/PETSc/Space.pyx:649
Return type
DualSpace
getDM()
Return the DM representing the reference cell of a DualSpace.
Not collective.
SEE ALSO:
setDM, PetscDualSpaceGetDM
Source code at petsc4py/PETSc/Space.pyx:662
Return type
DM
getDimension()
Return the dimension of the dual space.
Not collective.
The dimension of the dual space, i.e. the number of basis functionals.
SEE ALSO:
PetscDualSpaceGetDimension
Source code at petsc4py/PETSc/Space.pyx:696
Return type
int
getFunctional(i)
Return the i-th basis functional in the dual space.
Not collective.
Parameters
i (int) -- The basis number.
Return type
Quad
SEE ALSO:
PetscDualSpaceGetFunctional
Source code at petsc4py/PETSc/Space.pyx:826
getInteriorDimension()
Return the interior dimension of the dual space.
Not collective.
The interior dimension of the dual space, i.e. the number of basis functionals assigned to
the interior of the reference domain.
SEE ALSO:
PetscDualSpaceGetInteriorDimension
Source code at petsc4py/PETSc/Space.pyx:847
Return type
int
getLagrangeContinuity()
Return whether the element is continuous.
Not collective.
SEE ALSO:
setLagrangeContinuity, PetscDualSpaceLagrangeGetContinuity
Source code at petsc4py/PETSc/Space.pyx:864
Return type
bool
getLagrangeTensor()
Return the tensor nature of the dual space.
Not collective.
SEE ALSO:
setLagrangeTensor, PetscDualSpaceLagrangeGetTensor
Source code at petsc4py/PETSc/Space.pyx:896
Return type
bool
getLagrangeTrimmed()
Return the trimmed nature of the dual space.
Not collective.
SEE ALSO:
setLagrangeTrimmed, PetscDualSpaceLagrangeGetTrimmed
Source code at petsc4py/PETSc/Space.pyx:928
Return type
bool
getNumComponents()
Return the number of components for this space.
Not collective.
SEE ALSO:
setNumComponents, PetscDualSpaceGetNumComponents
Source code at petsc4py/PETSc/Space.pyx:712
Return type
int
getNumDof()
Return the number of degrees of freedom for each spatial dimension.
Not collective.
SEE ALSO:
PetscDualSpaceGetNumDof
Source code at petsc4py/PETSc/Space.pyx:810
Return type
ArrayInt
getOrder()
Return the order of the dual space.
Not collective.
SEE ALSO:
setOrder, PetscDualSpaceGetOrder
Source code at petsc4py/PETSc/Space.pyx:778
Return type
int
getType()
Return the type of the dual space object.
Not collective.
SEE ALSO:
setType, PetscDualSpaceGetType
Source code at petsc4py/PETSc/Space.pyx:744
Return type
str
setDM(dm)
Set the DM representing the reference cell.
Not collective.
Parameters
dm (DM) -- The reference cell.
Return type
None
SEE ALSO:
getDM, PetscDualSpaceSetDM
Source code at petsc4py/PETSc/Space.pyx:679
setLagrangeContinuity(continuous)
Indicate whether the element is continuous.
Not collective.
Parameters
continuous (bool) -- The flag for element continuity.
Return type
None
SEE ALSO:
getLagrangeContinuity, PetscDualSpaceLagrangeSetContinuity
Source code at petsc4py/PETSc/Space.pyx:878
setLagrangeTensor(tensor)
Set the tensor nature of the dual space.
Not collective.
Parameters
tensor (bool) -- Whether the dual space has tensor layout (vs. simplicial).
Return type
None
SEE ALSO:
getLagrangeTensor, PetscDualSpaceLagrangeSetTensor
Source code at petsc4py/PETSc/Space.pyx:910
setLagrangeTrimmed(trimmed)
Set the trimmed nature of the dual space.
Not collective.
Parameters
trimmed (bool) -- Whether the dual space represents to dual basis of a trimmed
polynomial space (e.g. Raviart-Thomas and higher order / other form degree
variants).
Return type
None
SEE ALSO:
getLagrangeTrimmed, PetscDualSpaceLagrangeSetTrimmed
Source code at petsc4py/PETSc/Space.pyx:942
setNumComponents(nc)
Set the number of components for this space.
Logically collective.
Parameters
nc (int) -- The number of components
Return type
None
SEE ALSO:
getNumComponents, PetscDualSpaceSetNumComponents
Source code at petsc4py/PETSc/Space.pyx:726
setOrder(order)
Set the order of the dual space.
Not collective.
Parameters
order (int) -- The order.
Return type
None
SEE ALSO:
getOrder, PetscDualSpaceSetOrder
Source code at petsc4py/PETSc/Space.pyx:792
setSimpleDimension(dim)
Set the number of functionals in the dual space basis.
Logically collective.
Parameters
dim (int) -- The basis dimension.
Return type
None
SEE ALSO:
PetscDualSpaceSimpleSetDimension
Source code at petsc4py/PETSc/Space.pyx:962
setSimpleFunctional(func, functional)
Set the given basis element for this dual space.
Not collective.
Parameters
• func (int) -- The basis index.
• functional (Quad) -- The basis functional.
Return type
None
SEE ALSO:
PetscDualSpaceSimpleSetFunctional
Source code at petsc4py/PETSc/Space.pyx:980
setType(dualspace_type)
Build a particular type of dual space.
Collective.
Parameters
dualspace_type (Type | str) -- The kind of space.
Return type
Self
SEE ALSO:
getType, PetscDualSpaceSetType
Source code at petsc4py/PETSc/Space.pyx:758
setUp()
Construct a basis for a DualSpace.
Collective.
SEE ALSO:
PetscDualSpaceSetUp
Source code at petsc4py/PETSc/Space.pyx:582
Return type
None
view(viewer=None)
View a DualSpace.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the DualSpace.
Return type
None
SEE ALSO:
PetscDualSpaceView
Source code at petsc4py/PETSc/Space.pyx:617
petsc4py.PETSc.FE
class petsc4py.PETSc.FE
Bases: Object
A PETSc object that manages a finite element space.
Enumerations
┌──────┬───────────────────────────┐
│ Type │ The finite element types. │
└──────┴───────────────────────────┘
petsc4py.PETSc.FE.Type
class petsc4py.PETSc.FE.Type
Bases: object
The finite element types.
Attributes Summary
┌───────────┬──────────────────────────────┐
│ BASIC │ Object BASIC of type str │
├───────────┼──────────────────────────────┤
│ COMPOSITE │ Object COMPOSITE of type str │
├───────────┼──────────────────────────────┤
│ OPENCL │ Object OPENCL of type str │
└───────────┴──────────────────────────────┘
Attributes Documentation
BASIC: str = BASIC
Object BASIC of type str
COMPOSITE: str = COMPOSITE
Object COMPOSITE of type str
OPENCL: str = OPENCL
Object OPENCL of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create an empty FE object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDefault(dim, nc, isSimplex[, │ Create a FE for basic FEM │
│ qorder, ...]) │ computation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createLagrange(dim, nc, isSimplex, │ Create a FE for the basic Lagrange │
│ k[, ...]) │ space of degree k. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the FE object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBasisSpace() │ Return the Space used for the │
│ │ approximation of the FE solution. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDimension() │ Return the dimension of the finite │
│ │ element space on a cell. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDualSpace() │ Return the DualSpace used to define │
│ │ the inner product for the FE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFaceQuadrature() │ Return the Quad used to calculate │
│ │ inner products on faces. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumComponents() │ Return the number of components in │
│ │ the element. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumDof() │ Return the number of DOFs. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getQuadrature() │ Return the Quad used to calculate │
│ │ inner products. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSpatialDimension() │ Return the spatial dimension of the │
│ │ element. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTileSizes() │ Return the tile sizes for evaluation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBasisSpace(sp) │ Set the Space used for the │
│ │ approximation of the solution. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDualSpace(dspace) │ Set the DualSpace used to define the │
│ │ inner product. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFaceQuadrature(quad) │ Set the Quad used to calculate inner │
│ │ products on faces. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set parameters in a FE from the │
│ │ options database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNumComponents(comp) │ Set the number of field components in │
│ │ the element. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setQuadrature(quad) │ Set the Quad used to calculate inner │
│ │ products. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTileSizes(blockSize, numBlocks, │ Set the tile sizes for evaluation. │
│ ...) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(fe_type) │ Build a particular FE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Construct data structures for the FE │
│ │ after the Type has been set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a FE object. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create an empty FE object.
Collective.
The type can then be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
setType, PetscFECreate
Source code at petsc4py/PETSc/FE.pyx:53
createDefault(dim, nc, isSimplex, qorder=DETERMINE, prefix=None, comm=None)
Create a FE for basic FEM computation.
Collective.
Parameters
• dim (int) -- The spatial dimension.
• nc (int) -- The number of components.
• isSimplex (bool) -- Flag for simplex reference cell, otherwise it's a tensor
product.
• qorder (int) -- The quadrature order or DETERMINE to use Space polynomial degree.
• prefix (str) -- The options prefix, or None.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscFECreateDefault
Source code at petsc4py/PETSc/FE.pyx:76
createLagrange(dim, nc, isSimplex, k, qorder=DETERMINE, comm=None)
Create a FE for the basic Lagrange space of degree k.
Collective.
Parameters
• dim (int) -- The spatial dimension.
• nc (int) -- The number of components.
• isSimplex (bool) -- Flag for simplex reference cell, otherwise it's a tensor
product.
• k (int) -- The degree of the space.
• qorder (int) -- The quadrature order or DETERMINE to use Space polynomial degree.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscFECreateLagrange
Source code at petsc4py/PETSc/FE.pyx:122
destroy()
Destroy the FE object.
Collective.
SEE ALSO:
PetscFEDestroy
Source code at petsc4py/PETSc/FE.pyx:40
Return type
Self
getBasisSpace()
Return the Space used for the approximation of the FE solution.
Not collective.
SEE ALSO:
setBasisSpace, PetscFEGetBasisSpace
Source code at petsc4py/PETSc/FE.pyx:387
Return type
Space
getDimension()
Return the dimension of the finite element space on a cell.
Not collective.
SEE ALSO:
PetscFEGetDimension
Source code at petsc4py/PETSc/FE.pyx:181
Return type
int
getDualSpace()
Return the DualSpace used to define the inner product for the FE.
Not collective.
SEE ALSO:
setDualSpace, DualSpace, PetscFEGetDualSpace
Source code at petsc4py/PETSc/FE.pyx:443
Return type
DualSpace
getFaceQuadrature()
Return the Quad used to calculate inner products on faces.
Not collective.
SEE ALSO:
setFaceQuadrature, PetscFEGetFaceQuadrature
Source code at petsc4py/PETSc/FE.pyx:316
Return type
Quad
getNumComponents()
Return the number of components in the element.
Not collective.
SEE ALSO:
setNumComponents, PetscFEGetNumComponents
Source code at petsc4py/PETSc/FE.pyx:209
Return type
int
getNumDof()
Return the number of DOFs.
Not collective.
Return the number of DOFs (dual basis vectors) associated with mesh points on the reference
cell of a given dimension.
SEE ALSO:
PetscFEGetNumDof
Source code at petsc4py/PETSc/FE.pyx:241
Return type
ndarray
getQuadrature()
Return the Quad used to calculate inner products.
Not collective.
SEE ALSO:
setQuadrature, PetscFEGetQuadrature
Source code at petsc4py/PETSc/FE.pyx:166
Return type
Quad
getSpatialDimension()
Return the spatial dimension of the element.
Not collective.
SEE ALSO:
PetscFEGetSpatialDimension
Source code at petsc4py/PETSc/FE.pyx:195
Return type
int
getTileSizes()
Return the tile sizes for evaluation.
Not collective.
Returns
• blockSize (int) -- The number of elements in a block.
• numBlocks (int) -- The number of blocks in a batch.
• batchSize (int) -- The number of elements in a batch.
• numBatches (int) -- The number of batches in a chunk.
Return type
tuple(int, int, int, int)
SEE ALSO:
setTileSizes, PetscFEGetTileSizes
Source code at petsc4py/PETSc/FE.pyx:260
setBasisSpace(sp)
Set the Space used for the approximation of the solution.
Not collective.
Parameters
sp (Space) -- The Space object.
Return type
None
SEE ALSO:
getBasisSpace, PetscFESetBasisSpace
Source code at petsc4py/PETSc/FE.pyx:402
setDualSpace(dspace)
Set the DualSpace used to define the inner product.
Not collective.
Parameters
dspace (DualSpace) -- The DualSpace object.
Return type
None
SEE ALSO:
getDualSpace, DualSpace, PetscFESetDualSpace
Source code at petsc4py/PETSc/FE.pyx:458
setFaceQuadrature(quad)
Set the Quad used to calculate inner products on faces.
Not collective.
Parameters
quad (Quad) -- The Quad object.
Return type
Quad
SEE ALSO:
getFaceQuadrature, PetscFESetFaceQuadrature
Source code at petsc4py/PETSc/FE.pyx:349
setFromOptions()
Set parameters in a FE from the options database.
Collective.
SEE ALSO:
Working with PETSc options, PetscFESetFromOptions
Source code at petsc4py/PETSc/FE.pyx:419
Return type
None
setNumComponents(comp)
Set the number of field components in the element.
Not collective.
Parameters
comp (int) -- The number of field components.
Return type
None
SEE ALSO:
getNumComponents, PetscFESetNumComponents
Source code at petsc4py/PETSc/FE.pyx:223
setQuadrature(quad)
Set the Quad used to calculate inner products.
Not collective.
Parameters
quad (Quad) -- The Quad object.
Return type
Self
SEE ALSO:
getQuadrature, PetscFESetQuadrature
Source code at petsc4py/PETSc/FE.pyx:331
setTileSizes(blockSize, numBlocks, batchSize, numBatches)
Set the tile sizes for evaluation.
Not collective.
Parameters
• blockSize (int) -- The number of elements in a block.
• numBlocks (int) -- The number of blocks in a batch.
• batchSize (int) -- The number of elements in a batch.
• numBatches (int) -- The number of batches in a chunk.
Return type
None
SEE ALSO:
getTileSizes, PetscFESetTileSizes
Source code at petsc4py/PETSc/FE.pyx:286
setType(fe_type)
Build a particular FE.
Collective.
Parameters
fe_type (Type | str) -- The kind of FEM space.
Return type
Self
SEE ALSO:
PetscFESetType
Source code at petsc4py/PETSc/FE.pyx:367
setUp()
Construct data structures for the FE after the Type has been set.
Collective.
SEE ALSO:
PetscFESetUp
Source code at petsc4py/PETSc/FE.pyx:431
Return type
None
view(viewer=None)
View a FE object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
PetscFEView
Source code at petsc4py/PETSc/FE.pyx:21
petsc4py.PETSc.IS
class petsc4py.PETSc.IS
Bases: Object
A collection of indices.
IS objects are used to index into vectors and matrices and to set up vector scatters.
SEE ALSO:
IS
Enumerations
┌──────┬──────────────────────┐
│ Type │ The index set types. │
└──────┴──────────────────────┘
petsc4py.PETSc.IS.Type
class petsc4py.PETSc.IS.Type
Bases: object
The index set types.
Attributes Summary
┌─────────┬────────────────────────────┐
│ BLOCK │ Object BLOCK of type str │
├─────────┼────────────────────────────┤
│ GENERAL │ Object GENERAL of type str │
├─────────┼────────────────────────────┤
│ STRIDE │ Object STRIDE of type str │
└─────────┴────────────────────────────┘
Attributes Documentation
BLOCK: str = BLOCK
Object BLOCK of type str
GENERAL: str = GENERAL
Object GENERAL of type str
STRIDE: str = STRIDE
Object STRIDE of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ allGather() │ Concatenate index sets stored across │
│ │ processors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ buildTwoSided([toindx]) │ Create an index set describing a │
│ │ global mapping. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ complement(nmin, nmax) │ Create a complement index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copy([result]) │ Copy the contents of the index set │
│ │ into another. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create an IS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createBlock(bsize, indices[, comm]) │ Create a blocked index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createGeneral(indices[, comm]) │ Create an IS with indices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createStride(size[, first, step, │ Create an index set consisting of │
│ comm]) │ evenly spaced values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ difference(iset) │ Return the difference between two │
│ │ index sets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ duplicate() │ Create a copy of the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ embed(iset, drop) │ Embed self into iset. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ equal(iset) │ Return whether the index sets have │
│ │ the same set of indices or not. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ expand(iset) │ Return the union of two (possibly │
│ │ unsorted) index sets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockIndices() │ Return the indices of an index set │
│ │ with type IS.Type.BLOCK. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSize() │ Return the number of elements in a │
│ │ block. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIndices() │ Return the indices of the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInfo() │ Return stride information for an │
│ │ index set with type IS.Type.STRIDE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSize() │ Return the process-local length of │
│ │ the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSize() │ Return the global length of an index │
│ │ set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSizes() │ Return the local and global sizes of │
│ │ the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStride() │ Return size and stride information. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the index set type associated │
│ │ with the IS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ invertPermutation([nlocal]) │ Invert the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isIdentity() │ Return whether the index set has been │
│ │ declared as an identity. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isPermutation() │ Return whether an index set has been │
│ │ declared to be a permutation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isSorted() │ Return whether the indices have been │
│ │ sorted. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ load(viewer) │ Load a stored index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ renumber([mult]) │ Renumber the non-negative entries of │
│ │ an index set, starting from 0. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBlockIndices(bsize, indices) │ Set the indices for an index set with │
│ │ type IS.Type.BLOCK. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBlockSize(bs) │ Set the block size of the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIdentity() │ Mark the index set as being an │
│ │ identity. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIndices(indices) │ Set the indices of an index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPermutation() │ Mark the index set as being a │
│ │ permutation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStride(size[, first, step]) │ Set the stride information for an │
│ │ index set with type IS.Type.STRIDE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(is_type) │ Set the type of the index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ sort() │ Sort the indices of an index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ sum(iset) │ Return the union of two (sorted) │
│ │ index sets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ toGeneral() │ Convert the index set type to │
│ │ IS.Type.GENERAL. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ union(iset) │ Return the union of two (possibly │
│ │ unsorted) index sets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Display the index set. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌─────────────┬───────────────────────────────────────┐
│ array │ View of the index set as an array of │
│ │ integers. │
├─────────────┼───────────────────────────────────────┤
│ block_size │ The number of elements in a block. │
├─────────────┼───────────────────────────────────────┤
│ identity │ True if index set is an identity, ‐ │
│ │ False otherwise. │
├─────────────┼───────────────────────────────────────┤
│ indices │ The indices of the index set. │
├─────────────┼───────────────────────────────────────┤
│ local_size │ The local size of the index set. │
├─────────────┼───────────────────────────────────────┤
│ permutation │ True if index set is a permutation, ‐ │
│ │ False otherwise. │
├─────────────┼───────────────────────────────────────┤
│ size │ The global size of the index set. │
├─────────────┼───────────────────────────────────────┤
│ sizes │ The local and global sizes of the │
│ │ index set. │
├─────────────┼───────────────────────────────────────┤
│ sorted │ True if index set is sorted, False │
│ │ otherwise. │
└─────────────┴───────────────────────────────────────┘
Methods Documentation
allGather()
Concatenate index sets stored across processors.
Collective.
The returned index set will be the same on every processor.
SEE ALSO:
ISAllGather
Source code at petsc4py/PETSc/IS.pyx:304
Return type
IS
buildTwoSided(toindx=None)
Create an index set describing a global mapping.
Collective.
This function generates an index set that contains new numbers from remote or local on the
index set.
Parameters
toindx (IS | None) -- Index set describing which indices to send, default is to send
natural numbering.
Returns
New index set containing the new numbers from remote or local.
Return type
IS
SEE ALSO:
ISBuildTwoSided
Source code at petsc4py/PETSc/IS.pyx:333
complement(nmin, nmax)
Create a complement index set.
Collective.
The complement set of indices is all indices that are not in the provided set (and within
the provided bounds).
Parameters
• nmin (int) -- Minimum index that can be found in the local part of the complement
index set.
• nmax (int) -- One greater than the maximum index that can be found in the local
part of the complement index set.
Return type
IS
Notes
For a parallel index set, this will generate the local part of the complement on each
process.
To generate the entire complement (on each process) of a parallel index set, first call
IS.allGather and then call this method.
SEE ALSO:
IS.allGather, ISComplement
Source code at petsc4py/PETSc/IS.pyx:674
copy(result=None)
Copy the contents of the index set into another.
Collective.
Parameters
result (IS | None) -- The target index set. If None then IS.duplicate is called
first.
Returns
The copied index set. If result is not None then this is returned here.
Return type
IS
SEE ALSO:
IS.duplicate, ISCopy
Source code at petsc4py/PETSc/IS.pyx:253
create(comm=None)
Create an IS.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
ISCreate
Source code at petsc4py/PETSc/IS.pyx:88
createBlock(bsize, indices, comm=None)
Create a blocked index set.
Collective.
Parameters
• bsize (int) -- Block size.
• indices (Sequence[int]) -- Integer array of indices.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
ISCreateBlock
Source code at petsc4py/PETSc/IS.pyx:171
createGeneral(indices, comm=None)
Create an IS with indices.
Collective.
Parameters
• indices (Sequence[int]) -- Integer array.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
ISCreateGeneral
Source code at petsc4py/PETSc/IS.pyx:142
createStride(size, first=0, step=0, comm=None)
Create an index set consisting of evenly spaced values.
Collective.
Parameters
• size (int) -- The length of the locally owned portion of the index set.
• first (int) -- The first element of the index set.
• step (int) -- The difference between adjacent indices.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
ISCreateStride
Source code at petsc4py/PETSc/IS.pyx:204
destroy()
Destroy the index set.
Collective.
SEE ALSO:
ISDestroy
Source code at petsc4py/PETSc/IS.pyx:75
Return type
Self
difference(iset)
Return the difference between two index sets.
Collective.
Parameters
iset (IS) -- Index set to compute the difference with.
Returns
Index set representing the difference between self and iset.
Return type
IS
SEE ALSO:
ISDifference
Source code at petsc4py/PETSc/IS.pyx:650
duplicate()
Create a copy of the index set.
Collective.
SEE ALSO:
IS.copy, ISDuplicate
Source code at petsc4py/PETSc/IS.pyx:239
Return type
IS
embed(iset, drop)
Embed self into iset.
Not collective.
The embedding is performed by finding the locations in iset that have the same indices as
self.
Parameters
• iset (IS) -- The index set to embed into.
• drop (bool) -- Flag indicating whether to drop indices from self that are not in
iset.
Returns
The embedded index set.
Return type
IS
SEE ALSO:
ISEmbed
Source code at petsc4py/PETSc/IS.pyx:710
equal(iset)
Return whether the index sets have the same set of indices or not.
Collective.
Parameters
iset (IS) -- The index set to compare indices with.
Return type
bool
SEE ALSO:
ISEqual
Source code at petsc4py/PETSc/IS.pyx:550
expand(iset)
Return the union of two (possibly unsorted) index sets.
Collective.
To compute the union, expand concatenates the two index sets and removes any duplicates.
Parameters
iset (IS) -- Index set to compute the union with.
Returns
The new, combined, index set.
Return type
IS
SEE ALSO:
ISExpand
Source code at petsc4py/PETSc/IS.pyx:588
getBlockIndices()
Return the indices of an index set with type IS.Type.BLOCK.
Not collective.
SEE ALSO:
ISBlockGetIndices
Source code at petsc4py/PETSc/IS.pyx:833
Return type
ArrayInt
getBlockSize()
Return the number of elements in a block.
Not collective.
SEE ALSO:
ISGetBlockSize
Source code at petsc4py/PETSc/IS.pyx:437
Return type
int
getIndices()
Return the indices of the index set.
Not collective.
SEE ALSO:
ISGetIndices
Source code at petsc4py/PETSc/IS.pyx:789
Return type
ArrayInt
getInfo()
Return stride information for an index set with type IS.Type.STRIDE.
Not collective.
Returns
• first (int) -- First element of the index set.
• step (int) -- Difference between adjacent indices.
Return type
tuple[int, int]
SEE ALSO:
IS.getStride, ISStrideGetInfo
Source code at petsc4py/PETSc/IS.pyx:903
getLocalSize()
Return the process-local length of the index set.
Not collective.
SEE ALSO:
ISGetLocalSize
Source code at petsc4py/PETSc/IS.pyx:401
Return type
int
getSize()
Return the global length of an index set.
Not collective.
SEE ALSO:
ISGetSize
Source code at petsc4py/PETSc/IS.pyx:387
Return type
int
getSizes()
Return the local and global sizes of the index set.
Not collective.
Returns
• local_size (int) -- The local size.
• global_size (int) -- The global size.
Return type
tuple[int, int]
SEE ALSO:
IS.getLocalSize, IS.getSize
Source code at petsc4py/PETSc/IS.pyx:415
getStride()
Return size and stride information.
Not collective.
Returns
• size (int) -- Length of the locally owned portion of the index set.
• first (int) -- First element of the index set.
• step (int) -- Difference between adjacent indices.
Return type
tuple[int, int, int]
SEE ALSO:
ISGetLocalSize, ISStrideGetInfo
Source code at petsc4py/PETSc/IS.pyx:879
getType()
Return the index set type associated with the IS.
Not collective.
SEE ALSO:
ISGetType
Source code at petsc4py/PETSc/IS.pyx:128
Return type
str
invertPermutation(nlocal=None)
Invert the index set.
Collective.
For this to be correct the index set must be a permutation.
Parameters
nlocal (int | None) -- The number of indices on this processor in the resulting
index set, defaults to PETSC_DECIDE.
Return type
IS
SEE ALSO:
ISInvertPermutation
Source code at petsc4py/PETSc/IS.pyx:363
isIdentity()
Return whether the index set has been declared as an identity.
Collective.
SEE ALSO:
ISIdentity
Source code at petsc4py/PETSc/IS.pyx:536
Return type
bool
isPermutation()
Return whether an index set has been declared to be a permutation.
Logically collective.
SEE ALSO:
ISPermutation
Source code at petsc4py/PETSc/IS.pyx:509
Return type
bool
isSorted()
Return whether the indices have been sorted.
Collective.
SEE ALSO:
ISSorted
Source code at petsc4py/PETSc/IS.pyx:482
Return type
bool
load(viewer)
Load a stored index set.
Collective.
Parameters
viewer (Viewer) -- Binary file viewer, either Viewer.Type.BINARY or
Viewer.Type.HDF5.
Return type
Self
SEE ALSO:
ISLoad
Source code at petsc4py/PETSc/IS.pyx:281
renumber(mult=None)
Renumber the non-negative entries of an index set, starting from 0.
Collective.
Parameters
mult (IS | None) -- The multiplicity of each entry in self, default implies a
multiplicity of 1.
Returns
• int -- One past the largest entry of the new index set.
• IS -- The renumbered index set.
Return type
tuple[int, IS]
SEE ALSO:
ISRenumber
Source code at petsc4py/PETSc/IS.pyx:741
setBlockIndices(bsize, indices)
Set the indices for an index set with type IS.Type.BLOCK.
Collective.
Parameters
• bsize (int) -- Number of elements in each block.
• indices (Sequence[int]) -- List of integers.
Return type
None
SEE ALSO:
ISBlockSetIndices
Source code at petsc4py/PETSc/IS.pyx:810
setBlockSize(bs)
Set the block size of the index set.
Logically collective.
Parameters
bs (int) -- Block size.
Return type
None
SEE ALSO:
ISSetBlockSize
Source code at petsc4py/PETSc/IS.pyx:451
setIdentity()
Mark the index set as being an identity.
Logically collective.
SEE ALSO:
ISSetIdentity
Source code at petsc4py/PETSc/IS.pyx:523
Return type
Self
setIndices(indices)
Set the indices of an index set.
Logically collective.
The index set is assumed to be of type IS.Type.GENERAL.
SEE ALSO:
ISGeneralSetIndices
Source code at petsc4py/PETSc/IS.pyx:772
Parameters
indices (Sequence[int])
Return type
None
setPermutation()
Mark the index set as being a permutation.
Logically collective.
SEE ALSO:
ISSetPermutation
Source code at petsc4py/PETSc/IS.pyx:496
Return type
Self
setStride(size, first=0, step=1)
Set the stride information for an index set with type IS.Type.STRIDE.
Logically collective.
Parameters
• size (int) -- Length of the locally owned portion of the index set.
• first (int) -- First element of the index set.
• step (int) -- Difference between adjacent indices.
Return type
None
SEE ALSO:
ISStrideSetStride
Source code at petsc4py/PETSc/IS.pyx:855
setType(is_type)
Set the type of the index set.
Collective.
Parameters
is_type (Type | str) -- The index set type.
Return type
None
SEE ALSO:
ISSetType
Source code at petsc4py/PETSc/IS.pyx:109
sort() Sort the indices of an index set.
Collective.
SEE ALSO:
ISSort
Source code at petsc4py/PETSc/IS.pyx:469
Return type
Self
sum(iset)
Return the union of two (sorted) index sets.
Collective.
Parameters
iset (IS) -- The index set to compute the union with.
Return type
IS
SEE ALSO:
ISSum
Source code at petsc4py/PETSc/IS.pyx:569
toGeneral()
Convert the index set type to IS.Type.GENERAL.
Collective.
SEE ALSO:
ISToGeneral, ISType
Source code at petsc4py/PETSc/IS.pyx:320
Return type
Self
union(iset)
Return the union of two (possibly unsorted) index sets.
Collective.
This function will call either ISSum or ISExpand depending on whether or not the input sets
are already sorted.
Sequential only (as ISSum is sequential only).
Parameters
iset (IS) -- Index set to compute the union with.
Returns
The new, combined, index set.
Return type
IS
SEE ALSO:
IS.expand, IS.sum
Source code at petsc4py/PETSc/IS.pyx:615
view(viewer=None)
Display the index set.
Collective.
Parameters
viewer (Viewer | None) -- Viewer used to display the IS.
Return type
None
SEE ALSO:
ISView
Source code at petsc4py/PETSc/IS.pyx:56
Attributes Documentation
array View of the index set as an array of integers.
Not collective.
Source code at petsc4py/PETSc/IS.pyx:1032
block_size
The number of elements in a block.
Not collective.
SEE ALSO:
IS.getBlockSize
Source code at petsc4py/PETSc/IS.pyx:1006
identity
True if index set is an identity, False otherwise.
Collective.
SEE ALSO:
IS.isIdentity
Source code at petsc4py/PETSc/IS.pyx:939
indices
The indices of the index set.
Not collective.
SEE ALSO:
IS.getIndices
Source code at petsc4py/PETSc/IS.pyx:1019
local_size
The local size of the index set.
Not collective.
SEE ALSO:
IS.getLocalSize
Source code at petsc4py/PETSc/IS.pyx:993
permutation
True if index set is a permutation, False otherwise.
Logically collective.
SEE ALSO:
IS.isPermutation
Source code at petsc4py/PETSc/IS.pyx:926
size The global size of the index set.
Not collective.
SEE ALSO:
IS.getSize
Source code at petsc4py/PETSc/IS.pyx:980
sizes The local and global sizes of the index set.
Not collective.
SEE ALSO:
IS.getSizes
Source code at petsc4py/PETSc/IS.pyx:967
sorted True if index set is sorted, False otherwise.
Collective.
SEE ALSO:
IS.isSorted
Source code at petsc4py/PETSc/IS.pyx:952
petsc4py.PETSc.InsertMode
class petsc4py.PETSc.InsertMode
Bases: object
Insertion mode.
Most commonly used insertion modes are:
INSERT Insert provided value/s discarding previous value/s.
ADD Add provided value/s to current value/s.
MAX Insert the maximum of provided value/s and current value/s.
SEE ALSO:
InsertMode
Attributes Summary
┌───────────────────┬───────────────────────────────────────┐
│ ADD │ Constant ADD of type int │
├───────────────────┼───────────────────────────────────────┤
│ ADD_ALL │ Constant ADD_ALL of type int │
├───────────────────┼───────────────────────────────────────┤
│ ADD_ALL_VALUES │ Constant ADD_ALL_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ ADD_BC │ Constant ADD_BC of type int │
├───────────────────┼───────────────────────────────────────┤
│ ADD_BC_VALUES │ Constant ADD_BC_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ ADD_VALUES │ Constant ADD_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT │ Constant INSERT of type int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT_ALL │ Constant INSERT_ALL of type int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT_ALL_VALUES │ Constant INSERT_ALL_VALUES of type ‐ │
│ │ int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT_BC │ Constant INSERT_BC of type int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT_BC_VALUES │ Constant INSERT_BC_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ INSERT_VALUES │ Constant INSERT_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ MAX │ Constant MAX of type int │
├───────────────────┼───────────────────────────────────────┤
│ MAX_VALUES │ Constant MAX_VALUES of type int │
├───────────────────┼───────────────────────────────────────┤
│ NOT_SET_VALUES │ Constant NOT_SET_VALUES of type int │
└───────────────────┴───────────────────────────────────────┘
Attributes Documentation
ADD: int = ADD
Constant ADD of type int
ADD_ALL: int = ADD_ALL
Constant ADD_ALL of type int
ADD_ALL_VALUES: int = ADD_ALL_VALUES
Constant ADD_ALL_VALUES of type int
ADD_BC: int = ADD_BC
Constant ADD_BC of type int
ADD_BC_VALUES: int = ADD_BC_VALUES
Constant ADD_BC_VALUES of type int
ADD_VALUES: int = ADD_VALUES
Constant ADD_VALUES of type int
INSERT: int = INSERT
Constant INSERT of type int
INSERT_ALL: int = INSERT_ALL
Constant INSERT_ALL of type int
INSERT_ALL_VALUES: int = INSERT_ALL_VALUES
Constant INSERT_ALL_VALUES of type int
INSERT_BC: int = INSERT_BC
Constant INSERT_BC of type int
INSERT_BC_VALUES: int = INSERT_BC_VALUES
Constant INSERT_BC_VALUES of type int
INSERT_VALUES: int = INSERT_VALUES
Constant INSERT_VALUES of type int
MAX: int = MAX
Constant MAX of type int
MAX_VALUES: int = MAX_VALUES
Constant MAX_VALUES of type int
NOT_SET_VALUES: int = NOT_SET_VALUES
Constant NOT_SET_VALUES of type int
petsc4py.PETSc.KSP
class petsc4py.PETSc.KSP
Bases: Object
Abstract PETSc object that manages all Krylov methods.
This is the object that manages the linear solves in PETSc (even those such as direct solvers that
do no use Krylov accelerators).
Notes
When a direct solver is used, but no Krylov solver is used, the KSP object is still used but with
a Type.PREONLY, meaning that only application of the preconditioner is used as the linear solver.
SEE ALSO:
create, setType, SNES, TS, PC, Type.CG, Type.GMRES, KSP
Enumerations
┌─────────────────┬───────────────────────────────┐
│ ConvergedReason │ KSP Converged Reason. │
├─────────────────┼───────────────────────────────┤
│ HPDDMType │ The HPDDM Krylov solver type. │
├─────────────────┼───────────────────────────────┤
│ NormType │ KSP norm type. │
├─────────────────┼───────────────────────────────┤
│ Type │ KSP Type. │
└─────────────────┴───────────────────────────────┘
petsc4py.PETSc.KSP.ConvergedReason
class petsc4py.PETSc.KSP.ConvergedReason
Bases: object
KSP Converged Reason.
CONVERGED_ITERATING
Still iterating
ITERATING
Still iterating
CONVERGED_RTOL_NORMAL
Undocumented.
CONVERGED_ATOL_NORMAL
Undocumented.
CONVERGED_RTOL
∥r∥ <= rtolnorm(b) or rtolnorm(b - Ax₀)
CONVERGED_ATOL
∥r∥ <= atol
CONVERGED_ITS
Used by the Type.PREONLY solver after the single iteration of the preconditioner is
applied. Also used when the KSPConvergedSkip convergence test routine is set in KSP.
CONVERGED_NEG_CURVE
Undocumented.
CONVERGED_STEP_LENGTH
Undocumented.
CONVERGED_HAPPY_BREAKDOWN
Undocumented.
DIVERGED_NULL
Undocumented.
DIVERGED_MAX_IT
Ran out of iterations before any convergence criteria was reached.
DIVERGED_DTOL
norm(r) >= dtol*norm(b)
DIVERGED_BREAKDOWN
A breakdown in the Krylov method was detected so the method could not continue to
enlarge the Krylov space. Could be due to a singular matrix or preconditioner. In
KSPHPDDM, this is also returned when some search directions within a block are
colinear.
DIVERGED_BREAKDOWN_BICG
A breakdown in the KSPBICG method was detected so the method could not continue to
enlarge the Krylov space.
DIVERGED_NONSYMMETRIC
It appears the operator or preconditioner is not symmetric and this Krylov method (‐
Type.CG, Type.MINRES, Type.CR) requires symmetry.
DIVERGED_INDEFINITE_PC
It appears the preconditioner is indefinite (has both positive and negative
eigenvalues) and this Krylov method (Type.CG) requires it to be positive definite.
DIVERGED_NANORINF
Undocumented.
DIVERGED_INDEFINITE_MAT
Undocumented.
DIVERGED_PCSETUP_FAILED
It was not possible to build or use the requested preconditioner. This is usually
due to a zero pivot in a factorization. It can also result from a failure in a
subpreconditioner inside a nested preconditioner such as PC.Type.FIELDSPLIT.
SEE ALSO:
None
Attributes Summary
┌───────────────────────────┬───────────────────────────────────────┐
│ CONVERGED_ATOL │ Constant CONVERGED_ATOL of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ATOL_NORMAL │ Constant CONVERGED_ATOL_NORMAL of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_HAPPY_BREAKDOWN │ Constant CONVERGED_HAPPY_BREAKDOWN of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITERATING │ Constant CONVERGED_ITERATING of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITS │ Constant CONVERGED_ITS of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_NEG_CURVE │ Constant CONVERGED_NEG_CURVE of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_RTOL │ Constant CONVERGED_RTOL of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_RTOL_NORMAL │ Constant CONVERGED_RTOL_NORMAL of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_STEP_LENGTH │ Constant CONVERGED_STEP_LENGTH of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_BREAKDOWN │ Constant DIVERGED_BREAKDOWN of type ‐ │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_BREAKDOWN_BICG │ Constant DIVERGED_BREAKDOWN_BICG of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_DTOL │ Constant DIVERGED_DTOL of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_INDEFINITE_MAT │ Constant DIVERGED_INDEFINITE_MAT of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_INDEFINITE_PC │ Constant DIVERGED_INDEFINITE_PC of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_MAX_IT │ Constant DIVERGED_MAX_IT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_NANORINF │ Constant DIVERGED_NANORINF of type ‐ │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_NONSYMMETRIC │ Constant DIVERGED_NONSYMMETRIC of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_NULL │ Constant DIVERGED_NULL of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_PCSETUP_FAILED │ Constant DIVERGED_PCSETUP_FAILED of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ ITERATING │ Constant ITERATING of type int │
└───────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
CONVERGED_ATOL: int = CONVERGED_ATOL
Constant CONVERGED_ATOL of type int
CONVERGED_ATOL_NORMAL: int = CONVERGED_ATOL_NORMAL
Constant CONVERGED_ATOL_NORMAL of type int
CONVERGED_HAPPY_BREAKDOWN: int = CONVERGED_HAPPY_BREAKDOWN
Constant CONVERGED_HAPPY_BREAKDOWN of type int
CONVERGED_ITERATING: int = CONVERGED_ITERATING
Constant CONVERGED_ITERATING of type int
CONVERGED_ITS: int = CONVERGED_ITS
Constant CONVERGED_ITS of type int
CONVERGED_NEG_CURVE: int = CONVERGED_NEG_CURVE
Constant CONVERGED_NEG_CURVE of type int
CONVERGED_RTOL: int = CONVERGED_RTOL
Constant CONVERGED_RTOL of type int
CONVERGED_RTOL_NORMAL: int = CONVERGED_RTOL_NORMAL
Constant CONVERGED_RTOL_NORMAL of type int
CONVERGED_STEP_LENGTH: int = CONVERGED_STEP_LENGTH
Constant CONVERGED_STEP_LENGTH of type int
DIVERGED_BREAKDOWN: int = DIVERGED_BREAKDOWN
Constant DIVERGED_BREAKDOWN of type int
DIVERGED_BREAKDOWN_BICG: int = DIVERGED_BREAKDOWN_BICG
Constant DIVERGED_BREAKDOWN_BICG of type int
DIVERGED_DTOL: int = DIVERGED_DTOL
Constant DIVERGED_DTOL of type int
DIVERGED_INDEFINITE_MAT: int = DIVERGED_INDEFINITE_MAT
Constant DIVERGED_INDEFINITE_MAT of type int
DIVERGED_INDEFINITE_PC: int = DIVERGED_INDEFINITE_PC
Constant DIVERGED_INDEFINITE_PC of type int
DIVERGED_MAX_IT: int = DIVERGED_MAX_IT
Constant DIVERGED_MAX_IT of type int
DIVERGED_NANORINF: int = DIVERGED_NANORINF
Constant DIVERGED_NANORINF of type int
DIVERGED_NONSYMMETRIC: int = DIVERGED_NONSYMMETRIC
Constant DIVERGED_NONSYMMETRIC of type int
DIVERGED_NULL: int = DIVERGED_NULL
Constant DIVERGED_NULL of type int
DIVERGED_PCSETUP_FAILED: int = DIVERGED_PCSETUP_FAILED
Constant DIVERGED_PCSETUP_FAILED of type int
ITERATING: int = ITERATING
Constant ITERATING of type int
petsc4py.PETSc.KSP.HPDDMType
class petsc4py.PETSc.KSP.HPDDMType
Bases: object
The HPDDM Krylov solver type.
Attributes Summary
┌─────────┬──────────────────────────────┐
│ BCG │ Constant BCG of type int │
├─────────┼──────────────────────────────┤
│ BFBCG │ Constant BFBCG of type int │
├─────────┼──────────────────────────────┤
│ BGCRODR │ Constant BGCRODR of type int │
├─────────┼──────────────────────────────┤
│ BGMRES │ Constant BGMRES of type int │
├─────────┼──────────────────────────────┤
│ CG │ Constant CG of type int │
├─────────┼──────────────────────────────┤
│ GCRODR │ Constant GCRODR of type int │
├─────────┼──────────────────────────────┤
│ GMRES │ Constant GMRES of type int │
├─────────┼──────────────────────────────┤
│ PREONLY │ Constant PREONLY of type int │
└─────────┴──────────────────────────────┘
Attributes Documentation
BCG: int = BCG
Constant BCG of type int
BFBCG: int = BFBCG
Constant BFBCG of type int
BGCRODR: int = BGCRODR
Constant BGCRODR of type int
BGMRES: int = BGMRES
Constant BGMRES of type int
CG: int = CG
Constant CG of type int
GCRODR: int = GCRODR
Constant GCRODR of type int
GMRES: int = GMRES
Constant GMRES of type int
PREONLY: int = PREONLY
Constant PREONLY of type int
petsc4py.PETSc.KSP.NormType
class petsc4py.PETSc.KSP.NormType
Bases: object
KSP norm type.
The available norm types are:
NONE Skips computing the norm, this should generally only be used if you are using the
Krylov method as a smoother with a fixed small number of iterations. Implicitly sets
KSPConvergedSkip as KSP convergence test. Note that certain algorithms such as
Type.GMRES ALWAYS require the norm calculation, for these methods the norms are
still computed, they are just not used in the convergence test.
PRECONDITIONED
The default for left preconditioned solves, uses the l₂ norm of the preconditioned
residual P⁻¹(b - Ax).
UNPRECONDITIONED
Uses the l₂ norm of the true b - Ax residual.
NATURAL
Supported by Type.CG, Type.CR, Type.CGNE, Type.CGS.
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ DEFAULT │ Constant DEFAULT of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NATURAL │ Constant NATURAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NO │ Constant NO of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NONE │ Constant NONE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NORM_DEFAULT │ Constant NORM_DEFAULT of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NORM_NATURAL │ Constant NORM_NATURAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NORM_NONE │ Constant NORM_NONE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ NORM_PRECONDITIONED │ Constant NORM_PRECONDITIONED of type │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ NORM_UNPRECONDITIONED │ Constant NORM_UNPRECONDITIONED of │
│ │ type int │
├───────────────────────┼───────────────────────────────────────┤
│ PRECONDITIONED │ Constant PRECONDITIONED of type int │
├───────────────────────┼───────────────────────────────────────┤
│ UNPRECONDITIONED │ Constant UNPRECONDITIONED of type int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
DEFAULT: int = DEFAULT
Constant DEFAULT of type int
NATURAL: int = NATURAL
Constant NATURAL of type int
NO: int = NO
Constant NO of type int
NONE: int = NONE
Constant NONE of type int
NORM_DEFAULT: int = NORM_DEFAULT
Constant NORM_DEFAULT of type int
NORM_NATURAL: int = NORM_NATURAL
Constant NORM_NATURAL of type int
NORM_NONE: int = NORM_NONE
Constant NORM_NONE of type int
NORM_PRECONDITIONED: int = NORM_PRECONDITIONED
Constant NORM_PRECONDITIONED of type int
NORM_UNPRECONDITIONED: int = NORM_UNPRECONDITIONED
Constant NORM_UNPRECONDITIONED of type int
PRECONDITIONED: int = PRECONDITIONED
Constant PRECONDITIONED of type int
UNPRECONDITIONED: int = UNPRECONDITIONED
Constant UNPRECONDITIONED of type int
petsc4py.PETSc.KSP.Type
class petsc4py.PETSc.KSP.Type
Bases: object
KSP Type.
The available types are:
RICHARDSON
The preconditioned Richardson iterative method KSPRICHARDSON.
CHEBYSHEV
The preconditioned Chebyshev iterative method. KSPCHEBYSHEV.
CG The Preconditioned Conjugate Gradient (PCG) iterative method. KSPCG
GROPPCG
A pipelined conjugate gradient method (Gropp). KSPGROPPCG
PIPECG A pipelined conjugate gradient method. KSPPIPECG
PIPECGRR
Pipelined Conjugate Gradients with Residual Replacement. KSPPIPECGRR
PIPELCG
Deep pipelined (length l) Conjugate Gradient method. KSPPIPELCG
PIPEPRCG
Pipelined predict-and-recompute conjugate gradient method. KSPPIPEPRCG
PIPECG2
Pipelined conjugate gradient method with a single non-blocking reduction per two
iterations. KSPPIPECG2
CGNE Applies the preconditioned conjugate gradient method to the normal equations without
explicitly forming AᵀA. KSPCGNE
NASH Conjugate gradient method subject to a constraint on the solution norm. KSPNASH
STCG Conjugate gradient method subject to a constraint on the solution norm. KSPSTCG
GLTR Conjugate gradient method subject to a constraint on the solution norm. KSPGLTR
FCG Flexible Conjugate Gradient method (FCG). Unlike most KSP methods this allows the
preconditioner to be nonlinear. KSPFCG
PIPEFCG
Pipelined, Flexible Conjugate Gradient method. KSPPIPEFCG
GMRES Generalized Minimal Residual method with restart. KSPGMRES
PIPEFGMRES
Pipelined (1-stage) Flexible Generalized Minimal Residual method. KSPPIPEFGMRES
FGMRES Implements the Flexible Generalized Minimal Residual method. KSPFGMRES
LGMRES Augments the standard Generalized Minimal Residual method approximation space with
approximations to the error from previous restart cycles. KSPLGMRES
DGMRES Deflated Generalized Minimal Residual method. In this implementation, the adaptive
strategy allows to switch to the deflated GMRES when the stagnation occurs. ‐
KSPDGMRES
PGMRES Pipelined Generalized Minimal Residual method. KSPPGMRES
TCQMR A variant of Quasi Minimal Residual (QMR). KSPTCQMR
BCGS Stabilized version of Biconjugate Gradient (BiCGStab) method. KSPBCGS
IBCGS Improved Stabilized version of BiConjugate Gradient (IBiCGStab) method in an
alternative form to have only a single global reduction operation instead of the
usual 3 (or 4). KSPIBCGS
QMRCGS Quasi- Minimal Residual variant of the Bi-CGStab algorithm (QMRCGStab) method. ‐
KSPQMRCGS
FBCGS Flexible Stabilized version of BiConjugate Gradient (BiCGStab) method. KSPFBCGS
FBCGSR A mathematically equivalent variant of flexible stabilized BiConjugate Gradient
(BiCGStab). KSPFBCGSR
BCGSL Variant of the L-step stabilized BiConjugate Gradient (BiCGStab(L)) algorithm. Uses
"L-step" Minimal Residual (MR) polynomials. The variation concerns cases when some
parameters are negative due to round-off. KSPBCGSL
PIPEBCGS
Pipelined stabilized BiConjugate Gradient (BiCGStab) method. KSPPIPEBCGS
CGS Conjugate Gradient Squared method. KSPCGS
TFQMR A Transpose Tree Quasi- Minimal Residual (QMR). KSPCR
CR (Preconditioned) Conjugate Residuals (CR) method. KSPCR
PIPECR Pipelined Conjugate Residual (CR) method. KSPPIPECR
LSQR Least squares solver. KSPLSQR
PREONLY
Applies ONLY the preconditioner exactly once. This may be used in inner iterations,
where it is desired to allow multiple iterations as well as the "0-iteration" case.
It is commonly used with the direct solver preconditioners like PCLU and PCCHOLESKY.
There is an alias of KSPNONE. KSPPREONLY
NONE No solver KSPNONE
QCG Conjugate Gradient (CG) method subject to a constraint on the solution norm. KSPQCG
BICG Implements the Biconjugate gradient method (BiCG). Similar to running the conjugate
gradient on the normal equations. KSPBICG
MINRES Minimum Residual (MINRES) method. KSPMINRES
SYMMLQ Symmetric LQ method (SymmLQ). Uses LQ decomposition (lower trapezoidal). KSPSYMMLQ
LCD Left Conjugate Direction (LCD) method. KSPLCD
PYTHON Python shell solver. Call Python function to implement solver. KSPPYTHON
GCR Preconditioned flexible Generalized Conjugate Residual (GCR) method. KSPGCR
PIPEGCR
Pipelined Generalized Conjugate Residual method. KSPPIPEGCR
TSIRM Two-Stage Iteration with least-squares Residual Minimization method. KSPTSIRM
CGLS Conjugate Gradient method for Least-Squares problems. Supports non-square
(rectangular) matrices. KSPCGLS
FETIDP Dual-Primal (DP) Finite Element Tearing and Interconnect (FETI) method. KSPFETIDP
HPDDM Interface with the HPDDM library. This KSP may be used to further select methods
that are currently not implemented natively in PETSc, e.g., GCRODR, a recycled
Krylov method which is similar to KSPLGMRES. KSPHPDDM
SEE ALSO:
Working with PETSc options, KSPType
Attributes Summary
┌────────────┬───────────────────────────────┐
│ BCGS │ Object BCGS of type str │
├────────────┼───────────────────────────────┤
│ BCGSL │ Object BCGSL of type str │
├────────────┼───────────────────────────────┤
│ BICG │ Object BICG of type str │
├────────────┼───────────────────────────────┤
│ CG │ Object CG of type str │
├────────────┼───────────────────────────────┤
│ CGLS │ Object CGLS of type str │
├────────────┼───────────────────────────────┤
│ CGNE │ Object CGNE of type str │
├────────────┼───────────────────────────────┤
│ CGS │ Object CGS of type str │
├────────────┼───────────────────────────────┤
│ CHEBYSHEV │ Object CHEBYSHEV of type str │
├────────────┼───────────────────────────────┤
│ CR │ Object CR of type str │
├────────────┼───────────────────────────────┤
│ DGMRES │ Object DGMRES of type str │
├────────────┼───────────────────────────────┤
│ FBCGS │ Object FBCGS of type str │
├────────────┼───────────────────────────────┤
│ FBCGSR │ Object FBCGSR of type str │
├────────────┼───────────────────────────────┤
│ FCG │ Object FCG of type str │
├────────────┼───────────────────────────────┤
│ FETIDP │ Object FETIDP of type str │
├────────────┼───────────────────────────────┤
│ FGMRES │ Object FGMRES of type str │
├────────────┼───────────────────────────────┤
│ GCR │ Object GCR of type str │
├────────────┼───────────────────────────────┤
│ GLTR │ Object GLTR of type str │
├────────────┼───────────────────────────────┤
│ GMRES │ Object GMRES of type str │
├────────────┼───────────────────────────────┤
│ GROPPCG │ Object GROPPCG of type str │
├────────────┼───────────────────────────────┤
│ HPDDM │ Object HPDDM of type str │
├────────────┼───────────────────────────────┤
│ IBCGS │ Object IBCGS of type str │
├────────────┼───────────────────────────────┤
│ LCD │ Object LCD of type str │
├────────────┼───────────────────────────────┤
│ LGMRES │ Object LGMRES of type str │
├────────────┼───────────────────────────────┤
│ LSQR │ Object LSQR of type str │
├────────────┼───────────────────────────────┤
│ MINRES │ Object MINRES of type str │
├────────────┼───────────────────────────────┤
│ NASH │ Object NASH of type str │
├────────────┼───────────────────────────────┤
│ NONE │ Object NONE of type str │
├────────────┼───────────────────────────────┤
│ PGMRES │ Object PGMRES of type str │
├────────────┼───────────────────────────────┤
│ PIPEBCGS │ Object PIPEBCGS of type str │
├────────────┼───────────────────────────────┤
│ PIPECG │ Object PIPECG of type str │
├────────────┼───────────────────────────────┤
│ PIPECG2 │ Object PIPECG2 of type str │
├────────────┼───────────────────────────────┤
│ PIPECGRR │ Object PIPECGRR of type str │
├────────────┼───────────────────────────────┤
│ PIPECR │ Object PIPECR of type str │
├────────────┼───────────────────────────────┤
│ PIPEFCG │ Object PIPEFCG of type str │
├────────────┼───────────────────────────────┤
│ PIPEFGMRES │ Object PIPEFGMRES of type str │
├────────────┼───────────────────────────────┤
│ PIPEGCR │ Object PIPEGCR of type str │
├────────────┼───────────────────────────────┤
│ PIPELCG │ Object PIPELCG of type str │
├────────────┼───────────────────────────────┤
│ PIPEPRCG │ Object PIPEPRCG of type str │
├────────────┼───────────────────────────────┤
│ PREONLY │ Object PREONLY of type str │
├────────────┼───────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├────────────┼───────────────────────────────┤
│ QCG │ Object QCG of type str │
├────────────┼───────────────────────────────┤
│ QMRCGS │ Object QMRCGS of type str │
├────────────┼───────────────────────────────┤
│ RICHARDSON │ Object RICHARDSON of type str │
├────────────┼───────────────────────────────┤
│ STCG │ Object STCG of type str │
├────────────┼───────────────────────────────┤
│ SYMMLQ │ Object SYMMLQ of type str │
├────────────┼───────────────────────────────┤
│ TCQMR │ Object TCQMR of type str │
├────────────┼───────────────────────────────┤
│ TFQMR │ Object TFQMR of type str │
├────────────┼───────────────────────────────┤
│ TSIRM │ Object TSIRM of type str │
└────────────┴───────────────────────────────┘
Attributes Documentation
BCGS: str = BCGS
Object BCGS of type str
BCGSL: str = BCGSL
Object BCGSL of type str
BICG: str = BICG
Object BICG of type str
CG: str = CG
Object CG of type str
CGLS: str = CGLS
Object CGLS of type str
CGNE: str = CGNE
Object CGNE of type str
CGS: str = CGS
Object CGS of type str
CHEBYSHEV: str = CHEBYSHEV
Object CHEBYSHEV of type str
CR: str = CR
Object CR of type str
DGMRES: str = DGMRES
Object DGMRES of type str
FBCGS: str = FBCGS
Object FBCGS of type str
FBCGSR: str = FBCGSR
Object FBCGSR of type str
FCG: str = FCG
Object FCG of type str
FETIDP: str = FETIDP
Object FETIDP of type str
FGMRES: str = FGMRES
Object FGMRES of type str
GCR: str = GCR
Object GCR of type str
GLTR: str = GLTR
Object GLTR of type str
GMRES: str = GMRES
Object GMRES of type str
GROPPCG: str = GROPPCG
Object GROPPCG of type str
HPDDM: str = HPDDM
Object HPDDM of type str
IBCGS: str = IBCGS
Object IBCGS of type str
LCD: str = LCD
Object LCD of type str
LGMRES: str = LGMRES
Object LGMRES of type str
LSQR: str = LSQR
Object LSQR of type str
MINRES: str = MINRES
Object MINRES of type str
NASH: str = NASH
Object NASH of type str
NONE: str = NONE
Object NONE of type str
PGMRES: str = PGMRES
Object PGMRES of type str
PIPEBCGS: str = PIPEBCGS
Object PIPEBCGS of type str
PIPECG: str = PIPECG
Object PIPECG of type str
PIPECG2: str = PIPECG2
Object PIPECG2 of type str
PIPECGRR: str = PIPECGRR
Object PIPECGRR of type str
PIPECR: str = PIPECR
Object PIPECR of type str
PIPEFCG: str = PIPEFCG
Object PIPEFCG of type str
PIPEFGMRES: str = PIPEFGMRES
Object PIPEFGMRES of type str
PIPEGCR: str = PIPEGCR
Object PIPEGCR of type str
PIPELCG: str = PIPELCG
Object PIPELCG of type str
PIPEPRCG: str = PIPEPRCG
Object PIPEPRCG of type str
PREONLY: str = PREONLY
Object PREONLY of type str
PYTHON: str = PYTHON
Object PYTHON of type str
QCG: str = QCG
Object QCG of type str
QMRCGS: str = QMRCGS
Object QMRCGS of type str
RICHARDSON: str = RICHARDSON
Object RICHARDSON of type str
STCG: str = STCG
Object STCG of type str
SYMMLQ: str = SYMMLQ
Object SYMMLQ of type str
TCQMR: str = TCQMR
Object TCQMR of type str
TFQMR: str = TFQMR
Object TFQMR of type str
TSIRM: str = TSIRM
Object TSIRM of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ addConvergenceTest(converged[, args, │ Add the function to be used to │
│ kargs, ...]) │ determine convergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix(prefix) │ Append to prefix used for all KSP │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ buildResidual([r]) │ Return the residual of the linear │
│ │ system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ buildSolution([x]) │ Return the solution vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ callConvergenceTest(its, rnorm) │ Call the convergence test callback. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeEigenvalues() │ Compute the extreme eigenvalues for │
│ │ the preconditioned operator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeExtremeSingularValues() │ Compute the extreme singular values │
│ │ for the preconditioned operator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create the KSP context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createPython([context, comm]) │ Create a linear solver of Python │
│ │ type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy KSP context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAppCtx() │ Return the user-defined context for │
│ │ the linear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCGObjectiveValue() │ Return the CG objective function │
│ │ value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getComputeEigenvalues() │ Return flag indicating whether │
│ │ eigenvalues will be calculated. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getComputeSingularValues() │ Return flag indicating whether │
│ │ singular values will be calculated. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergedReason() │ Use reason property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergenceHistory() │ Return array containing the residual │
│ │ history. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergenceTest() │ Return the function to be used to │
│ │ determine convergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM that may be used by │
│ │ some preconditioners. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getErrorIfNotConverged() │ Return the flag indicating the solver │
│ │ will error if divergent. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getHPDDMType() │ Return the Krylov solver type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInitialGuessKnoll() │ Determine whether the KSP solver is │
│ │ using the Knoll trick. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInitialGuessNonzero() │ Determine whether the KSP solver uses │
│ │ a zero initial guess. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIterationNumber() │ Use its property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMonitor() │ Return function used to monitor the │
│ │ residual. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNormType() │ Return the norm that is used for │
│ │ convergence testing. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOperators() │ Return the matrix associated with the │
│ │ linear system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for all KSP │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPC() │ Return the preconditioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPCSide() │ Return the preconditioning side. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing Python methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getResidualNorm() │ Use norm property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRhs() │ Return the right-hand side vector for │
│ │ the linear system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolution() │ Return the solution for the linear │
│ │ system to be solved. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTolerances() │ Return various tolerances used by the │
│ │ KSP convergence tests. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the KSP type as a string from │
│ │ the KSP object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getWorkVecs([right, left]) │ Create working vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ logConvergenceHistory(rnorm) │ Add residual to convergence history. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matSolve(B, X) │ Solve a linear system with multiple │
│ │ right-hand sides. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matSolveTranspose(B, X) │ Solve the transpose of a linear │
│ │ system with multiple RHS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitor(its, rnorm) │ Run the user provided monitor │
│ │ routines, if they exist. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitorCancel() │ Clear all monitors for a KSP object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Resets a KSP context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAppCtx(appctx) │ Set the optional user-defined context │
│ │ for the linear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setComputeEigenvalues(flag) │ Set a flag to compute eigenvalues. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setComputeOperators(operators[, args, │ Set routine to compute the linear │
│ kargs]) │ operators. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setComputeRHS(rhs[, args, kargs]) │ Set routine to compute the right-hand │
│ │ side of the linear system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setComputeSingularValues(flag) │ Set flag to calculate singular │
│ │ values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergedReason(reason) │ Use reason property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergenceHistory([length, │ Set the array used to hold the │
│ reset]) │ residual history. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergenceTest(converged[, args, │ Set the function to be used to │
│ kargs]) │ determine convergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM that may be used by some │
│ │ preconditioners. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDMActive(flag) │ DM should be used to generate system │
│ │ matrix & RHS vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setErrorIfNotConverged(flag) │ Cause solve to generate an error if │
│ │ not converged. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set KSP options from the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setGMRESRestart(restart) │ Set number of iterations at which KSP │
│ │ restarts. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMType(hpddm_type) │ Set the Krylov solver type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setInitialGuessKnoll(flag) │ Tell solver to use PC.apply to │
│ │ compute the initial guess. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setInitialGuessNonzero(flag) │ Tell the iterative solver that the │
│ │ initial guess is nonzero. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIterationNumber(its) │ Use its property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMonitor(monitor[, args, kargs]) │ Set additional function to monitor │
│ │ the residual. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNormType(normtype) │ Set the norm that is used for │
│ │ convergence testing. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOperators([A, P]) │ Set matrix associated with the linear │
│ │ system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for all KSP │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPC(pc) │ Set the preconditioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPCSide(side) │ Set the preconditioning side. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPostSolve(postsolve[, args, │ Set the function that is called at │
│ kargs]) │ the end of each KSP.solve. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPreSolve(presolve[, args, kargs]) │ Set the function that is called at │
│ │ the beginning of each KSP.solve. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext([context]) │ Set the instance of the class │
│ │ implementing Python methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setResidualNorm(rnorm) │ Use norm property. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTolerances([rtol, atol, divtol, │ Set various tolerances used by the │
│ max_it]) │ KSP convergence testers. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(ksp_type) │ Build the KSP data structure for a │
│ │ particular Type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up internal data structures for │
│ │ an iterative solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUpOnBlocks() │ Set up the preconditioner for each │
│ │ block in a block method. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUseFischerGuess(model, size) │ Use the Paul Fischer algorithm to │
│ │ compute initial guesses. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solve(b, x) │ Solve the linear system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveTranspose(b, x) │ Solve the transpose of a linear │
│ │ system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Print the KSP data structure. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────────┬───────────────────────────────────────┐
│ appctx │ The solver application context. │
├───────────────┼───────────────────────────────────────┤
│ atol │ The absolute tolerance of the solver. │
├───────────────┼───────────────────────────────────────┤
│ divtol │ The divergence tolerance of the │
│ │ solver. │
├───────────────┼───────────────────────────────────────┤
│ dm │ The solver DM. │
├───────────────┼───────────────────────────────────────┤
│ guess_knoll │ Whether solver uses Knoll trick. │
├───────────────┼───────────────────────────────────────┤
│ guess_nonzero │ Whether guess is non-zero. │
├───────────────┼───────────────────────────────────────┤
│ history │ The convergence history of the │
│ │ solver. │
├───────────────┼───────────────────────────────────────┤
│ is_converged │ Boolean indicating if the solver has │
│ │ converged. │
├───────────────┼───────────────────────────────────────┤
│ is_diverged │ Boolean indicating if the solver has │
│ │ failed. │
├───────────────┼───────────────────────────────────────┤
│ is_iterating │ Boolean indicating if the solver has │
│ │ not converged yet. │
├───────────────┼───────────────────────────────────────┤
│ its │ The current number of iterations the │
│ │ solver has taken. │
├───────────────┼───────────────────────────────────────┤
│ mat_op │ The system matrix operator. │
├───────────────┼───────────────────────────────────────┤
│ mat_pc │ The preconditioner operator. │
├───────────────┼───────────────────────────────────────┤
│ max_it │ The maximum number of iteration the │
│ │ solver may take. │
├───────────────┼───────────────────────────────────────┤
│ norm │ The norm of the residual at the │
│ │ current iteration. │
├───────────────┼───────────────────────────────────────┤
│ norm_type │ The norm used by the solver. │
├───────────────┼───────────────────────────────────────┤
│ pc │ The PC of the solver. │
├───────────────┼───────────────────────────────────────┤
│ pc_side │ The side on which preconditioning is │
│ │ performed. │
├───────────────┼───────────────────────────────────────┤
│ reason │ The converged reason. │
├───────────────┼───────────────────────────────────────┤
│ rtol │ The relative tolerance of the solver. │
├───────────────┼───────────────────────────────────────┤
│ vec_rhs │ The right-hand side vector. │
├───────────────┼───────────────────────────────────────┤
│ vec_sol │ The solution vector. │
└───────────────┴───────────────────────────────────────┘
Methods Documentation
addConvergenceTest(converged, args=None, kargs=None, prepend=False)
Add the function to be used to determine convergence.
Logically collective.
Parameters
• converged (KSPConvergenceTestFunction) -- Callback which computes the convergence.
• args (tuple[Any, ...] | None) -- Positional arguments for callback function.
• kargs (dict[str, Any] | None) -- Keyword arguments for callback function.
• prepend (bool) -- Whether to prepend this call before the default convergence test
or call it after.
Return type
None
Notes
Cannot be mixed with a call to setConvergenceTest. It can only be called once. If called
multiple times, it will generate an error.
SEE ALSO:
setTolerances, getConvergenceTest, setConvergenceTest, KSPSetConvergenceTest, ‐
KSPConvergedDefault
Source code at petsc4py/PETSc/KSP.pyx:1065
appendOptionsPrefix(prefix)
Append to prefix used for all KSP options in the database.
Logically collective.
Parameters
prefix (str | None) -- The options prefix to append.
Return type
None
Notes
A hyphen (-) must NOT be given at the beginning of the prefix name. The first character of
all runtime options is AUTOMATICALLY the hyphen.
SEE ALSO:
KSPAppendOptionsPrefix
Source code at petsc4py/PETSc/KSP.pyx:575
buildResidual(r=None)
Return the residual of the linear system.
Collective.
Parameters
r (Vec | None) -- Optional vector to use for the result.
Return type
Vec
SEE ALSO:
buildSolution, KSPBuildResidual
Source code at petsc4py/PETSc/KSP.pyx:2063
buildSolution(x=None)
Return the solution vector.
Collective.
Parameters
x (Vec | None) -- Optional vector to store the solution.
Return type
Vec
SEE ALSO:
buildResidual, KSPBuildSolution
Source code at petsc4py/PETSc/KSP.pyx:2041
callConvergenceTest(its, rnorm)
Call the convergence test callback.
Collective.
Parameters
• its (int) -- Number of iterations.
• rnorm (float) -- The residual norm.
Return type
None
Notes
This functionality is implemented in petsc4py.
Source code at petsc4py/PETSc/KSP.pyx:1121
computeEigenvalues()
Compute the extreme eigenvalues for the preconditioned operator.
Not collective.
SEE ALSO:
KSPComputeEigenvalues
Source code at petsc4py/PETSc/KSP.pyx:2085
Return type
ArrayComplex
computeExtremeSingularValues()
Compute the extreme singular values for the preconditioned operator.
Collective.
Returns
• smax (float) -- The maximum singular value.
• smin (float) -- The minimum singular value.
Return type
tuple[float, float]
SEE ALSO:
KSPComputeExtremeSingularValues
Source code at petsc4py/PETSc/KSP.pyx:2108
create(comm=None)
Create the KSP context.
Collective.
SEE ALSO:
KSPCreate
Source code at petsc4py/PETSc/KSP.pyx:457
Parameters
comm (Comm | None)
Return type
Self
createPython(context=None, comm=None)
Create a linear solver of Python type.
Collective.
Parameters
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python linear solver type, setType, setPythonContext, Type.PYTHON
Source code at petsc4py/PETSc/KSP.pyx:2154
destroy()
Destroy KSP context.
Collective.
SEE ALSO:
KSPDestroy
Source code at petsc4py/PETSc/KSP.pyx:444
Return type
Self
getAppCtx()
Return the user-defined context for the linear solver.
Not collective.
SEE ALSO:
setAppCtx
Source code at petsc4py/PETSc/KSP.pyx:640
Return type
Any
getCGObjectiveValue()
Return the CG objective function value.
Not collective.
SEE ALSO:
KSPCGGetObjFcn
Source code at petsc4py/PETSc/KSP.pyx:1882
Return type
float
getComputeEigenvalues()
Return flag indicating whether eigenvalues will be calculated.
Not collective.
Return the flag indicating that the extreme eigenvalues values will be calculated via a
Lanczos or Arnoldi process as the linear system is solved.
SEE ALSO:
setComputeEigenvalues, KSPSetComputeEigenvalues
Source code at petsc4py/PETSc/KSP.pyx:1430
Return type
bool
getComputeSingularValues()
Return flag indicating whether singular values will be calculated.
Not collective.
Return the flag indicating whether the extreme singular values will be calculated via a
Lanczos or Arnoldi process as the linear system is solved.
SEE ALSO:
setComputeSingularValues, KSPGetComputeSingularValues
Source code at petsc4py/PETSc/KSP.pyx:1474
Return type
bool
getConvergedReason()
Use reason property.
Source code at petsc4py/PETSc/KSP.pyx:1876
Return type
ConvergedReason
getConvergenceHistory()
Return array containing the residual history.
Not collective.
SEE ALSO:
setConvergenceHistory, KSPGetResidualHistory
Source code at petsc4py/PETSc/KSP.pyx:1188
Return type
ArrayReal
getConvergenceTest()
Return the function to be used to determine convergence.
Logically collective.
SEE ALSO:
setTolerances, setConvergenceTest, KSPGetConvergenceTest, KSPConvergedDefault
Source code at petsc4py/PETSc/KSP.pyx:1108
Return type
KSPConvergenceTestFunction
getDM()
Return the DM that may be used by some preconditioners.
Not collective.
SEE ALSO:
PETSc.KSP, DM, KSPGetDM
Source code at petsc4py/PETSc/KSP.pyx:654
Return type
DM
getErrorIfNotConverged()
Return the flag indicating the solver will error if divergent.
Not collective.
SEE ALSO:
KSPGetErrorIfNotConverged
Source code at petsc4py/PETSc/KSP.pyx:1946
Return type
bool
getHPDDMType()
Return the Krylov solver type.
Not collective.
SEE ALSO:
KSPHPDDMGetType
Source code at petsc4py/PETSc/KSP.pyx:1914
Return type
HPDDMType
getInitialGuessKnoll()
Determine whether the KSP solver is using the Knoll trick.
Not collective.
This uses the Knoll trick; using PC.apply to compute the initial guess.
SEE ALSO:
KSPGetInitialGuessKnoll
Source code at petsc4py/PETSc/KSP.pyx:1550
Return type
bool
getInitialGuessNonzero()
Determine whether the KSP solver uses a zero initial guess.
Not collective.
SEE ALSO:
KSPGetInitialGuessNonzero
Source code at petsc4py/PETSc/KSP.pyx:1516
Return type
bool
getIterationNumber()
Use its property.
Source code at petsc4py/PETSc/KSP.pyx:1854
Return type
int
getMonitor()
Return function used to monitor the residual.
Not collective.
SEE ALSO:
Working with PETSc options, setMonitor, monitor, monitorCancel, KSPGetMonitorContext
Source code at petsc4py/PETSc/KSP.pyx:1266
Return type
KSPMonitorFunction
getNormType()
Return the norm that is used for convergence testing.
Not collective.
SEE ALSO:
NormType, setNormType, KSPGetNormType, KSPConvergedSkip
Source code at petsc4py/PETSc/KSP.pyx:1390
Return type
NormType
getOperators()
Return the matrix associated with the linear system.
Collective.
Return the matrix associated with the linear system and a (possibly) different one used to
construct the preconditioner.
Returns
• A (Mat) -- Matrix that defines the linear system.
• P (Mat) -- Matrix to be used in constructing the preconditioner, usually the same
as A.
Return type
tuple[Mat, Mat]
SEE ALSO:
PETSc.KSP, solve, setOperators, KSPGetOperators
Source code at petsc4py/PETSc/KSP.pyx:850
getOptionsPrefix()
Return the prefix used for all KSP options in the database.
Not collective.
SEE ALSO:
KSPGetOptionsPrefix
Source code at petsc4py/PETSc/KSP.pyx:561
Return type
str
getPC()
Return the preconditioner.
Not collective.
SEE ALSO:
PETSc.KSP, setPC, KSPGetPC
Source code at petsc4py/PETSc/KSP.pyx:897
Return type
PC
getPCSide()
Return the preconditioning side.
Not collective.
SEE ALSO:
Working with PETSc options, setPCSide, setNormType, getNormType, KSPGetPCSide
Source code at petsc4py/PETSc/KSP.pyx:1349
Return type
Side
getPythonContext()
Return the instance of the class implementing Python methods.
Not collective.
SEE ALSO:
PETSc Python linear solver type, setPythonContext
Source code at petsc4py/PETSc/KSP.pyx:2195
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the solver.
Not collective.
SEE ALSO:
PETSc Python linear solver type, setPythonContext, setPythonType, KSPPythonGetType
Source code at petsc4py/PETSc/KSP.pyx:2225
Return type
str
getResidualNorm()
Use norm property.
Source code at petsc4py/PETSc/KSP.pyx:1865
Return type
float
getRhs()
Return the right-hand side vector for the linear system.
Not collective.
SEE ALSO:
KSPGetRhs
Source code at petsc4py/PETSc/KSP.pyx:1960
Return type
Vec
getSolution()
Return the solution for the linear system to be solved.
Not collective.
Note that this may not be the solution that is stored during the iterative process.
SEE ALSO:
KSPGetSolution
Source code at petsc4py/PETSc/KSP.pyx:1975
Return type
Vec
getTolerances()
Return various tolerances used by the KSP convergence tests.
Not collective.
Return the relative, absolute, divergence, and maximum iteration tolerances used by the
default KSP convergence tests.
Returns
• rtol (float) -- The relative convergence tolerance
• atol (float) -- The absolute convergence tolerance
• dtol (float) -- The divergence tolerance
• maxits (int) -- Maximum number of iterations
Return type
tuple[float, float, float, int]
SEE ALSO:
setTolerances, KSPGetTolerances
Source code at petsc4py/PETSc/KSP.pyx:971
getType()
Return the KSP type as a string from the KSP object.
Not collective.
SEE ALSO:
KSPGetType
Source code at petsc4py/PETSc/KSP.pyx:509
Return type
str
getWorkVecs(right=None, left=None)
Create working vectors.
Collective.
Parameters
• right (int | None) -- Number of right hand vectors to allocate.
• left (int | None) -- Number of left hand vectors to allocate.
Returns
• R (list of Vec) -- List of correctly allocated right hand vectors.
• L (list of Vec) -- List of correctly allocated left hand vectors.
Return type
tuple[list[Vec], list[Vec]] | list[Vec] | None
Source code at petsc4py/PETSc/KSP.pyx:1993
logConvergenceHistory(rnorm)
Add residual to convergence history.
Logically collective.
Parameters
rnorm (float) -- Residual norm to be added to convergence history.
Return type
None
Source code at petsc4py/PETSc/KSP.pyx:1203
matSolve(B, X)
Solve a linear system with multiple right-hand sides.
Collective.
These are stored as a Mat.Type.DENSE. Unlike solve, B and X must be different matrices.
Parameters
• B (Mat) -- Block of right-hand sides.
• X (Mat) -- Block of solutions.
Return type
None
SEE ALSO:
solve, KSPMatSolve
Source code at petsc4py/PETSc/KSP.pyx:1808
matSolveTranspose(B, X)
Solve the transpose of a linear system with multiple RHS.
Collective.
Parameters
• B (Mat) -- Block of right-hand sides.
• X (Mat) -- Block of solutions.
Return type
None
SEE ALSO:
solveTranspose, KSPMatSolve
Source code at petsc4py/PETSc/KSP.pyx:1830
monitor(its, rnorm)
Run the user provided monitor routines, if they exist.
Collective.
Notes
This routine is called by the KSP implementations. It does not typically need to be called
by the user.
SEE ALSO:
setMonitor, KSPMonitor
Source code at petsc4py/PETSc/KSP.pyx:1294
Parameters
• its (int)
• rnorm (float)
Return type
None
monitorCancel()
Clear all monitors for a KSP object.
Logically collective.
SEE ALSO:
Working with PETSc options, getMonitor, setMonitor, monitor, KSPMonitorCancel
Source code at petsc4py/PETSc/KSP.pyx:1279
Return type
None
reset()
Resets a KSP context.
Collective.
Resets a KSP context to the kspsetupcalled = 0 state and removes any allocated Vecs and
Mats.
SEE ALSO:
KSPReset
Source code at petsc4py/PETSc/KSP.pyx:1607
Return type
None
setAppCtx(appctx)
Set the optional user-defined context for the linear solver.
Not collective.
Parameters
appctx (Any) -- The user defined context
Return type
None
Notes
The user context is a way for users to attach any information to the KSP that they may need
later when interacting with the solver.
SEE ALSO:
getAppCtx
Source code at petsc4py/PETSc/KSP.pyx:617
setComputeEigenvalues(flag)
Set a flag to compute eigenvalues.
Logically collective.
Set a flag so that the extreme eigenvalues values will be calculated via a Lanczos or
Arnoldi process as the linear system is solved.
Parameters
flag (bool) -- Boolean whether to compute eigenvalues (or not).
Return type
None
Notes
Currently this option is not valid for all iterative methods.
SEE ALSO:
getComputeEigenvalues, KSPSetComputeEigenvalues
Source code at petsc4py/PETSc/KSP.pyx:1404
setComputeOperators(operators, args=None, kargs=None)
Set routine to compute the linear operators.
Logically collective.
Parameters
• operators (KSPOperatorsFunction) -- Function which computes the operators.
• args (tuple[Any, ...] | None) -- Positional arguments for callback function
operators.
• kargs (dict[str, Any] | None) -- Keyword arguments for callback function
operators.
Return type
None
Notes
The user provided function Operators will be called automatically at the very next call to
solve. It will NOT be called at future solve calls unless either setComputeOperators or
setOperators is called before that solve is called. This allows the same system to be
solved several times with different right-hand side functions, but is a confusing API since
one might expect it to be called for each solve.
To reuse the same preconditioner for the next solve and not compute a new one based on the
most recently computed matrix call KSPSetReusePreconditioner.
SEE ALSO:
PETSc.KSP, solve, setOperators, KSPSetComputeOperators, KSPSetReusePreconditioner
Source code at petsc4py/PETSc/KSP.pyx:764
setComputeRHS(rhs, args=None, kargs=None)
Set routine to compute the right-hand side of the linear system.
Logically collective.
Parameters
• rhs (KSPRHSFunction) -- Function which computes the right-hand side.
• args (tuple[Any, ...] | None) -- Positional arguments for callback function rhs.
• kargs (dict[str, Any] | None) -- Keyword arguments for callback function rhs.
Return type
None
Notes
The routine you provide will be called each time you call solve to prepare the new
right-hand side for that solve.
SEE ALSO:
PETSc.KSP, solve, KSPSetComputeRHS
Source code at petsc4py/PETSc/KSP.pyx:730
setComputeSingularValues(flag)
Set flag to calculate singular values.
Logically collective.
Set a flag so that the extreme singular values will be calculated via a Lanczos or Arnoldi
process as the linear system is solved.
Parameters
flag (bool) -- Boolean whether to compute singular values (or not).
Return type
None
Notes
Currently this option is not valid for all iterative methods.
SEE ALSO:
getComputeSingularValues, KSPSetComputeSingularValues
Source code at petsc4py/PETSc/KSP.pyx:1448
setConvergedReason(reason)
Use reason property.
Source code at petsc4py/PETSc/KSP.pyx:1871
Parameters
reason (ConvergedReason)
Return type
None
setConvergenceHistory(length=None, reset=False)
Set the array used to hold the residual history.
Not collective.
If set, this array will contain the residual norms computed at each iteration of the
solver.
Parameters
• length (int | None) -- Length of array to store history in.
• reset (bool) -- True indicates the history counter is reset to zero for each new
linear solve.
Return type
None
Notes
If length is not provided or None then a default array of length 10000 is allocated.
If the array is not long enough then once the iterations is longer than the array length
solve stops recording the history.
SEE ALSO:
getConvergenceHistory, KSPSetResidualHistory
Source code at petsc4py/PETSc/KSP.pyx:1144
setConvergenceTest(converged, args=None, kargs=None)
Set the function to be used to determine convergence.
Logically collective.
Parameters
• converged (KSPConvergenceTestFunction) -- Callback which computes the convergence.
• args (tuple[Any, ...] | None) -- Positional arguments for callback function.
• kargs (dict[str, Any] | None) -- Keyword arguments for callback function.
Return type
None
Notes
Must be called after the KSP type has been set so put this after a call to setType, or
setFromOptions.
The default is a combination of relative and absolute tolerances. The residual value that
is tested may be an approximation; routines that need exact values should compute them.
SEE ALSO:
addConvergenceTest, ConvergedReason, setTolerances, getConvergenceTest, buildResidual, ‐
KSPSetConvergenceTest, KSPConvergedDefault
Source code at petsc4py/PETSc/KSP.pyx:1000
setDM(dm)
Set the DM that may be used by some preconditioners.
Logically collective.
Parameters
dm (DM) -- The DM object, cannot be None.
Return type
None
Notes
If this is used then the KSP will attempt to use the DM to create the matrix and use the
routine set with DM.setKSPComputeOperators. Use setDMActive(False) to instead use the
matrix you have provided with setOperators.
A DM can only be used for solving one problem at a time because information about the
problem is stored on the DM, even when not using interfaces like DM.setKSPComputeOperators.
Use DM.clone to get a distinct DM when solving different problems using the same function
space.
SEE ALSO:
PETSc.KSP, DM, DM.setKSPComputeOperators, setOperators, DM.clone, KSPSetDM
Source code at petsc4py/PETSc/KSP.pyx:671
setDMActive(flag)
DM should be used to generate system matrix & RHS vector.
Logically collective.
Parameters
flag (bool) -- Whether to use the DM.
Return type
None
Notes
By default setDM sets the DM as active, call setDMActive(False) after setDM(dm) to not have
the KSP object use the DM to generate the matrices.
SEE ALSO:
PETSc.KSP, DM, setDM, KSPSetDMActive
Source code at petsc4py/PETSc/KSP.pyx:704
setErrorIfNotConverged(flag)
Cause solve to generate an error if not converged.
Logically collective.
Parameters
flag (bool) -- True enables this behavior.
Return type
None
SEE ALSO:
KSPSetErrorIfNotConverged
Source code at petsc4py/PETSc/KSP.pyx:1928
setFromOptions()
Set KSP options from the options database.
Collective.
This routine must be called before setUp if the user is to be allowed to set the Krylov
type.
SEE ALSO:
Working with PETSc options, KSPSetFromOptions
Source code at petsc4py/PETSc/KSP.pyx:600
Return type
None
setGMRESRestart(restart)
Set number of iterations at which KSP restarts.
Logically collective.
Suitable KSPs are: KSPGMRES, KSPFGMRES and KSPLGMRES.
Parameters
restart (int) -- Integer restart value.
Return type
None
SEE ALSO:
KSPGMRESSetRestart
Source code at petsc4py/PETSc/KSP.pyx:2132
setHPDDMType(hpddm_type)
Set the Krylov solver type.
Collective.
Parameters
hpddm_type (HPDDMType) -- The type of Krylov solver to use.
Return type
None
SEE ALSO:
KSPHPDDMSetType
Source code at petsc4py/PETSc/KSP.pyx:1896
setInitialGuessKnoll(flag)
Tell solver to use PC.apply to compute the initial guess.
Logically collective.
This is the Knoll trick.
Parameters
flag (bool) -- True uses Knoll trick.
Return type
None
SEE ALSO:
KSPSetInitialGuessKnoll
Source code at petsc4py/PETSc/KSP.pyx:1530
setInitialGuessNonzero(flag)
Tell the iterative solver that the initial guess is nonzero.
Logically collective.
Otherwise KSP assumes the initial guess is to be zero (and thus zeros it out before
solving).
Parameters
flag (bool) -- True indicates the guess is non-zero, False indicates the guess is
zero.
Return type
None
SEE ALSO:
KSPSetInitialGuessNonzero
Source code at petsc4py/PETSc/KSP.pyx:1494
setIterationNumber(its)
Use its property.
Source code at petsc4py/PETSc/KSP.pyx:1849
Parameters
its (int)
Return type
None
setMonitor(monitor, args=None, kargs=None)
Set additional function to monitor the residual.
Logically collective.
Set an ADDITIONAL function to be called at every iteration to monitor the residual/error
etc.
Parameters
• monitor (KSPMonitorFunction) -- Callback which monitors the convergence.
• args (tuple[Any, ...] | None) -- Positional arguments for callback function.
• kargs (dict[str, Any] | None) -- Keyword arguments for callback function.
Return type
None
Notes
The default is to do nothing. To print the residual, or preconditioned residual if
setNormType(NORM_PRECONDITIONED) was called, use monitor as the monitoring routine, with a
PETSc.Viewer.ASCII as the context.
Several different monitoring routines may be set by calling setMonitor multiple times; all
will be called in the order in which they were set.
SEE ALSO:
Working with PETSc options, getMonitor, monitor, monitorCancel, KSPMonitorSet
Source code at petsc4py/PETSc/KSP.pyx:1219
setNormType(normtype)
Set the norm that is used for convergence testing.
Logically collective.
Parameters
normtype (NormType) -- The norm type to use (see NormType).
Return type
None
Notes
Not all combinations of preconditioner side (see setPCSide) and norm type are supported by
all Krylov methods. If only one is set, PETSc tries to automatically change the other to
find a compatible pair. If no such combination is supported, PETSc will generate an error.
SEE ALSO:
NormType, Working with PETSc options, setUp, solve, destroy, setPCSide, getPCSide,
NormType, KSPSetNormType, KSPConvergedSkip, KSPSetCheckNormIteration
Source code at petsc4py/PETSc/KSP.pyx:1363
setOperators(A=None, P=None)
Set matrix associated with the linear system.
Collective.
Set the matrix associated with the linear system and a (possibly) different one from which
the preconditioner will be built.
Parameters
• A (Mat | None) -- Matrix that defines the linear system.
• P (Mat | None) -- Matrix to be used in constructing the preconditioner, usually
the same as A.
Return type
None
Notes
If you know the operator A has a null space you can use Mat.setNullSpace and
Mat.setTransposeNullSpace to supply the null space to A and the KSP solvers will
automatically use that null space as needed during the solution process.
All future calls to setOperators must use the same size matrices!
Passing None for A or P removes the matrix that is currently used.
SEE ALSO:
PETSc.KSP, solve, setComputeOperators, KSPSetOperators
Source code at petsc4py/PETSc/KSP.pyx:809
setOptionsPrefix(prefix)
Set the prefix used for all KSP options in the database.
Logically collective.
Parameters
prefix (str | None) -- The options prefix.
Return type
None
Notes
A hyphen (-) must NOT be given at the beginning of the prefix name. The first character of
all runtime options is AUTOMATICALLY the hyphen. For example, to distinguish between the
runtime options for two different KSP contexts, one could call ` KSPSetOptionsPrefix(ksp1,
"sys1_") KSPSetOptionsPrefix(ksp2, "sys2_") `
This would enable use of different options for each system, such as ` -sys1_ksp_type gmres
-sys1_ksp_rtol 1.e-3 -sys2_ksp_type bcgs -sys2_ksp_rtol 1.e-4 `
SEE ALSO:
Working with PETSc options, KSPSetOptionsPrefix
Source code at petsc4py/PETSc/KSP.pyx:523
setPC(pc)
Set the preconditioner.
Collective.
Set the preconditioner to be used to calculate the application of the preconditioner on a
vector.
Parameters
pc (PC) -- The preconditioner object
Return type
None
SEE ALSO:
PETSc.KSP, getPC, KSPSetPC
Source code at petsc4py/PETSc/KSP.pyx:877
setPCSide(side)
Set the preconditioning side.
Logically collective.
Parameters
side (Side) -- The preconditioning side (see PC.Side).
Return type
None
Notes
Left preconditioning is used by default for most Krylov methods except Type.FGMRES which
only supports right preconditioning.
For methods changing the side of the preconditioner changes the norm type that is used, see
setNormType.
Symmetric preconditioning is currently available only for the Type.QCG method. Note,
however, that symmetric preconditioning can be emulated by using either right or left
preconditioning and a pre or post processing step.
Setting the PC side often affects the default norm type. See setNormType for details.
SEE ALSO:
PC.Side, Working with PETSc options, getPCSide, setNormType, getNormType, KSPSetPCSide
Source code at petsc4py/PETSc/KSP.pyx:1315
setPostSolve(postsolve, args=None, kargs=None)
Set the function that is called at the end of each KSP.solve.
Logically collective.
Parameters
• postsolve (KSPPostSolveFunction | None) -- The callback function.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback function.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback function.
Return type
None
SEE ALSO:
solve, KSPSetPreSolve, KSPSetPostSolve
Source code at petsc4py/PETSc/KSP.pyx:1670
setPreSolve(presolve, args=None, kargs=None)
Set the function that is called at the beginning of each KSP.solve.
Logically collective.
Parameters
• presolve (KSPPreSolveFunction | None) -- The callback function.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback function.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback function.
Return type
None
SEE ALSO:
solve, KSPSetPreSolve, KSPSetPostSolve
Source code at petsc4py/PETSc/KSP.pyx:1637
setPythonContext(context=None)
Set the instance of the class implementing Python methods.
Not collective.
SEE ALSO:
PETSc Python linear solver type, getPythonContext
Source code at petsc4py/PETSc/KSP.pyx:2183
Parameters
context (Any | None)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
SEE ALSO:
PETSc Python linear solver type, setPythonContext, getPythonType, KSPPythonSetType
Source code at petsc4py/PETSc/KSP.pyx:2210
Parameters
py_type (str)
Return type
None
setResidualNorm(rnorm)
Use norm property.
Source code at petsc4py/PETSc/KSP.pyx:1860
Parameters
rnorm (float)
Return type
None
setTolerances(rtol=None, atol=None, divtol=None, max_it=None)
Set various tolerances used by the KSP convergence testers.
Logically collective.
Set the relative, absolute, divergence, and maximum iteration tolerances used by the
default KSP convergence testers.
Parameters
• rtol (float | None) -- The relative convergence tolerance, relative decrease in
the (possibly preconditioned) residual norm. Or DETERMINE to use the value when
the object's type was set.
• atol (float | None) -- The absolute convergence tolerance absolute size of the
(possibly preconditioned) residual norm. Or DETERMINE to use the value when the
object's type was set.
• dtol -- The divergence tolerance, amount (possibly preconditioned) residual norm
can increase before KSPConvergedDefault concludes that the method is diverging.
Or DETERMINE to use the value when the object's type was set.
• max_it (int | None) -- Maximum number of iterations to use. Or DETERMINE to use
the value when the object's type was set.
• divtol (float | None)
Return type
None
Notes
Use None to retain the default value of any of the tolerances.
SEE ALSO:
Working with PETSc options, getTolerances, setConvergenceTest, KSPSetTolerances, ‐
KSPConvergedDefault
Source code at petsc4py/PETSc/KSP.pyx:914
setType(ksp_type)
Build the KSP data structure for a particular Type.
Logically collective.
Parameters
ksp_type (Type | str) -- KSP Type object
Return type
None
Notes
See Type for available methods (for instance, Type.CG or Type.GMRES).
Normally, it is best to use the setFromOptions command and then set the KSP type from the
options database rather than by using this routine. Using the options database provides the
user with maximum flexibility in evaluating the many different Krylov methods. This method
is provided for those situations where it is necessary to set the iterative solver
independently of the command line or options database. This might be the case, for example,
when the choice of iterative solver changes during the execution of the program, and the
user's application is taking responsibility for choosing the appropriate method. In other
words, this routine is not for beginners.
SEE ALSO:
KSPSetType
Source code at petsc4py/PETSc/KSP.pyx:473
setUp()
Set up internal data structures for an iterative solver.
Collective.
SEE ALSO:
KSPSetUp
Source code at petsc4py/PETSc/KSP.pyx:1595
Return type
None
setUpOnBlocks()
Set up the preconditioner for each block in a block method.
Collective.
Methods include: block Jacobi, block Gauss-Seidel, and overlapping Schwarz methods.
SEE ALSO:
KSPSetUpOnBlocks
Source code at petsc4py/PETSc/KSP.pyx:1622
Return type
None
setUseFischerGuess(model, size)
Use the Paul Fischer algorithm to compute initial guesses.
Logically collective.
Use the Paul Fischer algorithm or its variants to compute initial guesses for a set of
solves with related right hand sides.
Parameters
• model (int) -- Use model 1, model 2, model 3, any other number to turn it off.
• size (int) -- Size of subspace used to generate initial guess.
Return type
None
SEE ALSO:
KSPSetUseFischerGuess
Source code at petsc4py/PETSc/KSP.pyx:1567
solve(b, x)
Solve the linear system.
Collective.
Parameters
• b (Vec) -- Right hand side vector.
• x (Vec) -- Solution vector.
Return type
None
Notes
If one uses setDM then x or b need not be passed. Use getSolution to access the solution in
this case.
The operator is specified with setOperators.
solve will normally return without generating an error regardless of whether the linear
system was solved or if constructing the preconditioner failed. Call getConvergedReason to
determine if the solver converged or failed and why. The option -ksp_error_if_not_converged
or function setErrorIfNotConverged will cause solve to error as soon as an error occurs in
the linear solver. In inner solves, DIVERGED_MAX_IT is not treated as an error because when
using nested solvers it may be fine that inner solvers in the preconditioner do not
converge during the solution process.
The number of iterations can be obtained from its.
If you provide a matrix that has a Mat.setNullSpace and Mat.setTransposeNullSpace this will
use that information to solve singular systems in the least squares sense with a norm
minimizing solution.
Ax = b where b = bₚ + bₜ where bₜ is not in the range of A (and hence by the fundamental
theorem of linear algebra is in the nullspace(Aᵀ), see Mat.setNullSpace.
KSP first removes bₜ producing the linear system Ax = bₚ (which has multiple solutions) and
solves this to find the ∥x∥ minimizing solution (and hence it finds the solution x
orthogonal to the nullspace(A). The algorithm is simply in each iteration of the Krylov
method we remove the nullspace(A) from the search direction thus the solution which is a
linear combination of the search directions has no component in the nullspace(A).
We recommend always using Type.GMRES for such singular systems. If nullspace(A) =
nullspace(Aᵀ) (note symmetric matrices always satisfy this property) then both left and
right preconditioning will work If nullspace(A) != nullspace(Aᵀ) then left preconditioning
will work but right preconditioning may not work (or it may).
If using a direct method (e.g., via the KSP solver Type.PREONLY and a preconditioner such
as PC.Type.LU or PC.Type.ILU, then its=1. See setTolerances for more details.
Understanding Convergence
The routines setMonitor and computeEigenvalues provide information on additional options to
monitor convergence and print eigenvalue information.
SEE ALSO:
create, setUp, destroy, setTolerances, is_converged, solveTranspose, its,
Mat.setNullSpace, Mat.setTransposeNullSpace, Type, setErrorIfNotConverged, KSPSolve
Source code at petsc4py/PETSc/KSP.pyx:1703
solveTranspose(b, x)
Solve the transpose of a linear system.
Collective.
Parameters
• b (Vec) -- Right hand side vector.
• x (Vec) -- Solution vector.
Return type
None
Notes
For complex numbers this solve the non-Hermitian transpose system.
SEE ALSO:
solve, KSPSolveTranspose
Source code at petsc4py/PETSc/KSP.pyx:1784
view(viewer=None)
Print the KSP data structure.
Collective.
Parameters
viewer (Viewer | None) -- Viewer used to display the KSP.
Return type
None
SEE ALSO:
KSPView
Source code at petsc4py/PETSc/KSP.pyx:425
Attributes Documentation
appctx The solver application context.
Source code at petsc4py/PETSc/KSP.pyx:2242
atol The absolute tolerance of the solver.
Source code at petsc4py/PETSc/KSP.pyx:2335
divtol The divergence tolerance of the solver.
Source code at petsc4py/PETSc/KSP.pyx:2343
dm The solver DM.
Source code at petsc4py/PETSc/KSP.pyx:2252
guess_knoll
Whether solver uses Knoll trick.
Source code at petsc4py/PETSc/KSP.pyx:2294
guess_nonzero
Whether guess is non-zero.
Source code at petsc4py/PETSc/KSP.pyx:2286
history
The convergence history of the solver.
Source code at petsc4py/PETSc/KSP.pyx:2377
is_converged
Boolean indicating if the solver has converged.
Source code at petsc4py/PETSc/KSP.pyx:2397
is_diverged
Boolean indicating if the solver has failed.
Source code at petsc4py/PETSc/KSP.pyx:2402
is_iterating
Boolean indicating if the solver has not converged yet.
Source code at petsc4py/PETSc/KSP.pyx:2392
its The current number of iterations the solver has taken.
Source code at petsc4py/PETSc/KSP.pyx:2361
mat_op The system matrix operator.
Source code at petsc4py/PETSc/KSP.pyx:2274
mat_pc The preconditioner operator.
Source code at petsc4py/PETSc/KSP.pyx:2279
max_it The maximum number of iteration the solver may take.
Source code at petsc4py/PETSc/KSP.pyx:2351
norm The norm of the residual at the current iteration.
Source code at petsc4py/PETSc/KSP.pyx:2369
norm_type
The norm used by the solver.
Source code at petsc4py/PETSc/KSP.pyx:2317
pc The PC of the solver.
Source code at petsc4py/PETSc/KSP.pyx:2304
pc_side
The side on which preconditioning is performed.
Source code at petsc4py/PETSc/KSP.pyx:2309
reason The converged reason.
Source code at petsc4py/PETSc/KSP.pyx:2384
rtol The relative tolerance of the solver.
Source code at petsc4py/PETSc/KSP.pyx:2327
vec_rhs
The right-hand side vector.
Source code at petsc4py/PETSc/KSP.pyx:2267
vec_sol
The solution vector.
Source code at petsc4py/PETSc/KSP.pyx:2262
petsc4py.PETSc.LGMap
class petsc4py.PETSc.LGMap
Bases: Object
Mapping from a local to a global ordering.
SEE ALSO:
ISLocalToGlobalMapping
Enumerations
┌───────────┬───────────────────────────────────────┐
│ GLMapMode │ Enum describing mapping behavior when │
│ │ global indices are missing. │
├───────────┼───────────────────────────────────────┤
│ Type │ Local to global map types. │
└───────────┴───────────────────────────────────────┘
petsc4py.PETSc.LGMap.GLMapMode
class petsc4py.PETSc.LGMap.GLMapMode
Bases: object
Enum describing mapping behavior when global indices are missing.
MASK Give missing global indices a local index of -1.
DROP Drop missing global indices.
SEE ALSO:
ISGlobalToLocalMappingMode
Attributes Summary
┌──────┬───────────────────────────┐
│ DROP │ Constant DROP of type int │
├──────┼───────────────────────────┤
│ MASK │ Constant MASK of type int │
└──────┴───────────────────────────┘
Attributes Documentation
DROP: int = DROP
Constant DROP of type int
MASK: int = MASK
Constant MASK of type int
petsc4py.PETSc.LGMap.Type
class petsc4py.PETSc.LGMap.Type
Bases: object
Local to global map types.
Attributes Summary
┌───────┬──────────────────────────┐
│ BASIC │ Object BASIC of type str │
├───────┼──────────────────────────┤
│ HASH │ Object HASH of type str │
└───────┴──────────────────────────┘
Attributes Documentation
BASIC: str = BASIC
Object BASIC of type str
HASH: str = HASH
Object HASH of type str
Methods Summary
┌────────────────────────────────────┬───────────────────────────────────────┐
│ apply(indices[, result]) │ Convert a locally numbered list of │
│ │ integers to a global numbering. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ applyBlock(indices[, result]) │ Convert a local block numbering to a │
│ │ global block numbering. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ applyBlockInverse(indices[, mode]) │ Compute blocked local numbering from │
│ │ blocked global numbering. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ applyIS(iset) │ Create an index set with global │
│ │ numbering from a local numbering. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ applyInverse(indices[, mode]) │ Compute local numbering from global │
│ │ numbering. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ create(indices[, bsize, comm]) │ Create a local-to-global mapping. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ createIS(iset) │ Create a local-to-global mapping from │
│ │ an index set. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ createSF(sf, start) │ Create a local-to-global mapping from │
│ │ a star forest. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the local-to-global mapping. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockIndices() │ Return the global indices for each │
│ │ local block. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockInfo() │ Determine the block indices shared │
│ │ with neighboring processes. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSize() │ Return the block size of the │
│ │ local-to-global mapping. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getIndices() │ Return the global indices for each │
│ │ local point in the mapping. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getInfo() │ Determine the indices shared with │
│ │ neighboring processes. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ getSize() │ Return the local size of the │
│ │ local-to-global mapping. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set mapping options from the options │
│ │ database. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ setType(lgmap_type) │ Set the type of the local-to-global │
│ │ map. │
├────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the local-to-global mapping. │
└────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────────┬───────────────────────────────────────┐
│ block_indices │ The global indices for each local │
│ │ block in the mapping. │
├───────────────┼───────────────────────────────────────┤
│ block_info │ Mapping describing block indices │
│ │ shared with neighboring processes. │
├───────────────┼───────────────────────────────────────┤
│ block_size │ The block size. │
├───────────────┼───────────────────────────────────────┤
│ indices │ The global indices for each local │
│ │ point in the mapping. │
├───────────────┼───────────────────────────────────────┤
│ info │ Mapping describing indices shared │
│ │ with neighboring processes. │
├───────────────┼───────────────────────────────────────┤
│ size │ The local size. │
└───────────────┴───────────────────────────────────────┘
Methods Documentation
apply(indices, result=None)
Convert a locally numbered list of integers to a global numbering.
Not collective.
Parameters
• indices (Sequence[int]) -- Input indices in local numbering.
• result (ArrayInt | None) -- Array to write the global numbering to. If None then a
new array will be allocated.
Returns
Indices in global numbering. If result is not None then this is returned here.
Return type
ArrayInt
SEE ALSO:
LGMap.applyBlock, ISLocalToGlobalMappingApply
Source code at petsc4py/PETSc/IS.pyx:1404
applyBlock(indices, result=None)
Convert a local block numbering to a global block numbering.
Not collective.
Parameters
• indices (Sequence[int]) -- Input block indices in local numbering.
• result (ArrayInt | None) -- Array to write the global numbering to. If None then a
new array will be allocated.
Returns
Block indices in global numbering. If result is not None then this is returned here.
Return type
ArrayInt
SEE ALSO:
LGMap.apply, ISLocalToGlobalMappingApplyBlock
Source code at petsc4py/PETSc/IS.pyx:1441
applyBlockInverse(indices, mode=None)
Compute blocked local numbering from blocked global numbering.
Not collective.
Parameters
• indices (Sequence[int]) -- Indices with a global block numbering.
• mode (GLMapMode | str | None) -- Flag indicating what to do with indices that have
no local value, defaults to "mask".
Returns
Indices with a local block numbering.
Return type
ArrayInt
SEE ALSO:
ISGlobalToLocalMappingApplyBlock
Source code at petsc4py/PETSc/IS.pyx:1542
applyIS(iset)
Create an index set with global numbering from a local numbering.
Collective.
Parameters
iset (IS) -- Index set with local numbering.
Returns
Index set with global numbering.
Return type
IS
SEE ALSO:
ISLocalToGlobalMappingApplyIS
Source code at petsc4py/PETSc/IS.pyx:1478
applyInverse(indices, mode=None)
Compute local numbering from global numbering.
Not collective.
Parameters
• indices (Sequence[int]) -- Indices with a global numbering.
• mode (GLMapMode | str | None) -- Flag indicating what to do with indices that have
no local value, defaults to "mask".
Returns
Indices with a local numbering.
Return type
ArrayInt
SEE ALSO:
ISGlobalToLocalMappingApply
Source code at petsc4py/PETSc/IS.pyx:1503
create(indices, bsize=None, comm=None)
Create a local-to-global mapping.
Not collective.
Parameters
• indices (Sequence[int]) -- Global index for each local element.
• bsize (int | None) -- Block size, defaults to 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
ISLocalToGlobalMappingCreate
Source code at petsc4py/PETSc/IS.pyx:1187
createIS(iset)
Create a local-to-global mapping from an index set.
Not collective.
Parameters
iset (IS) -- Index set containing the global numbers for each local number.
Return type
Self
SEE ALSO:
ISLocalToGlobalMappingCreateIS
Source code at petsc4py/PETSc/IS.pyx:1222
createSF(sf, start)
Create a local-to-global mapping from a star forest.
Collective.
Parameters
• sf (SF) -- Star forest mapping contiguous local indices to (rank, offset).
• start (int) -- First global index on this process.
Return type
Self
SEE ALSO:
ISLocalToGlobalMappingCreateSF
Source code at petsc4py/PETSc/IS.pyx:1243
destroy()
Destroy the local-to-global mapping.
Not collective.
SEE ALSO:
ISLocalToGlobalMappingDestroy
Source code at petsc4py/PETSc/IS.pyx:1174
Return type
Self
getBlockIndices()
Return the global indices for each local block.
Not collective.
SEE ALSO:
ISLocalToGlobalMappingGetBlockIndices
Source code at petsc4py/PETSc/IS.pyx:1318
Return type
ArrayInt
getBlockInfo()
Determine the block indices shared with neighboring processes.
Collective.
Returns
Mapping from neighboring processor number to an array of shared block indices (in
local numbering).
Return type
dict
SEE ALSO:
ISLocalToGlobalMappingGetBlockInfo
Source code at petsc4py/PETSc/IS.pyx:1373
getBlockSize()
Return the block size of the local-to-global mapping.
Not collective.
SEE ALSO:
ISLocalToGlobalMappingGetBlockSize
Source code at petsc4py/PETSc/IS.pyx:1280
Return type
int
getIndices()
Return the global indices for each local point in the mapping.
Not collective.
SEE ALSO:
ISLocalToGlobalMappingGetIndices
Source code at petsc4py/PETSc/IS.pyx:1294
Return type
ArrayInt
getInfo()
Determine the indices shared with neighboring processes.
Collective.
Returns
Mapping from neighboring processor number to an array of shared indices (in local
numbering).
Return type
dict
SEE ALSO:
ISLocalToGlobalMappingGetInfo
Source code at petsc4py/PETSc/IS.pyx:1344
getSize()
Return the local size of the local-to-global mapping.
Not collective.
SEE ALSO:
ISLocalToGlobalMappingGetSize
Source code at petsc4py/PETSc/IS.pyx:1266
Return type
int
setFromOptions()
Set mapping options from the options database.
Not collective.
SEE ALSO:
Working with PETSc options, ISLocalToGlobalMappingSetFromOptions
Source code at petsc4py/PETSc/IS.pyx:1143
Return type
None
setType(lgmap_type)
Set the type of the local-to-global map.
Logically collective.
Parameters
lgmap_type (Type | str) -- The type of the local-to-global mapping.
Return type
None
Notes
Use -islocaltoglobalmapping_type to set the type in the options database.
SEE ALSO:
Working with PETSc options, ISLocalToGlobalMappingSetType
Source code at petsc4py/PETSc/IS.pyx:1119
view(viewer=None)
View the local-to-global mapping.
Not collective.
Parameters
viewer (Viewer | None) -- Viewer instance, defaults to an instance of
Viewer.Type.ASCII.
Return type
None
SEE ALSO:
ISLocalToGlobalMappingView
Source code at petsc4py/PETSc/IS.pyx:1155
Attributes Documentation
block_indices
The global indices for each local block in the mapping.
Not collective.
SEE ALSO:
LGMap.getBlockIndices, ISLocalToGlobalMappingGetBlockIndices
Source code at petsc4py/PETSc/IS.pyx:1621
block_info
Mapping describing block indices shared with neighboring processes.
Collective.
SEE ALSO:
LGMap.getBlockInfo, ISLocalToGlobalMappingGetBlockInfo
Source code at petsc4py/PETSc/IS.pyx:1647
block_size
The block size.
Not collective.
SEE ALSO:
LGMap.getBlockSize
Source code at petsc4py/PETSc/IS.pyx:1595
indices
The global indices for each local point in the mapping.
Not collective.
SEE ALSO:
LGMap.getIndices, ISLocalToGlobalMappingGetIndices
Source code at petsc4py/PETSc/IS.pyx:1608
info Mapping describing indices shared with neighboring processes.
Collective.
SEE ALSO:
LGMap.getInfo, ISLocalToGlobalMappingGetInfo
Source code at petsc4py/PETSc/IS.pyx:1634
size The local size.
Not collective.
SEE ALSO:
LGMap.getSize
Source code at petsc4py/PETSc/IS.pyx:1582
petsc4py.PETSc.Log
class petsc4py.PETSc.Log
Bases: object
Logging support.
Methods Summary
┌───────────────────────────────┬───────────────────────────────────────┐
│ Class(name) │ Source code at │
│ │ petsc4py/PETSc/Log.pyx:25 │
├───────────────────────────────┼───────────────────────────────────────┤
│ Event(name[, klass]) │ Source code at │
│ │ petsc4py/PETSc/Log.pyx:39 │
├───────────────────────────────┼───────────────────────────────────────┤
│ EventDecorator([name, klass]) │ Decorate a function with a PETSc │
│ │ event. │
├───────────────────────────────┼───────────────────────────────────────┤
│ Stage(name) │ Source code at │
│ │ petsc4py/PETSc/Log.pyx:11 │
├───────────────────────────────┼───────────────────────────────────────┤
│ addFlops(flops) │ Add floating point operations to the │
│ │ current event. │
├───────────────────────────────┼───────────────────────────────────────┤
│ begin() │ Turn on logging of objects and │
│ │ events. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getCPUTime() │ Return the CPU time. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getFlops() │ Return the number of flops used on │
│ │ this processor since the program │
│ │ began. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getTime() │ Return the current time of day in │
│ │ seconds. │
├───────────────────────────────┼───────────────────────────────────────┤
│ isActive() │ Return whether logging is currently │
│ │ in progress. │
├───────────────────────────────┼───────────────────────────────────────┤
│ logFlops(flops) │ Add floating point operations to the │
│ │ current event. │
├───────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Print the log. │
└───────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
classmethod Class(name)
Source code at petsc4py/PETSc/Log.pyx:25
Return type
LogClass
classmethod Event(name, klass=None)
Source code at petsc4py/PETSc/Log.pyx:39
Return type
LogEvent
classmethod EventDecorator(name=None, klass=None)
Decorate a function with a PETSc event.
Source code at petsc4py/PETSc/Log.pyx:178
Return type
Any
classmethod Stage(name)
Source code at petsc4py/PETSc/Log.pyx:11
Return type
LogStage
classmethod addFlops(flops)
Add floating point operations to the current event.
Not collective.
Parameters
flops (float) -- The number of flops to log.
Return type
None
Notes
This method exists for backward compatibility.
SEE ALSO:
logFlops, PetscLogFlops
Source code at petsc4py/PETSc/Log.pyx:108
classmethod begin()
Turn on logging of objects and events.
Collective.
SEE ALSO:
PetscLogDefaultBegin
Source code at petsc4py/PETSc/Log.pyx:55
Return type
None
classmethod getCPUTime()
Return the CPU time.
Source code at petsc4py/PETSc/Log.pyx:171
Return type
float
classmethod getFlops()
Return the number of flops used on this processor since the program began.
Not collective.
Returns
Number of floating point operations.
Return type
float
SEE ALSO:
PetscGetFlops
Source code at petsc4py/PETSc/Log.pyx:131
classmethod getTime()
Return the current time of day in seconds.
Collective.
Returns
wctime -- Current time.
Return type
float
SEE ALSO:
PetscTime
Source code at petsc4py/PETSc/Log.pyx:151
classmethod isActive()
Return whether logging is currently in progress.
Not collective.
SEE ALSO:
PetscLogIsActive
Source code at petsc4py/PETSc/Log.pyx:193
Return type
bool
classmethod logFlops(flops)
Add floating point operations to the current event.
Not collective.
Parameters
flops (float) -- The number of flops to log.
Return type
None
SEE ALSO:
PetscLogFlops
Source code at petsc4py/PETSc/Log.pyx:89
classmethod view(viewer=None)
Print the log.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
Working with PETSc options, PetscLogView
Source code at petsc4py/PETSc/Log.pyx:68
petsc4py.PETSc.LogClass
class petsc4py.PETSc.LogClass
Bases: object
Logging support.
Methods Summary
┌─────────────────┬───────────────────────────────────────┐
│ activate() │ Activate the log class. │
├─────────────────┼───────────────────────────────────────┤
│ deactivate() │ Deactivate the log class. │
├─────────────────┼───────────────────────────────────────┤
│ getActive() │ Not implemented. │
├─────────────────┼───────────────────────────────────────┤
│ getName() │ Return the log class name. │
├─────────────────┼───────────────────────────────────────┤
│ setActive(flag) │ Activate or deactivate the log class. │
└─────────────────┴───────────────────────────────────────┘
Attributes Summary
┌────────┬───────────────────────────┐
│ active │ Log class activation. │
├────────┼───────────────────────────┤
│ id │ The log class identifier. │
├────────┼───────────────────────────┤
│ name │ The log class name. │
└────────┴───────────────────────────┘
Methods Documentation
activate()
Activate the log class.
Source code at petsc4py/PETSc/Log.pyx:431
Return type
None
deactivate()
Deactivate the log class.
Source code at petsc4py/PETSc/Log.pyx:435
Return type
None
getActive()
Not implemented.
Source code at petsc4py/PETSc/Log.pyx:439
Return type
bool
getName()
Return the log class name.
Source code at petsc4py/PETSc/Log.pyx:414
Return type
str
setActive(flag)
Activate or deactivate the log class.
Source code at petsc4py/PETSc/Log.pyx:444
Parameters
flag (bool)
Return type
None
Attributes Documentation
active Log class activation.
Source code at petsc4py/PETSc/Log.pyx:451
id The log class identifier.
Source code at petsc4py/PETSc/Log.pyx:401
name The log class name.
Source code at petsc4py/PETSc/Log.pyx:420
petsc4py.PETSc.LogEvent
class petsc4py.PETSc.LogEvent
Bases: object
Logging support.
Methods Summary
┌──────────────────────┬───────────────────────────────────────┐
│ activate() │ Indicate that the event should be │
│ │ logged. │
├──────────────────────┼───────────────────────────────────────┤
│ begin(*objs) │ Log the beginning of a user event. │
├──────────────────────┼───────────────────────────────────────┤
│ deactivate() │ Indicate that the event should not be │
│ │ logged. │
├──────────────────────┼───────────────────────────────────────┤
│ end(*objs) │ Log the end of a user event. │
├──────────────────────┼───────────────────────────────────────┤
│ getActive() │ Not implemented. │
├──────────────────────┼───────────────────────────────────────┤
│ getActiveAll() │ Not implemented. │
├──────────────────────┼───────────────────────────────────────┤
│ getName() │ The current event name. │
├──────────────────────┼───────────────────────────────────────┤
│ getPerfInfo([stage]) │ Get the performance information about │
│ │ the given event in the given event. │
├──────────────────────┼───────────────────────────────────────┤
│ setActive(flag) │ Indicate whether or not the event │
│ │ should be logged. │
├──────────────────────┼───────────────────────────────────────┤
│ setActiveAll(flag) │ Turn on logging of all events. │
└──────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌────────────┬───────────────────────────┐
│ active │ Event activation. │
├────────────┼───────────────────────────┤
│ active_all │ All events activation. │
├────────────┼───────────────────────────┤
│ id │ The log event identifier. │
├────────────┼───────────────────────────┤
│ name │ The current event name. │
└────────────┴───────────────────────────┘
Methods Documentation
activate()
Indicate that the event should be logged.
Logically collective.
SEE ALSO:
PetscLogEventActivate
Source code at petsc4py/PETSc/Log.pyx:552
Return type
None
begin(*objs)
Log the beginning of a user event.
Collective.
Parameters
*objs -- objects associated with the event
Return type
None
SEE ALSO:
PetscLogEventBegin
Source code at petsc4py/PETSc/Log.pyx:496
deactivate()
Indicate that the event should not be logged.
Logically collective.
SEE ALSO:
PetscLogEventDeactivate
Source code at petsc4py/PETSc/Log.pyx:564
Return type
None
end(*objs)
Log the end of a user event.
Collective.
Parameters
*objs -- Objects associated with the event.
Return type
None
SEE ALSO:
PetscLogEventEnd
Source code at petsc4py/PETSc/Log.pyx:515
getActive()
Not implemented.
Source code at petsc4py/PETSc/Log.pyx:576
Return type
bool
getActiveAll()
Not implemented.
Source code at petsc4py/PETSc/Log.pyx:609
Return type
bool
getName()
The current event name.
Source code at petsc4py/PETSc/Log.pyx:535
Return type
str
getPerfInfo(stage=None)
Get the performance information about the given event in the given event.
Not collective.
Parameters
stage (int | None) -- The stage number.
Returns
info -- This structure is filled with the performance information.
Return type
dict
SEE ALSO:
PetscLogEventGetPerfInfo
Source code at petsc4py/PETSc/Log.pyx:643
setActive(flag)
Indicate whether or not the event should be logged.
Logically collective.
Parameters
flag (bool) -- Activate or deactivate the event.
Return type
None
SEE ALSO:
PetscLogEventDeactivate, PetscLogEventActivate
Source code at petsc4py/PETSc/Log.pyx:581
setActiveAll(flag)
Turn on logging of all events.
Logically collective.
Parameters
flag (bool) -- Activate (if True) or deactivate (if False) the logging of all
events.
Return type
None
SEE ALSO:
PetscLogEventSetActiveAll
Source code at petsc4py/PETSc/Log.pyx:614
Attributes Documentation
active Event activation.
Source code at petsc4py/PETSc/Log.pyx:601
active_all
All events activation.
Source code at petsc4py/PETSc/Log.pyx:633
id The log event identifier.
Source code at petsc4py/PETSc/Log.pyx:478
name The current event name.
Source code at petsc4py/PETSc/Log.pyx:541
petsc4py.PETSc.LogStage
class petsc4py.PETSc.LogStage
Bases: object
Logging support for different stages.
Methods Summary
┌──────────────────┬───────────────────────────────────────┐
│ activate() │ Activate the stage. │
├──────────────────┼───────────────────────────────────────┤
│ deactivate() │ Deactivate the stage. │
├──────────────────┼───────────────────────────────────────┤
│ getActive() │ Check if the stage is activated. │
├──────────────────┼───────────────────────────────────────┤
│ getName() │ Return the current stage name. │
├──────────────────┼───────────────────────────────────────┤
│ getVisible() │ Return whether the stage is visible. │
├──────────────────┼───────────────────────────────────────┤
│ pop() │ Pop a stage from the logging stack. │
├──────────────────┼───────────────────────────────────────┤
│ push() │ Push a stage on the logging stack. │
├──────────────────┼───────────────────────────────────────┤
│ setActive(flag) │ Activate or deactivate the current │
│ │ stage. │
├──────────────────┼───────────────────────────────────────┤
│ setVisible(flag) │ Set the visibility of the stage. │
└──────────────────┴───────────────────────────────────────┘
Attributes Summary
┌─────────┬────────────────────────────────┐
│ active │ Whether the stage is activate. │
├─────────┼────────────────────────────────┤
│ id │ The log stage identifier. │
├─────────┼────────────────────────────────┤
│ name │ The current stage name. │
├─────────┼────────────────────────────────┤
│ visible │ Whether the stage is visible. │
└─────────┴────────────────────────────────┘
Methods Documentation
activate()
Activate the stage.
Logically collective.
SEE ALSO:
PetscLogStageSetActive
Source code at petsc4py/PETSc/Log.pyx:279
Return type
None
deactivate()
Deactivate the stage.
Logically collective.
SEE ALSO:
PetscLogStageSetActive
Source code at petsc4py/PETSc/Log.pyx:291
Return type
None
getActive()
Check if the stage is activated.
Not collective.
SEE ALSO:
PetscLogStageGetActive
Source code at petsc4py/PETSc/Log.pyx:303
Return type
bool
getName()
Return the current stage name.
Source code at petsc4py/PETSc/Log.pyx:262
Return type
str
getVisible()
Return whether the stage is visible.
Not collective.
SEE ALSO:
LogStage.setVisible, PetscLogStageSetVisible
Source code at petsc4py/PETSc/Log.pyx:341
Return type
bool
pop() Pop a stage from the logging stack.
Logically collective.
SEE ALSO:
LogStage.push, PetscLogStagePop
Source code at petsc4py/PETSc/Log.pyx:247
Return type
None
push() Push a stage on the logging stack.
Logically collective.
SEE ALSO:
LogStage.pop, PetscLogStagePush
Source code at petsc4py/PETSc/Log.pyx:235
Return type
None
setActive(flag)
Activate or deactivate the current stage.
Logically collective.
SEE ALSO:
PetscLogStageSetActive
Source code at petsc4py/PETSc/Log.pyx:317
Parameters
flag (bool)
Return type
None
setVisible(flag)
Set the visibility of the stage.
Logically collective.
Parameters
flag (bool) -- True to make the stage visible, False otherwise.
Return type
None
SEE ALSO:
LogStage.getVisible, PetscLogStageSetVisible
Source code at petsc4py/PETSc/Log.pyx:355
Attributes Documentation
active Whether the stage is activate.
Source code at petsc4py/PETSc/Log.pyx:331
id The log stage identifier.
Source code at petsc4py/PETSc/Log.pyx:215
name The current stage name.
Source code at petsc4py/PETSc/Log.pyx:268
visible
Whether the stage is visible.
Source code at petsc4py/PETSc/Log.pyx:374
petsc4py.PETSc.Mat
class petsc4py.PETSc.Mat
Bases: Object
Matrix object.
Mat is described in the PETSc manual.
SEE ALSO:
Mat
Enumerations
┌─────────────────┬───────────────────────────────────────┐
│ AssemblyType │ Matrix assembly type. │
├─────────────────┼───────────────────────────────────────┤
│ DuplicateOption │ Matrix duplicate option. │
├─────────────────┼───────────────────────────────────────┤
│ FactorShiftType │ Factored matrix shift type. │
├─────────────────┼───────────────────────────────────────┤
│ InfoType │ Matrix info type. │
├─────────────────┼───────────────────────────────────────┤
│ Option │ Matrix option. │
├─────────────────┼───────────────────────────────────────┤
│ OrderingType │ Factored matrix ordering type. │
├─────────────────┼───────────────────────────────────────┤
│ SORType │ Matrix SOR type. │
├─────────────────┼───────────────────────────────────────┤
│ SolverType │ Factored matrix solver type. │
├─────────────────┼───────────────────────────────────────┤
│ Stencil │ Associate structured grid coordinates │
│ │ with matrix indices. │
├─────────────────┼───────────────────────────────────────┤
│ Structure │ Matrix modification structure. │
├─────────────────┼───────────────────────────────────────┤
│ Type │ Matrix type. │
└─────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.Mat.AssemblyType
class petsc4py.PETSc.Mat.AssemblyType
Bases: object
Matrix assembly type.
SEE ALSO:
MatAssemblyType
Attributes Summary
┌────────────────┬─────────────────────────────────────┐
│ FINAL │ Constant FINAL of type int │
├────────────────┼─────────────────────────────────────┤
│ FINAL_ASSEMBLY │ Constant FINAL_ASSEMBLY of type int │
├────────────────┼─────────────────────────────────────┤
│ FLUSH │ Constant FLUSH of type int │
├────────────────┼─────────────────────────────────────┤
│ FLUSH_ASSEMBLY │ Constant FLUSH_ASSEMBLY of type int │
└────────────────┴─────────────────────────────────────┘
Attributes Documentation
FINAL: int = FINAL
Constant FINAL of type int
FINAL_ASSEMBLY: int = FINAL_ASSEMBLY
Constant FINAL_ASSEMBLY of type int
FLUSH: int = FLUSH
Constant FLUSH of type int
FLUSH_ASSEMBLY: int = FLUSH_ASSEMBLY
Constant FLUSH_ASSEMBLY of type int
petsc4py.PETSc.Mat.DuplicateOption
class petsc4py.PETSc.Mat.DuplicateOption
Bases: object
Matrix duplicate option.
SEE ALSO:
MatDuplicateOption
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ COPY_VALUES │ Constant COPY_VALUES of type int │
├───────────────────────┼───────────────────────────────────────┤
│ DO_NOT_COPY_VALUES │ Constant DO_NOT_COPY_VALUES of type ‐ │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ SHARE_NONZERO_PATTERN │ Constant SHARE_NONZERO_PATTERN of │
│ │ type int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
COPY_VALUES: int = COPY_VALUES
Constant COPY_VALUES of type int
DO_NOT_COPY_VALUES: int = DO_NOT_COPY_VALUES
Constant DO_NOT_COPY_VALUES of type int
SHARE_NONZERO_PATTERN: int = SHARE_NONZERO_PATTERN
Constant SHARE_NONZERO_PATTERN of type int
petsc4py.PETSc.Mat.FactorShiftType
class petsc4py.PETSc.Mat.FactorShiftType
Bases: object
Factored matrix shift type.
SEE ALSO:
MatFactorShiftType
Attributes Summary
┌───────────────────┬───────────────────────────────────────┐
│ INBLOCKS │ Constant INBLOCKS of type int │
├───────────────────┼───────────────────────────────────────┤
│ NONE │ Constant NONE of type int │
├───────────────────┼───────────────────────────────────────┤
│ NONZERO │ Constant NONZERO of type int │
├───────────────────┼───────────────────────────────────────┤
│ NZ │ Constant NZ of type int │
├───────────────────┼───────────────────────────────────────┤
│ PD │ Constant PD of type int │
├───────────────────┼───────────────────────────────────────┤
│ POSITIVE_DEFINITE │ Constant POSITIVE_DEFINITE of type ‐ │
│ │ int │
└───────────────────┴───────────────────────────────────────┘
Attributes Documentation
INBLOCKS: int = INBLOCKS
Constant INBLOCKS of type int
NONE: int = NONE
Constant NONE of type int
NONZERO: int = NONZERO
Constant NONZERO of type int
NZ: int = NZ
Constant NZ of type int
PD: int = PD
Constant PD of type int
POSITIVE_DEFINITE: int = POSITIVE_DEFINITE
Constant POSITIVE_DEFINITE of type int
petsc4py.PETSc.Mat.InfoType
class petsc4py.PETSc.Mat.InfoType
Bases: object
Matrix info type.
Attributes Summary
┌────────────┬─────────────────────────────────┐
│ GLOBAL_MAX │ Constant GLOBAL_MAX of type int │
├────────────┼─────────────────────────────────┤
│ GLOBAL_SUM │ Constant GLOBAL_SUM of type int │
├────────────┼─────────────────────────────────┤
│ LOCAL │ Constant LOCAL of type int │
└────────────┴─────────────────────────────────┘
Attributes Documentation
GLOBAL_MAX: int = GLOBAL_MAX
Constant GLOBAL_MAX of type int
GLOBAL_SUM: int = GLOBAL_SUM
Constant GLOBAL_SUM of type int
LOCAL: int = LOCAL
Constant LOCAL of type int
petsc4py.PETSc.Mat.Option
class petsc4py.PETSc.Mat.Option
Bases: object
Matrix option.
SEE ALSO:
MatOption
Attributes Summary
┌─────────────────────────────┬───────────────────────────────────────┐
│ ERROR_LOWER_TRIANGULAR │ Constant ERROR_LOWER_TRIANGULAR of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ FORCE_DIAGONAL_ENTRIES │ Constant FORCE_DIAGONAL_ENTRIES of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ GETROW_UPPERTRIANGULAR │ Constant GETROW_UPPERTRIANGULAR of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ HERMITIAN │ Constant HERMITIAN of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ IGNORE_LOWER_TRIANGULAR │ Constant IGNORE_LOWER_TRIANGULAR of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ IGNORE_OFF_PROC_ENTRIES │ Constant IGNORE_OFF_PROC_ENTRIES of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ IGNORE_ZERO_ENTRIES │ Constant IGNORE_ZERO_ENTRIES of type │
│ │ int │
├─────────────────────────────┼───────────────────────────────────────┤
│ KEEP_NONZERO_PATTERN │ Constant KEEP_NONZERO_PATTERN of type │
│ │ int │
├─────────────────────────────┼───────────────────────────────────────┤
│ NEW_NONZERO_ALLOCATION_ERR │ Constant NEW_NONZERO_ALLOCATION_ERR │
│ │ of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ NEW_NONZERO_LOCATIONS │ Constant NEW_NONZERO_LOCATIONS of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ NEW_NONZERO_LOCATION_ERR │ Constant NEW_NONZERO_LOCATION_ERR of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ NO_OFF_PROC_ENTRIES │ Constant NO_OFF_PROC_ENTRIES of type │
│ │ int │
├─────────────────────────────┼───────────────────────────────────────┤
│ NO_OFF_PROC_ZERO_ROWS │ Constant NO_OFF_PROC_ZERO_ROWS of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ OPTION_MAX │ Constant OPTION_MAX of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ OPTION_MIN │ Constant OPTION_MIN of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ ROW_ORIENTED │ Constant ROW_ORIENTED of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SORTED_FULL │ Constant SORTED_FULL of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SPD │ Constant SPD of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ STRUCTURALLY_SYMMETRIC │ Constant STRUCTURALLY_SYMMETRIC of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ STRUCTURE_ONLY │ Constant STRUCTURE_ONLY of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SUBMAT_SINGLEIS │ Constant SUBMAT_SINGLEIS of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SUBSET_OFF_PROC_ENTRIES │ Constant SUBSET_OFF_PROC_ENTRIES of │
│ │ type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SYMMETRIC │ Constant SYMMETRIC of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ SYMMETRY_ETERNAL │ Constant SYMMETRY_ETERNAL of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ UNUSED_NONZERO_LOCATION_ERR │ Constant UNUSED_NONZERO_LOCATION_ERR │
│ │ of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ USE_HASH_TABLE │ Constant USE_HASH_TABLE of type int │
├─────────────────────────────┼───────────────────────────────────────┤
│ USE_INODES │ Constant USE_INODES of type int │
└─────────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
ERROR_LOWER_TRIANGULAR: int = ERROR_LOWER_TRIANGULAR
Constant ERROR_LOWER_TRIANGULAR of type int
FORCE_DIAGONAL_ENTRIES: int = FORCE_DIAGONAL_ENTRIES
Constant FORCE_DIAGONAL_ENTRIES of type int
GETROW_UPPERTRIANGULAR: int = GETROW_UPPERTRIANGULAR
Constant GETROW_UPPERTRIANGULAR of type int
HERMITIAN: int = HERMITIAN
Constant HERMITIAN of type int
IGNORE_LOWER_TRIANGULAR: int = IGNORE_LOWER_TRIANGULAR
Constant IGNORE_LOWER_TRIANGULAR of type int
IGNORE_OFF_PROC_ENTRIES: int = IGNORE_OFF_PROC_ENTRIES
Constant IGNORE_OFF_PROC_ENTRIES of type int
IGNORE_ZERO_ENTRIES: int = IGNORE_ZERO_ENTRIES
Constant IGNORE_ZERO_ENTRIES of type int
KEEP_NONZERO_PATTERN: int = KEEP_NONZERO_PATTERN
Constant KEEP_NONZERO_PATTERN of type int
NEW_NONZERO_ALLOCATION_ERR: int = NEW_NONZERO_ALLOCATION_ERR
Constant NEW_NONZERO_ALLOCATION_ERR of type int
NEW_NONZERO_LOCATIONS: int = NEW_NONZERO_LOCATIONS
Constant NEW_NONZERO_LOCATIONS of type int
NEW_NONZERO_LOCATION_ERR: int = NEW_NONZERO_LOCATION_ERR
Constant NEW_NONZERO_LOCATION_ERR of type int
NO_OFF_PROC_ENTRIES: int = NO_OFF_PROC_ENTRIES
Constant NO_OFF_PROC_ENTRIES of type int
NO_OFF_PROC_ZERO_ROWS: int = NO_OFF_PROC_ZERO_ROWS
Constant NO_OFF_PROC_ZERO_ROWS of type int
OPTION_MAX: int = OPTION_MAX
Constant OPTION_MAX of type int
OPTION_MIN: int = OPTION_MIN
Constant OPTION_MIN of type int
ROW_ORIENTED: int = ROW_ORIENTED
Constant ROW_ORIENTED of type int
SORTED_FULL: int = SORTED_FULL
Constant SORTED_FULL of type int
SPD: int = SPD
Constant SPD of type int
STRUCTURALLY_SYMMETRIC: int = STRUCTURALLY_SYMMETRIC
Constant STRUCTURALLY_SYMMETRIC of type int
STRUCTURE_ONLY: int = STRUCTURE_ONLY
Constant STRUCTURE_ONLY of type int
SUBMAT_SINGLEIS: int = SUBMAT_SINGLEIS
Constant SUBMAT_SINGLEIS of type int
SUBSET_OFF_PROC_ENTRIES: int = SUBSET_OFF_PROC_ENTRIES
Constant SUBSET_OFF_PROC_ENTRIES of type int
SYMMETRIC: int = SYMMETRIC
Constant SYMMETRIC of type int
SYMMETRY_ETERNAL: int = SYMMETRY_ETERNAL
Constant SYMMETRY_ETERNAL of type int
UNUSED_NONZERO_LOCATION_ERR: int = UNUSED_NONZERO_LOCATION_ERR
Constant UNUSED_NONZERO_LOCATION_ERR of type int
USE_HASH_TABLE: int = USE_HASH_TABLE
Constant USE_HASH_TABLE of type int
USE_INODES: int = USE_INODES
Constant USE_INODES of type int
petsc4py.PETSc.Mat.OrderingType
class petsc4py.PETSc.Mat.OrderingType
Bases: object
Factored matrix ordering type.
SEE ALSO:
MatOrderingType
Attributes Summary
┌───────────┬──────────────────────────────┐
│ AMD │ Object AMD of type str │
├───────────┼──────────────────────────────┤
│ METISND │ Object METISND of type str │
├───────────┼──────────────────────────────┤
│ NATURAL │ Object NATURAL of type str │
├───────────┼──────────────────────────────┤
│ ND │ Object ND of type str │
├───────────┼──────────────────────────────┤
│ OWD │ Object OWD of type str │
├───────────┼──────────────────────────────┤
│ QMD │ Object QMD of type str │
├───────────┼──────────────────────────────┤
│ RCM │ Object RCM of type str │
├───────────┼──────────────────────────────┤
│ ROWLENGTH │ Object ROWLENGTH of type str │
├───────────┼──────────────────────────────┤
│ SPECTRAL │ Object SPECTRAL of type str │
├───────────┼──────────────────────────────┤
│ WBM │ Object WBM of type str │
└───────────┴──────────────────────────────┘
Attributes Documentation
AMD: str = AMD
Object AMD of type str
METISND: str = METISND
Object METISND of type str
NATURAL: str = NATURAL
Object NATURAL of type str
ND: str = ND
Object ND of type str
OWD: str = OWD
Object OWD of type str
QMD: str = QMD
Object QMD of type str
RCM: str = RCM
Object RCM of type str
ROWLENGTH: str = ROWLENGTH
Object ROWLENGTH of type str
SPECTRAL: str = SPECTRAL
Object SPECTRAL of type str
WBM: str = WBM
Object WBM of type str
petsc4py.PETSc.Mat.SORType
class petsc4py.PETSc.Mat.SORType
Bases: object
Matrix SOR type.
SEE ALSO:
MatSORType
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ APPLY_LOWER │ Constant APPLY_LOWER of type int │
├───────────────────────┼───────────────────────────────────────┤
│ APPLY_UPPER │ Constant APPLY_UPPER of type int │
├───────────────────────┼───────────────────────────────────────┤
│ BACKWARD_SWEEP │ Constant BACKWARD_SWEEP of type int │
├───────────────────────┼───────────────────────────────────────┤
│ EISENSTAT │ Constant EISENSTAT of type int │
├───────────────────────┼───────────────────────────────────────┤
│ FORWARD_SWEEP │ Constant FORWARD_SWEEP of type int │
├───────────────────────┼───────────────────────────────────────┤
│ LOCAL_BACKWARD_SWEEP │ Constant LOCAL_BACKWARD_SWEEP of type │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ LOCAL_FORWARD_SWEEP │ Constant LOCAL_FORWARD_SWEEP of type │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ LOCAL_SYMMETRIC_SWEEP │ Constant LOCAL_SYMMETRIC_SWEEP of │
│ │ type int │
├───────────────────────┼───────────────────────────────────────┤
│ SYMMETRY_SWEEP │ Constant SYMMETRY_SWEEP of type int │
├───────────────────────┼───────────────────────────────────────┤
│ ZERO_INITIAL_GUESS │ Constant ZERO_INITIAL_GUESS of type ‐ │
│ │ int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
APPLY_LOWER: int = APPLY_LOWER
Constant APPLY_LOWER of type int
APPLY_UPPER: int = APPLY_UPPER
Constant APPLY_UPPER of type int
BACKWARD_SWEEP: int = BACKWARD_SWEEP
Constant BACKWARD_SWEEP of type int
EISENSTAT: int = EISENSTAT
Constant EISENSTAT of type int
FORWARD_SWEEP: int = FORWARD_SWEEP
Constant FORWARD_SWEEP of type int
LOCAL_BACKWARD_SWEEP: int = LOCAL_BACKWARD_SWEEP
Constant LOCAL_BACKWARD_SWEEP of type int
LOCAL_FORWARD_SWEEP: int = LOCAL_FORWARD_SWEEP
Constant LOCAL_FORWARD_SWEEP of type int
LOCAL_SYMMETRIC_SWEEP: int = LOCAL_SYMMETRIC_SWEEP
Constant LOCAL_SYMMETRIC_SWEEP of type int
SYMMETRY_SWEEP: int = SYMMETRY_SWEEP
Constant SYMMETRY_SWEEP of type int
ZERO_INITIAL_GUESS: int = ZERO_INITIAL_GUESS
Constant ZERO_INITIAL_GUESS of type int
petsc4py.PETSc.Mat.SolverType
class petsc4py.PETSc.Mat.SolverType
Bases: object
Factored matrix solver type.
SEE ALSO:
MatSolverType
Attributes Summary
┌──────────────┬─────────────────────────────────┐
│ BAS │ Object BAS of type str │
├──────────────┼─────────────────────────────────┤
│ CHOLMOD │ Object CHOLMOD of type str │
├──────────────┼─────────────────────────────────┤
│ CUDA │ Object CUDA of type str │
├──────────────┼─────────────────────────────────┤
│ CUSPARSE │ Object CUSPARSE of type str │
├──────────────┼─────────────────────────────────┤
│ ELEMENTAL │ Object ELEMENTAL of type str │
├──────────────┼─────────────────────────────────┤
│ ESSL │ Object ESSL of type str │
├──────────────┼─────────────────────────────────┤
│ KLU │ Object KLU of type str │
├──────────────┼─────────────────────────────────┤
│ LUSOL │ Object LUSOL of type str │
├──────────────┼─────────────────────────────────┤
│ MATLAB │ Object MATLAB of type str │
├──────────────┼─────────────────────────────────┤
│ MKL_CPARDISO │ Object MKL_CPARDISO of type str │
├──────────────┼─────────────────────────────────┤
│ MKL_PARDISO │ Object MKL_PARDISO of type str │
├──────────────┼─────────────────────────────────┤
│ MUMPS │ Object MUMPS of type str │
├──────────────┼─────────────────────────────────┤
│ PASTIX │ Object PASTIX of type str │
├──────────────┼─────────────────────────────────┤
│ PETSC │ Object PETSC of type str │
├──────────────┼─────────────────────────────────┤
│ SCALAPACK │ Object SCALAPACK of type str │
├──────────────┼─────────────────────────────────┤
│ SPQR │ Object SPQR of type str │
├──────────────┼─────────────────────────────────┤
│ STRUMPACK │ Object STRUMPACK of type str │
├──────────────┼─────────────────────────────────┤
│ SUPERLU │ Object SUPERLU of type str │
├──────────────┼─────────────────────────────────┤
│ SUPERLU_DIST │ Object SUPERLU_DIST of type str │
├──────────────┼─────────────────────────────────┤
│ UMFPACK │ Object UMFPACK of type str │
└──────────────┴─────────────────────────────────┘
Attributes Documentation
BAS: str = BAS
Object BAS of type str
CHOLMOD: str = CHOLMOD
Object CHOLMOD of type str
CUDA: str = CUDA
Object CUDA of type str
CUSPARSE: str = CUSPARSE
Object CUSPARSE of type str
ELEMENTAL: str = ELEMENTAL
Object ELEMENTAL of type str
ESSL: str = ESSL
Object ESSL of type str
KLU: str = KLU
Object KLU of type str
LUSOL: str = LUSOL
Object LUSOL of type str
MATLAB: str = MATLAB
Object MATLAB of type str
MKL_CPARDISO: str = MKL_CPARDISO
Object MKL_CPARDISO of type str
MKL_PARDISO: str = MKL_PARDISO
Object MKL_PARDISO of type str
MUMPS: str = MUMPS
Object MUMPS of type str
PASTIX: str = PASTIX
Object PASTIX of type str
PETSC: str = PETSC
Object PETSC of type str
SCALAPACK: str = SCALAPACK
Object SCALAPACK of type str
SPQR: str = SPQR
Object SPQR of type str
STRUMPACK: str = STRUMPACK
Object STRUMPACK of type str
SUPERLU: str = SUPERLU
Object SUPERLU of type str
SUPERLU_DIST: str = SUPERLU_DIST
Object SUPERLU_DIST of type str
UMFPACK: str = UMFPACK
Object UMFPACK of type str
petsc4py.PETSc.Mat.Stencil
class petsc4py.PETSc.Mat.Stencil
Bases: object
Associate structured grid coordinates with matrix indices.
SEE ALSO:
MatStencil
Attributes Summary
┌───────┬─────────────────────────────────────┐
│ c │ Field component. │
├───────┼─────────────────────────────────────┤
│ field │ Field component. │
├───────┼─────────────────────────────────────┤
│ i │ First logical grid coordinate. │
├───────┼─────────────────────────────────────┤
│ index │ Logical grid coordinates (i, j, k). │
├───────┼─────────────────────────────────────┤
│ j │ Second logical grid coordinate. │
├───────┼─────────────────────────────────────┤
│ k │ Third logical grid coordinate. │
└───────┴─────────────────────────────────────┘
Attributes Documentation
c Field component.
Source code at petsc4py/PETSc/Mat.pyx:317
field Field component.
Source code at petsc4py/PETSc/Mat.pyx:336
i First logical grid coordinate.
Source code at petsc4py/PETSc/Mat.pyx:293
index Logical grid coordinates (i, j, k).
Source code at petsc4py/PETSc/Mat.pyx:325
j Second logical grid coordinate.
Source code at petsc4py/PETSc/Mat.pyx:301
k Third logical grid coordinate.
Source code at petsc4py/PETSc/Mat.pyx:309
petsc4py.PETSc.Mat.Structure
class petsc4py.PETSc.Mat.Structure
Bases: object
Matrix modification structure.
SEE ALSO:
MatStructure
Attributes Summary
┌───────────────────────────┬───────────────────────────────────────┐
│ DIFFERENT │ Constant DIFFERENT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIFFERENT_NONZERO_PATTERN │ Constant DIFFERENT_NONZERO_PATTERN of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DIFFERENT_NZ │ Constant DIFFERENT_NZ of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ SAME │ Constant SAME of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ SAME_NONZERO_PATTERN │ Constant SAME_NONZERO_PATTERN of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ SAME_NZ │ Constant SAME_NZ of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ SUBSET │ Constant SUBSET of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ SUBSET_NONZERO_PATTERN │ Constant SUBSET_NONZERO_PATTERN of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ SUBSET_NZ │ Constant SUBSET_NZ of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ UNKNOWN │ Constant UNKNOWN of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ UNKNOWN_NONZERO_PATTERN │ Constant UNKNOWN_NONZERO_PATTERN of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ UNKNOWN_NZ │ Constant UNKNOWN_NZ of type int │
└───────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
DIFFERENT: int = DIFFERENT
Constant DIFFERENT of type int
DIFFERENT_NONZERO_PATTERN: int = DIFFERENT_NONZERO_PATTERN
Constant DIFFERENT_NONZERO_PATTERN of type int
DIFFERENT_NZ: int = DIFFERENT_NZ
Constant DIFFERENT_NZ of type int
SAME: int = SAME
Constant SAME of type int
SAME_NONZERO_PATTERN: int = SAME_NONZERO_PATTERN
Constant SAME_NONZERO_PATTERN of type int
SAME_NZ: int = SAME_NZ
Constant SAME_NZ of type int
SUBSET: int = SUBSET
Constant SUBSET of type int
SUBSET_NONZERO_PATTERN: int = SUBSET_NONZERO_PATTERN
Constant SUBSET_NONZERO_PATTERN of type int
SUBSET_NZ: int = SUBSET_NZ
Constant SUBSET_NZ of type int
UNKNOWN: int = UNKNOWN
Constant UNKNOWN of type int
UNKNOWN_NONZERO_PATTERN: int = UNKNOWN_NONZERO_PATTERN
Constant UNKNOWN_NONZERO_PATTERN of type int
UNKNOWN_NZ: int = UNKNOWN_NZ
Constant UNKNOWN_NZ of type int
petsc4py.PETSc.Mat.Type
class petsc4py.PETSc.Mat.Type
Bases: object
Matrix type.
SEE ALSO:
MatType
Attributes Summary
┌────────────────────┬───────────────────────────────────────┐
│ AIJ │ Object AIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJCRL │ Object AIJCRL of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJCUSPARSE │ Object AIJCUSPARSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJMKL │ Object AIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJPERM │ Object AIJPERM of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJSELL │ Object AIJSELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ AIJVIENNACL │ Object AIJVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ BAIJ │ Object BAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ BAIJMKL │ Object BAIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ BLOCKMAT │ Object BLOCKMAT of type str │
├────────────────────┼───────────────────────────────────────┤
│ COMPOSITE │ Object COMPOSITE of type str │
├────────────────────┼───────────────────────────────────────┤
│ CONSTANTDIAGONAL │ Object CONSTANTDIAGONAL of type str │
├────────────────────┼───────────────────────────────────────┤
│ DENSE │ Object DENSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ DENSECUDA │ Object DENSECUDA of type str │
├────────────────────┼───────────────────────────────────────┤
│ DIAGONAL │ Object DIAGONAL of type str │
├────────────────────┼───────────────────────────────────────┤
│ DUMMY │ Object DUMMY of type str │
├────────────────────┼───────────────────────────────────────┤
│ ELEMENTAL │ Object ELEMENTAL of type str │
├────────────────────┼───────────────────────────────────────┤
│ FFT │ Object FFT of type str │
├────────────────────┼───────────────────────────────────────┤
│ FFTW │ Object FFTW of type str │
├────────────────────┼───────────────────────────────────────┤
│ H2OPUS │ Object H2OPUS of type str │
├────────────────────┼───────────────────────────────────────┤
│ HERMITIANTRANSPOSE │ Object HERMITIANTRANSPOSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ HYPRE │ Object HYPRE of type str │
├────────────────────┼───────────────────────────────────────┤
│ HYPRESSTRUCT │ Object HYPRESSTRUCT of type str │
├────────────────────┼───────────────────────────────────────┤
│ HYPRESTRUCT │ Object HYPRESTRUCT of type str │
├────────────────────┼───────────────────────────────────────┤
│ IS │ Object IS of type str │
├────────────────────┼───────────────────────────────────────┤
│ KAIJ │ Object KAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVM │ Object LMVM of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMBADBROYDEN │ Object LMVMBADBROYDEN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMBFGS │ Object LMVMBFGS of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMBROYDEN │ Object LMVMBROYDEN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMDBFGS │ Object LMVMDBFGS of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMDDFP │ Object LMVMDDFP of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMDFP │ Object LMVMDFP of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMDIAGBBROYDEN │ Object LMVMDIAGBBROYDEN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMDQN │ Object LMVMDQN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMSR1 │ Object LMVMSR1 of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMSYMBADBROYDEN │ Object LMVMSYMBADBROYDEN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVMSYMBROYDEN │ Object LMVMSYMBROYDEN of type str │
├────────────────────┼───────────────────────────────────────┤
│ LOCALREF │ Object LOCALREF of type str │
├────────────────────┼───────────────────────────────────────┤
│ LRC │ Object LRC of type str │
├────────────────────┼───────────────────────────────────────┤
│ MAIJ │ Object MAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MFFD │ Object MFFD of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIADJ │ Object MPIADJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJ │ Object MPIAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJCRL │ Object MPIAIJCRL of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJCUSPARSE │ Object MPIAIJCUSPARSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJMKL │ Object MPIAIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJPERM │ Object MPIAIJPERM of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJSELL │ Object MPIAIJSELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIAIJVIENNACL │ Object MPIAIJVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIBAIJ │ Object MPIBAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIBAIJMKL │ Object MPIBAIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIDENSE │ Object MPIDENSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIDENSECUDA │ Object MPIDENSECUDA of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIKAIJ │ Object MPIKAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPIMAIJ │ Object MPIMAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPISBAIJ │ Object MPISBAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ MPISELL │ Object MPISELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ NEST │ Object NEST of type str │
├────────────────────┼───────────────────────────────────────┤
│ NORMAL │ Object NORMAL of type str │
├────────────────────┼───────────────────────────────────────┤
│ NORMALHERMITIAN │ Object NORMALHERMITIAN of type str │
├────────────────────┼───────────────────────────────────────┤
│ PREALLOCATOR │ Object PREALLOCATOR of type str │
├────────────────────┼───────────────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├────────────────────┼───────────────────────────────────────┤
│ SAME │ Object SAME of type str │
├────────────────────┼───────────────────────────────────────┤
│ SBAIJ │ Object SBAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SCATTER │ Object SCATTER of type str │
├────────────────────┼───────────────────────────────────────┤
│ SCHURCOMPLEMENT │ Object SCHURCOMPLEMENT of type str │
├────────────────────┼───────────────────────────────────────┤
│ SELL │ Object SELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJ │ Object SEQAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJCRL │ Object SEQAIJCRL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJCUSPARSE │ Object SEQAIJCUSPARSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJMKL │ Object SEQAIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJPERM │ Object SEQAIJPERM of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJSELL │ Object SEQAIJSELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQAIJVIENNACL │ Object SEQAIJVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQBAIJ │ Object SEQBAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQBAIJMKL │ Object SEQBAIJMKL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQCUFFT │ Object SEQCUFFT of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQDENSE │ Object SEQDENSE of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQDENSECUDA │ Object SEQDENSECUDA of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQKAIJ │ Object SEQKAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQMAIJ │ Object SEQMAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQSBAIJ │ Object SEQSBAIJ of type str │
├────────────────────┼───────────────────────────────────────┤
│ SEQSELL │ Object SEQSELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SUBMATRIX │ Object SUBMATRIX of type str │
├────────────────────┼───────────────────────────────────────┤
│ TRANSPOSE │ Object TRANSPOSE of type str │
└────────────────────┴───────────────────────────────────────┘
Attributes Documentation
AIJ: str = AIJ
Object AIJ of type str
AIJCRL: str = AIJCRL
Object AIJCRL of type str
AIJCUSPARSE: str = AIJCUSPARSE
Object AIJCUSPARSE of type str
AIJMKL: str = AIJMKL
Object AIJMKL of type str
AIJPERM: str = AIJPERM
Object AIJPERM of type str
AIJSELL: str = AIJSELL
Object AIJSELL of type str
AIJVIENNACL: str = AIJVIENNACL
Object AIJVIENNACL of type str
BAIJ: str = BAIJ
Object BAIJ of type str
BAIJMKL: str = BAIJMKL
Object BAIJMKL of type str
BLOCKMAT: str = BLOCKMAT
Object BLOCKMAT of type str
COMPOSITE: str = COMPOSITE
Object COMPOSITE of type str
CONSTANTDIAGONAL: str = CONSTANTDIAGONAL
Object CONSTANTDIAGONAL of type str
DENSE: str = DENSE
Object DENSE of type str
DENSECUDA: str = DENSECUDA
Object DENSECUDA of type str
DIAGONAL: str = DIAGONAL
Object DIAGONAL of type str
DUMMY: str = DUMMY
Object DUMMY of type str
ELEMENTAL: str = ELEMENTAL
Object ELEMENTAL of type str
FFT: str = FFT
Object FFT of type str
FFTW: str = FFTW
Object FFTW of type str
H2OPUS: str = H2OPUS
Object H2OPUS of type str
HERMITIANTRANSPOSE: str = HERMITIANTRANSPOSE
Object HERMITIANTRANSPOSE of type str
HYPRE: str = HYPRE
Object HYPRE of type str
HYPRESSTRUCT: str = HYPRESSTRUCT
Object HYPRESSTRUCT of type str
HYPRESTRUCT: str = HYPRESTRUCT
Object HYPRESTRUCT of type str
IS: str = IS
Object IS of type str
KAIJ: str = KAIJ
Object KAIJ of type str
LMVM: str = LMVM
Object LMVM of type str
LMVMBADBROYDEN: str = LMVMBADBROYDEN
Object LMVMBADBROYDEN of type str
LMVMBFGS: str = LMVMBFGS
Object LMVMBFGS of type str
LMVMBROYDEN: str = LMVMBROYDEN
Object LMVMBROYDEN of type str
LMVMDBFGS: str = LMVMDBFGS
Object LMVMDBFGS of type str
LMVMDDFP: str = LMVMDDFP
Object LMVMDDFP of type str
LMVMDFP: str = LMVMDFP
Object LMVMDFP of type str
LMVMDIAGBBROYDEN: str = LMVMDIAGBBROYDEN
Object LMVMDIAGBBROYDEN of type str
LMVMDQN: str = LMVMDQN
Object LMVMDQN of type str
LMVMSR1: str = LMVMSR1
Object LMVMSR1 of type str
LMVMSYMBADBROYDEN: str = LMVMSYMBADBROYDEN
Object LMVMSYMBADBROYDEN of type str
LMVMSYMBROYDEN: str = LMVMSYMBROYDEN
Object LMVMSYMBROYDEN of type str
LOCALREF: str = LOCALREF
Object LOCALREF of type str
LRC: str = LRC
Object LRC of type str
MAIJ: str = MAIJ
Object MAIJ of type str
MFFD: str = MFFD
Object MFFD of type str
MPIADJ: str = MPIADJ
Object MPIADJ of type str
MPIAIJ: str = MPIAIJ
Object MPIAIJ of type str
MPIAIJCRL: str = MPIAIJCRL
Object MPIAIJCRL of type str
MPIAIJCUSPARSE: str = MPIAIJCUSPARSE
Object MPIAIJCUSPARSE of type str
MPIAIJMKL: str = MPIAIJMKL
Object MPIAIJMKL of type str
MPIAIJPERM: str = MPIAIJPERM
Object MPIAIJPERM of type str
MPIAIJSELL: str = MPIAIJSELL
Object MPIAIJSELL of type str
MPIAIJVIENNACL: str = MPIAIJVIENNACL
Object MPIAIJVIENNACL of type str
MPIBAIJ: str = MPIBAIJ
Object MPIBAIJ of type str
MPIBAIJMKL: str = MPIBAIJMKL
Object MPIBAIJMKL of type str
MPIDENSE: str = MPIDENSE
Object MPIDENSE of type str
MPIDENSECUDA: str = MPIDENSECUDA
Object MPIDENSECUDA of type str
MPIKAIJ: str = MPIKAIJ
Object MPIKAIJ of type str
MPIMAIJ: str = MPIMAIJ
Object MPIMAIJ of type str
MPISBAIJ: str = MPISBAIJ
Object MPISBAIJ of type str
MPISELL: str = MPISELL
Object MPISELL of type str
NEST: str = NEST
Object NEST of type str
NORMAL: str = NORMAL
Object NORMAL of type str
NORMALHERMITIAN: str = NORMALHERMITIAN
Object NORMALHERMITIAN of type str
PREALLOCATOR: str = PREALLOCATOR
Object PREALLOCATOR of type str
PYTHON: str = PYTHON
Object PYTHON of type str
SAME: str = SAME
Object SAME of type str
SBAIJ: str = SBAIJ
Object SBAIJ of type str
SCATTER: str = SCATTER
Object SCATTER of type str
SCHURCOMPLEMENT: str = SCHURCOMPLEMENT
Object SCHURCOMPLEMENT of type str
SELL: str = SELL
Object SELL of type str
SEQAIJ: str = SEQAIJ
Object SEQAIJ of type str
SEQAIJCRL: str = SEQAIJCRL
Object SEQAIJCRL of type str
SEQAIJCUSPARSE: str = SEQAIJCUSPARSE
Object SEQAIJCUSPARSE of type str
SEQAIJMKL: str = SEQAIJMKL
Object SEQAIJMKL of type str
SEQAIJPERM: str = SEQAIJPERM
Object SEQAIJPERM of type str
SEQAIJSELL: str = SEQAIJSELL
Object SEQAIJSELL of type str
SEQAIJVIENNACL: str = SEQAIJVIENNACL
Object SEQAIJVIENNACL of type str
SEQBAIJ: str = SEQBAIJ
Object SEQBAIJ of type str
SEQBAIJMKL: str = SEQBAIJMKL
Object SEQBAIJMKL of type str
SEQCUFFT: str = SEQCUFFT
Object SEQCUFFT of type str
SEQDENSE: str = SEQDENSE
Object SEQDENSE of type str
SEQDENSECUDA: str = SEQDENSECUDA
Object SEQDENSECUDA of type str
SEQKAIJ: str = SEQKAIJ
Object SEQKAIJ of type str
SEQMAIJ: str = SEQMAIJ
Object SEQMAIJ of type str
SEQSBAIJ: str = SEQSBAIJ
Object SEQSBAIJ of type str
SEQSELL: str = SEQSELL
Object SEQSELL of type str
SHELL: str = SHELL
Object SHELL of type str
SUBMATRIX: str = SUBMATRIX
Object SUBMATRIX of type str
TRANSPOSE: str = TRANSPOSE
Object TRANSPOSE of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ H2OpusCompress(tol) │ Compress a hierarchical matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ H2OpusLowRankUpdate(U[, V, s]) │ Perform a low-rank update of the form │
│ │ self += sUVᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ H2OpusOrthogonalize() │ Orthogonalize the basis tree of a │
│ │ hierarchical matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ SOR(b, x[, omega, sortype, shift, │ Compute relaxation (SOR, │
│ its, lits]) │ Gauss-Seidel) sweeps. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix([prefix]) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemble([assembly]) │ Assemble the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemblyBegin([assembly]) │ Begin an assembling stage of the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemblyEnd([assembly]) │ Complete an assembling stage of the │
│ │ matrix initiated with assemblyBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ axpy(alpha, X[, structure]) │ Perform the matrix summation self + = │
│ │ ɑ·X. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ aypx(alpha, X[, structure]) │ Perform the matrix summation self = │
│ │ ɑ·self + X. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ bindToCPU(flg) │ Mark a matrix to temporarily stay on │
│ │ the CPU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ boundToCPU() │ Query if a matrix is bound to the │
│ │ CPU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ chop(tol) │ Set entries smallest of tol (in │
│ │ absolute values) to zero. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ conjugate([out]) │ Return the conjugate matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ convert([mat_type, out]) │ Convert the matrix type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copy([result, structure]) │ Return a copy of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createAIJ(size[, bsize, nnz, csr, │ Create a sparse Type.AIJ matrix, │
│ comm]) │ optionally preallocating. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createAIJCRL(size[, bsize, nnz, csr, │ Create a sparse Type.AIJCRL matrix. │
│ comm]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createAIJWithArrays(size, csr[, │ Create a sparse Type.AIJ matrix with │
│ bsize, comm]) │ data in CSR format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createBAIJ(size, bsize[, nnz, csr, │ Create a sparse blocked Type.BAIJ │
│ comm]) │ matrix, optionally preallocating. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createConstantDiagonal(size, diag[, │ Create a diagonal matrix of type │
│ comm]) │ Type.CONSTANTDIAGONAL. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDense(size[, bsize, array, │ Create a Type.DENSE matrix. │
│ comm]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDenseCUDA(size[, bsize, array, │ Create a Type.DENSECUDA matrix with │
│ ...]) │ optional host and device data. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDiagonal(diag) │ Create a diagonal matrix of type │
│ │ Type.DIAGONAL. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createH2OpusFromMat(A[, coordinates, │ Create a hierarchical Type.H2OPUS │
│ dist, ...]) │ matrix sampling from a provided │
│ │ operator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createHermitianTranspose(mat) │ Create a Type.HERMITIANTRANSPOSE │
│ │ matrix that behaves like (A*)ᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createIS(size[, bsize, lgmapr, │ Create a Type.IS matrix representing │
│ lgmapc, comm]) │ globally unassembled operators. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createLRC(A, U, c, V) │ Create a low-rank correction Type.LRC │
│ │ matrix representing A + UCVᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createNest(mats[, isrows, iscols, │ Create a Type.NEST matrix containing │
│ comm]) │ multiple submatrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createNormal(mat) │ Create a Type.NORMAL matrix │
│ │ representing AᵀA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createNormalHermitian(mat) │ Create a Type.NORMALHERMITIAN matrix │
│ │ representing (A*)ᵀA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createPython(size[, context, comm]) │ Create a Type.PYTHON matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSBAIJ(size, bsize[, nnz, csr, │ Create a sparse Type.SBAIJ matrix in │
│ comm]) │ symmetric block format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createScatter(scatter[, comm]) │ Create a Type.SCATTER matrix from a │
│ │ vector scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSchurComplement(A00, Ap00, A01, │ Create a Type.SCHURCOMPLEMENT matrix. │
│ A10[, A11]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSubMatrices(isrows[, iscols, │ Return several sequential │
│ submats]) │ submatrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSubMatrix(isrow[, iscol, │ Return a submatrix. │
│ submat]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSubMatrixVirtual(A, isrow[, │ Create a Type.SUBMATRIX matrix that │
│ iscol]) │ acts as a submatrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createTranspose(mat) │ Create a Type.TRANSPOSE matrix that │
│ │ behaves like Aᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createVecLeft() │ Return a left vector, a vector that │
│ │ the matrix vector product can be │
│ │ stored in. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createVecRight() │ Return a right vector, a vector that │
│ │ the matrix can be multiplied against. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createVecs([side]) │ Return vectors that can be used in │
│ │ matrix vector products. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ diagonalScale([L, R]) │ Perform left and/or right diagonal │
│ │ scaling of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ duplicate([copy]) │ Return a clone of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ equal(mat) │ Return the result of matrix │
│ │ comparison. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorCholesky(isperm[, options]) │ Perform an in-place Cholesky │
│ │ factorization. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorICC(isperm[, options]) │ Perform an in-place an incomplete │
│ │ Cholesky factorization. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorILU(isrow, iscol[, options]) │ Perform an in-place ILU │
│ │ factorization. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorLU(isrow, iscol[, options]) │ Perform an in-place LU factorization. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorNumericCholesky(mat[, options]) │ Not implemented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorNumericLU(mat[, options]) │ Not implemented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorSymbolicCholesky(isperm[, │ Not implemented. │
│ options]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorSymbolicICC(isperm[, options]) │ Not implemented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorSymbolicILU(isrow, iscol[, │ Not implemented. │
│ options]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ factorSymbolicLU(mat, isrow, iscol[, │ Not implemented. │
│ options]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ findZeroRows() │ Return the index set of empty rows. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ fixISLocalEmpty([fix]) │ Compress out zero local rows from the │
│ │ local matrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSize() │ Return the matrix block size. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSizes() │ Return the row and column block │
│ │ sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getColumnIJ([symmetric, compressed]) │ Return the CSC representation of the │
│ │ local sparsity pattern. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getColumnVector(column[, result]) │ Return the columnᵗʰ column vector of │
│ │ the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM defining the data │
│ │ layout of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDenseArray([readonly]) │ Return the array where the data is │
│ │ stored. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDenseColumnVec(i[, mode]) │ Return the iᵗʰ column vector of the │
│ │ dense matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDenseLDA() │ Return the leading dimension of the │
│ │ array used by the dense matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDenseLocalMatrix() │ Return the local part of the dense │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDiagonal([result]) │ Return the diagonal of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDiagonalBlock() │ Return the part of the matrix │
│ │ associated with the on-process │
│ │ coupling. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getISAllowRepeated() │ Get the flag for repeated entries in │
│ │ the local to global map. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getISLocalMat() │ Return the local matrix stored inside │
│ │ a Type.IS matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInertia() │ Return the inertia from a factored │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInfo([info]) │ Return summary information. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLGMap() │ Return the local-to-global mappings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLRCMats() │ Return the constituents of a Type.LRC │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSize() │ Return the local number of rows and │
│ │ columns. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSubMatrix(isrow, iscol[, │ Return a reference to a submatrix │
│ submat]) │ specified in local numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsCntl(icntl) │ Return the MUMPS parameter, │
│ │ CNTL[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsIcntl(icntl) │ Return the MUMPS parameter, │
│ │ ICNTL[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsInfo(icntl) │ Return the MUMPS parameter, │
│ │ INFO[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsInfog(icntl) │ Return the MUMPS parameter, │
│ │ INFOG[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsRinfo(icntl) │ Return the MUMPS parameter, │
│ │ RINFO[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMumpsRinfog(icntl) │ Return the MUMPS parameter, │
│ │ RINFOG[icntl]. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNearNullSpace() │ Return the near-nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNestISs() │ Return the index sets representing │
│ │ the row and column spaces. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNestLocalISs() │ Return the local index sets │
│ │ representing the row and column │
│ │ spaces. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNestSize() │ Return the number of rows and columns │
│ │ of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNestSubMatrix(i, j) │ Return a single submatrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNullSpace() │ Return the nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOption(option) │ Return the option value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOrdering(ord_type) │ Return a reordering for a matrix to │
│ │ improve a LU factorization. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipIS() │ Return the ranges of rows and columns │
│ │ owned by each process as index sets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRange() │ Return the locally owned range of │
│ │ rows. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRangeColumn() │ Return the locally owned range of │
│ │ columns. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRanges() │ Return the range of rows owned by │
│ │ each process. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRangesColumn() │ Return the range of columns owned by │
│ │ each process. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRedundantMatrix(nsubcomm[, │ Return redundant matrices on │
│ subcomm, out]) │ subcommunicators. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRow(row) │ Return the column indices and values │
│ │ for the requested row. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRowIJ([symmetric, compressed]) │ Return the CSR representation of the │
│ │ local sparsity pattern. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRowSum([result]) │ Return the row-sum vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSchurComplementSubMatrices() │ Return Schur complement sub-matrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSize() │ Return the global number of rows and │
│ │ columns. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSizes() │ Return the tuple of matrix layouts. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTransposeNullSpace() │ Return the transpose nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValue(row, col) │ Return the value in the (row, col) │
│ │ position. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValues(rows, cols[, values]) │ Return the values in the zip(rows, │
│ │ cols) positions. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValuesCSR() │ Return the CSR representation of the │
│ │ local part of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVecType() │ Return the vector type used by the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ hermitianTranspose([out]) │ Return the transposed Hermitian │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ imagPart([out]) │ Return the imaginary part of the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ increaseOverlap(iset[, overlap]) │ Increase the overlap of a index set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ invertBlockDiagonal() │ Return the inverse of the │
│ │ block-diagonal entries. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isAssembled() │ The boolean flag indicating if the │
│ │ matrix is assembled. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isHermitian([tol]) │ Return the boolean indicating if the │
│ │ matrix is Hermitian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isHermitianKnown() │ Return the 2-tuple indicating if the │
│ │ matrix is known to be Hermitian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isStructurallySymmetric() │ Return the boolean indicating if the │
│ │ matrix is structurally symmetric. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isSymmetric([tol]) │ Return the boolean indicating if the │
│ │ matrix is symmetric. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isSymmetricKnown() │ Return the 2-tuple indicating if the │
│ │ matrix is known to be symmetric. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isTranspose([mat, tol]) │ Return the result of matrix │
│ │ comparison with transposition. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ kron(mat[, result]) │ Compute C, the Kronecker product of A │
│ │ and B. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ load(viewer) │ Load a matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matMatMult(B, C[, result, fill]) │ Perform matrix-matrix-matrix │
│ │ multiplication D=ABC. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matMult(mat[, result, fill]) │ Perform matrix-matrix multiplication │
│ │ C=AB. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matSolve(B, X) │ Solve AX=B, given a factored matrix │
│ │ A. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ matTransposeMult(mat[, result, fill]) │ Perform matrix-matrix multiplication │
│ │ C=ABᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mult(x, y) │ Perform the matrix vector product y = │
│ │ A @ x. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ multAdd(x, v, y) │ Perform the matrix vector product │
│ │ with addition y = A @ x + v. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ multHermitian(x, y) │ Perform the Hermitian matrix vector │
│ │ product y = A^H @ x. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ multHermitianAdd(x, v, y) │ Perform the Hermitian matrix vector │
│ │ product with addition y = A^H @ x + │
│ │ v. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ multTranspose(x, y) │ Perform the transposed matrix vector │
│ │ product y = A^T @ x. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ multTransposeAdd(x, v, y) │ Perform the transposed matrix vector │
│ │ product with addition y = A^T @ x + │
│ │ v. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ norm([norm_type]) │ Compute the requested matrix norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ permute(row, col) │ Return the permuted matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ preallocatorPreallocate(A[, fill]) │ Preallocate memory for a matrix using │
│ │ a preallocator matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ ptap(P[, result, fill]) │ Creates the matrix product C = PᵀAP. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ rart(R[, result, fill]) │ Create the matrix product C = RARᵀ. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ realPart([out]) │ Return the real part of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reorderForNonzeroDiagonal(isrow, │ Change a matrix ordering to remove │
│ iscol[, atol]) │ zeros from the diagonal. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreDenseColumnVec(i[, mode]) │ Restore the iᵗʰ column vector of the │
│ │ dense matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreISLocalMat(local) │ Restore the local matrix obtained │
│ │ with getISLocalMat. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreLocalSubMatrix(isrow, iscol, │ Restore a reference to a submatrix │
│ submat) │ obtained with getLocalSubMatrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ retrieveValues() │ Retrieve a copy of the matrix values │
│ │ previously stored with storeValues. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ scale(alpha) │ Scale the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBlockSize(bsize) │ Set the matrix block size (same for │
│ │ rows and columns). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBlockSizes(row_bsize, col_bsize) │ Set the row and column block sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM defining the data layout │
│ │ of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDenseLDA(lda) │ Set the leading dimension of the │
│ │ array used by the dense matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDiagonal(diag[, addv]) │ Set the diagonal values of the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the matrix from the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setISAllowRepeated([allow]) │ Allow repeated entries in the local │
│ │ to global map. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setISLocalMat(local) │ Set the local matrix stored inside a │
│ │ Type.IS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setISPreallocation(nnz, onnz) │ Preallocate memory for a Type.IS │
│ │ parallel matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLGMap(rmap[, cmap]) │ Set the local-to-global mappings. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLRCMats(A, U[, c, V]) │ Set the constituents of a Type.LRC │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMumpsCntl(icntl, val) │ Set a MUMPS parameter, CNTL[icntl] = │
│ │ val. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMumpsIcntl(icntl, ival) │ Set a MUMPS parameter, ICNTL[icntl] = │
│ │ ival. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNearNullSpace(nsp) │ Set the near-nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNestVecType(vec_type) │ Set the vector type for a Type.NEST │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNullSpace(nsp) │ Set the nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOption(option, flag) │ Set option. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix([prefix]) │ Set the prefix used for searching for │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPreallocationCSR(csr) │ Preallocate memory for the matrix │
│ │ with a CSR layout. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPreallocationDense(array) │ Set the array used for storing matrix │
│ │ elements for a dense matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPreallocationNNZ(nnz) │ Preallocate memory for the matrix │
│ │ with a non-zero pattern. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext(context) │ Set the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRandom([random]) │ Set random values in the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSizes(size[, bsize]) │ Set the local, global and block │
│ │ sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStencil(dims[, starts, dof]) │ Set matrix stencil. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTransposeNullSpace(nsp) │ Set the transpose nullspace. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTransposePrecursor(out) │ Set transpose precursor. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(mat_type) │ Set the matrix type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUnfactored() │ Set a factored matrix to be treated │
│ │ as unfactored. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValue(row, col, value[, addv]) │ Set a value to the (row, col) entry │
│ │ of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueBlockedStagStencil(row, col, │ Not implemented. │
│ value) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueBlockedStencil(row, col, │ Set a block of values to row and col │
│ value[, addv]) │ stencil. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueLocal(row, col, value[, │ Set a value to the (row, col) entry │
│ addv]) │ of the matrix in local ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueStagStencil(row, col, value[, │ Not implemented. │
│ addv]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueStencil(row, col, value[, │ Set a value to row and col stencil. │
│ addv]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValues(rows, cols, values[, addv]) │ Set values to the rows ⊗ cols entries │
│ │ of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlocked(rows, cols, values[, │ Set values to the rows ⊗ col block │
│ addv]) │ entries of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedCSR(I, J, V[, addv]) │ Set values stored in block CSR │
│ │ format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedIJV(I, J, V[, addv, │ Set a subset of values stored in │
│ rowmap]) │ block CSR format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedLocal(rows, cols, │ Set values to the rows ⊗ col block │
│ values[, addv]) │ entries of the matrix in local │
│ │ ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedLocalCSR(I, J, V[, │ Set values stored in block CSR │
│ addv]) │ format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedLocalIJV(I, J, V[, │ Set a subset of values stored in │
│ addv, rowmap]) │ block CSR format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedLocalRCV(R, C, V[, │ Undocumented. │
│ addv]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedRCV(R, C, V[, addv]) │ Undocumented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesCSR(I, J, V[, addv]) │ Set values stored in CSR format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesIJV(I, J, V[, addv, rowmap]) │ Set a subset of values stored in CSR │
│ │ format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesLocal(rows, cols, values[, │ Set values to the rows ⊗ col entries │
│ addv]) │ of the matrix in local ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesLocalCSR(I, J, V[, addv]) │ Set values stored in CSR format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesLocalIJV(I, J, V[, addv, │ Set a subset of values stored in CSR │
│ rowmap]) │ format. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesLocalRCV(R, C, V[, addv]) │ Undocumented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesRCV(R, C, V[, addv]) │ Undocumented. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setVariableBlockSizes(blocks) │ Set diagonal point-blocks of the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setVecType(vec_type) │ Set the vector type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ shift(alpha) │ Shift the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solve(b, x) │ Solve Ax=b, given a factored matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveAdd(b, y, x) │ Solve x=y+A⁻¹b, given a factored │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveBackward(b, x) │ Solve Ux=b, given a factored matrix │
│ │ A=LU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveForward(b, x) │ Solve Lx = b, given a factored matrix │
│ │ A = LU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveTranspose(b, x) │ Solve Aᵀx=b, given a factored matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solveTransposeAdd(b, y, x) │ Solve x=y+A⁻ᵀb, given a factored │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ storeValues() │ Stash a copy of the matrix values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ toDLPack([mode]) │ Return a DLPack PyCapsule wrapping │
│ │ the vector data. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ transpose([out]) │ Return the transposed matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ transposeMatMult(mat[, result, fill]) │ Perform matrix-matrix multiplication │
│ │ C=AᵀB. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroEntries() │ Zero the entries of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroRows(rows[, diag, x, b]) │ Zero selected rows of the matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroRowsColumns(rows[, diag, x, b]) │ Zero selected rows and columns of the │
│ │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroRowsColumnsLocal(rows[, diag, x, │ Zero selected rows and columns of the │
│ b]) │ matrix in local ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroRowsColumnsStencil(rows[, diag, │ Zero selected rows and columns of the │
│ x, b]) │ matrix. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroRowsLocal(rows[, diag, x, b]) │ Zero selected rows of the matrix in │
│ │ local ordering. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌──────────────┬───────────────────────────────────────┐
│ assembled │ The boolean flag indicating if the │
│ │ matrix is assembled. │
├──────────────┼───────────────────────────────────────┤
│ block_size │ Matrix block size. │
├──────────────┼───────────────────────────────────────┤
│ block_sizes │ Matrix row and column block sizes. │
├──────────────┼───────────────────────────────────────┤
│ hermitian │ The boolean flag indicating if the │
│ │ matrix is Hermitian. │
├──────────────┼───────────────────────────────────────┤
│ local_size │ Matrix local size. │
├──────────────┼───────────────────────────────────────┤
│ owner_range │ Matrix local row range. │
├──────────────┼───────────────────────────────────────┤
│ owner_ranges │ Matrix row ranges. │
├──────────────┼───────────────────────────────────────┤
│ size │ Matrix global size. │
├──────────────┼───────────────────────────────────────┤
│ sizes │ Matrix local and global sizes. │
├──────────────┼───────────────────────────────────────┤
│ structsymm │ The boolean flag indicating if the │
│ │ matrix is structurally symmetric. │
├──────────────┼───────────────────────────────────────┤
│ symmetric │ The boolean flag indicating if the │
│ │ matrix is symmetric. │
└──────────────┴───────────────────────────────────────┘
Methods Documentation
H2OpusCompress(tol)
Compress a hierarchical matrix.
Collective.
Parameters
tol (float) -- The absolute truncation threshold.
Return type
Self
SEE ALSO:
MatH2OpusCompress
Source code at petsc4py/PETSc/Mat.pyx:4992
H2OpusLowRankUpdate(U, V=None, s=1.0)
Perform a low-rank update of the form self += sUVᵀ.
Collective.
Parameters
• U (Mat) -- The dense low-rank update matrix.
• V (Mat | None) -- The dense low-rank update matrix. If None, V = U.
• s (float) -- The scaling factor.
Return type
Self
SEE ALSO:
MatH2OpusLowRankUpdate
Source code at petsc4py/PETSc/Mat.pyx:5011
H2OpusOrthogonalize()
Orthogonalize the basis tree of a hierarchical matrix.
Collective.
SEE ALSO:
MatH2OpusOrthogonalize
Source code at petsc4py/PETSc/Mat.pyx:4979
Return type
Self
SOR(b, x, omega=1.0, sortype=None, shift=0.0, its=1, lits=1)
Compute relaxation (SOR, Gauss-Seidel) sweeps.
Neighborwise collective.
SEE ALSO:
MatSOR
Source code at petsc4py/PETSc/Mat.pyx:3825
Parameters
• b (Vec)
• x (Vec)
• omega (float)
• sortype (SORType | None)
• shift (float)
• its (int)
• lits (int)
Return type
None
appendOptionsPrefix(prefix=None)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, MatAppendOptionsPrefix
Source code at petsc4py/PETSc/Mat.pyx:1751
Parameters
prefix (str | None)
Return type
None
assemble(assembly=None)
Assemble the matrix.
Collective.
Parameters
assembly (MatAssemblySpec) -- The assembly type.
Return type
None
SEE ALSO:
assemblyBegin, assemblyEnd
Source code at petsc4py/PETSc/Mat.pyx:3338
assemblyBegin(assembly=None)
Begin an assembling stage of the matrix.
Collective.
Parameters
assembly (MatAssemblySpec) -- The assembly type.
Return type
None
SEE ALSO:
assemblyEnd, assemble, MatAssemblyBegin
Source code at petsc4py/PETSc/Mat.pyx:3302
assemblyEnd(assembly=None)
Complete an assembling stage of the matrix initiated with assemblyBegin.
Collective.
Parameters
assembly (MatAssemblySpec) -- The assembly type.
Return type
None
SEE ALSO:
assemblyBegin, assemble, MatAssemblyEnd
Source code at petsc4py/PETSc/Mat.pyx:3320
axpy(alpha, X, structure=None)
Perform the matrix summation self + = ɑ·X.
Collective.
Parameters
• alpha (Scalar) -- The scalar.
• X (Mat) -- The matrix to be added.
• structure (Structure) -- The structure of the operation.
Return type
None
SEE ALSO:
MatAXPY
Source code at petsc4py/PETSc/Mat.pyx:4153
aypx(alpha, X, structure=None)
Perform the matrix summation self = ɑ·self + X.
Collective.
Parameters
• alpha (Scalar) -- The scalar.
• X (Mat) -- The matrix to be added.
• structure (Structure) -- The structure of the operation.
Return type
None
SEE ALSO:
MatAYPX
Source code at petsc4py/PETSc/Mat.pyx:4176
bindToCPU(flg)
Mark a matrix to temporarily stay on the CPU.
Collective.
Once marked, perform computations on the CPU.
Parameters
flg (bool) -- Bind to the CPU if True.
Return type
None
SEE ALSO:
MatBindToCPU
Source code at petsc4py/PETSc/Mat.pyx:4520
boundToCPU()
Query if a matrix is bound to the CPU.
Not collective.
SEE ALSO:
MatBoundToCPU
Source code at petsc4py/PETSc/Mat.pyx:4540
Return type
bool
chop(tol)
Set entries smallest of tol (in absolute values) to zero.
Collective.
SEE ALSO:
MatFilter
Source code at petsc4py/PETSc/Mat.pyx:4121
Parameters
tol (float)
Return type
None
conjugate(out=None)
Return the conjugate matrix.
Collective.
Parameters
out (Mat | None) -- Optional return matrix. If None, the operation is performed
in-place. Otherwise, the operation is performed on out.
Return type
Mat
SEE ALSO:
realPart, imagPart, MatConjugate
Source code at petsc4py/PETSc/Mat.pyx:2215
convert(mat_type=None, out=None)
Convert the matrix type.
Collective.
Parameters
• mat_type (Type | str) -- The type of the new matrix. If None uses Type.SAME.
• out (Mat | None) -- Optional return matrix. If None, inplace conversion is
performed. Otherwise, the matrix is reused.
Return type
Mat
SEE ALSO:
MatConvert
Source code at petsc4py/PETSc/Mat.pyx:2071
copy(result=None, structure=None)
Return a copy of the matrix.
Collective.
Parameters
• result (Mat | None) -- Optional return matrix. If None, it is internally created.
• structure (Structure | None) -- The copy structure. Only relevant if result is not
None.
Return type
Mat
SEE ALSO:
MatCopy, MatDuplicate
Source code at petsc4py/PETSc/Mat.pyx:2026
create(comm=None)
Create the matrix.
Collective.
Once created, the user should call setType or setFromOptions before using the matrix.
Alternatively, specific creation routines such as createAIJ or createBAIJ can be used.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
destroy, MatCreate
Source code at petsc4py/PETSc/Mat.pyx:488
createAIJ(size, bsize=None, nnz=None, csr=None, comm=None)
Create a sparse Type.AIJ matrix, optionally preallocating.
Collective.
To preallocate the matrix the user can either pass nnz or csr describing the sparsity. If
neither is set then preallocation will not occur. Consult the PETSc manual for more
information.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• nnz (NNZSpec | None) -- Optional non-zeros preallocation pattern.
• csr (CSRIndicesSpec | None) -- Optional compressed sparse row layout information.
If provided, it takes precedence on nnz.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
setSizes, createBAIJ, MATAIJ, MATSEQAIJ, MATMPIAIJ, MatCreateAIJ, ‐
MatSeqAIJSetPreallocation, MatSeqAIJSetPreallocationCSR
Source code at petsc4py/PETSc/Mat.pyx:693
createAIJCRL(size, bsize=None, nnz=None, csr=None, comm=None)
Create a sparse Type.AIJCRL matrix.
Collective.
This is similar to Type.AIJ matrices but stores some additional information that improves
vectorization for the matrix-vector product.
To preallocate the matrix the user can either pass nnz or csr describing the sparsity. If
neither is set then preallocation will not occur. Consult the PETSc manual for more
information.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• nnz (NNZSpec | None) -- Optional non-zeros preallocation pattern.
• csr (CSRIndicesSpec | None) -- Optional compressed sparse row layout information.
If provided, it takes precedence on nnz.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createAIJ, createBAIJ, MatCreateSeqAIJCRL, MatCreateMPIAIJCRL
Source code at petsc4py/PETSc/Mat.pyx:826
createAIJWithArrays(size, csr, bsize=None, comm=None)
Create a sparse Type.AIJ matrix with data in CSR format.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• csr (CSRSpec | tuple[CSRSpec, CSRSpec]) -- Local matrix data in compressed sparse
row format.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
Notes
For Type.SEQAIJ matrices, the csr data is not copied. For Type.MPIAIJ matrices, the csr
data is not copied only in the case it represents on-process and off-process information.
SEE ALSO:
createAIJ, MatCreateSeqAIJWithArrays, MatCreateMPIAIJWithArrays, ‐
MatCreateMPIAIJWithSplitArrays
Source code at petsc4py/PETSc/Mat.pyx:956
createBAIJ(size, bsize, nnz=None, csr=None, comm=None)
Create a sparse blocked Type.BAIJ matrix, optionally preallocating.
Collective.
To preallocate the matrix the user can either pass nnz or csr describing the sparsity. If
neither is set then preallocation will not occur. Consult the PETSc manual for more
information.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec) -- Matrix block size.
• nnz (NNZSpec | None) -- Optional non-zeros preallocation pattern for block rows.
• csr (CSRIndicesSpec | None) -- Optional block-compressed sparse row layout
information. If provided, it takes precedence on nnz.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
setSizes, createAIJ, MATBAIJ, MATSEQBAIJ, MATMPIBAIJ, MatCreateBAIJ
Source code at petsc4py/PETSc/Mat.pyx:738
createConstantDiagonal(size, diag, comm=None)
Create a diagonal matrix of type Type.CONSTANTDIAGONAL.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• diag (float) -- The diagonal value.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createDiagonal
Source code at petsc4py/PETSc/Mat.pyx:1561
createDense(size, bsize=None, array=None, comm=None)
Create a Type.DENSE matrix.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• array (Sequence[Scalar] | None) -- Optional matrix data. If None, memory is
internally allocated.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createDenseCUDA, MATDENSE, MatCreateDense
Source code at petsc4py/PETSc/Mat.pyx:1047
createDenseCUDA(size, bsize=None, array=None, cudahandle=None, comm=None)
Create a Type.DENSECUDA matrix with optional host and device data.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• array (Sequence[Scalar] | None) -- Host data. Will be lazily allocated if None.
• cudahandle (int | None) -- Address of the array on the GPU. Will be lazily
allocated if None. If cudahandle is provided, array will be ignored.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createDense, MatCreateDenseCUDA
Source code at petsc4py/PETSc/Mat.pyx:1083
createDiagonal(diag)
Create a diagonal matrix of type Type.DIAGONAL.
Collective.
Parameters
diag (Vec) -- The vector holding diagonal values.
Return type
Self
SEE ALSO:
createConstantDiagonal
Source code at petsc4py/PETSc/Mat.pyx:1594
createH2OpusFromMat(A, coordinates=None, dist=None, eta=None, leafsize=None, maxrank=None,
bs=None, rtol=None)
Create a hierarchical Type.H2OPUS matrix sampling from a provided operator.
Collective.
Parameters
• A (Mat) -- Matrix to be sampled.
• coordinates (Sequence[Scalar] | None) -- Coordinates of the points.
• dist (bool | None) -- Whether or not coordinates are distributed, defaults to ‐
False.
• eta (float | None) -- Admissibility condition tolerance, defaults to DECIDE.
• leafsize (int | None) -- Leaf size in cluster tree, defaults to DECIDE.
• maxrank (int | None) -- Maximum rank permitted, defaults to DECIDE.
• bs (int | None) -- Maximum number of samples to take concurrently, defaults to
DECIDE.
• rtol (float | None) -- Relative tolerance for construction, defaults to DECIDE.
Return type
Self
Notes
See MatCreateH2OpusFromMat for the appropriate database options.
SEE ALSO:
Working with PETSc options, MatCreateH2OpusFromMat
Source code at petsc4py/PETSc/Mat.pyx:1427
createHermitianTranspose(mat)
Create a Type.HERMITIANTRANSPOSE matrix that behaves like (A*)ᵀ.
Collective.
Parameters
mat (Mat) -- Matrix A to represent the hermitian transpose of.
Return type
Self
Notes
The Hermitian transpose is never actually formed.
SEE ALSO:
createNormal, createNormalHermitian, MATHERMITIANTRANSPOSEVIRTUAL, ‐
MatCreateHermitianTranspose
Source code at petsc4py/PETSc/Mat.pyx:1263
createIS(size, bsize=None, lgmapr=None, lgmapc=None, comm=None)
Create a Type.IS matrix representing globally unassembled operators.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
• lgmapr (LGMap | None) -- Optional local-to-global mapping for the rows. If None,
the local row space matches the global row space.
• lgmapc (LGMap | None) -- Optional local-to-global mapping for the columns. If ‐
None, the local column space matches the global column space.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
MATIS
Source code at petsc4py/PETSc/Mat.pyx:1508
createLRC(A, U, c, V)
Create a low-rank correction Type.LRC matrix representing A + UCVᵀ.
Collective.
Parameters
• A (Mat) -- Sparse matrix, can be None.
• U (Mat) -- Dense rectangular matrices.
• V (Mat) -- Dense rectangular matrices.
• c (Vec) -- Vector containing the diagonal of C, can be None.
Return type
Self
Notes
The matrix A + UCVᵀ is never actually formed.
C is a diagonal matrix (represented as a vector) of order k, where k is the number of
columns of both U and V.
If A is None then the new object behaves like a low-rank matrix UCVᵀ.
Use the same matrix for V and U (or V=None) for a symmetric low-rank correction, A + UCUᵀ.
If c is None then the low-rank correction is just U*Vᵀ. If a sequential c vector is used
for a parallel matrix, PETSc assumes that the values of the vector are consistently set
across processors.
SEE ALSO:
MATLRC, MatCreateLRC
Source code at petsc4py/PETSc/Mat.pyx:1288
createNest(mats, isrows=None, iscols=None, comm=None)
Create a Type.NEST matrix containing multiple submatrices.
Collective.
Parameters
• mats (Sequence[Sequence[Mat]]) -- Iterable of matrix block rows with size
len(isrows). Each matrix block row must be of size len(iscols). Empty
submatrices can be set with None.
• isrows (Sequence[IS] | None) -- Index set for each nested row block, defaults to
contiguous ordering.
• iscols (Sequence[IS] | None) -- Index set for each nested column block, defaults
to contiguous ordering.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
MatCreateNest, MATNEST
Source code at petsc4py/PETSc/Mat.pyx:1360
createNormal(mat)
Create a Type.NORMAL matrix representing AᵀA.
Collective.
Parameters
mat (Mat) -- The (possibly rectangular) matrix A.
Return type
Self
Notes
The product AᵀA is never actually formed. Instead A and Aᵀ are used during mult and various
other matrix operations.
SEE ALSO:
MATNORMAL, MatCreateNormal
Source code at petsc4py/PETSc/Mat.pyx:1188
createNormalHermitian(mat)
Create a Type.NORMALHERMITIAN matrix representing (A*)ᵀA.
Collective.
Parameters
mat (Mat) -- The (possibly rectangular) matrix A.
Return type
Self
Notes
The product (A*)ᵀA is never actually formed.
SEE ALSO:
createHermitianTranspose, MATNORMAL, MATNORMALHERMITIAN, MatCreateNormalHermitian
Source code at petsc4py/PETSc/Mat.pyx:1238
createPython(size, context=None, comm=None)
Create a Type.PYTHON matrix.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python matrix type, setType, setPythonContext, Type.PYTHON
Source code at petsc4py/PETSc/Mat.pyx:1617
createSBAIJ(size, bsize, nnz=None, csr=None, comm=None)
Create a sparse Type.SBAIJ matrix in symmetric block format.
Collective.
To preallocate the matrix the user can either pass nnz or csr describing the sparsity. If
neither is set then preallocation will not occur. Consult the PETSc manual for more
information.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec) -- Matrix block size.
• nnz (NNZSpec | None) -- Optional upper-triangular (including diagonal) non-zeros
preallocation pattern for block rows.
• csr (CSRIndicesSpec | None) -- Optional block-compressed sparse row layout
information. If provided, it takes precedence on nnz.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createAIJ, createBAIJ, MatCreateSBAIJ
Source code at petsc4py/PETSc/Mat.pyx:782
createScatter(scatter, comm=None)
Create a Type.SCATTER matrix from a vector scatter.
Collective.
Parameters
• scatter (Scatter) -- Vector scatter.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
MATSCATTER, MatCreateScatter
Source code at petsc4py/PETSc/Mat.pyx:1164
createSchurComplement(A00, Ap00, A01, A10, A11=None)
Create a Type.SCHURCOMPLEMENT matrix.
Collective.
Parameters
• A00 (Mat) -- the upper-left block of the original matrix A = [A00 A01; A10 A11].
• Ap00 (Mat) -- preconditioning matrix for use in ksp(A00,Ap00) to approximate the
action of A00^{-1}.
• A01 (Mat) -- the upper-right block of the original matrix A = [A00 A01; A10 A11].
• A10 (Mat) -- the lower-left block of the original matrix A = [A00 A01; A10 A11].
• A11 (Mat | None) -- Optional lower-right block of the original matrix A = [A00
A01; A10 A11].
Return type
Self
SEE ALSO:
MatCreateSchurComplement
Source code at petsc4py/PETSc/Mat.pyx:3969
createSubMatrices(isrows, iscols=None, submats=None)
Return several sequential submatrices.
Collective.
Parameters
• isrows (IS | Sequence[IS]) -- Row index sets.
• iscols (IS | Sequence[IS]) -- Column index sets. If None, iscols = isrows.
• submats (Mat | Sequence[Mat]) -- Optional resultant matrices. When None, new
matrices are created, and MAT_INITIAL_MATRIX is used. When not None, the matrices
are reused with MAT_REUSE_MATRIX.
Return type
Sequence[Mat]
SEE ALSO:
MatCreateSubMatrices
Source code at petsc4py/PETSc/Mat.pyx:3912
createSubMatrix(isrow, iscol=None, submat=None)
Return a submatrix.
Collective.
Parameters
• isrow (IS) -- Row index set.
• iscol (IS | None) -- Column index set. If None, iscol = isrow.
• submat (Mat | None) -- Optional resultant matrix. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When not None, the matrix is reused with
MAT_REUSE_MATRIX.
Return type
Mat
SEE ALSO:
MatCreateSubMatrix
Source code at petsc4py/PETSc/Mat.pyx:3882
createSubMatrixVirtual(A, isrow, iscol=None)
Create a Type.SUBMATRIX matrix that acts as a submatrix.
Collective.
Parameters
• A (Mat) -- Matrix to extract submatrix from.
• isrow (IS) -- Rows present in the submatrix.
• iscol (IS | None) -- Columns present in the submatrix, defaults to isrow.
Return type
Self
SEE ALSO:
MatCreateSubMatrixVirtual
Source code at petsc4py/PETSc/Mat.pyx:1335
createTranspose(mat)
Create a Type.TRANSPOSE matrix that behaves like Aᵀ.
Collective.
Parameters
mat (Mat) -- Matrix A to represent the transpose of.
Return type
Self
Notes
The transpose is never actually formed. Instead multTranspose is called whenever the
matrix-vector product is computed.
SEE ALSO:
createNormal, MatCreateTranspose
Source code at petsc4py/PETSc/Mat.pyx:1213
createVecLeft()
Return a left vector, a vector that the matrix vector product can be stored in.
Collective.
SEE ALSO:
createVecs, createVecRight, MatCreateVecs
Source code at petsc4py/PETSc/Mat.pyx:3438
Return type
Vec
createVecRight()
Return a right vector, a vector that the matrix can be multiplied against.
Collective.
SEE ALSO:
createVecs, createVecLeft, MatCreateVecs
Source code at petsc4py/PETSc/Mat.pyx:3424
Return type
Vec
createVecs(side=None)
Return vectors that can be used in matrix vector products.
Collective.
Parameters
side (Literal['r', 'R', 'right', 'Right', 'RIGHT', 'l', 'L', 'left', 'Left', 'LEFT']
| None) -- If None returns a 2-tuple of vectors (right, left). Otherwise it just
return a left or right vector.
Return type
Vec | tuple[Vec, Vec]
Notes
right vectors are vectors in the column space of the matrix. left vectors are vectors in
the row space of the matrix.
SEE ALSO:
createVecLeft, createVecRight, MatCreateVecs
Source code at petsc4py/PETSc/Mat.pyx:3385
destroy()
Destroy the matrix.
Collective.
SEE ALSO:
create, MatDestroy
Source code at petsc4py/PETSc/Mat.pyx:475
Return type
Self
diagonalScale(L=None, R=None)
Perform left and/or right diagonal scaling of the matrix.
Collective.
Parameters
• L (Vec | None) -- Optional left scaling vector.
• R (Vec | None) -- Optional right scaling vector.
Return type
None
SEE ALSO:
MatDiagonalScale
Source code at petsc4py/PETSc/Mat.pyx:3577
duplicate(copy=False)
Return a clone of the matrix.
Collective.
Parameters
copy (bool) -- If True, it also copies the values.
Return type
Mat
SEE ALSO:
MatDuplicate
Source code at petsc4py/PETSc/Mat.pyx:2004
equal(mat)
Return the result of matrix comparison.
Collective.
SEE ALSO:
MatEqual
Source code at petsc4py/PETSc/Mat.pyx:2259
Parameters
mat (Mat)
Return type
bool
factorCholesky(isperm, options=None)
Perform an in-place Cholesky factorization.
Collective.
Parameters
• isperm (IS) -- The row and column permutations.
• options (dict[str, Any] | None) -- An optional dictionary of options for the
factorization. These include fill, the expected fill as a ratio of the original
fill.
Return type
None
SEE ALSO:
factorLU, MatCholeskyFactor
Source code at petsc4py/PETSc/Mat.pyx:4684
factorICC(isperm, options=None)
Perform an in-place an incomplete Cholesky factorization.
Collective.
Parameters
• isperm (IS) -- The row and column permutations
• options (dict[str, Any] | None) -- An optional dictionary of options for the
factorization. These include fill, the expected fill as a ratio of the original
fill.
Return type
None
SEE ALSO:
factorILU, MatICCFactor
Source code at petsc4py/PETSc/Mat.pyx:4717
factorILU(isrow, iscol, options=None)
Perform an in-place ILU factorization.
Collective.
Parameters
• isrow (IS) -- The row permutation.
• iscol (IS) -- The column permutation.
• options (dict[str, Any] | None) -- An optional dictionary of options for the
factorization. These include levels, the number of levels of fill, fill, the
expected fill as a ratio of the original fill, and dtcol, the pivot tolerance
where 0 indicates no pivot and 1 indicates full column pivoting.
Return type
None
SEE ALSO:
MatILUFactor
Source code at petsc4py/PETSc/Mat.pyx:4650
factorLU(isrow, iscol, options=None)
Perform an in-place LU factorization.
Collective.
Parameters
• isrow (IS) -- The row permutation.
• iscol (IS) -- The column permutation.
• options (dict[str, Any] | None) -- An optional dictionary of options for the
factorization. These include fill, the expected fill as a ratio of the original
fill and dtcol, the pivot tolerance where 0 indicates no pivot and 1 indicates
full column pivoting.
Return type
None
SEE ALSO:
MatLUFactor
Source code at petsc4py/PETSc/Mat.pyx:4612
factorNumericCholesky(mat, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4713
Parameters
mat (Mat)
Return type
None
factorNumericLU(mat, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4646
Parameters
mat (Mat)
Return type
None
factorSymbolicCholesky(isperm, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4709
Parameters
isperm (IS)
Return type
None
factorSymbolicICC(isperm, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4742
Parameters
isperm (IS)
Return type
None
factorSymbolicILU(isrow, iscol, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4680
Parameters
• isrow (IS)
• iscol (IS)
Return type
None
factorSymbolicLU(mat, isrow, iscol, options=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:4642
Parameters
• mat (Mat)
• isrow (IS)
• iscol (IS)
Return type
None
findZeroRows()
Return the index set of empty rows.
Collective.
SEE ALSO:
MatFindZeroRows
Source code at petsc4py/PETSc/Mat.pyx:3371
Return type
IS
fixISLocalEmpty(fix=True)
Compress out zero local rows from the local matrices.
Collective.
Parameters
fix (bool) -- When True, new local matrices and local to global maps are generated
during the final assembly process.
Return type
None
SEE ALSO:
MatISFixLocalEmpty
Source code at petsc4py/PETSc/Mat.pyx:4817
getBlockSize()
Return the matrix block size.
Not collective.
SEE ALSO:
getBlockSize, MatGetBlockSize
Source code at petsc4py/PETSc/Mat.pyx:1874
Return type
int
getBlockSizes()
Return the row and column block sizes.
Not collective.
SEE ALSO:
getBlockSize, MatGetBlockSizes
Source code at petsc4py/PETSc/Mat.pyx:1888
Return type
tuple[int, int]
getColumnIJ(symmetric=False, compressed=False)
Return the CSC representation of the local sparsity pattern.
Collective.
Parameters
• symmetric (bool) -- If True, return the symmetrized graph.
• compressed (bool) -- If True, return the compressed graph.
Return type
tuple[ArrayInt, ArrayInt]
SEE ALSO:
MatGetRowIJ
Source code at petsc4py/PETSc/Mat.pyx:2518
getColumnVector(column, result=None)
Return the columnᵗʰ column vector of the matrix.
Collective.
Parameters
• column (int) -- Column index.
• result (Vec | None) -- Optional vector to store the result.
Return type
Vec
SEE ALSO:
MatGetColumnVector
Source code at petsc4py/PETSc/Mat.pyx:3458
getDM()
Return the DM defining the data layout of the matrix.
Not collective.
SEE ALSO:
MatGetDM
Source code at petsc4py/PETSc/Mat.pyx:5570
Return type
DM
getDenseArray(readonly=False)
Return the array where the data is stored.
Not collective.
Parameters
readonly (bool) -- Enable to obtain a read only array.
Return type
ArrayScalar
SEE ALSO:
MatDenseGetArrayRead, MatDenseGetArray
Source code at petsc4py/PETSc/Mat.pyx:5375
getDenseColumnVec(i, mode='rw')
Return the iᵗʰ column vector of the dense matrix.
Collective.
Parameters
• i (int) -- The column index to access.
• mode (AccessModeSpec) -- The access type of the returned array
Return type
Vec
SEE ALSO:
restoreDenseColumnVec, MatDenseGetColumnVec, MatDenseGetColumnVecRead, ‐
MatDenseGetColumnVecWrite
Source code at petsc4py/PETSc/Mat.pyx:5428
getDenseLDA()
Return the leading dimension of the array used by the dense matrix.
Not collective.
SEE ALSO:
MatDenseGetLDA
Source code at petsc4py/PETSc/Mat.pyx:5361
Return type
int
getDenseLocalMatrix()
Return the local part of the dense matrix.
Not collective.
SEE ALSO:
MatDenseGetLocalMatrix
Source code at petsc4py/PETSc/Mat.pyx:5413
Return type
Mat
getDiagonal(result=None)
Return the diagonal of the matrix.
Collective.
Parameters
result (Vec | None) -- Optional vector to store the result.
Return type
Vec
SEE ALSO:
setDiagonal, MatGetDiagonal
Source code at petsc4py/PETSc/Mat.pyx:3513
getDiagonalBlock()
Return the part of the matrix associated with the on-process coupling.
Not collective.
SEE ALSO:
MatGetDiagonalBlock
Source code at petsc4py/PETSc/Mat.pyx:3854
Return type
Mat
getISAllowRepeated()
Get the flag for repeated entries in the local to global map.
Not collective.
SEE ALSO:
setISAllowRepeated, MatISGetAllowRepeated
Source code at petsc4py/PETSc/Mat.pyx:4803
Return type
bool
getISLocalMat()
Return the local matrix stored inside a Type.IS matrix.
Not collective.
SEE ALSO:
MatISGetLocalMat
Source code at petsc4py/PETSc/Mat.pyx:4836
Return type
Mat
getInertia()
Return the inertia from a factored matrix.
Collective.
The matrix must have been factored by calling factorCholesky.
Returns
• n (int) -- The number of negative eigenvalues.
• z (int) -- The number of zero eigenvalues.
• p (int) -- The number of positive eigenvalues.
Return type
tuple[int, int, int]
SEE ALSO:
MatGetInertia
Source code at petsc4py/PETSc/Mat.pyx:4746
getInfo(info=None)
Return summary information.
Collective.
Parameters
info (InfoType) -- If None, it uses InfoType.GLOBAL_SUM.
Return type
dict[str, float]
SEE ALSO:
MatInfo, MatGetInfo
Source code at petsc4py/PETSc/Mat.pyx:1984
getLGMap()
Return the local-to-global mappings.
Not collective.
SEE ALSO:
setLGMap, MatGetLocalToGlobalMapping
Source code at petsc4py/PETSc/Mat.pyx:2784
Return type
tuple[LGMap, LGMap]
getLRCMats()
Return the constituents of a Type.LRC matrix.
Not collective.
Returns
• A (Mat) -- The A matrix.
• U (Mat) -- The first dense rectangular matrix.
• c (Vec) -- The sequential vector containing the diagonal of C.
• V (Mat) -- The second dense rectangular matrix.
Return type
tuple[Mat, Mat, Vec, Mat]
SEE ALSO:
MatLRCGetMats
Source code at petsc4py/PETSc/Mat.pyx:4918
getLocalSize()
Return the local number of rows and columns.
Not collective.
SEE ALSO:
getSize, MatGetLocalSize
Source code at petsc4py/PETSc/Mat.pyx:1844
Return type
tuple[int, int]
getLocalSubMatrix(isrow, iscol, submat=None)
Return a reference to a submatrix specified in local numbering.
Collective.
Parameters
• isrow (IS) -- Row index set.
• iscol (IS) -- Column index set.
• submat (Mat | None) -- Optional resultant matrix. When None, a new matrix is
created. When not None, the matrix is first destroyed and then recreated.
Return type
Mat
SEE ALSO:
restoreLocalSubMatrix, MatGetLocalSubMatrix
Source code at petsc4py/PETSc/Mat.pyx:4024
getMumpsCntl(icntl)
Return the MUMPS parameter, CNTL[icntl].
Logically collective.
SEE ALSO:
Working with PETSc options, MatMumpsGetCntl
Source code at petsc4py/PETSc/Mat.pyx:5096
Parameters
icntl (int)
Return type
float
getMumpsIcntl(icntl)
Return the MUMPS parameter, ICNTL[icntl].
Logically collective.
SEE ALSO:
Working with PETSc options, MatMumpsGetIcntl
Source code at petsc4py/PETSc/Mat.pyx:5060
Parameters
icntl (int)
Return type
int
getMumpsInfo(icntl)
Return the MUMPS parameter, INFO[icntl].
Logically collective.
Parameters
icntl (int) -- The index of the MUMPS INFO array.
Return type
int
SEE ALSO:
MatMumpsGetInfo
Source code at petsc4py/PETSc/Mat.pyx:5111
getMumpsInfog(icntl)
Return the MUMPS parameter, INFOG[icntl].
Logically collective.
Parameters
icntl (int) -- The index of the MUMPS INFOG array.
Return type
int
SEE ALSO:
MatMumpsGetInfog
Source code at petsc4py/PETSc/Mat.pyx:5131
getMumpsRinfo(icntl)
Return the MUMPS parameter, RINFO[icntl].
Logically collective.
Parameters
icntl (int) -- The index of the MUMPS RINFO array.
Return type
float
SEE ALSO:
MatMumpsGetRinfo
Source code at petsc4py/PETSc/Mat.pyx:5151
getMumpsRinfog(icntl)
Return the MUMPS parameter, RINFOG[icntl].
Logically collective.
Parameters
icntl (int) -- The index of the MUMPS RINFOG array.
Return type
float
SEE ALSO:
MatMumpsGetRinfog
Source code at petsc4py/PETSc/Mat.pyx:5171
getNearNullSpace()
Return the near-nullspace.
Not collective.
SEE ALSO:
getNullSpace, setNearNullSpace, MatSetNearNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3686
Return type
NullSpace
getNestISs()
Return the index sets representing the row and column spaces.
Not collective.
SEE ALSO:
MatNestGetISs
Source code at petsc4py/PETSc/Mat.pyx:5502
Return type
tuple[list[IS], list[IS]]
getNestLocalISs()
Return the local index sets representing the row and column spaces.
Not collective.
SEE ALSO:
MatNestGetLocalISs
Source code at petsc4py/PETSc/Mat.pyx:5523
Return type
tuple[list[IS], list[IS]]
getNestSize()
Return the number of rows and columns of the matrix.
Not collective.
SEE ALSO:
MatNestGetSize
Source code at petsc4py/PETSc/Mat.pyx:5488
Return type
tuple[int, int]
getNestSubMatrix(i, j)
Return a single submatrix.
Not collective.
Parameters
• i (int) -- The first index of the matrix within the nesting.
• j (int) -- The second index of the matrix within the nesting.
Return type
Mat
SEE ALSO:
MatNestGetSubMat
Source code at petsc4py/PETSc/Mat.pyx:5544
getNullSpace()
Return the nullspace.
Not collective.
SEE ALSO:
setNullSpace, MatGetNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3632
Return type
NullSpace
getOption(option)
Return the option value.
Not collective.
SEE ALSO:
setOption, MatGetOption
Source code at petsc4py/PETSc/Mat.pyx:1802
Parameters
option (Option)
Return type
bool
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, MatGetOptionsPrefix
Source code at petsc4py/PETSc/Mat.pyx:1737
Return type
str
getOrdering(ord_type)
Return a reordering for a matrix to improve a LU factorization.
Collective.
Parameters
ord_type (OrderingType) -- The type of reordering.
Returns
• rp (IS) -- The row permutation indices.
• cp (IS) -- The column permutation indices.
Return type
tuple[IS, IS]
SEE ALSO:
MatGetOrdering
Source code at petsc4py/PETSc/Mat.pyx:4556
getOwnershipIS()
Return the ranges of rows and columns owned by each process as index sets.
Not collective.
SEE ALSO:
getOwnershipRanges, getOwnershipRangesColumn, MatGetOwnershipIS
Source code at petsc4py/PETSc/Mat.pyx:1969
Return type
tuple[IS, IS]
getOwnershipRange()
Return the locally owned range of rows.
Not collective.
SEE ALSO:
getOwnershipRanges, getOwnershipRangeColumn, MatGetOwnershipRange
Source code at petsc4py/PETSc/Mat.pyx:1902
Return type
tuple[int, int]
getOwnershipRangeColumn()
Return the locally owned range of columns.
Not collective.
SEE ALSO:
getOwnershipRangesColumn, getOwnershipRange, MatGetOwnershipRangeColumn
Source code at petsc4py/PETSc/Mat.pyx:1936
Return type
tuple[int, int]
getOwnershipRanges()
Return the range of rows owned by each process.
Not collective.
The returned array is the result of exclusive scan of the local sizes.
SEE ALSO:
getOwnershipRange, MatGetOwnershipRanges
Source code at petsc4py/PETSc/Mat.pyx:1916
Return type
ArrayInt
getOwnershipRangesColumn()
Return the range of columns owned by each process.
Not collective.
SEE ALSO:
getOwnershipRangeColumn, MatGetOwnershipRangesColumn
Source code at petsc4py/PETSc/Mat.pyx:1951
Return type
ArrayInt
getPythonContext()
Return the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python matrix type, setPythonContext
Source code at petsc4py/PETSc/Mat.pyx:1671
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the matrix.
Not collective.
SEE ALSO:
PETSc Python matrix type, setPythonContext, setPythonType, MatPythonGetType
Source code at petsc4py/PETSc/Mat.pyx:1706
Return type
str
getRedundantMatrix(nsubcomm, subcomm=None, out=None)
Return redundant matrices on subcommunicators.
Collective.
Parameters
• nsubcomm (int) -- The number of subcommunicators.
• subcomm (Comm | None) -- Communicator split or None for the null communicator.
• out (Mat | None) -- Optional resultant matrix. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When not None, the matrix is reused with
MAT_REUSE_MATRIX.
Return type
Mat
SEE ALSO:
MatCreateRedundantMatrix
Source code at petsc4py/PETSc/Mat.pyx:3483
getRow(row)
Return the column indices and values for the requested row.
Not collective.
SEE ALSO:
MatGetRow
Source code at petsc4py/PETSc/Mat.pyx:2467
Parameters
row (int)
Return type
tuple[ArrayInt, ArrayScalar]
getRowIJ(symmetric=False, compressed=False)
Return the CSR representation of the local sparsity pattern.
Collective.
Parameters
• symmetric (bool) -- If True, return the symmetrized graph.
• compressed (bool) -- If True, return the compressed graph.
Return type
tuple[ArrayInt, ArrayInt]
SEE ALSO:
MatGetRowIJ
Source code at petsc4py/PETSc/Mat.pyx:2487
getRowSum(result=None)
Return the row-sum vector.
Collective.
Parameters
result (Vec | None) -- Optional vector to store the result.
Return type
Vec
SEE ALSO:
MatGetRowSum
Source code at petsc4py/PETSc/Mat.pyx:3535
getSchurComplementSubMatrices()
Return Schur complement sub-matrices.
Collective.
SEE ALSO:
MatSchurComplementGetSubMatrices
Source code at petsc4py/PETSc/Mat.pyx:4003
Return type
tuple[Mat, Mat, Mat, Mat, Mat]
getSize()
Return the global number of rows and columns.
Not collective.
SEE ALSO:
getLocalSize, getSizes, MatGetSize
Source code at petsc4py/PETSc/Mat.pyx:1830
Return type
tuple[int, int]
getSizes()
Return the tuple of matrix layouts.
Not collective.
SEE ALSO:
getLocalSize, getSize
Source code at petsc4py/PETSc/Mat.pyx:1858
Return type
tuple[LayoutSizeSpec, LayoutSizeSpec]
getTransposeNullSpace()
Return the transpose nullspace.
Not collective.
SEE ALSO:
getNullSpace, setTransposeNullSpace, MatGetTransposeNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3659
Return type
NullSpace
getType()
Return the type of the matrix.
Not collective.
SEE ALSO:
setType, Type, MatGetType
Source code at petsc4py/PETSc/Mat.pyx:1816
Return type
str
getValue(row, col)
Return the value in the (row, col) position.
Not collective.
SEE ALSO:
MatGetValues
Source code at petsc4py/PETSc/Mat.pyx:2392
Return type
Scalar
getValues(rows, cols, values=None)
Return the values in the zip(rows, cols) positions.
Not collective.
Parameters
• rows (Sequence[int]) -- Row indices.
• cols (Sequence[int]) -- Column indices.
• values (ArrayScalar) -- Optional array where to store the values.
Return type
ArrayScalar
SEE ALSO:
MatGetValues
Source code at petsc4py/PETSc/Mat.pyx:2408
getValuesCSR()
Return the CSR representation of the local part of the matrix.
Not collective.
SEE ALSO:
MatGetRow
Source code at petsc4py/PETSc/Mat.pyx:2429
Return type
tuple[ArrayInt, ArrayInt, ArrayScalar]
getVecType()
Return the vector type used by the matrix.
Not collective.
SEE ALSO:
setVecType, MatGetVecType
Source code at petsc4py/PETSc/Mat.pyx:658
Return type
str
hermitianTranspose(out=None)
Return the transposed Hermitian matrix.
Collective.
Parameters
out (Mat | None) -- Optional return matrix. If None, inplace transposition is
performed. Otherwise, the matrix is reused.
Return type
Mat
SEE ALSO:
MatHermitianTranspose
Source code at petsc4py/PETSc/Mat.pyx:2142
imagPart(out=None)
Return the imaginary part of the matrix.
Collective.
Parameters
out (Mat | None) -- Optional return matrix. If None, the operation is performed
in-place. Otherwise, the operation is performed on out.
Return type
Mat
SEE ALSO:
realPart, conjugate, MatImaginaryPart
Source code at petsc4py/PETSc/Mat.pyx:2192
increaseOverlap(iset, overlap=1)
Increase the overlap of a index set.
Collective.
SEE ALSO:
MatIncreaseOverlap
Source code at petsc4py/PETSc/Mat.pyx:3869
Parameters
• iset (IS)
• overlap (int)
Return type
None
invertBlockDiagonal()
Return the inverse of the block-diagonal entries.
Collective.
SEE ALSO:
MatInvertBlockDiagonal
Source code at petsc4py/PETSc/Mat.pyx:3599
Return type
ArrayScalar
isAssembled()
The boolean flag indicating if the matrix is assembled.
Not collective.
SEE ALSO:
assemble, MatAssembled
Source code at petsc4py/PETSc/Mat.pyx:3357
Return type
bool
isHermitian(tol=0)
Return the boolean indicating if the matrix is Hermitian.
Collective.
Parameters
tol (float) -- Tolerance for comparison.
Return type
bool
SEE ALSO:
MatIsHermitian
Source code at petsc4py/PETSc/Mat.pyx:2331
isHermitianKnown()
Return the 2-tuple indicating if the matrix is known to be Hermitian.
Not collective.
SEE ALSO:
MatIsHermitianKnown
Source code at petsc4py/PETSc/Mat.pyx:2351
Return type
tuple[bool, bool]
isStructurallySymmetric()
Return the boolean indicating if the matrix is structurally symmetric.
Not collective.
SEE ALSO:
MatIsStructurallySymmetric
Source code at petsc4py/PETSc/Mat.pyx:2366
Return type
bool
isSymmetric(tol=0)
Return the boolean indicating if the matrix is symmetric.
Collective.
Parameters
tol (float) -- Tolerance for comparison.
Return type
bool
SEE ALSO:
MatIsSymmetric
Source code at petsc4py/PETSc/Mat.pyx:2296
isSymmetricKnown()
Return the 2-tuple indicating if the matrix is known to be symmetric.
Not collective.
SEE ALSO:
MatIsSymmetricKnown
Source code at petsc4py/PETSc/Mat.pyx:2316
Return type
tuple[bool, bool]
isTranspose(mat=None, tol=0)
Return the result of matrix comparison with transposition.
Collective.
Parameters
• mat (Mat | None) -- Matrix to compare against. Uses self if None.
• tol (float) -- Tolerance for comparison.
Return type
bool
SEE ALSO:
MatIsTranspose
Source code at petsc4py/PETSc/Mat.pyx:2273
kron(mat, result=None)
Compute C, the Kronecker product of A and B.
Collective.
Parameters
• mat (Mat) -- The right hand matrix B.
• result (Mat | None) -- The optional resultant matrix. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When it is not None, the matrix is reused
with MAT_REUSE_MATRIX.
Returns
result -- The resultant matrix C, the Kronecker product of A and B.
Return type
Mat
SEE ALSO:
MatSeqAIJKron, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4485
load(viewer)
Load a matrix.
Collective.
SEE ALSO:
MatLoad
Source code at petsc4py/PETSc/Mat.pyx:2053
Parameters
viewer (Viewer)
Return type
Self
matMatMult(B, C, result=None, fill=None)
Perform matrix-matrix-matrix multiplication D=ABC.
Neighborwise collective.
Parameters
• B (Mat) -- The middle matrix B.
• C (Mat) -- The right hand matrix C.
• result (Mat | None) -- The optional resultant matrix D. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When D is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/nnz(A), use None if you do
not have a good estimate. If the result is a dense matrix this is irrelevant.
Returns
result -- The resultant product matrix D.
Return type
Mat
SEE ALSO:
MatMatMatMult, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4440
matMult(mat, result=None, fill=None)
Perform matrix-matrix multiplication C=AB.
Neighborwise collective.
Parameters
• mat (Mat) -- The right hand matrix B.
• result (Mat | None) -- The optional resultant matrix C. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When C is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/(nnz(A) + nnz(B)), use ‐
None if you do not have a good estimate. If the result is a dense matrix this is
irrelevant.
Returns
result -- The resultant product matrix C.
Return type
Mat
Notes
To determine the correct fill value, run with -info and search for the string "Fill ratio"
to see the value actually needed.
SEE ALSO:
MatMatMult, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4201
matSolve(B, X)
Solve AX=B, given a factored matrix A.
Neighborwise collective.
Parameters
• B (Mat) -- The right-hand side matrix of type Type.DENSE. Can be of type Type.AIJ
if using MUMPS.
• X (Mat) -- The output solution matrix, must be different than B.
Return type
None
SEE ALSO:
KSP.create, MatMatSolve
Source code at petsc4py/PETSc/Mat.pyx:5321
matTransposeMult(mat, result=None, fill=None)
Perform matrix-matrix multiplication C=ABᵀ.
Neighborwise collective.
Parameters
• mat (Mat) -- The right hand matrix B.
• result (Mat | None) -- The optional resultant matrix C. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When C is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/(nnz(A) + nnz(B)), use ‐
None if you do not have a good estimate. If the result is a dense matrix this is
irrelevant.
Returns
result -- The resultant product matrix C.
Return type
Mat
Notes
To determine the correct fill value, run with -info and search for the string "Fill ratio"
to see the value actually needed.
SEE ALSO:
MatMatTransposeMult, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4248
mult(x, y)
Perform the matrix vector product y = A @ x.
Collective.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMult
Source code at petsc4py/PETSc/Mat.pyx:3703
multAdd(x, v, y)
Perform the matrix vector product with addition y = A @ x + v.
Collective.
Parameters
• x (Vec) -- The input vector for the matrix-vector product.
• v (Vec) -- The input vector to be added to.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMultAdd
Source code at petsc4py/PETSc/Mat.pyx:3722
multHermitian(x, y)
Perform the Hermitian matrix vector product y = A^H @ x.
Collective.
Parameters
• x (Vec) -- The input vector for the Hermitian matrix-vector product.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMultHermitianTranspose
Source code at petsc4py/PETSc/Mat.pyx:3783
multHermitianAdd(x, v, y)
Perform the Hermitian matrix vector product with addition y = A^H @ x + v.
Collective.
Parameters
• x (Vec) -- The input vector for the Hermitian matrix-vector product.
• v (Vec) -- The input vector to be added to.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMultHermitianTransposeAdd
Source code at petsc4py/PETSc/Mat.pyx:3802
multTranspose(x, y)
Perform the transposed matrix vector product y = A^T @ x.
Collective.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMultTranspose
Source code at petsc4py/PETSc/Mat.pyx:3743
multTransposeAdd(x, v, y)
Perform the transposed matrix vector product with addition y = A^T @ x + v.
Collective.
Parameters
• x (Vec) -- The input vector for the transposed matrix-vector product.
• v (Vec) -- The input vector to be added to.
• y (Vec) -- The output vector.
Return type
None
SEE ALSO:
MatMultTransposeAdd
Source code at petsc4py/PETSc/Mat.pyx:3762
norm(norm_type=None)
Compute the requested matrix norm.
Collective.
A 2-tuple is returned if NormType.NORM_1_AND_2 is specified.
SEE ALSO:
MatNorm, NormType
Source code at petsc4py/PETSc/Mat.pyx:4073
Parameters
norm_type (NormTypeSpec)
Return type
float | tuple[float, float]
permute(row, col)
Return the permuted matrix.
Collective.
Parameters
• row (IS) -- Row permutation.
• col (IS) -- Column permutation.
Return type
Mat
SEE ALSO:
MatPermute
Source code at petsc4py/PETSc/Mat.pyx:2238
preallocatorPreallocate(A, fill=True)
Preallocate memory for a matrix using a preallocator matrix.
Collective.
The current matrix (self) must be of type Type.PREALLOCATOR.
Parameters
• A (Mat) -- The matrix to be preallocated.
• fill (bool) -- Flag indicating whether or not to insert zeros into the newly
allocated matrix, defaults to True.
Return type
None
SEE ALSO:
MatPreallocatorPreallocate
Source code at petsc4py/PETSc/Mat.pyx:933
ptap(P, result=None, fill=None)
Creates the matrix product C = PᵀAP.
Neighborwise collective.
Parameters
• P (Mat) -- The matrix P.
• result (Mat | None) -- The optional resultant matrix C. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When C is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/(nnz(A) + nnz(P)), use ‐
None if you do not have a good estimate. If the result is a dense matrix this is
irrelevant.
Returns
result -- The resultant product matrix C.
Return type
Mat
Notes
To determine the correct fill value, run with -info and search for the string "Fill ratio"
to see the value actually needed.
An alternative approach to this function is to use MatProductCreate and set the desired
options before the computation is done.
SEE ALSO:
MatPtAP, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4342
rart(R, result=None, fill=None)
Create the matrix product C = RARᵀ.
Neighborwise collective.
Parameters
• R (Mat) -- The projection matrix.
• result (Mat | None) -- The optional resultant matrix C. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When C is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/nnz(A), use None if you do
not have a good estimate. If the result is a dense matrix this is irrelevant.
Returns
result -- The resultant product matrix C.
Return type
Mat
Notes
To determine the correct fill value, run with -info and search for the string "Fill ratio"
to see the value actually needed.
SEE ALSO:
MatRARt, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4393
realPart(out=None)
Return the real part of the matrix.
Collective.
Parameters
out (Mat | None) -- Optional return matrix. If None, the operation is performed
in-place. Otherwise, the operation is performed on out.
Return type
Mat
SEE ALSO:
imagPart, conjugate, MatRealPart
Source code at petsc4py/PETSc/Mat.pyx:2169
reorderForNonzeroDiagonal(isrow, iscol, atol=0)
Change a matrix ordering to remove zeros from the diagonal.
Collective.
Parameters
• isrow (IS) -- The row reordering.
• iscol (IS) -- The column reordering.
• atol (float) -- The absolute tolerance. Values along the diagonal whose absolute
value are smaller than this tolerance are moved off the diagonal.
Return type
None
SEE ALSO:
getOrdering, MatReorderForNonzeroDiagonal
Source code at petsc4py/PETSc/Mat.pyx:4584
restoreDenseColumnVec(i, mode='rw')
Restore the iᵗʰ column vector of the dense matrix.
Collective.
Parameters
• i (int) -- The column index to be restored.
• mode (AccessModeSpec) -- The access type of the restored array
Return type
None
SEE ALSO:
getDenseColumnVec, MatDenseRestoreColumnVec, MatDenseRestoreColumnVecRead, ‐
MatDenseRestoreColumnVecWrite
Source code at petsc4py/PETSc/Mat.pyx:5460
restoreISLocalMat(local)
Restore the local matrix obtained with getISLocalMat.
Not collective.
Parameters
local (Mat) -- The local matrix.
Return type
None
SEE ALSO:
MatISRestoreLocalMat
Source code at petsc4py/PETSc/Mat.pyx:4851
restoreLocalSubMatrix(isrow, iscol, submat)
Restore a reference to a submatrix obtained with getLocalSubMatrix.
Collective.
Parameters
• isrow (IS) -- Row index set.
• iscol (IS) -- Column index set.
• submat (Mat) -- The submatrix.
Return type
None
SEE ALSO:
getLocalSubMatrix, MatRestoreLocalSubMatrix
Source code at petsc4py/PETSc/Mat.pyx:4050
retrieveValues()
Retrieve a copy of the matrix values previously stored with storeValues.
Collective.
SEE ALSO:
storeValues, MatRetrieveValues
Source code at petsc4py/PETSc/Mat.pyx:3290
Return type
None
scale(alpha)
Scale the matrix.
Collective.
SEE ALSO:
MatScale
Source code at petsc4py/PETSc/Mat.pyx:4095
Parameters
alpha (Scalar)
Return type
None
setBlockSize(bsize)
Set the matrix block size (same for rows and columns).
Logically collective.
Parameters
bsize (int) -- Block size.
Return type
None
SEE ALSO:
setBlockSizes, setSizes, MatSetBlockSize
Source code at petsc4py/PETSc/Mat.pyx:586
setBlockSizes(row_bsize, col_bsize)
Set the row and column block sizes.
Logically collective.
Parameters
• row_bsize (int) -- Row block size.
• col_bsize (int) -- Column block size.
Return type
None
SEE ALSO:
setBlockSize, setSizes, MatSetBlockSizes
Source code at petsc4py/PETSc/Mat.pyx:604
setDM(dm)
Set the DM defining the data layout of the matrix.
Not collective.
Parameters
dm (DM) -- The DM.
Return type
None
SEE ALSO:
MatSetDM
Source code at petsc4py/PETSc/Mat.pyx:5587
setDenseLDA(lda)
Set the leading dimension of the array used by the dense matrix.
Not collective.
Parameters
lda (int) -- The leading dimension.
Return type
None
SEE ALSO:
MatDenseSetLDA
Source code at petsc4py/PETSc/Mat.pyx:5343
setDiagonal(diag, addv=None)
Set the diagonal values of the matrix.
Collective.
Parameters
• diag (Vec) -- Vector storing diagonal values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
getDiagonal, MatDiagonalSet
Source code at petsc4py/PETSc/Mat.pyx:3557
setFromOptions()
Configure the matrix from the options database.
Collective.
SEE ALSO:
Working with PETSc options, MatSetFromOptions
Source code at petsc4py/PETSc/Mat.pyx:1765
Return type
None
setISAllowRepeated(allow=True)
Allow repeated entries in the local to global map.
Logically collective.
Parameters
allow (bool) -- When True, local dofs are allowed to map to the same global dof.
Return type
None
SEE ALSO:
getISAllowRepeated, MatISSetAllowRepeated
Source code at petsc4py/PETSc/Mat.pyx:4785
setISLocalMat(local)
Set the local matrix stored inside a Type.IS.
Not collective.
Parameters
local (Mat) -- The local matrix.
Return type
None
SEE ALSO:
MatISSetLocalMat
Source code at petsc4py/PETSc/Mat.pyx:4868
setISPreallocation(nnz, onnz)
Preallocate memory for a Type.IS parallel matrix.
Collective.
Parameters
• nnz (Sequence[int]) -- The sequence whose length corresponds to the number of
local rows and values which represent the number of nonzeros in the various rows
of the diagonal of the local submatrix.
• onnz (Sequence[int]) -- The sequence whose length corresponds to the number of
local rows and values which represent the number of nonzeros in the various rows
of the off-diagonal of the local submatrix.
Return type
Self
SEE ALSO:
MatISSetPreallocation
Source code at petsc4py/PETSc/Mat.pyx:4885
setLGMap(rmap, cmap=None)
Set the local-to-global mappings.
Collective.
Parameters
• rmap (LGMap) -- Row mapping.
• cmap (LGMap | None) -- Column mapping. If None, cmap = rmap.
Return type
None
SEE ALSO:
getLGMap, MatSetLocalToGlobalMapping
Source code at petsc4py/PETSc/Mat.pyx:2764
setLRCMats(A, U, c=None, V=None)
Set the constituents of a Type.LRC matrix.
Logically collective.
Parameters
• A (Mat) -- The A matrix, or None to omit A.
• U (Mat) -- The first dense rectangular matrix.
• c (Vec) -- The sequential vector containing the diagonal of C, or None for all
ones.
• V (Mat) -- The second dense rectangular matrix, or None for a copy of U.
Return type
None
SEE ALSO:
MatLRCSetMats
Source code at petsc4py/PETSc/Mat.pyx:4950
setMumpsCntl(icntl, val)
Set a MUMPS parameter, CNTL[icntl] = val.
Logically collective.
Parameters
• icntl (int) -- The index of the MUMPS parameter array.
• val (float) -- The value to set.
Return type
None
SEE ALSO:
Working with PETSc options, MatMumpsSetCntl
Source code at petsc4py/PETSc/Mat.pyx:5075
setMumpsIcntl(icntl, ival)
Set a MUMPS parameter, ICNTL[icntl] = ival.
Logically collective.
Parameters
• icntl (int) -- The index of the MUMPS parameter array.
• ival (int) -- The value to set.
Return type
None
SEE ALSO:
Working with PETSc options, MatMumpsSetIcntl
Source code at petsc4py/PETSc/Mat.pyx:5039
setNearNullSpace(nsp)
Set the near-nullspace.
Collective.
SEE ALSO:
setNullSpace, getNearNullSpace, MatSetNearNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3674
Parameters
nsp (NullSpace)
Return type
None
setNestVecType(vec_type)
Set the vector type for a Type.NEST matrix.
Collective.
Parameters
vec_type (Type | str) -- Vector type used when creating vectors with createVecs.
Return type
None
SEE ALSO:
getVecType, MatNestSetVecType
Source code at petsc4py/PETSc/Mat.pyx:672
setNullSpace(nsp)
Set the nullspace.
Collective.
SEE ALSO:
getNullSpace, MatSetNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3620
Parameters
nsp (NullSpace)
Return type
None
setOption(option, flag)
Set option.
Collective.
SEE ALSO:
getOption, MatSetOption
Source code at petsc4py/PETSc/Mat.pyx:1790
Parameters
• option (Option)
• flag (bool)
Return type
None
setOptionsPrefix(prefix=None)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, getOptionsPrefix, MatSetOptionsPrefix
Source code at petsc4py/PETSc/Mat.pyx:1723
Parameters
prefix (str | None)
Return type
None
setPreallocationCSR(csr)
Preallocate memory for the matrix with a CSR layout.
Collective.
Correct preallocation can result in a dramatic reduction in matrix assembly time.
Parameters
csr (CSRIndicesSpec) -- Local matrix data in compressed sparse row layout format.
Return type
Self
Notes
Must use the block-compressed form with Type.BAIJ and Type.SBAIJ.
SEE ALSO:
setPreallocationNNZ, createAIJ, createBAIJ, createSBAIJ, MatSeqAIJSetPreallocationCSR, ‐
MatMPIAIJSetPreallocationCSR, MatSeqBAIJSetPreallocationCSR, ‐
MatMPIBAIJSetPreallocationCSR, MatSeqSBAIJSetPreallocationCSR, ‐
MatMPISBAIJSetPreallocationCSR
Source code at petsc4py/PETSc/Mat.pyx:899
setPreallocationDense(array)
Set the array used for storing matrix elements for a dense matrix.
Collective.
Parameters
array (Sequence[Scalar]) -- Array that will be used to store matrix data.
Return type
Self
SEE ALSO:
MatSeqDenseSetPreallocation, MatMPIDenseSetPreallocation
Source code at petsc4py/PETSc/Mat.pyx:1140
setPreallocationNNZ(nnz)
Preallocate memory for the matrix with a non-zero pattern.
Collective.
Correct preallocation can result in a dramatic reduction in matrix assembly time.
Parameters
nnz (NNZSpec) -- The number of non-zeros per row for the local portion of the
matrix, or a 2-tuple for the on-process and off-process part of the matrix.
Return type
Self
SEE ALSO:
setPreallocationCSR, createAIJ, MatSeqAIJSetPreallocation, MatMPIAIJSetPreallocation
Source code at petsc4py/PETSc/Mat.pyx:873
setPythonContext(context)
Set the instance of the class implementing the required Python methods.
Logically collective.
Notes
In order to use the matrix, Mat.setUp must be called after having set the context. Pass ‐
None to reset the matrix to its initial state.
SEE ALSO:
PETSc Python matrix type, getPythonContext, setPythonType
Source code at petsc4py/PETSc/Mat.pyx:1654
Parameters
context (Any)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
Notes
In order to use the matrix, Mat.setUp must be called after having set the type.
SEE ALSO:
PETSc Python matrix type, setPythonContext, getPythonType, MatPythonSetType
Source code at petsc4py/PETSc/Mat.pyx:1686
Parameters
py_type (str)
Return type
None
setRandom(random=None)
Set random values in the matrix.
Collective.
Parameters
random (Random | None) -- The random number generator object or None for the
default.
Return type
None
SEE ALSO:
MatSetRandom
Source code at petsc4py/PETSc/Mat.pyx:4134
setSizes(size, bsize=None)
Set the local, global and block sizes.
Collective.
Parameters
• size (MatSizeSpec) -- Matrix size.
• bsize (MatBlockSizeSpec | None) -- Matrix block size. If None, a block size of 1
is set.
Return type
None
Examples
Create a Mat with n rows and columns and the same local and global sizes.
>>> mat = PETSc.Mat().create()
>>> mat.setFromOptions()
>>> mat.setSizes(n)
Create a Mat with nr rows, nc columns and the same local and global sizes.
>>> mat = PETSc.Mat().create()
>>> mat.setFromOptions()
>>> mat.setSizes([nr, nc])
Create a Mat with nrl local rows, nrg global rows, ncl local columns and ncg global
columns.
>>> mat = PETSc.Mat().create()
>>> mat.setFromOptions()
>>> mat.setSizes([[nrl, nrg], [ncl, ncg]])
SEE ALSO:
setBlockSize, setBlockSizes, MatSetSizes, MatSetBlockSize, MatSetBlockSizes
Source code at petsc4py/PETSc/Mat.pyx:533
setStencil(dims, starts=None, dof=1)
Set matrix stencil.
Not collective.
SEE ALSO:
MatSetStencil
Source code at petsc4py/PETSc/Mat.pyx:3022
Parameters
• dims (DimsSpec)
• starts (DimsSpec | None)
• dof (int)
Return type
None
setTransposeNullSpace(nsp)
Set the transpose nullspace.
Collective.
SEE ALSO:
setNullSpace, getTransposeNullSpace, MatSetTransposeNullSpace
Source code at petsc4py/PETSc/Mat.pyx:3647
Parameters
nsp (NullSpace)
Return type
None
setTransposePrecursor(out)
Set transpose precursor.
Logically collective.
SEE ALSO:
MatTransposeSetPrecursor
Source code at petsc4py/PETSc/Mat.pyx:2130
Parameters
out (Mat)
Return type
None
setType(mat_type)
Set the matrix type.
Collective.
Parameters
mat_type (Type | str) -- The matrix type.
Return type
None
SEE ALSO:
create, getType, MatSetType
Source code at petsc4py/PETSc/Mat.pyx:514
setUnfactored()
Set a factored matrix to be treated as unfactored.
Logically collective.
SEE ALSO:
MatSetUnfactored
Source code at petsc4py/PETSc/Mat.pyx:4771
Return type
None
setUp()
Set up the internal data structures for using the matrix.
Collective.
SEE ALSO:
MatSetUp
Source code at petsc4py/PETSc/Mat.pyx:1777
Return type
Self
setValue(row, col, value, addv=None)
Set a value to the (row, col) entry of the matrix.
Not collective.
Parameters
• row (int) -- Row index.
• col (int) -- Column index.
• value (Scalar) -- The scalar value.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValues
Source code at petsc4py/PETSc/Mat.pyx:2548
setValueBlockedStagStencil(row, col, value, addv=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:3106
Return type
None
setValueBlockedStencil(row, col, value, addv=None)
Set a block of values to row and col stencil.
Not collective.
Parameters
• row (Stencil) -- Row stencil.
• col (Stencil) -- Column stencil.
• value (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesBlockedStencil
Source code at petsc4py/PETSc/Mat.pyx:3076
setValueLocal(row, col, value, addv=None)
Set a value to the (row, col) entry of the matrix in local ordering.
Not collective.
Parameters
• row (int) -- Local row index.
• col (int) -- Local column index.
• value (Scalar) -- The scalar value.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesLocal
Source code at petsc4py/PETSc/Mat.pyx:2801
setValueStagStencil(row, col, value, addv=None)
Not implemented.
Source code at petsc4py/PETSc/Mat.pyx:3072
Return type
None
setValueStencil(row, col, value, addv=None)
Set a value to row and col stencil.
Not collective.
Parameters
• row (Stencil) -- Row stencil.
• col (Stencil) -- Column stencil.
• value (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesStencil
Source code at petsc4py/PETSc/Mat.pyx:3042
setValues(rows, cols, values, addv=None)
Set values to the rows ⊗ cols entries of the matrix.
Not collective.
Parameters
• rows (Sequence[int]) -- Row indices.
• cols (Sequence[int]) -- Column indices.
• values (Sequence[Scalar]) -- The scalar values. A sequence of length at least
len(rows) * len(cols).
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValues
Source code at petsc4py/PETSc/Mat.pyx:2580
setValuesBlocked(rows, cols, values, addv=None)
Set values to the rows ⊗ col block entries of the matrix.
Not collective.
Parameters
• rows (Sequence[int]) -- Block row indices.
• cols (Sequence[int]) -- Block column indices.
• values (Sequence[Scalar]) -- The scalar values. A sequence of length at least
len(rows) * len(cols) * bs * bs, where bs is the block size of the matrix.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesBlocked
Source code at petsc4py/PETSc/Mat.pyx:2671
setValuesBlockedCSR(I, J, V, addv=None)
Set values stored in block CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Block row pointers.
• J (Sequence[int]) -- Block column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesBlocked
Source code at petsc4py/PETSc/Mat.pyx:2736
setValuesBlockedIJV(I, J, V, addv=None, rowmap=None)
Set a subset of values stored in block CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Block row pointers.
• J (Sequence[int]) -- Block column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
• rowmap (Sequence[int]) -- Optional iterable indicating which block row to insert.
Return type
None
SEE ALSO:
MatSetValuesBlocked
Source code at petsc4py/PETSc/Mat.pyx:2705
setValuesBlockedLocal(rows, cols, values, addv=None)
Set values to the rows ⊗ col block entries of the matrix in local ordering.
Not collective.
Parameters
• rows (Sequence[int]) -- Local block row indices.
• cols (Sequence[int]) -- Local block column indices.
• values (Sequence[Scalar]) -- The scalar values. A sequence of length at least
len(rows) * len(cols) * bs * bs, where bs is the block size of the matrix.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesBlockedLocal
Source code at petsc4py/PETSc/Mat.pyx:2925
setValuesBlockedLocalCSR(I, J, V, addv=None)
Set values stored in block CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Block row pointers.
• J (Sequence[int]) -- Local block column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesBlockedLocal
Source code at petsc4py/PETSc/Mat.pyx:2990
setValuesBlockedLocalIJV(I, J, V, addv=None, rowmap=None)
Set a subset of values stored in block CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Block row pointers.
• J (Sequence[int]) -- Local block column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
• rowmap (Sequence[int]) -- Optional iterable indicating which block row to insert.
Return type
None
SEE ALSO:
MatSetValuesBlockedLocal
Source code at petsc4py/PETSc/Mat.pyx:2959
setValuesBlockedLocalRCV(R, C, V, addv=None)
Undocumented.
Source code at petsc4py/PETSc/Mat.pyx:2955
Return type
None
setValuesBlockedRCV(R, C, V, addv=None)
Undocumented.
Source code at petsc4py/PETSc/Mat.pyx:2701
Return type
None
setValuesCSR(I, J, V, addv=None)
Set values stored in CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Row pointers.
• J (Sequence[int]) -- Column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValues
Source code at petsc4py/PETSc/Mat.pyx:2643
setValuesIJV(I, J, V, addv=None, rowmap=None)
Set a subset of values stored in CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Row pointers.
• J (Sequence[int]) -- Column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
• rowmap (Sequence[int]) -- Optional iterable indicating which row to insert.
Return type
None
SEE ALSO:
MatSetValues
Source code at petsc4py/PETSc/Mat.pyx:2612
setValuesLocal(rows, cols, values, addv=None)
Set values to the rows ⊗ col entries of the matrix in local ordering.
Not collective.
Parameters
• rows (Sequence[int]) -- Local row indices.
• cols (Sequence[int]) -- Local column indices.
• values (Sequence[Scalar]) -- The scalar values. A sequence of length at least
len(rows) * len(cols).
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesLocal
Source code at petsc4py/PETSc/Mat.pyx:2834
setValuesLocalCSR(I, J, V, addv=None)
Set values stored in CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Row pointers.
• J (Sequence[int]) -- Local column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
MatSetValuesLocal
Source code at petsc4py/PETSc/Mat.pyx:2897
setValuesLocalIJV(I, J, V, addv=None, rowmap=None)
Set a subset of values stored in CSR format.
Not collective.
Parameters
• I (Sequence[int]) -- Row pointers.
• J (Sequence[int]) -- Local column indices.
• V (Sequence[Scalar]) -- The scalar values.
• addv (InsertModeSpec) -- Insertion mode.
• rowmap (Sequence[int]) -- Optional iterable indicating which row to insert.
Return type
None
SEE ALSO:
MatSetValuesLocal
Source code at petsc4py/PETSc/Mat.pyx:2866
setValuesLocalRCV(R, C, V, addv=None)
Undocumented.
Source code at petsc4py/PETSc/Mat.pyx:2862
Return type
None
setValuesRCV(R, C, V, addv=None)
Undocumented.
Source code at petsc4py/PETSc/Mat.pyx:2608
Return type
None
setVariableBlockSizes(blocks)
Set diagonal point-blocks of the matrix.
Not collective.
SEE ALSO:
setBlockSize, MatSetVariableBlockSizes
Source code at petsc4py/PETSc/Mat.pyx:625
Parameters
blocks (Sequence[int])
Return type
None
setVecType(vec_type)
Set the vector type.
Collective.
Parameters
vec_type (Type | str) -- Vector type used when creating vectors with createVecs.
Return type
None
SEE ALSO:
getVecType, MatSetVecType
Source code at petsc4py/PETSc/Mat.pyx:639
shift(alpha)
Shift the matrix.
Collective.
SEE ALSO:
MatShift
Source code at petsc4py/PETSc/Mat.pyx:4108
Parameters
alpha (Scalar)
Return type
None
solve(b, x)
Solve Ax=b, given a factored matrix.
Neighborwise collective.
The vectors b and x cannot be the same. Most users should employ the KSP interface for
linear solvers instead of working directly with matrix algebra routines.
Parameters
• b (Vec) -- The right-hand side vector.
• x (Vec) -- The output solution vector, must be different than b.
Return type
None
SEE ALSO:
KSP.create, solveTranspose, MatSolve
Source code at petsc4py/PETSc/Mat.pyx:5231
solveAdd(b, y, x)
Solve x=y+A⁻¹b, given a factored matrix.
Neighborwise collective.
The vectors b and x cannot be the same.
Parameters
• b (Vec) -- The right-hand side vector.
• y (Vec) -- The vector to be added
• x (Vec) -- The output solution vector, must be different than b.
Return type
None
SEE ALSO:
KSP.create, MatSolve, MatSolveAdd
Source code at petsc4py/PETSc/Mat.pyx:5275
solveBackward(b, x)
Solve Ux=b, given a factored matrix A=LU.
Neighborwise collective.
Parameters
• b (Vec) -- The right-hand side vector.
• x (Vec) -- The output solution vector.
Return type
None
SEE ALSO:
MatBackwardSolve
Source code at petsc4py/PETSc/Mat.pyx:5212
solveForward(b, x)
Solve Lx = b, given a factored matrix A = LU.
Neighborwise collective.
Parameters
• b (Vec) -- The right-hand side vector.
• x (Vec) -- The output solution vector.
Return type
None
SEE ALSO:
MatForwardSolve
Source code at petsc4py/PETSc/Mat.pyx:5193
solveTranspose(b, x)
Solve Aᵀx=b, given a factored matrix.
Neighborwise collective.
The vectors b and x cannot be the same.
Parameters
• b (Vec) -- The right-hand side vector.
• x (Vec) -- The output solution vector, must be different than b.
Return type
None
SEE ALSO:
KSP.create, MatSolve, MatSolveTranspose
Source code at petsc4py/PETSc/Mat.pyx:5254
solveTransposeAdd(b, y, x)
Solve x=y+A⁻ᵀb, given a factored matrix.
Neighborwise collective.
The vectors b and x cannot be the same.
Parameters
• b (Vec) -- The right-hand side vector.
• y (Vec) -- The vector to be added
• x (Vec) -- The output solution vector, must be different than b.
Return type
None
SEE ALSO:
KSP.create, MatSolve, MatSolveTransposeAdd
Source code at petsc4py/PETSc/Mat.pyx:5298
storeValues()
Stash a copy of the matrix values.
Collective.
SEE ALSO:
retrieveValues, MatStoreValues
Source code at petsc4py/PETSc/Mat.pyx:3278
Return type
None
toDLPack(mode='rw')
Return a DLPack PyCapsule wrapping the vector data.
Source code at petsc4py/PETSc/Mat.pyx:5675
Parameters
mode (AccessModeSpec)
Return type
Any
transpose(out=None)
Return the transposed matrix.
Collective.
Parameters
out (Mat | None) -- Optional return matrix. If None, inplace transposition is
performed. Otherwise, the matrix is reused.
Return type
Mat
SEE ALSO:
MatTranspose
Source code at petsc4py/PETSc/Mat.pyx:2103
transposeMatMult(mat, result=None, fill=None)
Perform matrix-matrix multiplication C=AᵀB.
Neighborwise collective.
Parameters
• mat (Mat) -- The right hand matrix B.
• result (Mat | None) -- The optional resultant matrix C. When None, a new matrix is
created, and MAT_INITIAL_MATRIX is used. When C is not None, the matrix is reused
with MAT_REUSE_MATRIX.
• fill (float | None) -- Expected fill as ratio of nnz(C)/(nnz(A) + nnz(B)), use ‐
None if you do not have a good estimate. If the result is a dense matrix this is
irrelevant.
Returns
result -- The resultant product matrix C.
Return type
Mat
Notes
To determine the correct fill value, run with -info and search for the string "Fill ratio"
to see the value actually needed.
SEE ALSO:
MatTransposeMatMult, MatReuse
Source code at petsc4py/PETSc/Mat.pyx:4295
view(viewer=None)
View the matrix.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
Notes
Viewers with type Viewer.Type.ASCII are only recommended for small matrices on small
numbers of processes. Larger matrices should use a binary format like Viewer.Type.BINARY.
SEE ALSO:
load, Viewer, MatView
Source code at petsc4py/PETSc/Mat.pyx:450
zeroEntries()
Zero the entries of the matrix.
Collective.
SEE ALSO:
MatZeroEntries
Source code at petsc4py/PETSc/Mat.pyx:2380
Return type
None
zeroRows(rows, diag=1, x=None, b=None)
Zero selected rows of the matrix.
Collective.
Parameters
• rows (IS | Sequence[int]) -- Row indices to be zeroed.
• diag (Scalar) -- Scalar value to be inserted into the diagonal.
• x (Vec | None) -- Optional solution vector to be modified for zeroed rows.
• b (Vec | None) -- Optional right-hand side vector to be modified. It will be
adjusted with provided solution entries.
Return type
None
SEE ALSO:
zeroRowsLocal, MatZeroRows, MatZeroRowsIS
Source code at petsc4py/PETSc/Mat.pyx:3110
zeroRowsColumns(rows, diag=1, x=None, b=None)
Zero selected rows and columns of the matrix.
Collective.
Parameters
• rows (IS | Sequence[int]) -- Row/column indices to be zeroed.
• diag (Scalar) -- Scalar value to be inserted into the diagonal.
• x (Vec | None) -- Optional solution vector to be modified for zeroed rows.
• b (Vec | None) -- Optional right-hand side vector to be modified. It will be
adjusted with provided solution entries.
Return type
None
SEE ALSO:
zeroRowsColumnsLocal, zeroRows, MatZeroRowsColumns, MatZeroRowsColumnsIS
Source code at petsc4py/PETSc/Mat.pyx:3176
zeroRowsColumnsLocal(rows, diag=1, x=None, b=None)
Zero selected rows and columns of the matrix in local ordering.
Collective.
Parameters
• rows (IS | Sequence[int]) -- Local row/column indices to be zeroed.
• diag (Scalar) -- Scalar value to be inserted into the diagonal.
• x (Vec | None) -- Optional solution vector to be modified for zeroed rows.
• b (Vec | None) -- Optional right-hand side vector to be modified. It will be
adjusted with provided solution entries.
Return type
None
SEE ALSO:
zeroRowsLocal, zeroRowsColumns, MatZeroRowsColumnsLocal, MatZeroRowsColumnsLocalIS
Source code at petsc4py/PETSc/Mat.pyx:3210
zeroRowsColumnsStencil(rows, diag=1, x=None, b=None)
Zero selected rows and columns of the matrix.
Collective.
Parameters
• rows (Sequence[Stencil]) -- Iterable of stencil rows and columns.
• diag (Scalar) -- Scalar value to be inserted into the diagonal.
• x (Vec | None) -- Optional solution vector to be modified for zeroed rows.
• b (Vec | None) -- Optional right-hand side vector to be modified. It will be
adjusted with provided solution entries.
Return type
None
SEE ALSO:
zeroRowsLocal, zeroRowsColumns, MatZeroRowsColumnsStencil
Source code at petsc4py/PETSc/Mat.pyx:3244
zeroRowsLocal(rows, diag=1, x=None, b=None)
Zero selected rows of the matrix in local ordering.
Collective.
Parameters
• rows (IS | Sequence[int]) -- Local row indices to be zeroed.
• diag (Scalar) -- Scalar value to be inserted into the diagonal.
• x (Vec | None) -- Optional solution vector to be modified for zeroed rows.
• b (Vec | None) -- Optional right-hand side vector to be modified. It will be
adjusted with provided solution entries.
Return type
None
SEE ALSO:
zeroRows, MatZeroRowsLocal, MatZeroRowsLocalIS
Source code at petsc4py/PETSc/Mat.pyx:3143
Attributes Documentation
assembled
The boolean flag indicating if the matrix is assembled.
Source code at petsc4py/PETSc/Mat.pyx:5650
block_size
Matrix block size.
Source code at petsc4py/PETSc/Mat.pyx:5628
block_sizes
Matrix row and column block sizes.
Source code at petsc4py/PETSc/Mat.pyx:5633
hermitian
The boolean flag indicating if the matrix is Hermitian.
Source code at petsc4py/PETSc/Mat.pyx:5658
local_size
Matrix local size.
Source code at petsc4py/PETSc/Mat.pyx:5623
owner_range
Matrix local row range.
Source code at petsc4py/PETSc/Mat.pyx:5638
owner_ranges
Matrix row ranges.
Source code at petsc4py/PETSc/Mat.pyx:5643
size Matrix global size.
Source code at petsc4py/PETSc/Mat.pyx:5618
sizes Matrix local and global sizes.
Source code at petsc4py/PETSc/Mat.pyx:5610
structsymm
The boolean flag indicating if the matrix is structurally symmetric.
Source code at petsc4py/PETSc/Mat.pyx:5662
symmetric
The boolean flag indicating if the matrix is symmetric.
Source code at petsc4py/PETSc/Mat.pyx:5654
petsc4py.PETSc.MatPartitioning
class petsc4py.PETSc.MatPartitioning
Bases: Object
Object for managing the partitioning of a matrix or graph.
Enumerations
┌──────┬─────────────────────────┐
│ Type │ The partitioning types. │
└──────┴─────────────────────────┘
petsc4py.PETSc.MatPartitioning.Type
class petsc4py.PETSc.MatPartitioning.Type
Bases: object
The partitioning types.
Attributes Summary
┌──────────────────────┬───────────────────────────────────────┐
│ PARTITIONINGAVERAGE │ Object PARTITIONINGAVERAGE of type ‐ │
│ │ str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGCHACO │ Object PARTITIONINGCHACO of type str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGCURRENT │ Object PARTITIONINGCURRENT of type ‐ │
│ │ str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGHIERARCH │ Object PARTITIONINGHIERARCH of type ‐ │
│ │ str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGPARMETIS │ Object PARTITIONINGPARMETIS of type ‐ │
│ │ str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGPARTY │ Object PARTITIONINGPARTY of type str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGPTSCOTCH │ Object PARTITIONINGPTSCOTCH of type ‐ │
│ │ str │
├──────────────────────┼───────────────────────────────────────┤
│ PARTITIONINGSQUARE │ Object PARTITIONINGSQUARE of type str │
└──────────────────────┴───────────────────────────────────────┘
Attributes Documentation
PARTITIONINGAVERAGE: str = PARTITIONINGAVERAGE
Object PARTITIONINGAVERAGE of type str
PARTITIONINGCHACO: str = PARTITIONINGCHACO
Object PARTITIONINGCHACO of type str
PARTITIONINGCURRENT: str = PARTITIONINGCURRENT
Object PARTITIONINGCURRENT of type str
PARTITIONINGHIERARCH: str = PARTITIONINGHIERARCH
Object PARTITIONINGHIERARCH of type str
PARTITIONINGPARMETIS: str = PARTITIONINGPARMETIS
Object PARTITIONINGPARMETIS of type str
PARTITIONINGPARTY: str = PARTITIONINGPARTY
Object PARTITIONINGPARTY of type str
PARTITIONINGPTSCOTCH: str = PARTITIONINGPTSCOTCH
Object PARTITIONINGPTSCOTCH of type str
PARTITIONINGSQUARE: str = PARTITIONINGSQUARE
Object PARTITIONINGSQUARE of type str
Methods Summary
┌───────────────────────────────┬───────────────────────────────────────┐
│ apply(partitioning) │ Return a partitioning for the graph │
│ │ represented by a sparse matrix. │
├───────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a partitioning context. │
├───────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the partitioning context. │
├───────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the partitioning method. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setAdjacency(adj) │ Set the adjacency graph (matrix) of │
│ │ the thing to be partitioned. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set parameters in the partitioner │
│ │ from the options database. │
├───────────────────────────────┼───────────────────────────────────────┤
│ setType(matpartitioning_type) │ Set the type of the partitioner to │
│ │ use. │
├───────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the partitioning data structure. │
└───────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
apply(partitioning)
Return a partitioning for the graph represented by a sparse matrix.
Collective.
For each local node this tells the processor number that that node is assigned to.
SEE ALSO:
MatPartitioningApply
Source code at petsc4py/PETSc/MatPartitioning.pyx:144
Parameters
partitioning (IS)
Return type
None
create(comm=None)
Create a partitioning context.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
destroy, MatPartitioningCreate
Source code at petsc4py/PETSc/MatPartitioning.pyx:62
destroy()
Destroy the partitioning context.
Collective.
SEE ALSO:
create, MatPartitioningDestroy
Source code at petsc4py/PETSc/MatPartitioning.pyx:49
Return type
Self
getType()
Return the partitioning method.
Not collective.
SEE ALSO:
setType, MatPartitioningGetType
Source code at petsc4py/PETSc/MatPartitioning.pyx:100
Return type
str
setAdjacency(adj)
Set the adjacency graph (matrix) of the thing to be partitioned.
Collective.
Parameters
adj (Mat) -- The adjacency matrix, this can be any Mat.Type but the natural
representation is Mat.Type.MPIADJ.
Return type
None
SEE ALSO:
MatPartitioningSetAdjacency
Source code at petsc4py/PETSc/MatPartitioning.pyx:126
setFromOptions()
Set parameters in the partitioner from the options database.
Collective.
SEE ALSO:
Working with PETSc options, MatPartitioningSetFromOptions
Source code at petsc4py/PETSc/MatPartitioning.pyx:114
Return type
None
setType(matpartitioning_type)
Set the type of the partitioner to use.
Collective.
Parameters
matpartitioning_type (Type | str) -- The partitioner type.
Return type
None
SEE ALSO:
getType, MatPartitioningSetType
Source code at petsc4py/PETSc/MatPartitioning.pyx:81
view(viewer=None)
View the partitioning data structure.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
MatPartitioningView
Source code at petsc4py/PETSc/MatPartitioning.pyx:29
petsc4py.PETSc.NormType
class petsc4py.PETSc.NormType
Bases: object
Norm type.
Commonly used norm types:
N1 The one norm.
N2 The two norm.
FROBENIUS
The Frobenius norm.
INFINITY
The infinity norm.
SEE ALSO:
NormType
Attributes Summary
┌────────────────┬─────────────────────────────────────┐
│ FRB │ Constant FRB of type int │
├────────────────┼─────────────────────────────────────┤
│ FROBENIUS │ Constant FROBENIUS of type int │
├────────────────┼─────────────────────────────────────┤
│ INF │ Constant INF of type int │
├────────────────┼─────────────────────────────────────┤
│ INFINITY │ Constant INFINITY of type int │
├────────────────┼─────────────────────────────────────┤
│ MAX │ Constant MAX of type int │
├────────────────┼─────────────────────────────────────┤
│ N1 │ Constant N1 of type int │
├────────────────┼─────────────────────────────────────┤
│ N12 │ Constant N12 of type int │
├────────────────┼─────────────────────────────────────┤
│ N2 │ Constant N2 of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_1 │ Constant NORM_1 of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_1_AND_2 │ Constant NORM_1_AND_2 of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_2 │ Constant NORM_2 of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_FROBENIUS │ Constant NORM_FROBENIUS of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_INFINITY │ Constant NORM_INFINITY of type int │
├────────────────┼─────────────────────────────────────┤
│ NORM_MAX │ Constant NORM_MAX of type int │
└────────────────┴─────────────────────────────────────┘
Attributes Documentation
FRB: int = FRB
Constant FRB of type int
FROBENIUS: int = FROBENIUS
Constant FROBENIUS of type int
INF: int = INF
Constant INF of type int
INFINITY: int = INFINITY
Constant INFINITY of type int
MAX: int = MAX
Constant MAX of type int
N1: int = N1
Constant N1 of type int
N12: int = N12
Constant N12 of type int
N2: int = N2
Constant N2 of type int
NORM_1: int = NORM_1
Constant NORM_1 of type int
NORM_1_AND_2: int = NORM_1_AND_2
Constant NORM_1_AND_2 of type int
NORM_2: int = NORM_2
Constant NORM_2 of type int
NORM_FROBENIUS: int = NORM_FROBENIUS
Constant NORM_FROBENIUS of type int
NORM_INFINITY: int = NORM_INFINITY
Constant NORM_INFINITY of type int
NORM_MAX: int = NORM_MAX
Constant NORM_MAX of type int
petsc4py.PETSc.NullSpace
class petsc4py.PETSc.NullSpace
Bases: Object
Nullspace object.
SEE ALSO:
MatNullSpace
Methods Summary
┌──────────────────────────────────────┬───────────────────────────────────────┐
│ create([constant, vectors, comm]) │ Create the null space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ createRigidBody(coords) │ Create rigid body modes from │
│ │ coordinates. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the null space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getFunction() │ Return the callback to remove the │
│ │ nullspace. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getVecs() │ Return the vectors defining the null │
│ │ space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ hasConstant() │ Return whether the null space │
│ │ contains the constant. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ remove(vec) │ Remove all components of a null space │
│ │ from a vector. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setFunction(function[, args, kargs]) │ Set the callback to remove the │
│ │ nullspace. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ test(mat) │ Return if the claimed null space is │
│ │ valid for a matrix. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the null space. │
└──────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(constant=False, vectors=(), comm=None)
Create the null space.
Collective.
Parameters
• constant (bool) -- A flag to indicate the null space contains the constant vector.
• vectors (Sequence[Vec]) -- The sequence of vectors that span the null space.
• comm -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
destroy, MatNullSpaceCreate
Source code at petsc4py/PETSc/Mat.pyx:5799
createRigidBody(coords)
Create rigid body modes from coordinates.
Collective.
Parameters
coords (Vec) -- The block coordinates of each node. Requires the block size to have
been set.
Return type
Self
SEE ALSO:
MatNullSpaceCreateRigidBody
Source code at petsc4py/PETSc/Mat.pyx:5835
destroy()
Destroy the null space.
Collective.
SEE ALSO:
create, MatNullSpaceDestroy
Source code at petsc4py/PETSc/Mat.pyx:5786
Return type
Self
getFunction()
Return the callback to remove the nullspace.
Not collective.
SEE ALSO:
setFunction
Source code at petsc4py/PETSc/Mat.pyx:5926
Return type
MatNullFunction
getVecs()
Return the vectors defining the null space.
Not collective.
SEE ALSO:
MatNullSpaceGetVecs
Source code at petsc4py/PETSc/Mat.pyx:5904
Return type
list[Vec]
hasConstant()
Return whether the null space contains the constant.
Not collective.
SEE ALSO:
MatNullSpaceGetVecs
Source code at petsc4py/PETSc/Mat.pyx:5890
Return type
bool
remove(vec)
Remove all components of a null space from a vector.
Collective.
Parameters
vec (Vec) -- The vector from which the null space is removed.
Return type
None
SEE ALSO:
MatNullSpaceRemove
Source code at petsc4py/PETSc/Mat.pyx:5940
setFunction(function, args=None, kargs=None)
Set the callback to remove the nullspace.
Logically collective.
Parameters
• function (MatNullFunction) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getFunction, MatNullSpaceSetFunction
Source code at petsc4py/PETSc/Mat.pyx:5856
test(mat)
Return if the claimed null space is valid for a matrix.
Collective.
Parameters
mat (Mat) -- The matrix to check.
Return type
bool
SEE ALSO:
MatNullSpaceTest
Source code at petsc4py/PETSc/Mat.pyx:5957
view(viewer=None)
View the null space.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
Viewer, MatNullSpaceView
Source code at petsc4py/PETSc/Mat.pyx:5767
petsc4py.PETSc.Object
class petsc4py.PETSc.Object
Bases: object
Base class wrapping a PETSc object.
SEE ALSO:
PetscObject
Methods Summary
┌──────────────────────────────────┬───────────────────────────────────────┐
│ appendOptionsPrefix(prefix) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ compose(name, obj) │ Associate a PETSc object using a key │
│ │ string. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ decRef() │ Decrement the object reference count. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ destroyOptionsHandlers() │ Clear all the option handlers. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getAttr(name) │ Return the attribute associated with │
│ │ a given name. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getClassId() │ Return the class identifier of the │
│ │ object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getClassName() │ Return the class name of the object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getComm() │ Return the communicator of the │
│ │ object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getDict() │ Return the dictionary of attributes. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getId() │ Return the unique identifier of the │
│ │ object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getName() │ Return the name of the object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getRefCount() │ Return the reference count of the │
│ │ object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getTabLevel() │ Return the PETSc object tab level. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the object type name. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ incRef() │ Increment the object reference count. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ incrementTabLevel(tab[, parent]) │ Increment the PETSc object tab level. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ query(name) │ Query for the PETSc object associated │
│ │ with a key string. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setAttr(name, attr) │ Set an the attribute associated with │
│ │ a given name. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the object from the options │
│ │ database. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setName(name) │ Associate a name to the object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsHandler(handler) │ Set the callback for processing extra │
│ │ options. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for searching for │
│ │ options in the database. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ setTabLevel(level) │ Set the PETSc object tab level. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ stateGet() │ Return the PETSc object state. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ stateIncrease() │ Increment the PETSc object state. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ stateSet(state) │ Set the PETSc object state. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Display the object. │
├──────────────────────────────────┼───────────────────────────────────────┤
│ viewFromOptions(name[, objpre]) │ View the object via command line │
│ │ options. │
└──────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌──────────┬────────────────────────────┐
│ classid │ The class identifier. │
├──────────┼────────────────────────────┤
│ comm │ The object communicator. │
├──────────┼────────────────────────────┤
│ fortran │ Fortran handle. │
├──────────┼────────────────────────────┤
│ handle │ Handle for ctypes support. │
├──────────┼────────────────────────────┤
│ id │ The object identifier. │
├──────────┼────────────────────────────┤
│ klass │ The class name. │
├──────────┼────────────────────────────┤
│ name │ The object name. │
├──────────┼────────────────────────────┤
│ prefix │ Options prefix. │
├──────────┼────────────────────────────┤
│ refcount │ Reference count. │
├──────────┼────────────────────────────┤
│ type │ Object type. │
└──────────┴────────────────────────────┘
Methods Documentation
appendOptionsPrefix(prefix)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, PetscObjectAppendOptionsPrefix
Source code at petsc4py/PETSc/Object.pyx:138
Parameters
prefix (str | None)
Return type
None
compose(name, obj)
Associate a PETSc object using a key string.
Logically collective.
Parameters
• name (str | None) -- The string identifying the object to be composed.
• obj (Object) -- The object to be composed.
Return type
None
SEE ALSO:
query, PetscObjectCompose
Source code at petsc4py/PETSc/Object.pyx:329
decRef()
Decrement the object reference count.
Logically collective.
SEE ALSO:
getRefCount, PetscObjectDereference
Source code at petsc4py/PETSc/Object.pyx:389
Return type
int
destroy()
Destroy the object.
Collective.
SEE ALSO:
PetscObjectDestroy
Source code at petsc4py/PETSc/Object.pyx:81
Return type
Self
destroyOptionsHandlers()
Clear all the option handlers.
Collective.
SEE ALSO:
Working with PETSc options, setOptionsHandler, PetscObjectDestroyOptionsHandlers
Source code at petsc4py/PETSc/Object.pyx:213
Return type
None
getAttr(name)
Return the attribute associated with a given name.
Not collective.
SEE ALSO:
setAttr, getDict
Source code at petsc4py/PETSc/Object.pyx:408
Parameters
name (str)
Return type
object
getClassId()
Return the class identifier of the object.
Not collective.
SEE ALSO:
PetscObjectGetClassId
Source code at petsc4py/PETSc/Object.pyx:270
Return type
int
getClassName()
Return the class name of the object.
Not collective.
SEE ALSO:
PetscObjectGetClassName
Source code at petsc4py/PETSc/Object.pyx:284
Return type
str
getComm()
Return the communicator of the object.
Not collective.
SEE ALSO:
PetscObjectGetComm
Source code at petsc4py/PETSc/Object.pyx:228
Return type
Comm
getDict()
Return the dictionary of attributes.
Not collective.
SEE ALSO:
setAttr, getAttr
Source code at petsc4py/PETSc/Object.pyx:436
Return type
dict
getId()
Return the unique identifier of the object.
Not collective.
SEE ALSO:
PetscObjectGetId
Source code at petsc4py/PETSc/Object.pyx:313
Return type
int
getName()
Return the name of the object.
Not collective.
SEE ALSO:
PetscObjectGetName
Source code at petsc4py/PETSc/Object.pyx:242
Return type
str
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, PetscObjectGetOptionsPrefix
Source code at petsc4py/PETSc/Object.pyx:124
Return type
str
getRefCount()
Return the reference count of the object.
Not collective.
SEE ALSO:
PetscObjectGetReference
Source code at petsc4py/PETSc/Object.pyx:298
Return type
int
getTabLevel()
Return the PETSc object tab level.
Not collective.
SEE ALSO:
setTabLevel, incrementTabLevel, PetscObjectGetTabLevel
Source code at petsc4py/PETSc/Object.pyx:518
Return type
None
getType()
Return the object type name.
Not collective.
SEE ALSO:
PetscObjectGetType
Source code at petsc4py/PETSc/Object.pyx:94
Return type
str
incRef()
Increment the object reference count.
Logically collective.
SEE ALSO:
getRefCount, PetscObjectReference
Source code at petsc4py/PETSc/Object.pyx:372
Return type
int
incrementTabLevel(tab, parent=None)
Increment the PETSc object tab level.
Logically collective.
SEE ALSO:
setTabLevel, getTabLevel, PetscObjectIncrementTabLevel
Source code at petsc4py/PETSc/Object.pyx:491
Parameters
• tab (int)
• parent (Object | None)
Return type
None
query(name)
Query for the PETSc object associated with a key string.
Not collective.
SEE ALSO:
compose, PetscObjectQuery
Source code at petsc4py/PETSc/Object.pyx:352
Parameters
name (str)
Return type
Object
setAttr(name, attr)
Set an the attribute associated with a given name.
Not collective.
SEE ALSO:
getAttr, getDict
Source code at petsc4py/PETSc/Object.pyx:422
Parameters
• name (str)
• attr (object)
Return type
None
setFromOptions()
Configure the object from the options database.
Collective.
Classes that do not implement setFromOptions use this method that, in turn, calls ‐
PetscObjectSetFromOptions.
SEE ALSO:
Working with PETSc options, PetscObjectSetFromOptions
Source code at petsc4py/PETSc/Object.pyx:152
Return type
None
setName(name)
Associate a name to the object.
Not collective.
SEE ALSO:
PetscObjectSetName
Source code at petsc4py/PETSc/Object.pyx:256
Parameters
name (str | None)
Return type
None
setOptionsHandler(handler)
Set the callback for processing extra options.
Logically collective.
Parameters
handler (PetscOptionsHandlerFunction | None) -- The callback function, called at the
end of a setFromOptions invocation for the given class.
Return type
None
SEE ALSO:
Working with PETSc options, Mat.setFromOptions, KSP.setFromOptions, ‐
PetscObjectAddOptionsHandler
Source code at petsc4py/PETSc/Object.pyx:190
setOptionsPrefix(prefix)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, getOptionsPrefix, PetscObjectSetOptionsPrefix
Source code at petsc4py/PETSc/Object.pyx:110
Parameters
prefix (str | None)
Return type
None
setTabLevel(level)
Set the PETSc object tab level.
Logically collective.
SEE ALSO:
incrementTabLevel, getTabLevel, PetscObjectSetTabLevel
Source code at petsc4py/PETSc/Object.pyx:505
Parameters
level (int)
Return type
None
stateGet()
Return the PETSc object state.
Not collective.
SEE ALSO:
stateSet, stateIncrease, PetscObjectStateGet
Source code at petsc4py/PETSc/Object.pyx:462
Return type
int
stateIncrease()
Increment the PETSc object state.
Logically collective.
SEE ALSO:
stateGet, stateSet, PetscObjectStateIncrease
Source code at petsc4py/PETSc/Object.pyx:450
Return type
None
stateSet(state)
Set the PETSc object state.
Logically collective.
SEE ALSO:
stateIncrease, stateGet, PetscObjectStateSet
Source code at petsc4py/PETSc/Object.pyx:476
Parameters
state (int)
Return type
None
view(viewer=None)
Display the object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
PetscObjectView
Source code at petsc4py/PETSc/Object.pyx:62
viewFromOptions(name, objpre=None)
View the object via command line options.
Collective.
Parameters
• name (str) -- The command line option.
• objpre (Object | None) -- Optional object that provides prefix.
Return type
None
SEE ALSO:
Working with PETSc options, PetscObjectViewFromOptions
Source code at petsc4py/PETSc/Object.pyx:167
Attributes Documentation
classid
The class identifier.
Source code at petsc4py/PETSc/Object.pyx:563
comm The object communicator.
Source code at petsc4py/PETSc/Object.pyx:550
fortran
Fortran handle.
Source code at petsc4py/PETSc/Object.pyx:593
handle Handle for ctypes support.
Source code at petsc4py/PETSc/Object.pyx:585
id The object identifier.
Source code at petsc4py/PETSc/Object.pyx:568
klass The class name.
Source code at petsc4py/PETSc/Object.pyx:573
name The object name.
Source code at petsc4py/PETSc/Object.pyx:555
prefix Options prefix.
Source code at petsc4py/PETSc/Object.pyx:542
refcount
Reference count.
Source code at petsc4py/PETSc/Object.pyx:578
type Object type.
Source code at petsc4py/PETSc/Object.pyx:534
petsc4py.PETSc.Options
class petsc4py.PETSc.Options
Bases: object
The options database object.
A dictionary-like object to store and operate with command line options.
Parameters
prefix (str, optional) -- Optional string to prepend to all the options.
Examples
Create an option database and operate with it.
>>> from petsc4py import PETSc
>>> opts = PETSc.Options()
>>> opts['a'] = 1 # insert the command-line option '-a 1'
>>> if 'a' in opts: # if the option is present
>>> val = opts['a'] # return the option value as 'str'
>>> a_int = opts.getInt('a') # return the option value as 'int'
>>> a_bool = opts.getBool('a') # return the option value as 'bool'
Read command line and use default values.
>>> from petsc4py import PETSc
>>> opts = PETSc.Options()
>>> b_float = opts.getReal('b', 1) # return the value or 1.0 if not present
Read command line options prepended with a prefix.
>>> from petsc4py import PETSc
>>> opts = PETSc.Options('prefix_')
>>> opts.getString('b', 'some_default_string') # read -prefix_b xxx
SEE ALSO:
Working with PETSc options
Methods Summary
┌─────────────────────────────────┬───────────────────────────────────────┐
│ clear() │ Clear an options database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ create() │ Create an options database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ delValue(name) │ Delete an option from the database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy an options database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getAll() │ Return all the options and their │
│ │ values. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getBool(name[, default]) │ Return the boolean value associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getBoolArray(name[, default]) │ Return the boolean values associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getInt(name[, default]) │ Return the integer value associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getIntArray(name[, default]) │ Return the integer array associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getReal(name[, default]) │ Return the real value associated with │
│ │ the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getRealArray(name[, default]) │ Return the real array associated with │
│ │ the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getScalar(name[, default]) │ Return the scalar value associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getScalarArray(name[, default]) │ Return the scalar array associated │
│ │ with the option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ getString(name[, default]) │ Return the string associated with the │
│ │ option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ hasName(name) │ Return the boolean indicating if the │
│ │ option is in the database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ insertString(string) │ Insert a string in the options │
│ │ database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ prefixPop() │ Pop a prefix for the options │
│ │ database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ prefixPush(prefix) │ Push a prefix for the options │
│ │ database. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ setValue(name, value) │ Set a value for an option. │
├─────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the options database. │
└─────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌────────┬─────────────────────┐
│ prefix │ Prefix for options. │
└────────┴─────────────────────┘
Methods Documentation
clear()
Clear an options database.
Source code at petsc4py/PETSc/Options.pyx:91
Return type
Self
create()
Create an options database.
Source code at petsc4py/PETSc/Options.pyx:79
Return type
Self
delValue(name)
Delete an option from the database.
Logically collective.
SEE ALSO:
setValue, PetscOptionsClearValue
Source code at petsc4py/PETSc/Options.pyx:195
Parameters
name (str)
Return type
None
destroy()
Destroy an options database.
Source code at petsc4py/PETSc/Options.pyx:85
Return type
Self
getAll()
Return all the options and their values.
Not collective.
SEE ALSO:
PetscOptionsGetAll
Source code at petsc4py/PETSc/Options.pyx:414
Return type
dict[str, str]
getBool(name, default=None)
Return the boolean value associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
bool
SEE ALSO:
getBoolArray, PetscOptionsGetBool
Source code at petsc4py/PETSc/Options.pyx:218
getBoolArray(name, default=None)
Return the boolean values associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
ArrayBool
SEE ALSO:
getBool, PetscOptionsGetBoolArray
Source code at petsc4py/PETSc/Options.pyx:238
getInt(name, default=None)
Return the integer value associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
int
SEE ALSO:
getIntArray, PetscOptionsGetInt
Source code at petsc4py/PETSc/Options.pyx:258
getIntArray(name, default=None)
Return the integer array associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
ArrayInt
SEE ALSO:
getInt, PetscOptionsGetIntArray
Source code at petsc4py/PETSc/Options.pyx:278
getReal(name, default=None)
Return the real value associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
float
SEE ALSO:
getRealArray, PetscOptionsGetReal
Source code at petsc4py/PETSc/Options.pyx:298
getRealArray(name, default=None)
Return the real array associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
ArrayReal
SEE ALSO:
getReal, PetscOptionsGetRealArray
Source code at petsc4py/PETSc/Options.pyx:318
getScalar(name, default=None)
Return the scalar value associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
Scalar
SEE ALSO:
getScalarArray, PetscOptionsGetScalar
Source code at petsc4py/PETSc/Options.pyx:338
getScalarArray(name, default=None)
Return the scalar array associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
ArrayScalar
SEE ALSO:
getScalar, PetscOptionsGetScalarArray
Source code at petsc4py/PETSc/Options.pyx:358
getString(name, default=None)
Return the string associated with the option.
Not collective.
Parameters
• name (str) -- The option name.
• default -- The default value. If None, it raises a KeyError if the option is not
found.
Return type
str
SEE ALSO:
PetscOptionsGetString
Source code at petsc4py/PETSc/Options.pyx:378
hasName(name)
Return the boolean indicating if the option is in the database.
Source code at petsc4py/PETSc/Options.pyx:144
Parameters
name (str)
Return type
bool
insertString(string)
Insert a string in the options database.
Logically collective.
SEE ALSO:
PetscOptionsInsertString
Source code at petsc4py/PETSc/Options.pyx:400
Parameters
string (str)
Return type
None
prefixPop()
Pop a prefix for the options database.
Logically collective.
SEE ALSO:
prefixPush, PetscOptionsPrefixPop
Source code at petsc4py/PETSc/Options.pyx:131
Return type
None
prefixPush(prefix)
Push a prefix for the options database.
Logically collective.
SEE ALSO:
prefixPop, PetscOptionsPrefixPush
Source code at petsc4py/PETSc/Options.pyx:116
Parameters
prefix (str | Options | Object | None)
Return type
None
setValue(name, value)
Set a value for an option.
Logically collective.
Parameters
• name (str) -- The string identifying the option.
• value (bool | int | float | Scalar | Sequence[bool] | Sequence[int] | Sequence[‐
float] | Sequence[Scalar] | str) -- The option value.
Return type
None
SEE ALSO:
delValue, PetscOptionsSetValue
Source code at petsc4py/PETSc/Options.pyx:153
view(viewer=None)
View the options database.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
Viewer, PetscOptionsView
Source code at petsc4py/PETSc/Options.pyx:97
Attributes Documentation
prefix Prefix for options.
Source code at petsc4py/PETSc/Options.pyx:67
petsc4py.PETSc.PC
class petsc4py.PETSc.PC
Bases: Object
Preconditioners.
PC is described in the PETSc manual. Calling the PC with a vector as an argument will apply the
preconditioner as shown in the example below.
Examples
>>> from petsc4py import PETSc
>>> v = PETSc.Vec().createWithArray([1, 2])
>>> m = PETSc.Mat().createDense(2, array=[[1, 0], [0, 1]])
>>> pc = PETSc.PC().create()
>>> pc.setOperators(m)
>>> u = pc(v) # u is created internally
>>> pc.apply(v, u) # u can also be passed as second argument
SEE ALSO:
PC
Enumerations
┌───────────────────────────┬───────────────────────────────────────┐
│ ASMType │ The ASM subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ CompositeType │ The composite type. │
├───────────────────────────┼───────────────────────────────────────┤
│ DeflationSpaceType │ The deflation space subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ FailedReason │ The reason the preconditioner has │
│ │ failed. │
├───────────────────────────┼───────────────────────────────────────┤
│ FieldSplitSchurFactType │ The field split Schur factorization │
│ │ type. │
├───────────────────────────┼───────────────────────────────────────┤
│ FieldSplitSchurPreType │ The field split Schur subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ GAMGType │ The GAMG subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ GASMType │ The GASM subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ HPDDMCoarseCorrectionType │ The HPDDM coarse correction type. │
├───────────────────────────┼───────────────────────────────────────┤
│ MGCycleType │ The MG cycle type. │
├───────────────────────────┼───────────────────────────────────────┤
│ MGType │ The MG subtype. │
├───────────────────────────┼───────────────────────────────────────┤
│ PatchConstructType │ The patch construction type. │
├───────────────────────────┼───────────────────────────────────────┤
│ Side │ The manner in which the │
│ │ preconditioner is applied. │
├───────────────────────────┼───────────────────────────────────────┤
│ Type │ The preconditioner method. │
└───────────────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.PC.ASMType
class petsc4py.PETSc.PC.ASMType
Bases: object
The ASM subtype.
Attributes Summary
┌─────────────┬──────────────────────────────────┐
│ BASIC │ Constant BASIC of type int │
├─────────────┼──────────────────────────────────┤
│ INTERPOLATE │ Constant INTERPOLATE of type int │
├─────────────┼──────────────────────────────────┤
│ NONE │ Constant NONE of type int │
├─────────────┼──────────────────────────────────┤
│ RESTRICT │ Constant RESTRICT of type int │
└─────────────┴──────────────────────────────────┘
Attributes Documentation
BASIC: int = BASIC
Constant BASIC of type int
INTERPOLATE: int = INTERPOLATE
Constant INTERPOLATE of type int
NONE: int = NONE
Constant NONE of type int
RESTRICT: int = RESTRICT
Constant RESTRICT of type int
petsc4py.PETSc.PC.CompositeType
class petsc4py.PETSc.PC.CompositeType
Bases: object
The composite type.
Attributes Summary
┌──────────────────────────┬───────────────────────────────────────┐
│ ADDITIVE │ Constant ADDITIVE of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ MULTIPLICATIVE │ Constant MULTIPLICATIVE of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ SCHUR │ Constant SCHUR of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ SPECIAL │ Constant SPECIAL of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ SYMMETRIC_MULTIPLICATIVE │ Constant SYMMETRIC_MULTIPLICATIVE of │
│ │ type int │
└──────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
ADDITIVE: int = ADDITIVE
Constant ADDITIVE of type int
MULTIPLICATIVE: int = MULTIPLICATIVE
Constant MULTIPLICATIVE of type int
SCHUR: int = SCHUR
Constant SCHUR of type int
SPECIAL: int = SPECIAL
Constant SPECIAL of type int
SYMMETRIC_MULTIPLICATIVE: int = SYMMETRIC_MULTIPLICATIVE
Constant SYMMETRIC_MULTIPLICATIVE of type int
petsc4py.PETSc.PC.DeflationSpaceType
class petsc4py.PETSc.PC.DeflationSpaceType
Bases: object
The deflation space subtype.
Attributes Summary
┌─────────────┬──────────────────────────────────┐
│ AGGREGATION │ Constant AGGREGATION of type int │
├─────────────┼──────────────────────────────────┤
│ BIORTH22 │ Constant BIORTH22 of type int │
├─────────────┼──────────────────────────────────┤
│ DB16 │ Constant DB16 of type int │
├─────────────┼──────────────────────────────────┤
│ DB2 │ Constant DB2 of type int │
├─────────────┼──────────────────────────────────┤
│ DB4 │ Constant DB4 of type int │
├─────────────┼──────────────────────────────────┤
│ DB8 │ Constant DB8 of type int │
├─────────────┼──────────────────────────────────┤
│ HAAR │ Constant HAAR of type int │
├─────────────┼──────────────────────────────────┤
│ MEYER │ Constant MEYER of type int │
├─────────────┼──────────────────────────────────┤
│ USER │ Constant USER of type int │
└─────────────┴──────────────────────────────────┘
Attributes Documentation
AGGREGATION: int = AGGREGATION
Constant AGGREGATION of type int
BIORTH22: int = BIORTH22
Constant BIORTH22 of type int
DB16: int = DB16
Constant DB16 of type int
DB2: int = DB2
Constant DB2 of type int
DB4: int = DB4
Constant DB4 of type int
DB8: int = DB8
Constant DB8 of type int
HAAR: int = HAAR
Constant HAAR of type int
MEYER: int = MEYER
Constant MEYER of type int
USER: int = USER
Constant USER of type int
petsc4py.PETSc.PC.FailedReason
class petsc4py.PETSc.PC.FailedReason
Bases: object
The reason the preconditioner has failed.
Attributes Summary
┌──────────────────────────┬───────────────────────────────────────┐
│ FACTOR_NUMERIC_ZEROPIVOT │ Constant FACTOR_NUMERIC_ZEROPIVOT of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ FACTOR_OTHER │ Constant FACTOR_OTHER of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ FACTOR_OUTMEMORY │ Constant FACTOR_OUTMEMORY of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ FACTOR_STRUCT_ZEROPIVOT │ Constant FACTOR_STRUCT_ZEROPIVOT of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ NOERROR │ Constant NOERROR of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ SETUP_ERROR │ Constant SETUP_ERROR of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ SUBPC_ERROR │ Constant SUBPC_ERROR of type int │
└──────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
FACTOR_NUMERIC_ZEROPIVOT: int = FACTOR_NUMERIC_ZEROPIVOT
Constant FACTOR_NUMERIC_ZEROPIVOT of type int
FACTOR_OTHER: int = FACTOR_OTHER
Constant FACTOR_OTHER of type int
FACTOR_OUTMEMORY: int = FACTOR_OUTMEMORY
Constant FACTOR_OUTMEMORY of type int
FACTOR_STRUCT_ZEROPIVOT: int = FACTOR_STRUCT_ZEROPIVOT
Constant FACTOR_STRUCT_ZEROPIVOT of type int
NOERROR: int = NOERROR
Constant NOERROR of type int
SETUP_ERROR: int = SETUP_ERROR
Constant SETUP_ERROR of type int
SUBPC_ERROR: int = SUBPC_ERROR
Constant SUBPC_ERROR of type int
petsc4py.PETSc.PC.FieldSplitSchurFactType
class petsc4py.PETSc.PC.FieldSplitSchurFactType
Bases: object
The field split Schur factorization type.
Attributes Summary
┌───────┬────────────────────────────┐
│ DIAG │ Constant DIAG of type int │
├───────┼────────────────────────────┤
│ FULL │ Constant FULL of type int │
├───────┼────────────────────────────┤
│ LOWER │ Constant LOWER of type int │
├───────┼────────────────────────────┤
│ UPPER │ Constant UPPER of type int │
└───────┴────────────────────────────┘
Attributes Documentation
DIAG: int = DIAG
Constant DIAG of type int
FULL: int = FULL
Constant FULL of type int
LOWER: int = LOWER
Constant LOWER of type int
UPPER: int = UPPER
Constant UPPER of type int
petsc4py.PETSc.PC.FieldSplitSchurPreType
class petsc4py.PETSc.PC.FieldSplitSchurPreType
Bases: object
The field split Schur subtype.
Attributes Summary
┌───────┬────────────────────────────┐
│ A11 │ Constant A11 of type int │
├───────┼────────────────────────────┤
│ FULL │ Constant FULL of type int │
├───────┼────────────────────────────┤
│ SELF │ Constant SELF of type int │
├───────┼────────────────────────────┤
│ SELFP │ Constant SELFP of type int │
├───────┼────────────────────────────┤
│ USER │ Constant USER of type int │
└───────┴────────────────────────────┘
Attributes Documentation
A11: int = A11
Constant A11 of type int
FULL: int = FULL
Constant FULL of type int
SELF: int = SELF
Constant SELF of type int
SELFP: int = SELFP
Constant SELFP of type int
USER: int = USER
Constant USER of type int
petsc4py.PETSc.PC.GAMGType
class petsc4py.PETSc.PC.GAMGType
Bases: object
The GAMG subtype.
Attributes Summary
┌───────────┬──────────────────────────────┐
│ AGG │ Object AGG of type str │
├───────────┼──────────────────────────────┤
│ CLASSICAL │ Object CLASSICAL of type str │
├───────────┼──────────────────────────────┤
│ GEO │ Object GEO of type str │
└───────────┴──────────────────────────────┘
Attributes Documentation
AGG: str = AGG
Object AGG of type str
CLASSICAL: str = CLASSICAL
Object CLASSICAL of type str
GEO: str = GEO
Object GEO of type str
petsc4py.PETSc.PC.GASMType
class petsc4py.PETSc.PC.GASMType
Bases: object
The GASM subtype.
Attributes Summary
┌─────────────┬──────────────────────────────────┐
│ BASIC │ Constant BASIC of type int │
├─────────────┼──────────────────────────────────┤
│ INTERPOLATE │ Constant INTERPOLATE of type int │
├─────────────┼──────────────────────────────────┤
│ NONE │ Constant NONE of type int │
├─────────────┼──────────────────────────────────┤
│ RESTRICT │ Constant RESTRICT of type int │
└─────────────┴──────────────────────────────────┘
Attributes Documentation
BASIC: int = BASIC
Constant BASIC of type int
INTERPOLATE: int = INTERPOLATE
Constant INTERPOLATE of type int
NONE: int = NONE
Constant NONE of type int
RESTRICT: int = RESTRICT
Constant RESTRICT of type int
petsc4py.PETSc.PC.HPDDMCoarseCorrectionType
class petsc4py.PETSc.PC.HPDDMCoarseCorrectionType
Bases: object
The HPDDM coarse correction type.
Attributes Summary
┌──────────┬───────────────────────────────┐
│ ADDITIVE │ Constant ADDITIVE of type int │
├──────────┼───────────────────────────────┤
│ BALANCED │ Constant BALANCED of type int │
├──────────┼───────────────────────────────┤
│ DEFLATED │ Constant DEFLATED of type int │
├──────────┼───────────────────────────────┤
│ NONE │ Constant NONE of type int │
└──────────┴───────────────────────────────┘
Attributes Documentation
ADDITIVE: int = ADDITIVE
Constant ADDITIVE of type int
BALANCED: int = BALANCED
Constant BALANCED of type int
DEFLATED: int = DEFLATED
Constant DEFLATED of type int
NONE: int = NONE
Constant NONE of type int
petsc4py.PETSc.PC.MGCycleType
class petsc4py.PETSc.PC.MGCycleType
Bases: object
The MG cycle type.
Attributes Summary
┌───┬────────────────────────┐
│ V │ Constant V of type int │
├───┼────────────────────────┤
│ W │ Constant W of type int │
└───┴────────────────────────┘
Attributes Documentation
V: int = V
Constant V of type int
W: int = W
Constant W of type int
petsc4py.PETSc.PC.MGType
class petsc4py.PETSc.PC.MGType
Bases: object
The MG subtype.
Attributes Summary
┌────────────────┬─────────────────────────────────────┐
│ ADDITIVE │ Constant ADDITIVE of type int │
├────────────────┼─────────────────────────────────────┤
│ FULL │ Constant FULL of type int │
├────────────────┼─────────────────────────────────────┤
│ KASKADE │ Constant KASKADE of type int │
├────────────────┼─────────────────────────────────────┤
│ MULTIPLICATIVE │ Constant MULTIPLICATIVE of type int │
└────────────────┴─────────────────────────────────────┘
Attributes Documentation
ADDITIVE: int = ADDITIVE
Constant ADDITIVE of type int
FULL: int = FULL
Constant FULL of type int
KASKADE: int = KASKADE
Constant KASKADE of type int
MULTIPLICATIVE: int = MULTIPLICATIVE
Constant MULTIPLICATIVE of type int
petsc4py.PETSc.PC.PatchConstructType
class petsc4py.PETSc.PC.PatchConstructType
Bases: object
The patch construction type.
Attributes Summary
┌───────────┬────────────────────────────────┐
│ PARDECOMP │ Constant PARDECOMP of type int │
├───────────┼────────────────────────────────┤
│ PYTHON │ Constant PYTHON of type int │
├───────────┼────────────────────────────────┤
│ STAR │ Constant STAR of type int │
├───────────┼────────────────────────────────┤
│ USER │ Constant USER of type int │
├───────────┼────────────────────────────────┤
│ VANKA │ Constant VANKA of type int │
└───────────┴────────────────────────────────┘
Attributes Documentation
PARDECOMP: int = PARDECOMP
Constant PARDECOMP of type int
PYTHON: int = PYTHON
Constant PYTHON of type int
STAR: int = STAR
Constant STAR of type int
USER: int = USER
Constant USER of type int
VANKA: int = VANKA
Constant VANKA of type int
petsc4py.PETSc.PC.Side
class petsc4py.PETSc.PC.Side
Bases: object
The manner in which the preconditioner is applied.
Attributes Summary
┌───────────┬────────────────────────────────┐
│ L │ Constant L of type int │
├───────────┼────────────────────────────────┤
│ LEFT │ Constant LEFT of type int │
├───────────┼────────────────────────────────┤
│ R │ Constant R of type int │
├───────────┼────────────────────────────────┤
│ RIGHT │ Constant RIGHT of type int │
├───────────┼────────────────────────────────┤
│ S │ Constant S of type int │
├───────────┼────────────────────────────────┤
│ SYMMETRIC │ Constant SYMMETRIC of type int │
└───────────┴────────────────────────────────┘
Attributes Documentation
L: int = L
Constant L of type int
LEFT: int = LEFT
Constant LEFT of type int
R: int = R
Constant R of type int
RIGHT: int = RIGHT
Constant RIGHT of type int
S: int = S
Constant S of type int
SYMMETRIC: int = SYMMETRIC
Constant SYMMETRIC of type int
petsc4py.PETSc.PC.Type
class petsc4py.PETSc.PC.Type
Bases: object
The preconditioner method.
Attributes Summary
┌────────────────────┬───────────────────────────────────────┐
│ ASM │ Object ASM of type str │
├────────────────────┼───────────────────────────────────────┤
│ BDDC │ Object BDDC of type str │
├────────────────────┼───────────────────────────────────────┤
│ BFBT │ Object BFBT of type str │
├────────────────────┼───────────────────────────────────────┤
│ BJACOBI │ Object BJACOBI of type str │
├────────────────────┼───────────────────────────────────────┤
│ CHOLESKY │ Object CHOLESKY of type str │
├────────────────────┼───────────────────────────────────────┤
│ CHOWILUVIENNACL │ Object CHOWILUVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ COMPOSITE │ Object COMPOSITE of type str │
├────────────────────┼───────────────────────────────────────┤
│ CP │ Object CP of type str │
├────────────────────┼───────────────────────────────────────┤
│ DEFLATION │ Object DEFLATION of type str │
├────────────────────┼───────────────────────────────────────┤
│ EISENSTAT │ Object EISENSTAT of type str │
├────────────────────┼───────────────────────────────────────┤
│ EXOTIC │ Object EXOTIC of type str │
├────────────────────┼───────────────────────────────────────┤
│ FIELDSPLIT │ Object FIELDSPLIT of type str │
├────────────────────┼───────────────────────────────────────┤
│ GALERKIN │ Object GALERKIN of type str │
├────────────────────┼───────────────────────────────────────┤
│ GAMG │ Object GAMG of type str │
├────────────────────┼───────────────────────────────────────┤
│ GASM │ Object GASM of type str │
├────────────────────┼───────────────────────────────────────┤
│ H2OPUS │ Object H2OPUS of type str │
├────────────────────┼───────────────────────────────────────┤
│ HMG │ Object HMG of type str │
├────────────────────┼───────────────────────────────────────┤
│ HPDDM │ Object HPDDM of type str │
├────────────────────┼───────────────────────────────────────┤
│ HYPRE │ Object HYPRE of type str │
├────────────────────┼───────────────────────────────────────┤
│ ICC │ Object ICC of type str │
├────────────────────┼───────────────────────────────────────┤
│ ILU │ Object ILU of type str │
├────────────────────┼───────────────────────────────────────┤
│ JACOBI │ Object JACOBI of type str │
├────────────────────┼───────────────────────────────────────┤
│ KACZMARZ │ Object KACZMARZ of type str │
├────────────────────┼───────────────────────────────────────┤
│ KSP │ Object KSP of type str │
├────────────────────┼───────────────────────────────────────┤
│ LMVM │ Object LMVM of type str │
├────────────────────┼───────────────────────────────────────┤
│ LSC │ Object LSC of type str │
├────────────────────┼───────────────────────────────────────┤
│ LU │ Object LU of type str │
├────────────────────┼───────────────────────────────────────┤
│ MAT │ Object MAT of type str │
├────────────────────┼───────────────────────────────────────┤
│ MG │ Object MG of type str │
├────────────────────┼───────────────────────────────────────┤
│ ML │ Object ML of type str │
├────────────────────┼───────────────────────────────────────┤
│ NN │ Object NN of type str │
├────────────────────┼───────────────────────────────────────┤
│ NONE │ Object NONE of type str │
├────────────────────┼───────────────────────────────────────┤
│ PARMS │ Object PARMS of type str │
├────────────────────┼───────────────────────────────────────┤
│ PATCH │ Object PATCH of type str │
├────────────────────┼───────────────────────────────────────┤
│ PBJACOBI │ Object PBJACOBI of type str │
├────────────────────┼───────────────────────────────────────┤
│ PFMG │ Object PFMG of type str │
├────────────────────┼───────────────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├────────────────────┼───────────────────────────────────────┤
│ QR │ Object QR of type str │
├────────────────────┼───────────────────────────────────────┤
│ REDISTRIBUTE │ Object REDISTRIBUTE of type str │
├────────────────────┼───────────────────────────────────────┤
│ REDUNDANT │ Object REDUNDANT of type str │
├────────────────────┼───────────────────────────────────────┤
│ ROWSCALINGVIENNACL │ Object ROWSCALINGVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SAVIENNACL │ Object SAVIENNACL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├────────────────────┼───────────────────────────────────────┤
│ SOR │ Object SOR of type str │
├────────────────────┼───────────────────────────────────────┤
│ SPAI │ Object SPAI of type str │
├────────────────────┼───────────────────────────────────────┤
│ SVD │ Object SVD of type str │
├────────────────────┼───────────────────────────────────────┤
│ SYSPFMG │ Object SYSPFMG of type str │
├────────────────────┼───────────────────────────────────────┤
│ TELESCOPE │ Object TELESCOPE of type str │
├────────────────────┼───────────────────────────────────────┤
│ TFS │ Object TFS of type str │
├────────────────────┼───────────────────────────────────────┤
│ VPBJACOBI │ Object VPBJACOBI of type str │
└────────────────────┴───────────────────────────────────────┘
Attributes Documentation
ASM: str = ASM
Object ASM of type str
BDDC: str = BDDC
Object BDDC of type str
BFBT: str = BFBT
Object BFBT of type str
BJACOBI: str = BJACOBI
Object BJACOBI of type str
CHOLESKY: str = CHOLESKY
Object CHOLESKY of type str
CHOWILUVIENNACL: str = CHOWILUVIENNACL
Object CHOWILUVIENNACL of type str
COMPOSITE: str = COMPOSITE
Object COMPOSITE of type str
CP: str = CP
Object CP of type str
DEFLATION: str = DEFLATION
Object DEFLATION of type str
EISENSTAT: str = EISENSTAT
Object EISENSTAT of type str
EXOTIC: str = EXOTIC
Object EXOTIC of type str
FIELDSPLIT: str = FIELDSPLIT
Object FIELDSPLIT of type str
GALERKIN: str = GALERKIN
Object GALERKIN of type str
GAMG: str = GAMG
Object GAMG of type str
GASM: str = GASM
Object GASM of type str
H2OPUS: str = H2OPUS
Object H2OPUS of type str
HMG: str = HMG
Object HMG of type str
HPDDM: str = HPDDM
Object HPDDM of type str
HYPRE: str = HYPRE
Object HYPRE of type str
ICC: str = ICC
Object ICC of type str
ILU: str = ILU
Object ILU of type str
JACOBI: str = JACOBI
Object JACOBI of type str
KACZMARZ: str = KACZMARZ
Object KACZMARZ of type str
KSP: str = KSP
Object KSP of type str
LMVM: str = LMVM
Object LMVM of type str
LSC: str = LSC
Object LSC of type str
LU: str = LU
Object LU of type str
MAT: str = MAT
Object MAT of type str
MG: str = MG
Object MG of type str
ML: str = ML
Object ML of type str
NN: str = NN
Object NN of type str
NONE: str = NONE
Object NONE of type str
PARMS: str = PARMS
Object PARMS of type str
PATCH: str = PATCH
Object PATCH of type str
PBJACOBI: str = PBJACOBI
Object PBJACOBI of type str
PFMG: str = PFMG
Object PFMG of type str
PYTHON: str = PYTHON
Object PYTHON of type str
QR: str = QR
Object QR of type str
REDISTRIBUTE: str = REDISTRIBUTE
Object REDISTRIBUTE of type str
REDUNDANT: str = REDUNDANT
Object REDUNDANT of type str
ROWSCALINGVIENNACL: str = ROWSCALINGVIENNACL
Object ROWSCALINGVIENNACL of type str
SAVIENNACL: str = SAVIENNACL
Object SAVIENNACL of type str
SHELL: str = SHELL
Object SHELL of type str
SOR: str = SOR
Object SOR of type str
SPAI: str = SPAI
Object SPAI of type str
SVD: str = SVD
Object SVD of type str
SYSPFMG: str = SYSPFMG
Object SYSPFMG of type str
TELESCOPE: str = TELESCOPE
Object TELESCOPE of type str
TFS: str = TFS
Object TFS of type str
VPBJACOBI: str = VPBJACOBI
Object VPBJACOBI of type str
Methods Summary
┌─────────────────────────────────────────────────┬───────────────────────────────────────┐
│ addCompositePCType(pc_type) │ Add a PC of the given type to the │
│ │ composite PC. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix(prefix) │ Append to the prefix used for all the │
│ │ PC options. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ apply(x, y) │ Apply the PC to a vector. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ applySymmetricLeft(x, y) │ Apply the left part of a symmetric PC │
│ │ to a vector. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ applySymmetricRight(x, y) │ Apply the right part of a symmetric │
│ │ PC to a vector. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ applyTranspose(x, y) │ Apply the transpose of the PC to a │
│ │ vector. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create an empty PC. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ createPython([context, comm]) │ Create a preconditioner of Python │
│ │ type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the PC that was created with │
│ │ create. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getASMSubKSP() │ Return the local KSP object for all │
│ │ blocks on this process. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getCompositePC(n) │ Return a component of the composite │
│ │ PC. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM associated with the PC. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getDeflationCoarseKSP() │ Return the coarse problem KSP. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getDeflationPC() │ Return the additional preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFactorMatrix() │ Return the factored matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFactorSolverType() │ Return the solver package used to │
│ │ perform the factorization. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFailedReason() │ Return the reason the PC terminated. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldSplitSchurGetSubKSP() │ Return the KSP for the Schur │
│ │ complement based splits. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldSplitSubIS(splitname) │ Return the IS associated with a given │
│ │ name. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldSplitSubKSP() │ Return the KSP for all splits. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHPDDMCoarseCorrectionType() │ Return the coarse correction type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHPDDMComplexities() │ Compute the grid and operator │
│ │ complexities. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHPDDMSTShareSubKSP() │ Return true if the KSP in SLEPc ST │
│ │ and the subdomain solver is shared. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHYPREType() │ Return the Type.HYPRE type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getKSP() │ Return the KSP if the PC is Type.KSP. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGCoarseSolve() │ Return the KSP used on the coarse │
│ │ grid. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGInterpolation(level) │ Return the interpolation operator for │
│ │ the given level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGLevels() │ Return the number of MG levels. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGRScale(level) │ Return the pointwise scaling for the │
│ │ restriction operator on the given │
│ │ level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGRestriction(level) │ Return the restriction operator for │
│ │ the given level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGSmoother(level) │ Return the KSP to be used as a │
│ │ smoother. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGSmootherDown(level) │ Return the KSP to be used as a │
│ │ smoother before coarse grid │
│ │ correction. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGSmootherUp(level) │ Return the KSP to be used as a │
│ │ smoother after coarse grid │
│ │ correction. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMGType() │ Return the form of multigrid. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getOperators() │ Return the matrices associated with a │
│ │ linear system. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for all the PC │
│ │ options. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPatchSubKSP() │ Return the local KSP object for all │
│ │ blocks on this process. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the preconditioner type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ getUseAmat() │ Return the flag to indicate if PC is │
│ │ applied to A or P. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ matApply(x, y) │ Apply the PC to many vectors stored │
│ │ as Mat.Type.DENSE. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Reset the PC, removing any allocated │
│ │ vectors and matrices. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setASMLocalSubdomains(nsd[, is_sub, │ Set the local subdomains. │
│ is_local]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setASMOverlap(overlap) │ Set the overlap between a pair of │
│ │ subdomains. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setASMSortIndices(dosort) │ Set to sort subdomain indices. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setASMTotalSubdomains(nsd[, is_sub, │ Set the subdomains for all processes. │
│ is_local]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setASMType(asmtype) │ Set the type of restriction and │
│ │ interpolation. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCChangeOfBasisMat(T[, │ Set a user defined change of basis │
│ interior]) │ for degrees of freedom. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCCoarseningRatio(cratio) │ Set the coarsening ratio used in the │
│ │ multilevel version. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDirichletBoundaries(bndr) │ Set the IS defining Dirichlet │
│ │ boundaries for the global problem. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDirichletBoundariesLocal(bndr) │ Set the IS defining Dirichlet │
│ │ boundaries in local ordering. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDiscreteGradient(G[, order, │ Set the discrete gradient. │
│ field, ...]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDivergenceMat(div[, trans, │ Set the linear operator representing │
│ l2l]) │ ∫ div(u)•p dx. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDofsSplitting(isfields) │ Set the index set(s) defining fields │
│ │ of the global matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCDofsSplittingLocal(isfields) │ Set the index set(s) defining fields │
│ │ of the local subdomain matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCLevels(levels) │ Set the maximum number of additional │
│ │ levels allowed. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCLocalAdjacency(csr) │ Provide a custom connectivity graph │
│ │ for local dofs. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCNeumannBoundaries(bndr) │ Set the IS defining Neumann │
│ │ boundaries for the global problem. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCNeumannBoundariesLocal(bndr) │ Set the IS defining Neumann │
│ │ boundaries in local ordering. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCPrimalVerticesIS(primv) │ Set additional user defined primal │
│ │ vertices. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBDDCPrimalVerticesLocalIS(primv) │ Set additional user defined primal │
│ │ vertices. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCompositeType(ctype) │ Set the type of composite │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setCoordinates(coordinates) │ Set the coordinates for the nodes on │
│ │ the local process. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM that may be used by some │
│ │ preconditioners. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationCoarseMat(mat) │ Set the coarse problem matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationCorrectionFactor(fact) │ Set the coarse problem correction │
│ │ factor. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationInitOnly(flg) │ Set to only perform the │
│ │ initialization. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationLevels(levels) │ Set the maximum level of deflation │
│ │ nesting. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationProjectionNullSpaceMat(mat) │ Set the projection null space matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationReductionFactor(red) │ Set the reduction factor for the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationSpace(W, transpose) │ Set the deflation space matrix or its │
│ │ (Hermitian) transpose. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setDeflationSpaceToCompute(space_type, │ Set the deflation space type. │
│ size) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorLevels(levels) │ Set the number of levels of fill. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorOrdering([ord_type, nzdiag, │ Set options for the matrix │
│ reuse]) │ factorization reordering. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorPivot([zeropivot, inblocks]) │ Set options for matrix factorization │
│ │ pivoting. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorSetUpSolverType() │ Set up the factorization solver. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorShift([shift_type, amount]) │ Set options for shifting diagonal │
│ │ entries of a matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFactorSolverType(solver) │ Set the solver package used to │
│ │ perform the factorization. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFailedReason(reason) │ Set the reason the PC terminated. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldSplitFields(bsize, *fields) │ Sets the elements for the field │
│ │ split. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldSplitIS(*fields) │ Set the elements for the field split │
│ │ by IS. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldSplitSchurFactType(ctype) │ Set the type of approximate block │
│ │ factorization. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldSplitSchurPreType(ptype[, pre]) │ Set from what operator the PC is │
│ │ constructed. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldSplitType(ctype) │ Set the type of composition of a │
│ │ field split preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set various PC parameters from user │
│ │ options. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGAMGLevels(levels) │ Set the maximum number of levels. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGAMGSmooths(smooths) │ Set the number of smoothing steps │
│ │ used on all levels. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGAMGType(gamgtype) │ Set the type of algorithm. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGASMOverlap(overlap) │ Set the overlap between a pair of │
│ │ subdomains. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGASMType(gasmtype) │ Set the type of restriction and │
│ │ interpolation. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMAuxiliaryMat(uis, uaux) │ Set the auxiliary matrix used by the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMCoarseCorrectionType(correction_type) │ Set the coarse correction type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMDeflationMat(uis, U) │ Set the deflation space used to │
│ │ assemble a coarse operator. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMHasNeumannMat(has) │ Set to indicate that the Mat passed │
│ │ to the PC is the local Neumann │
│ │ matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHPDDMRHSMat(B) │ Set the right-hand side matrix of the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPREAMSSetInteriorNodes(interior) │ Set the list of interior nodes to a │
│ │ zero conductivity region. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPREDiscreteCurl(mat) │ Set the discrete curl matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPREDiscreteGradient(mat) │ Set the discrete gradient matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPRESetAlphaPoissonMatrix(mat) │ Set the vector Poisson matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPRESetBetaPoissonMatrix([mat]) │ Set the Posson matrix. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPRESetEdgeConstantVectors(ozz, zoz[, │ Set the representation of the │
│ zzo]) │ constant vector fields in the edge │
│ │ element basis. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPRESetInterpolations(dim[, RT_Pi_Full, │ Set the interpolation matrices. │
│ ...]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHYPREType(hypretype) │ Set the Type.HYPRE type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGCycleType(cycle_type) │ Set the type of cycles. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGCycleTypeOnLevel(level, cycle_type) │ Set the type of cycle on the given │
│ │ level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGInterpolation(level, mat) │ Set the interpolation operator for │
│ │ the given level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGLevels(levels) │ Set the number of MG levels. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGR(level, r) │ Set the vector where the residual is │
│ │ stored. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGRScale(level, rscale) │ Set the pointwise scaling for the │
│ │ restriction operator on the given │
│ │ level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGRestriction(level, mat) │ Set the restriction operator for the │
│ │ given level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGRhs(level, rhs) │ Set the vector where the right-hand │
│ │ side is stored. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGType(mgtype) │ Set the form of multigrid. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMGX(level, x) │ Set the vector where the solution is │
│ │ stored. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setOperators([A, P]) │ Set the matrices associated with the │
│ │ linear system. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for all the PC │
│ │ options. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchCellNumbering(sec) │ Set the cell numbering. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeFunction(function[, args, │ Set compute operator callbacks. │
│ kargs]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeFunctionInteriorFacets(function) │ Set compute operator callbacks. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeOperator(operator[, args, │ Set compute operator callbacks. │
│ kargs]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeOperatorInteriorFacets(operator) │ Set compute operator callbacks. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchConstructType(typ[, operator, args, │ Set compute operator callbacks. │
│ ...]) │ │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchDiscretisationInfo(dms, bs, ...) │ Set discretisation info. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext(context) │ Set the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setReusePreconditioner(flag) │ Set to indicate the preconditioner is │
│ │ to be reused. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAIBlockSize(n) │ Set the block size of the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAICacheSize(size) │ Set the cache size. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAIEpsilon(val) │ Set the tolerance for the │
│ │ preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAIMax(maxval) │ Set the size of working buffers in │
│ │ the preconditioner. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAIMaxNew(maxval) │ Set the maximum number of new │
│ │ non-zero candidates per step. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAINBSteps(nbsteps) │ Set the maximum number of improvement │
│ │ steps per row. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAISp(sym) │ Set to specify a symmetric sparsity │
│ │ pattern. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSPAIVerbose(level) │ Set the verbosity level. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setType(pc_type) │ Set the preconditioner type. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for the PC. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setUpOnBlocks() │ Set up the PC for each block. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ setUseAmat(flag) │ Set to indicate to apply PC to A and │
│ │ not P. │
├─────────────────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the PC object. │
└─────────────────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
addCompositePCType(pc_type)
Add a PC of the given type to the composite PC.
Collective.
Parameters
pc_type (Type | str) -- The type of the preconditioner to add.
Return type
None
SEE ALSO:
PCCompositeAddPCType
Source code at petsc4py/PETSc/PC.pyx:1665
appendOptionsPrefix(prefix)
Append to the prefix used for all the PC options.
Logically collective.
Parameters
prefix (str | None) -- The prefix to append to the current prefix.
Return type
None
SEE ALSO:
Working with PETSc options, PCAppendOptionsPrefix
Source code at petsc4py/PETSc/PC.pyx:355
apply(x, y)
Apply the PC to a vector.
Collective.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector, cannot be the same as x.
Return type
None
SEE ALSO:
PCApply
Source code at petsc4py/PETSc/PC.pyx:581
applySymmetricLeft(x, y)
Apply the left part of a symmetric PC to a vector.
Collective.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector, cannot be the same as x.
Return type
None
SEE ALSO:
PCApplySymmetricLeft
Source code at petsc4py/PETSc/PC.pyx:641
applySymmetricRight(x, y)
Apply the right part of a symmetric PC to a vector.
Collective.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector, cannot be the same as x.
Return type
None
SEE ALSO:
PCApplySymmetricRight
Source code at petsc4py/PETSc/PC.pyx:660
applyTranspose(x, y)
Apply the transpose of the PC to a vector.
Collective.
For complex numbers this applies the non-Hermitian transpose.
Parameters
• x (Vec) -- The input vector.
• y (Vec) -- The output vector, cannot be the same as x.
Return type
None
SEE ALSO:
PCApply
Source code at petsc4py/PETSc/PC.pyx:619
create(comm=None)
Create an empty PC.
Collective.
The default preconditioner for sparse matrices is ILU or ICC with 0 fill on one process and
block Jacobi (BJACOBI) with ILU or ICC in parallel. For dense matrices it is always None.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
destroy, PCCreate
Source code at petsc4py/PETSc/PC.pyx:264
createPython(context=None, comm=None)
Create a preconditioner of Python type.
Collective.
Parameters
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python preconditioner type, setType, setPythonContext, PC.Type.PYTHON
Source code at petsc4py/PETSc/PC.pyx:742
destroy()
Destroy the PC that was created with create.
Collective.
SEE ALSO:
PCDestroy
Source code at petsc4py/PETSc/PC.pyx:250
Return type
Self
getASMSubKSP()
Return the local KSP object for all blocks on this process.
Not collective.
SEE ALSO:
PCASMGetSubKSP
Source code at petsc4py/PETSc/PC.pyx:946
Return type
list[KSP]
getCompositePC(n)
Return a component of the composite PC.
Not collective.
Parameters
n (int) -- The index of the PC in the composition.
Return type
None
SEE ALSO:
PCCompositeGetPC
Source code at petsc4py/PETSc/PC.pyx:1644
getDM()
Return the DM associated with the PC.
Not collective.
SEE ALSO:
PCGetDM
Source code at petsc4py/PETSc/PC.pyx:681
Return type
DM
getDeflationCoarseKSP()
Return the coarse problem KSP.
Not collective.
SEE ALSO:
PCDeflationGetCoarseKSP
Source code at petsc4py/PETSc/PC.pyx:2910
Return type
KSP
getDeflationPC()
Return the additional preconditioner.
Not collective.
SEE ALSO:
PCDeflationGetPC
Source code at petsc4py/PETSc/PC.pyx:2925
Return type
PC
getFactorMatrix()
Return the factored matrix.
Not collective.
SEE ALSO:
PCFactorGetMatrix
Source code at petsc4py/PETSc/PC.pyx:1434
Return type
Mat
getFactorSolverType()
Return the solver package used to perform the factorization.
Not collective.
SEE ALSO:
PCFactorGetMatSolverType
Source code at petsc4py/PETSc/PC.pyx:1290
Return type
str
getFailedReason()
Return the reason the PC terminated.
Not collective.
After a call to KSPCheckDot() or KSPCheckNorm() inside a KSPSolve(), or after a call to
PCReduceFailedReason() this is the maximum reason over all ranks in the PC communicator and
hence logically collective. Otherwise it is the local value.
SEE ALSO:
PCGetFailedReason
Source code at petsc4py/PETSc/PC.pyx:520
Return type
FailedReason
getFieldSplitSchurGetSubKSP()
Return the KSP for the Schur complement based splits.
Not collective.
SEE ALSO:
PCFieldSplitSchurGetSubKSP, PCFieldSplitGetSubKSP
Source code at petsc4py/PETSc/PC.pyx:1545
Return type
list[KSP]
getFieldSplitSubIS(splitname)
Return the IS associated with a given name.
Not collective.
SEE ALSO:
PCFieldSplitGetIS
Source code at petsc4py/PETSc/PC.pyx:1565
Parameters
splitname (str)
Return type
IS
getFieldSplitSubKSP()
Return the KSP for all splits.
Not collective.
SEE ALSO:
PCFieldSplitGetSubKSP
Source code at petsc4py/PETSc/PC.pyx:1525
Return type
list[KSP]
getHPDDMCoarseCorrectionType()
Return the coarse correction type.
Not collective.
SEE ALSO:
PCHPDDMGetCoarseCorrectionType
Source code at petsc4py/PETSc/PC.pyx:2562
Return type
HPDDMCoarseCorrectionType
getHPDDMComplexities()
Compute the grid and operator complexities.
Collective.
SEE ALSO:
PCHPDDMGetComplexities
Source code at petsc4py/PETSc/PC.pyx:2512
Return type
tuple[float, float]
getHPDDMSTShareSubKSP()
Return true if the KSP in SLEPc ST and the subdomain solver is shared.
Not collective.
SEE ALSO:
PCHPDDMGetSTShareSubKSP
Source code at petsc4py/PETSc/PC.pyx:2576
Return type
bool
getHYPREType()
Return the Type.HYPRE type.
Not collective.
SEE ALSO:
PCHYPREGetType
Source code at petsc4py/PETSc/PC.pyx:1076
Return type
str
getKSP()
Return the KSP if the PC is Type.KSP.
Not collective.
SEE ALSO:
PCKSPGetKSP
Source code at petsc4py/PETSc/PC.pyx:1686
Return type
KSP
getMGCoarseSolve()
Return the KSP used on the coarse grid.
Not collective.
SEE ALSO:
PCMGGetCoarseSolve
Source code at petsc4py/PETSc/PC.pyx:1762
Return type
KSP
getMGInterpolation(level)
Return the interpolation operator for the given level.
Logically collective.
Parameters
level (int) -- The level where interpolation is defined from level-1 to level.
Return type
Mat
SEE ALSO:
PCMGGetInterpolation
Source code at petsc4py/PETSc/PC.pyx:1797
getMGLevels()
Return the number of MG levels.
Not collective.
SEE ALSO:
PCMGGetLevels
Source code at petsc4py/PETSc/PC.pyx:1730
Return type
int
getMGRScale(level)
Return the pointwise scaling for the restriction operator on the given level.
Logically collective.
Parameters
level (int) -- The level where restriction is defined from level to level-1.
Return type
Vec
SEE ALSO:
PCMGGetRScale
Source code at petsc4py/PETSc/PC.pyx:1879
getMGRestriction(level)
Return the restriction operator for the given level.
Logically collective.
Parameters
level (int) -- The level where restriction is defined from level to level-1.
Return type
Mat
SEE ALSO:
PCMGGetRestriction
Source code at petsc4py/PETSc/PC.pyx:1838
getMGSmoother(level)
Return the KSP to be used as a smoother.
Not collective.
Parameters
level (int) -- The level of the smoother.
Return type
KSP
SEE ALSO:
getMGSmootherDown, getMGSmootherUp, PCMGGetSmoother
Source code at petsc4py/PETSc/PC.pyx:1900
getMGSmootherDown(level)
Return the KSP to be used as a smoother before coarse grid correction.
Not collective.
Parameters
level (int) -- The level of the smoother.
Return type
KSP
SEE ALSO:
getMGSmoother, getMGSmootherUp, PCMGGetSmootherDown
Source code at petsc4py/PETSc/PC.pyx:1921
getMGSmootherUp(level)
Return the KSP to be used as a smoother after coarse grid correction.
Not collective.
Parameters
level (int) -- The level of the smoother.
Return type
KSP
SEE ALSO:
getMGSmootherDown, getMGSmoother, PCMGGetSmootherUp
Source code at petsc4py/PETSc/PC.pyx:1942
getMGType()
Return the form of multigrid.
Logically collective.
SEE ALSO:
PCMGGetType
Source code at petsc4py/PETSc/PC.pyx:1703
Return type
MGType
getOperators()
Return the matrices associated with a linear system.
Not collective.
SEE ALSO:
setOperators, PCGetOperators
Source code at petsc4py/PETSc/PC.pyx:416
Return type
tuple[Mat, Mat]
getOptionsPrefix()
Return the prefix used for all the PC options.
Not collective.
SEE ALSO:
Working with PETSc options, PCGetOptionsPrefix
Source code at petsc4py/PETSc/PC.pyx:341
Return type
str
getPatchSubKSP()
Return the local KSP object for all blocks on this process.
Not collective.
Source code at petsc4py/PETSc/PC.pyx:2372
Return type
list[KSP]
getPythonContext()
Return the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python preconditioner type, setPythonContext
Source code at petsc4py/PETSc/PC.pyx:779
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the preconditioner.
Not collective.
SEE ALSO:
PETSc Python preconditioner type, setPythonContext, setPythonType, PCPythonGetType
Source code at petsc4py/PETSc/PC.pyx:808
Return type
str
getType()
Return the preconditioner type.
Not collective.
SEE ALSO:
setType, PCGetType
Source code at petsc4py/PETSc/PC.pyx:308
Return type
str
getUseAmat()
Return the flag to indicate if PC is applied to A or P.
Logically collective.
Returns
flag -- True if A is used and False if P.
Return type
bool
SEE ALSO:
setUseAmat, PCGetUseAmat
Source code at petsc4py/PETSc/PC.pyx:458
matApply(x, y)
Apply the PC to many vectors stored as Mat.Type.DENSE.
Collective.
Parameters
• x (Mat) -- The input matrix.
• y (Mat) -- The output matrix, cannot be the same as x.
Return type
None
SEE ALSO:
PCMatApply, PCApply
Source code at petsc4py/PETSc/PC.pyx:600
reset()
Reset the PC, removing any allocated vectors and matrices.
Collective.
SEE ALSO:
PCReset
Source code at petsc4py/PETSc/PC.pyx:553
Return type
None
setASMLocalSubdomains(nsd, is_sub=None, is_local=None)
Set the local subdomains.
Collective.
Parameters
• nsd (int) -- The number of subdomains for this process.
• is_sub (Sequence[IS] | None) -- Defines the subdomains for this process or None to
determine internally.
• is_local (Sequence[IS] | None) -- Defines the local part of the subdomains for
this process, only used for PC.ASMType.RESTRICT.
Return type
None
SEE ALSO:
setASMTotalSubdomains, PCASMSetLocalSubdomains
Source code at petsc4py/PETSc/PC.pyx:860
setASMOverlap(overlap)
Set the overlap between a pair of subdomains.
Logically collective.
Parameters
overlap (int) -- The amount of overlap between subdomains.
Return type
None
SEE ALSO:
PCASMSetOverlap
Source code at petsc4py/PETSc/PC.pyx:842
setASMSortIndices(dosort)
Set to sort subdomain indices.
Logically collective.
Parameters
dosort (bool) -- Set to True to sort indices
Return type
None
SEE ALSO:
PCASMSetSortIndices
Source code at petsc4py/PETSc/PC.pyx:961
setASMTotalSubdomains(nsd, is_sub=None, is_local=None)
Set the subdomains for all processes.
Collective.
Parameters
• nsd (int) -- The number of subdomains for all processes.
• is_sub (Sequence[IS] | None) -- Defines the subdomains for all processes or None
to determine internally.
• is_local (Sequence[IS] | None) -- Defines the local part of the subdomains for
this process, only used for PC.ASMType.RESTRICT.
Return type
None
SEE ALSO:
setASMLocalSubdomains, PCASMSetTotalSubdomains
Source code at petsc4py/PETSc/PC.pyx:903
setASMType(asmtype)
Set the type of restriction and interpolation.
Logically collective.
Parameters
asmtype (ASMType) -- The type of ASM you wish to use.
Return type
None
SEE ALSO:
PCASMSetType
Source code at petsc4py/PETSc/PC.pyx:824
setBDDCChangeOfBasisMat(T, interior=False)
Set a user defined change of basis for degrees of freedom.
Collective.
Parameters
• T (Mat) -- The matrix representing the change of basis.
• interior (bool) -- Enable to indicate the change of basis affects interior degrees
of freedom.
Return type
None
SEE ALSO:
PCBDDCSetChangeOfBasisMat
Source code at petsc4py/PETSc/PC.pyx:2165
setBDDCCoarseningRatio(cratio)
Set the coarsening ratio used in the multilevel version.
Logically collective.
Parameters
cratio (int) -- The coarsening ratio at the coarse level
Return type
None
SEE ALSO:
PCBDDCSetCoarseningRatio
Source code at petsc4py/PETSc/PC.pyx:2220
setBDDCDirichletBoundaries(bndr)
Set the IS defining Dirichlet boundaries for the global problem.
Collective.
Parameters
bndr (IS) -- The parallel IS defining Dirichlet boundaries.
Return type
None
SEE ALSO:
PCBDDCSetDirichletBoundaries
Source code at petsc4py/PETSc/PC.pyx:2256
setBDDCDirichletBoundariesLocal(bndr)
Set the IS defining Dirichlet boundaries in local ordering.
Collective.
Parameters
bndr (IS) -- The parallel IS defining Dirichlet boundaries in local ordering.
Return type
None
SEE ALSO:
setBDDCDirichletBoundaries, PCBDDCSetDirichletBoundariesLocal
Source code at petsc4py/PETSc/PC.pyx:2273
setBDDCDiscreteGradient(G, order=1, field=1, gord=True, conforming=True)
Set the discrete gradient.
Collective.
Parameters
• G (Mat) -- The discrete gradient matrix in Mat.Type.AIJ format.
• order (int) -- The order of the Nedelec space.
• field (int) -- The field number of the Nedelec degrees of freedom. This is not
used if no fields have been specified.
• gord (bool) -- Enable to use global ordering in the rows of G.
• conforming (bool) -- Enable if the mesh is conforming.
Return type
None
SEE ALSO:
PCBDDCSetDiscreteGradient
Source code at petsc4py/PETSc/PC.pyx:2129
setBDDCDivergenceMat(div, trans=False, l2l=None)
Set the linear operator representing ∫ div(u)•p dx.
Collective.
Parameters
• div (Mat) -- The matrix in Mat.Type.IS format.
• trans (bool) -- If True, the pressure/velocity is in the trial/test space
respectively. If False the pressure/velocity is in the test/trial space.
• l2l (IS | None) -- Optional IS describing the local to local map for velocities.
Return type
None
SEE ALSO:
PCBDDCSetDivergenceMat
Source code at petsc4py/PETSc/PC.pyx:2103
setBDDCDofsSplitting(isfields)
Set the index set(s) defining fields of the global matrix.
Collective.
Parameters
isfields (IS | Sequence[IS]) -- The sequence of IS describing the fields in global
ordering.
Return type
None
SEE ALSO:
PCBDDCSetDofsSplitting
Source code at petsc4py/PETSc/PC.pyx:2324
setBDDCDofsSplittingLocal(isfields)
Set the index set(s) defining fields of the local subdomain matrix.
Collective.
Not all nodes need to be listed. Unlisted nodes will belong to the complement field.
Parameters
isfields (IS | Sequence[IS]) -- The sequence of IS describing the fields in local
ordering.
Return type
None
SEE ALSO:
PCBDDCSetDofsSplittingLocal
Source code at petsc4py/PETSc/PC.pyx:2346
setBDDCLevels(levels)
Set the maximum number of additional levels allowed.
Logically collective.
Parameters
levels (int) -- The maximum number of levels.
Return type
None
SEE ALSO:
PCBDDCSetLevels
Source code at petsc4py/PETSc/PC.pyx:2238
setBDDCLocalAdjacency(csr)
Provide a custom connectivity graph for local dofs.
Not collective.
Parameters
csr (CSRIndicesSpec) -- Compressed sparse row layout information.
Return type
None
SEE ALSO:
PCBDDCSetLocalAdjacencyGraph
Source code at petsc4py/PETSc/PC.pyx:2073
setBDDCNeumannBoundaries(bndr)
Set the IS defining Neumann boundaries for the global problem.
Collective.
Parameters
bndr (IS) -- The parallel IS defining Neumann boundaries.
Return type
None
SEE ALSO:
PCBDDCSetNeumannBoundaries
Source code at petsc4py/PETSc/PC.pyx:2290
setBDDCNeumannBoundariesLocal(bndr)
Set the IS defining Neumann boundaries in local ordering.
Collective.
Parameters
bndr (IS) -- The parallel IS defining Neumann boundaries in local ordering.
Return type
None
SEE ALSO:
setBDDCNeumannBoundaries, PCBDDCSetNeumannBoundariesLocal
Source code at petsc4py/PETSc/PC.pyx:2307
setBDDCPrimalVerticesIS(primv)
Set additional user defined primal vertices.
Collective.
Parameters
primv (IS) -- The IS of primal vertices in global numbering.
Return type
None
SEE ALSO:
PCBDDCSetPrimalVerticesIS
Source code at petsc4py/PETSc/PC.pyx:2186
setBDDCPrimalVerticesLocalIS(primv)
Set additional user defined primal vertices.
Collective.
Parameters
primv (IS) -- The IS of primal vertices in local numbering.
Return type
None
SEE ALSO:
PCBDDCSetPrimalVerticesLocalIS
Source code at petsc4py/PETSc/PC.pyx:2203
setCompositeType(ctype)
Set the type of composite preconditioner.
Logically collective.
Parameters
ctype (CompositeType) -- The type of composition.
Return type
None
SEE ALSO:
PCCompositeSetType
Source code at petsc4py/PETSc/PC.pyx:1626
setCoordinates(coordinates)
Set the coordinates for the nodes on the local process.
Collective.
Parameters
coordinates (Sequence[Sequence[float]]) -- The two dimensional coordinate array.
Return type
None
SEE ALSO:
PCSetCoordinates
Source code at petsc4py/PETSc/PC.pyx:715
setDM(dm)
Set the DM that may be used by some preconditioners.
Logically collective.
Parameters
dm (DM) -- The DM object.
Return type
None
SEE ALSO:
PCSetDM
Source code at petsc4py/PETSc/PC.pyx:698
setDeflationCoarseMat(mat)
Set the coarse problem matrix.
Collective.
Parameters
mat (Mat) -- The coarse problem matrix.
Return type
None
SEE ALSO:
PCDeflationSetCoarseMat
Source code at petsc4py/PETSc/PC.pyx:2893
setDeflationCorrectionFactor(fact)
Set the coarse problem correction factor.
Logically collective.
Parameters
fact (float) -- The correction factor.
Return type
None
SEE ALSO:
PCDeflationSetCorrectionFactor
Source code at petsc4py/PETSc/PC.pyx:2816
setDeflationInitOnly(flg)
Set to only perform the initialization.
Logically collective.
Sets initial guess to the solution on the deflation space but does not apply the deflation
preconditioner. The additional preconditioner is still applied.
Parameters
flg (bool) -- Enable to only initialize the preconditioner.
Return type
None
SEE ALSO:
PCDeflationSetInitOnly
Source code at petsc4py/PETSc/PC.pyx:2758
setDeflationLevels(levels)
Set the maximum level of deflation nesting.
Logically collective.
Parameters
levels (int) -- The maximum deflation level.
Return type
None
SEE ALSO:
PCDeflationSetLevels
Source code at petsc4py/PETSc/PC.pyx:2780
setDeflationProjectionNullSpaceMat(mat)
Set the projection null space matrix.
Collective.
Parameters
mat (Mat) -- The projection null space matrix.
Return type
None
SEE ALSO:
PCDeflationSetProjectionNullSpaceMat
Source code at petsc4py/PETSc/PC.pyx:2876
setDeflationReductionFactor(red)
Set the reduction factor for the preconditioner.
Logically collective.
Parameters
red (int) -- The reduction factor or DEFAULT.
Return type
None
SEE ALSO:
PCDeflationSetReductionFactor
Source code at petsc4py/PETSc/PC.pyx:2798
setDeflationSpace(W, transpose)
Set the deflation space matrix or its (Hermitian) transpose.
Logically collective.
Parameters
• W (Mat) -- The deflation matrix.
• transpose (bool) -- Enable to indicate that W is an explicit transpose of the
deflation matrix.
Return type
None
SEE ALSO:
PCDeflationSetSpace
Source code at petsc4py/PETSc/PC.pyx:2855
setDeflationSpaceToCompute(space_type, size)
Set the deflation space type.
Logically collective.
Parameters
• space_type (DeflationSpaceType) -- The deflation space type.
• size (int) -- The size of the space to compute
Return type
None
SEE ALSO:
PCDeflationSetSpaceToCompute
Source code at petsc4py/PETSc/PC.pyx:2834
setFactorLevels(levels)
Set the number of levels of fill.
Logically collective.
Parameters
levels (int) -- The number of levels to fill.
Return type
None
SEE ALSO:
PCFactorSetLevels
Source code at petsc4py/PETSc/PC.pyx:1416
setFactorOrdering(ord_type=None, nzdiag=None, reuse=None)
Set options for the matrix factorization reordering.
Logically collective.
Parameters
• ord_type (str | None) -- The name of the matrix ordering or None to leave
unchanged.
• nzdiag (float | None) -- Threshold to consider diagonal entries in the matrix as
zero.
• reuse (bool | None) -- Enable to reuse the ordering of a factored matrix.
Return type
None
SEE ALSO:
PCFactorSetMatOrderingType, PCFactorReorderForNonzeroDiagonal, PCFactorSetReuseOrdering
Source code at petsc4py/PETSc/PC.pyx:1320
setFactorPivot(zeropivot=None, inblocks=None)
Set options for matrix factorization pivoting.
Logically collective.
Parameters
• zeropivot (float | None) -- The size at which smaller pivots are treated as zero.
• inblocks (bool | None) -- Enable to allow pivoting while factoring in blocks.
Return type
None
SEE ALSO:
PCFactorSetZeroPivot, PCFactorSetPivotInBlocks
Source code at petsc4py/PETSc/PC.pyx:1357
setFactorSetUpSolverType()
Set up the factorization solver.
Collective.
This can be called after KSP.setOperators or PC.setOperators, causes MatGetFactor to be
called so then one may set the options for that particular factorization object.
SEE ALSO:
Working with PETSc options, PCFactorSetUpMatSolverType
Source code at petsc4py/PETSc/PC.pyx:1304
Return type
None
setFactorShift(shift_type=None, amount=None)
Set options for shifting diagonal entries of a matrix.
Logically collective.
Parameters
• shift_type (FactorShiftType | None) -- The type of shift, or None to leave
unchanged.
• amount (float | None) -- The amount of shift. Specify DEFAULT to determine
internally or None to leave unchanged.
Return type
None
SEE ALSO:
PCFactorSetShiftType, PCFactorSetShiftAmount
Source code at petsc4py/PETSc/PC.pyx:1386
setFactorSolverType(solver)
Set the solver package used to perform the factorization.
Logically collective.
Parameters
solver (SolverType | str) -- The solver package used to factorize.
Return type
None
SEE ALSO:
PCFactorSetMatSolverType
Source code at petsc4py/PETSc/PC.pyx:1271
setFailedReason(reason)
Set the reason the PC terminated.
Logically collective.
Parameters
reason (FailedReason | str) -- the reason the PC terminated
Return type
None
SEE ALSO:
PCSetFailedReason
Source code at petsc4py/PETSc/PC.pyx:502
setFieldSplitFields(bsize, *fields)
Sets the elements for the field split.
Collective.
Parameters
• bsize (int) -- The block size
• fields (Tuple[str, Sequence[int]]) -- A sequence of tuples containing the split
name and a sequence of integers that define the elements in the split.
Return type
None
SEE ALSO:
PCFieldSplitSetBlockSize, PCFieldSplitSetFields
Source code at petsc4py/PETSc/PC.pyx:1495
setFieldSplitIS(*fields)
Set the elements for the field split by IS.
Logically collective.
Solve options for this split will be available under the prefix -fieldsplit_SPLITNAME_*.
Parameters
fields (Tuple[str, IS]) -- A sequence of tuples containing the split name and the IS
that defines the elements in the split.
Return type
None
SEE ALSO:
Working with PETSc options, PCFieldSplitSetIS
Source code at petsc4py/PETSc/PC.pyx:1469
setFieldSplitSchurFactType(ctype)
Set the type of approximate block factorization.
Collective.
Parameters
ctype (FieldSplitSchurFactType) -- The type indicating which blocks to retain.
Return type
None
SEE ALSO:
PCFieldSplitSetSchurFactType
Source code at petsc4py/PETSc/PC.pyx:1581
setFieldSplitSchurPreType(ptype, pre=None)
Set from what operator the PC is constructed.
Collective.
Parameters
• ptype (FieldSplitSchurPreType) -- The type of matrix to use for preconditioning
the Schur complement.
• pre (Mat | None) -- The optional matrix to use for preconditioning.
Return type
None
SEE ALSO:
PCFieldSplitSetSchurPre
Source code at petsc4py/PETSc/PC.pyx:1599
setFieldSplitType(ctype)
Set the type of composition of a field split preconditioner.
Collective.
Parameters
ctype (CompositeType) -- The type of composition.
Return type
None
SEE ALSO:
PCFieldSplitSetType
Source code at petsc4py/PETSc/PC.pyx:1451
setFromOptions()
Set various PC parameters from user options.
Collective.
SEE ALSO:
Working with PETSc options, PCSetFromOptions
Source code at petsc4py/PETSc/PC.pyx:374
Return type
None
setGAMGLevels(levels)
Set the maximum number of levels.
Not collective.
Parameters
levels (int) -- The maximum number of levels to use.
Return type
None
SEE ALSO:
PCGAMGSetNlevels
Source code at petsc4py/PETSc/PC.pyx:1038
setGAMGSmooths(smooths)
Set the number of smoothing steps used on all levels.
Logically collective.
Parameters
smooths (int) -- The maximum number of smooths.
Return type
None
SEE ALSO:
PCGAMGSetNSmooths
Source code at petsc4py/PETSc/PC.pyx:1056
setGAMGType(gamgtype)
Set the type of algorithm.
Collective.
Parameters
gamgtype (GAMGType | str) -- The type of GAMG
Return type
None
SEE ALSO:
PCGAMGSetType
Source code at petsc4py/PETSc/PC.pyx:1019
setGASMOverlap(overlap)
Set the overlap between a pair of subdomains.
Logically collective.
Parameters
overlap (int) -- The amount of overlap between subdomains.
Return type
None
SEE ALSO:
PCGASMSetOverlap
Source code at petsc4py/PETSc/PC.pyx:999
setGASMType(gasmtype)
Set the type of restriction and interpolation.
Logically collective.
Parameters
gasmtype (GASMType) -- The type of GASM.
Return type
None
SEE ALSO:
PCGASMSetType
Source code at petsc4py/PETSc/PC.pyx:981
setHPDDMAuxiliaryMat(uis, uaux)
Set the auxiliary matrix used by the preconditioner.
Logically collective.
Parameters
• uis (IS) -- The IS of the local auxiliary matrix
• uaux (Mat) -- The auxiliary sequential matrix
Return type
None
SEE ALSO:
PCHPDDMSetAuxiliaryMat
Source code at petsc4py/PETSc/PC.pyx:2476
setHPDDMCoarseCorrectionType(correction_type)
Set the coarse correction type.
Collective.
Parameters
correction_type (HPDDMCoarseCorrectionType) -- The type of coarse correction to
apply.
Return type
None
SEE ALSO:
PCHPDDMSetCoarseCorrectionType
Source code at petsc4py/PETSc/PC.pyx:2544
setHPDDMDeflationMat(uis, U)
Set the deflation space used to assemble a coarse operator.
Logically collective.
Parameters
• uis (IS) -- The IS of the local deflation matrix.
• U (Mat) -- The deflation sequential matrix of type Mat.Type.DENSE.
Return type
None
SEE ALSO:
PCHPDDMSetDeflationMat
Source code at petsc4py/PETSc/PC.pyx:2590
setHPDDMHasNeumannMat(has)
Set to indicate that the Mat passed to the PC is the local Neumann matrix.
Logically collective.
Parameters
has (bool) -- Enable to indicate the matrix is the local Neumann matrix.
Return type
None
SEE ALSO:
PCHPDDMHasNeumannMat
Source code at petsc4py/PETSc/PC.pyx:2526
setHPDDMRHSMat(B)
Set the right-hand side matrix of the preconditioner.
Logically collective.
Parameters
B (Mat) -- The right-hand side sequential matrix.
Return type
None
SEE ALSO:
PCHPDDMSetRHSMat
Source code at petsc4py/PETSc/PC.pyx:2495
setHYPREAMSSetInteriorNodes(interior)
Set the list of interior nodes to a zero conductivity region.
Collective.
Parameters
interior (Vec) -- A vector where a value of 1.0 indicates an interior node.
Return type
None
SEE ALSO:
PCHYPREAMSSetInteriorNodes
Source code at petsc4py/PETSc/PC.pyx:1252
setHYPREDiscreteCurl(mat)
Set the discrete curl matrix.
Collective.
Parameters
mat (Mat) -- The discrete curl.
Return type
None
SEE ALSO:
PCHYPRESetDiscreteCurl
Source code at petsc4py/PETSc/PC.pyx:1110
setHYPREDiscreteGradient(mat)
Set the discrete gradient matrix.
Collective.
Parameters
mat (Mat) -- The discrete gradient.
Return type
None
SEE ALSO:
PCHYPRESetDiscreteGradient
Source code at petsc4py/PETSc/PC.pyx:1127
setHYPRESetAlphaPoissonMatrix(mat)
Set the vector Poisson matrix.
Collective.
Parameters
mat (Mat) -- The vector Poisson matrix.
Return type
None
SEE ALSO:
PCHYPRESetAlphaPoissonMatrix
Source code at petsc4py/PETSc/PC.pyx:1144
setHYPRESetBetaPoissonMatrix(mat=None)
Set the Posson matrix.
Collective.
Parameters
mat (Mat | None) -- The Poisson matrix or None to turn off.
Return type
None
SEE ALSO:
PCHYPRESetBetaPoissonMatrix
Source code at petsc4py/PETSc/PC.pyx:1161
setHYPRESetEdgeConstantVectors(ozz, zoz, zzo=None)
Set the representation of the constant vector fields in the edge element basis.
Collective.
Parameters
• ozz (Vec) -- A vector representing [1, 0, 0] or [1, 0] in 2D.
• zoz (Vec) -- A vector representing [0, 1, 0] or [0, 1] in 2D.
• zzo (Vec | None) -- A vector representing [0, 0, 1] or None in 2D.
Return type
None
SEE ALSO:
PCHYPRESetEdgeConstantVectors
Source code at petsc4py/PETSc/PC.pyx:1228
setHYPRESetInterpolations(dim, RT_Pi_Full=None, RT_Pi=None, ND_Pi_Full=None, ND_Pi=None)
Set the interpolation matrices.
Collective.
Parameters
• dim (int) -- The dimension of the problem.
• RT_Pi_Full (Mat | None) -- The Raviart-Thomas interpolation matrix or None to
omit.
• RT_Pi -- The xyz components of the Raviart-Thomas interpolation matrix, or None to
omit.
• ND_Pi_Full (Mat | None) -- The Nedelec interpolation matrix or None to omit.
• ND_Pi -- The xyz components of the Nedelec interpolation matrix, or None to omit.
Return type
None
SEE ALSO:
PCHYPRESetInterpolations
Source code at petsc4py/PETSc/PC.pyx:1180
setHYPREType(hypretype)
Set the Type.HYPRE type.
Collective.
Parameters
hypretype (str) -- The name of the type, one of "euclid", "pilut", "parasails",
"boomeramg", "ams", "ads"
Return type
None
SEE ALSO:
PCHYPRESetType
Source code at petsc4py/PETSc/PC.pyx:1090
setMGCycleType(cycle_type)
Set the type of cycles.
Logically collective.
Parameters
cycle_type (MGCycleType) -- The type of multigrid cycles to use.
Return type
None
SEE ALSO:
setMGCycleTypeOnLevel, PCMGSetCycleType
Source code at petsc4py/PETSc/PC.pyx:1963
setMGCycleTypeOnLevel(level, cycle_type)
Set the type of cycle on the given level.
Logically collective.
Parameters
• level (int) -- The level on which to set the cycle type.
• cycle_type (MGCycleType) -- The type of multigrid cycles to use.
Return type
None
SEE ALSO:
setMGCycleType, PCMGSetCycleTypeOnLevel
Source code at petsc4py/PETSc/PC.pyx:1981
setMGInterpolation(level, mat)
Set the interpolation operator for the given level.
Logically collective.
Parameters
• level -- The level where interpolation is defined from level-1 to level.
• mat (Mat) -- The interpolation operator
Return type
None
SEE ALSO:
PCMGSetInterpolation
Source code at petsc4py/PETSc/PC.pyx:1777
setMGLevels(levels)
Set the number of MG levels.
Logically collective.
Parameters
levels (int) -- The number of levels
Return type
None
SEE ALSO:
PCMGSetLevels
Source code at petsc4py/PETSc/PC.pyx:1744
setMGR(level, r)
Set the vector where the residual is stored.
Logically collective.
If not provided, one will be set internally. Will be cleaned up in destroy.
Parameters
• level (int) -- The level on which to set the residual.
• r (Vec) -- The vector where the residual is stored.
Return type
None
SEE ALSO:
PCMGSetR
Source code at petsc4py/PETSc/PC.pyx:2048
setMGRScale(level, rscale)
Set the pointwise scaling for the restriction operator on the given level.
Logically collective.
Parameters
• level (int) -- The level where restriction is defined from level to level-1.
• rscale (Vec) -- The scaling vector.
Return type
None
SEE ALSO:
PCMGSetRScale
Source code at petsc4py/PETSc/PC.pyx:1859
setMGRestriction(level, mat)
Set the restriction operator for the given level.
Logically collective.
Parameters
• level (int) -- The level where restriction is defined from level to level-1.
• mat (Mat) -- The restriction operator
Return type
None
SEE ALSO:
PCMGSetRestriction
Source code at petsc4py/PETSc/PC.pyx:1818
setMGRhs(level, rhs)
Set the vector where the right-hand side is stored.
Logically collective.
If not provided, one will be set internally. Will be cleaned up in destroy.
Parameters
• level (int) -- The level on which to set the right-hand side.
• rhs (Vec) -- The vector where the right-hand side is stored.
Return type
None
SEE ALSO:
PCMGSetRhs
Source code at petsc4py/PETSc/PC.pyx:2002
setMGType(mgtype)
Set the form of multigrid.
Logically collective.
SEE ALSO:
PCMGSetType
Source code at petsc4py/PETSc/PC.pyx:1717
Parameters
mgtype (MGType)
Return type
None
setMGX(level, x)
Set the vector where the solution is stored.
Logically collective.
If not provided, one will be set internally. Will be cleaned up in destroy.
Parameters
• level (int) -- The level on which to set the solution.
• x (Vec) -- The vector where the solution is stored.
Return type
None
SEE ALSO:
PCMGSetX
Source code at petsc4py/PETSc/PC.pyx:2025
setOperators(A=None, P=None)
Set the matrices associated with the linear system.
Logically collective.
Passing None for A or P removes the matrix that is currently used. PETSc does not reset the
matrix entries of either A or P to zero after a linear solve; the user is completely
responsible for matrix assembly. See Mat.zeroEntries to zero all elements of a matrix.
Parameters
• A (Mat | None) -- the matrix which defines the linear system
• P (Mat | None) -- the matrix to be used in constructing the preconditioner,
usually the same as A
Return type
None
SEE ALSO:
PCSetOperators
Source code at petsc4py/PETSc/PC.pyx:386
setOptionsPrefix(prefix)
Set the prefix used for all the PC options.
Logically collective.
Parameters
prefix (str | None) -- The prefix to prepend to all option names.
Return type
None
SEE ALSO:
Working with PETSc options, PCSetOptionsPrefix
Source code at petsc4py/PETSc/PC.pyx:322
setPatchCellNumbering(sec)
Set the cell numbering.
Source code at petsc4py/PETSc/PC.pyx:2383
Parameters
sec (Section)
Return type
None
setPatchComputeFunction(function, args=None, kargs=None)
Set compute operator callbacks.
Source code at petsc4py/PETSc/PC.pyx:2444
Return type
None
setPatchComputeFunctionInteriorFacets(function, args=None, kargs=None)
Set compute operator callbacks.
Source code at petsc4py/PETSc/PC.pyx:2452
Return type
None
setPatchComputeOperator(operator, args=None, kargs=None)
Set compute operator callbacks.
Source code at petsc4py/PETSc/PC.pyx:2428
Return type
None
setPatchComputeOperatorInteriorFacets(operator, args=None, kargs=None)
Set compute operator callbacks.
Source code at petsc4py/PETSc/PC.pyx:2436
Return type
None
setPatchConstructType(typ, operator=None, args=None, kargs=None)
Set compute operator callbacks.
Source code at petsc4py/PETSc/PC.pyx:2460
Return type
None
setPatchDiscretisationInfo(dms, bs, cellNodeMaps, subspaceOffsets, ghostBcNodes, globalBcNodes)
Set discretisation info.
Source code at petsc4py/PETSc/PC.pyx:2387
Return type
None
setPythonContext(context)
Set the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python preconditioner type, getPythonContext
Source code at petsc4py/PETSc/PC.pyx:767
Parameters
context (Any)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
SEE ALSO:
PETSc Python preconditioner type, setPythonContext, getPythonType, PCPythonSetType
Source code at petsc4py/PETSc/PC.pyx:794
Parameters
py_type (str)
Return type
None
setReusePreconditioner(flag)
Set to indicate the preconditioner is to be reused.
Logically collective.
Normally if the A matrix inside a PC changes, the PC automatically updates itself using
information from the changed matrix. Enable this option prevents this.
Parameters
flag (bool) -- Set to True to use the reuse the current preconditioner and False to
recompute on changes to the matrix.
Return type
None
SEE ALSO:
setOperators, PCSetReusePreconditioner
Source code at petsc4py/PETSc/PC.pyx:477
setSPAIBlockSize(n)
Set the block size of the preconditioner.
Logically collective.
Parameters
n (int) -- The block size, defaults to 1.
Return type
None
SEE ALSO:
PCSPAISetBlockSize
Source code at petsc4py/PETSc/PC.pyx:2684
setSPAICacheSize(size)
Set the cache size.
Logically collective.
Parameters
size (int) -- The size of the cache, defaults to 5.
Return type
None
SEE ALSO:
PCSPAISetCacheSize
Source code at petsc4py/PETSc/PC.pyx:2702
setSPAIEpsilon(val)
Set the tolerance for the preconditioner.
Logically collective.
Parameters
val (float) -- The tolerance, defaults to 0.4.
Return type
None
SEE ALSO:
PCSPAISetEpsilon
Source code at petsc4py/PETSc/PC.pyx:2611
setSPAIMax(maxval)
Set the size of working buffers in the preconditioner.
Logically collective.
Parameters
maxval (int) -- Number of entries in the work arrays to be allocated, defaults to
5000.
Return type
None
SEE ALSO:
PCSPAISetMax
Source code at petsc4py/PETSc/PC.pyx:2647
setSPAIMaxNew(maxval)
Set the maximum number of new non-zero candidates per step.
Logically collective.
Parameters
maxval (int) -- Number of entries allowed, defaults to 5.
Return type
None
SEE ALSO:
PCSPAISetMaxNew
Source code at petsc4py/PETSc/PC.pyx:2666
setSPAINBSteps(nbsteps)
Set the maximum number of improvement steps per row.
Logically collective.
Parameters
nbsteps (int) -- The number of steps, defaults to 5.
Return type
None
SEE ALSO:
PCSPAISetNBSteps
Source code at petsc4py/PETSc/PC.pyx:2629
setSPAISp(sym)
Set to specify a symmetric sparsity pattern.
Logically collective.
Parameters
sym (int) -- Enable to indicate the matrix is symmetric.
Return type
None
SEE ALSO:
PCSPAISetSp
Source code at petsc4py/PETSc/PC.pyx:2738
setSPAIVerbose(level)
Set the verbosity level.
Logically collective.
Parameters
level (int) -- The level of verbosity, defaults to 1.
Return type
None
SEE ALSO:
PCSPAISetVerbose
Source code at petsc4py/PETSc/PC.pyx:2720
setType(pc_type)
Set the preconditioner type.
Collective.
Parameters
pc_type (Type | str) -- The preconditioner type.
Return type
None
SEE ALSO:
Working with PETSc options, getType, TSSetType
Source code at petsc4py/PETSc/PC.pyx:289
setUp()
Set up the internal data structures for the PC.
Collective.
SEE ALSO:
PCSetUp
Source code at petsc4py/PETSc/PC.pyx:541
Return type
None
setUpOnBlocks()
Set up the PC for each block.
Collective.
For nested preconditioners such as BJACOBI, setUp is not called on each sub-KSP when setUp
is called on the outer PC. This routine ensures it is called.
SEE ALSO:
setUp, PCSetUpOnBlocks
Source code at petsc4py/PETSc/PC.pyx:565
Return type
None
setUseAmat(flag)
Set to indicate to apply PC to A and not P.
Logically collective.
Sets a flag to indicate that when the preconditioner needs to apply (part of) the operator
during the preconditioning process, it applies to A provided to TS.setRHSJacobian,
TS.setIJacobian, SNES.setJacobian, KSP.setOperators or PC.setOperators not the P.
Parameters
flag (bool) -- Set True to use A and False to use P.
Return type
None
SEE ALSO:
setOperators, PCSetUseAmat
Source code at petsc4py/PETSc/PC.pyx:432
view(viewer=None)
View the PC object.
Collective.
Parameters
viewer (Viewer | None) -- The visualization context.
Return type
None
SEE ALSO:
PCView
Source code at petsc4py/PETSc/PC.pyx:231
petsc4py.PETSc.Partitioner
class petsc4py.PETSc.Partitioner
Bases: Object
A graph partitioner.
Enumerations
┌──────┬────────────────────────┐
│ Type │ The partitioner types. │
└──────┴────────────────────────┘
petsc4py.PETSc.Partitioner.Type
class petsc4py.PETSc.Partitioner.Type
Bases: object
The partitioner types.
Attributes Summary
┌─────────────────┬────────────────────────────────────┐
│ CHACO │ Object CHACO of type str │
├─────────────────┼────────────────────────────────────┤
│ GATHER │ Object GATHER of type str │
├─────────────────┼────────────────────────────────────┤
│ MATPARTITIONING │ Object MATPARTITIONING of type str │
├─────────────────┼────────────────────────────────────┤
│ PARMETIS │ Object PARMETIS of type str │
├─────────────────┼────────────────────────────────────┤
│ PTSCOTCH │ Object PTSCOTCH of type str │
├─────────────────┼────────────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├─────────────────┼────────────────────────────────────┤
│ SIMPLE │ Object SIMPLE of type str │
└─────────────────┴────────────────────────────────────┘
Attributes Documentation
CHACO: str = CHACO
Object CHACO of type str
GATHER: str = GATHER
Object GATHER of type str
MATPARTITIONING: str = MATPARTITIONING
Object MATPARTITIONING of type str
PARMETIS: str = PARMETIS
Object PARMETIS of type str
PTSCOTCH: str = PTSCOTCH
Object PTSCOTCH of type str
SHELL: str = SHELL
Object SHELL of type str
SIMPLE: str = SIMPLE
Object SIMPLE of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create an empty partitioner object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the partitioner object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the partitioner type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Reset data structures of the │
│ │ partitioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set parameters in the partitioner │
│ │ from the options database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setShellPartition(numProcs[, sizes, │ Set a custom partition for a mesh. │
│ points]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(part_type) │ Build a particular type of the │
│ │ partitioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Construct data structures for the │
│ │ partitioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the partitioner. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create an empty partitioner object.
Collective.
The type can be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
setType, PetscPartitionerCreate
Source code at petsc4py/PETSc/Partitioner.pyx:57
destroy()
Destroy the partitioner object.
Collective.
SEE ALSO:
PetscPartitionerDestroy
Source code at petsc4py/PETSc/Partitioner.pyx:44
Return type
Self
getType()
Return the partitioner type.
Not collective.
SEE ALSO:
setType, PetscPartitionerGetType
Source code at petsc4py/PETSc/Partitioner.pyx:99
Return type
Type
reset()
Reset data structures of the partitioner.
Collective.
SEE ALSO:
PetscPartitionerReset
Source code at petsc4py/PETSc/Partitioner.pyx:137
Return type
None
setFromOptions()
Set parameters in the partitioner from the options database.
Collective.
SEE ALSO:
Working with PETSc options, PetscPartitionerSetFromOptions
Source code at petsc4py/PETSc/Partitioner.pyx:113
Return type
None
setShellPartition(numProcs, sizes=None, points=None)
Set a custom partition for a mesh.
Collective.
Parameters
• sizes (Sequence[int] | None) -- The number of points in each partition.
• points (Sequence[int] | None) -- A permutation of the points that groups those
assigned to each partition in order (i.e., partition 0 first, partition 1 next,
etc.).
• numProcs (int)
Return type
None
SEE ALSO:
PetscPartitionerShellSetPartition
Source code at petsc4py/PETSc/Partitioner.pyx:149
setType(part_type)
Build a particular type of the partitioner.
Collective.
Parameters
part_type (Type | str) -- The kind of partitioner.
Return type
None
SEE ALSO:
getType, PetscPartitionerSetType
Source code at petsc4py/PETSc/Partitioner.pyx:80
setUp()
Construct data structures for the partitioner.
Collective.
SEE ALSO:
PetscPartitionerSetUp
Source code at petsc4py/PETSc/Partitioner.pyx:125
Return type
None
view(viewer=None)
View the partitioner.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
PetscPartitionerView
Source code at petsc4py/PETSc/Partitioner.pyx:25
petsc4py.PETSc.Quad
class petsc4py.PETSc.Quad
Bases: Object
Quadrature rule for integration.
Methods Summary
┌──────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create a Quad object. │
├──────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the Quad object. │
├──────────────────────┼───────────────────────────────────────┤
│ duplicate() │ Create a deep copy of the Quad │
│ │ object. │
├──────────────────────┼───────────────────────────────────────┤
│ getData() │ Return the data defining the Quad. │
├──────────────────────┼───────────────────────────────────────┤
│ getNumComponents() │ Return the number of components for │
│ │ functions to be integrated. │
├──────────────────────┼───────────────────────────────────────┤
│ getOrder() │ Return the order of the method in the │
│ │ Quad. │
├──────────────────────┼───────────────────────────────────────┤
│ setNumComponents(nc) │ Return the number of components for │
│ │ functions to be integrated. │
├──────────────────────┼───────────────────────────────────────┤
│ setOrder(order) │ Set the order of the method in the │
│ │ Quad. │
├──────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a Quad object. │
└──────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create a Quad object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscQuadratureCreate
Source code at petsc4py/PETSc/DT.pyx:28
destroy()
Destroy the Quad object.
Collective.
SEE ALSO:
PetscQuadratureDestroy
Source code at petsc4py/PETSc/DT.pyx:63
Return type
Self
duplicate()
Create a deep copy of the Quad object.
Collective.
SEE ALSO:
PetscQuadratureDuplicate
Source code at petsc4py/PETSc/DT.pyx:49
Return type
Quad
getData()
Return the data defining the Quad.
Not collective.
Returns
• points (ArrayReal) -- The coordinates of the quadrature points.
• weights (ArrayReal) -- The quadrature weights.
Return type
tuple(ArrayReal, ArrayReal)
SEE ALSO:
PetscQuadratureGetData
Source code at petsc4py/PETSc/DT.pyx:76
getNumComponents()
Return the number of components for functions to be integrated.
Not collective.
SEE ALSO:
setNumComponents, PetscQuadratureGetNumComponents
Source code at petsc4py/PETSc/DT.pyx:104
Return type
int
getOrder()
Return the order of the method in the Quad.
Not collective.
SEE ALSO:
setOrder, PetscQuadratureGetOrder
Source code at petsc4py/PETSc/DT.pyx:136
Return type
int
setNumComponents(nc)
Return the number of components for functions to be integrated.
Not collective.
Parameters
nc (int) -- The number of components.
Return type
None
SEE ALSO:
getNumComponents, PetscQuadratureSetNumComponents
Source code at petsc4py/PETSc/DT.pyx:118
setOrder(order)
Set the order of the method in the Quad.
Not collective.
Parameters
order (int) -- The order of the quadrature, i.e. the highest degree polynomial that
is exactly integrated.
Return type
None
SEE ALSO:
getOrder, PetscQuadratureSetOrder
Source code at petsc4py/PETSc/DT.pyx:150
view(viewer=None)
View a Quad object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
PetscQuadratureView
Source code at petsc4py/PETSc/DT.pyx:9
petsc4py.PETSc.Random
class petsc4py.PETSc.Random
Bases: Object
The random number generator object.
SEE ALSO:
PetscRandom
Enumerations
┌──────┬───────────────────────────────────┐
│ Type │ The random number generator type. │
└──────┴───────────────────────────────────┘
petsc4py.PETSc.Random.Type
class petsc4py.PETSc.Random.Type
Bases: object
The random number generator type.
Attributes Summary
┌───────────┬──────────────────────────────┐
│ RAND │ Object RAND of type str │
├───────────┼──────────────────────────────┤
│ RAND48 │ Object RAND48 of type str │
├───────────┼──────────────────────────────┤
│ RANDER48 │ Object RANDER48 of type str │
├───────────┼──────────────────────────────┤
│ RANDOM123 │ Object RANDOM123 of type str │
├───────────┼──────────────────────────────┤
│ SPRNG │ Object SPRNG of type str │
└───────────┴──────────────────────────────┘
Attributes Documentation
RAND: str = RAND
Object RAND of type str
RAND48: str = RAND48
Object RAND48 of type str
RANDER48: str = RANDER48
Object RANDER48 of type str
RANDOM123: str = RANDOM123
Object RANDOM123 of type str
SPRNG: str = SPRNG
Object SPRNG of type str
Methods Summary
┌───────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create a random number generator │
│ │ object. │
├───────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the random number generator │
│ │ object. │
├───────────────────────┼───────────────────────────────────────┤
│ getInterval() │ Return the interval containing the │
│ │ random numbers generated. │
├───────────────────────┼───────────────────────────────────────┤
│ getSeed() │ Return the random number generator │
│ │ seed. │
├───────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the random number │
│ │ generator object. │
├───────────────────────┼───────────────────────────────────────┤
│ getValue() │ Generate a scalar random number. │
├───────────────────────┼───────────────────────────────────────┤
│ getValueReal() │ Generate a real random number. │
├───────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the random number generator │
│ │ from the options database. │
├───────────────────────┼───────────────────────────────────────┤
│ setInterval(interval) │ Set the interval of the random number │
│ │ generator. │
├───────────────────────┼───────────────────────────────────────┤
│ setSeed([seed]) │ Set the seed of random number │
│ │ generator. │
├───────────────────────┼───────────────────────────────────────┤
│ setType(rnd_type) │ Set the type of the random number │
│ │ generator object. │
├───────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a random number generator │
│ │ object. │
└───────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌──────────┬───────────────────────────────────────┐
│ interval │ The interval of the generated random │
│ │ numbers. │
├──────────┼───────────────────────────────────────┤
│ seed │ The seed of the random number │
│ │ generator. │
└──────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create a random number generator object.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, PetscRandomCreate
Source code at petsc4py/PETSc/Random.pyx:74
destroy()
Destroy the random number generator object.
Collective.
SEE ALSO:
PetscRandomDestroy
Source code at petsc4py/PETSc/Random.pyx:61
Return type
Self
getInterval()
Return the interval containing the random numbers generated.
Not collective.
SEE ALSO:
setInterval, PetscRandomGetInterval
Source code at petsc4py/PETSc/Random.pyx:199
Return type
tuple[Scalar, Scalar]
getSeed()
Return the random number generator seed.
Not collective.
SEE ALSO:
setSeed, PetscRandomGetSeed
Source code at petsc4py/PETSc/Random.pyx:166
Return type
int
getType()
Return the type of the random number generator object.
Not collective.
SEE ALSO:
setType, PetscRandomGetType
Source code at petsc4py/PETSc/Random.pyx:112
Return type
str
getValue()
Generate a scalar random number.
Not collective.
SEE ALSO:
PetscRandomGetValue
Source code at petsc4py/PETSc/Random.pyx:138
Return type
Scalar
getValueReal()
Generate a real random number.
Not collective.
SEE ALSO:
PetscRandomGetValueReal
Source code at petsc4py/PETSc/Random.pyx:152
Return type
float
setFromOptions()
Configure the random number generator from the options database.
Collective.
SEE ALSO:
Working with PETSc options, PetscRandomSetFromOptions
Source code at petsc4py/PETSc/Random.pyx:126
Return type
None
setInterval(interval)
Set the interval of the random number generator.
Not collective.
SEE ALSO:
getInterval, PetscRandomSetInterval
Source code at petsc4py/PETSc/Random.pyx:214
Parameters
interval (tuple[Scalar, Scalar])
Return type
None
setSeed(seed=None)
Set the seed of random number generator.
Not collective.
Parameters
seed (int | None) -- The value for the seed. If None, it only seeds the generator.
Return type
None
SEE ALSO:
getSeed, PetscRandomSetSeed, PetscRandomSeed
Source code at petsc4py/PETSc/Random.pyx:180
setType(rnd_type)
Set the type of the random number generator object.
Collective.
Parameters
rnd_type (Type | str) -- The type of the generator.
Return type
None
SEE ALSO:
getType, PetscRandomSetType
Source code at petsc4py/PETSc/Random.pyx:93
view(viewer=None)
View a random number generator object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
PetscRandomView
Source code at petsc4py/PETSc/Random.pyx:41
Attributes Documentation
interval
The interval of the generated random numbers.
Source code at petsc4py/PETSc/Random.pyx:241
seed The seed of the random number generator.
Source code at petsc4py/PETSc/Random.pyx:233
petsc4py.PETSc.SF
class petsc4py.PETSc.SF
Bases: Object
Star Forest object for communication.
SF is used for setting up and managing the communication of certain entries of arrays and Vec
between MPI processes.
Enumerations
┌──────┬────────────────────────┐
│ Type │ The star forest types. │
└──────┴────────────────────────┘
petsc4py.PETSc.SF.Type
class petsc4py.PETSc.SF.Type
Bases: object
The star forest types.
Attributes Summary
┌────────────┬───────────────────────────────┐
│ ALLGATHER │ Object ALLGATHER of type str │
├────────────┼───────────────────────────────┤
│ ALLGATHERV │ Object ALLGATHERV of type str │
├────────────┼───────────────────────────────┤
│ ALLTOALL │ Object ALLTOALL of type str │
├────────────┼───────────────────────────────┤
│ BASIC │ Object BASIC of type str │
├────────────┼───────────────────────────────┤
│ GATHER │ Object GATHER of type str │
├────────────┼───────────────────────────────┤
│ GATHERV │ Object GATHERV of type str │
├────────────┼───────────────────────────────┤
│ NEIGHBOR │ Object NEIGHBOR of type str │
├────────────┼───────────────────────────────┤
│ WINDOW │ Object WINDOW of type str │
└────────────┴───────────────────────────────┘
Attributes Documentation
ALLGATHER: str = ALLGATHER
Object ALLGATHER of type str
ALLGATHERV: str = ALLGATHERV
Object ALLGATHERV of type str
ALLTOALL: str = ALLTOALL
Object ALLTOALL of type str
BASIC: str = BASIC
Object BASIC of type str
GATHER: str = GATHER
Object GATHER of type str
GATHERV: str = GATHERV
Object GATHERV of type str
NEIGHBOR: str = NEIGHBOR
Object NEIGHBOR of type str
WINDOW: str = WINDOW
Object WINDOW of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ bcastBegin(unit, rootdata, leafdata, │ Begin pointwise broadcast. │
│ op) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ bcastEnd(unit, rootdata, leafdata, │ End a broadcast & reduce operation │
│ op) │ started with bcastBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ compose(sf) │ Compose a new SF. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeDegree() │ Compute and return the degree of each │
│ │ root vertex. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a star forest communication │
│ │ context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createEmbeddedLeafSF(selected) │ Remove edges from all but the │
│ │ selected leaves. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createEmbeddedRootSF(selected) │ Remove edges from all but the │
│ │ selected roots. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createInverse() │ Create the inverse map. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSectionSF(rootSection, │ Create an expanded SF of DOFs. │
│ remoteOffsets, ...) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the star forest. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ distributeSection(rootSection[, │ Create a new, reorganized Section. │
│ leafSection]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ fetchAndOpBegin(unit, rootdata, │ Begin fetch and update operation. │
│ leafdata, ...) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ fetchAndOpEnd(unit, rootdata, │ End operation started in a matching │
│ leafdata, ...) │ call to fetchAndOpBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ gatherBegin(unit, leafdata, │ Begin pointwise gather of all leaves │
│ multirootdata) │ into multi-roots. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ gatherEnd(unit, leafdata, │ End gather operation that was started │
│ multirootdata) │ with gatherBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGraph() │ Return star forest graph. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMulti() │ Return the inner SF implementing │
│ │ gathers and scatters. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type name of the star │
│ │ forest. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reduceBegin(unit, leafdata, rootdata, │ Begin reduction of leafdata into │
│ op) │ rootdata. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reduceEnd(unit, leafdata, rootdata, │ End a reduction operation started │
│ op) │ with reduceBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Reset a star forest so that different │
│ │ sizes or neighbors can be used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ scatterBegin(unit, multirootdata, │ Begin pointwise scatter operation. │
│ leafdata) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ scatterEnd(unit, multirootdata, │ End scatter operation that was │
│ leafdata) │ started with scatterBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set options using the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setGraph(nroots, local, remote) │ Set star forest graph. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRankOrder(flag) │ Sort multi-points for gathers and │
│ │ scatters by rank order. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(sf_type) │ Set the type of the star forest. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up communication structures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a star forest. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
bcastBegin(unit, rootdata, leafdata, op)
Begin pointwise broadcast.
Collective.
Root values are reduced to leaf values. This call has to be concluded with a call to
bcastEnd.
Parameters
• unit (Datatype) -- MPI datatype.
• rootdata (ndarray) -- Buffer to broadcast.
• leafdata (ndarray) -- Buffer to be reduced with values from each leaf's respective
root.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
bcastEnd, PetscSFBcastBegin
Source code at petsc4py/PETSc/SF.pyx:434
bcastEnd(unit, rootdata, leafdata, op)
End a broadcast & reduce operation started with bcastBegin.
Collective.
Parameters
• unit (Datatype) -- MPI datatype.
• rootdata (ndarray) -- Buffer to broadcast.
• leafdata (ndarray) -- Buffer to be reduced with values from each leaf's respective
root.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
bcastBegin, PetscSFBcastEnd
Source code at petsc4py/PETSc/SF.pyx:463
compose(sf)
Compose a new SF.
Collective.
Puts the sf under this object in a top (roots) down (leaves) view.
Parameters
sf (SF) -- SF to put under this object.
Return type
SF
SEE ALSO:
PetscSFCompose
Source code at petsc4py/PETSc/SF.pyx:413
computeDegree()
Compute and return the degree of each root vertex.
Collective.
SEE ALSO:
PetscSFComputeDegreeBegin, PetscSFComputeDegreeEnd
Source code at petsc4py/PETSc/SF.pyx:279
Return type
ArrayInt
create(comm=None)
Create a star forest communication context.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscSFCreate
Source code at petsc4py/PETSc/SF.pyx:63
createEmbeddedLeafSF(selected)
Remove edges from all but the selected leaves.
Collective.
Does not remap indices.
Parameters
selected (Sequence[int]) -- Indices of the selected roots on this process.
Return type
SF
SEE ALSO:
PetscSFCreateEmbeddedLeafSF
Source code at petsc4py/PETSc/SF.pyx:321
createEmbeddedRootSF(selected)
Remove edges from all but the selected roots.
Collective.
Does not remap indices.
Parameters
selected (Sequence[int]) -- Indices of the selected roots on this process.
Return type
SF
SEE ALSO:
PetscSFCreateEmbeddedRootSF
Source code at petsc4py/PETSc/SF.pyx:297
createInverse()
Create the inverse map.
Collective.
Create the inverse map given a PetscSF in which all vertices have degree 1.
SEE ALSO:
PetscSFCreateInverseSF
Source code at petsc4py/PETSc/SF.pyx:262
Return type
SF
createSectionSF(rootSection, remoteOffsets, leafSection)
Create an expanded SF of DOFs.
Collective.
Assumes the input SF relates points.
Parameters
• rootSection (Section) -- Data layout of remote points for outgoing data (this is
usually the serial section).
• remoteOffsets (Sequence[int] | None) -- Offsets for point data on remote processes
(these are offsets from the root section), or None.
• leafSection (Section) -- Data layout of local points for incoming data (this is
the distributed section).
Return type
SF
SEE ALSO:
PetscSFCreateSectionSF
Source code at petsc4py/PETSc/SF.pyx:345
destroy()
Destroy the star forest.
Collective.
SEE ALSO:
PetscSFDestroy
Source code at petsc4py/PETSc/SF.pyx:50
Return type
Self
distributeSection(rootSection, leafSection=None)
Create a new, reorganized Section.
Collective.
Moves from the root to the leaves of the SF.
Parameters
• rootSection (Section) -- Section defined on root space.
• leafSection (Section | None) -- Section defined on the leaf space.
Return type
tuple[ArrayInt, Section]
SEE ALSO:
PetscSFDistributeSection
Source code at petsc4py/PETSc/SF.pyx:378
fetchAndOpBegin(unit, rootdata, leafdata, leafupdate, op)
Begin fetch and update operation.
Collective.
This operation fetches values from root and updates atomically by applying an operation
using the leaf value.
This call has to be completed with fetchAndOpEnd.
Parameters
• unit (Datatype) -- MPI datatype.
• rootdata (ndarray) -- Root values to be updated, input state is seen by first
process to perform an update.
• leafdata (ndarray) -- Leaf values to use in reduction.
• leafupdate (ndarray) -- State at each leaf's respective root immediately prior to
my atomic update.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
fetchAndOpEnd, PetscSFFetchAndOpBegin
Source code at petsc4py/PETSc/SF.pyx:642
fetchAndOpEnd(unit, rootdata, leafdata, leafupdate, op)
End operation started in a matching call to fetchAndOpBegin.
Collective.
Parameters
• unit (Datatype) -- MPI datatype.
• rootdata (ndarray) -- Root values to be updated, input state is seen by first
process to perform an update.
• leafdata (ndarray) -- Leaf values to use in reduction.
• leafupdate (ndarray) -- State at each leaf's respective root immediately prior to
my atomic update.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
fetchAndOpBegin, PetscSFFetchAndOpEnd
Source code at petsc4py/PETSc/SF.pyx:678
gatherBegin(unit, leafdata, multirootdata)
Begin pointwise gather of all leaves into multi-roots.
Collective.
This call has to be completed with gatherEnd.
Parameters
• unit (Datatype) -- MPI datatype.
• leafdata (ndarray) -- Leaf data to gather to roots.
• multirootdata (ndarray) -- Root buffer to gather into, amount of space per root is
equal to its degree.
Return type
None
SEE ALSO:
gatherEnd, PetscSFGatherBegin
Source code at petsc4py/PETSc/SF.pyx:592
gatherEnd(unit, leafdata, multirootdata)
End gather operation that was started with gatherBegin.
Collective.
Parameters
• unit (Datatype) -- MPI datatype.
• leafdata (ndarray) -- Leaf data to gather to roots.
• multirootdata (ndarray) -- Root buffer to gather into, amount of space per root is
equal to its degree.
Return type
None
SEE ALSO:
gatherBegin, PetscSFGatherEnd
Source code at petsc4py/PETSc/SF.pyx:618
getGraph()
Return star forest graph.
Not collective.
The number of leaves can be determined from the size of ilocal.
Returns
• nroots (int) -- Number of root vertices on the current process (these are possible
targets for other process to attach leaves).
• ilocal (ArrayInt) -- Locations of leaves in leafdata buffers.
• iremote (ArrayInt) -- Remote locations of root vertices for each leaf on the
current process.
Return type
tuple[int, ArrayInt, ArrayInt]
SEE ALSO:
PetscSFGetGraph
Source code at petsc4py/PETSc/SF.pyx:155
getMulti()
Return the inner SF implementing gathers and scatters.
Collective.
SEE ALSO:
PetscSFGetMultiSF
Source code at petsc4py/PETSc/SF.pyx:247
Return type
SF
getType()
Return the type name of the star forest.
Collective.
SEE ALSO:
PetscSFGetType
Source code at petsc4py/PETSc/SF.pyx:103
Return type
str
reduceBegin(unit, leafdata, rootdata, op)
Begin reduction of leafdata into rootdata.
Collective.
This call has to be completed with call to reduceEnd.
Parameters
• unit (Datatype) -- MPI datatype.
• leafdata (ndarray) -- Values to reduce.
• rootdata (ndarray) -- Result of reduction of values from all leaves of each root.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
reduceEnd, PetscSFReduceBegin
Source code at petsc4py/PETSc/SF.pyx:489
reduceEnd(unit, leafdata, rootdata, op)
End a reduction operation started with reduceBegin.
Collective.
Parameters
• unit (Datatype) -- MPI datatype.
• leafdata (ndarray) -- Values to reduce.
• rootdata (ndarray) -- Result of reduction of values from all leaves of each root.
• op (Op) -- MPI reduction operation.
Return type
None
SEE ALSO:
reduceBegin, PetscSFReduceEnd
Source code at petsc4py/PETSc/SF.pyx:517
reset()
Reset a star forest so that different sizes or neighbors can be used.
Collective.
SEE ALSO:
PetscSFReset
Source code at petsc4py/PETSc/SF.pyx:141
Return type
None
scatterBegin(unit, multirootdata, leafdata)
Begin pointwise scatter operation.
Collective.
Operation is from multi-roots to leaves. This call has to be completed with scatterEnd.
Parameters
• unit (Datatype) -- MPI datatype.
• multirootdata (ndarray) -- Root buffer to send to each leaf, one unit of data per
leaf.
• leafdata (ndarray) -- Leaf data to be updated with personal data from each
respective root.
Return type
None
SEE ALSO:
scatterEnd, PetscSFScatterBegin
Source code at petsc4py/PETSc/SF.pyx:543
scatterEnd(unit, multirootdata, leafdata)
End scatter operation that was started with scatterBegin.
Collective.
Parameters
• unit (Datatype) -- MPI datatype.
• multirootdata (ndarray) -- Root buffer to send to each leaf, one unit of data per
leaf.
• leafdata (ndarray) -- Leaf data to be updated with personal data from each
respective root.
Return type
None
SEE ALSO:
scatterBegin, PetscSFScatterEnd
Source code at petsc4py/PETSc/SF.pyx:569
setFromOptions()
Set options using the options database.
Logically collective.
SEE ALSO:
Working with PETSc options, PetscSFSetFromOptions
Source code at petsc4py/PETSc/SF.pyx:117
Return type
None
setGraph(nroots, local, remote)
Set star forest graph.
Collective.
The number of leaves argument can be determined from the size of local and/or remote.
Parameters
• nroots (int) -- Number of root vertices on the current process (these are possible
targets for other process to attach leaves).
• local (Sequence[int]) -- Locations of leaves in leafdata buffers, pass None for
contiguous storage.
• remote (Sequence[int]) -- Remote locations of root vertices for each leaf on the
current process. Should be 2*nleaves long as (rank, index) pairs.
Return type
None
SEE ALSO:
PetscSFSetGraph
Source code at petsc4py/PETSc/SF.pyx:190
setRankOrder(flag)
Sort multi-points for gathers and scatters by rank order.
Logically collective.
Parameters
flag (bool) -- True to sort, False to skip sorting.
Return type
None
SEE ALSO:
PetscSFSetRankOrder
Source code at petsc4py/PETSc/SF.pyx:229
setType(sf_type)
Set the type of the star forest.
Collective.
Parameters
sf_type (Type | str) -- The star forest type.
Return type
None
SEE ALSO:
PetscSFSetType
Source code at petsc4py/PETSc/SF.pyx:84
setUp()
Set up communication structures.
Collective.
SEE ALSO:
PetscSFSetUp
Source code at petsc4py/PETSc/SF.pyx:129
Return type
None
view(viewer=None)
View a star forest.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the graph.
Return type
None
SEE ALSO:
PetscSFView
Source code at petsc4py/PETSc/SF.pyx:31
petsc4py.PETSc.SNES
class petsc4py.PETSc.SNES
Bases: Object
Nonlinear equations solver.
SNES is described in the PETSc manual.
SEE ALSO:
SNES
Enumerations
┌─────────────────┬─────────────────────────────────┐
│ ConvergedReason │ SNES solver termination reason. │
├─────────────────┼─────────────────────────────────┤
│ NormSchedule │ SNES norm schedule. │
├─────────────────┼─────────────────────────────────┤
│ Type │ SNES solver type. │
└─────────────────┴─────────────────────────────────┘
petsc4py.PETSc.SNES.ConvergedReason
class petsc4py.PETSc.SNES.ConvergedReason
Bases: object
SNES solver termination reason.
SEE ALSO:
SNESGetConvergedReason
Attributes Summary
┌──────────────────────────┬───────────────────────────────────────┐
│ CONVERGED_FNORM_ABS │ Constant CONVERGED_FNORM_ABS of type │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_FNORM_RELATIVE │ Constant CONVERGED_FNORM_RELATIVE of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITERATING │ Constant CONVERGED_ITERATING of type │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITS │ Constant CONVERGED_ITS of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_SNORM_RELATIVE │ Constant CONVERGED_SNORM_RELATIVE of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_DTOL │ Constant DIVERGED_DTOL of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_FNORM_NAN │ Constant DIVERGED_FNORM_NAN of type ‐ │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_FUNCTION_COUNT │ Constant DIVERGED_FUNCTION_COUNT of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_FUNCTION_DOMAIN │ Constant DIVERGED_FUNCTION_DOMAIN of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_INNER │ Constant DIVERGED_INNER of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_JACOBIAN_DOMAIN │ Constant DIVERGED_JACOBIAN_DOMAIN of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_LINEAR_SOLVE │ Constant DIVERGED_LINEAR_SOLVE of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_LINE_SEARCH │ Constant DIVERGED_LINE_SEARCH of type │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_LOCAL_MIN │ Constant DIVERGED_LOCAL_MIN of type ‐ │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_MAX_IT │ Constant DIVERGED_MAX_IT of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_TR_DELTA │ Constant DIVERGED_TR_DELTA of type ‐ │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ ITERATING │ Constant ITERATING of type int │
└──────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
CONVERGED_FNORM_ABS: int = CONVERGED_FNORM_ABS
Constant CONVERGED_FNORM_ABS of type int
CONVERGED_FNORM_RELATIVE: int = CONVERGED_FNORM_RELATIVE
Constant CONVERGED_FNORM_RELATIVE of type int
CONVERGED_ITERATING: int = CONVERGED_ITERATING
Constant CONVERGED_ITERATING of type int
CONVERGED_ITS: int = CONVERGED_ITS
Constant CONVERGED_ITS of type int
CONVERGED_SNORM_RELATIVE: int = CONVERGED_SNORM_RELATIVE
Constant CONVERGED_SNORM_RELATIVE of type int
DIVERGED_DTOL: int = DIVERGED_DTOL
Constant DIVERGED_DTOL of type int
DIVERGED_FNORM_NAN: int = DIVERGED_FNORM_NAN
Constant DIVERGED_FNORM_NAN of type int
DIVERGED_FUNCTION_COUNT: int = DIVERGED_FUNCTION_COUNT
Constant DIVERGED_FUNCTION_COUNT of type int
DIVERGED_FUNCTION_DOMAIN: int = DIVERGED_FUNCTION_DOMAIN
Constant DIVERGED_FUNCTION_DOMAIN of type int
DIVERGED_INNER: int = DIVERGED_INNER
Constant DIVERGED_INNER of type int
DIVERGED_JACOBIAN_DOMAIN: int = DIVERGED_JACOBIAN_DOMAIN
Constant DIVERGED_JACOBIAN_DOMAIN of type int
DIVERGED_LINEAR_SOLVE: int = DIVERGED_LINEAR_SOLVE
Constant DIVERGED_LINEAR_SOLVE of type int
DIVERGED_LINE_SEARCH: int = DIVERGED_LINE_SEARCH
Constant DIVERGED_LINE_SEARCH of type int
DIVERGED_LOCAL_MIN: int = DIVERGED_LOCAL_MIN
Constant DIVERGED_LOCAL_MIN of type int
DIVERGED_MAX_IT: int = DIVERGED_MAX_IT
Constant DIVERGED_MAX_IT of type int
DIVERGED_TR_DELTA: int = DIVERGED_TR_DELTA
Constant DIVERGED_TR_DELTA of type int
ITERATING: int = ITERATING
Constant ITERATING of type int
petsc4py.PETSc.SNES.NormSchedule
class petsc4py.PETSc.SNES.NormSchedule
Bases: object
SNES norm schedule.
SEE ALSO:
SNESNormSchedule
Attributes Summary
┌─────────────────────────┬───────────────────────────────────────┐
│ ALWAYS │ Constant ALWAYS of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ DEFAULT │ Constant DEFAULT of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ FINAL_ONLY │ Constant FINAL_ONLY of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ INITIAL_FINAL_ONLY │ Constant INITIAL_FINAL_ONLY of type ‐ │
│ │ int │
├─────────────────────────┼───────────────────────────────────────┤
│ INITIAL_ONLY │ Constant INITIAL_ONLY of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NONE │ Constant NONE of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_ALWAYS │ Constant NORM_ALWAYS of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_DEFAULT │ Constant NORM_DEFAULT of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_FINAL_ONLY │ Constant NORM_FINAL_ONLY of type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_INITIAL_FINAL_ONLY │ Constant NORM_INITIAL_FINAL_ONLY of │
│ │ type int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_INITIAL_ONLY │ Constant NORM_INITIAL_ONLY of type ‐ │
│ │ int │
├─────────────────────────┼───────────────────────────────────────┤
│ NORM_NONE │ Constant NORM_NONE of type int │
└─────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
ALWAYS: int = ALWAYS
Constant ALWAYS of type int
DEFAULT: int = DEFAULT
Constant DEFAULT of type int
FINAL_ONLY: int = FINAL_ONLY
Constant FINAL_ONLY of type int
INITIAL_FINAL_ONLY: int = INITIAL_FINAL_ONLY
Constant INITIAL_FINAL_ONLY of type int
INITIAL_ONLY: int = INITIAL_ONLY
Constant INITIAL_ONLY of type int
NONE: int = NONE
Constant NONE of type int
NORM_ALWAYS: int = NORM_ALWAYS
Constant NORM_ALWAYS of type int
NORM_DEFAULT: int = NORM_DEFAULT
Constant NORM_DEFAULT of type int
NORM_FINAL_ONLY: int = NORM_FINAL_ONLY
Constant NORM_FINAL_ONLY of type int
NORM_INITIAL_FINAL_ONLY: int = NORM_INITIAL_FINAL_ONLY
Constant NORM_INITIAL_FINAL_ONLY of type int
NORM_INITIAL_ONLY: int = NORM_INITIAL_ONLY
Constant NORM_INITIAL_ONLY of type int
NORM_NONE: int = NORM_NONE
Constant NORM_NONE of type int
petsc4py.PETSc.SNES.Type
class petsc4py.PETSc.SNES.Type
Bases: object
SNES solver type.
SEE ALSO:
SNESType
Attributes Summary
┌──────────────────┬─────────────────────────────────────┐
│ ANDERSON │ Object ANDERSON of type str │
├──────────────────┼─────────────────────────────────────┤
│ ASPIN │ Object ASPIN of type str │
├──────────────────┼─────────────────────────────────────┤
│ COMPOSITE │ Object COMPOSITE of type str │
├──────────────────┼─────────────────────────────────────┤
│ FAS │ Object FAS of type str │
├──────────────────┼─────────────────────────────────────┤
│ KSPONLY │ Object KSPONLY of type str │
├──────────────────┼─────────────────────────────────────┤
│ KSPTRANSPOSEONLY │ Object KSPTRANSPOSEONLY of type str │
├──────────────────┼─────────────────────────────────────┤
│ MS │ Object MS of type str │
├──────────────────┼─────────────────────────────────────┤
│ NASM │ Object NASM of type str │
├──────────────────┼─────────────────────────────────────┤
│ NCG │ Object NCG of type str │
├──────────────────┼─────────────────────────────────────┤
│ NEWTONLS │ Object NEWTONLS of type str │
├──────────────────┼─────────────────────────────────────┤
│ NEWTONTR │ Object NEWTONTR of type str │
├──────────────────┼─────────────────────────────────────┤
│ NGMRES │ Object NGMRES of type str │
├──────────────────┼─────────────────────────────────────┤
│ NGS │ Object NGS of type str │
├──────────────────┼─────────────────────────────────────┤
│ NRICHARDSON │ Object NRICHARDSON of type str │
├──────────────────┼─────────────────────────────────────┤
│ PATCH │ Object PATCH of type str │
├──────────────────┼─────────────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├──────────────────┼─────────────────────────────────────┤
│ QN │ Object QN of type str │
├──────────────────┼─────────────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├──────────────────┼─────────────────────────────────────┤
│ VINEWTONRSLS │ Object VINEWTONRSLS of type str │
├──────────────────┼─────────────────────────────────────┤
│ VINEWTONSSLS │ Object VINEWTONSSLS of type str │
└──────────────────┴─────────────────────────────────────┘
Attributes Documentation
ANDERSON: str = ANDERSON
Object ANDERSON of type str
ASPIN: str = ASPIN
Object ASPIN of type str
COMPOSITE: str = COMPOSITE
Object COMPOSITE of type str
FAS: str = FAS
Object FAS of type str
KSPONLY: str = KSPONLY
Object KSPONLY of type str
KSPTRANSPOSEONLY: str = KSPTRANSPOSEONLY
Object KSPTRANSPOSEONLY of type str
MS: str = MS
Object MS of type str
NASM: str = NASM
Object NASM of type str
NCG: str = NCG
Object NCG of type str
NEWTONLS: str = NEWTONLS
Object NEWTONLS of type str
NEWTONTR: str = NEWTONTR
Object NEWTONTR of type str
NGMRES: str = NGMRES
Object NGMRES of type str
NGS: str = NGS
Object NGS of type str
NRICHARDSON: str = NRICHARDSON
Object NRICHARDSON of type str
PATCH: str = PATCH
Object PATCH of type str
PYTHON: str = PYTHON
Object PYTHON of type str
QN: str = QN
Object QN of type str
SHELL: str = SHELL
Object SHELL of type str
VINEWTONRSLS: str = VINEWTONRSLS
Object VINEWTONRSLS of type str
VINEWTONSSLS: str = VINEWTONSSLS
Object VINEWTONSSLS of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ appendOptionsPrefix(prefix) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ callConvergenceTest(its, xnorm, │ Compute the convergence test. │
│ ynorm, fnorm) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeFunction(x, f) │ Compute the function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeJacobian(x, J[, P]) │ Compute the Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeNGS(x[, b]) │ Compute a nonlinear Gauss-Seidel │
│ │ step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeObjective(x) │ Compute the value of the objective │
│ │ function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ converged(its, xnorm, ynorm, fnorm) │ Compute the convergence test and │
│ │ update the solver converged reason. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a SNES solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createPython([context, comm]) │ Create a nonlinear solver of Python │
│ │ type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getApplicationContext() │ Return the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCompositeNumber() │ Return the number of solvers in the │
│ │ composite. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCompositeSNES(n) │ Return the n-th solver in the │
│ │ composite. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergedReason() │ Return the termination flag. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergenceHistory() │ Return the convergence history. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergenceTest() │ Return the callback to used as │
│ │ convergence test. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM associated with the │
│ │ solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDivergenceTolerance() │ Get the divergence tolerance │
│ │ parameter used in the convergence │
│ │ tests. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getErrorIfNotConverged() │ Return the flag indicating error on │
│ │ divergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASCoarseSolve() │ Return the SNES used at the coarsest │
│ │ level of the FAS hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASCycleSNES(level) │ Return the SNES corresponding to a │
│ │ particular level of the FAS │
│ │ hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASInjection(level) │ Return the Mat used to apply the │
│ │ injection from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASInterpolation(level) │ Return the Mat used to apply the │
│ │ interpolation from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASLevels() │ Return the number of levels used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASRestriction(level) │ Return the Mat used to apply the │
│ │ restriction from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASSmoother(level) │ Return the smoother used at a given │
│ │ level of the FAS hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASSmootherDown(level) │ Return the downsmoother used at a │
│ │ given level of the FAS hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFASSmootherUp(level) │ Return the upsmoother used at a given │
│ │ level of the FAS hierarchy. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFunction() │ Return the callback to compute the │
│ │ nonlinear function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFunctionEvaluations() │ Return the current number of function │
│ │ evaluations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFunctionNorm() │ Return the function norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getInitialGuess() │ Return the callback to compute the │
│ │ initial guess. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIterationNumber() │ Return the current iteration number. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getJacobian() │ Return the matrices used to compute │
│ │ the Jacobian and the callback tuple. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getKSP() │ Return the linear solver used by the │
│ │ nonlinear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getKSPFailures() │ Return the current number of linear │
│ │ solve failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLinearSolveIterations() │ Return the total number of linear │
│ │ iterations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxFunctionEvaluations() │ Return the maximum allowed number of │
│ │ function evaluations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxKSPFailures() │ Return the maximum allowed number of │
│ │ linear solve failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxStepFailures() │ Return the maximum allowed number of │
│ │ step failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMonitor() │ Return the callback used to monitor │
│ │ solver convergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNASMNumber() │ Return the number of solvers in NASM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNASMSNES(n) │ Return the n-th solver in NASM. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNGS() │ Return the nonlinear Gauss-Seidel │
│ │ callback tuple. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNPC() │ Return the nonlinear preconditioner │
│ │ associated with the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNPCSide() │ Return the nonlinear preconditioning │
│ │ side. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNormSchedule() │ Return the norm schedule. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getObjective() │ Return the objective callback tuple. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getParamsEW() │ Get the parameters of the Eisenstat │
│ │ and Walker trick. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRhs() │ Return the vector holding the │
│ │ right-hand side. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolution() │ Return the vector holding the │
│ │ solution. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolutionUpdate() │ Return the vector holding the │
│ │ solution update. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStepFailures() │ Return the current number of step │
│ │ failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTRTolerances() │ Return the tolerance parameters used │
│ │ for the trust region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTRUpdateParameters() │ Return the update parameters used for │
│ │ the trust region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTolerances() │ Return the tolerance parameters used │
│ │ in the solver convergence tests. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getUpdate() │ Return the callback to compute the │
│ │ update at the beginning of each step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getUseEW() │ Return the flag indicating if the │
│ │ solver uses the Eisenstat-Walker │
│ │ trick. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getUseFD() │ Return true if the solver uses color │
│ │ finite-differencing for the Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getUseKSP() │ Return the flag indicating if the │
│ │ solver uses a linear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getUseMF() │ Return the flag indicating if the │
│ │ solver uses matrix-free │
│ │ finite-differencing. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVIInactiveSet() │ Return the index set for the inactive │
│ │ set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ hasNPC() │ Return a boolean indicating whether │
│ │ the solver has a nonlinear │
│ │ preconditioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ logConvergenceHistory(norm[, │ Log residual norm and linear │
│ linear_its]) │ iterations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitor(its, rnorm) │ Monitor the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitorCancel() │ Cancel all the monitors of the │
│ │ solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Reset the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setApplicationContext(appctx) │ Set the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergedReason(reason) │ Set the termination flag. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergenceHistory([length, │ Set the convergence history. │
│ reset]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergenceTest(converged[, args, │ Set the callback to use as │
│ kargs]) │ convergence test. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Associate a DM with the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDivergenceTolerance(dtol) │ Set the divergence tolerance │
│ │ parameter used in the convergence │
│ │ tests. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setErrorIfNotConverged(flag) │ Immediately generate an error if the │
│ │ solver has not converged. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFASInjection(level, mat) │ Set the Mat to be used to apply the │
│ │ injection from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFASInterpolation(level, mat) │ Set the Mat to be used to apply the │
│ │ interpolation from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFASLevels(levels[, comms]) │ Set the number of levels to use with │
│ │ FAS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFASRScale(level, vec) │ Set the scaling factor of the │
│ │ restriction operator from level to │
│ │ level-1. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFASRestriction(level, mat) │ Set the Mat to be used to apply the │
│ │ restriction from level-1 to level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setForceIteration(force) │ Force solve to take at least one │
│ │ iteration. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the solver from the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFunction(function[, f, args, │ Set the callback to compute the │
│ kargs]) │ nonlinear function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFunctionNorm(norm) │ Set the function norm value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setInitialGuess(initialguess[, args, │ Set the callback to compute the │
│ kargs]) │ initial guess. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIterationNumber(its) │ Set the current iteration number. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobian(jacobian[, J, P, args, │ Set the callback to compute the │
│ kargs]) │ Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setKSP(ksp) │ Set the linear solver that will be │
│ │ used by the nonlinear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLineSearchPreCheck(precheck[, │ Set the callback that will be called │
│ args, kargs]) │ before applying the linesearch. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxFunctionEvaluations(max_funcs) │ Set the maximum allowed number of │
│ │ function evaluations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxKSPFailures(max_fails) │ Set the maximum allowed number of │
│ │ linear solve failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxStepFailures(max_fails) │ Set the maximum allowed number of │
│ │ step failures. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMonitor(monitor[, args, kargs]) │ Set the callback used to monitor │
│ │ solver convergence. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNGS(ngs[, args, kargs]) │ Set the callback to compute nonlinear │
│ │ Gauss-Seidel. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNPC(snes) │ Set the nonlinear preconditioner. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNPCSide(side) │ Set the nonlinear preconditioning │
│ │ side. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNormSchedule(normsched) │ Set the norm schedule. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setObjective(objective[, args, │ Set the callback to compute the │
│ kargs]) │ objective function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for searching for │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setParamsEW([version, rtol_0, │ Set the parameters for the Eisenstat │
│ rtol_max, ...]) │ and Walker trick. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchCellNumbering(sec) │ Set cell patch numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeFunction(function[, │ Set patch compute function. │
│ args, kargs]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchComputeOperator(operator[, │ Set patch compute operator. │
│ args, kargs]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchConstructType(typ[, operator, │ Set patch construct type. │
│ args, ...]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPatchDiscretisationInfo(dms, bs, │ Set patch discretisation information. │
│ ...) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext(context) │ Set the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setResetCounters([reset]) │ Set the flag to reset the counters. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSolution(vec) │ Set the vector used to store the │
│ │ solution. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTRTolerances([delta_min, │ Set the tolerance parameters used for │
│ delta_max, delta_0]) │ the trust region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTRUpdateParameters([eta1, eta2, │ Set the update parameters used for │
│ eta3, t1, t2]) │ the trust region. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTolerances([rtol, atol, stol, │ Set the tolerance parameters used in │
│ max_it]) │ the solver convergence tests. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(snes_type) │ Set the type of the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUpMatrices() │ Ensures that matrices are available │
│ │ for Newton-like methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUpdate(update[, args, kargs]) │ Set the callback to compute update at │
│ │ the beginning of each step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUseEW([flag]) │ Tell the solver to use the │
│ │ Eisenstat-Walker trick. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUseFD([flag]) │ Set the boolean flag to use coloring │
│ │ finite-differencing for Jacobian │
│ │ assembly. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUseKSP([flag]) │ Set the boolean flag indicating to │
│ │ use a linear solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUseMF([flag]) │ Set the boolean flag indicating to │
│ │ use matrix-free finite-differencing. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setVariableBounds(xl, xu) │ Set the vector for the variable │
│ │ bounds. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solve([b, x]) │ Solve the nonlinear equations. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the solver. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌──────────────┬───────────────────────────────────────┐
│ appctx │ Application context. │
├──────────────┼───────────────────────────────────────┤
│ atol │ Absolute residual tolerance. │
├──────────────┼───────────────────────────────────────┤
│ dm │ DM. │
├──────────────┼───────────────────────────────────────┤
│ history │ Convergence history. │
├──────────────┼───────────────────────────────────────┤
│ is_converged │ Boolean indicating if the solver has │
│ │ converged. │
├──────────────┼───────────────────────────────────────┤
│ is_diverged │ Boolean indicating if the solver has │
│ │ failed. │
├──────────────┼───────────────────────────────────────┤
│ is_iterating │ Boolean indicating if the solver has │
│ │ not converged yet. │
├──────────────┼───────────────────────────────────────┤
│ its │ Number of iterations. │
├──────────────┼───────────────────────────────────────┤
│ ksp │ Linear solver. │
├──────────────┼───────────────────────────────────────┤
│ max_funcs │ Maximum number of function │
│ │ evaluations. │
├──────────────┼───────────────────────────────────────┤
│ max_it │ Maximum number of iterations. │
├──────────────┼───────────────────────────────────────┤
│ norm │ Function norm. │
├──────────────┼───────────────────────────────────────┤
│ npc │ Nonlinear preconditioner. │
├──────────────┼───────────────────────────────────────┤
│ reason │ Converged reason. │
├──────────────┼───────────────────────────────────────┤
│ rtol │ Relative residual tolerance. │
├──────────────┼───────────────────────────────────────┤
│ stol │ Solution update tolerance. │
├──────────────┼───────────────────────────────────────┤
│ use_ew │ Use the Eisenstat-Walker trick. │
├──────────────┼───────────────────────────────────────┤
│ use_fd │ Boolean indicating if the solver uses │
│ │ coloring finite-differencing. │
├──────────────┼───────────────────────────────────────┤
│ use_ksp │ Boolean indicating if the solver uses │
│ │ a linear solver. │
├──────────────┼───────────────────────────────────────┤
│ use_mf │ Boolean indicating if the solver uses │
│ │ matrix-free finite-differencing. │
├──────────────┼───────────────────────────────────────┤
│ vec_rhs │ Right-hand side vector. │
├──────────────┼───────────────────────────────────────┤
│ vec_sol │ Solution vector. │
├──────────────┼───────────────────────────────────────┤
│ vec_upd │ Update vector. │
└──────────────┴───────────────────────────────────────┘
Methods Documentation
appendOptionsPrefix(prefix)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, SNESAppendOptionsPrefix
Source code at petsc4py/PETSc/SNES.pyx:227
Parameters
prefix (str | None)
Return type
None
callConvergenceTest(its, xnorm, ynorm, fnorm)
Compute the convergence test.
Collective.
Parameters
• its (int) -- Iteration number.
• xnorm (float) -- Solution norm.
• ynorm (float) -- Update norm.
• fnorm (float) -- Function norm.
Return type
ConvergedReason
SEE ALSO:
setConvergenceTest, getConvergenceTest
Source code at petsc4py/PETSc/SNES.pyx:1326
computeFunction(x, f)
Compute the function.
Collective.
Parameters
• x (Vec) -- The input state vector.
• f (Vec) -- The output vector.
Return type
None
SEE ALSO:
setFunction, SNESComputeFunction
Source code at petsc4py/PETSc/SNES.pyx:1027
computeJacobian(x, J, P=None)
Compute the Jacobian.
Collective.
Parameters
• x (Vec) -- The input state vector.
• J (Mat) -- The output Jacobian matrix.
• P (Mat | None) -- The output Jacobian matrix used to construct the preconditioner.
Return type
None
SEE ALSO:
setJacobian, SNESComputeJacobian
Source code at petsc4py/PETSc/SNES.pyx:1046
computeNGS(x, b=None)
Compute a nonlinear Gauss-Seidel step.
Collective.
Parameters
• x (Vec) -- The input/output state vector.
• b (Vec | None) -- The input right-hand side vector.
Return type
None
SEE ALSO:
setNGS, getNGS, SNESComputeNGS
Source code at petsc4py/PETSc/SNES.pyx:1133
computeObjective(x)
Compute the value of the objective function.
Collective.
Parameters
x (Vec) -- The input state vector.
Return type
float
SEE ALSO:
setObjective, SNESComputeObjective
Source code at petsc4py/PETSc/SNES.pyx:1069
converged(its, xnorm, ynorm, fnorm)
Compute the convergence test and update the solver converged reason.
Collective.
Parameters
• its (int) -- Iteration number.
• xnorm (float) -- Solution norm.
• ynorm (float) -- Update norm.
• fnorm (float) -- Function norm.
Return type
None
SEE ALSO:
setConvergenceTest, getConvergenceTest, SNESConverged
Source code at petsc4py/PETSc/SNES.pyx:1356
create(comm=None)
Create a SNES solver.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, SNESCreate
Source code at petsc4py/PETSc/SNES.pyx:145
createPython(context=None, comm=None)
Create a nonlinear solver of Python type.
Collective.
Parameters
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python nonlinear solver type (TODO), setType, setPythonContext, Type.PYTHON
Source code at petsc4py/PETSc/SNES.pyx:2179
destroy()
Destroy the solver.
Collective.
SEE ALSO:
SNESDestroy
Source code at petsc4py/PETSc/SNES.pyx:132
Return type
Self
getApplicationContext()
Return the application context.
Source code at petsc4py/PETSc/SNES.pyx:264
Return type
Any
getCompositeNumber()
Return the number of solvers in the composite.
Not collective.
SEE ALSO:
getCompositeSNES, SNESCompositeGetNumber, SNESCOMPOSITE
Source code at petsc4py/PETSc/SNES.pyx:2280
Return type
int
getCompositeSNES(n)
Return the n-th solver in the composite.
Not collective.
SEE ALSO:
getCompositeNumber, SNESCompositeGetSNES, SNESCOMPOSITE
Source code at petsc4py/PETSc/SNES.pyx:2263
Parameters
n (int)
Return type
SNES
getConvergedReason()
Return the termination flag.
Not collective.
SEE ALSO:
setConvergedReason, SNESGetConvergedReason
Source code at petsc4py/PETSc/SNES.pyx:1739
Return type
ConvergedReason
getConvergenceHistory()
Return the convergence history.
Not collective.
SEE ALSO:
SNESGetConvergenceHistory
Source code at petsc4py/PETSc/SNES.pyx:1407
Return type
tuple[ArrayReal, ArrayInt]
getConvergenceTest()
Return the callback to used as convergence test.
Not collective.
SEE ALSO:
setConvergenceTest, callConvergenceTest
Source code at petsc4py/PETSc/SNES.pyx:1314
Return type
SNESConvergedFunction
getDM()
Return the DM associated with the solver.
Not collective.
SEE ALSO:
setDM, SNESGetDM
Source code at petsc4py/PETSc/SNES.pyx:279
Return type
DM
getDivergenceTolerance()
Get the divergence tolerance parameter used in the convergence tests.
Not collective.
SEE ALSO:
setDivergenceTolerance, getTolerances, SNESGetDivergenceTolerance
Source code at petsc4py/PETSc/SNES.pyx:1239
Return type
float
getErrorIfNotConverged()
Return the flag indicating error on divergence.
Not collective.
SEE ALSO:
setErrorIfNotConverged, SNESGetErrorIfNotConverged
Source code at petsc4py/PETSc/SNES.pyx:1766
Return type
bool
getFASCoarseSolve()
Return the SNES used at the coarsest level of the FAS hierarchy.
Not collective.
SEE ALSO:
getFASSmoother, SNESFASGetCoarseSolve, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:594
Return type
SNES
getFASCycleSNES(level)
Return the SNES corresponding to a particular level of the FAS hierarchy.
Not collective.
SEE ALSO:
setFASLevels, getFASCoarseSolve, getFASSmoother, SNESFASGetCycleSNES, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:577
Parameters
level (int)
Return type
SNES
getFASInjection(level)
Return the Mat used to apply the injection from level-1 to level.
Not collective.
SEE ALSO:
setFASInjection, SNESFASGetInjection, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:500
Parameters
level (int)
Return type
Mat
getFASInterpolation(level)
Return the Mat used to apply the interpolation from level-1 to level.
Not collective.
SEE ALSO:
setFASInterpolation, SNESFASGetInterpolation, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:440
Parameters
level (int)
Return type
Mat
getFASLevels()
Return the number of levels used.
Not collective.
SEE ALSO:
setFASLevels, SNESFASGetLevels, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:563
Return type
int
getFASRestriction(level)
Return the Mat used to apply the restriction from level-1 to level.
Not collective.
SEE ALSO:
setFASRestriction, SNESFASGetRestriction, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:470
Parameters
level (int)
Return type
Mat
getFASSmoother(level)
Return the smoother used at a given level of the FAS hierarchy.
Not collective.
SEE ALSO:
setFASLevels, getFASCoarseSolve, getFASSmootherDown, getFASSmootherUp, ‐
SNESFASGetSmoother, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:609
Parameters
level (int)
Return type
SNES
getFASSmootherDown(level)
Return the downsmoother used at a given level of the FAS hierarchy.
Not collective.
SEE ALSO:
setFASLevels, getFASCoarseSolve, getFASSmoother, getFASSmootherUp, ‐
SNESFASGetSmootherDown, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:626
Parameters
level (int)
Return type
SNES
getFASSmootherUp(level)
Return the upsmoother used at a given level of the FAS hierarchy.
Not collective.
SEE ALSO:
setFASLevels, getFASCoarseSolve, getFASSmoother, getFASSmootherDown, ‐
SNESFASGetSmootherUp, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:643
Parameters
level (int)
Return type
SNES
getFunction()
Return the callback to compute the nonlinear function.
Not collective.
SEE ALSO:
setFunction, SNESGetFunction
Source code at petsc4py/PETSc/SNES.pyx:843
Return type
SNESFunction
getFunctionEvaluations()
Return the current number of function evaluations.
Not collective.
SEE ALSO:
setMaxFunctionEvaluations, SNESGetNumberFunctionEvals
Source code at petsc4py/PETSc/SNES.pyx:1560
Return type
int
getFunctionNorm()
Return the function norm.
Not collective.
SEE ALSO:
setFunctionNorm, SNESGetFunctionNorm
Source code at petsc4py/PETSc/SNES.pyx:1837
Return type
float
getInitialGuess()
Return the callback to compute the initial guess.
Not collective.
SEE ALSO:
setInitialGuess
Source code at petsc4py/PETSc/SNES.pyx:796
Return type
SNESGuessFunction
getIterationNumber()
Return the current iteration number.
Not collective.
SEE ALSO:
setIterationNumber, SNESGetIterationNumber
Source code at petsc4py/PETSc/SNES.pyx:1795
Return type
int
getJacobian()
Return the matrices used to compute the Jacobian and the callback tuple.
Not collective.
Returns
• J (Mat) -- The matrix to store the Jacobian.
• P (Mat) -- The matrix to construct the preconditioner.
• callback (SNESJacobianFunction) -- callback, positional and keyword arguments.
Return type
tuple[Mat, Mat, SNESJacobianFunction]
SEE ALSO:
setJacobian, SNESGetJacobian
Source code at petsc4py/PETSc/SNES.pyx:955
getKSP()
Return the linear solver used by the nonlinear solver.
Not collective.
SEE ALSO:
setKSP, SNESGetKSP
Source code at petsc4py/PETSc/SNES.pyx:1936
Return type
KSP
getKSPFailures()
Return the current number of linear solve failures.
Not collective.
SEE ALSO:
getMaxKSPFailures, SNESGetLinearSolveFailures
Source code at petsc4py/PETSc/SNES.pyx:1642
Return type
int
getLinearSolveIterations()
Return the total number of linear iterations.
Not collective.
SEE ALSO:
SNESGetLinearSolveIterations
Source code at petsc4py/PETSc/SNES.pyx:1851
Return type
int
getMaxFunctionEvaluations()
Return the maximum allowed number of function evaluations.
Not collective.
SEE ALSO:
setMaxFunctionEvaluations, SNESSetTolerances
Source code at petsc4py/PETSc/SNES.pyx:1544
Return type
int
getMaxKSPFailures()
Return the maximum allowed number of linear solve failures.
Not collective.
SEE ALSO:
setMaxKSPFailures, SNESGetMaxLinearSolveFailures
Source code at petsc4py/PETSc/SNES.pyx:1628
Return type
int
getMaxStepFailures()
Return the maximum allowed number of step failures.
Not collective.
SEE ALSO:
setMaxStepFailures, SNESGetMaxNonlinearStepFailures
Source code at petsc4py/PETSc/SNES.pyx:1587
Return type
int
getMonitor()
Return the callback used to monitor solver convergence.
Not collective.
SEE ALSO:
setMonitor
Source code at petsc4py/PETSc/SNES.pyx:1479
Return type
list[tuple[SNESMonitorFunction, tuple[Any, ...], dict[str, Any]]]
getNASMNumber()
Return the number of solvers in NASM.
Not collective.
SEE ALSO:
getNASMSNES, SNESNASMGetNumber, SNESNASM
Source code at petsc4py/PETSc/SNES.pyx:2312
Return type
int
getNASMSNES(n)
Return the n-th solver in NASM.
Not collective.
SEE ALSO:
getNASMNumber, SNESNASMGetSNES, SNESNASM
Source code at petsc4py/PETSc/SNES.pyx:2296
Parameters
n (int)
Return type
SNES
getNGS()
Return the nonlinear Gauss-Seidel callback tuple.
Not collective.
SEE ALSO:
setNGS, computeNGS
Source code at petsc4py/PETSc/SNES.pyx:1119
Return type
SNESNGSFunction
getNPC()
Return the nonlinear preconditioner associated with the solver.
Not collective.
SEE ALSO:
setNPC, hasNPC, setNPCSide, getNPCSide, SNESGetNPC
Source code at petsc4py/PETSc/SNES.pyx:662
Return type
SNES
getNPCSide()
Return the nonlinear preconditioning side.
Not collective.
SEE ALSO:
setNPC, getNPC, hasNPC, setNPCSide, SNESGetNPCSide
Source code at petsc4py/PETSc/SNES.pyx:715
Return type
Side
getNormSchedule()
Return the norm schedule.
Not collective.
SEE ALSO:
setNormSchedule, SNESGetNormSchedule
Source code at petsc4py/PETSc/SNES.pyx:1265
Return type
NormSchedule
getObjective()
Return the objective callback tuple.
Not collective.
SEE ALSO:
setObjective
Source code at petsc4py/PETSc/SNES.pyx:1013
Return type
SNESObjFunction
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, SNESGetOptionsPrefix
Source code at petsc4py/PETSc/SNES.pyx:213
Return type
str
getParamsEW()
Get the parameters of the Eisenstat and Walker trick.
Not collective.
SEE ALSO:
setUseEW, setParamsEW, SNESKSPGetParametersEW
Source code at petsc4py/PETSc/SNES.pyx:2040
Return type
dict[str, int | float]
getPythonContext()
Return the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python nonlinear solver type (TODO), setPythonContext
Source code at petsc4py/PETSc/SNES.pyx:2216
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the solver.
Not collective.
SEE ALSO:
PETSc Python nonlinear solver type (TODO), setPythonContext, setPythonType, ‐
SNESPythonGetType
Source code at petsc4py/PETSc/SNES.pyx:2246
Return type
str
getRhs()
Return the vector holding the right-hand side.
Not collective.
SEE ALSO:
SNESGetRhs
Source code at petsc4py/PETSc/SNES.pyx:1865
Return type
Vec
getSolution()
Return the vector holding the solution.
Not collective.
SEE ALSO:
setSolution, SNESGetSolution
Source code at petsc4py/PETSc/SNES.pyx:1880
Return type
Vec
getSolutionUpdate()
Return the vector holding the solution update.
Not collective.
SEE ALSO:
SNESGetSolutionUpdate
Source code at petsc4py/PETSc/SNES.pyx:1907
Return type
Vec
getStepFailures()
Return the current number of step failures.
Not collective.
SEE ALSO:
getMaxStepFailures, SNESGetNonlinearStepFailures
Source code at petsc4py/PETSc/SNES.pyx:1601
Return type
int
getTRTolerances()
Return the tolerance parameters used for the trust region.
Not collective.
Returns
• delta_min (float) -- The minimum allowed trust region size.
• delta_max (float) -- The maximum allowed trust region size.
• delta_0 (float) -- The initial trust region size.
Return type
tuple[float, float, float]
SEE ALSO:
setTRTolerances, getTRUpdateParameters, SNESNewtonTRGetTolerances
Source code at petsc4py/PETSc/SNES.pyx:337
getTRUpdateParameters()
Return the update parameters used for the trust region.
Not collective.
Returns
• eta1 (float) -- The step acceptance tolerance.
• eta2 (float) -- The shrinking tolerance.
• eta3 (float) -- The enlarging tolerance.
• t1 (float) -- The shrinking factor.
• t2 (float) -- The enlarging factor.
Return type
tuple[float, float, float, float, float]
SEE ALSO:
setTRUpdateParameters, getTRTolerances, SNESNewtonTRGetUpdateParameters
Source code at petsc4py/PETSc/SNES.pyx:396
getTolerances()
Return the tolerance parameters used in the solver convergence tests.
Not collective.
Returns
• rtol (float) -- The relative norm of the residual.
• atol (float) -- The absolute norm of the residual.
• stol (float) -- The absolute norm of the step.
• max_it (int) -- The maximum allowed number of iterations.
Return type
tuple[float, float, float, int]
SEE ALSO:
setTolerances, SNESGetTolerances
Source code at petsc4py/PETSc/SNES.pyx:1195
getType()
Return the type of the solver.
Not collective.
SEE ALSO:
setType, SNESGetType
Source code at petsc4py/PETSc/SNES.pyx:185
Return type
str
getUpdate()
Return the callback to compute the update at the beginning of each step.
Not collective.
SEE ALSO:
setUpdate
Source code at petsc4py/PETSc/SNES.pyx:904
Return type
SNESUpdateFunction
getUseEW()
Return the flag indicating if the solver uses the Eisenstat-Walker trick.
Not collective.
SEE ALSO:
setUseEW, setParamsEW, SNESKSPGetUseEW
Source code at petsc4py/PETSc/SNES.pyx:1974
Return type
bool
getUseFD()
Return true if the solver uses color finite-differencing for the Jacobian.
Not collective.
SEE ALSO:
setUseFD
Source code at petsc4py/PETSc/SNES.pyx:2134
Return type
False
getUseKSP()
Return the flag indicating if the solver uses a linear solver.
Not collective.
SEE ALSO:
setUseKSP
Source code at petsc4py/PETSc/SNES.pyx:2078
Return type
bool
getUseMF()
Return the flag indicating if the solver uses matrix-free finite-differencing.
Not collective.
SEE ALSO:
setUseMF
Source code at petsc4py/PETSc/SNES.pyx:2107
Return type
bool
getVIInactiveSet()
Return the index set for the inactive set.
Not collective.
SEE ALSO:
SNESVIGetInactiveSet
Source code at petsc4py/PETSc/SNES.pyx:2162
Return type
IS
hasNPC()
Return a boolean indicating whether the solver has a nonlinear preconditioner.
Not collective.
SEE ALSO:
setNPC, getNPC, setNPCSide, getNPCSide, SNESHasNPC
Source code at petsc4py/PETSc/SNES.pyx:677
Return type
bool
logConvergenceHistory(norm, linear_its=0)
Log residual norm and linear iterations.
Source code at petsc4py/PETSc/SNES.pyx:1425
Parameters
• norm (float)
• linear_its (int)
Return type
None
monitor(its, rnorm)
Monitor the solver.
Collective.
Parameters
• its -- Current number of iterations.
• rnorm -- Current value of the residual norm.
Return type
None
SEE ALSO:
setMonitor, SNESMonitor
Source code at petsc4py/PETSc/SNES.pyx:1506
monitorCancel()
Cancel all the monitors of the solver.
Logically collective.
SEE ALSO:
setMonitor, SNESMonitorCancel
Source code at petsc4py/PETSc/SNES.pyx:1491
Return type
None
reset()
Reset the solver.
Collective.
SEE ALSO:
SNESReset
Source code at petsc4py/PETSc/SNES.pyx:1691
Return type
None
setApplicationContext(appctx)
Set the application context.
Source code at petsc4py/PETSc/SNES.pyx:255
Parameters
appctx (Any)
Return type
None
setConvergedReason(reason)
Set the termination flag.
Collective.
SEE ALSO:
getConvergedReason, SNESSetConvergedReason
Source code at petsc4py/PETSc/SNES.pyx:1726
Parameters
reason (ConvergedReason)
Return type
None
setConvergenceHistory(length=None, reset=False)
Set the convergence history.
Logically collective.
SEE ALSO:
SNESSetConvergenceHistory
Source code at petsc4py/PETSc/SNES.pyx:1383
Return type
None
setConvergenceTest(converged, args=None, kargs=None)
Set the callback to use as convergence test.
Logically collective.
Parameters
• converged (SNESConvergedFunction | Literal['skip', 'default']) -- The convergence
testing callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getConvergenceTest, callConvergenceTest, SNESSetConvergenceTest
Source code at petsc4py/PETSc/SNES.pyx:1279
setDM(dm)
Associate a DM with the solver.
Not collective.
SEE ALSO:
getDM, SNESSetDM
Source code at petsc4py/PETSc/SNES.pyx:296
Parameters
dm (DM)
Return type
None
setDivergenceTolerance(dtol)
Set the divergence tolerance parameter used in the convergence tests.
Logically collective.
Parameters
dtol (float) -- The divergence tolerance.
Return type
None
SEE ALSO:
getDivergenceTolerance, setTolerances, SNESSetDivergenceTolerance
Source code at petsc4py/PETSc/SNES.pyx:1222
setErrorIfNotConverged(flag)
Immediately generate an error if the solver has not converged.
Collective.
SEE ALSO:
getErrorIfNotConverged, SNESSetErrorIfNotConverged
Source code at petsc4py/PETSc/SNES.pyx:1753
Parameters
flag (bool)
Return type
None
setFASInjection(level, mat)
Set the Mat to be used to apply the injection from level-1 to level.
Collective.
SEE ALSO:
getFASInjection, setFASInterpolation, setFASRestriction, SNESFASSetInjection, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:486
Parameters
• level (int)
• mat (Mat)
Return type
None
setFASInterpolation(level, mat)
Set the Mat to be used to apply the interpolation from level-1 to level.
Collective.
SEE ALSO:
getFASInterpolation, setFASRestriction, setFASInjection, SNESFASSetInterpolation, ‐
SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:426
Parameters
• level (int)
• mat (Mat)
Return type
None
setFASLevels(levels, comms=None)
Set the number of levels to use with FAS.
Collective.
Parameters
• levels (int) -- The number of levels
• comms (Sequence[Comm]) -- An optional sequence of communicators of length Logging
Levels, or None for the default communicator Sys.getDefaultComm.
Return type
None
SEE ALSO:
getFASLevels, SNESFASSetLevels, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:529
setFASRScale(level, vec)
Set the scaling factor of the restriction operator from level to level-1.
Collective.
SEE ALSO:
setFASRestriction, SNESFASSetRScale, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:516
Parameters
• level (int)
• vec (Vec)
Return type
None
setFASRestriction(level, mat)
Set the Mat to be used to apply the restriction from level-1 to level.
Collective.
SEE ALSO:
setFASRScale, getFASRestriction, setFASInterpolation, setFASInjection, ‐
SNESFASSetRestriction, SNESFAS
Source code at petsc4py/PETSc/SNES.pyx:456
Parameters
• level (int)
• mat (Mat)
Return type
None
setForceIteration(force)
Force solve to take at least one iteration.
Collective.
SEE ALSO:
SNESSetForceIteration
Source code at petsc4py/PETSc/SNES.pyx:1809
Parameters
force (bool)
Return type
None
setFromOptions()
Configure the solver from the options database.
Collective.
SEE ALSO:
Working with PETSc options, SNESSetFromOptions
Source code at petsc4py/PETSc/SNES.pyx:241
Return type
None
setFunction(function, f=None, args=None, kargs=None)
Set the callback to compute the nonlinear function.
Logically collective.
Parameters
• function (SNESFunction | None) -- The callback.
• f (Vec | None) -- An optional vector to store the result.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getFunction, SNESSetFunction
Source code at petsc4py/PETSc/SNES.pyx:808
setFunctionNorm(norm)
Set the function norm value.
Collective.
This is only of use to implementers of custom SNES types.
SEE ALSO:
getFunctionNorm, SNESSetFunctionNorm
Source code at petsc4py/PETSc/SNES.pyx:1822
Parameters
norm (float)
Return type
None
setInitialGuess(initialguess, args=None, kargs=None)
Set the callback to compute the initial guess.
Logically collective.
Parameters
• initialguess (SNESGuessFunction | None) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getInitialGuess, SNESSetComputeInitialGuess
Source code at petsc4py/PETSc/SNES.pyx:765
setIterationNumber(its)
Set the current iteration number.
Collective.
This is only of use to implementers of custom SNES types.
SEE ALSO:
getIterationNumber, SNESSetIterationNumber
Source code at petsc4py/PETSc/SNES.pyx:1780
Parameters
its (int)
Return type
None
setJacobian(jacobian, J=None, P=None, args=None, kargs=None)
Set the callback to compute the Jacobian.
Logically collective.
Parameters
• jacobian (SNESJacobianFunction | None) -- The Jacobian callback.
• J (Mat | None) -- The matrix to store the Jacobian.
• P (Mat | None) -- The matrix to construct the preconditioner.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getJacobian, SNESSetJacobian
Source code at petsc4py/PETSc/SNES.pyx:916
setKSP(ksp)
Set the linear solver that will be used by the nonlinear solver.
Logically collective.
SEE ALSO:
getKSP, SNESSetKSP
Source code at petsc4py/PETSc/SNES.pyx:1924
Parameters
ksp (KSP)
Return type
None
setLineSearchPreCheck(precheck, args=None, kargs=None)
Set the callback that will be called before applying the linesearch.
Logically collective.
Parameters
• precheck (SNESLSPreFunction | None) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
SNESLineSearchSetPreCheck
Source code at petsc4py/PETSc/SNES.pyx:731
setMaxFunctionEvaluations(max_funcs)
Set the maximum allowed number of function evaluations.
Collective.
SEE ALSO:
getMaxFunctionEvaluations, SNESSetTolerances
Source code at petsc4py/PETSc/SNES.pyx:1529
Parameters
max_funcs (int)
Return type
None
setMaxKSPFailures(max_fails)
Set the maximum allowed number of linear solve failures.
Collective.
SEE ALSO:
getMaxKSPFailures, SNESSetMaxLinearSolveFailures
Source code at petsc4py/PETSc/SNES.pyx:1615
Parameters
max_fails (int)
Return type
None
setMaxStepFailures(max_fails)
Set the maximum allowed number of step failures.
Collective.
SEE ALSO:
getMaxStepFailures, SNESSetMaxNonlinearStepFailures
Source code at petsc4py/PETSc/SNES.pyx:1574
Parameters
max_fails (int)
Return type
None
setMonitor(monitor, args=None, kargs=None)
Set the callback used to monitor solver convergence.
Logically collective.
Parameters
• monitor (SNESMonitorFunction | None) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getMonitor, SNESMonitorSet
Source code at petsc4py/PETSc/SNES.pyx:1446
setNGS(ngs, args=None, kargs=None)
Set the callback to compute nonlinear Gauss-Seidel.
Logically collective.
Parameters
• ngs (SNESNGSFunction | None) -- The nonlinear Gauss-Seidel callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getNGS, computeNGS, SNESSetNGS
Source code at petsc4py/PETSc/SNES.pyx:1088
setNPC(snes)
Set the nonlinear preconditioner.
Logically collective.
SEE ALSO:
getNPC, hasNPC, setNPCSide, getNPCSide, SNESSetNPC
Source code at petsc4py/PETSc/SNES.pyx:691
Parameters
snes (SNES)
Return type
None
setNPCSide(side)
Set the nonlinear preconditioning side.
Collective.
SEE ALSO:
setNPC, getNPC, hasNPC, getNPCSide, SNESSetNPCSide
Source code at petsc4py/PETSc/SNES.pyx:703
Parameters
side (Side)
Return type
None
setNormSchedule(normsched)
Set the norm schedule.
Collective.
SEE ALSO:
getNormSchedule, SNESSetNormSchedule
Source code at petsc4py/PETSc/SNES.pyx:1253
Parameters
normsched (NormSchedule)
Return type
None
setObjective(objective, args=None, kargs=None)
Set the callback to compute the objective function.
Logically collective.
Parameters
• objective (SNESObjFunction | None) -- The Jacobian callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getObjective, SNESSetObjective
Source code at petsc4py/PETSc/SNES.pyx:982
setOptionsPrefix(prefix)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, SNESSetOptionsPrefix
Source code at petsc4py/PETSc/SNES.pyx:199
Parameters
prefix (str | None)
Return type
None
setParamsEW(version=None, rtol_0=None, rtol_max=None, gamma=None, alpha=None, alpha2=None,
threshold=None)
Set the parameters for the Eisenstat and Walker trick.
Logically collective.
Parameters
• version (int) -- The version of the algorithm. Defaults to CURRENT.
• rtol_0 (float) -- The initial relative residual norm. Defaults to CURRENT.
• rtol_max (float) -- The maximum relative residual norm. Defaults to CURRENT.
• gamma (float) -- Parameter. Defaults to CURRENT.
• alpha (float) -- Parameter. Defaults to CURRENT.
• alpha2 (float) -- Parameter. Defaults to CURRENT.
• threshold (float) -- Parameter. Defaults to CURRENT.
Return type
None
SEE ALSO:
setUseEW, getParamsEW, SNESKSPSetParametersEW
Source code at petsc4py/PETSc/SNES.pyx:1988
setPatchCellNumbering(sec)
Set cell patch numbering.
Source code at petsc4py/PETSc/SNES.pyx:2328
Parameters
sec (Section)
Return type
None
setPatchComputeFunction(function, args=None, kargs=None)
Set patch compute function.
Source code at petsc4py/PETSc/SNES.pyx:2381
Return type
None
setPatchComputeOperator(operator, args=None, kargs=None)
Set patch compute operator.
Source code at petsc4py/PETSc/SNES.pyx:2373
Return type
None
setPatchConstructType(typ, operator=None, args=None, kargs=None)
Set patch construct type.
Source code at petsc4py/PETSc/SNES.pyx:2389
Return type
None
setPatchDiscretisationInfo(dms, bs, cellNodeMaps, subspaceOffsets, ghostBcNodes, globalBcNodes)
Set patch discretisation information.
Source code at petsc4py/PETSc/SNES.pyx:2332
Return type
None
setPythonContext(context)
Set the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python nonlinear solver type (TODO), getPythonContext
Source code at petsc4py/PETSc/SNES.pyx:2204
Parameters
context (Any)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
SEE ALSO:
PETSc Python nonlinear solver type (TODO), setPythonContext, getPythonType, ‐
SNESPythonSetType
Source code at petsc4py/PETSc/SNES.pyx:2231
Parameters
py_type (str)
Return type
None
setResetCounters(reset=True)
Set the flag to reset the counters.
Collective.
SEE ALSO:
SNESSetCountersReset
Source code at petsc4py/PETSc/SNES.pyx:1431
Parameters
reset (bool)
Return type
None
setSolution(vec)
Set the vector used to store the solution.
Collective.
SEE ALSO:
getSolution, SNESSetSolution
Source code at petsc4py/PETSc/SNES.pyx:1895
Parameters
vec (Vec)
Return type
None
setTRTolerances(delta_min=None, delta_max=None, delta_0=None)
Set the tolerance parameters used for the trust region.
Logically collective.
Parameters
• delta_min (float) -- The minimum allowed trust region size. Defaults to CURRENT.
• delta_max (float) -- The maximum allowed trust region size. Defaults to CURRENT.
• delta_0 (float) -- The initial trust region size. Defaults to CURRENT.
Return type
None
SEE ALSO:
getTRTolerances, setTRUpdateParameters, SNESNewtonTRSetTolerances
Source code at petsc4py/PETSc/SNES.pyx:310
setTRUpdateParameters(eta1=None, eta2=None, eta3=None, t1=None, t2=None)
Set the update parameters used for the trust region.
Logically collective.
Parameters
• eta1 (float) -- The step acceptance tolerance. Defaults to CURRENT.
• eta2 (float) -- The shrinking tolerance. Defaults to CURRENT.
• eta3 (float) -- The enlarging tolerance. Defaults to CURRENT.
• t1 (float) -- The shrinking factor. Defaults to CURRENT.
• t2 (float) -- The enlarging factor. Defaults to CURRENT.
Return type
None
SEE ALSO:
setTRTolerances, getTRUpdateParameters, SNESNewtonTRSetUpdateParameters
Source code at petsc4py/PETSc/SNES.pyx:361
setTolerances(rtol=None, atol=None, stol=None, max_it=None)
Set the tolerance parameters used in the solver convergence tests.
Logically collective.
Parameters
• rtol (float) -- The relative norm of the residual, or DETERMINE to use the value
when the object's type was set. Defaults to CURRENT.
• atol (float) -- The absolute norm of the residual, or DETERMINE to use the value
when the object's type was set. Defaults to CURRENT.
• stol (float) -- The absolute norm of the step, or DETERMINE to use the value when
the object's type was set. Defaults to CURRENT.
• max_it (int) -- The maximum allowed number of iterations, or DETERMINE to use the
value when the object's type was set. Defaults to CURRENT. Use UNLIMITED to have
no maximum.
Return type
None
SEE ALSO:
getTolerances, SNESSetTolerances
Source code at petsc4py/PETSc/SNES.pyx:1156
setType(snes_type)
Set the type of the solver.
Logically collective.
Parameters
snes_type (Type | str) -- The type of the solver.
Return type
None
SEE ALSO:
getType, SNESSetType
Source code at petsc4py/PETSc/SNES.pyx:166
setUp()
Set up the internal data structures for using the solver.
Collective.
SEE ALSO:
SNESSetUp
Source code at petsc4py/PETSc/SNES.pyx:1665
Return type
None
setUpMatrices()
Ensures that matrices are available for Newton-like methods.
Collective.
This is only of use to implementers of custom SNES types.
SEE ALSO:
setUp, SNESSetUpMatrices
Source code at petsc4py/PETSc/SNES.pyx:1677
Return type
None
setUpdate(update, args=None, kargs=None)
Set the callback to compute update at the beginning of each step.
Logically collective.
Parameters
• update (SNESUpdateFunction | None) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getUpdate, SNESSetUpdate
Source code at petsc4py/PETSc/SNES.pyx:873
setUseEW(flag=True, *targs, **kargs)
Tell the solver to use the Eisenstat-Walker trick.
Logically collective.
Parameters
• flag (bool) -- Whether or not to use the Eisenstat-Walker trick.
• *targs (Any) -- Positional arguments for setParamsEW.
• **kargs (Any) -- Keyword arguments for setParamsEW.
Return type
None
SEE ALSO:
getUseEW, setParamsEW, SNESKSPSetUseEW
Source code at petsc4py/PETSc/SNES.pyx:1951
setUseFD(flag=True)
Set the boolean flag to use coloring finite-differencing for Jacobian assembly.
Logically collective.
SEE ALSO:
getUseFD
Source code at petsc4py/PETSc/SNES.pyx:2121
Return type
None
setUseKSP(flag=True)
Set the boolean flag indicating to use a linear solver.
Logically collective.
SEE ALSO:
getUseKSP
Source code at petsc4py/PETSc/SNES.pyx:2065
Return type
None
setUseMF(flag=True)
Set the boolean flag indicating to use matrix-free finite-differencing.
Logically collective.
SEE ALSO:
getUseMF
Source code at petsc4py/PETSc/SNES.pyx:2094
Return type
None
setVariableBounds(xl, xu)
Set the vector for the variable bounds.
Collective.
SEE ALSO:
SNESVISetVariableBounds
Source code at petsc4py/PETSc/SNES.pyx:2150
Parameters
• xl (Vec)
• xu (Vec)
Return type
None
solve(b=None, x=None)
Solve the nonlinear equations.
Collective.
Parameters
• b (Vec | None) -- The affine right-hand side or None to use zero.
• x (Vec | None) -- The starting vector or None to use the vector stored internally.
Return type
None
SEE ALSO:
setSolution, getSolution, SNESSolve
Source code at petsc4py/PETSc/SNES.pyx:1703
view(viewer=None)
View the solver.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
SNESView
Source code at petsc4py/PETSc/SNES.pyx:113
Attributes Documentation
appctx Application context.
Source code at petsc4py/PETSc/SNES.pyx:2405
atol Absolute residual tolerance.
Source code at petsc4py/PETSc/SNES.pyx:2486
dm DM.
Source code at petsc4py/PETSc/SNES.pyx:2415
history
Convergence history.
Source code at petsc4py/PETSc/SNES.pyx:2538
is_converged
Boolean indicating if the solver has converged.
Source code at petsc4py/PETSc/SNES.pyx:2558
is_diverged
Boolean indicating if the solver has failed.
Source code at petsc4py/PETSc/SNES.pyx:2563
is_iterating
Boolean indicating if the solver has not converged yet.
Source code at petsc4py/PETSc/SNES.pyx:2553
its Number of iterations.
Source code at petsc4py/PETSc/SNES.pyx:2522
ksp Linear solver.
Source code at petsc4py/PETSc/SNES.pyx:2452
max_funcs
Maximum number of function evaluations.
Source code at petsc4py/PETSc/SNES.pyx:2512
max_it Maximum number of iterations.
Source code at petsc4py/PETSc/SNES.pyx:2502
norm Function norm.
Source code at petsc4py/PETSc/SNES.pyx:2530
npc Nonlinear preconditioner.
Source code at petsc4py/PETSc/SNES.pyx:2425
reason Converged reason.
Source code at petsc4py/PETSc/SNES.pyx:2545
rtol Relative residual tolerance.
Source code at petsc4py/PETSc/SNES.pyx:2478
stol Solution update tolerance.
Source code at petsc4py/PETSc/SNES.pyx:2494
use_ew Use the Eisenstat-Walker trick.
Source code at petsc4py/PETSc/SNES.pyx:2468
use_fd Boolean indicating if the solver uses coloring finite-differencing.
Source code at petsc4py/PETSc/SNES.pyx:2578
use_ksp
Boolean indicating if the solver uses a linear solver.
Source code at petsc4py/PETSc/SNES.pyx:2460
use_mf Boolean indicating if the solver uses matrix-free finite-differencing.
Source code at petsc4py/PETSc/SNES.pyx:2570
vec_rhs
Right-hand side vector.
Source code at petsc4py/PETSc/SNES.pyx:2445
vec_sol
Solution vector.
Source code at petsc4py/PETSc/SNES.pyx:2435
vec_upd
Update vector.
Source code at petsc4py/PETSc/SNES.pyx:2440
petsc4py.PETSc.Scatter
class petsc4py.PETSc.Scatter
Bases: Object
Scatter object.
The object used to perform data movement between vectors. Scatter is described in the PETSc
manual.
SEE ALSO:
Vec, SF, VecScatter
Enumerations
┌──────┬───────────────┐
│ Mode │ Scatter mode. │
├──────┼───────────────┤
│ Type │ Scatter type. │
└──────┴───────────────┘
petsc4py.PETSc.Scatter.Mode
class petsc4py.PETSc.Scatter.Mode
Bases: object
Scatter mode.
Most commonly used scatter modes are:
FORWARD
Scatter values in the forward direction.
REVERSE
Scatter values in the reverse direction.
SEE ALSO:
Scatter.create, Scatter.begin, Scatter.end, ScatterMode
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ FORWARD │ Constant FORWARD of type int │
├───────────────────────┼───────────────────────────────────────┤
│ FORWARD_LOCAL │ Constant FORWARD_LOCAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ REVERSE │ Constant REVERSE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ REVERSE_LOCAL │ Constant REVERSE_LOCAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_FORWARD │ Constant SCATTER_FORWARD of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_FORWARD_LOCAL │ Constant SCATTER_FORWARD_LOCAL of │
│ │ type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_REVERSE │ Constant SCATTER_REVERSE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_REVERSE_LOCAL │ Constant SCATTER_REVERSE_LOCAL of │
│ │ type int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
FORWARD: int = FORWARD
Constant FORWARD of type int
FORWARD_LOCAL: int = FORWARD_LOCAL
Constant FORWARD_LOCAL of type int
REVERSE: int = REVERSE
Constant REVERSE of type int
REVERSE_LOCAL: int = REVERSE_LOCAL
Constant REVERSE_LOCAL of type int
SCATTER_FORWARD: int = SCATTER_FORWARD
Constant SCATTER_FORWARD of type int
SCATTER_FORWARD_LOCAL: int = SCATTER_FORWARD_LOCAL
Constant SCATTER_FORWARD_LOCAL of type int
SCATTER_REVERSE: int = SCATTER_REVERSE
Constant SCATTER_REVERSE of type int
SCATTER_REVERSE_LOCAL: int = SCATTER_REVERSE_LOCAL
Constant SCATTER_REVERSE_LOCAL of type int
petsc4py.PETSc.Scatter.Type
class petsc4py.PETSc.Scatter.Type
Bases: object
Scatter type.
SEE ALSO:
VecScatterType
Attributes Summary
┌────────────┬───────────────────────────────┐
│ ALLGATHER │ Object ALLGATHER of type str │
├────────────┼───────────────────────────────┤
│ ALLGATHERV │ Object ALLGATHERV of type str │
├────────────┼───────────────────────────────┤
│ ALLTOALL │ Object ALLTOALL of type str │
├────────────┼───────────────────────────────┤
│ BASIC │ Object BASIC of type str │
├────────────┼───────────────────────────────┤
│ GATHER │ Object GATHER of type str │
├────────────┼───────────────────────────────┤
│ GATHERV │ Object GATHERV of type str │
├────────────┼───────────────────────────────┤
│ NEIGHBOR │ Object NEIGHBOR of type str │
├────────────┼───────────────────────────────┤
│ WINDOW │ Object WINDOW of type str │
└────────────┴───────────────────────────────┘
Attributes Documentation
ALLGATHER: str = ALLGATHER
Object ALLGATHER of type str
ALLGATHERV: str = ALLGATHERV
Object ALLGATHERV of type str
ALLTOALL: str = ALLTOALL
Object ALLTOALL of type str
BASIC: str = BASIC
Object BASIC of type str
GATHER: str = GATHER
Object GATHER of type str
GATHERV: str = GATHERV
Object GATHERV of type str
NEIGHBOR: str = NEIGHBOR
Object NEIGHBOR of type str
WINDOW: str = WINDOW
Object WINDOW of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ begin(vec_from, vec_to[, addv, mode]) │ Begin a generalized scatter from one │
│ │ vector into another. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copy() │ Return a copy of the scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create(vec_from, is_from, vec_to, │ Create a scatter object. │
│ is_to) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ end(vec_from, vec_to[, addv, mode]) │ Complete a generalized scatter from │
│ │ one vector into another. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ scatter(vec_from, vec_to[, addv, │ Perform a generalized scatter from │
│ mode]) │ one vector into another. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the scatter from the │
│ │ options database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(scatter_type) │ Set the type of the scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the scatter. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ toAll(vec) │ Create a scatter that communicates a │
│ │ vector to all sharing processes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ toZero(vec) │ Create a scatter that communicates a │
│ │ vector to rank zero. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the scatter. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
begin(vec_from, vec_to, addv=None, mode=None)
Begin a generalized scatter from one vector into another.
Collective.
This call has to be concluded with a call to end. For additional details on the
Parameters, see scatter.
SEE ALSO:
create, end, VecScatterBegin
Source code at petsc4py/PETSc/Scatter.pyx:262
Parameters
• vec_from (Vec)
• vec_to (Vec)
• addv (InsertModeSpec)
• mode (ScatterModeSpec)
Return type
None
copy() Return a copy of the scatter.
Source code at petsc4py/PETSc/Scatter.pyx:199
Return type
Scatter
create(vec_from, is_from, vec_to, is_to)
Create a scatter object.
Collective.
Parameters
• vec_from (Vec) -- Representative vector from which to scatter the data.
• is_from (IS) -- Indices of vec_from to scatter. If None, use all indices.
• vec_to (Vec) -- Representative vector to which scatter the data.
• is_to (IS) -- Indices of vec_to where to receive. If None, use all indices.
Return type
Self
Examples
The scatter object can be used to repeatedly perform data movement. It is the PETSc
equivalent of NumPy-like indexing and slicing, with support for parallel communications:
>>> revmode = PETSc.Scatter.Mode.REVERSE
>>> v1 = PETSc.Vec().createWithArray([1, 2, 3])
>>> v2 = PETSc.Vec().createWithArray([0, 0, 0])
>>> sct = PETSc.Scatter().create(v1,None,v2,None)
>>> sct.scatter(v1,v2) # v2[:] = v1[:]
>>> sct.scatter(v2,v1,mode=revmode) # v1[:] = v2[:]
>>> revmode = PETSc.Scatter.Mode.REVERSE
>>> v1 = PETSc.Vec().createWithArray([1, 2, 3, 4])
>>> v2 = PETSc.Vec().createWithArray([0, 0])
>>> is1 = PETSc.IS().createStride(2, 3, -2)
>>> sct = PETSc.Scatter().create(v1,is1,v2,None)
>>> sct.scatter(v1,v2) # v2[:] = v1[3:0:-2]
>>> sct.scatter(v2,v1,mode=revmode) # v1[3:0:-2] = v2[:]
SEE ALSO:
IS, VecScatterCreate
Source code at petsc4py/PETSc/Scatter.pyx:90
destroy()
Destroy the scatter.
Collective.
SEE ALSO:
VecScatterDestroy
Source code at petsc4py/PETSc/Scatter.pyx:77
Return type
Self
end(vec_from, vec_to, addv=None, mode=None)
Complete a generalized scatter from one vector into another.
Collective.
This call has to be preceded by a call to begin. For additional details on the Parameters,
see scatter.
SEE ALSO:
create, begin, VecScatterEnd
Source code at petsc4py/PETSc/Scatter.pyx:285
Parameters
• vec_from (Vec)
• vec_to (Vec)
• addv (InsertModeSpec)
• mode (ScatterModeSpec)
Return type
None
getType()
Return the type of the scatter.
Not collective.
SEE ALSO:
setType, VecScatterGetType
Source code at petsc4py/PETSc/Scatter.pyx:160
Return type
str
scatter(vec_from, vec_to, addv=None, mode=None)
Perform a generalized scatter from one vector into another.
Collective.
Parameters
• vec_from (Vec) -- The source vector.
• vec_to (Vec) -- The destination vector.
• addv (InsertModeSpec) -- Insertion mode.
• mode (ScatterModeSpec) -- Scatter mode.
Return type
None
SEE ALSO:
create, begin, end, VecScatterBegin, VecScatterEnd
Source code at petsc4py/PETSc/Scatter.pyx:308
setFromOptions()
Configure the scatter from the options database.
Collective.
SEE ALSO:
Working with PETSc options, VecScatterSetFromOptions
Source code at petsc4py/PETSc/Scatter.pyx:174
Return type
None
setType(scatter_type)
Set the type of the scatter.
Logically collective.
SEE ALSO:
getType, VecScatterSetType
Source code at petsc4py/PETSc/Scatter.pyx:146
Parameters
scatter_type (Type | str)
Return type
None
setUp()
Set up the internal data structures for using the scatter.
Collective.
SEE ALSO:
VecScatterSetUp
Source code at petsc4py/PETSc/Scatter.pyx:186
Return type
Self
classmethod toAll(vec)
Create a scatter that communicates a vector to all sharing processes.
Collective.
Parameters
vec (Vec) -- The vector to scatter from.
Return type
tuple[Scatter, Vec]
Notes
The created scatter will have the same communicator of vec. The method also returns an
output vector of appropriate size to contain the result of the operation.
SEE ALSO:
toZero, VecScatterCreateToAll
Source code at petsc4py/PETSc/Scatter.pyx:205
classmethod toZero(vec)
Create a scatter that communicates a vector to rank zero.
Collective.
Parameters
vec (Vec) -- The vector to scatter from.
Return type
tuple[Scatter, Vec]
Notes
The created scatter will have the same communicator of vec. The method also returns an
output vector of appropriate size to contain the result of the operation.
SEE ALSO:
toAll, VecScatterCreateToZero
Source code at petsc4py/PETSc/Scatter.pyx:233
view(viewer=None)
View the scatter.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
VecScatterView
Source code at petsc4py/PETSc/Scatter.pyx:58
petsc4py.PETSc.ScatterMode
class petsc4py.PETSc.ScatterMode
Bases: object
Scatter mode.
Most commonly used scatter modes are:
FORWARD
Scatter values in the forward direction.
REVERSE
Scatter values in the reverse direction.
SEE ALSO:
Scatter.create, Scatter.begin, Scatter.end, ScatterMode
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ FORWARD │ Constant FORWARD of type int │
├───────────────────────┼───────────────────────────────────────┤
│ FORWARD_LOCAL │ Constant FORWARD_LOCAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ REVERSE │ Constant REVERSE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ REVERSE_LOCAL │ Constant REVERSE_LOCAL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_FORWARD │ Constant SCATTER_FORWARD of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_FORWARD_LOCAL │ Constant SCATTER_FORWARD_LOCAL of │
│ │ type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_REVERSE │ Constant SCATTER_REVERSE of type int │
├───────────────────────┼───────────────────────────────────────┤
│ SCATTER_REVERSE_LOCAL │ Constant SCATTER_REVERSE_LOCAL of │
│ │ type int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
FORWARD: int = FORWARD
Constant FORWARD of type int
FORWARD_LOCAL: int = FORWARD_LOCAL
Constant FORWARD_LOCAL of type int
REVERSE: int = REVERSE
Constant REVERSE of type int
REVERSE_LOCAL: int = REVERSE_LOCAL
Constant REVERSE_LOCAL of type int
SCATTER_FORWARD: int = SCATTER_FORWARD
Constant SCATTER_FORWARD of type int
SCATTER_FORWARD_LOCAL: int = SCATTER_FORWARD_LOCAL
Constant SCATTER_FORWARD_LOCAL of type int
SCATTER_REVERSE: int = SCATTER_REVERSE
Constant SCATTER_REVERSE of type int
SCATTER_REVERSE_LOCAL: int = SCATTER_REVERSE_LOCAL
Constant SCATTER_REVERSE_LOCAL of type int
petsc4py.PETSc.Section
class petsc4py.PETSc.Section
Bases: Object
Mapping from integers in a range to unstructured set of integers.
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ addConstraintDof(point, numDof) │ Increment the number of constrained │
│ │ DOFs for a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addDof(point, numDof) │ Add numDof degrees of freedom │
│ │ associated with a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addFieldConstraintDof(point, field, │ Add numDof constrained DOFs for a │
│ numDof) │ given field on a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addFieldDof(point, field, numDof) │ Add numDof DOFs associated with a │
│ │ field on a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clone() │ Return a copy of the section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Allocate a section and set the map │
│ │ contents to the default. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createGlobalSection(sf) │ Create a section describing the │
│ │ global field layout. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy a section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getChart() │ Return the range in which points │
│ │ (indices) lie for this section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConstrainedStorageSize() │ Return the size capable of holding │
│ │ all unconstrained DOFs in a section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConstraintDof(point) │ Return the number of constrained DOFs │
│ │ associated with a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConstraintIndices(point) │ Return the point DOFs numbers which │
│ │ are constrained for a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDof(point) │ Return the number of degrees of │
│ │ freedom for a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldComponents(field) │ Return the number of field components │
│ │ for the given field. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldConstraintDof(point, field) │ Return the number of constrained DOFs │
│ │ for a given field on a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldConstraintIndices(point, │ Return the field DOFs numbers, in [0, │
│ field) │ DOFs), which are constrained. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldDof(point, field) │ Return the number of DOFs associated │
│ │ with a field on a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldName(field) │ Return the name of a field in the │
│ │ section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFieldOffset(point, field) │ Return the offset for the field DOFs │
│ │ on the given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxDof() │ Return the maximum number of DOFs for │
│ │ any point in the section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumFields() │ Return the number of fields in a │
│ │ section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOffset(point) │ Return the offset for the DOFs │
│ │ associated with the given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOffsetRange() │ Return the full range of offsets, │
│ │ [start, end), for a section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPermutation() │ Return the permutation that was set │
│ │ with setPermutation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStorageSize() │ Return the size capable of holding │
│ │ all the DOFs defined in a section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Free all section data. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setChart(pStart, pEnd) │ Set the range in which points │
│ │ (indices) lie for this section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConstraintDof(point, numDof) │ Set the number of constrained DOFs │
│ │ associated with a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConstraintIndices(point, indices) │ Set the point DOFs numbers, in [0, │
│ │ DOFs), which are constrained. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDof(point, numDof) │ Set the number of degrees of freedom │
│ │ associated with a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldComponents(field, numComp) │ Set the number of field components │
│ │ for the given field. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldConstraintDof(point, field, │ Set the number of constrained DOFs │
│ numDof) │ for a given field on a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldConstraintIndices(point, │ Set the field DOFs numbers, in [0, │
│ field, indices) │ DOFs), which are constrained. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldDof(point, field, numDof) │ Set the number of DOFs associated │
│ │ with a field on a given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldName(field, fieldName) │ Set the name of a field in the │
│ │ section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFieldOffset(point, field, offset) │ Set the offset for the DOFs on the │
│ │ given field at a point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNumFields(numFields) │ Set the number of fields in a │
│ │ section. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOffset(point, offset) │ Set the offset for the DOFs │
│ │ associated with the given point. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPermutation(perm) │ Set the permutation for [0, pEnd - │
│ │ pStart). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Calculate offsets. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the section. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
addConstraintDof(point, numDof)
Increment the number of constrained DOFs for a given point.
Not collective.
Parameters
• point (int) -- The point.
• numDof (int) -- The number of additional DOFs which are fixed by constraints.
Return type
None
SEE ALSO:
setConstraintDof, getConstraintDof, PetscSectionAddConstraintDof
Source code at petsc4py/PETSc/Section.pyx:485
addDof(point, numDof)
Add numDof degrees of freedom associated with a given point.
Not collective.
Parameters
• point (int) -- The point.
• numDof (int) -- The number of additional DOFs.
Return type
None
SEE ALSO:
setDof, getDof, PetscSectionAddDof
Source code at petsc4py/PETSc/Section.pyx:354
addFieldConstraintDof(point, field, numDof)
Add numDof constrained DOFs for a given field on a point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
• numDof (int) -- The number of additional DOFs which are fixed by constraints.
Return type
None
SEE ALSO:
setFieldConstraintDof, getFieldConstraintDof, PetscSectionAddFieldConstraintDof
Source code at petsc4py/PETSc/Section.pyx:557
addFieldDof(point, field, numDof)
Add numDof DOFs associated with a field on a given point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
• numDof (int) -- The number of additional DOFs.
Return type
None
SEE ALSO:
setFieldDof, getFieldDof, PetscSectionAddFieldDof
Source code at petsc4py/PETSc/Section.pyx:421
clone()
Return a copy of the section.
Collective.
The copy is shallow, if possible.
SEE ALSO:
PetscSectionClone
Source code at petsc4py/PETSc/Section.pyx:80
Return type
Section
create(comm=None)
Allocate a section and set the map contents to the default.
Collective.
Typical calling sequence: - create - setNumFields - setChart - setDof - setUp - getOffset -
destroy
The Section object and methods are intended to be used in the PETSc Vec and Mat
implementations. The indices returned by the Section are appropriate for the kind of Vec it
is associated with. For example, if the vector being indexed is a local vector, we call the
section a local section. If the section indexes a global vector, we call it a global
section. For parallel vectors, like global vectors, we use negative indices to indicate
DOFs owned by other processes.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscSectionCreate
Source code at petsc4py/PETSc/Section.pyx:42
createGlobalSection(sf)
Create a section describing the global field layout.
Collective.
The section describes the global field layout using the local section and an SF describing
the section point overlap.
If we have a set of local sections defining the layout of a set of local vectors, and also
an SF to determine which section points are shared and the ownership, we can calculate a
global section defining the parallel data layout, and the associated global vector.
This gives negative sizes and offsets to points not owned by this process.
includeConstraints and localOffsets parameters of the C API are always set to False.
Parameters
sf (SF) -- The SF describing the parallel layout of the section points (leaves are
unowned local points).
Return type
Section
SEE ALSO:
PetscSectionCreateGlobalSection
Source code at petsc4py/PETSc/Section.pyx:846
destroy()
Destroy a section.
Not collective.
SEE ALSO:
PetscSectionDestroy
Source code at petsc4py/PETSc/Section.pyx:29
Return type
Self
getChart()
Return the range in which points (indices) lie for this section.
Not collective.
The range is [pStart, pEnd), i.e., from the first point to one past the last point.
SEE ALSO:
PetscSectionGetChart
Source code at petsc4py/PETSc/Section.pyx:238
Return type
tuple[int, int]
getConstrainedStorageSize()
Return the size capable of holding all unconstrained DOFs in a section.
Not collective.
SEE ALSO:
getStorageSize, PetscSectionGetConstrainedStorageSize
Source code at petsc4py/PETSc/Section.pyx:720
Return type
int
getConstraintDof(point)
Return the number of constrained DOFs associated with a given point.
Not collective.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
setConstraintDof, PetscSectionGetConstraintDof
Source code at petsc4py/PETSc/Section.pyx:445
getConstraintIndices(point)
Return the point DOFs numbers which are constrained for a given point.
Not collective.
The range is in [0, DOFs).
Parameters
point (int) -- The point.
Return type
ArrayInt
SEE ALSO:
setConstraintIndices, PetscSectionGetConstraintIndices
Source code at petsc4py/PETSc/Section.pyx:586
getDof(point)
Return the number of degrees of freedom for a given point.
Not collective.
In a global section, this value will be negative for points not owned by this process.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
setDof, addDof, PetscSectionGetDof
Source code at petsc4py/PETSc/Section.pyx:311
getFieldComponents(field)
Return the number of field components for the given field.
Not collective.
Parameters
field (int) -- The field number.
Return type
int
SEE ALSO:
setFieldComponents, PetscSectionGetFieldComponents
Source code at petsc4py/PETSc/Section.pyx:198
getFieldConstraintDof(point, field)
Return the number of constrained DOFs for a given field on a point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
Return type
int
SEE ALSO:
setFieldConstraintDof, PetscSectionGetFieldConstraintDof
Source code at petsc4py/PETSc/Section.pyx:506
getFieldConstraintIndices(point, field)
Return the field DOFs numbers, in [0, DOFs), which are constrained.
Not collective.
The constrained DOFs are sorted in ascending order.
Parameters
• field (int) -- The field number.
• point (int) -- The point.
Return type
ArrayInt
SEE ALSO:
setFieldConstraintIndices, PetscSectionGetFieldConstraintIndices
Source code at petsc4py/PETSc/Section.pyx:634
getFieldDof(point, field)
Return the number of DOFs associated with a field on a given point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
Return type
int
SEE ALSO:
setFieldDof, PetscSectionGetFieldDof
Source code at petsc4py/PETSc/Section.pyx:375
getFieldName(field)
Return the name of a field in the section.
Not collective.
Parameters
field (int) -- The field number.
Return type
str
SEE ALSO:
setFieldName, PetscSectionGetFieldName
Source code at petsc4py/PETSc/Section.pyx:156
getFieldOffset(point, field)
Return the offset for the field DOFs on the given point.
Not collective.
In a global section, this offset will be negative for points not owned by this process.
Parameters
• point (int) -- The point.
• field (int) -- The field.
Return type
int
SEE ALSO:
setFieldOffset, PetscSectionGetFieldOffset
Source code at petsc4py/PETSc/Section.pyx:779
getMaxDof()
Return the maximum number of DOFs for any point in the section.
Not collective.
SEE ALSO:
PetscSectionGetMaxDof
Source code at petsc4py/PETSc/Section.pyx:692
Return type
int
getNumFields()
Return the number of fields in a section.
Not collective.
Returns 0 if no fields were defined.
SEE ALSO:
setNumFields, PetscSectionGetNumFields
Source code at petsc4py/PETSc/Section.pyx:122
Return type
int
getOffset(point)
Return the offset for the DOFs associated with the given point.
Not collective.
In a global section, this offset will be negative for points not owned by this process.
Parameters
point (int) -- The point.
Return type
int
SEE ALSO:
setOffset, PetscSectionGetOffset
Source code at petsc4py/PETSc/Section.pyx:734
getOffsetRange()
Return the full range of offsets, [start, end), for a section.
Not collective.
SEE ALSO:
PetscSectionGetOffsetRange
Source code at petsc4py/PETSc/Section.pyx:831
Return type
tuple[int, int]
getPermutation()
Return the permutation that was set with setPermutation.
Not collective.
SEE ALSO:
setPermutation, PetscSectionGetPermutation
Source code at petsc4py/PETSc/Section.pyx:279
Return type
IS
getStorageSize()
Return the size capable of holding all the DOFs defined in a section.
Not collective.
SEE ALSO:
getConstrainedStorageSize, PetscSectionGetStorageSize
Source code at petsc4py/PETSc/Section.pyx:706
Return type
int
reset()
Free all section data.
Not collective.
SEE ALSO:
PetscSectionReset
Source code at petsc4py/PETSc/Section.pyx:110
Return type
None
setChart(pStart, pEnd)
Set the range in which points (indices) lie for this section.
Not collective.
The range is [pStart, pEnd), i.e., from the first point to one past the last point.
Parameters
• pStart (int) -- The first point.
• pEnd (int) -- One past the last point.
Return type
None
SEE ALSO:
PetscSectionSetChart
Source code at petsc4py/PETSc/Section.pyx:255
setConstraintDof(point, numDof)
Set the number of constrained DOFs associated with a given point.
Not collective.
Parameters
• point (int) -- The point.
• numDof (int) -- The number of DOFs which are fixed by constraints.
Return type
None
SEE ALSO:
getConstraintDof, addConstraintDof, PetscSectionSetConstraintDof
Source code at petsc4py/PETSc/Section.pyx:464
setConstraintIndices(point, indices)
Set the point DOFs numbers, in [0, DOFs), which are constrained.
Not collective.
Parameters
• point (int) -- The point.
• indices (Sequence[int]) -- The constrained DOFs.
Return type
None
SEE ALSO:
getConstraintIndices, PetscSectionSetConstraintIndices
Source code at petsc4py/PETSc/Section.pyx:610
setDof(point, numDof)
Set the number of degrees of freedom associated with a given point.
Not collective.
Parameters
• point (int) -- The point.
• numDof (int) -- The number of DOFs.
Return type
None
SEE ALSO:
getDof, addDof, PetscSectionSetDof
Source code at petsc4py/PETSc/Section.pyx:333
setFieldComponents(field, numComp)
Set the number of field components for the given field.
Not collective.
Parameters
• field (int) -- The field number.
• numComp (int) -- The number of field components.
Return type
None
SEE ALSO:
getFieldComponents, PetscSectionSetFieldComponents
Source code at petsc4py/PETSc/Section.pyx:217
setFieldConstraintDof(point, field, numDof)
Set the number of constrained DOFs for a given field on a point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
• numDof (int) -- The number of DOFs which are fixed by constraints.
Return type
None
SEE ALSO:
getFieldConstraintDof, addFieldConstraintDof, PetscSectionSetFieldConstraintDof
Source code at petsc4py/PETSc/Section.pyx:528
setFieldConstraintIndices(point, field, indices)
Set the field DOFs numbers, in [0, DOFs), which are constrained.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field number.
• indices (Sequence[int]) -- The constrained DOFs.
Return type
None
SEE ALSO:
getFieldConstraintIndices, PetscSectionSetFieldConstraintIndices
Source code at petsc4py/PETSc/Section.pyx:661
setFieldDof(point, field, numDof)
Set the number of DOFs associated with a field on a given point.
Not collective.
Parameters
• point (int) -- The point.
• field (int) -- The field.
• numDof (int) -- The number of DOFs.
Return type
None
SEE ALSO:
getFieldDof, addFieldDof, PetscSectionSetFieldDof
Source code at petsc4py/PETSc/Section.pyx:397
setFieldName(field, fieldName)
Set the name of a field in the section.
Not collective.
Parameters
• field (int) -- The field number.
• fieldName (str) -- The field name.
Return type
None
SEE ALSO:
getFieldName, PetscSectionSetFieldName
Source code at petsc4py/PETSc/Section.pyx:176
setFieldOffset(point, field, offset)
Set the offset for the DOFs on the given field at a point.
Not collective.
The user usually does not call this function, but uses setUp.
Parameters
• point (int) -- The point.
• field (int) -- The field.
• offset (int) -- The offset.
Return type
None
SEE ALSO:
getFieldOffset, PetscSectionSetFieldOffset
Source code at petsc4py/PETSc/Section.pyx:805
setNumFields(numFields)
Set the number of fields in a section.
Not collective.
Parameters
numFields (int) -- The number of fields.
Return type
None
SEE ALSO:
getNumFields, PetscSectionSetNumFields
Source code at petsc4py/PETSc/Section.pyx:138
setOffset(point, offset)
Set the offset for the DOFs associated with the given point.
Not collective.
The user usually does not call this function, but uses setUp.
Parameters
• point (int) -- The point.
• offset (int) -- The offset.
Return type
None
SEE ALSO:
getOffset, PetscSectionSetOffset
Source code at petsc4py/PETSc/Section.pyx:756
setPermutation(perm)
Set the permutation for [0, pEnd - pStart).
Not collective.
Parameters
perm (IS) -- The permutation of points.
Return type
None
SEE ALSO:
getPermutation, PetscSectionSetPermutation
Source code at petsc4py/PETSc/Section.pyx:294
setUp()
Calculate offsets.
Not collective.
Offsets are based on the number of degrees of freedom for each point.
SEE ALSO:
PetscSectionSetUp
Source code at petsc4py/PETSc/Section.pyx:96
Return type
None
view(viewer=None)
View the section.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the section.
Return type
None
SEE ALSO:
PetscSectionView
Source code at petsc4py/PETSc/Section.pyx:10
petsc4py.PETSc.Space
class petsc4py.PETSc.Space
Bases: Object
Function space object.
Enumerations
┌──────┬───────────────────────────┐
│ Type │ The function space types. │
└──────┴───────────────────────────┘
petsc4py.PETSc.Space.Type
class petsc4py.PETSc.Space.Type
Bases: object
The function space types.
Attributes Summary
┌────────────┬───────────────────────────────┐
│ POINT │ Object POINT of type str │
├────────────┼───────────────────────────────┤
│ POLYNOMIAL │ Object POLYNOMIAL of type str │
├────────────┼───────────────────────────────┤
│ PTRIMMED │ Object PTRIMMED of type str │
├────────────┼───────────────────────────────┤
│ SUBSPACE │ Object SUBSPACE of type str │
├────────────┼───────────────────────────────┤
│ SUM │ Object SUM of type str │
├────────────┼───────────────────────────────┤
│ TENSOR │ Object TENSOR of type str │
├────────────┼───────────────────────────────┤
│ WXY │ Object WXY of type str │
└────────────┴───────────────────────────────┘
Attributes Documentation
POINT: str = POINT
Object POINT of type str
POLYNOMIAL: str = POLYNOMIAL
Object POLYNOMIAL of type str
PTRIMMED: str = PTRIMMED
Object PTRIMMED of type str
SUBSPACE: str = SUBSPACE
Object SUBSPACE of type str
SUM: str = SUM
Object SUM of type str
TENSOR: str = TENSOR
Object TENSOR of type str
WXY: str = WXY
Object WXY of type str
Methods Summary
┌──────────────────────────────────────┬───────────────────────────────────────┐
│ create([comm]) │ Create an empty Space object. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the Space object. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getDegree() │ Return the polynomial degrees that │
│ │ characterize this space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getDimension() │ Return the number of basis vectors. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getNumComponents() │ Return the number of components for │
│ │ this space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getNumVariables() │ Return the number of variables for │
│ │ this space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getPTrimmedFormDegree() │ Return the form degree of the trimmed │
│ │ polynomials. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getPointPoints() │ Return the evaluation points for the │
│ │ space as the points of a quad. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getPolynomialTensor() │ Return whether a function space is a │
│ │ space of tensor polynomials. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getSumConcatenate() │ Return the concatenate flag for this │
│ │ space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getSumNumSubspaces() │ Return the number of spaces in the │
│ │ sum. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getSumSubspace(s) │ Return a space in the sum. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getTensorNumSubspaces() │ Return the number of spaces in the │
│ │ tensor product. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getTensorSubspace(s) │ Return a space in the tensor product. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the space object. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setDegree(degree, maxDegree) │ Set the degree of approximation for │
│ │ this space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set parameters in Space from the │
│ │ options database. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setNumComponents(nc) │ Set the number of components for this │
│ │ space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setNumVariables(n) │ Set the number of variables for this │
│ │ space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setPTrimmedFormDegree(formDegree) │ Set the form degree of the trimmed │
│ │ polynomials. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setPointPoints(quad) │ Set the evaluation points for the │
│ │ space to be based on a quad. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setPolynomialTensor(tensor) │ Set whether a function space is a │
│ │ space of tensor polynomials. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setSumConcatenate(concatenate) │ Set the concatenate flag for this │
│ │ space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setSumNumSubspaces(numSumSpaces) │ Set the number of spaces in the sum. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setSumSubspace(s, subsp) │ Set a space in the sum. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setTensorNumSubspaces(numTensSpaces) │ Set the number of spaces in the │
│ │ tensor product. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setTensorSubspace(s, subsp) │ Set a space in the tensor product. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setType(space_type) │ Build a particular type of space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Construct data structures for the │
│ │ Space. │
├──────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View a Space. │
└──────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(comm=None)
Create an empty Space object.
Collective.
The type can then be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PetscSpaceCreate
Source code at petsc4py/PETSc/Space.pyx:36
destroy()
Destroy the Space object.
Collective.
SEE ALSO:
PetscSpaceDestroy
Source code at petsc4py/PETSc/Space.pyx:59
Return type
Self
getDegree()
Return the polynomial degrees that characterize this space.
Not collective.
Returns
• minDegree (int) -- The degree of the largest polynomial space contained in the
space.
• maxDegree (int) -- The degree of the smallest polynomial space containing the
space.
Return type
tuple[int, int]
SEE ALSO:
setDegree, PetscSpaceGetDegree
Source code at petsc4py/PETSc/Space.pyx:117
getDimension()
Return the number of basis vectors.
Not collective.
SEE ALSO:
PetscSpaceGetDimension
Source code at petsc4py/PETSc/Space.pyx:103
Return type
int
getNumComponents()
Return the number of components for this space.
Not collective.
SEE ALSO:
setNumComponents, PetscSpaceGetNumComponents
Source code at petsc4py/PETSc/Space.pyx:195
Return type
int
getNumVariables()
Return the number of variables for this space.
Not collective.
SEE ALSO:
setNumVariables, PetscSpaceGetNumVariables
Source code at petsc4py/PETSc/Space.pyx:163
Return type
int
getPTrimmedFormDegree()
Return the form degree of the trimmed polynomials.
Not collective.
SEE ALSO:
setPTrimmedFormDegree, PetscSpacePTrimmedGetFormDegree
Source code at petsc4py/PETSc/Space.pyx:546
Return type
int
getPointPoints()
Return the evaluation points for the space as the points of a quad.
Logically collective.
SEE ALSO:
setPointPoints, PetscSpacePointGetPoints
Source code at petsc4py/PETSc/Space.pyx:513
Return type
Quad
getPolynomialTensor()
Return whether a function space is a space of tensor polynomials.
Not collective.
Return True if a function space is a space of tensor polynomials (the space is spanned by
polynomials whose degree in each variable is bounded by the given order), as opposed to
polynomials (the space is spanned by polynomials whose total degree—summing over all
variables is bounded by the given order).
SEE ALSO:
setPolynomialTensor, PetscSpacePolynomialGetTensor
Source code at petsc4py/PETSc/Space.pyx:448
Return type
bool
getSumConcatenate()
Return the concatenate flag for this space.
Not collective.
A concatenated sum space will have the number of components equal to the sum of the number
of components of all subspaces. A non-concatenated, or direct sum space will have the same
number of components as its subspaces.
SEE ALSO:
setSumConcatenate, PetscSpaceSumGetConcatenate
Source code at petsc4py/PETSc/Space.pyx:261
Return type
bool
getSumNumSubspaces()
Return the number of spaces in the sum.
Not collective.
SEE ALSO:
setSumNumSubspaces, PetscSpaceSumGetNumSubspaces
Source code at petsc4py/PETSc/Space.pyx:304
Return type
int
getSumSubspace(s)
Return a space in the sum.
Not collective.
Parameters
s (int) -- The space number.
Return type
Space
SEE ALSO:
setSumSubspace, PetscSpaceSumGetSubspace
Source code at petsc4py/PETSc/Space.pyx:318
getTensorNumSubspaces()
Return the number of spaces in the tensor product.
Not collective.
SEE ALSO:
setTensorNumSubspaces, PetscSpaceTensorGetNumSubspaces
Source code at petsc4py/PETSc/Space.pyx:376
Return type
int
getTensorSubspace(s)
Return a space in the tensor product.
Not collective.
Parameters
s (int) -- The space number.
Return type
Space
SEE ALSO:
setTensorSubspace, PetscSpaceTensorGetSubspace
Source code at petsc4py/PETSc/Space.pyx:410
getType()
Return the type of the space object.
Not collective.
SEE ALSO:
setType, PetscSpaceGetType
Source code at petsc4py/PETSc/Space.pyx:227
Return type
str
setDegree(degree, maxDegree)
Set the degree of approximation for this space.
Logically collective.
One of degree and maxDegree can be None.
Parameters
• degree (int | None) -- The degree of the largest polynomial space contained in the
space.
• maxDegree (int | None) -- The degree of the largest polynomial space containing
the space.
Return type
None
SEE ALSO:
getDegree, PetscSpaceSetDegree
Source code at petsc4py/PETSc/Space.pyx:138
setFromOptions()
Set parameters in Space from the options database.
Collective.
SEE ALSO:
Working with PETSc options, PetscSpaceSetFromOptions
Source code at petsc4py/PETSc/Space.pyx:91
Return type
None
setNumComponents(nc)
Set the number of components for this space.
Logically collective.
Parameters
nc (int) -- The number of components.
Return type
None
SEE ALSO:
getNumComponents, PetscSpaceSetNumComponents
Source code at petsc4py/PETSc/Space.pyx:209
setNumVariables(n)
Set the number of variables for this space.
Logically collective.
Parameters
n (int) -- The number of variables (x, y, z etc.).
Return type
None
SEE ALSO:
getNumVariables, PetscSpaceSetNumVariables
Source code at petsc4py/PETSc/Space.pyx:177
setPTrimmedFormDegree(formDegree)
Set the form degree of the trimmed polynomials.
Logically collective.
Parameters
formDegree (int) -- The form degree.
Return type
None
SEE ALSO:
getPTrimmedFormDegree, PetscSpacePTrimmedSetFormDegree
Source code at petsc4py/PETSc/Space.pyx:528
setPointPoints(quad)
Set the evaluation points for the space to be based on a quad.
Logically collective.
Sets the evaluation points for the space to coincide with the points of a quadrature rule.
Parameters
quad (Quad) -- The Quad defining the points.
Return type
None
SEE ALSO:
getPointPoints, PetscSpacePointSetPoints
Source code at petsc4py/PETSc/Space.pyx:493
setPolynomialTensor(tensor)
Set whether a function space is a space of tensor polynomials.
Logically collective.
Set to True for a function space which is a space of tensor polynomials (the space is
spanned by polynomials whose degree in each variable is bounded by the given order), as
opposed to polynomials (the space is spanned by polynomials whose total degree—summing over
all variables is bounded by the given order).
Parameters
tensor (bool) -- True for a tensor polynomial space, False for a polynomial space.
Return type
None
SEE ALSO:
getPolynomialTensor, PetscSpacePolynomialSetTensor
Source code at petsc4py/PETSc/Space.pyx:468
setSumConcatenate(concatenate)
Set the concatenate flag for this space.
Logically collective.
A concatenated sum space will have the number of components equal to the sum of the number
of components of all subspaces. A non-concatenated, or direct sum space will have the same
number of components as its subspaces.
Parameters
concatenate (bool) -- True if subspaces are concatenated components, False if direct
summands.
Return type
None
SEE ALSO:
getSumConcatenate, PetscSpaceSumSetConcatenate
Source code at petsc4py/PETSc/Space.pyx:280
setSumNumSubspaces(numSumSpaces)
Set the number of spaces in the sum.
Logically collective.
Parameters
numSumSpaces (int) -- The number of spaces.
Return type
None
SEE ALSO:
getSumNumSubspaces, PetscSpaceSumSetNumSubspaces
Source code at petsc4py/PETSc/Space.pyx:358
setSumSubspace(s, subsp)
Set a space in the sum.
Logically collective.
Parameters
• s (int) -- The space number.
• subsp (Space) -- The number of spaces.
Return type
None
SEE ALSO:
getSumSubspace, PetscSpaceSumSetSubspace
Source code at petsc4py/PETSc/Space.pyx:338
setTensorNumSubspaces(numTensSpaces)
Set the number of spaces in the tensor product.
Logically collective.
Parameters
numTensSpaces (int) -- The number of spaces.
Return type
None
SEE ALSO:
getTensorNumSubspaces, PetscSpaceTensorSetNumSubspaces
Source code at petsc4py/PETSc/Space.pyx:430
setTensorSubspace(s, subsp)
Set a space in the tensor product.
Logically collective.
Parameters
• s (int) -- The space number.
• subsp (Space) -- The number of spaces.
Return type
None
SEE ALSO:
getTensorSubspace, PetscSpaceTensorSetSubspace
Source code at petsc4py/PETSc/Space.pyx:390
setType(space_type)
Build a particular type of space.
Collective.
Parameters
space_type (Type | str) -- The kind of space.
Return type
Self
SEE ALSO:
getType, PetscSpaceSetType
Source code at petsc4py/PETSc/Space.pyx:241
setUp()
Construct data structures for the Space.
Collective.
SEE ALSO:
PetscSpaceSetUp
Source code at petsc4py/PETSc/Space.pyx:24
Return type
None
view(viewer=None)
View a Space.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer to display the Space.
Return type
None
SEE ALSO:
PetscSpaceView
Source code at petsc4py/PETSc/Space.pyx:72
petsc4py.PETSc.Sys
class petsc4py.PETSc.Sys
Bases: object
System utilities.
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ Print(*args[, sep, end, comm]) │ Print output from the first processor │
│ │ of a communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDefaultComm() │ Get the default MPI communicator used │
│ │ to create PETSc objects. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVersion([devel, date, author]) │ Return PETSc version information. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getVersionInfo() │ Return PETSc version information. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ hasExternalPackage(package) │ Return whether PETSc has support for │
│ │ external package. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ infoAllow(flag[, filename, mode]) │ Enables or disables PETSc info │
│ │ messages. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isFinalized() │ Return whether PETSc has been │
│ │ finalized. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isInitialized() │ Return whether PETSc has been │
│ │ initialized. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ popErrorHandler() │ Remove the current error handler. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ popSignalHandler() │ Remove the current signal handler. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pushErrorHandler(errhandler) │ Set the current error handler. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ registerCitation(citation) │ Register BibTeX citation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDefaultComm(comm) │ Set the default MPI communicator used │
│ │ to create PETSc objects. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ sleep([seconds]) │ Sleep some number of seconds. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ splitOwnership(size[, bsize, comm]) │ Given a global (or local) size │
│ │ determines a local (or global) size. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ syncFlush([comm]) │ Flush output from previous syncPrint │
│ │ calls. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ syncPrint(*args[, sep, end, flush, │ Print synchronized output from │
│ comm]) │ several processors of a communicator. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
classmethod Print(*args, sep=' ', end='\n', comm=None, **kwargs)
Print output from the first processor of a communicator.
Collective.
Parameters
• *args (Any) -- Positional arguments.
• sep (str) -- String inserted between values, by default a space.
• end (str) -- String appended after the last value, by default a newline.
• comm (Comm | None) -- MPI communicator, defaults to getDefaultComm.
• **kwargs (Any) -- Keyword arguments.
Return type
None
SEE ALSO:
PetscPrintf
Source code at petsc4py/PETSc/Sys.pyx:155
classmethod getDefaultComm()
Get the default MPI communicator used to create PETSc objects.
Not collective.
SEE ALSO:
setDefaultComm
Source code at petsc4py/PETSc/Sys.pyx:116
Return type
Comm
classmethod getVersion(devel=False, date=False, author=False)
Return PETSc version information.
Not collective.
Parameters
• devel (bool) -- Additionally, return whether using an in-development version.
• date (bool) -- Additionally, return date information.
• author (bool) -- Additionally, return author information.
Returns
• major (int) -- Major version number.
• minor (int) -- Minor version number.
• micro (int) -- Micro (or patch) version number.
Return type
tuple[int, int, int]
SEE ALSO:
PetscGetVersion, PetscGetVersionNumber
Source code at petsc4py/PETSc/Sys.pyx:7
classmethod getVersionInfo()
Return PETSc version information.
Not collective.
Returns
info -- Dictionary with version information.
Return type
dict
SEE ALSO:
PetscGetVersion, PetscGetVersionNumber
Source code at petsc4py/PETSc/Sys.pyx:62
classmethod hasExternalPackage(package)
Return whether PETSc has support for external package.
Not collective.
Parameters
package (str) -- The external package name.
Return type
bool
SEE ALSO:
PetscHasExternalPackage
Source code at petsc4py/PETSc/Sys.pyx:449
classmethod infoAllow(flag, filename=None, mode='w')
Enables or disables PETSc info messages.
Not collective.
Parameters
• flag (bool) -- Whether to enable info messages.
• filename (str | None) -- Name of a file where to dump output.
• mode (str) -- Write mode for file, by default "w".
Return type
None
SEE ALSO:
PetscInfoAllow, PetscInfoSetFile
Source code at petsc4py/PETSc/Sys.pyx:392
classmethod isFinalized()
Return whether PETSc has been finalized.
Not collective.
SEE ALSO:
isInitialized
Source code at petsc4py/PETSc/Sys.pyx:101
Return type
bool
classmethod isInitialized()
Return whether PETSc has been initialized.
Not collective.
SEE ALSO:
isFinalized
Source code at petsc4py/PETSc/Sys.pyx:88
Return type
bool
classmethod popErrorHandler()
Remove the current error handler.
Logically collective.
SEE ALSO:
PetscPopErrorHandler
Source code at petsc4py/PETSc/Sys.pyx:366
Return type
None
classmethod popSignalHandler()
Remove the current signal handler.
Logically collective.
SEE ALSO:
PetscPopSignalHandler
Source code at petsc4py/PETSc/Sys.pyx:379
Return type
None
classmethod pushErrorHandler(errhandler)
Set the current error handler.
Logically collective.
Parameters
errhandler (str) -- The name of the error handler.
Return type
None
SEE ALSO:
PetscPushErrorHandler
Source code at petsc4py/PETSc/Sys.pyx:331
classmethod registerCitation(citation)
Register BibTeX citation.
Not collective.
Parameters
citation (str) -- The BibTex citation entry to register.
Return type
None
SEE ALSO:
PetscCitationsRegister
Source code at petsc4py/PETSc/Sys.pyx:426
classmethod setDefaultComm(comm)
Set the default MPI communicator used to create PETSc objects.
Logically collective.
Parameters
comm (Comm | None) -- MPI communicator. If set to None, uses COMM_WORLD.
Return type
None
SEE ALSO:
getDefaultComm
Source code at petsc4py/PETSc/Sys.pyx:131
classmethod sleep(seconds=1.0)
Sleep some number of seconds.
Not collective.
Parameters
seconds (float) -- Time to sleep in seconds.
Return type
None
SEE ALSO:
PetscSleep
Source code at petsc4py/PETSc/Sys.pyx:310
classmethod splitOwnership(size, bsize=None, comm=None)
Given a global (or local) size determines a local (or global) size.
Collective.
Parameters
• size (int | tuple[int, int]) -- Global size N or 2-tuple (n, N) with local and
global sizes. Either of n or N (but not both) can be None.
• bsize (int | None) -- Block size, defaults to 1.
• comm (Comm | None) -- MPI communicator, defaults to getDefaultComm.
Returns
• n (int) -- The local size.
• N (int) -- The global size.
Return type
tuple[int, int]
Notes
The size argument corresponds to the full size of the vector. That is, an array with 10
blocks and a block size of 3 will have a size of 30, not 10.
SEE ALSO:
PetscSplitOwnership
Source code at petsc4py/PETSc/Sys.pyx:261
classmethod syncFlush(comm=None)
Flush output from previous syncPrint calls.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to getDefaultComm.
Return type
None
SEE ALSO:
PetscSynchronizedPrintf, PetscSynchronizedFlush
Source code at petsc4py/PETSc/Sys.pyx:240
classmethod syncPrint(*args, sep=' ', end='\n', flush=False, comm=None, **kwargs)
Print synchronized output from several processors of a communicator.
Not collective.
Parameters
• *args (Any) -- Positional arguments.
• sep (str) -- String inserted between values, by default a space.
• end (str) -- String appended after the last value, by default a newline.
• flush (bool) -- Whether to flush output with syncFlush.
• comm (Comm | None) -- MPI communicator, defaults to getDefaultComm.
• **kwargs (Any) -- Keyword arguments.
Return type
None
SEE ALSO:
PetscSynchronizedPrintf, PetscSynchronizedFlush
Source code at petsc4py/PETSc/Sys.pyx:197
petsc4py.PETSc.TAO
class petsc4py.PETSc.TAO
Bases: Object
Optimization solver.
TAO is described in the PETSc manual.
SEE ALSO:
Tao
Enumerations
┌─────────────────┬───────────────────────────────────────┐
│ BNCGType │ TAO Bound Constrained Conjugate │
│ │ Gradient (BNCG) Update Type. │
├─────────────────┼───────────────────────────────────────┤
│ ConvergedReason │ TAO solver termination reason. │
├─────────────────┼───────────────────────────────────────┤
│ Type │ TAO solver type. │
└─────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.TAO.BNCGType
class petsc4py.PETSc.TAO.BNCGType
Bases: object
TAO Bound Constrained Conjugate Gradient (BNCG) Update Type.
Attributes Summary
┌───────────┬────────────────────────────────┐
│ DK │ Constant DK of type int │
├───────────┼────────────────────────────────┤
│ DY │ Constant DY of type int │
├───────────┼────────────────────────────────┤
│ FR │ Constant FR of type int │
├───────────┼────────────────────────────────┤
│ GD │ Constant GD of type int │
├───────────┼────────────────────────────────┤
│ HS │ Constant HS of type int │
├───────────┼────────────────────────────────┤
│ HZ │ Constant HZ of type int │
├───────────┼────────────────────────────────┤
│ KD │ Constant KD of type int │
├───────────┼────────────────────────────────┤
│ PCGD │ Constant PCGD of type int │
├───────────┼────────────────────────────────┤
│ PRP │ Constant PRP of type int │
├───────────┼────────────────────────────────┤
│ PRP_PLUS │ Constant PRP_PLUS of type int │
├───────────┼────────────────────────────────┤
│ SSML_BFGS │ Constant SSML_BFGS of type int │
├───────────┼────────────────────────────────┤
│ SSML_BRDN │ Constant SSML_BRDN of type int │
├───────────┼────────────────────────────────┤
│ SSML_DFP │ Constant SSML_DFP of type int │
└───────────┴────────────────────────────────┘
Attributes Documentation
DK: int = DK
Constant DK of type int
DY: int = DY
Constant DY of type int
FR: int = FR
Constant FR of type int
GD: int = GD
Constant GD of type int
HS: int = HS
Constant HS of type int
HZ: int = HZ
Constant HZ of type int
KD: int = KD
Constant KD of type int
PCGD: int = PCGD
Constant PCGD of type int
PRP: int = PRP
Constant PRP of type int
PRP_PLUS: int = PRP_PLUS
Constant PRP_PLUS of type int
SSML_BFGS: int = SSML_BFGS
Constant SSML_BFGS of type int
SSML_BRDN: int = SSML_BRDN
Constant SSML_BRDN of type int
SSML_DFP: int = SSML_DFP
Constant SSML_DFP of type int
petsc4py.PETSc.TAO.ConvergedReason
class petsc4py.PETSc.TAO.ConvergedReason
Bases: object
TAO solver termination reason.
SEE ALSO:
TaoConvergedReason
Attributes Summary
┌───────────────────────┬───────────────────────────────────────┐
│ CONTINUE_ITERATING │ Constant CONTINUE_ITERATING of type ‐ │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_GATOL │ Constant CONVERGED_GATOL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_GRTOL │ Constant CONVERGED_GRTOL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_GTTOL │ Constant CONVERGED_GTTOL of type int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITERATING │ Constant CONVERGED_ITERATING of type │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_MINF │ Constant CONVERGED_MINF of type int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_STEPTOL │ Constant CONVERGED_STEPTOL of type ‐ │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ CONVERGED_USER │ Constant CONVERGED_USER of type int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_LS_FAILURE │ Constant DIVERGED_LS_FAILURE of type │
│ │ int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_MAXFCN │ Constant DIVERGED_MAXFCN of type int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_MAXITS │ Constant DIVERGED_MAXITS of type int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_NAN │ Constant DIVERGED_NAN of type int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_TR_REDUCTION │ Constant DIVERGED_TR_REDUCTION of │
│ │ type int │
├───────────────────────┼───────────────────────────────────────┤
│ DIVERGED_USER │ Constant DIVERGED_USER of type int │
├───────────────────────┼───────────────────────────────────────┤
│ ITERATING │ Constant ITERATING of type int │
└───────────────────────┴───────────────────────────────────────┘
Attributes Documentation
CONTINUE_ITERATING: int = CONTINUE_ITERATING
Constant CONTINUE_ITERATING of type int
CONVERGED_GATOL: int = CONVERGED_GATOL
Constant CONVERGED_GATOL of type int
CONVERGED_GRTOL: int = CONVERGED_GRTOL
Constant CONVERGED_GRTOL of type int
CONVERGED_GTTOL: int = CONVERGED_GTTOL
Constant CONVERGED_GTTOL of type int
CONVERGED_ITERATING: int = CONVERGED_ITERATING
Constant CONVERGED_ITERATING of type int
CONVERGED_MINF: int = CONVERGED_MINF
Constant CONVERGED_MINF of type int
CONVERGED_STEPTOL: int = CONVERGED_STEPTOL
Constant CONVERGED_STEPTOL of type int
CONVERGED_USER: int = CONVERGED_USER
Constant CONVERGED_USER of type int
DIVERGED_LS_FAILURE: int = DIVERGED_LS_FAILURE
Constant DIVERGED_LS_FAILURE of type int
DIVERGED_MAXFCN: int = DIVERGED_MAXFCN
Constant DIVERGED_MAXFCN of type int
DIVERGED_MAXITS: int = DIVERGED_MAXITS
Constant DIVERGED_MAXITS of type int
DIVERGED_NAN: int = DIVERGED_NAN
Constant DIVERGED_NAN of type int
DIVERGED_TR_REDUCTION: int = DIVERGED_TR_REDUCTION
Constant DIVERGED_TR_REDUCTION of type int
DIVERGED_USER: int = DIVERGED_USER
Constant DIVERGED_USER of type int
ITERATING: int = ITERATING
Constant ITERATING of type int
petsc4py.PETSc.TAO.Type
class petsc4py.PETSc.TAO.Type
Bases: object
TAO solver type.
SEE ALSO:
TaoType
Attributes Summary
┌──────────┬─────────────────────────────┐
│ ADMM │ Object ADMM of type str │
├──────────┼─────────────────────────────┤
│ ALMM │ Object ALMM of type str │
├──────────┼─────────────────────────────┤
│ ASFLS │ Object ASFLS of type str │
├──────────┼─────────────────────────────┤
│ ASILS │ Object ASILS of type str │
├──────────┼─────────────────────────────┤
│ BLMVM │ Object BLMVM of type str │
├──────────┼─────────────────────────────┤
│ BMRM │ Object BMRM of type str │
├──────────┼─────────────────────────────┤
│ BNCG │ Object BNCG of type str │
├──────────┼─────────────────────────────┤
│ BNLS │ Object BNLS of type str │
├──────────┼─────────────────────────────┤
│ BNTL │ Object BNTL of type str │
├──────────┼─────────────────────────────┤
│ BNTR │ Object BNTR of type str │
├──────────┼─────────────────────────────┤
│ BQNKLS │ Object BQNKLS of type str │
├──────────┼─────────────────────────────┤
│ BQNKTL │ Object BQNKTL of type str │
├──────────┼─────────────────────────────┤
│ BQNKTR │ Object BQNKTR of type str │
├──────────┼─────────────────────────────┤
│ BQNLS │ Object BQNLS of type str │
├──────────┼─────────────────────────────┤
│ BQPIP │ Object BQPIP of type str │
├──────────┼─────────────────────────────┤
│ BRGN │ Object BRGN of type str │
├──────────┼─────────────────────────────┤
│ CG │ Object CG of type str │
├──────────┼─────────────────────────────┤
│ GPCG │ Object GPCG of type str │
├──────────┼─────────────────────────────┤
│ IPM │ Object IPM of type str │
├──────────┼─────────────────────────────┤
│ LCL │ Object LCL of type str │
├──────────┼─────────────────────────────┤
│ LMVM │ Object LMVM of type str │
├──────────┼─────────────────────────────┤
│ NLS │ Object NLS of type str │
├──────────┼─────────────────────────────┤
│ NM │ Object NM of type str │
├──────────┼─────────────────────────────┤
│ NTL │ Object NTL of type str │
├──────────┼─────────────────────────────┤
│ NTR │ Object NTR of type str │
├──────────┼─────────────────────────────┤
│ OWLQN │ Object OWLQN of type str │
├──────────┼─────────────────────────────┤
│ PDIPM │ Object PDIPM of type str │
├──────────┼─────────────────────────────┤
│ POUNDERS │ Object POUNDERS of type str │
├──────────┼─────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├──────────┼─────────────────────────────┤
│ SHELL │ Object SHELL of type str │
├──────────┼─────────────────────────────┤
│ SSFLS │ Object SSFLS of type str │
├──────────┼─────────────────────────────┤
│ SSILS │ Object SSILS of type str │
├──────────┼─────────────────────────────┤
│ TRON │ Object TRON of type str │
└──────────┴─────────────────────────────┘
Attributes Documentation
ADMM: str = ADMM
Object ADMM of type str
ALMM: str = ALMM
Object ALMM of type str
ASFLS: str = ASFLS
Object ASFLS of type str
ASILS: str = ASILS
Object ASILS of type str
BLMVM: str = BLMVM
Object BLMVM of type str
BMRM: str = BMRM
Object BMRM of type str
BNCG: str = BNCG
Object BNCG of type str
BNLS: str = BNLS
Object BNLS of type str
BNTL: str = BNTL
Object BNTL of type str
BNTR: str = BNTR
Object BNTR of type str
BQNKLS: str = BQNKLS
Object BQNKLS of type str
BQNKTL: str = BQNKTL
Object BQNKTL of type str
BQNKTR: str = BQNKTR
Object BQNKTR of type str
BQNLS: str = BQNLS
Object BQNLS of type str
BQPIP: str = BQPIP
Object BQPIP of type str
BRGN: str = BRGN
Object BRGN of type str
CG: str = CG
Object CG of type str
GPCG: str = GPCG
Object GPCG of type str
IPM: str = IPM
Object IPM of type str
LCL: str = LCL
Object LCL of type str
LMVM: str = LMVM
Object LMVM of type str
NLS: str = NLS
Object NLS of type str
NM: str = NM
Object NM of type str
NTL: str = NTL
Object NTL of type str
NTR: str = NTR
Object NTR of type str
OWLQN: str = OWLQN
Object OWLQN of type str
PDIPM: str = PDIPM
Object PDIPM of type str
POUNDERS: str = POUNDERS
Object POUNDERS of type str
PYTHON: str = PYTHON
Object PYTHON of type str
SHELL: str = SHELL
Object SHELL of type str
SSFLS: str = SSFLS
Object SSFLS of type str
SSILS: str = SSILS
Object SSILS of type str
TRON: str = TRON
Object TRON of type str
Methods Summary
┌──────────────────────────────────────────────┬───────────────────────────────────────┐
│ appendOptionsPrefix(prefix) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ cancelMonitor() │ Cancel all the monitors of the │
│ │ solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeConstraints(x, c) │ Compute the vector corresponding to │
│ │ the constraints. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeDualVariables(xl, xu) │ Compute the dual vectors │
│ │ corresponding to variables' bounds. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeGradient(x, g) │ Compute the gradient of the objective │
│ │ function. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeHessian(x, H[, P]) │ Compute the Hessian of the objective │
│ │ function. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeJacobian(x, J[, P]) │ Compute the Jacobian. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeObjective(x) │ Compute the value of the objective │
│ │ function. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeObjectiveGradient(x, g) │ Compute the gradient of the objective │
│ │ function and its value. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeResidual(x, f) │ Compute the residual. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ computeVariableBounds(xl, xu) │ Compute the vectors corresponding to │
│ │ variables' bounds. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a TAO solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ createPython([context, comm]) │ Create an optimization solver of │
│ │ Python type. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getAppCtx() │ Return the application context. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getBNCGType() │ Return the type of the BNCG solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getBRGNDampingVector() │ Return the damping vector. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getBRGNSubsolver() │ Return the subsolver inside the BRGN │
│ │ solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getConstraintTolerances() │ Return the constraints tolerance │
│ │ parameters used in the convergence │
│ │ tests. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergedReason() │ Return the termination flag. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergenceTest() │ Return the callback used to test for │
│ │ solver convergence. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getGradient() │ Return the vector used to store the │
│ │ gradient and the evaluation callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getGradientNorm() │ Return the matrix used to compute │
│ │ inner products. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getHessian() │ Return the matrices used to store the │
│ │ Hessian and the evaluation callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getIterationNumber() │ Return the current iteration number. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getKSP() │ Return the linear solver used by the │
│ │ nonlinear solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getLMVMH0() │ Return the initial Hessian for the │
│ │ quasi-Newton approximation. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getLMVMH0KSP() │ Return the KSP for the inverse of the │
│ │ initial Hessian approximation. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getLineSearch() │ Return the TAO Line Search object. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMaximumFunctionEvaluations() │ Return the maximum number of │
│ │ objective evaluations within the │
│ │ solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMaximumIterations() │ Return the maximum number of solver │
│ │ iterations. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getMonitor() │ Return the callback used to monitor │
│ │ solver convergence. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getObjectiveAndGradient() │ Return the vector used to store the │
│ │ gradient and the evaluation callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getObjectiveValue() │ Return the current value of the │
│ │ objective function. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSolution() │ Return the vector holding the │
│ │ solution. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSolutionNorm() │ Return the objective function value │
│ │ and the norms of gradient and │
│ │ constraints. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getSolutionStatus() │ Return the solution status. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getTolerances() │ Return the tolerance parameters used │
│ │ in the solver convergence tests. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getUpdate() │ Return the callback to compute the │
│ │ update. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ getVariableBounds() │ Return the upper and lower bounds │
│ │ vectors. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ monitor([its, f, res, cnorm, step]) │ Monitor the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setAppCtx(appctx) │ Set the application context. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBNCGType(cg_type) │ Set the type of the BNCG solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBRGNDictionaryMatrix(D) │ Set the dictionary matrix. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBRGNRegularizerHessian(hessian[, │ Set the callback to compute the │
│ H, ...]) │ regularizer Hessian. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBRGNRegularizerObjectiveGradient(objgrad) │ Set the callback to compute the │
│ │ regularizer objective and gradient. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBRGNRegularizerWeight(weight) │ Set the regularizer weight. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setBRGNSmoothL1Epsilon(epsilon) │ Set the smooth L1 epsilon. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConstraintTolerances([catol, crtol]) │ Set the constraints tolerance │
│ │ parameters used in the solver │
│ │ convergence tests. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConstraints(constraints[, C, args, │ Set the callback to compute │
│ kargs]) │ constraints. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergedReason(reason) │ Set the termination flag. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergenceTest(converged[, args, kargs]) │ Set the callback used to test for │
│ │ solver convergence. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setEqualityConstraints(equality_constraints, │ Set equality constraints callback. │
│ c) │ │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the solver from the options │
│ │ database. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGradient(gradient[, g, args, kargs]) │ Set the gradient evaluation callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setGradientNorm(mat) │ Set the matrix used to compute inner │
│ │ products. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setHessian(hessian[, H, P, args, kargs]) │ Set the callback to compute the │
│ │ Hessian matrix. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setInitialTrustRegionRadius(radius) │ Set the initial trust region radius. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setIterationNumber(its) │ Set the current iteration number. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobian(jacobian[, J, P, args, kargs]) │ Set the callback to compute the │
│ │ Jacobian. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobianDesign(jacobian_design[, J, ...]) │ Set Jacobian design callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobianEquality(jacobian_equality[, J, │ Set Jacobian equality constraints │
│ ...]) │ callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobianResidual(jacobian[, J, P, args, │ Set the callback to compute the │
│ ...]) │ least-squares residual Jacobian. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setJacobianState(jacobian_state[, J, P, I, │ Set Jacobian state callback. │
│ ...]) │ │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setLMVMH0(mat) │ Set the initial Hessian for the │
│ │ quasi-Newton approximation. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMaximumFunctionEvaluations(mit) │ Set the maximum number of objective │
│ │ evaluations within the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMaximumIterations(mit) │ Set the maximum number of solver │
│ │ iterations. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setMonitor(monitor[, args, kargs]) │ Set the callback used to monitor │
│ │ solver convergence. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setObjective(objective[, args, kargs]) │ Set the objective function evaluation │
│ │ callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setObjectiveGradient(objgrad[, g, args, │ Set the objective function and │
│ kargs]) │ gradient evaluation callback. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for searching for │
│ │ options in the database. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext(context) │ Set the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setResidual(residual, R[, args, kargs]) │ Set the residual evaluation callback │
│ │ for least-squares applications. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setSolution(x) │ Set the vector used to store the │
│ │ solution. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setStateDesignIS([state, design]) │ Set the index sets indicating state │
│ │ and design variables. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setTolerances([gatol, grtol, gttol]) │ Set the tolerance parameters used in │
│ │ the solver convergence tests. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setType(tao_type) │ Set the type of the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the solver. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setUpdate(update[, args, kargs]) │ Set the callback to compute update at │
│ │ each optimization step. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ setVariableBounds(varbounds[, args, kargs]) │ Set the upper and lower bounds for │
│ │ the optimization problem. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ solve([x]) │ Solve the optimization problem. │
├──────────────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the solver. │
└──────────────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────┬───────────────────────────────────────┐
│ appctx │ Application context. │
├───────────┼───────────────────────────────────────┤
│ cnorm │ Constraints norm. │
├───────────┼───────────────────────────────────────┤
│ converged │ Boolean indicating if the solver has │
│ │ converged. │
├───────────┼───────────────────────────────────────┤
│ ctol │ Broken. │
├───────────┼───────────────────────────────────────┤
│ diverged │ Boolean indicating if the solver has │
│ │ failed. │
├───────────┼───────────────────────────────────────┤
│ ftol │ Broken. │
├───────────┼───────────────────────────────────────┤
│ function │ Objective value. │
├───────────┼───────────────────────────────────────┤
│ gnorm │ Gradient norm. │
├───────────┼───────────────────────────────────────┤
│ gradient │ Gradient vector. │
├───────────┼───────────────────────────────────────┤
│ gtol │ Broken. │
├───────────┼───────────────────────────────────────┤
│ iterating │ Boolean indicating if the solver has │
│ │ not converged yet. │
├───────────┼───────────────────────────────────────┤
│ its │ Number of iterations. │
├───────────┼───────────────────────────────────────┤
│ ksp │ Linear solver. │
├───────────┼───────────────────────────────────────┤
│ objective │ Objective value. │
├───────────┼───────────────────────────────────────┤
│ reason │ Converged reason. │
├───────────┼───────────────────────────────────────┤
│ solution │ Solution vector. │
└───────────┴───────────────────────────────────────┘
Methods Documentation
appendOptionsPrefix(prefix)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, TaoAppendOptionsPrefix
Source code at petsc4py/PETSc/TAO.pyx:213
Parameters
prefix (str | None)
Return type
None
cancelMonitor()
Cancel all the monitors of the solver.
Logically collective.
SEE ALSO:
setMonitor, TaoMonitorCancel
Source code at petsc4py/PETSc/TAO.pyx:1220
Return type
None
computeConstraints(x, c)
Compute the vector corresponding to the constraints.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• c (Vec) -- The output constraints vector.
Return type
None
SEE ALSO:
setVariableBounds, TaoComputeVariableBounds
Source code at petsc4py/PETSc/TAO.pyx:887
computeDualVariables(xl, xu)
Compute the dual vectors corresponding to variables' bounds.
Collective.
SEE ALSO:
TaoComputeDualVariables
Source code at petsc4py/PETSc/TAO.pyx:851
Parameters
• xl (Vec)
• xu (Vec)
Return type
None
computeGradient(x, g)
Compute the gradient of the objective function.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• g (Vec) -- The output gradient vector.
Return type
None
SEE ALSO:
setGradient, TaoComputeGradient
Source code at petsc4py/PETSc/TAO.pyx:810
computeHessian(x, H, P=None)
Compute the Hessian of the objective function.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• H (Mat) -- The output Hessian matrix.
• P (Mat | None) -- The output Hessian matrix used to construct the preconditioner.
Return type
None
SEE ALSO:
setHessian, TaoComputeHessian
Source code at petsc4py/PETSc/TAO.pyx:906
computeJacobian(x, J, P=None)
Compute the Jacobian.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• J (Mat) -- The output Jacobian matrix.
• P (Mat | None) -- The output Jacobian matrix used to construct the preconditioner.
Return type
None
SEE ALSO:
setJacobian, TaoComputeJacobian
Source code at petsc4py/PETSc/TAO.pyx:929
computeObjective(x)
Compute the value of the objective function.
Collective.
Parameters
x (Vec) -- The parameter vector.
Return type
float
SEE ALSO:
setObjective, TaoComputeObjective
Source code at petsc4py/PETSc/TAO.pyx:772
computeObjectiveGradient(x, g)
Compute the gradient of the objective function and its value.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• g (Vec) -- The output gradient vector.
Return type
float
SEE ALSO:
setObjectiveGradient, setGradient, setObjective, TaoComputeObjectiveAndGradient
Source code at petsc4py/PETSc/TAO.pyx:829
computeResidual(x, f)
Compute the residual.
Collective.
Parameters
• x (Vec) -- The parameter vector.
• f (Vec) -- The output vector.
Return type
None
SEE ALSO:
setResidual, TaoComputeResidual
Source code at petsc4py/PETSc/TAO.pyx:791
computeVariableBounds(xl, xu)
Compute the vectors corresponding to variables' bounds.
Collective.
SEE ALSO:
setVariableBounds, TaoComputeVariableBounds
Source code at petsc4py/PETSc/TAO.pyx:863
Parameters
• xl (Vec)
• xu (Vec)
Return type
None
create(comm=None)
Create a TAO solver.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, TaoCreate
Source code at petsc4py/PETSc/TAO.pyx:145
createPython(context=None, comm=None)
Create an optimization solver of Python type.
Collective.
Parameters
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python optimization solver type (TODO), setType, setPythonContext, Type.PYTHON
Source code at petsc4py/PETSc/TAO.pyx:1662
destroy()
Destroy the solver.
Collective.
SEE ALSO:
TaoDestroy
Source code at petsc4py/PETSc/TAO.pyx:132
Return type
Self
getAppCtx()
Return the application context.
Source code at petsc4py/PETSc/TAO.pyx:286
Return type
Any
getBNCGType()
Return the type of the BNCG solver.
Not collective.
SEE ALSO:
setBNCGType, TaoBNCGGetType
Source code at petsc4py/PETSc/TAO.pyx:1416
Return type
BNCGType
getBRGNDampingVector()
Return the damping vector.
Not collective.
Source code at petsc4py/PETSc/TAO.pyx:1647
Return type
Vec
getBRGNSubsolver()
Return the subsolver inside the BRGN solver.
Not collective.
SEE ALSO:
TaoBRGNGetSubsolver
Source code at petsc4py/PETSc/TAO.pyx:1564
Return type
TAO
getConstraintTolerances()
Return the constraints tolerance parameters used in the convergence tests.
Not collective.
Returns
• catol (float) -- The absolute norm of the constraints.
• crtol (float) -- The relative norm of the constraints.
Return type
tuple[float, float]
SEE ALSO:
setConstraintTolerances, TaoGetConstraintTolerances
Source code at petsc4py/PETSc/TAO.pyx:1091
getConvergedReason()
Return the termination flag.
Not collective.
SEE ALSO:
setConvergedReason, TaoGetConvergedReason
Source code at petsc4py/PETSc/TAO.pyx:1165
Return type
ConvergedReason
getConvergenceTest()
Return the callback used to test for solver convergence.
Not collective.
SEE ALSO:
setConvergenceTest
Source code at petsc4py/PETSc/TAO.pyx:1140
Return type
tuple[TAOConvergedFunction, tuple[Any, ...], dict[str, Any]]
getGradient()
Return the vector used to store the gradient and the evaluation callback.
Not collective.
SEE ALSO:
setGradient, setHessian, TaoGetGradient
Source code at petsc4py/PETSc/TAO.pyx:416
Return type
tuple[Vec, TAOGradientFunction]
getGradientNorm()
Return the matrix used to compute inner products.
Not collective.
SEE ALSO:
setGradientNorm, TaoGetGradientNorm
Source code at petsc4py/PETSc/TAO.pyx:1331
Return type
Mat
getHessian()
Return the matrices used to store the Hessian and the evaluation callback.
Not collective.
SEE ALSO:
setHessian, TaoGetHessian
Source code at petsc4py/PETSc/TAO.pyx:578
Return type
tuple[Mat, Mat, TAOHessianFunction]
getIterationNumber()
Return the current iteration number.
Not collective.
SEE ALSO:
setIterationNumber, TaoGetIterationNumber
Source code at petsc4py/PETSc/TAO.pyx:1443
Return type
int
getKSP()
Return the linear solver used by the nonlinear solver.
Not collective.
SEE ALSO:
TaoGetKSP
Source code at petsc4py/PETSc/TAO.pyx:1547
Return type
KSP
getLMVMH0()
Return the initial Hessian for the quasi-Newton approximation.
Not collective.
SEE ALSO:
setLMVMH0, TaoLMVMGetH0
Source code at petsc4py/PETSc/TAO.pyx:1358
Return type
Mat
getLMVMH0KSP()
Return the KSP for the inverse of the initial Hessian approximation.
Not collective.
SEE ALSO:
setLMVMH0, TaoLMVMGetH0KSP
Source code at petsc4py/PETSc/TAO.pyx:1373
Return type
KSP
getLineSearch()
Return the TAO Line Search object.
Not collective.
SEE ALSO:
TaoGetLineSearch
Source code at petsc4py/PETSc/TAO.pyx:1744
Return type
TAOLineSearch
getMaximumFunctionEvaluations()
Return the maximum number of objective evaluations within the solver.
Not collective.
SEE ALSO:
setMaximumFunctionEvaluations, TaoGetMaximumFunctionEvaluations
Source code at petsc4py/PETSc/TAO.pyx:1051
Return type
int
getMaximumIterations()
Return the maximum number of solver iterations.
Not collective.
SEE ALSO:
setMaximumIterations, TaoGetMaximumIterations
Source code at petsc4py/PETSc/TAO.pyx:1024
Return type
int
getMonitor()
Return the callback used to monitor solver convergence.
Not collective.
SEE ALSO:
setMonitor
Source code at petsc4py/PETSc/TAO.pyx:1208
Return type
list[tuple[TAOMonitorFunction, tuple[Any, ...], dict[str, Any]]]
getObjectiveAndGradient()
Return the vector used to store the gradient and the evaluation callback.
Not collective.
SEE ALSO:
setObjectiveGradient, TaoGetObjectiveAndGradient
Source code at petsc4py/PETSc/TAO.pyx:462
Return type
tuple[Vec, TAOObjectiveGradientFunction]
getObjectiveValue()
Return the current value of the objective function.
Not collective.
SEE ALSO:
setObjective, TaoGetSolutionStatus
Source code at petsc4py/PETSc/TAO.pyx:1457
Return type
float
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, TaoGetOptionsPrefix
Source code at petsc4py/PETSc/TAO.pyx:227
Return type
str
getPythonContext()
Return the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python optimization solver type (TODO), setPythonContext
Source code at petsc4py/PETSc/TAO.pyx:1699
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the solver.
Not collective.
SEE ALSO:
PETSc Python optimization solver type (TODO), setPythonContext, setPythonType, ‐
TaoPythonGetType
Source code at petsc4py/PETSc/TAO.pyx:1729
Return type
str
getSolution()
Return the vector holding the solution.
Not collective.
SEE ALSO:
setSolution, TaoGetSolution
Source code at petsc4py/PETSc/TAO.pyx:1304
Return type
Vec
getSolutionNorm()
Return the objective function value and the norms of gradient and constraints.
Not collective.
Returns
• f (float) -- Current value of the objective function.
• res (float) -- Current value of the residual norm.
• cnorm (float) -- Current value of the constrains norm.
Return type
tuple[float, float, float]
SEE ALSO:
getSolutionStatus, TaoGetSolutionStatus
Source code at petsc4py/PETSc/TAO.pyx:1487
getSolutionStatus()
Return the solution status.
Not collective.
Returns
• its (int) -- Current number of iterations.
• f (float) -- Current value of the objective function.
• res (float) -- Current value of the residual norm.
• cnorm (float) -- Current value of the constrains norm.
• step (float) -- Current value of the step.
• reason (ConvergedReason) -- Current value of converged reason.
Return type
tuple[int, float, float, float, float, ConvergedReason]
SEE ALSO:
TaoGetSolutionStatus
Source code at petsc4py/PETSc/TAO.pyx:1512
getTolerances()
Return the tolerance parameters used in the solver convergence tests.
Not collective.
Returns
• gatol (float) -- The absolute norm of the gradient.
• grtol (float) -- The relative norm of the gradient.
• gttol (float) -- The relative norm of the gradient with respect to the initial
norm of the gradient.
Return type
tuple[float, float, float]
SEE ALSO:
setTolerances, TaoGetTolerances
Source code at petsc4py/PETSc/TAO.pyx:987
getType()
Return the type of the solver.
Not collective.
SEE ALSO:
setType, TaoGetType
Source code at petsc4py/PETSc/TAO.pyx:185
Return type
str
getUpdate()
Return the callback to compute the update.
Not collective.
SEE ALSO:
setUpdate
Source code at petsc4py/PETSc/TAO.pyx:758
Return type
tuple[TAOUpdateFunction, tuple[Any, ...], dict[str, Any]]
getVariableBounds()
Return the upper and lower bounds vectors.
Not collective.
SEE ALSO:
setVariableBounds, TaoGetVariableBounds
Source code at petsc4py/PETSc/TAO.pyx:1388
Return type
tuple[Vec, Vec]
monitor(its=None, f=None, res=None, cnorm=None, step=None)
Monitor the solver.
Collective.
This function should be called without arguments, unless users want to modify the values
internally stored by the solver.
Parameters
• its (int) -- Current number of iterations or None to use the value stored
internally by the solver.
• f (float) -- Current value of the objective function or None to use the value
stored internally by the solver.
• res (float) -- Current value of the residual norm or None to use the value stored
internally by the solver.
• cnorm (float) -- Current value of the constrains norm or None to use the value
stored internally by the solver.
• step (float) -- Current value of the step or None to use the value stored
internally by the solver.
Return type
None
SEE ALSO:
setMonitor, TaoMonitor
Source code at petsc4py/PETSc/TAO.pyx:1234
setAppCtx(appctx)
Set the application context.
Source code at petsc4py/PETSc/TAO.pyx:282
Parameters
appctx (Any)
Return type
None
setBNCGType(cg_type)
Set the type of the BNCG solver.
Collective.
SEE ALSO:
getBNCGType, TaoBNCGSetType
Source code at petsc4py/PETSc/TAO.pyx:1403
Parameters
cg_type (BNCGType)
Return type
None
setBRGNDictionaryMatrix(D)
Set the dictionary matrix.
Collective.
SEE ALSO:
TaoBRGNSetDictionaryMatrix
Source code at petsc4py/PETSc/TAO.pyx:1635
Parameters
D (Mat)
Return type
None
setBRGNRegularizerHessian(hessian, H=None, args=None, kargs=None)
Set the callback to compute the regularizer Hessian.
Logically collective.
SEE ALSO:
TaoBRGNSetRegularizerHessianRoutine
Source code at petsc4py/PETSc/TAO.pyx:1595
Parameters
• H (Mat | None)
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setBRGNRegularizerObjectiveGradient(objgrad, args=None, kargs=None)
Set the callback to compute the regularizer objective and gradient.
Logically collective.
SEE ALSO:
TaoBRGNSetRegularizerObjectiveAndGradientRoutine
Source code at petsc4py/PETSc/TAO.pyx:1579
Parameters
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setBRGNRegularizerWeight(weight)
Set the regularizer weight.
Collective.
Source code at petsc4py/PETSc/TAO.pyx:1613
Parameters
weight (float)
Return type
None
setBRGNSmoothL1Epsilon(epsilon)
Set the smooth L1 epsilon.
Collective.
SEE ALSO:
TaoBRGNSetL1SmoothEpsilon
Source code at petsc4py/PETSc/TAO.pyx:1622
Parameters
epsilon (float)
Return type
None
setConstraintTolerances(catol=None, crtol=None)
Set the constraints tolerance parameters used in the solver convergence tests.
Collective.
Parameters
• catol (float) -- The absolute norm of the constraints, or DETERMINE to use the
value when the object's type was set. Defaults to CURRENT.
• crtol (float) -- The relative norm of the constraints, or DETERMINE to use the
value when the object's type was set. Defaults to CURRENT.
Return type
None
SEE ALSO:
getConstraintTolerances, TaoSetConstraintTolerances
Source code at petsc4py/PETSc/TAO.pyx:1065
setConstraints(constraints, C=None, args=None, kargs=None)
Set the callback to compute constraints.
Logically collective.
Parameters
• constraints (TAOConstraintsFunction) -- The callback.
• C (Vec | None) -- The vector to hold the constraints.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
TaoSetConstraintsRoutine
Source code at petsc4py/PETSc/TAO.pyx:514
setConvergedReason(reason)
Set the termination flag.
Collective.
SEE ALSO:
getConvergedReason, TaoSetConvergedReason
Source code at petsc4py/PETSc/TAO.pyx:1152
Parameters
reason (ConvergedReason)
Return type
None
setConvergenceTest(converged, args=None, kargs=None)
Set the callback used to test for solver convergence.
Logically collective.
Parameters
• converged (TAOConvergedFunction | None) -- The callback. If None, reset to the
default convergence test.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getConvergenceTest, TaoSetConvergenceTest
Source code at petsc4py/PETSc/TAO.pyx:1112
setEqualityConstraints(equality_constraints, c, args=None, kargs=None)
Set equality constraints callback.
Logically collective.
SEE ALSO:
TaoSetEqualityConstraintsRoutine
Source code at petsc4py/PETSc/TAO.pyx:689
Parameters
• c (Vec)
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setFromOptions()
Configure the solver from the options database.
Collective.
SEE ALSO:
Working with PETSc options, TaoSetFromOptions
Source code at petsc4py/PETSc/TAO.pyx:241
Return type
None
setGradient(gradient, g=None, args=None, kargs=None)
Set the gradient evaluation callback.
Logically collective.
Parameters
• gradient (TAOGradientFunction) -- The gradient callback.
• g (Vec | None) -- The vector to store the gradient.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setObjective, setObjectiveGradient, setHessian, TaoSetGradient
Source code at petsc4py/PETSc/TAO.pyx:387
setGradientNorm(mat)
Set the matrix used to compute inner products.
Collective.
SEE ALSO:
getGradientNorm, TaoSetGradientNorm
Source code at petsc4py/PETSc/TAO.pyx:1319
Parameters
mat (Mat)
Return type
None
setHessian(hessian, H=None, P=None, args=None, kargs=None)
Set the callback to compute the Hessian matrix.
Logically collective.
Parameters
• hessian (TAOHessianFunction) -- The Hessian callback.
• H (Mat | None) -- The matrix to store the Hessian.
• P (Mat | None) -- The matrix to construct the preconditioner.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getHessian, setObjective, setObjectiveGradient, setGradient, TaoSetHessian
Source code at petsc4py/PETSc/TAO.pyx:543
setInitialTrustRegionRadius(radius)
Set the initial trust region radius.
Collective.
SEE ALSO:
TaoSetInitialTrustRegionRadius
Source code at petsc4py/PETSc/TAO.pyx:267
Parameters
radius (float)
Return type
None
setIterationNumber(its)
Set the current iteration number.
Collective.
SEE ALSO:
getIterationNumber, TaoSetIterationNumber
Source code at petsc4py/PETSc/TAO.pyx:1430
Parameters
its (int)
Return type
None
setJacobian(jacobian, J=None, P=None, args=None, kargs=None)
Set the callback to compute the Jacobian.
Logically collective.
Parameters
• jacobian (TAOJacobianFunction) -- The Jacobian callback.
• J (Mat | None) -- The matrix to store the Jacobian.
• P (Mat | None) -- The matrix to construct the preconditioner.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
TaoSetJacobianRoutine
Source code at petsc4py/PETSc/TAO.pyx:596
setJacobianDesign(jacobian_design, J=None, args=None, kargs=None)
Set Jacobian design callback.
Logically collective.
SEE ALSO:
TaoSetJacobianDesignRoutine
Source code at petsc4py/PETSc/TAO.pyx:669
Parameters
• J (Mat | None)
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setJacobianEquality(jacobian_equality, J=None, P=None, args=None, kargs=None)
Set Jacobian equality constraints callback.
Logically collective.
SEE ALSO:
TaoSetJacobianEqualityRoutine
Source code at petsc4py/PETSc/TAO.pyx:707
Parameters
• J (Mat | None)
• P (Mat | None)
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setJacobianResidual(jacobian, J=None, P=None, args=None, kargs=None)
Set the callback to compute the least-squares residual Jacobian.
Logically collective.
Parameters
• jacobian (TAOJacobianResidualFunction) -- The Jacobian callback.
• J (Mat | None) -- The matrix to store the Jacobian.
• P (Mat | None) -- The matrix to construct the preconditioner.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setResidual, TaoSetJacobianResidualRoutine
Source code at petsc4py/PETSc/TAO.pyx:354
setJacobianState(jacobian_state, J=None, P=None, I=None, args=None, kargs=None)
Set Jacobian state callback.
Logically collective.
SEE ALSO:
TaoSetJacobianStateRoutine
Source code at petsc4py/PETSc/TAO.pyx:645
Parameters
• J (Mat | None)
• P (Mat | None)
• I (Mat | None)
• args (tuple[Any, ...] | None)
• kargs (dict[str, Any] | None)
Return type
None
setLMVMH0(mat)
Set the initial Hessian for the quasi-Newton approximation.
Collective.
SEE ALSO:
getLMVMH0, TaoLMVMSetH0
Source code at petsc4py/PETSc/TAO.pyx:1346
Parameters
mat (Mat)
Return type
None
setMaximumFunctionEvaluations(mit)
Set the maximum number of objective evaluations within the solver.
Collective.
SEE ALSO:
setMaximumIterations, TaoSetMaximumFunctionEvaluations
Source code at petsc4py/PETSc/TAO.pyx:1038
Parameters
mit (int)
Return type
None
setMaximumIterations(mit)
Set the maximum number of solver iterations.
Collective.
SEE ALSO:
setTolerances, TaoSetMaximumIterations
Source code at petsc4py/PETSc/TAO.pyx:1011
Parameters
mit (int)
Return type
float
setMonitor(monitor, args=None, kargs=None)
Set the callback used to monitor solver convergence.
Logically collective.
Parameters
• monitor (TAOMonitorFunction) -- The callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getMonitor, TaoMonitorSet
Source code at petsc4py/PETSc/TAO.pyx:1179
setObjective(objective, args=None, kargs=None)
Set the objective function evaluation callback.
Logically collective.
Parameters
• objective (TAOObjectiveFunction) -- The objective function callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setGradient, setObjectiveGradient, TaoSetObjective
Source code at petsc4py/PETSc/TAO.pyx:302
setObjectiveGradient(objgrad, g=None, args=None, kargs=None)
Set the objective function and gradient evaluation callback.
Logically collective.
Parameters
• objgrad (TAOObjectiveGradientFunction) -- The objective function and gradient
callback.
• g (Vec | None) -- The vector to store the gradient.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setObjective, setGradient, setHessian, getObjectiveAndGradient, ‐
TaoSetObjectiveAndGradient
Source code at petsc4py/PETSc/TAO.pyx:432
setOptionsPrefix(prefix)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, TaoSetOptionsPrefix
Source code at petsc4py/PETSc/TAO.pyx:199
Parameters
prefix (str | None)
Return type
None
setPythonContext(context)
Set the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python optimization solver type (TODO), getPythonContext
Source code at petsc4py/PETSc/TAO.pyx:1687
Parameters
context (Any)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
SEE ALSO:
PETSc Python optimization solver type (TODO), setPythonContext, getPythonType, ‐
TaoPythonSetType
Source code at petsc4py/PETSc/TAO.pyx:1714
Parameters
py_type (str)
Return type
None
setResidual(residual, R, args=None, kargs=None)
Set the residual evaluation callback for least-squares applications.
Logically collective.
Parameters
• residual (TAOResidualFunction) -- The residual callback.
• R (Vec) -- The vector to store the residual.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setJacobianResidual, TaoSetResidualRoutine
Source code at petsc4py/PETSc/TAO.pyx:327
setSolution(x)
Set the vector used to store the solution.
Collective.
SEE ALSO:
getSolution, TaoSetSolution
Source code at petsc4py/PETSc/TAO.pyx:290
Parameters
x (Vec)
Return type
None
setStateDesignIS(state=None, design=None)
Set the index sets indicating state and design variables.
Collective.
SEE ALSO:
TaoSetStateDesignIS
Source code at petsc4py/PETSc/TAO.pyx:630
Parameters
• state (IS | None)
• design (IS | None)
Return type
None
setTolerances(gatol=None, grtol=None, gttol=None)
Set the tolerance parameters used in the solver convergence tests.
Collective.
Parameters
• gatol (float) -- The absolute norm of the gradient, or DETERMINE to use the value
when the object's type was set. Defaults to CURRENT.
• grtol (float) -- The relative norm of the gradient with respect to the initial
norm of the objective, or DETERMINE to use the value when the object's type was
set. Defaults to CURRENT.
• gttol (float) -- The relative norm of the gradient with respect to the initial
norm of the gradient, or DETERMINE to use the value when the object's type was
set. Defaults to CURRENT.
Return type
None
SEE ALSO:
getTolerances, TaoSetTolerances
Source code at petsc4py/PETSc/TAO.pyx:954
setType(tao_type)
Set the type of the solver.
Logically collective.
Parameters
tao_type (Type | str) -- The type of the solver.
Return type
None
SEE ALSO:
getType, TaoSetType
Source code at petsc4py/PETSc/TAO.pyx:166
setUp()
Set up the internal data structures for using the solver.
Collective.
SEE ALSO:
TaoSetUp
Source code at petsc4py/PETSc/TAO.pyx:253
Return type
None
setUpdate(update, args=None, kargs=None)
Set the callback to compute update at each optimization step.
Logically collective.
Parameters
• update (TAOUpdateFunction) -- The update callback or None to reset it.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
getUpdate, TaoSetUpdate
Source code at petsc4py/PETSc/TAO.pyx:729
setVariableBounds(varbounds, args=None, kargs=None)
Set the upper and lower bounds for the optimization problem.
Logically collective.
Parameters
• varbounds (tuple[Vec, Vec] | TAOVariableBoundsFunction) -- Either a tuple of Vec
or a TAOVariableBoundsFunction callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
TaoSetVariableBounds, TaoSetVariableBoundsRoutine
Source code at petsc4py/PETSc/TAO.pyx:478
solve(x=None)
Solve the optimization problem.
Collective.
Parameters
x (Vec | None) -- The starting vector or None to use the vector stored internally.
Return type
None
SEE ALSO:
setSolution, getSolution, TaoSolve
Source code at petsc4py/PETSc/TAO.pyx:1285
view(viewer=None)
View the solver.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
TaoView
Source code at petsc4py/PETSc/TAO.pyx:113
Attributes Documentation
appctx Application context.
Source code at petsc4py/PETSc/TAO.pyx:1765
cnorm Constraints norm.
Source code at petsc4py/PETSc/TAO.pyx:1834
converged
Boolean indicating if the solver has converged.
Source code at petsc4py/PETSc/TAO.pyx:1871
ctol Broken.
Source code at petsc4py/PETSc/TAO.pyx:1809
diverged
Boolean indicating if the solver has failed.
Source code at petsc4py/PETSc/TAO.pyx:1876
ftol Broken.
Source code at petsc4py/PETSc/TAO.pyx:1783
function
Objective value.
Source code at petsc4py/PETSc/TAO.pyx:1849
gnorm Gradient norm.
Source code at petsc4py/PETSc/TAO.pyx:1829
gradient
Gradient vector.
Source code at petsc4py/PETSc/TAO.pyx:1854
gtol Broken.
Source code at petsc4py/PETSc/TAO.pyx:1796
iterating
Boolean indicating if the solver has not converged yet.
Source code at petsc4py/PETSc/TAO.pyx:1866
its Number of iterations.
Source code at petsc4py/PETSc/TAO.pyx:1824
ksp Linear solver.
Source code at petsc4py/PETSc/TAO.pyx:1775
objective
Objective value.
Source code at petsc4py/PETSc/TAO.pyx:1844
reason Converged reason.
Source code at petsc4py/PETSc/TAO.pyx:1861
solution
Solution vector.
Source code at petsc4py/PETSc/TAO.pyx:1839
petsc4py.PETSc.TAOLineSearch
class petsc4py.PETSc.TAOLineSearch
Bases: Object
TAO Line Search.
Enumerations
┌─────────────────┬──────────────────────────────────────┐
│ ConvergedReason │ TAO Line Search Termination Reasons. │
├─────────────────┼──────────────────────────────────────┤
│ Type │ TAO Line Search Types. │
└─────────────────┴──────────────────────────────────────┘
petsc4py.PETSc.TAOLineSearch.ConvergedReason
class petsc4py.PETSc.TAOLineSearch.ConvergedReason
Bases: object
TAO Line Search Termination Reasons.
Attributes Summary
┌─────────────────────┬───────────────────────────────────────┐
│ CONTINUE_SEARCH │ Constant CONTINUE_SEARCH of type int │
├─────────────────────┼───────────────────────────────────────┤
│ FAILED_ASCENT │ Constant FAILED_ASCENT of type int │
├─────────────────────┼───────────────────────────────────────┤
│ FAILED_BADPARAMETER │ Constant FAILED_BADPARAMETER of type │
│ │ int │
├─────────────────────┼───────────────────────────────────────┤
│ FAILED_INFORNAN │ Constant FAILED_INFORNAN of type int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_LOWERBOUND │ Constant HALTED_LOWERBOUND of type ‐ │
│ │ int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_MAXFCN │ Constant HALTED_MAXFCN of type int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_OTHER │ Constant HALTED_OTHER of type int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_RTOL │ Constant HALTED_RTOL of type int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_UPPERBOUND │ Constant HALTED_UPPERBOUND of type ‐ │
│ │ int │
├─────────────────────┼───────────────────────────────────────┤
│ HALTED_USER │ Constant HALTED_USER of type int │
├─────────────────────┼───────────────────────────────────────┤
│ SUCCESS │ Constant SUCCESS of type int │
├─────────────────────┼───────────────────────────────────────┤
│ SUCCESS_USER │ Constant SUCCESS_USER of type int │
└─────────────────────┴───────────────────────────────────────┘
Attributes Documentation
CONTINUE_SEARCH: int = CONTINUE_SEARCH
Constant CONTINUE_SEARCH of type int
FAILED_ASCENT: int = FAILED_ASCENT
Constant FAILED_ASCENT of type int
FAILED_BADPARAMETER: int = FAILED_BADPARAMETER
Constant FAILED_BADPARAMETER of type int
FAILED_INFORNAN: int = FAILED_INFORNAN
Constant FAILED_INFORNAN of type int
HALTED_LOWERBOUND: int = HALTED_LOWERBOUND
Constant HALTED_LOWERBOUND of type int
HALTED_MAXFCN: int = HALTED_MAXFCN
Constant HALTED_MAXFCN of type int
HALTED_OTHER: int = HALTED_OTHER
Constant HALTED_OTHER of type int
HALTED_RTOL: int = HALTED_RTOL
Constant HALTED_RTOL of type int
HALTED_UPPERBOUND: int = HALTED_UPPERBOUND
Constant HALTED_UPPERBOUND of type int
HALTED_USER: int = HALTED_USER
Constant HALTED_USER of type int
SUCCESS: int = SUCCESS
Constant SUCCESS of type int
SUCCESS_USER: int = SUCCESS_USER
Constant SUCCESS_USER of type int
petsc4py.PETSc.TAOLineSearch.Type
class petsc4py.PETSc.TAOLineSearch.Type
Bases: object
TAO Line Search Types.
Attributes Summary
┌─────────────┬────────────────────────────────┐
│ ARMIJO │ Object ARMIJO of type str │
├─────────────┼────────────────────────────────┤
│ GPCG │ Object GPCG of type str │
├─────────────┼────────────────────────────────┤
│ IPM │ Object IPM of type str │
├─────────────┼────────────────────────────────┤
│ MORETHUENTE │ Object MORETHUENTE of type str │
├─────────────┼────────────────────────────────┤
│ OWARMIJO │ Object OWARMIJO of type str │
├─────────────┼────────────────────────────────┤
│ UNIT │ Object UNIT of type str │
└─────────────┴────────────────────────────────┘
Attributes Documentation
ARMIJO: str = ARMIJO
Object ARMIJO of type str
GPCG: str = GPCG
Object GPCG of type str
IPM: str = IPM
Object IPM of type str
MORETHUENTE: str = MORETHUENTE
Object MORETHUENTE of type str
OWARMIJO: str = OWARMIJO
Object OWARMIJO of type str
UNIT: str = UNIT
Object UNIT of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ apply(x, g, s) │ Performs a line-search in a given │
│ │ step direction. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a TAO linesearch. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the linesearch object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the linesearch. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the linesearch from the │
│ │ options database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setGradient(gradient[, args, kargs]) │ Set the gradient evaluation callback. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setObjective(objective[, args, │ Set the objective function evaluation │
│ kargs]) │ callback. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setObjectiveGradient(objgrad[, args, │ Set the objective function and │
│ kargs]) │ gradient evaluation callback. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix([prefix]) │ Set the prefix used for searching for │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(ls_type) │ Set the type of the linesearch. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the linesearch. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ useTAORoutine(tao) │ Use the objective and gradient │
│ │ evaluation routines from the given │
│ │ Tao object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ View the linesearch object. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
apply(x, g, s)
Performs a line-search in a given step direction.
Collective.
SEE ALSO:
TaoLineSearchApply
Source code at petsc4py/PETSc/TAO.pyx:2161
Parameters
• x (Vec)
• g (Vec)
• s (Vec)
Return type
tuple[float, float, str]
create(comm=None)
Create a TAO linesearch.
Collective.
Parameters
comm -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, TaoLineSearchCreate
Source code at petsc4py/PETSc/TAO.pyx:1964
destroy()
Destroy the linesearch object.
Collective.
SEE ALSO:
TaoLineSearchDestroy
Source code at petsc4py/PETSc/TAO.pyx:1951
Return type
Self
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, TaoLineSearchGetOptionsPrefix
Source code at petsc4py/PETSc/TAO.pyx:2056
Return type
str
getType()
Return the type of the linesearch.
Not collective.
SEE ALSO:
setType, TaoLineSearchGetType
Source code at petsc4py/PETSc/TAO.pyx:2004
Return type
str
setFromOptions()
Configure the linesearch from the options database.
Collective.
SEE ALSO:
Working with PETSc options, TaoLineSearchSetFromOptions
Source code at petsc4py/PETSc/TAO.pyx:2018
Return type
None
setGradient(gradient, args=None, kargs=None)
Set the gradient evaluation callback.
Logically collective.
Parameters
• gradient (TAOLSGradientFunction) -- The gradient callback.
• g -- The vector to store the gradient.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setObjective, setObjectiveGradient, setHessian, TaoLineSearchSetGradientRoutine
Source code at petsc4py/PETSc/TAO.pyx:2095
setObjective(objective, args=None, kargs=None)
Set the objective function evaluation callback.
Logically collective.
Parameters
• objective (TAOLSObjectiveFunction) -- The objective function callback.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setGradient, setObjectiveGradient, TaoLineSearchSetObjectiveRoutine
Source code at petsc4py/PETSc/TAO.pyx:2070
setObjectiveGradient(objgrad, args=None, kargs=None)
Set the objective function and gradient evaluation callback.
Logically collective.
Parameters
• objgrad (TAOLSObjectiveGradientFunction) -- The objective function and gradient
callback.
• g -- The vector to store the gradient.
• args (tuple[Any, ...] | None) -- Positional arguments for the callback.
• kargs (dict[str, Any] | None) -- Keyword arguments for the callback.
Return type
None
SEE ALSO:
setObjective, setGradient, setHessian, getObjectiveAndGradient, ‐
TaoLineSearchSetObjectiveAndGradientRoutine
Source code at petsc4py/PETSc/TAO.pyx:2122
setOptionsPrefix(prefix=None)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, TaoLineSearchSetOptionsPrefix
Source code at petsc4py/PETSc/TAO.pyx:2042
Parameters
prefix (str | None)
Return type
None
setType(ls_type)
Set the type of the linesearch.
Logically collective.
Parameters
ls_type (Type | str) -- The type of the solver.
Return type
None
SEE ALSO:
getType, TaoLineSearchSetType
Source code at petsc4py/PETSc/TAO.pyx:1985
setUp()
Set up the internal data structures for using the linesearch.
Collective.
SEE ALSO:
TaoLineSearchSetUp
Source code at petsc4py/PETSc/TAO.pyx:2030
Return type
None
useTAORoutine(tao)
Use the objective and gradient evaluation routines from the given Tao object.
Logically collective.
SEE ALSO:
TaoLineSearchUseTaoRoutines
Source code at petsc4py/PETSc/TAO.pyx:2149
Parameters
tao (TAO)
Return type
None
view(viewer=None)
View the linesearch object.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
TaoLineSearchView
Source code at petsc4py/PETSc/TAO.pyx:1932
petsc4py.PETSc.TS
class petsc4py.PETSc.TS
Bases: Object
ODE integrator.
TS is described in the PETSc manual.
SEE ALSO:
TS
Enumerations
┌─────────────────┬───────────────────────────────────────┐
│ ARKIMEXType │ The ARKIMEX subtype. │
├─────────────────┼───────────────────────────────────────┤
│ ConvergedReason │ The reason the time step is │
│ │ converging. │
├─────────────────┼───────────────────────────────────────┤
│ DIRKType │ The DIRK subtype. │
├─────────────────┼───────────────────────────────────────┤
│ EquationType │ Distinguishes among types of explicit │
│ │ and implicit equations. │
├─────────────────┼───────────────────────────────────────┤
│ ExactFinalTime │ The method for ending time stepping. │
├─────────────────┼───────────────────────────────────────┤
│ ProblemType │ Distinguishes linear and nonlinear │
│ │ problems. │
├─────────────────┼───────────────────────────────────────┤
│ RKType │ The RK subtype. │
├─────────────────┼───────────────────────────────────────┤
│ Type │ The time stepping method. │
└─────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.TS.ARKIMEXType
class petsc4py.PETSc.TS.ARKIMEXType
Bases: object
The ARKIMEX subtype.
Attributes Summary
┌───────────────┬──────────────────────────────────┐
│ ARKIMEX1BEE │ Object ARKIMEX1BEE of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX2C │ Object ARKIMEX2C of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX2D │ Object ARKIMEX2D of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX2E │ Object ARKIMEX2E of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX3 │ Object ARKIMEX3 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX4 │ Object ARKIMEX4 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEX5 │ Object ARKIMEX5 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXA2 │ Object ARKIMEXA2 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXARS122 │ Object ARKIMEXARS122 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXARS443 │ Object ARKIMEXARS443 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXBPR3 │ Object ARKIMEXBPR3 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXL2 │ Object ARKIMEXL2 of type str │
├───────────────┼──────────────────────────────────┤
│ ARKIMEXPRSSP2 │ Object ARKIMEXPRSSP2 of type str │
└───────────────┴──────────────────────────────────┘
Attributes Documentation
ARKIMEX1BEE: str = ARKIMEX1BEE
Object ARKIMEX1BEE of type str
ARKIMEX2C: str = ARKIMEX2C
Object ARKIMEX2C of type str
ARKIMEX2D: str = ARKIMEX2D
Object ARKIMEX2D of type str
ARKIMEX2E: str = ARKIMEX2E
Object ARKIMEX2E of type str
ARKIMEX3: str = ARKIMEX3
Object ARKIMEX3 of type str
ARKIMEX4: str = ARKIMEX4
Object ARKIMEX4 of type str
ARKIMEX5: str = ARKIMEX5
Object ARKIMEX5 of type str
ARKIMEXA2: str = ARKIMEXA2
Object ARKIMEXA2 of type str
ARKIMEXARS122: str = ARKIMEXARS122
Object ARKIMEXARS122 of type str
ARKIMEXARS443: str = ARKIMEXARS443
Object ARKIMEXARS443 of type str
ARKIMEXBPR3: str = ARKIMEXBPR3
Object ARKIMEXBPR3 of type str
ARKIMEXL2: str = ARKIMEXL2
Object ARKIMEXL2 of type str
ARKIMEXPRSSP2: str = ARKIMEXPRSSP2
Object ARKIMEXPRSSP2 of type str
petsc4py.PETSc.TS.ConvergedReason
class petsc4py.PETSc.TS.ConvergedReason
Bases: object
The reason the time step is converging.
Attributes Summary
┌──────────────────────────┬───────────────────────────────────────┐
│ CONVERGED_EVENT │ Constant CONVERGED_EVENT of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITERATING │ Constant CONVERGED_ITERATING of type │
│ │ int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_ITS │ Constant CONVERGED_ITS of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_TIME │ Constant CONVERGED_TIME of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ CONVERGED_USER │ Constant CONVERGED_USER of type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_NONLINEAR_SOLVE │ Constant DIVERGED_NONLINEAR_SOLVE of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ DIVERGED_STEP_REJECTED │ Constant DIVERGED_STEP_REJECTED of │
│ │ type int │
├──────────────────────────┼───────────────────────────────────────┤
│ ITERATING │ Constant ITERATING of type int │
└──────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
CONVERGED_EVENT: int = CONVERGED_EVENT
Constant CONVERGED_EVENT of type int
CONVERGED_ITERATING: int = CONVERGED_ITERATING
Constant CONVERGED_ITERATING of type int
CONVERGED_ITS: int = CONVERGED_ITS
Constant CONVERGED_ITS of type int
CONVERGED_TIME: int = CONVERGED_TIME
Constant CONVERGED_TIME of type int
CONVERGED_USER: int = CONVERGED_USER
Constant CONVERGED_USER of type int
DIVERGED_NONLINEAR_SOLVE: int = DIVERGED_NONLINEAR_SOLVE
Constant DIVERGED_NONLINEAR_SOLVE of type int
DIVERGED_STEP_REJECTED: int = DIVERGED_STEP_REJECTED
Constant DIVERGED_STEP_REJECTED of type int
ITERATING: int = ITERATING
Constant ITERATING of type int
petsc4py.PETSc.TS.DIRKType
class petsc4py.PETSc.TS.DIRKType
Bases: object
The DIRK subtype.
Attributes Summary
┌───────────────┬──────────────────────────────────┐
│ DIRK657A │ Object DIRK657A of type str │
├───────────────┼──────────────────────────────────┤
│ DIRK658A │ Object DIRK658A of type str │
├───────────────┼──────────────────────────────────┤
│ DIRK7510SAL │ Object DIRK7510SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRK759A │ Object DIRK759A of type str │
├───────────────┼──────────────────────────────────┤
│ DIRK8614A │ Object DIRK8614A of type str │
├───────────────┼──────────────────────────────────┤
│ DIRK8616SAL │ Object DIRK8616SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES122SAL │ Object DIRKES122SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES213SAL │ Object DIRKES213SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES324SAL │ Object DIRKES324SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES325SAL │ Object DIRKES325SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES648SA │ Object DIRKES648SA of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES7510SA │ Object DIRKES7510SA of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKES8516SAL │ Object DIRKES8516SAL of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKS212 │ Object DIRKS212 of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKS659A │ Object DIRKS659A of type str │
├───────────────┼──────────────────────────────────┤
│ DIRKS7511SAL │ Object DIRKS7511SAL of type str │
└───────────────┴──────────────────────────────────┘
Attributes Documentation
DIRK657A: str = DIRK657A
Object DIRK657A of type str
DIRK658A: str = DIRK658A
Object DIRK658A of type str
DIRK7510SAL: str = DIRK7510SAL
Object DIRK7510SAL of type str
DIRK759A: str = DIRK759A
Object DIRK759A of type str
DIRK8614A: str = DIRK8614A
Object DIRK8614A of type str
DIRK8616SAL: str = DIRK8616SAL
Object DIRK8616SAL of type str
DIRKES122SAL: str = DIRKES122SAL
Object DIRKES122SAL of type str
DIRKES213SAL: str = DIRKES213SAL
Object DIRKES213SAL of type str
DIRKES324SAL: str = DIRKES324SAL
Object DIRKES324SAL of type str
DIRKES325SAL: str = DIRKES325SAL
Object DIRKES325SAL of type str
DIRKES648SA: str = DIRKES648SA
Object DIRKES648SA of type str
DIRKES7510SA: str = DIRKES7510SA
Object DIRKES7510SA of type str
DIRKES8516SAL: str = DIRKES8516SAL
Object DIRKES8516SAL of type str
DIRKS212: str = DIRKS212
Object DIRKS212 of type str
DIRKS659A: str = DIRKS659A
Object DIRKS659A of type str
DIRKS7511SAL: str = DIRKS7511SAL
Object DIRKS7511SAL of type str
petsc4py.PETSc.TS.EquationType
class petsc4py.PETSc.TS.EquationType
Bases: object
Distinguishes among types of explicit and implicit equations.
Attributes Summary
┌───────────────────────────┬───────────────────────────────────────┐
│ DAE_IMPLICIT_INDEX1 │ Constant DAE_IMPLICIT_INDEX1 of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_IMPLICIT_INDEX2 │ Constant DAE_IMPLICIT_INDEX2 of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_IMPLICIT_INDEX3 │ Constant DAE_IMPLICIT_INDEX3 of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_IMPLICIT_INDEXHI │ Constant DAE_IMPLICIT_INDEXHI of type │
│ │ int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_SEMI_EXPLICIT_INDEX1 │ Constant DAE_SEMI_EXPLICIT_INDEX1 of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_SEMI_EXPLICIT_INDEX2 │ Constant DAE_SEMI_EXPLICIT_INDEX2 of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_SEMI_EXPLICIT_INDEX3 │ Constant DAE_SEMI_EXPLICIT_INDEX3 of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ DAE_SEMI_EXPLICIT_INDEXHI │ Constant DAE_SEMI_EXPLICIT_INDEXHI of │
│ │ type int │
├───────────────────────────┼───────────────────────────────────────┤
│ EXPLICIT │ Constant EXPLICIT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ IMPLICIT │ Constant IMPLICIT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ ODE_EXPLICIT │ Constant ODE_EXPLICIT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ ODE_IMPLICIT │ Constant ODE_IMPLICIT of type int │
├───────────────────────────┼───────────────────────────────────────┤
│ UNSPECIFIED │ Constant UNSPECIFIED of type int │
└───────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
DAE_IMPLICIT_INDEX1: int = DAE_IMPLICIT_INDEX1
Constant DAE_IMPLICIT_INDEX1 of type int
DAE_IMPLICIT_INDEX2: int = DAE_IMPLICIT_INDEX2
Constant DAE_IMPLICIT_INDEX2 of type int
DAE_IMPLICIT_INDEX3: int = DAE_IMPLICIT_INDEX3
Constant DAE_IMPLICIT_INDEX3 of type int
DAE_IMPLICIT_INDEXHI: int = DAE_IMPLICIT_INDEXHI
Constant DAE_IMPLICIT_INDEXHI of type int
DAE_SEMI_EXPLICIT_INDEX1: int = DAE_SEMI_EXPLICIT_INDEX1
Constant DAE_SEMI_EXPLICIT_INDEX1 of type int
DAE_SEMI_EXPLICIT_INDEX2: int = DAE_SEMI_EXPLICIT_INDEX2
Constant DAE_SEMI_EXPLICIT_INDEX2 of type int
DAE_SEMI_EXPLICIT_INDEX3: int = DAE_SEMI_EXPLICIT_INDEX3
Constant DAE_SEMI_EXPLICIT_INDEX3 of type int
DAE_SEMI_EXPLICIT_INDEXHI: int = DAE_SEMI_EXPLICIT_INDEXHI
Constant DAE_SEMI_EXPLICIT_INDEXHI of type int
EXPLICIT: int = EXPLICIT
Constant EXPLICIT of type int
IMPLICIT: int = IMPLICIT
Constant IMPLICIT of type int
ODE_EXPLICIT: int = ODE_EXPLICIT
Constant ODE_EXPLICIT of type int
ODE_IMPLICIT: int = ODE_IMPLICIT
Constant ODE_IMPLICIT of type int
UNSPECIFIED: int = UNSPECIFIED
Constant UNSPECIFIED of type int
petsc4py.PETSc.TS.ExactFinalTime
class petsc4py.PETSc.TS.ExactFinalTime
Bases: object
The method for ending time stepping.
Attributes Summary
┌─────────────┬──────────────────────────────────┐
│ INTERPOLATE │ Constant INTERPOLATE of type int │
├─────────────┼──────────────────────────────────┤
│ MATCHSTEP │ Constant MATCHSTEP of type int │
├─────────────┼──────────────────────────────────┤
│ STEPOVER │ Constant STEPOVER of type int │
├─────────────┼──────────────────────────────────┤
│ UNSPECIFIED │ Constant UNSPECIFIED of type int │
└─────────────┴──────────────────────────────────┘
Attributes Documentation
INTERPOLATE: int = INTERPOLATE
Constant INTERPOLATE of type int
MATCHSTEP: int = MATCHSTEP
Constant MATCHSTEP of type int
STEPOVER: int = STEPOVER
Constant STEPOVER of type int
UNSPECIFIED: int = UNSPECIFIED
Constant UNSPECIFIED of type int
petsc4py.PETSc.TS.ProblemType
class petsc4py.PETSc.TS.ProblemType
Bases: object
Distinguishes linear and nonlinear problems.
Attributes Summary
┌───────────┬────────────────────────────────┐
│ LINEAR │ Constant LINEAR of type int │
├───────────┼────────────────────────────────┤
│ NONLINEAR │ Constant NONLINEAR of type int │
└───────────┴────────────────────────────────┘
Attributes Documentation
LINEAR: int = LINEAR
Constant LINEAR of type int
NONLINEAR: int = NONLINEAR
Constant NONLINEAR of type int
petsc4py.PETSc.TS.RKType
class petsc4py.PETSc.TS.RKType
Bases: object
The RK subtype.
Attributes Summary
┌───────┬──────────────────────────┐
│ RK1FE │ Object RK1FE of type str │
├───────┼──────────────────────────┤
│ RK2A │ Object RK2A of type str │
├───────┼──────────────────────────┤
│ RK2B │ Object RK2B of type str │
├───────┼──────────────────────────┤
│ RK3 │ Object RK3 of type str │
├───────┼──────────────────────────┤
│ RK3BS │ Object RK3BS of type str │
├───────┼──────────────────────────┤
│ RK4 │ Object RK4 of type str │
├───────┼──────────────────────────┤
│ RK5BS │ Object RK5BS of type str │
├───────┼──────────────────────────┤
│ RK5DP │ Object RK5DP of type str │
├───────┼──────────────────────────┤
│ RK5F │ Object RK5F of type str │
├───────┼──────────────────────────┤
│ RK6VR │ Object RK6VR of type str │
├───────┼──────────────────────────┤
│ RK7VR │ Object RK7VR of type str │
├───────┼──────────────────────────┤
│ RK8VR │ Object RK8VR of type str │
└───────┴──────────────────────────┘
Attributes Documentation
RK1FE: str = RK1FE
Object RK1FE of type str
RK2A: str = RK2A
Object RK2A of type str
RK2B: str = RK2B
Object RK2B of type str
RK3: str = RK3
Object RK3 of type str
RK3BS: str = RK3BS
Object RK3BS of type str
RK4: str = RK4
Object RK4 of type str
RK5BS: str = RK5BS
Object RK5BS of type str
RK5DP: str = RK5DP
Object RK5DP of type str
RK5F: str = RK5F
Object RK5F of type str
RK6VR: str = RK6VR
Object RK6VR of type str
RK7VR: str = RK7VR
Object RK7VR of type str
RK8VR: str = RK8VR
Object RK8VR of type str
petsc4py.PETSc.TS.Type
class petsc4py.PETSc.TS.Type
Bases: object
The time stepping method.
Attributes Summary
┌─────────────────┬────────────────────────────────────┐
│ ALPHA │ Object ALPHA of type str │
├─────────────────┼────────────────────────────────────┤
│ ALPHA2 │ Object ALPHA2 of type str │
├─────────────────┼────────────────────────────────────┤
│ ARKIMEX │ Object ARKIMEX of type str │
├─────────────────┼────────────────────────────────────┤
│ BASICSYMPLECTIC │ Object BASICSYMPLECTIC of type str │
├─────────────────┼────────────────────────────────────┤
│ BDF │ Object BDF of type str │
├─────────────────┼────────────────────────────────────┤
│ BE │ Object BE of type str │
├─────────────────┼────────────────────────────────────┤
│ BEULER │ Object BEULER of type str │
├─────────────────┼────────────────────────────────────┤
│ CN │ Object CN of type str │
├─────────────────┼────────────────────────────────────┤
│ CRANK_NICOLSON │ Object CRANK_NICOLSON of type str │
├─────────────────┼────────────────────────────────────┤
│ DIRK │ Object DIRK of type str │
├─────────────────┼────────────────────────────────────┤
│ DISCGRAD │ Object DISCGRAD of type str │
├─────────────────┼────────────────────────────────────┤
│ EIMEX │ Object EIMEX of type str │
├─────────────────┼────────────────────────────────────┤
│ EULER │ Object EULER of type str │
├─────────────────┼────────────────────────────────────┤
│ FE │ Object FE of type str │
├─────────────────┼────────────────────────────────────┤
│ GLEE │ Object GLEE of type str │
├─────────────────┼────────────────────────────────────┤
│ GLLE │ Object GLLE of type str │
├─────────────────┼────────────────────────────────────┤
│ MIMEX │ Object MIMEX of type str │
├─────────────────┼────────────────────────────────────┤
│ MPRK │ Object MPRK of type str │
├─────────────────┼────────────────────────────────────┤
│ PSEUDO │ Object PSEUDO of type str │
├─────────────────┼────────────────────────────────────┤
│ PYTHON │ Object PYTHON of type str │
├─────────────────┼────────────────────────────────────┤
│ RADAU5 │ Object RADAU5 of type str │
├─────────────────┼────────────────────────────────────┤
│ RK │ Object RK of type str │
├─────────────────┼────────────────────────────────────┤
│ ROSW │ Object ROSW of type str │
├─────────────────┼────────────────────────────────────┤
│ RUNGE_KUTTA │ Object RUNGE_KUTTA of type str │
├─────────────────┼────────────────────────────────────┤
│ SSP │ Object SSP of type str │
├─────────────────┼────────────────────────────────────┤
│ SUNDIALS │ Object SUNDIALS of type str │
├─────────────────┼────────────────────────────────────┤
│ TH │ Object TH of type str │
├─────────────────┼────────────────────────────────────┤
│ THETA │ Object THETA of type str │
└─────────────────┴────────────────────────────────────┘
Attributes Documentation
ALPHA: str = ALPHA
Object ALPHA of type str
ALPHA2: str = ALPHA2
Object ALPHA2 of type str
ARKIMEX: str = ARKIMEX
Object ARKIMEX of type str
BASICSYMPLECTIC: str = BASICSYMPLECTIC
Object BASICSYMPLECTIC of type str
BDF: str = BDF
Object BDF of type str
BE: str = BE
Object BE of type str
BEULER: str = BEULER
Object BEULER of type str
CN: str = CN
Object CN of type str
CRANK_NICOLSON: str = CRANK_NICOLSON
Object CRANK_NICOLSON of type str
DIRK: str = DIRK
Object DIRK of type str
DISCGRAD: str = DISCGRAD
Object DISCGRAD of type str
EIMEX: str = EIMEX
Object EIMEX of type str
EULER: str = EULER
Object EULER of type str
FE: str = FE
Object FE of type str
GLEE: str = GLEE
Object GLEE of type str
GLLE: str = GLLE
Object GLLE of type str
MIMEX: str = MIMEX
Object MIMEX of type str
MPRK: str = MPRK
Object MPRK of type str
PSEUDO: str = PSEUDO
Object PSEUDO of type str
PYTHON: str = PYTHON
Object PYTHON of type str
RADAU5: str = RADAU5
Object RADAU5 of type str
RK: str = RK
Object RK of type str
ROSW: str = ROSW
Object ROSW of type str
RUNGE_KUTTA: str = RUNGE_KUTTA
Object RUNGE_KUTTA of type str
SSP: str = SSP
Object SSP of type str
SUNDIALS: str = SUNDIALS
Object SUNDIALS of type str
TH: str = TH
Object TH of type str
THETA: str = THETA
Object THETA of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ adjointReset() │ Reset a TS, removing any allocated │
│ │ vectors and matrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ adjointSetSteps(adjoint_steps) │ Set the number of steps the adjoint │
│ │ solver should take backward in time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ adjointSetUp() │ Set up the internal data structures │
│ │ for the later use of an adjoint │
│ │ solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ adjointSolve() │ Solve the discrete adjoint problem │
│ │ for an ODE/DAE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ adjointStep() │ Step one time step backward in the │
│ │ adjoint run. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix(prefix) │ Append to the prefix used for all the │
│ │ TS options. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clone() │ Return a shallow clone of the TS │
│ │ object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeI2Function(t, x, xdot, │ Evaluate the DAE residual in implicit │
│ xdotdot, f) │ form. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeI2Jacobian(t, x, xdot, │ Evaluate the Jacobian of the DAE. │
│ xdotdot, v, a, J) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeIFunction(t, x, xdot, f[, │ Evaluate the DAE residual written in │
│ imex]) │ implicit form. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeIJacobian(t, x, xdot, a, J[, │ Evaluate the Jacobian of the DAE. │
│ P, imex]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeIJacobianP(t, x, xdot, a, J[, │ Evaluate the Jacobian with respect to │
│ imex]) │ parameters. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeRHSFunction(t, x, f) │ Evaluate the right-hand side │
│ │ function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeRHSFunctionLinear(t, x, f) │ Evaluate the right-hand side via the │
│ │ user-provided Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeRHSJacobian(t, x, J[, P]) │ Compute the Jacobian matrix that has │
│ │ been set with setRHSJacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeRHSJacobianConstant(t, x, J[, │ Reuse a Jacobian that is │
│ P]) │ time-independent. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ computeRHSJacobianP(t, x, J) │ Run the user-defined JacobianP │
│ │ function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create an empty TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createPython([context, comm]) │ Create an integrator of Python type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createQuadratureTS([forward]) │ Create a sub TS that evaluates │
│ │ integrals over time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the TS that was created with │
│ │ create. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getARKIMEXType() │ Return the Type.ARKIMEX scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAlphaParams() │ Return the algorithmic parameters for │
│ │ Type.ALPHA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getAppCtx() │ Return the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getConvergedReason() │ Return the reason the TS step was │
│ │ stopped. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCostGradients() │ Return the cost gradients. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCostIntegral() │ Return a vector of values of the │
│ │ integral term in the cost functions. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDIRKType() │ Return the Type.DIRK scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM associated with the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getEquationType() │ Get the type of the equation that TS │
│ │ is solving. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getI2Function() │ Return the vector and function which │
│ │ computes the residual. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getI2Jacobian() │ Return the matrices and function │
│ │ which computes the Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIFunction() │ Return the vector and function which │
│ │ computes the implicit residual. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getIJacobian() │ Return the matrices and function │
│ │ which computes the implicit Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getKSP() │ Return the KSP associated with the │
│ │ TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getKSPIterations() │ Return the total number of linear │
│ │ iterations used by the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxSteps() │ Return the maximum number of steps to │
│ │ use. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMaxTime() │ Return the maximum (final) time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getMonitor() │ Return the monitor. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNumEvents() │ Return the number of events. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for all the TS │
│ │ options. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPostStep() │ Return the poststep function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPreStep() │ Return the prestep function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPrevTime() │ Return the starting time of the │
│ │ previously completed step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getProblemType() │ Return the type of problem to be │
│ │ solved. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonContext() │ Return the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getPythonType() │ Return the fully qualified Python │
│ │ name of the class used by the solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getQuadratureTS() │ Return the sub TS that evaluates │
│ │ integrals over time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRHSFunction() │ Return the vector where the rhs is │
│ │ stored and the function used to │
│ │ compute it. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRHSJacobian() │ Return the Jacobian and the function │
│ │ used to compute them. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getRKType() │ Return the Type.RK scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSNES() │ Return the SNES associated with the │
│ │ TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSNESFailures() │ Return the total number of failed │
│ │ SNES solves in the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSNESIterations() │ Return the total number of nonlinear │
│ │ iterations used by the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolution() │ Return the solution at the present │
│ │ timestep. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolution2() │ Return the solution and time │
│ │ derivative at the present timestep. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSolveTime() │ Return the time after a call to │
│ │ solve. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStepLimits() │ Return the minimum and maximum │
│ │ allowed time step sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStepNumber() │ Return the number of time steps │
│ │ completed. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getStepRejections() │ Return the total number of rejected │
│ │ steps. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTheta() │ Return the abscissa of the stage in │
│ │ (0, 1] for Type.THETA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getThetaEndpoint() │ Return whether the endpoint variable │
│ │ of Type.THETA is used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTime() │ Return the time of the most recently │
│ │ completed step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTimeSpan() │ Return the time span. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTimeSpanSolutions() │ Return the solutions at the times in │
│ │ the time span. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTimeStep() │ Return the duration of the current │
│ │ timestep. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getTolerances() │ Return the tolerances for local │
│ │ truncation error. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the TS type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ interpolate(t, u) │ Interpolate the solution to a given │
│ │ time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ load(viewer) │ Load a TS that has been stored in │
│ │ binary with view. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitor(step, time[, u]) │ Monitor the solve. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ monitorCancel() │ Clear all the monitors that have been │
│ │ set. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ removeTrajectory() │ Remove the internal TS trajectory │
│ │ object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reset() │ Reset the TS, removing any allocated │
│ │ vectors and matrices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restartStep() │ Flag the solver to restart the next │
│ │ step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ rollBack() │ Roll back one time step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setARKIMEXFastSlowSplit(flag) │ Use ARKIMEX for solving a fast-slow │
│ │ system. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setARKIMEXFullyImplicit(flag) │ Solve both parts of the equation │
│ │ implicitly. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setARKIMEXType(ts_type) │ Set the type of Type.ARKIMEX scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAlphaParams([alpha_m, alpha_f, │ Set the algorithmic parameters for │
│ gamma]) │ Type.ALPHA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAlphaRadius(radius) │ Set the spectral radius for │
│ │ Type.ALPHA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setAppCtx(appctx) │ Set the application context. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setConvergedReason(reason) │ Set the reason for handling the │
│ │ convergence of solve. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setCostGradients(vl[, vm]) │ Set the cost gradients. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDIRKType(ts_type) │ Set the type of Type.DIRK scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Set the DM that may be used by some │
│ │ nonlinear solvers or preconditioners. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setEquationType(eqtype) │ Set the type of the equation that TS │
│ │ is solving. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setErrorIfStepFails([flag]) │ Immediately error is no step │
│ │ succeeds. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setEventHandler(direction, terminate, │ Set a function used for detecting │
│ indicator) │ events. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setEventTolerances([tol, vtol]) │ Set tolerances for event zero │
│ │ crossings when using event handler. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setExactFinalTime(option) │ Set method of computing the final │
│ │ time step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Set various TS parameters from user │
│ │ options. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setI2Function(function[, f, args, │ Set the function to compute the 2nd │
│ kargs]) │ order DAE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setI2Jacobian(jacobian[, J, P, args, │ Set the function to compute the │
│ kargs]) │ Jacobian of the 2nd order DAE. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIFunction(function[, f, args, │ Set the function representing the DAE │
│ kargs]) │ to be solved. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIJacobian(jacobian[, J, P, args, │ Set the function to compute the │
│ kargs]) │ Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setIJacobianP(jacobian[, J, args, │ Set the function that computes the │
│ kargs]) │ Jacobian. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxSNESFailures(n) │ Set the maximum number of SNES solves │
│ │ failures allowed. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxStepRejections(n) │ Set the maximum number of step │
│ │ rejections before a time step fails. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxSteps(max_steps) │ Set the maximum number of steps to │
│ │ use. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMaxTime(max_time) │ Set the maximum (final) time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMonitor(monitor[, args, kargs]) │ Set an additional monitor to the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for all the TS │
│ │ options. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPostStep(poststep[, args, kargs]) │ Set a function to be called at the │
│ │ end of each time step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPreStep(prestep[, args, kargs]) │ Set a function to be called at the │
│ │ beginning of each time step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setProblemType(ptype) │ Set the type of problem to be solved. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonContext(context) │ Set the instance of the class │
│ │ implementing the required Python │
│ │ methods. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setPythonType(py_type) │ Set the fully qualified Python name │
│ │ of the class to be used. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSFunction(function[, f, args, │ Set the routine for evaluating the │
│ kargs]) │ function G in U_t = G(t, u). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSJacobian(jacobian[, J, P, args, │ Set the function to compute the │
│ kargs]) │ Jacobian of G in U_t = G(U, t). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSJacobianP(jacobianp[, A, args, │ Set the function that computes the │
│ kargs]) │ Jacobian with respect to the │
│ │ parameters. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSSplitIFunction(splitname, │ Set the split implicit functions. │
│ function[, ...]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSSplitIJacobian(splitname, │ Set the Jacobian for the split │
│ jacobian[, ...]) │ implicit function. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSSplitIS(splitname, iss) │ Set the index set for the specified │
│ │ split. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRHSSplitRHSFunction(splitname, │ Set the split right-hand-side │
│ function) │ functions. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRKType(ts_type) │ Set the type of the Runge-Kutta │
│ │ scheme. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSaveTrajectory() │ Enable to save solutions as an │
│ │ internal TS trajectory. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSolution(u) │ Set the initial solution vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSolution2(u, v) │ Set the initial solution and its time │
│ │ derivative. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStepLimits(hmin, hmax) │ Set the minimum and maximum allowed │
│ │ step sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setStepNumber(step_number) │ Set the number of steps completed. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTheta(theta) │ Set the abscissa of the stage in (0, │
│ │ 1] for Type.THETA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setThetaEndpoint([flag]) │ Set to use the endpoint variant of │
│ │ Type.THETA. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTime(t) │ Set the time. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTimeSpan(tspan) │ Set the time span. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTimeStep(time_step) │ Set the duration of the timestep. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setTolerances([rtol, atol]) │ Set tolerances for local truncation │
│ │ error when using an adaptive │
│ │ controller. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(ts_type) │ Set the method to be used as the TS │
│ │ solver. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for the TS. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ solve([u]) │ Step the requested number of │
│ │ timesteps. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ step() │ Take one step. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Print the TS object. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌───────────────┬──────────────────────────────────────┐
│ appctx │ Application context. │
├───────────────┼──────────────────────────────────────┤
│ atol │ The absolute tolerance. │
├───────────────┼──────────────────────────────────────┤
│ converged │ Indicates the TS has converged. │
├───────────────┼──────────────────────────────────────┤
│ diverged │ Indicates the TS has stopped. │
├───────────────┼──────────────────────────────────────┤
│ dm │ The DM. │
├───────────────┼──────────────────────────────────────┤
│ equation_type │ The equation type. │
├───────────────┼──────────────────────────────────────┤
│ iterating │ Indicates the TS is still iterating. │
├───────────────┼──────────────────────────────────────┤
│ ksp │ The KSP. │
├───────────────┼──────────────────────────────────────┤
│ max_steps │ The maximum number of steps. │
├───────────────┼──────────────────────────────────────┤
│ max_time │ The maximum time. │
├───────────────┼──────────────────────────────────────┤
│ problem_type │ The problem type. │
├───────────────┼──────────────────────────────────────┤
│ reason │ The converged reason. │
├───────────────┼──────────────────────────────────────┤
│ rtol │ The relative tolerance. │
├───────────────┼──────────────────────────────────────┤
│ snes │ The SNES. │
├───────────────┼──────────────────────────────────────┤
│ step_number │ The current step number. │
├───────────────┼──────────────────────────────────────┤
│ time │ The current time. │
├───────────────┼──────────────────────────────────────┤
│ time_step │ The current time step size. │
├───────────────┼──────────────────────────────────────┤
│ vec_sol │ The solution vector. │
└───────────────┴──────────────────────────────────────┘
Methods Documentation
adjointReset()
Reset a TS, removing any allocated vectors and matrices.
Collective.
SEE ALSO:
TSAdjointReset
Source code at petsc4py/PETSc/TS.pyx:2849
Return type
None
adjointSetSteps(adjoint_steps)
Set the number of steps the adjoint solver should take backward in time.
Logically collective.
Parameters
adjoint_steps (int) -- The number of steps to take.
Return type
None
SEE ALSO:
TSAdjointSetSteps
Source code at petsc4py/PETSc/TS.pyx:2795
adjointSetUp()
Set up the internal data structures for the later use of an adjoint solver.
Collective.
SEE ALSO:
TSAdjointSetUp
Source code at petsc4py/PETSc/TS.pyx:2813
Return type
None
adjointSolve()
Solve the discrete adjoint problem for an ODE/DAE.
Collective.
SEE ALSO:
TSAdjointSolve
Source code at petsc4py/PETSc/TS.pyx:2825
Return type
None
adjointStep()
Step one time step backward in the adjoint run.
Collective.
SEE ALSO:
TSAdjointStep
Source code at petsc4py/PETSc/TS.pyx:2837
Return type
None
appendOptionsPrefix(prefix)
Append to the prefix used for all the TS options.
Logically collective.
Parameters
prefix (str | None) -- The prefix to append to the current prefix.
Return type
None
Notes
A hyphen must not be given at the beginning of the prefix name.
SEE ALSO:
Working with PETSc options, TSAppendOptionsPrefix
Source code at petsc4py/PETSc/TS.pyx:539
clone()
Return a shallow clone of the TS object.
Collective.
SEE ALSO:
TSClone
Source code at petsc4py/PETSc/TS.pyx:243
Return type
TS
computeI2Function(t, x, xdot, xdotdot, f)
Evaluate the DAE residual in implicit form.
Collective.
Parameters
• t (float) -- The current time.
• x (Vec) -- The state vector.
• xdot (Vec) -- The time derivative of the state vector.
• xdotdot (Vec) -- The second time derivative of the state vector.
• f (Vec) -- The vector into which the residual is stored.
Return type
None
SEE ALSO:
TSComputeI2Function
Source code at petsc4py/PETSc/TS.pyx:1142
computeI2Jacobian(t, x, xdot, xdotdot, v, a, J, P=None)
Evaluate the Jacobian of the DAE.
Collective.
If F(t, U, V, A)=0 is the DAE, the required Jacobian is dF/dU + v dF/dV + a dF/dA.
Parameters
• t (float) -- The current time.
• x (Vec) -- The state vector.
• xdot (Vec) -- The time derivative of the state vector.
• xdotdot (Vec) -- The second time derivative of the state vector.
• v (float) -- The shift to apply to the first derivative.
• a (float) -- The shift to apply to the second derivative.
• J (Mat) -- The matrix into which the Jacobian is computed.
• P (Mat | None) -- The optional matrix to use for building a preconditioner matrix.
Return type
None
SEE ALSO:
TSComputeI2Jacobian
Source code at petsc4py/PETSc/TS.pyx:1169
computeIFunction(t, x, xdot, f, imex=False)
Evaluate the DAE residual written in implicit form.
Collective.
Parameters
• t (float) -- The current time.
• x (Vec) -- The state vector.
• xdot (Vec) -- The time derivative of the state vector.
• f (Vec) -- The vector into which the residual is stored.
• imex (bool) -- A flag which indicates if the RHS should be kept separate.
Return type
None
SEE ALSO:
TSComputeIFunction
Source code at petsc4py/PETSc/TS.pyx:927
computeIJacobian(t, x, xdot, a, J, P=None, imex=False)
Evaluate the Jacobian of the DAE.
Collective.
If F(t, U, Udot)=0 is the DAE, the required Jacobian is dF/dU + shift*dF/dUdot
Parameters
• t (float) -- The current time.
• x (Vec) -- The state vector.
• xdot (Vec) -- The time derivative of the state vector.
• a (float) -- The shift to apply
• J (Mat) -- The matrix into which the Jacobian is computed.
• P (Mat | None) -- The optional matrix to use for building a preconditioner matrix.
• imex (bool) -- A flag which indicates if the RHS should be kept separate.
Return type
None
SEE ALSO:
TSComputeIJacobian
Source code at petsc4py/PETSc/TS.pyx:957
computeIJacobianP(t, x, xdot, a, J, imex=False)
Evaluate the Jacobian with respect to parameters.
Collective.
Parameters
• t (float) -- The current time.
• x (Vec) -- The state vector.
• xdot (Vec) -- The time derivative of the state vector.
• a (float) -- The shift to apply
• J (Mat) -- The matrix into which the Jacobian is computed.
• imex (bool) -- A flag which indicates if the RHS should be kept separate.
Return type
None
SEE ALSO:
TSComputeIJacobianP
Source code at petsc4py/PETSc/TS.pyx:997
computeRHSFunction(t, x, f)
Evaluate the right-hand side function.
Collective.
Parameters
• t (float) -- The time at which to evaluate the RHS.
• x (Vec) -- The state vector.
• f (Vec) -- The Vec into which the RHS is computed.
Return type
None
SEE ALSO:
TSComputeRHSFunction
Source code at petsc4py/PETSc/TS.pyx:674
computeRHSFunctionLinear(t, x, f)
Evaluate the right-hand side via the user-provided Jacobian.
Collective.
Parameters
• t (float) -- The time at which to evaluate the RHS.
• x (Vec) -- The state vector.
• f (Vec) -- The Vec into which the RHS is computed.
Return type
None
SEE ALSO:
TSComputeRHSFunctionLinear
Source code at petsc4py/PETSc/TS.pyx:696
computeRHSJacobian(t, x, J, P=None)
Compute the Jacobian matrix that has been set with setRHSJacobian.
Collective.
Parameters
• t (float) -- The time at which to evaluate the Jacobian.
• x (Vec) -- The state vector.
• J (Mat) -- The matrix into which the Jacobian is computed.
• P (Mat | None) -- The optional matrix to use for building a preconditioner matrix.
Return type
None
SEE ALSO:
TSComputeRHSJacobian
Source code at petsc4py/PETSc/TS.pyx:718
computeRHSJacobianConstant(t, x, J, P=None)
Reuse a Jacobian that is time-independent.
Collective.
Parameters
• t (float) -- The time at which to evaluate the Jacobian.
• x (Vec) -- The state vector.
• J (Mat) -- A pointer to the stored Jacobian.
• P (Mat | None) -- An optional pointer to the preconditioner matrix.
Return type
None
SEE ALSO:
TSComputeRHSJacobianConstant
Source code at petsc4py/PETSc/TS.pyx:744
computeRHSJacobianP(t, x, J)
Run the user-defined JacobianP function.
Collective.
Parameters
• t (float) -- The time at which to compute the Jacobian.
• x (Vec) -- The solution at which to compute the Jacobian.
• J (Mat) -- The output Jacobian matrix.
Return type
None
SEE ALSO:
TSComputeRHSJacobianP
Source code at petsc4py/PETSc/TS.pyx:2773
create(comm=None)
Create an empty TS.
Collective.
The problem type can then be set with setProblemType and the type of solver can then be set
with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
TSCreate
Source code at petsc4py/PETSc/TS.pyx:219
createPython(context=None, comm=None)
Create an integrator of Python type.
Collective.
Parameters
• context (Any) -- An instance of the Python class implementing the required
methods.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
PETSc Python ode-integrator type (TODO), setType, setPythonContext, Type.PYTHON
Source code at petsc4py/PETSc/TS.pyx:2863
createQuadratureTS(forward=True)
Create a sub TS that evaluates integrals over time.
Collective.
Parameters
forward (bool) -- Enable to evaluate forward in time.
Return type
TS
SEE ALSO:
TSCreateQuadratureTS
Source code at petsc4py/PETSc/TS.pyx:2692
destroy()
Destroy the TS that was created with create.
Collective.
SEE ALSO:
TSDestroy
Source code at petsc4py/PETSc/TS.pyx:206
Return type
Self
getARKIMEXType()
Return the Type.ARKIMEX scheme.
Not collective.
SEE ALSO:
TSARKIMEXGetType
Source code at petsc4py/PETSc/TS.pyx:389
Return type
str
getAlphaParams()
Return the algorithmic parameters for Type.ALPHA.
Not collective.
SEE ALSO:
TSAlphaGetParams
Source code at petsc4py/PETSc/TS.pyx:3070
Return type
tuple[float, float, float]
getAppCtx()
Return the application context.
Source code at petsc4py/PETSc/TS.pyx:589
Return type
Any
getConvergedReason()
Return the reason the TS step was stopped.
Not collective.
Can only be called once solve is complete.
SEE ALSO:
TSGetConvergedReason
Source code at petsc4py/PETSc/TS.pyx:2090
Return type
ConvergedReason
getCostGradients()
Return the cost gradients.
Not collective.
SEE ALSO:
setCostGradients, TSGetCostGradients
Source code at petsc4py/PETSc/TS.pyx:2634
Return type
tuple[list[Vec], list[Vec]]
getCostIntegral()
Return a vector of values of the integral term in the cost functions.
Not collective.
SEE ALSO:
TSGetCostIntegral
Source code at petsc4py/PETSc/TS.pyx:2573
Return type
Vec
getDIRKType()
Return the Type.DIRK scheme.
Not collective.
SEE ALSO:
setDIRKType, TSDIRKGetType
Source code at petsc4py/PETSc/TS.pyx:426
Return type
str
getDM()
Return the DM associated with the TS.
Not collective.
Only valid if nonlinear solvers or preconditioners are used which use the DM.
SEE ALSO:
TSGetDM
Source code at petsc4py/PETSc/TS.pyx:1589
Return type
DM
getEquationType()
Get the type of the equation that TS is solving.
Not collective.
SEE ALSO:
TSGetEquationType
Source code at petsc4py/PETSc/TS.pyx:488
Return type
EquationType
getI2Function()
Return the vector and function which computes the residual.
Not collective.
SEE ALSO:
TSGetI2Function
Source code at petsc4py/PETSc/TS.pyx:1218
Return type
tuple[Vec, TSI2Function]
getI2Jacobian()
Return the matrices and function which computes the Jacobian.
Not collective.
SEE ALSO:
TSGetI2Jacobian
Source code at petsc4py/PETSc/TS.pyx:1234
Return type
tuple[Mat, Mat, TSI2Jacobian]
getIFunction()
Return the vector and function which computes the implicit residual.
Not collective.
SEE ALSO:
TSGetIFunction
Source code at petsc4py/PETSc/TS.pyx:1031
Return type
tuple[Vec, TSIFunction]
getIJacobian()
Return the matrices and function which computes the implicit Jacobian.
Not collective.
SEE ALSO:
TSGetIJacobian
Source code at petsc4py/PETSc/TS.pyx:1047
Return type
tuple[Mat, Mat, TSIJacobian]
getKSP()
Return the KSP associated with the TS.
Not collective.
SEE ALSO:
TSGetKSP
Source code at petsc4py/PETSc/TS.pyx:1572
Return type
KSP
getKSPIterations()
Return the total number of linear iterations used by the TS.
Not collective.
This counter is reset to zero for each successive call to solve.
SEE ALSO:
TSGetKSPIterations
Source code at petsc4py/PETSc/TS.pyx:1857
Return type
int
getMaxSteps()
Return the maximum number of steps to use.
Not collective.
SEE ALSO:
TSGetMaxSteps
Source code at petsc4py/PETSc/TS.pyx:1826
Return type
int
getMaxTime()
Return the maximum (final) time.
Not collective.
Defaults to 5.
SEE ALSO:
TSGetMaxTime
Source code at petsc4py/PETSc/TS.pyx:1790
Return type
float
getMonitor()
Return the monitor.
Not collective.
SEE ALSO:
setMonitor
Source code at petsc4py/PETSc/TS.pyx:2142
Return type
list[tuple[TSMonitorFunction, tuple[Any, ...], dict[str, Any]]]
getNumEvents()
Return the number of events.
Logically collective.
SEE ALSO:
TSGetNumEvents
Source code at petsc4py/PETSc/TS.pyx:2289
Return type
int
getOptionsPrefix()
Return the prefix used for all the TS options.
Not collective.
SEE ALSO:
TSGetOptionsPrefix
Source code at petsc4py/PETSc/TS.pyx:525
Return type
str
getPostStep()
Return the poststep function.
Source code at petsc4py/PETSc/TS.pyx:2382
Return type
tuple[TSPostStepFunction, tuple[Any, ...] | None, dict[str, Any] | None]
getPreStep()
Return the prestep function.
Not collective.
SEE ALSO:
setPreStep
Source code at petsc4py/PETSc/TS.pyx:2338
Return type
tuple[TSPreStepFunction, tuple[Any, ...] | None, dict[str, Any] | None]
getPrevTime()
Return the starting time of the previously completed step.
Not collective.
SEE ALSO:
TSGetPrevTime
Source code at petsc4py/PETSc/TS.pyx:1664
Return type
float
getProblemType()
Return the type of problem to be solved.
Not collective.
SEE ALSO:
TSGetProblemType
Source code at petsc4py/PETSc/TS.pyx:457
Return type
ProblemType
getPythonContext()
Return the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python ode-integrator type (TODO), setPythonContext
Source code at petsc4py/PETSc/TS.pyx:2900
Return type
Any
getPythonType()
Return the fully qualified Python name of the class used by the solver.
Not collective.
SEE ALSO:
PETSc Python ode-integrator type (TODO), setPythonContext, setPythonType, ‐
TSPythonGetType
Source code at petsc4py/PETSc/TS.pyx:2929
Return type
str
getQuadratureTS()
Return the sub TS that evaluates integrals over time.
Not collective.
Returns
• forward (bool) -- True if evaluating the integral forward in time
• qts (TS) -- The sub TS
Return type
tuple[bool, TS]
SEE ALSO:
TSGetQuadratureTS
Source code at petsc4py/PETSc/TS.pyx:2713
getRHSFunction()
Return the vector where the rhs is stored and the function used to compute it.
Not collective.
SEE ALSO:
TSGetRHSFunction
Source code at petsc4py/PETSc/TS.pyx:770
Return type
tuple[Vec, TSRHSFunction]
getRHSJacobian()
Return the Jacobian and the function used to compute them.
Not collective.
SEE ALSO:
TSGetRHSJacobian
Source code at petsc4py/PETSc/TS.pyx:786
Return type
tuple[Mat, Mat, TSRHSJacobian]
getRKType()
Return the Type.RK scheme.
Not collective.
SEE ALSO:
TSRKGetType
Source code at petsc4py/PETSc/TS.pyx:375
Return type
str
getSNES()
Return the SNES associated with the TS.
Not collective.
SEE ALSO:
TSGetSNES
Source code at petsc4py/PETSc/TS.pyx:1557
Return type
SNES
getSNESFailures()
Return the total number of failed SNES solves in the TS.
Not collective.
This counter is reset to zero for each successive call to solve.
SEE ALSO:
TSGetSNESFailures
Source code at petsc4py/PETSc/TS.pyx:1931
Return type
int
getSNESIterations()
Return the total number of nonlinear iterations used by the TS.
Not collective.
This counter is reset to zero for each successive call to solve.
SEE ALSO:
TSGetSNESIterations
Source code at petsc4py/PETSc/TS.pyx:1840
Return type
int
getSolution()
Return the solution at the present timestep.
Not collective.
It is valid to call this routine inside the function that you are evaluating in order to
move to the new timestep. This vector is not changed until the solution at the next
timestep has been calculated.
SEE ALSO:
TSGetSolution
Source code at petsc4py/PETSc/TS.pyx:1428
Return type
Vec
getSolution2()
Return the solution and time derivative at the present timestep.
Not collective.
It is valid to call this routine inside the function that you are evaluating in order to
move to the new timestep. These vectors are not changed until the solution at the next
timestep has been calculated.
SEE ALSO:
TS2GetSolution
Source code at petsc4py/PETSc/TS.pyx:1466
Return type
tuple[Vec, Vec]
getSolveTime()
Return the time after a call to solve.
Not collective.
This time corresponds to the final time set with setMaxTime.
SEE ALSO:
TSGetSolveTime
Source code at petsc4py/PETSc/TS.pyx:1678
Return type
float
getStepLimits()
Return the minimum and maximum allowed time step sizes.
Not collective.
SEE ALSO:
TSAdaptGetStepLimits
Source code at petsc4py/PETSc/TS.pyx:2523
Return type
tuple[float, float]
getStepNumber()
Return the number of time steps completed.
Not collective.
SEE ALSO:
TSGetStepNumber
Source code at petsc4py/PETSc/TS.pyx:1754
Return type
int
getStepRejections()
Return the total number of rejected steps.
Not collective.
This counter is reset to zero for each successive call to solve.
SEE ALSO:
TSGetStepRejections
Source code at petsc4py/PETSc/TS.pyx:1896
Return type
int
getTheta()
Return the abscissa of the stage in (0, 1] for Type.THETA.
Not collective.
SEE ALSO:
TSThetaGetTheta
Source code at petsc4py/PETSc/TS.pyx:2967
Return type
float
getThetaEndpoint()
Return whether the endpoint variable of Type.THETA is used.
Not collective.
SEE ALSO:
TSThetaGetEndpoint
Source code at petsc4py/PETSc/TS.pyx:2999
Return type
bool
getTime()
Return the time of the most recently completed step.
Not collective.
When called during time step evaluation (e.g. during residual evaluation or via hooks set
using setPreStep or setPostStep), the time returned is at the start of the step.
SEE ALSO:
TSGetTime
Source code at petsc4py/PETSc/TS.pyx:1646
Return type
float
getTimeSpan()
Return the time span.
Not collective.
SEE ALSO:
TSGetTimeSpan
Source code at petsc4py/PETSc/TS.pyx:1521
Return type
ArrayReal
getTimeSpanSolutions()
Return the solutions at the times in the time span.
Not collective.
SEE ALSO:
setTimeSpan, TSGetTimeSpanSolutions
Source code at petsc4py/PETSc/TS.pyx:1537
Return type
list[Vec]
getTimeStep()
Return the duration of the current timestep.
Not collective.
SEE ALSO:
TSGetTimeStep
Source code at petsc4py/PETSc/TS.pyx:1713
Return type
float
getTolerances()
Return the tolerances for local truncation error.
Logically collective.
Returns
• rtol (float) -- the relative tolerance
• atol (float) -- the absolute tolerance
Return type
tuple[float, float]
SEE ALSO:
TSGetTolerances
Source code at petsc4py/PETSc/TS.pyx:2013
getType()
Return the TS type.
Not collective.
SEE ALSO:
TSGetType
Source code at petsc4py/PETSc/TS.pyx:361
Return type
str
interpolate(t, u)
Interpolate the solution to a given time.
Collective.
Parameters
• t (float) -- The time to interpolate.
• u (Vec) -- The state vector to interpolate.
Return type
None
SEE ALSO:
TSInterpolate
Source code at petsc4py/PETSc/TS.pyx:2480
load(viewer)
Load a TS that has been stored in binary with view.
Collective.
Parameters
viewer (Viewer) -- The visualization context.
Return type
None
SEE ALSO:
TSLoad
Source code at petsc4py/PETSc/TS.pyx:189
monitor(step, time, u=None)
Monitor the solve.
Collective.
Parameters
• step (int) -- The step number that has just completed.
• time (float) -- The model time of the state.
• u (Vec | None) -- The state at the current model time.
Return type
None
SEE ALSO:
TSMonitor
Source code at petsc4py/PETSc/TS.pyx:2169
monitorCancel()
Clear all the monitors that have been set.
Logically collective.
SEE ALSO:
TSMonitorCancel
Source code at petsc4py/PETSc/TS.pyx:2154
Return type
None
removeTrajectory()
Remove the internal TS trajectory object.
Collective.
SEE ALSO:
TSRemoveTrajectory
Source code at petsc4py/PETSc/TS.pyx:2561
Return type
None
reset()
Reset the TS, removing any allocated vectors and matrices.
Collective.
SEE ALSO:
TSReset
Source code at petsc4py/PETSc/TS.pyx:2398
Return type
None
restartStep()
Flag the solver to restart the next step.
Collective.
Multistep methods like TSBDF or Runge-Kutta methods with FSAL property require restarting
the solver in the event of discontinuities. These discontinuities may be introduced as a
consequence of explicitly modifications to the solution vector (which PETSc attempts to
detect and handle) or problem coefficients (which PETSc is not able to detect). For the
sake of correctness and maximum safety, users are expected to call TSRestart() whenever
they introduce discontinuities in callback routines (e.g. prestep and poststep routines, or
implicit/rhs function routines with discontinuous source terms).
SEE ALSO:
TSRestartStep
Source code at petsc4py/PETSc/TS.pyx:2426
Return type
None
rollBack()
Roll back one time step.
Collective.
SEE ALSO:
TSRollBack
Source code at petsc4py/PETSc/TS.pyx:2449
Return type
None
setARKIMEXFastSlowSplit(flag)
Use ARKIMEX for solving a fast-slow system.
Logically collective.
Parameters
flag (bool) -- Set to True for fast-slow partitioned systems.
Return type
None
SEE ALSO:
TSARKIMEXSetType
Source code at petsc4py/PETSc/TS.pyx:344
setARKIMEXFullyImplicit(flag)
Solve both parts of the equation implicitly.
Logically collective.
Parameters
flag (bool) -- Set to True for fully implicit.
Return type
None
SEE ALSO:
TSARKIMEXSetFullyImplicit
Source code at petsc4py/PETSc/TS.pyx:326
setARKIMEXType(ts_type)
Set the type of Type.ARKIMEX scheme.
Logically collective.
Parameters
ts_type (ARKIMEXType | str) -- The type of Type.ARKIMEX scheme.
Return type
None
Notes
-ts_arkimex_type sets scheme type from the commandline.
SEE ALSO:
TSARKIMEXSetType
Source code at petsc4py/PETSc/TS.pyx:303
setAlphaParams(alpha_m=None, alpha_f=None, gamma=None)
Set the algorithmic parameters for Type.ALPHA.
Logically collective.
Users should call setAlphaRadius.
Parameters
• alpha_m (float | None) -- Parameter, leave None to keep current value.
• alpha_f (float | None) -- Parameter, leave None to keep current value.
• gamma (float | None) -- Parameter, leave None to keep current value.
Return type
None
SEE ALSO:
TSAlphaSetParams
Source code at petsc4py/PETSc/TS.pyx:3037
setAlphaRadius(radius)
Set the spectral radius for Type.ALPHA.
Logically collective.
Parameters
radius (float) -- the spectral radius
Return type
None
Notes
-ts_alpha_radius can be used to set this from the commandline.
SEE ALSO:
TSAlphaSetRadius
Source code at petsc4py/PETSc/TS.pyx:3015
setAppCtx(appctx)
Set the application context.
Not collective.
Parameters
appctx (Any) -- The application context.
Return type
None
Source code at petsc4py/PETSc/TS.pyx:576
setConvergedReason(reason)
Set the reason for handling the convergence of solve.
Logically collective.
Can only be called when solve is active and reason must contain common value.
Parameters
reason (ConvergedReason) -- The reason for convergence.
Return type
None
SEE ALSO:
TSSetConvergedReason
Source code at petsc4py/PETSc/TS.pyx:2069
setCostGradients(vl, vm=None)
Set the cost gradients.
Logically collective.
Parameters
• vl (Vec | Sequence[Vec] | None) -- gradients with respect to the initial condition
variables, the dimension and parallel layout of these vectors is the same as the
ODE solution vector
• vm (Vec | Sequence[Vec] | None) -- gradients with respect to the parameters, the
number of entries in these vectors is the same as the number of parameters
Return type
None
SEE ALSO:
TSSetCostGradients
Source code at petsc4py/PETSc/TS.pyx:2588
setDIRKType(ts_type)
Set the type of Type.DIRK scheme.
Logically collective.
Parameters
ts_type (DIRKType | str) -- The type of Type.DIRK scheme.
Return type
None
Notes
-ts_dirk_type sets scheme type from the commandline.
SEE ALSO:
TSDIRKSetType
Source code at petsc4py/PETSc/TS.pyx:403
setDM(dm)
Set the DM that may be used by some nonlinear solvers or preconditioners.
Logically collective.
Parameters
dm (DM) -- The DM object.
Return type
None
SEE ALSO:
TSSetDM
Source code at petsc4py/PETSc/TS.pyx:1609
setEquationType(eqtype)
Set the type of the equation that TS is solving.
Logically collective.
Parameters
eqtype (EquationType) -- The type of equation.
Return type
None
SEE ALSO:
TSSetEquationType
Source code at petsc4py/PETSc/TS.pyx:471
setErrorIfStepFails(flag=True)
Immediately error is no step succeeds.
Not collective.
Parameters
flag (bool) -- Enable to error if no step succeeds.
Return type
None
Notes
-ts_error_if_step_fails to enable from the commandline.
SEE ALSO:
TSSetErrorIfStepFails
Source code at petsc4py/PETSc/TS.pyx:1948
setEventHandler(direction, terminate, indicator, postevent=None, args=None, kargs=None)
Set a function used for detecting events.
Logically collective.
Parameters
• direction (Sequence[int]) -- Direction of zero crossing to be detected {-1, 0,
+1}.
• terminate (Sequence[bool]) -- Flags for each event to indicate stepping should be
terminated.
• indicator (TSIndicatorFunction | None) -- Function for defining the
indicator-functions marking the events
• postevent (TSPostEventFunction) -- Function to execute after the event
• args (tuple[Any, ...] | None) -- Additional positional arguments for indicator.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for indicator.
Return type
None
SEE ALSO:
TSSetEventHandler
Source code at petsc4py/PETSc/TS.pyx:2198
setEventTolerances(tol=None, vtol=None)
Set tolerances for event zero crossings when using event handler.
Logically collective.
setEventHandler must have already been called.
Parameters
• tol (float) -- The scalar tolerance or None to leave at the current value
• vtol (Sequence[float]) -- A sequence of scalar tolerance for each event. Used in
preference to tol if present. Set to None to leave at the current value.
Return type
None
Notes
-ts_event_tol can be used to set values from the commandline.
SEE ALSO:
TSSetEventTolerances
Source code at petsc4py/PETSc/TS.pyx:2253
setExactFinalTime(option)
Set method of computing the final time step.
Logically collective.
Parameters
option (ExactFinalTime) -- The exact final time option
Return type
None
Notes
-ts_exact_final_time may be used to specify from the commandline.
SEE ALSO:
TSSetExactFinalTime
Source code at petsc4py/PETSc/TS.pyx:2047
setFromOptions()
Set various TS parameters from user options.
Collective.
SEE ALSO:
Working with PETSc options, TSSetFromOptions
Source code at petsc4py/PETSc/TS.pyx:562
Return type
None
setI2Function(function, f=None, args=None, kargs=None)
Set the function to compute the 2nd order DAE.
Logically collective.
Parameters
• function (TSI2Function | None) -- The right-hand side function.
• f (Vec | None) -- The vector to store values or None to be created internally.
• args (tuple[Any, ...] | None) -- Additional positional arguments for function.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for function.
Return type
None
SEE ALSO:
TSSetI2Function
Source code at petsc4py/PETSc/TS.pyx:1063
setI2Jacobian(jacobian, J=None, P=None, args=None, kargs=None)
Set the function to compute the Jacobian of the 2nd order DAE.
Logically collective.
Parameters
• jacobian (TSI2Jacobian | None) -- The function which computes the Jacobian.
• J (Mat | None) -- The matrix into which the Jacobian is computed.
• P (Mat | None) -- The optional matrix to use for building a preconditioner matrix.
• args -- Additional positional arguments for jacobian.
• kargs -- Additional keyword arguments for jacobian.
Return type
None
SEE ALSO:
TSSetI2Jacobian
Source code at petsc4py/PETSc/TS.pyx:1100
setIFunction(function, f=None, args=None, kargs=None)
Set the function representing the DAE to be solved.
Logically collective.
Parameters
• function (TSIFunction | None) -- The right-hand side function.
• f (Vec | None) -- The vector to store values or None to be created internally.
• args (tuple[Any, ...] | None) -- Additional positional arguments for function.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for function.
Return type
None
SEE ALSO:
TSSetIFunction
Source code at petsc4py/PETSc/TS.pyx:804
setIJacobian(jacobian, J=None, P=None, args=None, kargs=None)
Set the function to compute the Jacobian.
Logically collective.
Set the function to compute the matrix dF/dU + a*dF/dU_t where F(t, U, U_t) is the function
provided with setIFunction.
Parameters
• jacobian (TSIJacobian | None) -- The function which computes the Jacobian.
• J (Mat | None) -- The matrix into which the Jacobian is computed.
• P (Mat | None) -- The optional matrix to use for building a preconditioner matrix.
• args (tuple[Any, ...] | None) -- Additional positional arguments for jacobian.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for jacobian.
Return type
None
SEE ALSO:
TSSetIJacobian
Source code at petsc4py/PETSc/TS.pyx:841
setIJacobianP(jacobian, J=None, args=None, kargs=None)
Set the function that computes the Jacobian.
Logically collective.
Set the function that computes the Jacobian of F with respect to the parameters P where
F(Udot, U, t) = G(U, P, t), as well as the location to store the matrix.
Parameters
• jacobian -- The function which computes the Jacobian.
• J (Mat | None) -- The matrix into which the Jacobian is computed.
• args (tuple[Any, ...] | None) -- Additional positional arguments for jacobian.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for jacobian.
Return type
None
SEE ALSO:
TSSetIJacobianP
Source code at petsc4py/PETSc/TS.pyx:886
setMaxSNESFailures(n)
Set the maximum number of SNES solves failures allowed.
Not collective.
Parameters
n (int) -- The maximum number of failed nonlinear solver, use -1 for unlimited.
Return type
None
SEE ALSO:
TSSetMaxSNESFailures
Source code at petsc4py/PETSc/TS.pyx:1913
setMaxStepRejections(n)
Set the maximum number of step rejections before a time step fails.
Not collective.
Parameters
n (int) -- The maximum number of rejected steps, use -1 for unlimited.
Return type
None
Notes
-ts_max_reject can be used to set this from the commandline
SEE ALSO:
TSSetMaxStepRejections
Source code at petsc4py/PETSc/TS.pyx:1874
setMaxSteps(max_steps)
Set the maximum number of steps to use.
Logically collective.
Defaults to 5000.
Parameters
max_steps (int) -- The maximum number of steps to use.
Return type
None
SEE ALSO:
TSSetMaxSteps
Source code at petsc4py/PETSc/TS.pyx:1806
setMaxTime(max_time)
Set the maximum (final) time.
Logically collective.
Parameters
max_time (float) -- the final time
Return type
None
Notes
-ts_max_time sets the max time from the commandline
SEE ALSO:
TSSetMaxTime
Source code at petsc4py/PETSc/TS.pyx:1768
setMonitor(monitor, args=None, kargs=None)
Set an additional monitor to the TS.
Logically collective.
Parameters
• monitor (TSMonitorFunction | None) -- The custom monitor function.
• args (tuple[Any, ...] | None) -- Additional positional arguments for monitor.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for monitor.
Return type
None
SEE ALSO:
TSMonitorSet
Source code at petsc4py/PETSc/TS.pyx:2108
setOptionsPrefix(prefix)
Set the prefix used for all the TS options.
Logically collective.
Parameters
prefix (str | None) -- The prefix to prepend to all option names.
Return type
None
Notes
A hyphen must not be given at the beginning of the prefix name.
SEE ALSO:
Working with PETSc options, TSSetOptionsPrefix
Source code at petsc4py/PETSc/TS.pyx:502
setPostStep(poststep, args=None, kargs=None)
Set a function to be called at the end of each time step.
Logically collective.
Parameters
• poststep (TSPostStepFunction | None) -- The function to be called at the end of
each step.
• args (tuple[Any, ...] | None) -- Additional positional arguments for poststep.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for poststep.
Return type
None
SEE ALSO:
TSSetPostStep
Source code at petsc4py/PETSc/TS.pyx:2350
setPreStep(prestep, args=None, kargs=None)
Set a function to be called at the beginning of each time step.
Logically collective.
Parameters
• prestep (TSPreStepFunction | None) -- The function to be called at the beginning
of each step.
• args (tuple[Any, ...] | None) -- Additional positional arguments for prestep.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for prestep.
Return type
None
SEE ALSO:
TSSetPreStep
Source code at petsc4py/PETSc/TS.pyx:2305
setProblemType(ptype)
Set the type of problem to be solved.
Logically collective.
Parameters
ptype (ProblemType) -- The type of problem of the forms.
Return type
None
SEE ALSO:
TSSetProblemType
Source code at petsc4py/PETSc/TS.pyx:440
setPythonContext(context)
Set the instance of the class implementing the required Python methods.
Not collective.
SEE ALSO:
PETSc Python ode-integrator type (TODO), getPythonContext
Source code at petsc4py/PETSc/TS.pyx:2888
Parameters
context (Any)
Return type
None
setPythonType(py_type)
Set the fully qualified Python name of the class to be used.
Collective.
SEE ALSO:
PETSc Python ode-integrator type (TODO), setPythonContext, getPythonType, ‐
TSPythonSetType
Source code at petsc4py/PETSc/TS.pyx:2915
Parameters
py_type (str)
Return type
None
setRHSFunction(function, f=None, args=None, kargs=None)
Set the routine for evaluating the function G in U_t = G(t, u).
Logically collective.
Parameters
• function (TSRHSFunction | None) -- The right-hand side function.
• f (Vec | None) -- The vector into which the right-hand side is computed.
• args (tuple[Any, ...] | None) -- Additional positional arguments for function.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for function.
Return type
None
SEE ALSO:
TSSetRHSFunction
Source code at petsc4py/PETSc/TS.pyx:595
setRHSJacobian(jacobian, J=None, P=None, args=None, kargs=None)
Set the function to compute the Jacobian of G in U_t = G(U, t).
Logically collective.
Parameters
• jacobian (TSRHSJacobian | None) -- The right-hand side function.
• J (Mat | None) -- The matrix into which the jacobian is computed.
• P (Mat | None) -- The matrix into which the preconditioner is computed.
• args (tuple[Any, ...] | None) -- Additional positional arguments for jacobian.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for jacobian.
Return type
None
SEE ALSO:
TSSetRHSJacobian
Source code at petsc4py/PETSc/TS.pyx:632
setRHSJacobianP(jacobianp, A=None, args=None, kargs=None)
Set the function that computes the Jacobian with respect to the parameters.
Logically collective.
Parameters
• jacobianp (TSRHSJacobianP | None) -- The user-defined function.
• A (Mat | None) -- The matrix into which the Jacobian will be computed.
• args (tuple[Any, ...] | None) -- Additional positional arguments for jacobianp.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for jacobianp.
Return type
None
SEE ALSO:
TSSetRHSJacobianP
Source code at petsc4py/PETSc/TS.pyx:2655
setRHSSplitIFunction(splitname, function, r=None, args=None, kargs=None)
Set the split implicit functions.
Logically collective.
Parameters
• splitname (str) -- Name of the split.
• function (TSIFunction) -- The implicit function evaluation routine.
• r (Vec | None) -- Vector to hold the residual.
• args (tuple[Any, ...] | None) -- Additional positional arguments for function.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for function.
Return type
None
SEE ALSO:
TSRHSSplitSetIFunction
Source code at petsc4py/PETSc/TS.pyx:1316
setRHSSplitIJacobian(splitname, jacobian, J=None, P=None, args=None, kargs=None)
Set the Jacobian for the split implicit function.
Logically collective.
Parameters
• splitname (str) -- Name of the split.
• jacobian (TSRHSJacobian) -- The Jacobian evaluation routine.
• J (Mat | None) -- Matrix to store Jacobian entries computed by jacobian.
• P (Mat | None) -- Matrix used to compute preconditioner (usually the same as J).
• args (tuple[Any, ...] | None) -- Additional positional arguments for jacobian.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for jacobian.
Return type
None
SEE ALSO:
TSRHSSplitSetIJacobian
Source code at petsc4py/PETSc/TS.pyx:1360
setRHSSplitIS(splitname, iss)
Set the index set for the specified split.
Logically collective.
Parameters
• splitname (str) -- Name of this split, if None the number of the split is used.
• iss (IS) -- The index set for part of the solution vector.
Return type
None
SEE ALSO:
TSRHSSplitSetIS
Source code at petsc4py/PETSc/TS.pyx:1251
setRHSSplitRHSFunction(splitname, function, r=None, args=None, kargs=None)
Set the split right-hand-side functions.
Logically collective.
Parameters
• splitname (str) -- Name of the split.
• function (TSRHSFunction) -- The RHS function evaluation routine.
• r (Vec | None) -- Vector to hold the residual.
• args (tuple[Any, ...] | None) -- Additional positional arguments for function.
• kargs (dict[str, Any] | None) -- Additional keyword arguments for function.
Return type
None
SEE ALSO:
TSRHSSplitSetRHSFunction
Source code at petsc4py/PETSc/TS.pyx:1272
setRKType(ts_type)
Set the type of the Runge-Kutta scheme.
Logically collective.
Parameters
ts_type (RKType | str) -- The type of scheme.
Return type
None
Notes
-ts_rk_type sets scheme type from the commandline.
SEE ALSO:
TSRKSetType
Source code at petsc4py/PETSc/TS.pyx:280
setSaveTrajectory()
Enable to save solutions as an internal TS trajectory.
Collective.
This routine should be called after all TS options have been set.
Notes
-ts_save_trajectory can be used to save a trajectory to a file.
SEE ALSO:
TSSetSaveTrajectory
Source code at petsc4py/PETSc/TS.pyx:2542
Return type
None
setSolution(u)
Set the initial solution vector.
Logically collective.
Parameters
u (Vec) -- The solution vector.
Return type
None
SEE ALSO:
TSSetSolution
Source code at petsc4py/PETSc/TS.pyx:1411
setSolution2(u, v)
Set the initial solution and its time derivative.
Logically collective.
Parameters
• u (Vec) -- The solution vector.
• v (Vec) -- The time derivative vector.
Return type
None
SEE ALSO:
TS2SetSolution
Source code at petsc4py/PETSc/TS.pyx:1447
setStepLimits(hmin, hmax)
Set the minimum and maximum allowed step sizes.
Logically collective.
Parameters
• hmin (float) -- the minimum step size
• hmax (float) -- the maximum step size
Return type
None
SEE ALSO:
TSAdaptSetStepLimits
Source code at petsc4py/PETSc/TS.pyx:2500
setStepNumber(step_number)
Set the number of steps completed.
Logically collective.
For most uses of the TS solvers the user need not explicitly call setStepNumber, as the
step counter is appropriately updated in solve/step/rollBack. Power users may call this
routine to reinitialize timestepping by setting the step counter to zero (and time to the
initial time) to solve a similar problem with different initial conditions or parameters.
It may also be used to continue timestepping from a previously interrupted run in such a
way that TS monitors will be called with a initial nonzero step counter.
Parameters
step_number (int) -- the number of steps completed
Return type
None
SEE ALSO:
TSSetStepNumber
Source code at petsc4py/PETSc/TS.pyx:1727
setTheta(theta)
Set the abscissa of the stage in (0, 1] for Type.THETA.
Logically collective.
Parameters
theta (float) -- stage abscissa
Return type
None
Notes
-ts_theta_theta can be used to set a value from the commandline.
SEE ALSO:
TSThetaSetTheta
Source code at petsc4py/PETSc/TS.pyx:2945
setThetaEndpoint(flag=True)
Set to use the endpoint variant of Type.THETA.
Logically collective.
Parameters
flag -- Enable to use the endpoint variant.
Return type
None
SEE ALSO:
TSThetaSetEndpoint
Source code at petsc4py/PETSc/TS.pyx:2981
setTime(t)
Set the time.
Logically collective.
Parameters
t (float) -- The time.
Return type
None
SEE ALSO:
TSSetTime
Source code at petsc4py/PETSc/TS.pyx:1628
setTimeSpan(tspan)
Set the time span.
Collective.
The solution will be computed and stored for each time requested in the span. The times
must be all increasing and correspond to the intermediate points for time integration.
ExactFinalTime.MATCHSTEP must be used to make the last time step in each sub-interval match
the intermediate points specified. The intermediate solutions are saved in a vector array
that can be accessed with getTimeSpanSolutions.
Parameters
tspan (Sequence[float]) -- The sequence of time points.
Return type
None
Notes
-ts_time_span <t0, ..., tf> sets the time span from the commandline
SEE ALSO:
TSSetTimeSpan
Source code at petsc4py/PETSc/TS.pyx:1489
setTimeStep(time_step)
Set the duration of the timestep.
Logically collective.
Parameters
time_step (float) -- the duration of the timestep
Return type
None
SEE ALSO:
TSSetTimeStep
Source code at petsc4py/PETSc/TS.pyx:1695
setTolerances(rtol=None, atol=None)
Set tolerances for local truncation error when using an adaptive controller.
Logically collective.
Parameters
• rtol (float) -- The relative tolerance, DETERMINE to use the value when the
object's type was set, or None to leave the current value.
• atol (float) -- The absolute tolerance, DETERMINE to use the value when the
object's type was set, or None to leave the current value.
Return type
None
Notes
-ts_rtol and -ts_atol may be used to set values from the commandline.
SEE ALSO:
TSSetTolerances
Source code at petsc4py/PETSc/TS.pyx:1970
setType(ts_type)
Set the method to be used as the TS solver.
Collective.
Parameters
ts_type (Type | str) -- The solver type.
Return type
None
Notes
-ts_type sets the method from the commandline
SEE ALSO:
TSSetType
Source code at petsc4py/PETSc/TS.pyx:257
setUp()
Set up the internal data structures for the TS.
Collective.
SEE ALSO:
TSSetUp
Source code at petsc4py/PETSc/TS.pyx:2386
Return type
None
solve(u=None)
Step the requested number of timesteps.
Collective.
Parameters
u (Vec | None) -- The solution vector. Can be None.
Return type
None
SEE ALSO:
TSSolve
Source code at petsc4py/PETSc/TS.pyx:2461
step() Take one step.
Collective.
The preferred interface for the TS solvers is solve. If you need to execute code at the
beginning or ending of each step, use setPreStep and setPostStep respectively.
SEE ALSO:
TSStep
Source code at petsc4py/PETSc/TS.pyx:2410
Return type
None
view(viewer=None)
Print the TS object.
Collective.
Parameters
viewer (Viewer | None) -- The visualization context.
Return type
None
Notes
-ts_view calls TSView at the end of TSStep
SEE ALSO:
TSView
Source code at petsc4py/PETSc/TS.pyx:166
Attributes Documentation
appctx Application context.
Source code at petsc4py/PETSc/TS.pyx:3086
atol The absolute tolerance.
Source code at petsc4py/PETSc/TS.pyx:3189
converged
Indicates the TS has converged.
Source code at petsc4py/PETSc/TS.pyx:3210
diverged
Indicates the TS has stopped.
Source code at petsc4py/PETSc/TS.pyx:3215
dm The DM.
Source code at petsc4py/PETSc/TS.pyx:3096
equation_type
The equation type.
Source code at petsc4py/PETSc/TS.pyx:3114
iterating
Indicates the TS is still iterating.
Source code at petsc4py/PETSc/TS.pyx:3205
ksp The KSP.
Source code at petsc4py/PETSc/TS.pyx:3127
max_steps
The maximum number of steps.
Source code at petsc4py/PETSc/TS.pyx:3171
max_time
The maximum time.
Source code at petsc4py/PETSc/TS.pyx:3163
problem_type
The problem type.
Source code at petsc4py/PETSc/TS.pyx:3106
reason The converged reason.
Source code at petsc4py/PETSc/TS.pyx:3197
rtol The relative tolerance.
Source code at petsc4py/PETSc/TS.pyx:3181
snes The SNES.
Source code at petsc4py/PETSc/TS.pyx:3122
step_number
The current step number.
Source code at petsc4py/PETSc/TS.pyx:3155
time The current time.
Source code at petsc4py/PETSc/TS.pyx:3139
time_step
The current time step size.
Source code at petsc4py/PETSc/TS.pyx:3147
vec_sol
The solution vector.
Source code at petsc4py/PETSc/TS.pyx:3132
petsc4py.PETSc.Vec
class petsc4py.PETSc.Vec
Bases: Object
A vector object.
SEE ALSO:
Vec
Enumerations
┌────────┬─────────────────────────┐
│ Option │ Vector assembly option. │
├────────┼─────────────────────────┤
│ Type │ The vector type. │
└────────┴─────────────────────────┘
petsc4py.PETSc.Vec.Option
class petsc4py.PETSc.Vec.Option
Bases: object
Vector assembly option.
Attributes Summary
┌─────────────────────────┬───────────────────────────────────────┐
│ IGNORE_NEGATIVE_INDICES │ Constant IGNORE_NEGATIVE_INDICES of │
│ │ type int │
├─────────────────────────┼───────────────────────────────────────┤
│ IGNORE_OFF_PROC_ENTRIES │ Constant IGNORE_OFF_PROC_ENTRIES of │
│ │ type int │
└─────────────────────────┴───────────────────────────────────────┘
Attributes Documentation
IGNORE_NEGATIVE_INDICES: int = IGNORE_NEGATIVE_INDICES
Constant IGNORE_NEGATIVE_INDICES of type int
IGNORE_OFF_PROC_ENTRIES: int = IGNORE_OFF_PROC_ENTRIES
Constant IGNORE_OFF_PROC_ENTRIES of type int
petsc4py.PETSc.Vec.Type
class petsc4py.PETSc.Vec.Type
Bases: object
The vector type.
Attributes Summary
┌─────────────┬────────────────────────────────┐
│ CUDA │ Object CUDA of type str │
├─────────────┼────────────────────────────────┤
│ HIP │ Object HIP of type str │
├─────────────┼────────────────────────────────┤
│ KOKKOS │ Object KOKKOS of type str │
├─────────────┼────────────────────────────────┤
│ MPI │ Object MPI of type str │
├─────────────┼────────────────────────────────┤
│ MPICUDA │ Object MPICUDA of type str │
├─────────────┼────────────────────────────────┤
│ MPIHIP │ Object MPIHIP of type str │
├─────────────┼────────────────────────────────┤
│ MPIKOKKOS │ Object MPIKOKKOS of type str │
├─────────────┼────────────────────────────────┤
│ MPIVIENNACL │ Object MPIVIENNACL of type str │
├─────────────┼────────────────────────────────┤
│ NEST │ Object NEST of type str │
├─────────────┼────────────────────────────────┤
│ SEQ │ Object SEQ of type str │
├─────────────┼────────────────────────────────┤
│ SEQCUDA │ Object SEQCUDA of type str │
├─────────────┼────────────────────────────────┤
│ SEQHIP │ Object SEQHIP of type str │
├─────────────┼────────────────────────────────┤
│ SEQKOKKOS │ Object SEQKOKKOS of type str │
├─────────────┼────────────────────────────────┤
│ SEQVIENNACL │ Object SEQVIENNACL of type str │
├─────────────┼────────────────────────────────┤
│ SHARED │ Object SHARED of type str │
├─────────────┼────────────────────────────────┤
│ STANDARD │ Object STANDARD of type str │
├─────────────┼────────────────────────────────┤
│ VIENNACL │ Object VIENNACL of type str │
└─────────────┴────────────────────────────────┘
Attributes Documentation
CUDA: str = CUDA
Object CUDA of type str
HIP: str = HIP
Object HIP of type str
KOKKOS: str = KOKKOS
Object KOKKOS of type str
MPI: str = MPI
Object MPI of type str
MPICUDA: str = MPICUDA
Object MPICUDA of type str
MPIHIP: str = MPIHIP
Object MPIHIP of type str
MPIKOKKOS: str = MPIKOKKOS
Object MPIKOKKOS of type str
MPIVIENNACL: str = MPIVIENNACL
Object MPIVIENNACL of type str
NEST: str = NEST
Object NEST of type str
SEQ: str = SEQ
Object SEQ of type str
SEQCUDA: str = SEQCUDA
Object SEQCUDA of type str
SEQHIP: str = SEQHIP
Object SEQHIP of type str
SEQKOKKOS: str = SEQKOKKOS
Object SEQKOKKOS of type str
SEQVIENNACL: str = SEQVIENNACL
Object SEQVIENNACL of type str
SHARED: str = SHARED
Object SHARED of type str
STANDARD: str = STANDARD
Object STANDARD of type str
VIENNACL: str = VIENNACL
Object VIENNACL of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ abs() │ Replace each entry (xₙ) in the vector │
│ │ by abs|xₙ|. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ appendOptionsPrefix(prefix) │ Append to the prefix used for │
│ │ searching for options in the │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemble() │ Assemble the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemblyBegin() │ Begin an assembling stage of the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ assemblyEnd() │ Finish the assembling stage initiated │
│ │ with assemblyBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ attachDLPackInfo([vec, dltensor]) │ Attach tensor information from │
│ │ another vector or DLPack tensor. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ axpby(alpha, beta, x) │ Compute and store y = ɑ·x + β·y. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ axpy(alpha, x) │ Compute and store y = ɑ·x + y. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ aypx(alpha, x) │ Compute and store y = x + ɑ·y. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ bindToCPU(flg) │ Bind vector operations execution on │
│ │ the CPU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ boundToCPU() │ Return whether the vector has been │
│ │ bound to the CPU. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ chop(tol) │ Set all vector entries less than some │
│ │ absolute tolerance to zero. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearDLPackInfo() │ Clear tensor information. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ concatenate(vecs) │ Concatenate vectors into a single │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ conjugate() │ Conjugate the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ copy([result]) │ Return a copy of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a vector object. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createCUDAWithArrays([cpuarray, │ Create a Type.CUDA vector with │
│ cudahandle, ...]) │ optional arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createGhost(ghosts, size[, bsize, │ Create a parallel vector with ghost │
│ comm]) │ padding on each processor. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createGhostWithArray(ghosts, array[, │ Create a parallel vector with ghost │
│ size, ...]) │ padding and provided arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createHIPWithArrays([cpuarray, │ Create a Type.HIP vector with │
│ hiphandle, ...]) │ optional arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createLocalVector() │ Create a local vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMPI(size[, bsize, comm]) │ Create a parallel Type.MPI vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createNest(vecs[, isets, comm]) │ Create a Type.NEST vector containing │
│ │ multiple nested subvectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createSeq(size[, bsize, comm]) │ Create a sequential Type.SEQ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createShared(size[, bsize, comm]) │ Create a Type.SHARED vector that uses │
│ │ shared memory. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createViennaCLWithArrays([cpuarray, │ Create a Type.VIENNACL vector with │
│ ...]) │ optional arrays. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createWithArray(array[, size, bsize, │ Create a vector using a provided │
│ comm]) │ array. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createWithDLPack(dltensor[, size, │ Create a vector wrapping a DLPack │
│ bsize, comm]) │ object, sharing the same memory. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ dot(vec) │ Return the dot product with vec. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ dotBegin(vec) │ Begin computing the dot product. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ dotEnd(vec) │ Finish computing the dot product │
│ │ initiated with dotBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ dotNorm2(vec) │ Return the dot product with vec and │
│ │ its squared norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ duplicate([array]) │ Create a new vector with the same │
│ │ type, optionally with data. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ equal(vec) │ Return whether the vector is equal to │
│ │ another. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ exp() │ Replace each entry (xₙ) in the vector │
│ │ by exp(xₙ). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getArray([readonly]) │ Return local portion of the vector as │
│ │ an ndarray. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBlockSize() │ Return the block size of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getBuffer([readonly]) │ Return a buffered view of the local │
│ │ portion of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCLContextHandle() │ Return the OpenCL context associated │
│ │ with the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCLMemHandle([mode]) │ Return the OpenCL buffer associated │
│ │ with the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCLQueueHandle() │ Return the OpenCL command queue │
│ │ associated with the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getCUDAHandle([mode]) │ Return a pointer to the device │
│ │ buffer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getDM() │ Return the DM associated to the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getGhostIS() │ Return ghosting indices of a ghost │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getHIPHandle([mode]) │ Return a pointer to the device │
│ │ buffer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLGMap() │ Return the local-to-global mapping. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalSize() │ Return the local size of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getLocalVector(lvec[, readonly]) │ Maps the local portion of the vector │
│ │ into a local vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getNestSubVecs() │ Return all the vectors contained in │
│ │ the nested vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOffloadMask() │ Return the offloading status of the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOptionsPrefix() │ Return the prefix used for searching │
│ │ for options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRange() │ Return the locally owned range of │
│ │ indices (start, end). │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getOwnershipRanges() │ Return the range of indices owned by │
│ │ each process. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSize() │ Return the global size of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSizes() │ Return the vector sizes. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSubVector(iset[, subvec]) │ Return a subvector from given │
│ │ indices. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValue(index) │ Return a single value from the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValues(indices[, values]) │ Return values from certain locations │
│ │ in the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getValuesStagStencil(indices[, │ Not implemented. │
│ values]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ ghostUpdate([addv, mode]) │ Update ghosted vector entries. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ ghostUpdateBegin([addv, mode]) │ Begin updating ghosted vector │
│ │ entries. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ ghostUpdateEnd([addv, mode]) │ Finish updating ghosted vector │
│ │ entries initiated with │
│ │ ghostUpdateBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isaxpy(idx, alpha, x) │ Add a scaled reduced-space vector to │
│ │ a subset of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ isset(idx, alpha) │ Set specific elements of the vector │
│ │ to the same value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ load(viewer) │ Load a vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ localForm() │ Return a context manager for viewing │
│ │ ghost vectors in local form. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ log() │ Replace each entry in the vector by │
│ │ its natural logarithm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mDot(vecs[, out]) │ Compute Xᴴ·y with X an array of │
│ │ vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mDotBegin(vecs, out) │ Starts a split phase multiple dot │
│ │ product computation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mDotEnd(vecs, out) │ Ends a split phase multiple dot │
│ │ product computation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ max() │ Return the vector entry with maximum │
│ │ real part and its location. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ maxPointwiseDivide(vec) │ Return the maximum of the │
│ │ component-wise absolute value │
│ │ division. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ maxpy(alphas, vecs) │ Compute and store y = Σₙ(ɑₙ·Xₙ) + y │
│ │ with X an array of vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ min() │ Return the vector entry with minimum │
│ │ real part and its location. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mtDot(vecs[, out]) │ Compute Xᵀ·y with X an array of │
│ │ vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mtDotBegin(vecs, out) │ Starts a split phase transpose │
│ │ multiple dot product computation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ mtDotEnd(vecs, out) │ Ends a split phase transpose multiple │
│ │ dot product computation. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ norm([norm_type]) │ Compute the vector norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ normBegin([norm_type]) │ Begin computing the vector norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ normEnd([norm_type]) │ Finish computations initiated with │
│ │ normBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ normalize() │ Normalize the vector by its 2-norm. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ permute(order[, invert]) │ Permute the vector in-place with a │
│ │ provided ordering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ placeArray(array) │ Set the local portion of the vector │
│ │ to a provided array. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pointwiseDivide(x, y) │ Compute and store the component-wise │
│ │ division of two vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pointwiseMax(x, y) │ Compute and store the component-wise │
│ │ maximum of two vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pointwiseMaxAbs(x, y) │ Compute and store the component-wise │
│ │ maximum absolute values. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pointwiseMin(x, y) │ Compute and store the component-wise │
│ │ minimum of two vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pointwiseMult(x, y) │ Compute and store the component-wise │
│ │ multiplication of two vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ reciprocal() │ Replace each entry in the vector by │
│ │ its reciprocal. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ resetArray([force]) │ Reset the vector to use its default │
│ │ array. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreCLMemHandle() │ Restore a pointer to the OpenCL │
│ │ buffer obtained with getCLMemHandle. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreCUDAHandle(handle[, mode]) │ Restore a pointer to the device │
│ │ buffer obtained with getCUDAHandle. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreHIPHandle(handle[, mode]) │ Restore a pointer to the device │
│ │ buffer obtained with getHIPHandle. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreLocalVector(lvec[, readonly]) │ Unmap a local access obtained with │
│ │ getLocalVector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreSubVector(iset, subvec) │ Restore a subvector extracted using │
│ │ getSubVector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ scale(alpha) │ Scale all entries of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ set(alpha) │ Set all components of the vector to │
│ │ the same value. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setArray(array) │ Set values for the local portion of │
│ │ the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setBlockSize(bsize) │ Set the block size of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDM(dm) │ Associate a DM to the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFromOptions() │ Configure the vector from the options │
│ │ database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setLGMap(lgmap) │ Set the local-to-global mapping. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setMPIGhost(ghosts) │ Set the ghost points for a ghosted │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setNestSubVecs(sx[, idxm]) │ Set the component vectors at │
│ │ specified indices in the nested │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOption(option, flag) │ Set option. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setOptionsPrefix(prefix) │ Set the prefix used for searching for │
│ │ options in the database. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setRandom([random]) │ Set all components of the vector to │
│ │ random numbers. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setSizes(size[, bsize]) │ Set the local and global sizes of the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(vec_type) │ Set the vector type. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setUp() │ Set up the internal data structures │
│ │ for using the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValue(index, value[, addv]) │ Insert or add a single value in the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValueLocal(index, value[, addv]) │ Insert or add a single value in the │
│ │ vector using a local numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValues(indices, values[, addv]) │ Insert or add multiple values in the │
│ │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlocked(indices, values[, │ Insert or add blocks of values in the │
│ addv]) │ vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesBlockedLocal(indices, │ Insert or add blocks of values in the │
│ values[, addv]) │ vector with a local numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesLocal(indices, values[, │ Insert or add multiple values in the │
│ addv]) │ vector with a local numbering. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setValuesStagStencil(indices, │ Not implemented. │
│ values[, addv]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ shift(alpha) │ Shift all entries in the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ sqrtabs() │ Replace each entry (xₙ) in the vector │
│ │ by √|xₙ|. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideGather(field, vec[, addv]) │ Insert component values into a │
│ │ single-component vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideMax(field) │ Return the maximum of entries in a │
│ │ subvector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideMin(field) │ Return the minimum of entries in a │
│ │ subvector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideNorm(field[, norm_type]) │ Return the norm of entries in a │
│ │ subvector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideScale(field, alpha) │ Scale a component of the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideScatter(field, vec[, addv]) │ Scatter entries into a component of │
│ │ another vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ strideSum(field) │ Sum subvector entries. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ sum() │ Return the sum of all the entries of │
│ │ the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ swap(vec) │ Swap the content of two vectors. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ tDot(vec) │ Return the indefinite dot product │
│ │ with vec. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ tDotBegin(vec) │ Begin computing the indefinite dot │
│ │ product. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ tDotEnd(vec) │ Finish computing the indefinite dot │
│ │ product initiated with tDotBegin. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ toDLPack([mode]) │ Return a DLPack PyCapsule wrapping │
│ │ the vector data. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([viewer]) │ Display the vector. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ waxpy(alpha, x, y) │ Compute and store w = ɑ·x + y. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ zeroEntries() │ Set all entries in the vector to │
│ │ zero. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Attributes Summary
┌──────────────┬───────────────────────────────────────┐
│ array │ Alias for array_w. │
├──────────────┼───────────────────────────────────────┤
│ array_r │ Read-only ndarray containing the │
│ │ local portion of the vector. │
├──────────────┼───────────────────────────────────────┤
│ array_w │ Writeable ndarray containing the │
│ │ local portion of the vector. │
├──────────────┼───────────────────────────────────────┤
│ block_size │ The block size. │
├──────────────┼───────────────────────────────────────┤
│ buffer │ Alias for buffer_w. │
├──────────────┼───────────────────────────────────────┤
│ buffer_r │ Read-only buffered view of the local │
│ │ portion of the vector. │
├──────────────┼───────────────────────────────────────┤
│ buffer_w │ Writeable buffered view of the local │
│ │ portion of the vector. │
├──────────────┼───────────────────────────────────────┤
│ local_size │ The local vector size. │
├──────────────┼───────────────────────────────────────┤
│ owner_range │ The locally owned range of indices in │
│ │ the form [low, high). │
├──────────────┼───────────────────────────────────────┤
│ owner_ranges │ The range of indices owned by each │
│ │ process. │
├──────────────┼───────────────────────────────────────┤
│ size │ The global vector size. │
├──────────────┼───────────────────────────────────────┤
│ sizes │ The local and global vector sizes. │
└──────────────┴───────────────────────────────────────┘
Methods Documentation
abs() Replace each entry (xₙ) in the vector by abs|xₙ|.
Logically collective.
SEE ALSO:
VecAbs
Source code at petsc4py/PETSc/Vec.pyx:2293
Return type
None
appendOptionsPrefix(prefix)
Append to the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, VecAppendOptionsPrefix
Source code at petsc4py/PETSc/Vec.pyx:1028
Parameters
prefix (str | None)
Return type
None
assemble()
Assemble the vector.
Collective.
SEE ALSO:
assemblyBegin, assemblyEnd
Source code at petsc4py/PETSc/Vec.pyx:3047
Return type
None
assemblyBegin()
Begin an assembling stage of the vector.
Collective.
SEE ALSO:
assemblyEnd, VecAssemblyBegin
Source code at petsc4py/PETSc/Vec.pyx:3023
Return type
None
assemblyEnd()
Finish the assembling stage initiated with assemblyBegin.
Collective.
SEE ALSO:
assemblyBegin, VecAssemblyEnd
Source code at petsc4py/PETSc/Vec.pyx:3035
Return type
None
attachDLPackInfo(vec=None, dltensor=None)
Attach tensor information from another vector or DLPack tensor.
Logically collective.
This tensor information is required when converting a Vec to a DLPack object.
Parameters
• vec (Vec | None) -- Vector with attached tensor information. This is typically
created by calling createWithDLPack.
• dltensor -- DLPack tensor. This will only be used if vec is None.
Return type
Self
Notes
This operation does not copy any data from vec or dltensor.
SEE ALSO:
clearDLPackInfo, createWithDLPack
Source code at petsc4py/PETSc/Vec.pyx:643
axpby(alpha, beta, x)
Compute and store y = ɑ·x + β·y.
Logically collective.
Parameters
• alpha (Scalar) -- First scale factor.
• beta (Scalar) -- Second scale factor.
• x (Vec) -- Input vector, must not be the current vector.
Return type
None
SEE ALSO:
axpy, aypx, waxpy, VecAXPBY
Source code at petsc4py/PETSc/Vec.pyx:2524
axpy(alpha, x)
Compute and store y = ɑ·x + y.
Logically collective.
Parameters
• alpha (Scalar) -- Scale factor.
• x (Vec) -- Input vector.
Return type
None
SEE ALSO:
isaxpy, VecAXPY
Source code at petsc4py/PETSc/Vec.pyx:2460
aypx(alpha, x)
Compute and store y = x + ɑ·y.
Logically collective.
Parameters
• alpha (Scalar) -- Scale factor.
• x (Vec) -- Input vector, must not be the current vector.
Return type
None
SEE ALSO:
axpy, axpby, VecAYPX
Source code at petsc4py/PETSc/Vec.pyx:2504
bindToCPU(flg)
Bind vector operations execution on the CPU.
Logically collective.
SEE ALSO:
boundToCPU, VecBindToCPU
Source code at petsc4py/PETSc/Vec.pyx:1396
Parameters
flg (bool)
Return type
None
boundToCPU()
Return whether the vector has been bound to the CPU.
Not collective.
SEE ALSO:
bindToCPU, VecBoundToCPU
Source code at petsc4py/PETSc/Vec.pyx:1409
Return type
bool
chop(tol)
Set all vector entries less than some absolute tolerance to zero.
Collective.
Parameters
tol (float) -- The absolute tolerance below which entries are set to zero.
Return type
None
SEE ALSO:
VecFilter
Source code at petsc4py/PETSc/Vec.pyx:1732
clearDLPackInfo()
Clear tensor information.
Logically collective.
SEE ALSO:
attachDLPackInfo, createWithDLPack
Source code at petsc4py/PETSc/Vec.pyx:705
Return type
Self
classmethod concatenate(vecs)
Concatenate vectors into a single vector.
Collective.
Parameters
vecs (Sequence[Vec]) -- The vectors to be concatenated.
Returns
• vector_out (Vec) -- The concatenated vector.
• indices_list (list of IS) -- A list of index sets corresponding to the
concatenated components.
Return type
tuple[Vec, list[IS]]
SEE ALSO:
VecConcatenate
Source code at petsc4py/PETSc/Vec.pyx:3536
conjugate()
Conjugate the vector.
Logically collective.
SEE ALSO:
VecConjugate
Source code at petsc4py/PETSc/Vec.pyx:2305
Return type
None
copy(result=None)
Return a copy of the vector.
Logically collective.
This operation copies vector entries to the new vector.
Parameters
result (Vec | None) -- Target vector for the copy. If None then a new vector is
created internally.
Return type
Vec
SEE ALSO:
duplicate, VecCopy
Source code at petsc4py/PETSc/Vec.pyx:1707
create(comm=None)
Create a vector object.
Collective.
After creation the vector type can then be set with setType.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
destroy, VecCreate
Source code at petsc4py/PETSc/Vec.pyx:176
createCUDAWithArrays(cpuarray=None, cudahandle=None, size=None, bsize=None, comm=None)
Create a Type.CUDA vector with optional arrays.
Collective.
Parameters
• cpuarray (Sequence[Scalar] | None) -- Host array. Will be lazily allocated if not
provided.
• cudahandle (Any | None) -- Address of the array on the GPU. Will be lazily
allocated if not provided.
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateSeqCUDAWithArrays, VecCreateMPICUDAWithArrays
Source code at petsc4py/PETSc/Vec.pyx:370
createGhost(ghosts, size, bsize=None, comm=None)
Create a parallel vector with ghost padding on each processor.
Collective.
Parameters
• ghosts (Sequence[int]) -- Global indices of ghost points.
• size (LayoutSizeSpec) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createGhostWithArray, VecCreateGhost, VecCreateGhostBlock
Source code at petsc4py/PETSc/Vec.pyx:819
createGhostWithArray(ghosts, array, size=None, bsize=None, comm=None)
Create a parallel vector with ghost padding and provided arrays.
Collective.
Parameters
• ghosts (Sequence[int]) -- Global indices of ghost points.
• array (Sequence[Scalar]) -- Array to store the vector values. Must be at least as
large as the local size of the vector (including ghost points).
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createGhost, VecCreateGhostWithArray, VecCreateGhostBlockWithArray
Source code at petsc4py/PETSc/Vec.pyx:861
createHIPWithArrays(cpuarray=None, hiphandle=None, size=None, bsize=None, comm=None)
Create a Type.HIP vector with optional arrays.
Collective.
Parameters
• cpuarray (Sequence[Scalar] | None) -- Host array. Will be lazily allocated if not
provided.
• hiphandle (Any | None) -- Address of the array on the GPU. Will be lazily
allocated if not provided.
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateSeqHIPWithArrays, VecCreateMPIHIPWithArrays
Source code at petsc4py/PETSc/Vec.pyx:428
createLocalVector()
Create a local vector.
Not collective.
Returns
The local vector.
Return type
Vec
SEE ALSO:
getLocalVector, VecCreateLocalVector
Source code at petsc4py/PETSc/Vec.pyx:1204
createMPI(size, bsize=None, comm=None)
Create a parallel Type.MPI vector.
Collective.
Parameters
• size (LayoutSizeSpec) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
createSeq, VecCreateMPI
Source code at petsc4py/PETSc/Vec.pyx:283
createNest(vecs, isets=None, comm=None)
Create a Type.NEST vector containing multiple nested subvectors.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Iterable of subvectors.
• isets (Sequence[IS]) -- Iterable of index sets for each nested subvector.
Defaults to contiguous ordering.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateNest
Source code at petsc4py/PETSc/Vec.pyx:952
createSeq(size, bsize=None, comm=None)
Create a sequential Type.SEQ vector.
Collective.
Parameters
• size (LayoutSizeSpec) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to COMM_SELF.
Return type
Self
SEE ALSO:
createMPI, VecCreateSeq
Source code at petsc4py/PETSc/Vec.pyx:247
createShared(size, bsize=None, comm=None)
Create a Type.SHARED vector that uses shared memory.
Collective.
Parameters
• size (LayoutSizeSpec) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateShared
Source code at petsc4py/PETSc/Vec.pyx:918
createViennaCLWithArrays(cpuarray=None, viennaclvechandle=None, size=None, bsize=None, comm=None)
Create a Type.VIENNACL vector with optional arrays.
Collective.
Parameters
• cpuarray (Sequence[Scalar] | None) -- Host array. Will be lazily allocated if not
provided.
• viennaclvechandle (Any | None) -- Address of the array on the GPU. Will be lazily
allocated if not provided.
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateSeqViennaCLWithArrays, VecCreateMPIViennaCLWithArrays
Source code at petsc4py/PETSc/Vec.pyx:486
createWithArray(array, size=None, bsize=None, comm=None)
Create a vector using a provided array.
Collective.
This method will create either a Type.SEQ or Type.MPI depending on the size of the
communicator.
Parameters
• array (Sequence[Scalar]) -- Array to store the vector values. Must be at least as
large as the local size of the vector.
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
VecCreateSeqWithArray, VecCreateMPIWithArray
Source code at petsc4py/PETSc/Vec.pyx:319
createWithDLPack(dltensor, size=None, bsize=None, comm=None)
Create a vector wrapping a DLPack object, sharing the same memory.
Collective.
This operation does not modify the storage of the original tensor and should be used with
contiguous tensors only. If the tensor is stored in row-major order (e.g. PyTorch tensors),
the resulting vector will look like an unrolled tensor using row-major order.
The resulting vector type will be one of Type.SEQ, Type.MPI, Type.SEQCUDA, Type.MPICUDA,
Type.SEQHIP or Type.MPIHIP depending on the type of dltensor and the number of processes in
the communicator.
Parameters
• dltensor -- Either an object with a __dlpack__ method or a DLPack tensor object.
• size (LayoutSizeSpec | None) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
Source code at petsc4py/PETSc/Vec.pyx:545
destroy()
Destroy the vector.
Collective.
SEE ALSO:
create, VecDestroy
Source code at petsc4py/PETSc/Vec.pyx:163
Return type
Self
dot(vec)
Return the dot product with vec.
Collective.
For complex numbers this computes yᴴ·x with self as x, vec as y and where yᴴ denotes the
conjugate transpose of y.
Use tDot for the indefinite form yᵀ·x where yᵀ denotes the transpose of y.
Parameters
vec (Vec) -- Vector to compute the dot product with.
Return type
Scalar
SEE ALSO:
dotBegin, dotEnd, tDot, VecDot
Source code at petsc4py/PETSc/Vec.pyx:1787
dotBegin(vec)
Begin computing the dot product.
Collective.
This should be paired with a call to dotEnd.
Parameters
vec (Vec) -- Vector to compute the dot product with.
Return type
None
SEE ALSO:
dotEnd, dot, VecDotBegin
Source code at petsc4py/PETSc/Vec.pyx:1812
dotEnd(vec)
Finish computing the dot product initiated with dotBegin.
Collective.
SEE ALSO:
dotBegin, dot, VecDotEnd
Source code at petsc4py/PETSc/Vec.pyx:1832
Parameters
vec (Vec)
Return type
Scalar
dotNorm2(vec)
Return the dot product with vec and its squared norm.
Collective.
SEE ALSO:
dot, norm, VecDotNorm2
Source code at petsc4py/PETSc/Vec.pyx:2151
Parameters
vec (Vec)
Return type
tuple[Scalar, float]
duplicate(array=None)
Create a new vector with the same type, optionally with data.
Collective.
Parameters
array (Sequence[Scalar] | None) -- Optional values to store in the new vector.
Return type
Vec
SEE ALSO:
copy, VecDuplicate
Source code at petsc4py/PETSc/Vec.pyx:1682
equal(vec)
Return whether the vector is equal to another.
Collective.
Parameters
vec (Vec) -- Vector to compare with.
Return type
bool
SEE ALSO:
VecEqual
Source code at petsc4py/PETSc/Vec.pyx:1768
exp() Replace each entry (xₙ) in the vector by exp(xₙ).
Logically collective.
SEE ALSO:
log, VecExp
Source code at petsc4py/PETSc/Vec.pyx:2257
Return type
None
getArray(readonly=False)
Return local portion of the vector as an ndarray.
Logically collective.
Parameters
readonly (bool) -- Request read-only access.
Return type
ArrayScalar
SEE ALSO:
setArray, getBuffer
Source code at petsc4py/PETSc/Vec.pyx:1313
getBlockSize()
Return the block size of the vector.
Not collective.
SEE ALSO:
VecGetBlockSize
Source code at petsc4py/PETSc/Vec.pyx:1149
Return type
int
getBuffer(readonly=False)
Return a buffered view of the local portion of the vector.
Logically collective.
Parameters
readonly (bool) -- Request read-only access.
Returns
Buffer object wrapping the local portion of the vector data. This can be used either
as a context manager providing access as a numpy array or can be passed to array
constructors accepting buffered objects such as numpy.asarray.
Return type
typing.Any
Examples
Accessing the data with a context manager:
>>> vec = PETSc.Vec().createWithArray([1, 2, 3])
>>> with vec.getBuffer() as arr:
... arr
array([1., 2., 3.])
Converting the buffer to an ndarray:
>>> buf = PETSc.Vec().createWithArray([1, 2, 3]).getBuffer()
>>> np.asarray(buf)
array([1., 2., 3.])
SEE ALSO:
getArray
Source code at petsc4py/PETSc/Vec.pyx:1270
getCLContextHandle()
Return the OpenCL context associated with the vector.
Not collective.
Returns
Pointer to underlying CL context. This can be used with pyopencl through
pyopencl.Context.from_int_ptr.
Return type
int
SEE ALSO:
getCLQueueHandle, VecViennaCLGetCLContext
Source code at petsc4py/PETSc/Vec.pyx:1593
getCLMemHandle(mode='rw')
Return the OpenCL buffer associated with the vector.
Not collective.
Returns
Pointer to the device buffer. This can be used with pyopencl through
pyopencl.Context.from_int_ptr.
Return type
int
Parameters
mode (AccessModeSpec)
Notes
This method may incur a host-to-device copy if the device data is out of date and mode is
"r" or "rw".
SEE ALSO:
restoreCLMemHandle, VecViennaCLGetCLMem, VecViennaCLGetCLMemRead, ‐
VecViennaCLGetCLMemWrite
Source code at petsc4py/PETSc/Vec.pyx:1633
getCLQueueHandle()
Return the OpenCL command queue associated with the vector.
Not collective.
Returns
Pointer to underlying CL command queue. This can be used with pyopencl through
pyopencl.Context.from_int_ptr.
Return type
int
SEE ALSO:
getCLContextHandle, VecViennaCLGetCLQueue
Source code at petsc4py/PETSc/Vec.pyx:1613
getCUDAHandle(mode='rw')
Return a pointer to the device buffer.
Not collective.
The returned pointer should be released using restoreCUDAHandle with the same access mode.
Returns
CUDA device pointer.
Return type
typing.Any
Parameters
mode (AccessModeSpec)
Notes
This method may incur a host-to-device copy if the device data is out of date and mode is
"r" or "rw".
SEE ALSO:
restoreCUDAHandle, VecCUDAGetArray, VecCUDAGetArrayRead, VecCUDAGetArrayWrite
Source code at petsc4py/PETSc/Vec.pyx:1423
getDM()
Return the DM associated to the vector.
Not collective.
SEE ALSO:
setDM, VecGetDM
Source code at petsc4py/PETSc/Vec.pyx:3519
Return type
DM
getGhostIS()
Return ghosting indices of a ghost vector.
Collective.
Returns
Indices of ghosts.
Return type
IS
SEE ALSO:
VecGhostGetGhostIS
Source code at petsc4py/PETSc/Vec.pyx:3385
getHIPHandle(mode='rw')
Return a pointer to the device buffer.
Not collective.
The returned pointer should be released using restoreHIPHandle with the same access mode.
Returns
HIP device pointer.
Return type
typing.Any
Parameters
mode (AccessModeSpec)
Notes
This method may incur a host-to-device copy if the device data is out of date and mode is
"r" or "rw".
SEE ALSO:
restoreHIPHandle, VecHIPGetArray, VecHIPGetArrayRead, VecHIPGetArrayWrite
Source code at petsc4py/PETSc/Vec.pyx:1495
getLGMap()
Return the local-to-global mapping.
Not collective.
SEE ALSO:
setLGMap, VecGetLocalToGlobalMapping
Source code at petsc4py/PETSc/Vec.pyx:2899
Return type
LGMap
getLocalSize()
Return the local size of the vector.
Not collective.
SEE ALSO:
setSizes, getSize, VecGetLocalSize
Source code at petsc4py/PETSc/Vec.pyx:1107
Return type
int
getLocalVector(lvec, readonly=False)
Maps the local portion of the vector into a local vector.
Logically collective.
Parameters
• lvec (Vec) -- The local vector obtained from createLocalVector.
• readonly (bool) -- Request read-only access.
Return type
None
SEE ALSO:
createLocalVector, restoreLocalVector, VecGetLocalVectorRead, VecGetLocalVector
Source code at petsc4py/PETSc/Vec.pyx:1223
getNestSubVecs()
Return all the vectors contained in the nested vector.
Not collective.
SEE ALSO:
setNestSubVecs, VecNestGetSubVecs
Source code at petsc4py/PETSc/Vec.pyx:3451
Return type
list[Vec]
getOffloadMask()
Return the offloading status of the vector.
Not collective.
Common return values include:
• 1: PETSC_OFFLOAD_CPU - CPU has valid entries
• 2: PETSC_OFFLOAD_GPU - GPU has valid entries
• 3: PETSC_OFFLOAD_BOTH - CPU and GPU are in sync
Returns
Enum value from PetscOffloadMask describing the offloading status.
Return type
int
SEE ALSO:
VecGetOffloadMask, PetscOffloadMask
Source code at petsc4py/PETSc/Vec.pyx:1567
getOptionsPrefix()
Return the prefix used for searching for options in the database.
Not collective.
SEE ALSO:
Working with PETSc options, setOptionsPrefix, VecGetOptionsPrefix
Source code at petsc4py/PETSc/Vec.pyx:1014
Return type
str
getOwnershipRange()
Return the locally owned range of indices (start, end).
Not collective.
Returns
• start (int) -- The first local element.
• end (int) -- One more than the last local element.
Return type
tuple[int, int]
SEE ALSO:
getOwnershipRanges, VecGetOwnershipRange
Source code at petsc4py/PETSc/Vec.pyx:1163
getOwnershipRanges()
Return the range of indices owned by each process.
Not collective.
The returned array is the result of exclusive scan of the local sizes.
SEE ALSO:
getOwnershipRange, VecGetOwnershipRanges
Source code at petsc4py/PETSc/Vec.pyx:1184
Return type
ArrayInt
getSize()
Return the global size of the vector.
Not collective.
SEE ALSO:
setSizes, getLocalSize, VecGetSize
Source code at petsc4py/PETSc/Vec.pyx:1093
Return type
int
getSizes()
Return the vector sizes.
Not collective.
SEE ALSO:
getSize, getLocalSize, VecGetLocalSize, VecGetSize
Source code at petsc4py/PETSc/Vec.pyx:1121
Return type
LayoutSizeSpec
getSubVector(iset, subvec=None)
Return a subvector from given indices.
Collective.
Once finished with the subvector it should be returned with restoreSubVector.
Parameters
• iset (IS) -- Index set describing which indices to extract into the subvector.
• subvec (Vec | None) -- Subvector to copy entries into. If None then a new Vec will
be created.
Return type
Vec
SEE ALSO:
restoreSubVector, VecGetSubVector
Source code at petsc4py/PETSc/Vec.pyx:3406
getType()
Return the type of the vector.
Not collective.
SEE ALSO:
setType, VecGetType
Source code at petsc4py/PETSc/Vec.pyx:1079
Return type
str
getValue(index)
Return a single value from the vector.
Not collective.
Only values locally stored may be accessed.
Parameters
index (int) -- Location of the value to read.
Return type
Scalar
SEE ALSO:
getValues, VecGetValues
Source code at petsc4py/PETSc/Vec.pyx:2720
getValues(indices, values=None)
Return values from certain locations in the vector.
Not collective.
Only values locally stored may be accessed.
Parameters
• indices (Sequence[int]) -- Locations of the values to read.
• values (Sequence[Scalar] | None) -- Location to store the collected values. If not
provided then a new array will be allocated.
Return type
ArrayScalar
SEE ALSO:
getValue, setValues, VecGetValues
Source code at petsc4py/PETSc/Vec.pyx:2742
getValuesStagStencil(indices, values=None)
Not implemented.
Source code at petsc4py/PETSc/Vec.pyx:2767
Return type
None
ghostUpdate(addv=None, mode=None)
Update ghosted vector entries.
Neighborwise collective.
Parameters
• addv (InsertModeSpec) -- Insertion mode.
• mode (ScatterModeSpec) -- Scatter mode.
Return type
None
Examples
To accumulate ghost region values onto owning processes:
>>> vec.ghostUpdate(InsertMode.ADD_VALUES, ScatterMode.REVERSE)
Update ghost regions:
>>> vec.ghostUpdate(InsertMode.INSERT_VALUES, ScatterMode.FORWARD)
SEE ALSO:
ghostUpdateBegin, ghostUpdateEnd
Source code at petsc4py/PETSc/Vec.pyx:3331
ghostUpdateBegin(addv=None, mode=None)
Begin updating ghosted vector entries.
Neighborwise collective.
SEE ALSO:
ghostUpdateEnd, ghostUpdate, createGhost, VecGhostUpdateBegin
Source code at petsc4py/PETSc/Vec.pyx:3297
Parameters
• addv (InsertModeSpec)
• mode (ScatterModeSpec)
Return type
None
ghostUpdateEnd(addv=None, mode=None)
Finish updating ghosted vector entries initiated with ghostUpdateBegin.
Neighborwise collective.
SEE ALSO:
ghostUpdateBegin, ghostUpdate, createGhost, VecGhostUpdateEnd
Source code at petsc4py/PETSc/Vec.pyx:3314
Parameters
• addv (InsertModeSpec)
• mode (ScatterModeSpec)
Return type
None
isaxpy(idx, alpha, x)
Add a scaled reduced-space vector to a subset of the vector.
Logically collective.
This is equivalent to y[idx[i]] += alpha*x[i].
Parameters
• idx (IS) -- Index set for the reduced space. Negative indices are skipped.
• alpha (Scalar) -- Scale factor.
• x (Vec) -- Reduced-space vector.
Return type
None
SEE ALSO:
axpy, aypx, axpby, VecISAXPY
Source code at petsc4py/PETSc/Vec.pyx:2480
isset(idx, alpha)
Set specific elements of the vector to the same value.
Not collective.
Parameters
• idx (IS) -- Index set specifying the vector entries to set.
• alpha (Scalar) -- Value to set the selected entries to.
Return type
None
SEE ALSO:
set, zeroEntries, VecISSet
Source code at petsc4py/PETSc/Vec.pyx:2383
load(viewer)
Load a vector.
Collective.
SEE ALSO:
view, VecLoad
Source code at petsc4py/PETSc/Vec.pyx:1750
Parameters
viewer (Viewer)
Return type
Self
localForm()
Return a context manager for viewing ghost vectors in local form.
Logically collective.
Returns
Context manager yielding the vector in local (ghosted) form.
Return type
typing.Any
Notes
This operation does not perform a copy. To obtain up-to-date ghost values ghostUpdateBegin
and ghostUpdateEnd must be called first.
Non-ghost values can be found at values[0:nlocal] and ghost values at
values[nlocal:nlocal+nghost].
Examples
>>> with vec.localForm() as lf:
... # compute with lf
SEE ALSO:
createGhost, ghostUpdateBegin, ghostUpdateEnd, VecGhostGetLocalForm, ‐
VecGhostRestoreLocalForm
Source code at petsc4py/PETSc/Vec.pyx:3264
log() Replace each entry in the vector by its natural logarithm.
Logically collective.
SEE ALSO:
exp, VecLog
Source code at petsc4py/PETSc/Vec.pyx:2269
Return type
None
mDot(vecs, out=None)
Compute Xᴴ·y with X an array of vectors.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar | None) -- Optional placeholder for the result.
Return type
ArrayScalar
SEE ALSO:
dot, tDot, mDotBegin, mDotEnd, VecMDot
Source code at petsc4py/PETSc/Vec.pyx:1902
mDotBegin(vecs, out)
Starts a split phase multiple dot product computation.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar) -- Placeholder for the result.
Return type
None
SEE ALSO:
mDot, mDotEnd, VecMDotBegin
Source code at petsc4py/PETSc/Vec.pyx:1935
mDotEnd(vecs, out)
Ends a split phase multiple dot product computation.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar) -- Placeholder for the result.
Return type
ArrayScalar
SEE ALSO:
mDot, mDotBegin, VecMDotEnd
Source code at petsc4py/PETSc/Vec.pyx:1965
max() Return the vector entry with maximum real part and its location.
Collective.
Returns
• p (int) -- Location of the maximum value. If multiple entries exist with the same
value then the smallest index will be returned.
• val (Scalar) -- Minimum value.
Return type
tuple[int, float]
SEE ALSO:
min, VecMax
Source code at petsc4py/PETSc/Vec.pyx:2203
maxPointwiseDivide(vec)
Return the maximum of the component-wise absolute value division.
Logically collective.
Equivalent to result = max_i abs(x[i] / y[i]).
Parameters
• x -- Numerator vector.
• y -- Denominator vector.
• vec (Vec)
Return type
float
SEE ALSO:
pointwiseMin, pointwiseMax, pointwiseMaxAbs, VecMaxPointwiseDivide
Source code at petsc4py/PETSc/Vec.pyx:2696
maxpy(alphas, vecs)
Compute and store y = Σₙ(ɑₙ·Xₙ) + y with X an array of vectors.
Logically collective.
Equivalent to y[:] = alphas[i]*vecs[i, :] + y[:].
Parameters
• alphas (Sequence[Scalar]) -- Array of scale factors, one for each vector in vecs.
• vecs (Sequence[Vec]) -- Array of vectors.
Return type
None
SEE ALSO:
axpy, aypx, axpby, waxpy, VecMAXPY
Source code at petsc4py/PETSc/Vec.pyx:2569
min() Return the vector entry with minimum real part and its location.
Collective.
Returns
• p (int) -- Location of the minimum value. If multiple entries exist with the same
value then the smallest index will be returned.
• val (Scalar) -- Minimum value.
Return type
tuple[int, float]
SEE ALSO:
max, VecMin
Source code at petsc4py/PETSc/Vec.pyx:2180
mtDot(vecs, out=None)
Compute Xᵀ·y with X an array of vectors.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar | None) -- Optional placeholder for the result.
Return type
ArrayScalar
SEE ALSO:
tDot, mDot, mtDotBegin, mtDotEnd, VecMTDot
Source code at petsc4py/PETSc/Vec.pyx:1996
mtDotBegin(vecs, out)
Starts a split phase transpose multiple dot product computation.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar) -- Placeholder for the result.
Return type
None
SEE ALSO:
mtDot, mtDotEnd, VecMTDotBegin
Source code at petsc4py/PETSc/Vec.pyx:2029
mtDotEnd(vecs, out)
Ends a split phase transpose multiple dot product computation.
Collective.
Parameters
• vecs (Sequence[Vec]) -- Array of vectors.
• out (ArrayScalar) -- Placeholder for the result.
Return type
ArrayScalar
SEE ALSO:
mtDot, mtDotBegin, VecMTDotEnd
Source code at petsc4py/PETSc/Vec.pyx:2059
norm(norm_type=None)
Compute the vector norm.
Collective.
A 2-tuple is returned if NormType.NORM_1_AND_2 is specified.
SEE ALSO:
VecNorm, NormType
Source code at petsc4py/PETSc/Vec.pyx:2090
Parameters
norm_type (NormTypeSpec)
Return type
float | tuple[float, float]
normBegin(norm_type=None)
Begin computing the vector norm.
Collective.
This should be paired with a call to normEnd.
SEE ALSO:
normEnd, norm, VecNormBegin
Source code at petsc4py/PETSc/Vec.pyx:2112
Parameters
norm_type (NormTypeSpec)
Return type
None
normEnd(norm_type=None)
Finish computations initiated with normBegin.
Collective.
SEE ALSO:
normBegin, norm, VecNormEnd
Source code at petsc4py/PETSc/Vec.pyx:2131
Parameters
norm_type (NormTypeSpec)
Return type
float | tuple[float, float]
normalize()
Normalize the vector by its 2-norm.
Collective.
Returns
The vector norm before normalization.
Return type
float
SEE ALSO:
norm, VecNormalize
Source code at petsc4py/PETSc/Vec.pyx:2226
permute(order, invert=False)
Permute the vector in-place with a provided ordering.
Collective.
Parameters
• order (IS) -- Ordering for the permutation.
• invert (bool) -- Whether to invert the permutation.
Return type
None
SEE ALSO:
VecPermute
Source code at petsc4py/PETSc/Vec.pyx:2337
placeArray(array)
Set the local portion of the vector to a provided array.
Not collective.
SEE ALSO:
resetArray, setArray, VecPlaceArray
Source code at petsc4py/PETSc/Vec.pyx:1345
Parameters
array (Sequence[Scalar])
Return type
None
pointwiseDivide(x, y)
Compute and store the component-wise division of two vectors.
Logically collective.
Equivalent to w[i] = x[i] / y[i].
Parameters
• x (Vec) -- Numerator vector.
• y (Vec) -- Denominator vector.
Return type
None
SEE ALSO:
pointwiseMult, VecPointwiseDivide
Source code at petsc4py/PETSc/Vec.pyx:2618
pointwiseMax(x, y)
Compute and store the component-wise maximum of two vectors.
Logically collective.
Equivalent to w[i] = max(x[i], y[i]).
Parameters
• x (Vec) -- Input vectors to find the component-wise maxima.
• y (Vec) -- Input vectors to find the component-wise maxima.
Return type
None
SEE ALSO:
pointwiseMin, pointwiseMaxAbs, VecPointwiseMax
Source code at petsc4py/PETSc/Vec.pyx:2658
pointwiseMaxAbs(x, y)
Compute and store the component-wise maximum absolute values.
Logically collective.
Equivalent to w[i] = max(abs(x[i]), abs(y[i])).
Parameters
• x (Vec) -- Input vectors to find the component-wise maxima.
• y (Vec) -- Input vectors to find the component-wise maxima.
Return type
None
SEE ALSO:
pointwiseMin, pointwiseMax, VecPointwiseMaxAbs
Source code at petsc4py/PETSc/Vec.pyx:2677
pointwiseMin(x, y)
Compute and store the component-wise minimum of two vectors.
Logically collective.
Equivalent to w[i] = min(x[i], y[i]).
Parameters
• x (Vec) -- Input vectors to find the component-wise minima.
• y (Vec) -- Input vectors to find the component-wise minima.
Return type
None
SEE ALSO:
pointwiseMax, pointwiseMaxAbs, VecPointwiseMin
Source code at petsc4py/PETSc/Vec.pyx:2639
pointwiseMult(x, y)
Compute and store the component-wise multiplication of two vectors.
Logically collective.
Equivalent to w[i] = x[i] * y[i].
Parameters
• x (Vec) -- Input vectors to multiply component-wise.
• y (Vec) -- Input vectors to multiply component-wise.
Return type
None
SEE ALSO:
pointwiseDivide, VecPointwiseMult
Source code at petsc4py/PETSc/Vec.pyx:2599
reciprocal()
Replace each entry in the vector by its reciprocal.
Logically collective.
SEE ALSO:
VecReciprocal
Source code at petsc4py/PETSc/Vec.pyx:2245
Return type
None
resetArray(force=False)
Reset the vector to use its default array.
Not collective.
Parameters
force (bool) -- Force the calling of VecResetArray even if no user array has been
placed with placeArray.
Returns
The array previously provided by the user with placeArray. Can be None if force is
True and no array was placed before.
Return type
ArrayScalar
SEE ALSO:
placeArray, VecResetArray
Source code at petsc4py/PETSc/Vec.pyx:1366
restoreCLMemHandle()
Restore a pointer to the OpenCL buffer obtained with getCLMemHandle.
Not collective.
SEE ALSO:
getCLMemHandle, VecViennaCLRestoreCLMemWrite
Source code at petsc4py/PETSc/Vec.pyx:1670
Return type
None
restoreCUDAHandle(handle, mode='rw')
Restore a pointer to the device buffer obtained with getCUDAHandle.
Not collective.
Parameters
• handle (Any) -- CUDA device pointer.
• mode (AccessModeSpec) -- Access mode.
Return type
None
SEE ALSO:
getCUDAHandle, VecCUDARestoreArray, VecCUDARestoreArrayRead, VecCUDARestoreArrayWrite
Source code at petsc4py/PETSc/Vec.pyx:1462
restoreHIPHandle(handle, mode='rw')
Restore a pointer to the device buffer obtained with getHIPHandle.
Not collective.
Parameters
• handle (Any) -- HIP device pointer.
• mode (AccessModeSpec) -- Access mode.
Return type
None
SEE ALSO:
getHIPHandle, VecHIPRestoreArray, VecHIPRestoreArrayRead, VecHIPRestoreArrayWrite
Source code at petsc4py/PETSc/Vec.pyx:1534
restoreLocalVector(lvec, readonly=False)
Unmap a local access obtained with getLocalVector.
Logically collective.
Parameters
• lvec (Vec) -- The local vector.
• readonly (bool) -- Request read-only access.
Return type
None
SEE ALSO:
createLocalVector, getLocalVector, VecRestoreLocalVectorRead, VecRestoreLocalVector
Source code at petsc4py/PETSc/Vec.pyx:1246
restoreSubVector(iset, subvec)
Restore a subvector extracted using getSubVector.
Collective.
Parameters
• iset (IS) -- Index set describing the indices represented by the subvector.
• subvec (Vec) -- Subvector to be restored.
Return type
None
SEE ALSO:
getSubVector, VecRestoreSubVector
Source code at petsc4py/PETSc/Vec.pyx:3432
scale(alpha)
Scale all entries of the vector.
Collective.
This method sets each entry (xₙ) in the vector to ɑ·xₙ.
Parameters
alpha (Scalar) -- The scaling factor.
Return type
None
SEE ALSO:
shift, VecScale
Source code at petsc4py/PETSc/Vec.pyx:2403
set(alpha)
Set all components of the vector to the same value.
Collective.
SEE ALSO:
zeroEntries, isset, VecSet
Source code at petsc4py/PETSc/Vec.pyx:2370
Parameters
alpha (Scalar)
Return type
None
setArray(array)
Set values for the local portion of the vector.
Logically collective.
SEE ALSO:
placeArray
Source code at petsc4py/PETSc/Vec.pyx:1333
Parameters
array (Sequence[Scalar])
Return type
None
setBlockSize(bsize)
Set the block size of the vector.
Logically collective.
SEE ALSO:
VecSetBlockSize
Source code at petsc4py/PETSc/Vec.pyx:1136
Parameters
bsize (int)
Return type
None
setDM(dm)
Associate a DM to the vector.
Not collective.
SEE ALSO:
getDM, VecSetDM
Source code at petsc4py/PETSc/Vec.pyx:3507
Parameters
dm (DM)
Return type
None
setFromOptions()
Configure the vector from the options database.
Collective.
SEE ALSO:
Working with PETSc options, VecSetFromOptions
Source code at petsc4py/PETSc/Vec.pyx:1042
Return type
None
setLGMap(lgmap)
Set the local-to-global mapping.
Logically collective.
This allows users to insert vector entries using a local numbering with setValuesLocal.
SEE ALSO:
setValues, setValuesLocal, getLGMap, VecSetLocalToGlobalMapping
Source code at petsc4py/PETSc/Vec.pyx:2884
Parameters
lgmap (LGMap)
Return type
None
setMPIGhost(ghosts)
Set the ghost points for a ghosted vector.
Collective.
Parameters
ghosts (Sequence[int]) -- Global indices of ghost points.
Return type
None
SEE ALSO:
createGhost
Source code at petsc4py/PETSc/Vec.pyx:3366
setNestSubVecs(sx, idxm=None)
Set the component vectors at specified indices in the nested vector.
Not collective.
Parameters
• sx (Sequence[Vec]) -- Array of component vectors.
• idxm (Sequence[int] | None) -- Indices of the component vectors, defaults to
range(len(sx)).
Return type
None
SEE ALSO:
getNestSubVecs, VecNestSetSubVecs
Source code at petsc4py/PETSc/Vec.pyx:3473
setOption(option, flag)
Set option.
Collective.
SEE ALSO:
VecSetOption
Source code at petsc4py/PETSc/Vec.pyx:1067
Parameters
• option (Option)
• flag (bool)
Return type
None
setOptionsPrefix(prefix)
Set the prefix used for searching for options in the database.
Logically collective.
SEE ALSO:
Working with PETSc options, getOptionsPrefix, VecSetOptionsPrefix
Source code at petsc4py/PETSc/Vec.pyx:1000
Parameters
prefix (str | None)
Return type
None
setRandom(random=None)
Set all components of the vector to random numbers.
Collective.
Parameters
random (Random | None) -- Random number generator. If None then one will be created
internally.
Return type
None
SEE ALSO:
VecSetRandom
Source code at petsc4py/PETSc/Vec.pyx:2317
setSizes(size, bsize=None)
Set the local and global sizes of the vector.
Collective.
Parameters
• size (LayoutSizeSpec) -- Vector size.
• bsize (int | None) -- Vector block size. If None, bsize = 1.
Return type
None
SEE ALSO:
getSizes, VecSetSizes
Source code at petsc4py/PETSc/Vec.pyx:218
setType(vec_type)
Set the vector type.
Collective.
Parameters
vec_type (Type | str) -- The vector type.
Return type
None
SEE ALSO:
create, getType, VecSetType
Source code at petsc4py/PETSc/Vec.pyx:199
setUp()
Set up the internal data structures for using the vector.
Collective.
SEE ALSO:
create, destroy, VecSetUp
Source code at petsc4py/PETSc/Vec.pyx:1054
Return type
Self
setValue(index, value, addv=None)
Insert or add a single value in the vector.
Not collective.
Parameters
• index (int) -- Location to write to. Negative indices are ignored.
• value (Scalar) -- Value to insert at index.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValue cannot be made with different values for addv without
intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValues, VecSetValues
Source code at petsc4py/PETSc/Vec.pyx:2771
setValueLocal(index, value, addv=None)
Insert or add a single value in the vector using a local numbering.
Not collective.
Parameters
• index (int) -- Location to write to.
• value (Scalar) -- Value to insert at index.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValueLocal cannot be made with different values for addv without
intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValuesLocal, VecSetValuesLocal
Source code at petsc4py/PETSc/Vec.pyx:2914
setValues(indices, values, addv=None)
Insert or add multiple values in the vector.
Not collective.
Parameters
• indices (Sequence[int]) -- Locations to write to. Negative indices are ignored.
• values (Sequence[Scalar]) -- Values to insert at indices.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValues cannot be made with different values for addv without
intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValue, VecSetValues
Source code at petsc4py/PETSc/Vec.pyx:2808
setValuesBlocked(indices, values, addv=None)
Insert or add blocks of values in the vector.
Not collective.
Equivalent to x[bs*indices[i]+j] = y[bs*i+j] for 0 <= i < len(indices), 0 <= j < bs and bs
block_size.
Parameters
• indices (Sequence[int]) -- Block indices to write to. Negative indices are
ignored.
• values (Sequence[Scalar]) -- Values to insert at indices. Should have length
len(indices) * vec.block_size.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValuesBlocked cannot be made with different values for addv without
intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValues, VecSetValuesBlocked
Source code at petsc4py/PETSc/Vec.pyx:2842
setValuesBlockedLocal(indices, values, addv=None)
Insert or add blocks of values in the vector with a local numbering.
Not collective.
Equivalent to x[bs*indices[i]+j] = y[bs*i+j] for 0 <= i < len(indices), 0 <= j < bs and bs
block_size.
Parameters
• indices (Sequence[int]) -- Local block indices to write to.
• values (Sequence[Scalar]) -- Values to insert at indices. Should have length
len(indices) * vec.block_size.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValuesBlockedLocal cannot be made with different values for addv
without intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValuesBlocked, setValuesLocal, VecSetValuesBlockedLocal
Source code at petsc4py/PETSc/Vec.pyx:2985
setValuesLocal(indices, values, addv=None)
Insert or add multiple values in the vector with a local numbering.
Not collective.
Parameters
• indices (Sequence[int]) -- Locations to write to.
• values (Sequence[Scalar]) -- Values to insert at indices.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
Notes
The values may be cached so assemblyBegin and assemblyEnd must be called after all calls of
this method are completed.
Multiple calls to setValuesLocal cannot be made with different values for addv without
intermediate calls to assemblyBegin and assemblyEnd.
SEE ALSO:
setValues, VecSetValuesLocal
Source code at petsc4py/PETSc/Vec.pyx:2951
setValuesStagStencil(indices, values, addv=None)
Not implemented.
Source code at petsc4py/PETSc/Vec.pyx:2880
Return type
None
shift(alpha)
Shift all entries in the vector.
Collective.
This method sets each entry (xₙ) in the vector to xₙ + ɑ.
Parameters
alpha (Scalar) -- The shift to apply to the vector values.
Return type
None
SEE ALSO:
scale, VecShift
Source code at petsc4py/PETSc/Vec.pyx:2423
sqrtabs()
Replace each entry (xₙ) in the vector by √|xₙ|.
Logically collective.
SEE ALSO:
VecSqrtAbs
Source code at petsc4py/PETSc/Vec.pyx:2281
Return type
None
strideGather(field, vec, addv=None)
Insert component values into a single-component vector.
Collective.
The current vector is expected to be multi-component (block_size greater than 1) and the
target vector is expected to be single-component.
Parameters
• field (int) -- Component index. Must be between 0 and vec.block_size.
• vec (Vec) -- Single-component vector to be inserted into.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
strideScatter, VecStrideScatter
Source code at petsc4py/PETSc/Vec.pyx:3231
strideMax(field)
Return the maximum of entries in a subvector.
Collective.
Equivalent to max(x[field], x[field+bs], x[field+2*bs], ...) where bs is block_size.
Parameters
field (int) -- Component index. Must be between 0 and vec.block_size.
Returns
• int -- Location of maximum.
• float -- Maximum value.
Return type
tuple[int, float]
SEE ALSO:
strideScale, strideSum, strideMin, VecStrideMax
Source code at petsc4py/PETSc/Vec.pyx:3137
strideMin(field)
Return the minimum of entries in a subvector.
Collective.
Equivalent to min(x[field], x[field+bs], x[field+2*bs], ...) where bs is block_size.
Parameters
field (int) -- Component index. Must be between 0 and vec.block_size.
Returns
• int -- Location of minimum.
• float -- Minimum value.
Return type
tuple[int, float]
SEE ALSO:
strideScale, strideSum, strideMax, VecStrideMin
Source code at petsc4py/PETSc/Vec.pyx:3106
strideNorm(field, norm_type=None)
Return the norm of entries in a subvector.
Collective.
Equivalent to norm(x[field], x[field+bs], x[field+2*bs], ...) where bs is block_size.
Parameters
• field (int) -- Component index. Must be between 0 and vec.block_size.
• norm_type (NormTypeSpec) -- The norm type.
Return type
float | tuple[float, float]
SEE ALSO:
norm, strideScale, strideSum, VecStrideNorm
Source code at petsc4py/PETSc/Vec.pyx:3168
strideScale(field, alpha)
Scale a component of the vector.
Logically collective.
Parameters
• field (int) -- Component index. Must be between 0 and vec.block_size.
• alpha (Scalar) -- Factor to multiple the component entries by.
Return type
None
SEE ALSO:
strideSum, strideMin, strideMax, VecStrideScale
Source code at petsc4py/PETSc/Vec.pyx:3062
strideScatter(field, vec, addv=None)
Scatter entries into a component of another vector.
Collective.
The current vector is expected to be single-component (block_size of 1) and the target
vector is expected to be multi-component.
Parameters
• field (int) -- Component index. Must be between 0 and vec.block_size.
• vec (Vec) -- Multi-component vector to be scattered into.
• addv (InsertModeSpec) -- Insertion mode.
Return type
None
SEE ALSO:
strideGather, VecStrideScatter
Source code at petsc4py/PETSc/Vec.pyx:3200
strideSum(field)
Sum subvector entries.
Collective.
Equivalent to sum(x[field], x[field+bs], x[field+2*bs], ...) where bs is block_size.
Parameters
field (int) -- Component index. Must be between 0 and vec.block_size.
Return type
Scalar
SEE ALSO:
strideScale, strideMin, strideMax, VecStrideSum
Source code at petsc4py/PETSc/Vec.pyx:3083
sum() Return the sum of all the entries of the vector.
Collective.
SEE ALSO:
VecSum
Source code at petsc4py/PETSc/Vec.pyx:2166
Return type
Scalar
swap(vec)
Swap the content of two vectors.
Logically collective.
Parameters
vec (Vec) -- The vector to swap data with.
Return type
None
SEE ALSO:
VecSwap
Source code at petsc4py/PETSc/Vec.pyx:2443
tDot(vec)
Return the indefinite dot product with vec.
Collective.
This computes yᵀ·x with self as x, vec as y and where yᵀ denotes the transpose of y.
Parameters
vec (Vec) -- Vector to compute the indefinite dot product with.
Return type
Scalar
SEE ALSO:
tDotBegin, tDotEnd, dot, VecTDot
Source code at petsc4py/PETSc/Vec.pyx:1846
tDotBegin(vec)
Begin computing the indefinite dot product.
Collective.
This should be paired with a call to tDotEnd.
Parameters
vec (Vec) -- Vector to compute the indefinite dot product with.
Return type
None
SEE ALSO:
tDotEnd, tDot, VecTDotBegin
Source code at petsc4py/PETSc/Vec.pyx:1868
tDotEnd(vec)
Finish computing the indefinite dot product initiated with tDotBegin.
Collective.
SEE ALSO:
tDotBegin, tDot, VecTDotEnd
Source code at petsc4py/PETSc/Vec.pyx:1888
Parameters
vec (Vec)
Return type
Scalar
toDLPack(mode='rw')
Return a DLPack PyCapsule wrapping the vector data.
Collective.
Parameters
mode (AccessModeSpec) -- Access mode for the vector.
Returns
Capsule of a DLPack tensor wrapping a Vec.
Return type
PyCapsule
Notes
It is important that the access mode is respected by the consumer as this is not enforced
internally.
SEE ALSO:
createWithDLPack
Source code at petsc4py/PETSc/Vec.pyx:726
view(viewer=None)
Display the vector.
Collective.
Parameters
viewer (Viewer | None) -- A Viewer instance or None for the default viewer.
Return type
None
SEE ALSO:
load, VecView
Source code at petsc4py/PETSc/Vec.pyx:144
waxpy(alpha, x, y)
Compute and store w = ɑ·x + y.
Logically collective.
Parameters
• alpha (Scalar) -- Scale factor.
• x (Vec) -- First input vector.
• y (Vec) -- Second input vector.
Return type
None
SEE ALSO:
axpy, aypx, axpby, maxpy, VecWAXPY
Source code at petsc4py/PETSc/Vec.pyx:2547
zeroEntries()
Set all entries in the vector to zero.
Logically collective.
SEE ALSO:
set, VecZeroEntries
Source code at petsc4py/PETSc/Vec.pyx:2358
Return type
None
Attributes Documentation
array Alias for array_w.
Source code at petsc4py/PETSc/Vec.pyx:3642
array_r
Read-only ndarray containing the local portion of the vector.
Source code at petsc4py/PETSc/Vec.pyx:3632
array_w
Writeable ndarray containing the local portion of the vector.
Source code at petsc4py/PETSc/Vec.pyx:3623
block_size
The block size.
Source code at petsc4py/PETSc/Vec.pyx:3598
buffer Alias for buffer_w.
Source code at petsc4py/PETSc/Vec.pyx:3637
buffer_r
Read-only buffered view of the local portion of the vector.
Source code at petsc4py/PETSc/Vec.pyx:3618
buffer_w
Writeable buffered view of the local portion of the vector.
Source code at petsc4py/PETSc/Vec.pyx:3613
local_size
The local vector size.
Source code at petsc4py/PETSc/Vec.pyx:3593
owner_range
The locally owned range of indices in the form [low, high).
Source code at petsc4py/PETSc/Vec.pyx:3603
owner_ranges
The range of indices owned by each process.
Source code at petsc4py/PETSc/Vec.pyx:3608
size The global vector size.
Source code at petsc4py/PETSc/Vec.pyx:3588
sizes The local and global vector sizes.
Source code at petsc4py/PETSc/Vec.pyx:3580
petsc4py.PETSc.Viewer
class petsc4py.PETSc.Viewer
Bases: Object
Viewer object.
Viewer is described in the PETSc manual.
Viewers can be called as functions where the argument specified is the PETSc object to be viewed.
See the example below.
Examples
>>> from petsc4py import PETSc
>>> u = PETSc.Vec().createWithArray([1,2])
>>> v = PETSc.Viewer()
>>> v(u)
Vec Object: 1 MPI process
type: seq
1.
2.
SEE ALSO:
PetscViewer
Enumerations
┌──────────┬───────────────────┐
│ DrawSize │ Window size. │
├──────────┼───────────────────┤
│ FileMode │ Viewer file mode. │
├──────────┼───────────────────┤
│ Format │ Viewer format. │
├──────────┼───────────────────┤
│ Type │ Viewer type. │
└──────────┴───────────────────┘
petsc4py.PETSc.Viewer.DrawSize
class petsc4py.PETSc.Viewer.DrawSize
Bases: object
Window size.
Attributes Summary
┌──────────────┬───────────────────────────────────┐
│ FULL │ Constant FULL of type int │
├──────────────┼───────────────────────────────────┤
│ FULL_SIZE │ Constant FULL_SIZE of type int │
├──────────────┼───────────────────────────────────┤
│ HALF │ Constant HALF of type int │
├──────────────┼───────────────────────────────────┤
│ HALF_SIZE │ Constant HALF_SIZE of type int │
├──────────────┼───────────────────────────────────┤
│ QUARTER │ Constant QUARTER of type int │
├──────────────┼───────────────────────────────────┤
│ QUARTER_SIZE │ Constant QUARTER_SIZE of type int │
├──────────────┼───────────────────────────────────┤
│ THIRD │ Constant THIRD of type int │
├──────────────┼───────────────────────────────────┤
│ THIRD_SIZE │ Constant THIRD_SIZE of type int │
└──────────────┴───────────────────────────────────┘
Attributes Documentation
FULL: int = FULL
Constant FULL of type int
FULL_SIZE: int = FULL_SIZE
Constant FULL_SIZE of type int
HALF: int = HALF
Constant HALF of type int
HALF_SIZE: int = HALF_SIZE
Constant HALF_SIZE of type int
QUARTER: int = QUARTER
Constant QUARTER of type int
QUARTER_SIZE: int = QUARTER_SIZE
Constant QUARTER_SIZE of type int
THIRD: int = THIRD
Constant THIRD of type int
THIRD_SIZE: int = THIRD_SIZE
Constant THIRD_SIZE of type int
petsc4py.PETSc.Viewer.FileMode
class petsc4py.PETSc.Viewer.FileMode
Bases: object
Viewer file mode.
Attributes Summary
┌───────────────┬────────────────────────────────────┐
│ A │ Constant A of type int │
├───────────────┼────────────────────────────────────┤
│ APPEND │ Constant APPEND of type int │
├───────────────┼────────────────────────────────────┤
│ APPEND_UPDATE │ Constant APPEND_UPDATE of type int │
├───────────────┼────────────────────────────────────┤
│ AU │ Constant AU of type int │
├───────────────┼────────────────────────────────────┤
│ R │ Constant R of type int │
├───────────────┼────────────────────────────────────┤
│ READ │ Constant READ of type int │
├───────────────┼────────────────────────────────────┤
│ U │ Constant U of type int │
├───────────────┼────────────────────────────────────┤
│ UA │ Constant UA of type int │
├───────────────┼────────────────────────────────────┤
│ UPDATE │ Constant UPDATE of type int │
├───────────────┼────────────────────────────────────┤
│ W │ Constant W of type int │
├───────────────┼────────────────────────────────────┤
│ WRITE │ Constant WRITE of type int │
└───────────────┴────────────────────────────────────┘
Attributes Documentation
A: int = A
Constant A of type int
APPEND: int = APPEND
Constant APPEND of type int
APPEND_UPDATE: int = APPEND_UPDATE
Constant APPEND_UPDATE of type int
AU: int = AU
Constant AU of type int
R: int = R
Constant R of type int
READ: int = READ
Constant READ of type int
U: int = U
Constant U of type int
UA: int = UA
Constant UA of type int
UPDATE: int = UPDATE
Constant UPDATE of type int
W: int = W
Constant W of type int
WRITE: int = WRITE
Constant WRITE of type int
petsc4py.PETSc.Viewer.Format
class petsc4py.PETSc.Viewer.Format
Bases: object
Viewer format.
Attributes Summary
┌────────────────────┬───────────────────────────────────────┐
│ ASCII_COMMON │ Constant ASCII_COMMON of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_CSV │ Constant ASCII_CSV of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_DENSE │ Constant ASCII_DENSE of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_FACTOR_INFO │ Constant ASCII_FACTOR_INFO of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_GLVIS │ Constant ASCII_GLVIS of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_IMPL │ Constant ASCII_IMPL of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_INDEX │ Constant ASCII_INDEX of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_INFO │ Constant ASCII_INFO of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_INFO_DETAIL │ Constant ASCII_INFO_DETAIL of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_LATEX │ Constant ASCII_LATEX of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_MATHEMATICA │ Constant ASCII_MATHEMATICA of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_MATLAB │ Constant ASCII_MATLAB of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_MATRIXMARKET │ Constant ASCII_MATRIXMARKET of type ‐ │
│ │ int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_PCICE │ Constant ASCII_PCICE of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_PYTHON │ Constant ASCII_PYTHON of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_SYMMODU │ Constant ASCII_SYMMODU of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_VTK │ Constant ASCII_VTK of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_VTK_CELL │ Constant ASCII_VTK_CELL of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_VTK_COORDS │ Constant ASCII_VTK_COORDS of type int │
├────────────────────┼───────────────────────────────────────┤
│ ASCII_XML │ Constant ASCII_XML of type int │
├────────────────────┼───────────────────────────────────────┤
│ BINARY_MATLAB │ Constant BINARY_MATLAB of type int │
├────────────────────┼───────────────────────────────────────┤
│ DEFAULT │ Constant DEFAULT of type int │
├────────────────────┼───────────────────────────────────────┤
│ DRAW_BASIC │ Constant DRAW_BASIC of type int │
├────────────────────┼───────────────────────────────────────┤
│ DRAW_CONTOUR │ Constant DRAW_CONTOUR of type int │
├────────────────────┼───────────────────────────────────────┤
│ DRAW_LG │ Constant DRAW_LG of type int │
├────────────────────┼───────────────────────────────────────┤
│ DRAW_LG_XRANGE │ Constant DRAW_LG_XRANGE of type int │
├────────────────────┼───────────────────────────────────────┤
│ DRAW_PORTS │ Constant DRAW_PORTS of type int │
├────────────────────┼───────────────────────────────────────┤
│ FAILED │ Constant FAILED of type int │
├────────────────────┼───────────────────────────────────────┤
│ HDF5_MAT │ Constant HDF5_MAT of type int │
├────────────────────┼───────────────────────────────────────┤
│ HDF5_PETSC │ Constant HDF5_PETSC of type int │
├────────────────────┼───────────────────────────────────────┤
│ HDF5_VIZ │ Constant HDF5_VIZ of type int │
├────────────────────┼───────────────────────────────────────┤
│ HDF5_XDMF │ Constant HDF5_XDMF of type int │
├────────────────────┼───────────────────────────────────────┤
│ LOAD_BALANCE │ Constant LOAD_BALANCE of type int │
├────────────────────┼───────────────────────────────────────┤
│ NATIVE │ Constant NATIVE of type int │
├────────────────────┼───────────────────────────────────────┤
│ NOFORMAT │ Constant NOFORMAT of type int │
├────────────────────┼───────────────────────────────────────┤
│ VTK_VTR │ Constant VTK_VTR of type int │
├────────────────────┼───────────────────────────────────────┤
│ VTK_VTS │ Constant VTK_VTS of type int │
├────────────────────┼───────────────────────────────────────┤
│ VTK_VTU │ Constant VTK_VTU of type int │
└────────────────────┴───────────────────────────────────────┘
Attributes Documentation
ASCII_COMMON: int = ASCII_COMMON
Constant ASCII_COMMON of type int
ASCII_CSV: int = ASCII_CSV
Constant ASCII_CSV of type int
ASCII_DENSE: int = ASCII_DENSE
Constant ASCII_DENSE of type int
ASCII_FACTOR_INFO: int = ASCII_FACTOR_INFO
Constant ASCII_FACTOR_INFO of type int
ASCII_GLVIS: int = ASCII_GLVIS
Constant ASCII_GLVIS of type int
ASCII_IMPL: int = ASCII_IMPL
Constant ASCII_IMPL of type int
ASCII_INDEX: int = ASCII_INDEX
Constant ASCII_INDEX of type int
ASCII_INFO: int = ASCII_INFO
Constant ASCII_INFO of type int
ASCII_INFO_DETAIL: int = ASCII_INFO_DETAIL
Constant ASCII_INFO_DETAIL of type int
ASCII_LATEX: int = ASCII_LATEX
Constant ASCII_LATEX of type int
ASCII_MATHEMATICA: int = ASCII_MATHEMATICA
Constant ASCII_MATHEMATICA of type int
ASCII_MATLAB: int = ASCII_MATLAB
Constant ASCII_MATLAB of type int
ASCII_MATRIXMARKET: int = ASCII_MATRIXMARKET
Constant ASCII_MATRIXMARKET of type int
ASCII_PCICE: int = ASCII_PCICE
Constant ASCII_PCICE of type int
ASCII_PYTHON: int = ASCII_PYTHON
Constant ASCII_PYTHON of type int
ASCII_SYMMODU: int = ASCII_SYMMODU
Constant ASCII_SYMMODU of type int
ASCII_VTK: int = ASCII_VTK
Constant ASCII_VTK of type int
ASCII_VTK_CELL: int = ASCII_VTK_CELL
Constant ASCII_VTK_CELL of type int
ASCII_VTK_COORDS: int = ASCII_VTK_COORDS
Constant ASCII_VTK_COORDS of type int
ASCII_XML: int = ASCII_XML
Constant ASCII_XML of type int
BINARY_MATLAB: int = BINARY_MATLAB
Constant BINARY_MATLAB of type int
DEFAULT: int = DEFAULT
Constant DEFAULT of type int
DRAW_BASIC: int = DRAW_BASIC
Constant DRAW_BASIC of type int
DRAW_CONTOUR: int = DRAW_CONTOUR
Constant DRAW_CONTOUR of type int
DRAW_LG: int = DRAW_LG
Constant DRAW_LG of type int
DRAW_LG_XRANGE: int = DRAW_LG_XRANGE
Constant DRAW_LG_XRANGE of type int
DRAW_PORTS: int = DRAW_PORTS
Constant DRAW_PORTS of type int
FAILED: int = FAILED
Constant FAILED of type int
HDF5_MAT: int = HDF5_MAT
Constant HDF5_MAT of type int
HDF5_PETSC: int = HDF5_PETSC
Constant HDF5_PETSC of type int
HDF5_VIZ: int = HDF5_VIZ
Constant HDF5_VIZ of type int
HDF5_XDMF: int = HDF5_XDMF
Constant HDF5_XDMF of type int
LOAD_BALANCE: int = LOAD_BALANCE
Constant LOAD_BALANCE of type int
NATIVE: int = NATIVE
Constant NATIVE of type int
NOFORMAT: int = NOFORMAT
Constant NOFORMAT of type int
VTK_VTR: int = VTK_VTR
Constant VTK_VTR of type int
VTK_VTS: int = VTK_VTS
Constant VTK_VTS of type int
VTK_VTU: int = VTK_VTU
Constant VTK_VTU of type int
petsc4py.PETSc.Viewer.Type
class petsc4py.PETSc.Viewer.Type
Bases: object
Viewer type.
Attributes Summary
┌─────────────┬────────────────────────────────┐
│ ADIOS │ Object ADIOS of type str │
├─────────────┼────────────────────────────────┤
│ ASCII │ Object ASCII of type str │
├─────────────┼────────────────────────────────┤
│ BINARY │ Object BINARY of type str │
├─────────────┼────────────────────────────────┤
│ DRAW │ Object DRAW of type str │
├─────────────┼────────────────────────────────┤
│ EXODUSII │ Object EXODUSII of type str │
├─────────────┼────────────────────────────────┤
│ GLVIS │ Object GLVIS of type str │
├─────────────┼────────────────────────────────┤
│ HDF5 │ Object HDF5 of type str │
├─────────────┼────────────────────────────────┤
│ MATHEMATICA │ Object MATHEMATICA of type str │
├─────────────┼────────────────────────────────┤
│ MATLAB │ Object MATLAB of type str │
├─────────────┼────────────────────────────────┤
│ SAWS │ Object SAWS of type str │
├─────────────┼────────────────────────────────┤
│ SOCKET │ Object SOCKET of type str │
├─────────────┼────────────────────────────────┤
│ STRING │ Object STRING of type str │
├─────────────┼────────────────────────────────┤
│ VTK │ Object VTK of type str │
├─────────────┼────────────────────────────────┤
│ VU │ Object VU of type str │
└─────────────┴────────────────────────────────┘
Attributes Documentation
ADIOS: str = ADIOS
Object ADIOS of type str
ASCII: str = ASCII
Object ASCII of type str
BINARY: str = BINARY
Object BINARY of type str
DRAW: str = DRAW
Object DRAW of type str
EXODUSII: str = EXODUSII
Object EXODUSII of type str
GLVIS: str = GLVIS
Object GLVIS of type str
HDF5: str = HDF5
Object HDF5 of type str
MATHEMATICA: str = MATHEMATICA
Object MATHEMATICA of type str
MATLAB: str = MATLAB
Object MATLAB of type str
SAWS: str = SAWS
Object SAWS of type str
SOCKET: str = SOCKET
Object SOCKET of type str
STRING: str = STRING
Object STRING of type str
VTK: str = VTK
Object VTK of type str
VU: str = VU
Object VU of type str
Methods Summary
┌───────────────────────────────────────┬───────────────────────────────────────┐
│ ASCII(name[, comm]) │ Return an ASCII viewer associated │
│ │ with the communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ BINARY([comm]) │ Return the default Type.BINARY viewer │
│ │ associated with the communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ DRAW([comm]) │ Return the default Type.DRAW viewer │
│ │ associated with the communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ STDERR([comm]) │ Return the standard error viewer │
│ │ associated with the communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ STDOUT([comm]) │ Return the standard output viewer │
│ │ associated with the communicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ addASCIITab(tabs) │ Increment the ASCII tab level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ clearDraw() │ Reset graphics. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ create([comm]) │ Create a viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createASCII(name[, mode, comm]) │ Create a viewer of type Type.ASCII. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createBinary(name[, mode, comm]) │ Create a viewer of type Type.BINARY. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createDraw([display, title, position, │ Create a Type.DRAW viewer. │
│ size, ...]) │ │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createHDF5(name[, mode, comm]) │ Create a viewer of type Type.HDF5. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createMPIIO(name[, mode, comm]) │ Create a viewer of type Type.BINARY │
│ │ supporting MPI-IO. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ createVTK(name[, mode, comm]) │ Create a viewer of type Type.VTK. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ destroy() │ Destroy the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ flush() │ Flush the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getASCIITab() │ Return the ASCII tab level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFileMode() │ Return the file mode. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFileName() │ Return file name. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getFormat() │ Return the format of the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getSubViewer([comm]) │ Return a viewer defined on a │
│ │ subcommunicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ getType() │ Return the type of the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ popASCIISynchronized() │ Disallow ASCII synchronized calls. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ popASCIITab() │ Pop an additional tab level pushed │
│ │ via pushASCIITab. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ popFormat() │ Pop format from the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ printfASCII(msg) │ Print a message. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ printfASCIISynchronized(msg) │ Print a synchronized message. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pushASCIISynchronized() │ Allow ASCII synchronized calls. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pushASCIITab() │ Push an additional tab level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ pushFormat(format) │ Push format to the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ restoreSubViewer(sub) │ Restore a viewer defined on a │
│ │ subcommunicator. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setASCIITab(tabs) │ Set ASCII tab level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setDrawInfo([display, title, │ Set window information for a │
│ position, size]) │ Type.DRAW viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFileMode(mode) │ Set file mode. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setFileName(name) │ Set file name. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ setType(vwr_type) │ Set the type of the viewer. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ subtractASCIITab(tabs) │ Decrement the ASCII tab level. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ useASCIITabs(flag) │ Enable/disable the use of ASCII tabs. │
├───────────────────────────────────────┼───────────────────────────────────────┤
│ view([obj]) │ View the viewer. │
└───────────────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
classmethod ASCII(name, comm=None)
Return an ASCII viewer associated with the communicator.
Collective.
Parameters
• name (str) -- The filename.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Viewer
Source code at petsc4py/PETSc/Viewer.pyx:580
classmethod BINARY(comm=None)
Return the default Type.BINARY viewer associated with the communicator.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Viewer
Source code at petsc4py/PETSc/Viewer.pyx:601
classmethod DRAW(comm=None)
Return the default Type.DRAW viewer associated with the communicator.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Viewer
Source code at petsc4py/PETSc/Viewer.pyx:619
classmethod STDERR(comm=None)
Return the standard error viewer associated with the communicator.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Viewer
Source code at petsc4py/PETSc/Viewer.pyx:562
classmethod STDOUT(comm=None)
Return the standard output viewer associated with the communicator.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Viewer
Source code at petsc4py/PETSc/Viewer.pyx:544
addASCIITab(tabs)
Increment the ASCII tab level.
Collective.
SEE ALSO:
PetscViewerASCIIAddTab
Source code at petsc4py/PETSc/Viewer.pyx:666
Parameters
tabs (int)
Return type
None
clearDraw()
Reset graphics.
Not collective.
SEE ALSO:
PetscViewerDrawClear
Source code at petsc4py/PETSc/Viewer.pyx:897
Return type
None
create(comm=None)
Create a viewer.
Collective.
Parameters
comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, PetscViewerCreate
Source code at petsc4py/PETSc/Viewer.pyx:180
createASCII(name, mode=None, comm=None)
Create a viewer of type Type.ASCII.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
create, setType, setFileMode, setFileName, Sys.getDefaultComm, setASCIITab, addASCIITab,
subtractASCIITab, getASCIITab
Source code at petsc4py/PETSc/Viewer.pyx:201
createBinary(name, mode=None, comm=None)
Create a viewer of type Type.BINARY.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
create, setType, setFileMode, setFileName, Sys.getDefaultComm
Source code at petsc4py/PETSc/Viewer.pyx:239
createDraw(display=None, title=None, position=None, size=None, comm=None)
Create a Type.DRAW viewer.
Collective.
Parameters
• display (str | None) -- The X display to use or None for the local machine.
• title (str | None) -- The window title or None for no title.
• position (tuple[int, int] | None) -- Screen coordinates of the upper left corner,
or None for default.
• size (tuple[int, int] | int | None) -- Window size or None for default.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Sys.getDefaultComm, PetscViewerDrawOpen
Source code at petsc4py/PETSc/Viewer.pyx:381
createHDF5(name, mode=None, comm=None)
Create a viewer of type Type.HDF5.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
create, setType, setFileMode, setFileName, Sys.getDefaultComm
Source code at petsc4py/PETSc/Viewer.pyx:345
createMPIIO(name, mode=None, comm=None)
Create a viewer of type Type.BINARY supporting MPI-IO.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
create, setType, setFileMode, setFileName, Sys.getDefaultComm
Source code at petsc4py/PETSc/Viewer.pyx:272
createVTK(name, mode=None, comm=None)
Create a viewer of type Type.VTK.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
create, setType, setFileMode, setFileName, Sys.getDefaultComm
Source code at petsc4py/PETSc/Viewer.pyx:309
destroy()
Destroy the viewer.
Collective.
SEE ALSO:
PetscViewerDestroy
Source code at petsc4py/PETSc/Viewer.pyx:167
Return type
Self
flush()
Flush the viewer.
Collective.
SEE ALSO:
PetscViewerFlush
Source code at petsc4py/PETSc/Viewer.pyx:785
Return type
None
getASCIITab()
Return the ASCII tab level.
Not collective.
SEE ALSO:
setASCIITab, PetscViewerASCIIGetTab
Source code at petsc4py/PETSc/Viewer.pyx:652
Return type
int
getFileMode()
Return the file mode.
Not collective.
SEE ALSO:
setFileMode, PetscViewerFileGetMode
Source code at petsc4py/PETSc/Viewer.pyx:809
Return type
FileMode
getFileName()
Return file name.
Not collective.
SEE ALSO:
setFileName, PetscViewerFileGetName
Source code at petsc4py/PETSc/Viewer.pyx:837
Return type
str
getFormat()
Return the format of the viewer.
Not collective.
SEE ALSO:
pushFormat, popFormat, PetscViewerGetFormat
Source code at petsc4py/PETSc/Viewer.pyx:464
Return type
Format
getSubViewer(comm=None)
Return a viewer defined on a subcommunicator.
Collective.
Parameters
comm (Comm | None) -- The subcommunicator. If None, uses COMM_SELF.
Return type
Viewer
Notes
Users must call restoreSubViewer when done.
SEE ALSO:
restoreSubViewer, PetscViewerGetSubViewer
Source code at petsc4py/PETSc/Viewer.pyx:502
getType()
Return the type of the viewer.
Not collective.
SEE ALSO:
setType, PetscViewerGetType
Source code at petsc4py/PETSc/Viewer.pyx:450
Return type
str
popASCIISynchronized()
Disallow ASCII synchronized calls.
Collective.
SEE ALSO:
printfASCIISynchronized, pushASCIISynchronized, PetscViewerASCIIPopSynchronized
Source code at petsc4py/PETSc/Viewer.pyx:705
Return type
None
popASCIITab()
Pop an additional tab level pushed via pushASCIITab.
Collective.
SEE ALSO:
pushASCIITab, PetscViewerASCIIPopTab
Source code at petsc4py/PETSc/Viewer.pyx:730
Return type
None
popFormat()
Pop format from the viewer.
Collective.
SEE ALSO:
pushFormat, PetscViewerPopFormat
Source code at petsc4py/PETSc/Viewer.pyx:490
Return type
None
printfASCII(msg)
Print a message.
Collective.
SEE ALSO:
PetscViewerASCIIPrintf
Source code at petsc4py/PETSc/Viewer.pyx:755
Parameters
msg (str)
Return type
None
printfASCIISynchronized(msg)
Print a synchronized message.
Collective.
SEE ALSO:
pushASCIISynchronized, PetscViewerASCIISynchronizedPrintf
Source code at petsc4py/PETSc/Viewer.pyx:769
Parameters
msg (str)
Return type
None
pushASCIISynchronized()
Allow ASCII synchronized calls.
Collective.
SEE ALSO:
printfASCIISynchronized, popASCIISynchronized, PetscViewerASCIIPushSynchronized
Source code at petsc4py/PETSc/Viewer.pyx:692
Return type
None
pushASCIITab()
Push an additional tab level.
Collective.
SEE ALSO:
popASCIITab, PetscViewerASCIIPushTab
Source code at petsc4py/PETSc/Viewer.pyx:718
Return type
None
pushFormat(format)
Push format to the viewer.
Collective.
SEE ALSO:
popFormat, PetscViewerPushFormat
Source code at petsc4py/PETSc/Viewer.pyx:478
Parameters
format (Format)
Return type
None
restoreSubViewer(sub)
Restore a viewer defined on a subcommunicator.
Collective.
Parameters
sub (Viewer) -- The subviewer obtained from getSubViewer.
Return type
None
SEE ALSO:
getSubViewer, PetscViewerRestoreSubViewer
Source code at petsc4py/PETSc/Viewer.pyx:526
setASCIITab(tabs)
Set ASCII tab level.
Collective.
SEE ALSO:
getASCIITab, PetscViewerASCIISetTab
Source code at petsc4py/PETSc/Viewer.pyx:639
Parameters
tabs (int)
Return type
None
setDrawInfo(display=None, title=None, position=None, size=None)
Set window information for a Type.DRAW viewer.
Collective.
Parameters
• display (str | None) -- The X display to use or None for the local machine.
• title (str | None) -- The window title or None for no title.
• position (tuple[int, int] | None) -- Screen coordinates of the upper left corner,
or None for default.
• size (tuple[int, int] | int | None) -- Window size or None for default.
Return type
None
Source code at petsc4py/PETSc/Viewer.pyx:853
setFileMode(mode)
Set file mode.
Collective.
SEE ALSO:
getFileMode, PetscViewerFileSetMode
Source code at petsc4py/PETSc/Viewer.pyx:797
Parameters
mode (FileMode | str)
Return type
None
setFileName(name)
Set file name.
Collective.
SEE ALSO:
getFileName, PetscViewerFileSetName
Source code at petsc4py/PETSc/Viewer.pyx:823
Parameters
name (str)
Return type
None
setType(vwr_type)
Set the type of the viewer.
Logically collective.
Parameters
vwr_type (Type | str) -- The type of the viewer.
Return type
None
SEE ALSO:
getType, PetscViewerSetType
Source code at petsc4py/PETSc/Viewer.pyx:431
subtractASCIITab(tabs)
Decrement the ASCII tab level.
Collective.
SEE ALSO:
PetscViewerASCIISubtractTab
Source code at petsc4py/PETSc/Viewer.pyx:679
Parameters
tabs (int)
Return type
None
useASCIITabs(flag)
Enable/disable the use of ASCII tabs.
Collective.
SEE ALSO:
PetscViewerASCIIUseTabs
Source code at petsc4py/PETSc/Viewer.pyx:742
Parameters
flag (bool)
Return type
None
view(obj=None)
View the viewer.
Collective.
Parameters
obj (Viewer | Object | None) -- A Viewer instance or None for the default viewer.
If none of the above applies, it assumes obj is an instance of Object and it calls
the generic view for obj.
Return type
None
Notes
SEE ALSO:
PetscViewerView
Source code at petsc4py/PETSc/Viewer.pyx:139
petsc4py.PETSc.ViewerHDF5
class petsc4py.PETSc.ViewerHDF5
Bases: Viewer
Viewer object for HDF5 file formats.
Viewer is described in the PETSc manual.
SEE ALSO:
Viewer
Methods Summary
┌────────────────────────────┬───────────────────────────────────────┐
│ create(name[, mode, comm]) │ Create a viewer of type Type.HDF5. │
├────────────────────────────┼───────────────────────────────────────┤
│ getGroup() │ Return the current group. │
├────────────────────────────┼───────────────────────────────────────┤
│ getTimestep() │ Return the current time step. │
├────────────────────────────┼───────────────────────────────────────┤
│ incrementTimestep() │ Increment the time step. │
├────────────────────────────┼───────────────────────────────────────┤
│ popGroup() │ Pop the current group from the stack. │
├────────────────────────────┼───────────────────────────────────────┤
│ popTimestepping() │ Deactivate the timestepping mode. │
├────────────────────────────┼───────────────────────────────────────┤
│ pushGroup(group) │ Set the current group. │
├────────────────────────────┼───────────────────────────────────────┤
│ pushTimestepping() │ Activate the timestepping mode. │
├────────────────────────────┼───────────────────────────────────────┤
│ setTimestep(timestep) │ Set the current time step. │
└────────────────────────────┴───────────────────────────────────────┘
Methods Documentation
create(name, mode=None, comm=None)
Create a viewer of type Type.HDF5.
Collective.
Parameters
• name (str) -- The filename associated with the viewer.
• mode (FileMode | str | None) -- The mode type.
• comm (Comm | None) -- MPI communicator, defaults to Sys.getDefaultComm.
Return type
Self
SEE ALSO:
Viewer.createHDF5
Source code at petsc4py/PETSc/Viewer.pyx:922
getGroup()
Return the current group.
Not collective.
SEE ALSO:
pushGroup, popGroup, PetscViewerHDF5GetGroup
Source code at petsc4py/PETSc/Viewer.pyx:1049
Return type
str
getTimestep()
Return the current time step.
Not collective.
SEE ALSO:
pushTimestepping, setTimestep, incrementTimestep, PetscViewerHDF5GetTimestep
Source code at petsc4py/PETSc/Viewer.pyx:982
Return type
int
incrementTimestep()
Increment the time step.
Logically collective.
SEE ALSO:
pushTimestepping, setTimestep, getTimestep, PetscViewerHDF5IncrementTimestep
Source code at petsc4py/PETSc/Viewer.pyx:1010
Return type
None
popGroup()
Pop the current group from the stack.
Logically collective.
SEE ALSO:
pushGroup, getGroup, PetscViewerHDF5PopGroup
Source code at petsc4py/PETSc/Viewer.pyx:1037
Return type
None
popTimestepping()
Deactivate the timestepping mode.
Logically collective.
SEE ALSO:
pushTimestepping, PetscViewerHDF5PopTimestepping
Source code at petsc4py/PETSc/Viewer.pyx:970
Return type
None
pushGroup(group)
Set the current group.
Logically collective.
SEE ALSO:
popGroup, getGroup, PetscViewerHDF5PushGroup
Source code at petsc4py/PETSc/Viewer.pyx:1023
Parameters
group (str)
Return type
None
pushTimestepping()
Activate the timestepping mode.
Logically collective.
SEE ALSO:
popTimestepping, PetscViewerHDF5PushTimestepping
Source code at petsc4py/PETSc/Viewer.pyx:958
Return type
None
setTimestep(timestep)
Set the current time step.
Logically collective.
SEE ALSO:
pushTimestepping, getTimestep, incrementTimestep, PetscViewerHDF5SetTimestep
Source code at petsc4py/PETSc/Viewer.pyx:997
Parameters
timestep (int)
Return type
None
Exceptions
┌───────┬──────────────┐
│ Error │ PETSc Error. │
└───────┴──────────────┘
petsc4py.PETSc.Error
exception petsc4py.PETSc.Error
PETSc Error.
ierr PETSc error code.
Type int
Functions
┌─────────────────────────┬───────────────────────────────────────┐
│ garbage_cleanup([comm]) │ Clean up unused PETSc objects. │
├─────────────────────────┼───────────────────────────────────────┤
│ garbage_view([comm]) │ Print summary of the garbage PETSc │
│ │ objects. │
└─────────────────────────┴───────────────────────────────────────┘
petsc4py.PETSc.garbage_cleanup
petsc4py.PETSc.garbage_cleanup(comm=None)
Clean up unused PETSc objects.
Collective.
Notes
If the communicator comm if not provided or it is None, then COMM_WORLD is used.
Source code at petsc4py/PETSc/cyclicgc.pxi:39
Parameters
comm (Comm | None)
Return type
None
petsc4py.PETSc.garbage_view
petsc4py.PETSc.garbage_view(comm=None)
Print summary of the garbage PETSc objects.
Collective.
Notes
Print out garbage summary on each rank of the communicator comm. If no communicator is provided
then COMM_WORLD is used.
Source code at petsc4py/PETSc/cyclicgc.pxi:63
Parameters
comm (Comm | None)
Return type
None
Attributes
┌────────────┬────────────────────────────────┐
│ DECIDE │ Constant DECIDE of type int │
├────────────┼────────────────────────────────┤
│ DEFAULT │ Constant DEFAULT of type int │
├────────────┼────────────────────────────────┤
│ DETERMINE │ Constant DETERMINE of type int │
├────────────┼────────────────────────────────┤
│ CURRENT │ Constant CURRENT of type int │
├────────────┼────────────────────────────────┤
│ UNLIMITED │ Constant UNLIMITED of type int │
├────────────┼────────────────────────────────┤
│ INFINITY │ Object INFINITY of type float │
├────────────┼────────────────────────────────┤
│ NINFINITY │ Object NINFINITY of type float │
├────────────┼────────────────────────────────┤
│ PINFINITY │ Object PINFINITY of type float │
├────────────┼────────────────────────────────┤
│ COMM_NULL │ Object COMM_NULL of type Comm │
├────────────┼────────────────────────────────┤
│ COMM_SELF │ Object COMM_SELF of type Comm │
├────────────┼────────────────────────────────┤
│ COMM_WORLD │ Object COMM_WORLD of type Comm │
└────────────┴────────────────────────────────┘
petsc4py.PETSc.DECIDE
petsc4py.PETSc.DECIDE: int = DECIDE
Constant DECIDE of type int
petsc4py.PETSc.DEFAULT
petsc4py.PETSc.DEFAULT: int = DEFAULT
Constant DEFAULT of type int
petsc4py.PETSc.DETERMINE
petsc4py.PETSc.DETERMINE: int = DETERMINE
Constant DETERMINE of type int
petsc4py.PETSc.CURRENT
petsc4py.PETSc.CURRENT: int = CURRENT
Constant CURRENT of type int
petsc4py.PETSc.UNLIMITED
petsc4py.PETSc.UNLIMITED: int = UNLIMITED
Constant UNLIMITED of type int
petsc4py.PETSc.INFINITY
petsc4py.PETSc.INFINITY: float = INFINITY
Object INFINITY of type float
petsc4py.PETSc.NINFINITY
petsc4py.PETSc.NINFINITY: float = NINFINITY
Object NINFINITY of type float
petsc4py.PETSc.PINFINITY
petsc4py.PETSc.PINFINITY: float = PINFINITY
Object PINFINITY of type float
petsc4py.PETSc.COMM_NULL
petsc4py.PETSc.COMM_NULL: Comm = COMM_NULL
Object COMM_NULL of type Comm
petsc4py.PETSc.COMM_SELF
petsc4py.PETSc.COMM_SELF: Comm = COMM_SELF
Object COMM_SELF of type Comm
petsc4py.PETSc.COMM_WORLD
petsc4py.PETSc.COMM_WORLD: Comm = COMM_WORLD
Object COMM_WORLD of type Comm
PETSC PYTHON TYPES
Here we discuss details about Python-aware PETSc types that can be used within the library.
In particular, we discuss matrices, preconditioners, Krylov solvers, nonlinear solvers and ODE
integrators.
The low-level, Cython implementation exposing the Python methods is in ‐
src/petsc4py/PETSc/libpetsc4py.pyx.
The scripts used here can be found at demo/python_types.
PETSc Python matrix type
PETSc provides a convenient way to compute the action of linear operators coded in Python through the
petsc4py.PETSc.Mat.Type.PYTHON type.
In addition to the matrix action, the implementation can expose additional methods for use within the
library. A template class for the supported methods is given below.
from petsc4py.typing import Scalar
from petsc4py.PETSc import Mat
from petsc4py.PETSc import Vec
from petsc4py.PETSc import IS
from petsc4py.PETSc import InsertMode
from petsc4py.PETSc import NormType
from petsc4py.PETSc import Viewer
# A template class with the Python methods supported by MATPYTHON
class MatPythonProtocol:
def mult(self, A: Mat, x: Vec, y: Vec) -> None:
"""Matrix vector multiplication: y = A @ x."""
...
def multAdd(self, A: Mat, x: Vec, y: Vec, z: Vec) -> None:
"""Matrix vector multiplication: z = A @ x + y."""
...
def multTranspose(self, A: Mat, x: Vec, y: Vec) -> None:
"""Transposed matrix vector multiplication: y = A^T @ x."""
...
def multTransposeAdd(self, A: Mat, x: Vec, y: Vec, z: Vec) -> None:
"""Transposed matrix vector multiplication: z = A^T @ x + y."""
...
def multHermitian(self, A: Mat, x: Vec, y: Vec) -> None:
"""Hermitian matrix vector multiplication: y = A^H @ x."""
...
def multHermitianAdd(self, A: Mat, x: Vec, y: Vec, z: Vec) -> None:
"""Hermitian matrix vector multiplication: z = A^H @ x + y."""
...
def view(self, A: Mat, viewer: Viewer) -> None:
"""View the matrix."""
...
def setFromOptions(self, A: Mat) -> None:
"""Process command line for customization."""
...
def multDiagonalBlock(self, A: Mat, x: Vec, y: Vec) -> None:
"""Perform the on-process matrix vector multiplication."""
...
def createVecs(self, A: Mat) -> tuple[Vec, Vec]:
"""Return tuple of vectors (x,y) suitable for A @ x = y."""
...
def scale(self, A: Mat, s: Scalar) -> None:
"""Scale the matrix by a scalar."""
...
def shift(self, A: Mat, s: Scalar) -> None:
"""Shift the matrix by a scalar."""
...
def createSubMatrix(self, A: Mat, r: IS, c: IS, out: Mat) -> Mat:
"""Return the submatrix corresponding to r rows and c columns.
Matrix out must be reused if not None.
"""
...
def zeroRowsColumns(self, A: Mat, r: IS, diag: Scalar, x: Vec, b: Vec) -> None:
"""Zero rows and columns of the matrix corresponding to the index set r.
Insert diag on the diagonal and modify vectors x and b accordingly if not None.
"""
...
def getDiagonal(self, A: Mat, d: Vec) -> None:
"""Compute the diagonal of the matrix: d = diag(A)."""
...
def setDiagonal(self, A: Mat, d: Vec, im: InsertMode) -> None:
"""Set the diagonal of the matrix."""
...
def missingDiagonal(self, A: Mat, d: Vec, im: InsertMode) -> tuple[bool, int]:
"""Return a flag indicating if the matrix is missing a diagonal entry and the location."""
...
def diagonalScale(self, A: Mat, L: Vec, R: Vec) -> None:
"""Perform left and right diagonal scaling if vectors are not None.
A = diag(L)@A@diag(R).
"""
...
def getDiagonalBlock(self, A: Mat) -> Mat:
"""Return the on-process matrix."""
...
def setUp(self, A: Mat) -> None:
"""Perform the required setup."""
...
def duplicate(self, A: Mat, op: Mat.DuplicateOption) -> Mat:
"""Duplicate the matrix."""
...
def copy(self, A: Mat, B: Mat, op: Mat.Structure) -> None:
"""Copy the matrix: B = A."""
...
def productSetFromOptions(
self, A: Mat, prodtype: str, X: Mat, Y: Mat, Z: Mat
) -> bool:
"""The boolean flag indicating if the matrix supports prodtype."""
...
def productSymbolic(
self, A: Mat, product: Mat, producttype: str, X: Mat, Y: Mat, Z: Mat
) -> None:
"""Perform the symbolic stage of the requested matrix product."""
...
def productNumeric(
self, A: Mat, product: Mat, producttype: str, X: Mat, Y: Mat, Z: Mat
) -> None:
"""Perform the numeric stage of the requested matrix product."""
...
def zeroEntries(self, A: Mat) -> None:
"""Set the matrix to zero."""
...
def norm(self, A: Mat, normtype: NormType) -> float:
"""Compute the norm of the matrix."""
...
def solve(self, A: Mat, y: Vec, x: Vec) -> None:
"""Solve the equation: x = inv(A) y."""
...
def solveAdd(self, A: Mat, y: Vec, z: Vec, x: Vec) -> None:
"""Solve the equation: x = inv(A) y + z."""
...
def solveTranspose(self, A: Mat, y: Vec, x: Vec) -> None:
"""Solve the equation: x = inv(A)^T y."""
...
def solveTransposeAdd(self, A: Mat, y: Vec, z: Vec, x: Vec) -> None:
"""Solve the equation: x = inv(A)^T y + z."""
...
def SOR(
self,
A: Mat,
b: Vec,
omega: float,
sortype: Mat.SORType,
shift: float,
its: int,
lits: int,
x: Vec,
) -> None:
"""Perform SOR iterations."""
...
def conjugate(self, A: Mat) -> None:
"""Perform the conjugation of the matrix: A = conj(A)."""
...
def imagPart(self, A: Mat) -> None:
"""Set real part to zero. A = imag(A)."""
...
def realPart(self, A: Mat) -> None:
"""Set imaginary part to zero. A = real(A)."""
...
In the example below, we create an operator that applies the Laplacian operator on a two-dimensional
grid, and use it to solve the associated linear system. The default preconditioner in the script is
petsc4py.PETSc.PC.Type.JACOBI which needs to access the diagonal of the matrix.
# ------------------------------------------------------------------------
#
# Poisson problem. This problem is modeled by the partial
# differential equation
#
# -Laplacian(u) = 1, 0 < x,y < 1,
#
# with boundary conditions
#
# u = 0 for x = 0, x = 1, y = 0, y = 1
#
# A finite difference approximation with the usual 5-point stencil
# is used to discretize the boundary value problem to obtain a
# nonlinear system of equations. The problem is solved in a 2D
# rectangular domain, using distributed arrays (DAs) to partition
# the parallel grid.
#
# ------------------------------------------------------------------------
# We first import petsc4py and sys to initialize PETSc
import sys
import petsc4py
petsc4py.init(sys.argv)
# Import the PETSc module
from petsc4py import PETSc
# Here we define a class representing the discretized operator
# This allows us to apply the operator "matrix-free"
class Poisson2D:
def __init__(self, da):
self.da = da
self.localX = da.createLocalVec()
# This is the method that PETSc will look for when applying
# the operator. `X` is the PETSc input vector, `Y` the output vector,
# while `mat` is the PETSc matrix holding the PETSc datastructures.
def mult(self, mat, X, Y):
# Grid sizes
mx, my = self.da.getSizes()
hx, hy = (1.0 / m for m in [mx, my])
# Bounds for the local part of the grid this process owns
(xs, xe), (ys, ye) = self.da.getRanges()
# Map global vector to local vectors
self.da.globalToLocal(X, self.localX)
# We can access the vector data as NumPy arrays
x = self.da.getVecArray(self.localX)
y = self.da.getVecArray(Y)
# Loop on the local grid and compute the local action of the operator
for j in range(ys, ye):
for i in range(xs, xe):
u = x[i, j] # center
u_e = u_w = u_n = u_s = 0
if i > 0:
u_w = x[i - 1, j] # west
if i < mx - 1:
u_e = x[i + 1, j] # east
if j > 0:
u_s = x[i, j - 1] # south
if j < ny - 1:
u_n = x[i, j + 1] # north
u_xx = (-u_e + 2 * u - u_w) * hy / hx
u_yy = (-u_n + 2 * u - u_s) * hx / hy
y[i, j] = u_xx + u_yy
# This is the method that PETSc will look for when the diagonal of the matrix is needed.
def getDiagonal(self, mat, D):
mx, my = self.da.getSizes()
hx, hy = (1.0 / m for m in [mx, my])
(xs, xe), (ys, ye) = self.da.getRanges()
d = self.da.getVecArray(D)
# Loop on the local grid and compute the diagonal
for j in range(ys, ye):
for i in range(xs, xe):
d[i, j] = 2 * hy / hx + 2 * hx / hy
# The class can contain other methods that PETSc won't use
def formRHS(self, B):
b = self.da.getVecArray(B)
mx, my = self.da.getSizes()
hx, hy = (1.0 / m for m in [mx, my])
(xs, xe), (ys, ye) = self.da.getRanges()
for j in range(ys, ye):
for i in range(xs, xe):
b[i, j] = 1 * hx * hy
# Access the option database and read options from the command line
OptDB = PETSc.Options()
nx, ny = OptDB.getIntArray(
'grid', (16, 16)
) # Read `-grid <int,int>`, defaults to 16,16
# Create the distributed memory implementation for structured grid
da = PETSc.DMDA().create([nx, ny], stencil_width=1)
# Create vectors to hold the solution and the right-hand side
x = da.createGlobalVec()
b = da.createGlobalVec()
# Instantiate an object of our Poisson2D class
pde = Poisson2D(da)
# Create a PETSc matrix of type Python using `pde` as context
A = PETSc.Mat().create(comm=da.comm)
A.setSizes([x.getSizes(), b.getSizes()])
A.setType(PETSc.Mat.Type.PYTHON)
A.setPythonContext(pde)
A.setUp()
# Create a Conjugate Gradient Krylov solver
ksp = PETSc.KSP().create()
ksp.setType(PETSc.KSP.Type.CG)
# Use diagonal preconditioning
ksp.getPC().setType(PETSc.PC.Type.JACOBI)
# Allow command-line customization
ksp.setFromOptions()
# Assemble right-hand side and solve the linear system
pde.formRHS(b)
ksp.setOperators(A)
ksp.solve(b, x)
# Here we programmatically visualize the solution
if OptDB.getBool('plot', True):
# Modify the option database: keep the X window open for 1 second
OptDB['draw_pause'] = 1
# Obtain a viewer of type DRAW
draw = PETSc.Viewer.DRAW(x.comm)
# View the vector in the X window
draw(x)
# We can also visualize the solution by command line options
# For example, we can dump a VTK file with:
#
# $ python poisson2d.py -plot 0 -view_solution vtk:sol.vts:
#
# or obtain the same visualization as programmatically done above as:
#
# $ python poisson2d.py -plot 0 -view_solution draw -draw_pause 1
#
x.viewFromOptions('-view_solution')
PETSc Python preconditioner type
The protocol for the petsc4py.PETSc.PC.Type.PYTHON preconditioner is:
from petsc4py.PETSc import KSP
from petsc4py.PETSc import PC
from petsc4py.PETSc import Mat
from petsc4py.PETSc import Vec
from petsc4py.PETSc import Viewer
# A template class with the Python methods supported by PCPYTHON
class PCPythonProtocol:
def apply(self, pc: PC, b: Vec, x: Vec) -> None:
"""Apply the preconditioner on vector b, return in x."""
...
def applySymmetricLeft(self, pc: PC, b: Vec, x: Vec) -> None:
"""Apply the symmetric left part of the preconditioner on vector b, return in x."""
...
def applySymmetricRight(self, pc: PC, b: Vec, x: Vec) -> None:
"""Apply the symmetric right part of the preconditioner on vector b, return in x."""
...
def applyTranspose(self, pc: PC, b: Vec, x: Vec) -> None:
"""Apply the transposed preconditioner on vector b, return in x."""
...
def applyMat(self, pc: PC, B: Mat, X: Mat) -> None:
"""Apply the preconditioner on a block of right-hand sides B, return in X."""
...
def preSolve(self, pc: PC, ksp: KSP, b: Vec, x: Vec) -> None:
"""Callback called at the beginning of a Krylov method.
This method is allowed to modify the right-hand side b and the initial guess x.
"""
...
def postSolve(self, pc: PC, ksp: KSP, b: Vec, x: Vec) -> None:
"""Callback called at the end of a Krylov method.
This method is allowed to modify the right-hand side b and the solution x.
"""
def view(self, pc: PC, viewer: Viewer) -> None:
"""View the preconditioner."""
...
def setFromOptions(self, pc: PC) -> None:
"""Process command line for customization."""
...
def setUp(self, pc: PC) -> None:
"""Perform the required setup."""
...
def reset(self, pc: PC) -> None:
"""Reset the preconditioner."""
...
In the example below, we create a Jacobi preconditioner, which needs to access the diagonal of the
matrix. The action of the preconditioner consists of the pointwise multiplication of the inverse diagonal
with the input vector.
# The user-defined Python class implementing the Jacobi method.
class myJacobi:
# Setup the internal data. In this case, we access the matrix diagonal.
def setUp(self, pc):
_, P = pc.getOperators()
self.D = P.getDiagonal()
# Apply the preconditioner
def apply(self, pc, x, y):
y.pointwiseDivide(x, self.D)
We can run the script used to test our matrix class and use command line arguments to specify that our
preconditioner should be used:
$ python mat.py -pc_type python -pc_python_type pc.myJacobi -ksp_view
KSP Object: 1 MPI process
type: cg
maximum iterations=10000, initial guess is zero
tolerances: relative=1e-05, absolute=1e-50, divergence=10000.
left preconditioning
using PRECONDITIONED norm type for convergence test
PC Object: 1 MPI process
type: python
Python: pc.myJacobi
linear system matrix = precond matrix:
Mat Object: 1 MPI process
type: python
rows=256, cols=256
Python: __main__.Poisson2D
PETSc Python linear solver type
The protocol for the petsc4py.PETSc.KSP.Type.PYTHON Krylov solver is:
from petsc4py.PETSc import KSP
from petsc4py.PETSc import Vec
from petsc4py.PETSc import Viewer
# A template class with the Python methods supported by KSPPYTHON
class KSPPythonProtocol:
def solve(self, ksp: KSP, b: Vec, x: Vec) -> None:
"""Solve the linear system with right-hand side b. Return solution in x."""
...
def solveTranspose(self, ksp: KSP, b: Vec, x: Vec) -> None:
"""Solve the transposed linear system with right-hand side b. Return solution in x."""
...
def view(self, ksp: KSP, viewer: Viewer) -> None:
"""View the Krylov solver."""
...
def setFromOptions(self, ksp: KSP) -> None:
"""Process command line for customization."""
...
def setUp(self, ksp: KSP) -> None:
"""Perform the required setup."""
...
def buildSolution(self, ksp: KSP, x: Vec) -> None:
"""Compute the solution vector."""
...
def buildResidual(self, ksp: KSP, t: Vec, r: Vec) -> None:
"""Compute the residual vector, return it in r. t is a scratch working vector."""
...
def reset(self, ksp: KSP) -> None:
"""Reset the Krylov solver."""
...
PETSc Python nonlinear solver type (TODO)
PETSc Python ode-integrator type (TODO)
PETSc Python optimization solver type (TODO)
WORKING WITH PETSC OPTIONS
A very powerful feature of PETSc is that objects can be configured via command-line options. In this
way, one can choose the method to be used or set different parameters without changing the source code.
See the PETSc manual for additional information.
In order to use command-line options in a petsc4py program, it is important to initialize the module as
follows:
# We first import petsc4py and sys to initialize PETSc
import sys, petsc4py
petsc4py.init(sys.argv)
# Import the PETSc module
from petsc4py import PETSc
Then one can provide command-line options when running a script:
$ python foo.py -ksp_type gmres -ksp_gmres_restart 100 -ksp_view
When the above initialization method is not possible, PETSc options can be also specified via environment
variables or configuration files, e.g.:
$ PETSC_OPTIONS='-ksp_type gmres -ksp_gmres_restart 100 -ksp_view' python foo.py
Command-line options can be read via an instance of the Options class. For instance:
OptDB = PETSc.Options()
n = OptDB.getInt('n', 16)
eta = OptDB.getReal('eta', 0.014)
alpha = OptDB.getScalar('alpha', -12.3)
In this way, if the script is run with
$ python foo.py -n 50 -alpha 8.8
the options, n and alpha will get the values 50 and 8.8, respectively, while eta will be assigned the
value specified as default, 0.014.
The options database is accessible also as a Python dictionary, so that one can for instance override,
insert or delete an option:
OptDB['draw_pause'] = 1
del OptDB['draw_pause']
PETSC4PY DEMOS
DOCUMENTATION STANDARDS FOR PETSC4PY
Subject to exceptions given below, new contributions to petsc4py must include type annotations for
function parameters and results, and docstrings on every class, function and method.
The documentation should be consistent with the corresponding C API documentation, including copying text
where this is appropriate. More in-depth documentation from the C API (such as extended discussions of
algorithmic or performance factors) should not be copied.
Docstring standards
Docstrings are to be written in numpydoc:format format.
The first line of a class, function or method docstring must be a short description of the method in
imperative mood ("Return the norm of the matrix.") "Return" is to be preferred over "Get" in this
sentence. A blank line must follow this description. Use one-liner descriptions for properties.
If the corresponding C API documentation of a method lists a function as being collective, then this
information must be repeated on the next line of the docstring. Valid strings are: "Not collective.",
"Logically collective.", "Collective.", "Neighborwise collective.", or "Collective the first time it is
called".
The initial description section can contain more information if this is useful. In particular, if there
is a PETSc manual chapter about a class, then this should be referred to from here.
Use double backticks around literals (like strings and numbers), e.g., ``2``, ``"foo"``.
Reference PETSc functions simply using backticks, e.g., KSP refers to the PETSc C documentation for KSP.
Do not use URLs in docstrings. Always use Intersphinx references.
The following sections describe the use of numpydoc sections. Other sections allowed by numpydoc may be
included if they are useful.
Parameters
This is required for methods unless there are no parameters, or it will be completely obvious to even a
novice user what the parameters do.
If a class has a non-trivial constructor, the arguments of the constructor and their types must be
explicitly documented within this section.
For methods, types should only be specified in this section if for some reason the types provided by
typing prove to be inadequate. If no type is being specified, do not include a colon (:) to the right of
the parameter name.
Use Sys.getDefaultComm when specifying the default communicator.
Returns
This should only be specified if the return value is not obvious from the initial description and typing.
If a "Returns" section is required, the type of the returned items must be specified, even if this
duplicates typing information.
See Also
If any of the following apply, then this section is required. The order of entries is as follows. Other
links are permitted in this section if they add information useful to users.
Every setFromOptions must include the link `petsc_options`.
Any closely related part of the petsc4py API not already linked in the docstring should appear (e.g.
setters and getters should cross-refer).
If there is a corresponding C API documentation page, this must be linked from the "See also" section,
e.g. `petsc.MatSetValues`.
End docstring with an empty line - "closing three quotation marks must be on a line by itself, preferably
preceded by a blank line"
Type hint standards
If returning self, use -> Self in function signature.
Type hints are not required when the static type signature includes a PETSc type (e.g. Vec x). These will
be automatically generated. This will also work for = None. When using type hints, use spacing around the
equals in any = None.
Communicators in type signatures must use Python typing instead of c-typing (i.e. comm: Comm not Comm
comm). This is because communicators can come from mpi4py and not just the petsc4py.PETSc.Comm class.
For petsc4py native types that are strings, the type is argument: KSP.Type | str (not e.g.: KSPType
argument). If the type is strictly an enum the | str can be omitted. Full signature example:
def setType(self, ksp_type: KSP.Type | str) -> None:
If a NumPy array is returned, use ArrayBool/ArrayInt/ArrayReal/ArrayScalar as the return type.
AUTHOR
Lisandro Dalcin
3.22 Mar 12, 2025 PETSC4PY(3)