HYPRE: add option -hypre_umpire_device_pool_size <size in MiB>When hypre is configured with Umpire (recommended by hypre), the default Umpire pool size on device is setto 4 GB per process by hypre
HYPRE: add option -hypre_umpire_device_pool_size <size in MiB>When hypre is configured with Umpire (recommended by hypre), the default Umpire pool size on device is setto 4 GB per process by hypre which could lead to out-of-memory when one maps multiple MPI processes to one GPU.
show more ...
Fix the inconsistent usage of #if [!]defined XXX compared to defined(XXX)Thanks-to: Pierre JolivetAn LLM Claude detected the incosnsitency it was not used to remove the inconsistency
Add automatic generated fortran support for setting and returning contextsMajor 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 contextsMajor 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 PetscCtxDestroyFnBoth of these are typedef to void*Also removed most use of user and userctx for context arguments now consistently named ctxImproved documentation on PetscCtx and PetscCtxRt and on how to use contexts (including getting them) from Fortran
Merge branch 'barry/2025-12-04/fix-use-mpi-f08' into 'main'Replace -with-mpi-f90module-visibility with -with-mpi-ftn-module=mpi_f08See merge request petsc/petsc!8885
Merge remote-tracking branch 'origin/release'
Replace -with-mpi-f90module-visibility with -with-mpi-f90module=mpi_f08Add PETSC_INT_KIND and PETSC_MPIINT_KINDReported-by: M.Weiland@epcc.ed.ac.uk
__fp16: fix 'make check'
Fix missing equal sign
Proper capitalization from Gram-Schmidt orthogonalization
MatView(): do not print block size twice
Merge branch 'zach/dmlabel-fix-lookups' into 'main'DMLabel: Guard BT checks to allow for lookup/deletion operations beyond the set point rangeSee merge request petsc/petsc!8884
tests: Add new alt for failing test snes_tutorials-ex28
Remove unneeded blank lines
Merge branch 'barry/2025-10-18/optimize-aij-ops' into 'main'Refactor handling of diagonal marking in *AIJ and SELL matricesSee merge request petsc/petsc!8797
- Replace MatMissingDiagonal() and MatMarkDiagonals_SeqXXX() with MatGetDiagonalMarkers_SeqXXX() - Mat_SeqXXX->diag is not automatically created during MatAssemblyEnd() saving memory and time
- Replace MatMissingDiagonal() and MatMarkDiagonals_SeqXXX() with MatGetDiagonalMarkers_SeqXXX() - Mat_SeqXXX->diag is not automatically created during MatAssemblyEnd() saving memory and time - Accessing Mat_SeqXXX->diag now requires the use of MatGetDiagonalMarkers_SeqXXX() except when the current values are known to be correct; for example during numerical factorizations and solves - Mat_SeqXXX->diag is now never shared among matrices; hence the free_diag flag is gone. That was always a risky proposition since any of the owning matrices could chang the values thus making them incorrect for other owners.
Remove unused code
Fix terminology for Pmat in KSPView output.
Fortran: enforce lower case keywords and operatorsalso fixed occasional capitals in used modules with the help of @prj-
cleanup suggestions by @BarrySmithalso noticed a few stray functions not marked as external and put theminto modules
use modules instead of externalthis allows for argument checking
remove labeled do loopslabeled do loops confused fprettify, so used it to rectify indentation
place all the include statements at the topRepeated inclusion in multiple location, e.g. at the start of amodule or function is not needed. This becomes clear if all includes areoutside of the ac
place all the include statements at the topRepeated inclusion in multiple location, e.g. at the start of amodule or function is not needed. This becomes clear if all includes areoutside of the actual Fortran code.Added regex to check that with the help of @sbalay
Build: print make check command with V=1
checkbadSource: enforce proper style in makefiles
MUMPS: add multi-precision support
12345678910>>...27