| 0e6a1e94 | 30-Jan-2025 |
Mark Adams <524115-markadams4@users.noreply.gitlab.com> |
aijkokkos: setting block sizes for product of PtAP, etc to aijkokkos and cusparse |
| 45402d8a | 30-Jan-2025 |
Junchao Zhang <jczhang@anl.gov> |
Kokkos: add support of AMD MI300A
* Use HostMirrorMemorySpace instead of HostSpace to fix compile errors on MI300A
* Replace Kokkos::HostSpace with HostMirrorMemorySpace to fix compile errors on MI
Kokkos: add support of AMD MI300A
* Use HostMirrorMemorySpace instead of HostSpace to fix compile errors on MI300A
* Replace Kokkos::HostSpace with HostMirrorMemorySpace to fix compile errors on MI300A, since the latter is what Kokkos::DualView use for its host view
* Fix a subtle bug in KokkosDualViewSync() w.r.t MI300A. Suppose we want to sync a petsc VecKokkos v on host. On MI300A, the host copy v_h and the device copy v_d share the memory. So in the old code, we used if (v_dual.need_sync_host()) to skip the device to host memory copy. But I should not skip the exec.fence(). As the device might still have kernels writing v_d, we still need to sync the device/stream to make v_d ready for use on CPU (via v_h).
show more ...
|
| e91c04df | 26-Jan-2025 |
Pierre Jolivet <pierre@joliv.et> |
Remove unneeded PetscMPIIntCast() for routines using PetscCount
Fix #1661 |
| 76d69608 | 19-Jan-2025 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' |
| 0b4b7b1c | 26-Nov-2024 |
Barry Smith <bsmith@mcs.anl.gov> |
Improve some manual pages in KSP/SNES |
| a982d554 | 16-Jan-2025 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' |
| b2d4ea15 | 15-Jan-2025 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jolivet/fix-docs' into 'release'
Docs: minor fixes
See merge request petsc/petsc!8073 |
| 0c335700 | 15-Jan-2025 |
Barry Smith <bsmith@mcs.anl.gov> |
Print the requested inode size when unsupported size generates an error |
| 57761e9a | 11-Jan-2025 |
Junchao Zhang <jczhang@anl.gov> |
Mat: leverage MatConvert_AIJ_HYPRE to convert aijkokkos matrices to mathypre ones |
| f8d70eaa | 14-Jan-2025 |
Pierre Jolivet <pierre@joliv.et> |
Docs: minor fixes |
| 1c265611 | 11-Jan-2025 |
Junchao Zhang <jczhang@anl.gov> |
Mat: add some comments |
| 3fdc7080 | 06-Jan-2025 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'docs' into 'release'
Improvements to the documentation
See merge request petsc/petsc!8068 |
| 5163b989 | 02-Jan-2025 |
Nuno Nobre <nuno.nobre@stfc.ac.uk> |
Fix minor typos in the docs for create/preallocation routines
Co-authored-by: Barry Smith <bsmith@petsc.dev> |
| 3531e584 | 03-Jan-2025 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' |
| eb14dd14 | 20-Dec-2024 |
Alex Lindsay <alexlindsay239@gmail.com> |
Fix MatResetPreallocation_MPIAIJ
Per Barry's suggesetion I inserted a `MatDisAssemble` which immediately fixed my issue. I will work on adding a test |
| 674b392b | 11-Nov-2024 |
Alexander <alexander.lindsay@inl.gov> |
Add a MatResetHash API |
| fe1fc275 | 29-Oct-2024 |
Alexander <alexander.lindsay@inl.gov> |
Add MatCopyHashToXAIJ() to copy hash table entries into an XAIJ matrix type |
| 2e45e1b1 | 24-Oct-2024 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' |
| e58947e7 | 22-Oct-2024 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'jrwrigh/cleanup_malloc' into 'release'
sys: Cleanup PetscMalloc and PetscCalloc
See merge request petsc/petsc!7892 |
| 32603206 | 02-Oct-2024 |
James Wright <james@jameswright.xyz> |
Address potential Malloc/Calloc ternary operator bugs
- Bug either by the argument of the ternary operator being cast inappropriately to `size_t` or by the values themselves not being cast to `s
Address potential Malloc/Calloc ternary operator bugs
- Bug either by the argument of the ternary operator being cast inappropriately to `size_t` or by the values themselves not being cast to `size_t` when necessary.
show more ...
|
| 835f2295 | 05-Oct-2024 |
Stefano Zampini <stefano.zampini@gmail.com> |
Brain dead fixes for useless casts |
| 5a236de6 | 21-Oct-2024 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/release' |
| ad781fe3 | 21-Oct-2024 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'barry/2024-09-29/fix-function-typedef-style' into 'main'
Unify handling of context destructors
See merge request petsc/petsc!7900 |
| 2e1d0745 | 19-Oct-2024 |
Jose E. Roman <jroman@dsic.upv.es> |
Fix ranlib warnings 'file has no symbols'
These warnings appear in macOS when configured --with-shared-libraries=0
/Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-nosh
Fix ranlib warnings 'file has no symbols'
These warnings appear in macOS when configured --with-shared-libraries=0
/Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(sectionhdf5.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(zhdf5io.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(hdf5io.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(aijhdf5.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(baijfact81.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(densehdf5.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(feceed.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(fvceed.o) has no symbols /Library/Developer/CommandLineTools/usr/bin/ranlib: file: arch-darwin-c-debug-noshared/lib/libpetsc.a(plexhdf5xdmf.o) has no symbols
Includes the removal of unnecessary custom fortran stubs.
show more ...
|
| 49abdd8a | 29-Sep-2024 |
Barry Smith <bsmith@mcs.anl.gov> |
Unifies all context destructors to have a form of PetscCtxDestroyFn == PetscErrorCode (*)(void **)
Changes the previous subset of destructor APIs that used PetscErrorCode (*)(void *) (mostly those t
Unifies all context destructors to have a form of PetscCtxDestroyFn == PetscErrorCode (*)(void **)
Changes the previous subset of destructor APIs that used PetscErrorCode (*)(void *) (mostly those that used PetscContainer
- Now allows any context to be a PetscObject - Will provide a cleaner mapping to bindings in other languages - Simplifies the maintenance of PETSc source code; improves clarity
Not backward compatible, compiler warnings will tell users what functions need to be updated
show more ...
|