chkerr and friends wrapped
- Replace the current CUPM initialization infrastructure with PetscDevice.- Remove -petsc_use_default_null_stream and -[cuda|hip]_synchronize options- Remove PetscCUDASynchronize and PetscHIPSynchr
- Replace the current CUPM initialization infrastructure with PetscDevice.- Remove -petsc_use_default_null_stream and -[cuda|hip]_synchronize options- Remove PetscCUDASynchronize and PetscHIPSynchronize- Remove PetscCUDAInitialize(), PetscCUDAInitializeCheck(), PetscHIPInitialize(), andPetscHIPInitializeCheck()- Remove PetscCUBLASInitializeHandle(), PetscCUSOLVERDnInitializeHandle(),PetscHIPBLASInitializeHandle(), and PetscHIPSOLVERInitializeHandle().- Remove petsc_gputimer_begin and petsc_gputimer_begin- Add -device_enable, -device_select and -device_view options- Replace -[cuda|hip]_device with split options -device_enable_[cuda|hip] and -device_select_[cuda|hip]- Replace -[cuda|hip]_view with -device_view_[cuda|hip]- Add PetscDeviceInitType- Add PetscDeviceInitialize() and PetscDeviceInitialized()- Add PetscDeviceView()
show more ...
Sys: reuse PetscInitialize code between C and Fortran
Style: replace "!rank" with "rank == 0"In SF tutorial ex1 (src/vec/is/sf/tutorials/ex1.c), add parentheses around "rank == 0". This is relevant because ! binds more tightly than +, but == binds les
Style: replace "!rank" with "rank == 0"In SF tutorial ex1 (src/vec/is/sf/tutorials/ex1.c), add parentheses around "rank == 0". This is relevant because ! binds more tightly than +, but == binds lesstightly, so the result of the computation would otherwise change.
__float128: enable complex build from Cxx using c99 support
Fix spelling errors in manpages and comments
Merge branch 'balay/fix-mpi-fortran-parameters' into 'main'MPI_REAL: cannot assume MPI defined it via fortran 'parameters' - it can be...See merge request petsc/petsc!4246
DM: New idea for cell orientations- Add DMPolytopeTypeGetNumArrangments()- Add DMPolytopeTypeGetArrangment()- Add DMPolytopeTypeGetVertexArrangment()- Add DMPolytopeTypeComposeOrientation()- Add
DM: New idea for cell orientations- Add DMPolytopeTypeGetNumArrangments()- Add DMPolytopeTypeGetArrangment()- Add DMPolytopeTypeGetVertexArrangment()- Add DMPolytopeTypeComposeOrientation()- Add DMPolytopeTypeComposeOrientationInv()- Add DMPolytopeGetOrientation()- Add DMPolytopeGetVertexOrientation()- Inversion now uses just negation instead of face size- Remove DMPlexOrientCell(), DMPlexReverseCell(), DMPlexCompareOrientations()- Add DMPlexOrientPoint()- Add MPIU_4INT and MPI_4INT- Rewrote transitive closure- DMPlexGetTransitiveClosure_Depth1_Static() now correctly handles ornt- PetscDualSpaceLagrange and PetscSection use the number of arragnements and not the cone size- Update examples
MPI_REAL: cannot assume MPI defined it via fortran 'parameters' - it can be 'module variables' as in MPItrampoline- always set MPIU_REAL etc from C- fix PetscMPIFortranDatatypeToC to accept C types
MPI_REAL: cannot assume MPI defined it via fortran 'parameters' - it can be 'module variables' as in MPItrampoline- always set MPIU_REAL etc from C- fix PetscMPIFortranDatatypeToC to accept C types aswell
PetscStack : check for correct push/popEnforce checkstack for CI jobsFixes from testsuite
MPI: define proper datatypes for composite reductionsthis was a long-standing bug, dating back to 1996 or so
Remove all double blank lines from sourceCommit-type: petsc-style/2h
fortran: enable help message by adding PetscInitialize(filename,help,ierr)
Fix portability issues with OpenSUSE
Fortran: add PETSC_NULL_MPI_COMM for PCMGSetLevelsclose #868
remove PETSC_HAVE_MPI_C_DOUBLE_COMPLEX
PETSC_HAVE_COMPLEX: set flag only if CLANGUAGE (i.e library build language) supports complex, and cleanup logic wrt c/c++, library/user code.Also cleanup dependent code (wrt PETSC_HAVE_COMPLEX usage
PETSC_HAVE_COMPLEX: set flag only if CLANGUAGE (i.e library build language) supports complex, and cleanup logic wrt c/c++, library/user code.Also cleanup dependent code (wrt PETSC_HAVE_COMPLEX usage).
YAML: Move YAML options implementation sources closer to related sources
Merge remote-tracking branch 'origin/release'
petscviewer: fix the fortran bindings of XXXViewFromOptions when called with obj=PETSC_NULL_XXX
Convert MPI error type to PETSc error with string message for all MPI callsNow PETSc examples will ONLY return PETSc error codes and never MPI error codes directly so we can understand and post-pro
Convert MPI error type to PETSc error with string message for all MPI callsNow PETSc examples will ONLY return PETSc error codes and never MPI error codes directly so we can understand and post-process their errors better.The test harness will now automatically retry tests that fail with MPI, this may help with Intel MPI that produces seemingly random failures.Commit-type: error-checking/spend 30m
add PetscHasExternalPackage() parsing PETSC_HAVE_PACKAGES
Turn on checkbadSource test to generate an error when found; fix all source code that causes errorsCommit-type: portability-fix, testing-fix, style-fix, feature, maintainability/spend 1.5h
Add support of CUDA/HIP initialization at the same time
Do lazy petsc cuda initialization and validationSo that we can avoid overburdening the GPU in CI.See more at https://gitlab.com/petsc/petsc/-/issues/360#note_373723821
12345678910