| 3338378c | 18-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATMPIAIJCUSPARSE: add support for MatConvert |
| 49735bf3 | 18-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATSEQAIJCUSPARSE: allow MatConvert with reuse != MAT_INPLACE_MATRIX |
| 5706b986 | 18-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATMPIAIJ: remove sprintf in favor of PetscSNPrintf |
| 540e20f2 | 14-Jun-2020 |
Pierre Jolivet <pierre.jolivet@enseeiht.fr> |
Fix a deadlock with MATELEMENTAL |
| 589a23ca | 02-Jun-2020 |
Barry Smith <bsmith@mcs.anl.gov> |
Updated the use of sizeof() when possible instead of using hardwired sizes for functions whose string arguments
need sizes. In particular done for PetscOptionsGetString(), PetscOptionsString(), and a
Updated the use of sizeof() when possible instead of using hardwired sizes for functions whose string arguments
need sizes. In particular done for PetscOptionsGetString(), PetscOptionsString(), and a few other utilities
Commit-type: style-fix
Development Tools: Vim, Emacs, Eclipse
show more ...
|
| a1bfbe63 | 12-Jun-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'stefanozampini/fix-matproduct-logging' into 'master'
fix matproduct logging
See merge request petsc/petsc!2857 |
| 2bcef1f2 | 12-Jun-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/maint' |
| 93aa15f2 | 11-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatMultNumericAdd_SeqAIJ_SeqDense: Improve performances
1M x 1M AIJ matrix with 10 nonzeros per row times 2 columns -> 2x improvement
smaller improvements (20% in time) for larger numbers of columns |
| c8378d12 | 11-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATSEQAIJCUSPARSE: add logging support for MatProduct with dense matrix |
| 383ef339 | 10-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATSEQAIJVIENNACL: call Vec implementations in matvecs |
| 38640ff5 | 10-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATMPIAIJ: add missing reduce for allcolumns case
this is needed because otherwise the code will use different code paths
No need to specify allcolumns to be logically collective inside _SingleIS_lo
MATMPIAIJ: add missing reduce for allcolumns case
this is needed because otherwise the code will use different code paths
No need to specify allcolumns to be logically collective inside _SingleIS_local, as every operation there is local
show more ...
|
| daccdfde | 10-Jun-2020 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/maint' |
| 2a09556f | 09-Jun-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatMatMultSymbolic_SeqAIJ_SeqAIJ_Sorted: prevent from division by zero |
| 5ea7661a | 23-May-2020 |
Pierre Jolivet <pierre.jolivet@enseeiht.fr> |
Change how solves with multiple RHS work
* Deprecate KSPHPDDMMatSolve
* Add KSPMatSolve, previously known as KSPHPDDMMatSolve
* New option -ksp_matsolve_block_size
* New routines MatDense[Get|Restor
Change how solves with multiple RHS work
* Deprecate KSPHPDDMMatSolve
* Add KSPMatSolve, previously known as KSPHPDDMMatSolve
* New option -ksp_matsolve_block_size
* New routines MatDense[Get|Restore]SubMatrix
show more ...
|
| 22235d61 | 24-May-2020 |
Pierre Jolivet <pierre.jolivet@enseeiht.fr> |
Update to hypre 2.19.0 and to MUMPS 5.3.1 |
| 0595b67c | 30-May-2020 |
Jose E. Roman <jroman@dsic.upv.es> |
Fix compile warning |
| ccdfe979 | 14-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATSEQAIJCUSPARSE: support for MatMat operations
fix issue with ILU reusage (leaks and not setting the offdiagonal flag properly)
add missing nullify of function composition |
| 6718818e | 17-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatProduct: proper cleanup of additional data structure
Do not mess with view/destroy routine, add an extra slot to MatProduct struct to stash the data, destroy/view routines
Deprecate MatFreeInterm
MatProduct: proper cleanup of additional data structure
Do not mess with view/destroy routine, add an extra slot to MatProduct struct to stash the data, destroy/view routines
Deprecate MatFreeIntermediateStructures in favor of MatProductClear
Clean up base headers for matrix classes
Update tests (remove some todos from ex70 because now the tests work properly)
MatProductSetType should not set the setfromoptions operation!
MatProductClear should reset operations
Remove no longer needed function composition
Add few more PetscInfo messages
Single dispatch routine
MatProductSetFromOptions routines are now allowed to fail
MatProductSetFromOptions_SeqXBAIJ_SeqDense: support for MATPRODUCT_AtB
MatTransposeMatMultNumeric_SeqAIJ_SeqDense: fix bug with leading dimensions
Make internal functions PETSC_INTERN
Fix a couple of places where the destroy routine of the matrix was changed
Products should all use internal data (or composed data attached to the internal data)
Fix few bugs in MPIAIJ_MPIDENSE product with stages
show more ...
|
| 86214cee | 11-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatMatMultNumeric_SeqDense_SeqAIJ: fix bug with leading dimensions
preserve C type if already of dense type |
| 7a3c3d58 | 06-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatProduct: add support for basic AB and AtB products with B of type dense
do not fail if not supported
MatProductSetAlgorithm should copy the string, not the pointer!
Fix various checks
Fix new mat
MatProduct: add support for basic AB and AtB products with B of type dense
do not fail if not supported
MatProductSetAlgorithm should copy the string, not the pointer!
Fix various checks
Fix new mat/vec type propagation in few cases
Reported-by: "Jose E. Roman" <jroman@dsic.upv.es>, Pierre Jolivet <pierre.jolivet@enseeiht.fr>
show more ...
|
| 637a0070 | 06-Apr-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATMPIDENSE: support CUDA
MatSeqDense: add support to check for symmetricity
Add array accessors routines
fix MatSetRandom for leading dimension
Use PetscSF for MatMult
- uses the right communica
MATMPIDENSE: support CUDA
MatSeqDense: add support to check for symmetricity
Add array accessors routines
fix MatSetRandom for leading dimension
Use PetscSF for MatMult
- uses the right communication pattern instead of point-to-point
- can take advantage of CUDA aware MPI
Fix bugs related with LDA
Fix direct usage of cpu memory: use MatDenseGetArray (and variants) instead
Fix MatZeroRows
Fix MatView in Binary for SeqDense
show more ...
|
| 1ca9667a | 07-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatMatMultSymbolic_SeqAIJ_SeqDense: C lda |
| 4b2d9054 | 07-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MATMPIAIJCUSPARSE: fix destroy routine |
| 0ce8acde | 07-May-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
MatConvert_SeqAIJ_SeqAIJCUSPARSE: fix bug with reuse != MAT_INPLACE_MATRIX |
| ea13f565 | 09-Apr-2020 |
Stefano Zampini <stefano.zampini@gmail.com> |
Fix misuse of PETSC_COMM_WORLD in library code
There are still many left, I'm tired of fixing them
[szampini@localhost petsc]$ git grep PETSC_COMM_WORLD | grep -v tests | grep -v tutorials | grep '
Fix misuse of PETSC_COMM_WORLD in library code
There are still many left, I'm tired of fixing them
[szampini@localhost petsc]$ git grep PETSC_COMM_WORLD | grep -v tests | grep -v tutorials | grep '\.c' | awk '{print $1}' | uniq
src/benchmarks/streams/CUDAVersion.cu:
src/benchmarks/streams/SSEVersion.c:
src/contrib/fun3d/comp/flow.c:
src/contrib/fun3d/incomp/flow.c:
src/dm/impls/forest/p4est/petsc_p4est_package.c:
src/dm/impls/moab/dmmbfem.cxx:
src/dm/impls/moab/dmmbmg.cxx:
src/dm/impls/moab/dmmbutil.cxx:
src/dm/impls/moab/dmmbvec.cxx:
src/dm/impls/moab/dmmoab.cxx:
src/dm/impls/network/network.c:
src/dm/impls/stag/stag.c:
src/dm/impls/stag/stag1d.c:
src/dm/impls/stag/stag2d.c:
src/dm/impls/stag/stag3d.c:
src/dm/impls/stag/stagda.c:
src/dm/impls/stag/stagutils.c:$
src/dm/impls/swarm/data_ex.c:
src/dm/impls/swarm/swarm.c:
src/dm/impls/swarm/swarm_migrate.c:
src/ksp/ksp/impls/fcg/pipefcg/pipefcg.c:
src/ksp/ksp/impls/gcr/pipegcr/pipegcr.c:
src/ksp/ksp/impls/gmres/pipefgmres/pipefgmres.c:
src/ksp/ksp/impls/tsirm/tsirm.c:
src/ksp/ksp/interface/itcreate.c:
src/ksp/ksp/interface/iterativ.c:
src/ksp/ksp/interface/saws/kspsaws.c:
src/ksp/pc/impls/bddc/bddcfetidp.c:
src/ksp/pc/impls/fieldsplit/fieldsplit.c:
src/ksp/pc/impls/gamg/util.c:
src/ksp/pc/impls/gasm/gasm.c:
src/ksp/pc/impls/is/nn/nn.c:
src/ksp/pc/impls/patch/pcpatch.c:
src/ksp/pc/impls/tfs/gs.c:
src/ksp/pc/impls/tfs/tfs.c:
src/ksp/pc/impls/tfs/xxt.c:
src/ksp/pc/impls/tfs/xyt.c:
src/ksp/pc/interface/precon.c:
src/mat/impls/aij/mpi/mpiaij.c:#define
src/mat/interface/matrix.c:
src/mat/interface/matrix.c:.
src/mat/interface/matrix.c:
src/mat/interface/matrix.c:$
src/mat/utils/multequal.c:
src/snes/interface/saws/snessaws.c:
src/snes/interface/snes.c:
src/sys/classes/draw/interface/drawreg.c:
src/sys/classes/random/interface/random.c:
src/sys/classes/random/interface/randomc.c:
src/sys/classes/viewer/impls/ams/ams.c:
src/sys/classes/viewer/impls/ams/amsopen.c:
src/sys/classes/viewer/impls/ascii/vcreatea.c:
src/sys/classes/viewer/impls/mathematica/mathematica.c:
src/sys/dll/reg.c:
src/sys/dll/reg.c:static
src/sys/dll/reg.c:
src/sys/error/adebug.c:
src/sys/error/checkptr.c:
src/sys/error/errstop.c:
src/sys/error/pstack.c:
src/sys/error/signal.c:
src/sys/ftn-custom/zutils.c:
src/sys/info/verboseinfo.c:
src/sys/logging/plog.c:
src/sys/logging/utils/eventlog.c:
src/sys/logging/xmllogevent.c:
src/sys/memory/mal.c:
src/sys/memory/mtr.c:
src/sys/objects/aoptions.c:
src/sys/objects/aoptions.c:+
src/sys/objects/aoptions.c:
src/sys/objects/ftn-custom/zstart.c:
src/sys/objects/ftn-custom/zstartf.c:
src/sys/objects/inherit.c:
src/sys/objects/init.c:
src/sys/objects/options.c:+
src/sys/objects/options.c:
src/sys/objects/pinit.c:MPI_Comm
src/sys/objects/pinit.c:
src/sys/utils/mpitr.c:
src/sys/utils/mpits.c:+
src/sys/utils/pbarrier.c:
src/sys/utils/pdisplay.c:
src/sys/yaml/yamlimpls.c:
src/sys/yaml/yamlimpls.c:+
src/sys/yaml/yamlimpls.c:
src/tao/pde_constrained/impls/lcl/lcl.c:
src/ts/interface/ts.c:
src/vec/is/is/utils/iscoloring.c:
src/vec/vec/impls/seq/seqviennacl/vecviennacl.cxx:
src/vec/vec/interface/vector.c:.
src/vec/vec/interface/vector.c:
show more ...
|