optimize MatTransposeMatMultSymbolic_MPIAIJ_MPIAIJ_nonscalable()

start rewrite MatTransposeMatMultSymbolic_MPIAIJ_MPIAIJ_nonscalable() -- modify from MatPtAPSymbolic_MPIAIJ_MPIAIJ_nonscalable

MatTransposeMatMult_SeqAIJ_SeqAIJ() is implemented as At=A^T and C=At*B

optimize MatTransposeMatMult()
Reported-by: Jed Brown <jed@jedbrown.org>

MatResetPreallocation_SeqAIJ: fix compiler warnings

MatResetPreallocation: minor format fixes

MatResetPreallocation: Reset mat to use the original nonzero pattern provided by users.

Add finite difference support for ELL

Funded-by:
Project: PETSc for Theta
Time: 6.0 hours
Reported-by:
Thanks-to:

Error out when the number of rows is not multiple of 8

Funded-by:
Project: PETSc for Theta
Time: 0.5 hours
Reported-by:
Thanks-to:

Add MatConvert for ELL

* It requires MatDisAssemble;
* Crucial to set up assembled and was_assembed flag correctly.
Funded-by:
Project: PETSc for Theta
Time: 14 hours
Reported-by:
Thanks-to:

build: fix compile warnings with VS6

more remove __FUNCT__

Bug fixes
Fix for test 107_2. To prevent MKL routine returning error in case when MatSetOption(mat,MAT_STRUCTURE_ONLY,PETSC_TRUE) is called. In this case matrix will be optimized before call to mkl_s

Bug fixes
Fix for test 107_2. To prevent MKL routine returning error in case when MatSetOption(mat,MAT_STRUCTURE_ONLY,PETSC_TRUE) is called. In this case matrix will be optimized before call to mkl_sparse_x_mv.
The same problem will appear in AIJMKl case.
Also added MatCreateBAIJMKL and MatCreateSeqBAIJMKL to external include to call them from examples

show more ...

Merge branch 'rmills/add-aijmkl'

* rmills/add-aijmkl:
Adds AIJMKL matrix class to facilitate use of MKL sparse BLAS routines
BitBucket Pull Request 737
This is the initial version of the AIJMKL matr

Merge branch 'rmills/add-aijmkl'

* rmills/add-aijmkl:
Adds AIJMKL matrix class to facilitate use of MKL sparse BLAS routines
BitBucket Pull Request 737
This is the initial version of the AIJMKL matrix class,
a subclass of AIJ that has the goal of using MKL sparse BLAS routines whenever practicable.
If the MKL version is new enough, the sparse inspector-executor
("SpMV2" -- terrible name, but that's what the MKL team called it) routines are used by default.
Currently only MatMult, MatMultAdd, MatMultTranspose, and MatMultTransposeAdd operations are supported,
but more will be added once this initial attempt is at a point
that it provides an acceptable framework for adding additional further functionality.

show more ...

Fortran stub cannot be automatic since it generates too long a line for the modules file :-(

Commit-type: bug-fix
Funded-by: ECP
Time: .1 hours
Reported-by: bitbucket pipelines

Merge branch 'maint'

Fortran stub can be autogenerated

Commit-type: feature
Funded-by: ECP
Time: .1 hours

MKL: Fixed compilation problems for older MKL versions without mkl_sparse_optimize().

Fixes to handle null matrices (no explicit entries) correctly in _SpMV2 routines.

add MatView_MPIAIJ_PTAP

Edits to MPIAIJMKL manual page.

Removed obsolete comment.

Registration of SeqAIJ conversion routines requires definition of PETSC_HAVE_MKL.

add scalable/nonscalable to '-info' for MatPtAP implementation

Edits to the MatCreateSeqAIJMKL manual page.