| 4863603a | 28-Jun-2019 |
Satish Balay <balay@mcs.anl.gov> |
Adding vector logging, started matrix logging |
| f6c3de16 | 27-Jun-2019 |
Junchao Zhang <junchao.zhang@gmail.com> |
Merged in jczhang/mat-remove-unnecessary-global-IS (pull request #1816)
Remove unnecessary global IS when setting up Mvctx
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
Approved-by: Jed Brown <jed@
Merged in jczhang/mat-remove-unnecessary-global-IS (pull request #1816)
Remove unnecessary global IS when setting up Mvctx
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
Approved-by: Jed Brown <jed@59a2.org>
show more ...
|
| a2b725a8 | 27-Jun-2019 |
William Gropp <wgropp@illinois.edu> |
Fixes for doctext update |
| b6a92dca | 26-Jun-2019 |
BarryFSmith <bsmith@mcs.anl.gov> |
Merged in barry/cuda-multigrid-test (pull request #1763)
Various improvements for GPUs (mostly for performance and CUDA) |
| 071fcb05 | 05-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments
1) PetscCalloc*() now uses system calloc()
2) Merged some Pets
Non-numeric optimizations focused on AIJ, MatFDColoring, and DMCreateMatrix_DA_*AIJ, looking to improve performance in GPU environments
1) PetscCalloc*() now uses system calloc()
2) Merged some PetscMalloc*()
3) Eliminated unneeded PetscCalloc*()
4) Removed some memory allocations and copies in MatFDColoringSetUp(), added local variables for better compiler optimization
5) Added MatSetValues_SeqAIJ_SortedFull(), added MatSetOption(MAT_SORTED_FULL)
6) Optimized DMCreateMatrix_DA_*AIJ for nonperiodic case to automatically have sorted columns (faster MatSetValues() times)
7) Eliminated call to PetscMemzero() in PetscFree()
Commit-type: style-fix, feature
show more ...
|
| fdc842d1 | 31-May-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Various improvements for GPUs (mostly for performance and CUDA)
1) Add VecPinToCPU() for CUDA vector and matrices
2) Move initialization of cuBLAS to PetscInitialize() since it takes 1/2 second and
Various improvements for GPUs (mostly for performance and CUDA)
1) Add VecPinToCPU() for CUDA vector and matrices
2) Move initialization of cuBLAS to PetscInitialize() since it takes 1/2 second and distorts timing with -log_view
3) Add logging for DMCreateMatrix (for large meshes this is very large)
4) Add VecGet/RestoreArrayWrite() to prevent unneeded copies from GPU (only implemented so far for CUDA);
added a small number of usages in the source so that snes tutorials ex19 does not do unneeded communication from the GPU
5) Automatically convert MAIJ matrices to AIJ for CUDA since they are not yet supported natively in PETSc's CUDA matrix implementation
6) Pinned objects should still use the CUDA/ViennaCL versions of Destroy to clean up the GPU stuff
Commit-type: feature
show more ...
|
| a3ebf921 | 25-Jun-2019 |
Junchao Zhang <jczhang@mcs.anl.gov> |
Remove unnecessary global IS when setting up Mvctx
ISCreateGeneral(((PetscObject)mat)->comm..) will incur MPI_Allreduce on the communicator. |
| f22e0265 | 19-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Remove dead Matlab code, fix typo, fix caste needed for const free
Commit-type: portability-fix
Reported-by: Satish Balay <balay@mcs.anl.gov> |
| 70990e77 | 18-Jun-2019 |
Satish Balay <balay@mcs.anl.gov> |
fix -Wunused-value and -Wunused-but-set-variable warnings |
| 8f8f2f0d | 17-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Added MatUpdateMPIAIJWithArrays()
Commit-type: optimization, feature, example
Reported-by: Hong Zhang <hongzhang@anl.gov> |
| 857a15f1 | 17-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Resolved issues brought up in PR
Commit-type: bug-fix, style-fix
Reported-by: Patrick Sanan <patrick.sanan@gmail.com> |
| 580bdb30 | 07-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Add PetscArraycmp(), PetscArraycpy(), PetscArrayzero(), PetscArraymove(), update code to use new forms
Replace a couple multi-mallocs with a single malloc
Replace backwards loops in MatSetValues_*()
Add PetscArraycmp(), PetscArraycpy(), PetscArrayzero(), PetscArraymove(), update code to use new forms
Replace a couple multi-mallocs with a single malloc
Replace backwards loops in MatSetValues_*() with PetscArraymove()
Commit-type: style-fix, feature
show more ...
|
| 5363a190 | 09-Jun-2019 |
Satish Balay <balay@mcs.anl.gov> |
Merge branch 'pr1723/tappel/extend-mumps-parameters/master' [PR #1723] |
| cd70c088 | 09-Jun-2019 |
Satish Balay <balay@mcs.anl.gov> |
Merge remote-tracking branch 'origin/maint' |
| f6f02116 | 08-Jun-2019 |
Richard Tran Mills <rmills@rmills.org> |
Fixed misspelling of "paradigm" throughout manual pages. |
| d083f849 | 01-Jun-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Update the use of Collective on in the manual pages to reflect the new style
Commit-type: style-fix, documentation
Thanks-to: Patrick Sanan <patrick.sanan@gmail.com> |
| a0e18203 | 28-May-2019 |
Thibaut Appel <t.appel17@imperial.ac.uk> |
MUMPS: activate Block Low-Rank parameters
Version 5.2.0 of MUMPS features BLR (Block Low-Rank) factorization.
Extended ICNTL, INFO and INFOG to sizes 60, 80 and 80.
Added description and control par
MUMPS: activate Block Low-Rank parameters
Version 5.2.0 of MUMPS features BLR (Block Low-Rank) factorization.
Extended ICNTL, INFO and INFOG to sizes 60, 80 and 80.
Added description and control parameters (ICNTL) 35, 36 and 38.
show more ...
|
| bfcb38ea | 27-May-2019 |
Patrick Sanan <patrick.sanan@gmail.com> |
Man pages: remove .keywords: fields
This field is recognized by doctext from Sowing (http://wgropp.cs.illinois.edu/projects/software/sowing/doctext/node20.htm#Node20),
but it doesn't seem to be unif
Man pages: remove .keywords: fields
This field is recognized by doctext from Sowing (http://wgropp.cs.illinois.edu/projects/software/sowing/doctext/node20.htm#Node20),
but it doesn't seem to be uniformly used or maintained.
Thus, remove all .keywords: fields, and a following blank line, if present.
This is accomplished with GNU sed (gsed on OS X), with the following commands.
*Warning* that this type of command can corrupt a .git directory,
so be cautious in reusing or modifying these commands. They first look
for and delete matching lines with a following line consisting of only whitespace,
and then delete any remaining matching lines.
find src/ -type f -exec gsed -i '/keywords:/ {N; /\n\s*$/d}' {} +
find src/ -type f -exec gsed -i '/keywords:/d' {} +
find include/ -type f -exec gsed -i '/keywords:/ {N; /\n\s*$/d}' {} +
find include/ -type f -exec gsed -i '/keywords:/d' {} +
Hints on the sed command obtained from: https://unix.stackexchange.com/questions/100754/how-to-delete-a-specific-line-and-the-following-blank-line-using-gnu-sed
show more ...
|
| f2d70e9d | 25-May-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Remove the ReadWrite notation from Vec array access for GPU vectors to match usage on the CPU
Commit-type: style-fix
Development Tools: Vim, Emacs, Eclipse |
| b72fa766 | 16-May-2019 |
Lisandro Dalcin <dalcinl@gmail.com> |
Merged in dalcinl/fix-io-gmsh (pull request #1660)
Binary I/O And Gmsh DMPlex Reader
Approved-by: Matthew Knepley <knepley@gmail.com>
Approved-by: BarryFSmith <bsmith@mcs.anl.gov> |
| 0c0d7e18 | 13-May-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MatSetValues_MPIAIJ/SeqAIJ: added logflops for additions |
| 49c8f2b8 | 13-May-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: added flops for "allatonce" and "allatonce_merged" |
| 4584204d | 13-May-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: removed extra flops in "scalable" and "nonscalale"
It looks like all flops are already counted in AProw_xxx. |
| 9860990e | 03-May-2019 |
Lisandro Dalcin <dalcinl@gmail.com> |
Binary I/O: Various fixes and enhancements
* Change PetscBinary[Synchronized]Read() to allow for reading
items up to EOF without erroring
* Fix PetscViewerBinaryRead() to properly return the numbe
Binary I/O: Various fixes and enhancements
* Change PetscBinary[Synchronized]Read() to allow for reading
items up to EOF without erroring
* Fix PetscViewerBinaryRead() to properly return the number of items read
* Fix PetscViewerRead() to prevent infinite loops at EOF
* Various fixes for PetscDataType PETSC_COMPLEX
show more ...
|
| 4edbe3a6 | 12-May-2019 |
Karl Rupp <me@karlrupp.net> |
Merge branch 'barry/feature-pintocpu' [PR #1641]
* barry/feature-pintocpu:
Adding a MatPinToCPU() and VecPinToGPU() capability
For matrices this will prevent copies to the GPU when they will never b
Merge branch 'barry/feature-pintocpu' [PR #1641]
* barry/feature-pintocpu:
Adding a MatPinToCPU() and VecPinToGPU() capability
For matrices this will prevent copies to the GPU when they will never be used there.
For vectors this will prevent vectors from boucing back and forth between the CPU.
show more ...
|