MatMatMult[Symbolic|Numeric]_MPIAIJ_MPIDense: skip symbolic phase

Merge branch 'dalcinl/bt-byte' into 'main'

Implement PetscBT with new PetscByte datatype as unsigned char

See merge request petsc/petsc!9046

Merge remote-tracking branch 'origin/release'

Mat: fix MPIAIJ COO reallocation copy/free bug (#1863)

Switch some defined(PETSC_ to PetscDefined(

Merge branch 'jose/fix-hipsparse-csrmv-trans' into 'release'

hipSPARSE: workaround for issue with transpose matmult in ROCm 7.2.0

See merge request petsc/petsc!9056

HIPSPARSE: workaround for issue with transpose matmult in ROCm 7.2.0

When built with ROCm 7.2.0 MatMultTranspose() fails with:

[0]PETSC ERROR: --------------------- Error Message ------------------

HIPSPARSE: workaround for issue with transpose matmult in ROCm 7.2.0

When built with ROCm 7.2.0 MatMultTranspose() fails with:

[0]PETSC ERROR: --------------------- Error Message --------------------------------------------------------------
[0]PETSC ERROR: GPU error
[0]PETSC ERROR: hipSPARSE errorcode 3 (HIPSPARSE_STATUS_INVALID_VALUE)
[0]PETSC ERROR: See https://petsc.org/release/faq/ for trouble shooting.
[0]PETSC ERROR: PETSc Development Git Revision: v3.24.4-488-g2c105492db5 Git Date: 2026-02-19 16:00:40 +0000
[0]PETSC ERROR: ../test1 with 1 MPI process(es) and PETSC_ARCH arch-gnu-c-opt-hip Fri Feb 20 16:47:04 2026
[0]PETSC ERROR: Configure options: --with-hip --with-debugging=0 COPTFLAGS=-O FOPTFLAGS=-O CXXOPTFLAGS=-O HIPOPTFLAGS=-O
[0]PETSC ERROR: #1 MatMultAddKernel_SeqAIJHIPSPARSE() at petsc/src/mat/impls/aij/seq/seqhipsparse/aijhipsparse.hip.cxx:3116
[0]PETSC ERROR: #2 MatMultTranspose_SeqAIJHIPSPARSE() at petsc/src/mat/impls/aij/seq/seqhipsparse/aijhipsparse.hip.cxx:3010
[0]PETSC ERROR: #3 MatMultTranspose() at petsc/src/mat/interface/matrix.c:2741
[0]PETSC ERROR: #4 MatMult_Transpose() at petsc/src/mat/impls/transpose/transm.c:9

The issue can be attributed to ROCm 7.2.0 using four minimal examples
for CSR mat-vec: level2 and generic interfaces, both transpose and
non-transpose. The generic-transpose version does not work, it fails
with code: 10, reason: function is not implemented. The workaround in
PETSc is to fall back to the level2 interface if ROCm version is 7.2.0.

The second change is to avoid a compile warning.

show more ...

Fix compile warning with recent version of ROCm

src/mat/impls/aij/seq/seqhipsparse/aijhipsparse.hip.cpp:4199:27: warning: 'identity<int>' is deprecated: use ::internal::identity instead [-Wdeprecate

Fix compile warning with recent version of ROCm

src/mat/impls/aij/seq/seqhipsparse/aijhipsparse.hip.cpp:4199:27: warning: 'identity<int>' is deprecated: use ::internal::identity instead [-Wdeprecated-declarations]
4199 | auto pred = thrust::identity<int>();
| ^
/opt/rocm-7.2.0/include/thrust/functional.h:1182:8: note: 'identity<int>' has been explicitly marked deprecated here
1182 | struct THRUST_DEPRECATED_BECAUSE("use ::internal::identity instead") identity
| ^
/opt/rocm-7.2.0/include/thrust/detail/config/deprecated.h:41:44: note: expanded from macro 'THRUST_DEPRECATED_BECAUSE'
41 | # define THRUST_DEPRECATED_BECAUSE(MSG) [[deprecated(MSG)]]
| ^

show more ...

Change *.cpp to *.cxx

Implement PetscBT with new PetscByte datatype as unsigned char

Remove the last of the use of horizontal lines --- as seperators. With modern code development systems they are not needed and just an eye-sore

Replace mpirun with mpiexec, as only the latter is in the standard

MATSOLVERMUMPS: minor cleanup

Deprecate -matmatmult_Bbn in favor of -matproduct_batch_size

See also -ksp_matsolve_batch_size

Add automatic generated fortran support for setting and returning contexts

Major cleanup of the code for setting and returning application (previously called user) contexts
- PetscCtx ctx is now t

Add automatic generated fortran support for setting and returning contexts

Major cleanup of the code for setting and returning application (previously called user) contexts
- PetscCtx ctx is now the standard for passing in contexts
- PetscCtxRt ctx is the standard for passing out contexts, including context destroy routines based on PetscCtxDestroyFn

Both of these are typedef to void*

Also removed most use of user and userctx for context arguments now consistently named ctx

Improved documentation on PetscCtx and PetscCtxRt and on how to use contexts (including getting them) from Fortran

show more ...

Merge remote-tracking branch 'origin/release'

Merge branch 'jczhang/2025-12-23/fix-MatPtAP' into 'release'

Fix bugs in MatPtAP

See merge request petsc/petsc!8911

Merge branch 'jczhang/2025-12-25/mumps-out-of-core' into 'main'

Support MUMPS out-of-core facility

Closes #1116

See merge request petsc/petsc!8915

MUMPS: support its out-of-core facility

close #1116

MUMPS: fix a naming typo

MatConjugate(): no need to check for USE_COMPLEX in implementations

Merge branch 'jolivet/minor-cleanup' into 'main'

Minor cleanup: use MPI_IN_PLACE when possible and avoid extra allocation

See merge request petsc/petsc!8925

Merge branch 'release'

Minor cleanup: use MPI_IN_PLACE when possible and avoid extra allocation

Remove legacy '+1' allocations in XXXDiagonalScaleLocalSetUp() routines for AIJ and BAIJ parallel matrices

This commit removes '+1's in some memory allocations that are believed
to be leftover from

Remove legacy '+1' allocations in XXXDiagonalScaleLocalSetUp() routines for AIJ and BAIJ parallel matrices

This commit removes '+1's in some memory allocations that are believed
to be leftover from long ago to handle corner cases with malloc() calls
of size 0, which some implementations would not handle correctly. This
ceased to be an issue long ago.

Thanks-to: Pierre Jolivet <pierre@joliv.et>, Barry Smith <bsmith@petsc.dev>

show more ...