added test to detect common overflow error

MPIAIJ in manual pages should be MATMPIAIJ in order to produce links

Merge branch 'master' of bitbucket.org:petsc/petsc

Merge branch 'pr530/psanan/mat-viennacl-conversions/master'

* pr530/psanan/mat-viennacl-conversions/master
MATSEQAIJVIENNACL: add no-copy in-place and out-of-place conversion from SeqAIJ
This extrac

Merge branch 'pr530/psanan/mat-viennacl-conversions/master'

* pr530/psanan/mat-viennacl-conversions/master
MATSEQAIJVIENNACL: add no-copy in-place and out-of-place conversion from SeqAIJ
This extracts the portion of the creation routine which converts a SeqAIJ Mat to a SeqAIJViennaCL Mat and provides it as a conversion routine.

MATSEQAIJVIENNACL: remove redundant setting of ops with MatAssemblyEnd.

Mat tests: add ViennaCL tests with conversions.

Note that we have not yet added an efficient conversion from MATMPIAIJ to MATMPIAIJVIENNACL.
This can probably be done easily by calling the sequential conversion routines on the two (per rank) submatrices stored.

Conflicts:
src/mat/examples/tests/makefile

show more ...

remove dead Adifor code

Time: .1 hours
Reported-by: Sebastien Gilles <sebastien.gilles@inria.fr>

MATSEQAIJVIENNACL: remove redundant setting of ops with MatAssemblyEnd.

MATSEQAIJVIENNACL: add no-copy in-place and out-of-place conversion from SeqAIJ

This extracts the portion of the creation routine which converts a SeqAIJ Mat to
a SeqAIJViennaCL Mat and provides it

MATSEQAIJVIENNACL: add no-copy in-place and out-of-place conversion from SeqAIJ

This extracts the portion of the creation routine which converts a SeqAIJ Mat to
a SeqAIJViennaCL Mat and provides it as a conversion routine.

show more ...

update uses of mat->errortype to mat->factorerrortype in optional package code

Time: .1 hour
Reported-by: nightly tests

Added MatFactorGetErrorZeroPivot()

Time: 2 hours
Reported-by: Glenn E Hammond <gehammo@sandia.gov>

Merge branch 'barry/add-matshell-matgetdiagonalblock-fortran'

Removed the use of PetscObjectQueryFunction() with with MatGetDiagonalBlock()

that I missed when I first converted MatGetDiagonalBlock() from a query function
to a table function

Time: .3 hours
Re

Removed the use of PetscObjectQueryFunction() with with MatGetDiagonalBlock()

that I missed when I first converted MatGetDiagonalBlock() from a query function
to a table function

Time: .3 hours
Reported-by: nightly tests

show more ...

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

add support for MatShellSetOperation(Mat,MATOP_GET_DIAGONAL_BLOCK, for Fortran

This required changing the handling of MatGetDiagonalBlock() from a query function based
method to a regular method in

add support for MatShellSetOperation(Mat,MATOP_GET_DIAGONAL_BLOCK, for Fortran

This required changing the handling of MatGetDiagonalBlock() from a query function based
method to a regular method in the function table

Time: .75 hours
Reported-by: Steven Dargaville <dargaville.steven@gmail.com>
Thanks-to: Dave May <dave.mayhem23@gmail.com>

show more ...

Hoist management of DM usage for MatFDColoringApply() for IS_COLORING_LOCAL up to dm

This is because the DM calls cannot be made in the Mat library when not using --with-single-library

Time: 1.6 ho

Hoist management of DM usage for MatFDColoringApply() for IS_COLORING_LOCAL up to dm

This is because the DM calls cannot be made in the Mat library when not using --with-single-library

Time: 1.6 hours
Reported-by: nightly tests

show more ...

For some strange reason the ctype was set to IS_COLORING_LOCAL always with sbaij matrices

Time: .25 hours
Reported-by: nightly tests

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

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

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

show more ...

clearify when MatMkl_CPardisoSetCntl() can be used in the manual pages

Time: .1 hours
Reported-by: Matthew Overholt <overholt@capesim.com>

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

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

MatIS: added conversion routine from MPIAIJ to MATIS

the conversions is very simple, it just compress the columns and merge diagonal and offdiagonal block
reuse case to be done

Merge branch 'jose/fix-cusparse-flag'

* jose/fix-cusparse-flag:
In MatSeqAIJCUSPARSECopyToGPU the case of simplified copy must also set the GPU consistency flag
PR #514

Merge branch 'maint'

prevent a possible segfault when m is 0 (or less)

essl: fix PetscOptionsGetReal() usage

Reported-by: Matthew Niemerg <matthewniemerg@us.ibm.com>

Fix performance issue in MatAIJCUSPARSE after 34d6c7a

In MatSeqAIJCUSPARSECopyToGPU the case of simplified copy must also
set the GPU consistency flag

Merge branch 'jose/veccuda-tests'

Conflicts:
config/PETSc/Regression.py

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

Merge branch 'jose/veccuda-tests'

Conflicts:
config/PETSc/Regression.py

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

show more ...