Merge branch 'paulmullowney/cusp-vector-scatter-with-fix'

* paulmullowney/cusp-vector-scatter-with-fix:
CUDA/CUSP: Implementation of Sequential to Sequential Vector Scatters

implement MatFDColoringCreate_SeqXAIJ() s.t. it sets default brows and bcols.

add MatFDColoringSetUp(); rename MatFDColoringCreate_xxx -> MatFDColoringSetUp_xxx

blocked implimentation (use brows and bcols) works for htype=ds

set default bcols s.t. dy takes 50% of memory as matrix

optimize MatFDColoring routines for seqaij using brows and bcols

Added MatColoring object to replace MatGetColor()

cleanup MatGetColumnIJ_SeqAIJ_Color and MatGetColumnIJ_SeqBAIJ_Color

Merge branch 'barry/dmvecmattypes'

The MatType argument is removed from DMCreateMatrix(), you can use
DMSetMatType() to indicate the type you want used with a DM, defaults to
MATAIJ.

* barry/dmvecm

Merge branch 'barry/dmvecmattypes'

The MatType argument is removed from DMCreateMatrix(), you can use
DMSetMatType() to indicate the type you want used with a DM, defaults to
MATAIJ.

* barry/dmvecmattypes:
DMPlex ExodusII: fix dm->vectype pointer syntax
removed use of VecSetFromOptions() all over the placed, instead use MatGetVecs() or use dm->vectype to determine type added DMGetVecType() and DMGetMatTYpe()
removed MatType argument from DMCreateMatrix() and DMCreateColoring() since information is obtained from DM

Conflicts:
src/dm/impls/da/fdda.c
src/dm/impls/plex/plex.c

show more ...

Fix to AIJCUSP to Enable larger parallel simulations with Ellpack Storage

The construction of the offdiagonal matrices has been changed to enforce
compressed row format. Before this commit, the enti

Fix to AIJCUSP to Enable larger parallel simulations with Ellpack Storage

The construction of the offdiagonal matrices has been changed to enforce
compressed row format. Before this commit, the entire CSR format of the
offdiagonal block matrices (used in MatMultAdd) was being used to convert
to ellpack. This lead to a huge amount of fill because many of the rows in
the offdiagonal blocks can often be empty. With this commit, I calculate
the compressed format and calculate the ellpack matrix from this form.
No change in test results.

show more ...

cleanup MatFDColoringApply

cleanup MatFDColoringCreate_MPIXAIJ()

rm old members of _p_MatFDColoring: rows, columnsforrow and vscaleforrow (replaced by matentry)

replace old impl of MatFDColoring routines with new ones.

cleanup

replace MatFDColoringApply_SeqBAIJ with MatFDColoringApply_BAIJ_new

add new impl of MatFDColoring routines for mpibaij - works for htype=wp

Merge branch 'madams/mat-residual'

* madams/mat-residual:
refactored residuals by adding a 'residual' method to Mat

merge MatFDColoringApply_SeqAIJ() and xxx_MPIAIJ() into MatFDColoringApply_AIJ_new()

cleanup MatFDColoringCreate for seqaij and mpiaij formats

Merge branch 'barry/fixmatmultseqaijflopcount'

* barry/fixmatmultseqaijflopcount:
removed Mat option for skipping checking of compressed row format since it is now free using the nonzerorowcnt pre

Merge branch 'barry/fixmatmultseqaijflopcount'

* barry/fixmatmultseqaijflopcount:
removed Mat option for skipping checking of compressed row format since it is now free using the nonzerorowcnt previously introduced
changed seqbaij to count nonzero rows in assembly and use those values to compute flops in MatMult
added seqij nonzerorowcnt used to determine flop count in MatMult_SeqAIJ()

show more ...

Use MatEntry struct for MatFDColoring routines for seqaij and seqbaij matrices

rm useless segment of MatFDColoringApply_MPIAIJ(); add tests

optimize MatFDColoringApply_MPIAIJ by moving 'if htype= ' outside of for-loop

when htype=wp, dx is a constant scalar, thus does not need vscale