docs: update DOI for v3.23
Remove obsolete (and now removed) function from UCRT
Sys: Need to cast when indexing with negative enums
Merge branch 'jolivet/rm-explicit-empty-output_file' into 'main'Remove 535 empty .out and consolidate the use of output/empty.outSee merge request petsc/petsc!8538
Merge branch 'zach/log_roctx' into 'main'Add `-log_roctx` to automatically instrument PETSc events for rocprofSee merge request petsc/petsc!8372
Add `-log_roctx` to automatically instrument PETSc events for rocprof
Minor style fix
Merge remote-tracking branch 'origin/release'
Doc: Add docs for -python
Add #define PetscObjectNullify(o) o%v = PETSC_FORTRAN_TYPE_INITIALIZE to allow Fortran users to reset a variable to behave as if it had just been declared and not yet been assigned a PETSc object.R
Add #define PetscObjectNullify(o) o%v = PETSC_FORTRAN_TYPE_INITIALIZE to allow Fortran users to reset a variable to behave as if it had just been declared and not yet been assigned a PETSc object.Reported-by: Glenn Hammond
show more ...
Merge branch 'release'
Fix a couple bugs in current Fortran stubs
KOKKOS: enable C++ threads backenddo not overwrite warning argument from code, use environment variable insteadAdd configuration to CIUse {Min|Max}FirstLoc instead of {Min|Max}Loc see https://git
KOKKOS: enable C++ threads backenddo not overwrite warning argument from code, use environment variable insteadAdd configuration to CIUse {Min|Max}FirstLoc instead of {Min|Max}Loc see https://github.com/kokkos/kokkos/issues/8097
sycl: use sycl::cpu_selector_v as sycl::host_selector() is removed
PetscOptionsDeprecated: do not overwrite new option if it is provided
petscerror.h: iwyu export semi-private headerpetscerror.h cannot be included directly unless petscsys.h has alreadybeen included (and that unconditionally includes petscerror.h). Thisupdates docs
petscerror.h: iwyu export semi-private headerpetscerror.h cannot be included directly unless petscsys.h has alreadybeen included (and that unconditionally includes petscerror.h). Thisupdates docs and uses IWYU pragma export so IDEs (clangd) willautomatically include the correct header when you use things likeSETERRQ that appear petscerror.h.Fix #1254
CUPM: Fix some mult routines and make some small performance improvementsVecSeq_CUPM: Fix ::Dot, ::TDot, ::WAXPYAsync, and ::AXPBYAsync to work with non-device vectorsMat_SeqDenseCUPM: fix ::SetR
CUPM: Fix some mult routines and make some small performance improvementsVecSeq_CUPM: Fix ::Dot, ::TDot, ::WAXPYAsync, and ::AXPBYAsync to work with non-device vectorsMat_SeqDenseCUPM: fix ::SetRandom for hipMat_SeqDenseCUPM: implement conjugate on the deviceMat_SeqDenseCUPM: Fix MatMult() (and friends) when the vector is not on the deviceThis implementation assumes that the cost of moving the matrix to thehost is more expensive that moving the vector to the device, so temporarydevice copies of the host vectors are used.VecCUPM: Avoid device synchronization in some cases of ResetArray()The documentation says that the PetscDeviceSynchronization() isonly needed if CopyToDevice_() resulted in a HtoD memcpy,which would only happen if v->offloadmask == PETSC_OFFLOAD_CPU.If we test this condition, we can avoid the synchronization.This improves the peformance of MatDenseRestoreColumnVecWrite() inperformance critical loops.CUPM: use thrust::hip::par_nosync
Fix wrong case for PETSc
Fix manual pages related to FortranRemove a couple of dead Fortran bindings
release: set petsc v3.23.0 strings
Fix fortran notes in man pages
Minor cleanup of Fortran binding stuff to simplify future maintainanceThere is no distinction between F90 and non-F90 code so combine ftn-custom and f90-custom directories and fortranimpl.h and f90
Minor cleanup of Fortran binding stuff to simplify future maintainanceThere is no distinction between F90 and non-F90 code so combine ftn-custom and f90-custom directories and fortranimpl.h and f90impl.h files. Also move uses of f90 to ftn when simple
12345678910>>...99