| #
8a9f67ba
|
| 22-Apr-2019 |
Lisandro Dalcin <dalcinl@gmail.com> |
Fix hash table map
* ValType cannot be assumed to support any unary/binary operator.
* Remove hashmapiv.h as it is trivial and used only once.
|
| #
acc4240f
|
| 21-Apr-2019 |
Fande Kong <fdkong.jd@gmail.com> |
Merged in Fande-Kong/feature-ptap-all-at-once (pull request #1552)
All-at-once algorithm for MPIPtAP
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
|
| #
ef7a94f2
|
| 21-Apr-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: fixed some compiling warnings
|
| #
4a56b808
|
| 22-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: implement all-at-once algorithm
scalable and nonscalable just take too much memory since they cache the intermediate data structure.
The all-at-once algorithm do all caculations at once wi
MPIPtAP: implement all-at-once algorithm
scalable and nonscalable just take too much memory since they cache the intermediate data structure.
The all-at-once algorithm do all caculations at once without caching any data. It saves a lot of the memory
There are two implementations: allatonce and allatonce_merged
``allatonce" overlapp the communication and the computation with taking a few extra operations.
``allatonce_merged" do all caculations together for remote and local parts.
Both are memory friendly
show more ...
|
| #
5b5f1a93
|
| 17-Apr-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
Merged in hzhang/matmatops-alg (pull request #1548)
maintain algorithm type for mat-mat ops after calling MatFreeIntermediateDataStruct
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
|
| #
9b3d8a68
|
| 15-Mar-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
maintain algtype for mat-mat ops after calling MatFreeIntermediateDataStructures().
Requested by Fande Kong
|
| #
9a09376b
|
| 24-Mar-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Merge branch 'master' of bitbucket.org:petsc/petsc
|
| #
f04ab7ec
|
| 22-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
Merged in Fande-Kong/fixed_PtAP (pull request #1452)
MPIPtAP: Enable large-scale simulations
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
|
| #
e83e5f86
|
| 21-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP and MatMatMult: take the prefix from the parent matrix
when calling an inner MatMatMult
|
| #
154d0d78
|
| 20-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: Always call MatMatMultNumeric_SeqAIJ_SeqAIJ_Scalable in MatPtAPNumeric_MPIAIJ_MPIAIJ_scalable
since we care about the memory usage. Some symbolic algorithms such as heap is really good sinc
MPIPtAP: Always call MatMatMultNumeric_SeqAIJ_SeqAIJ_Scalable in MatPtAPNumeric_MPIAIJ_MPIAIJ_scalable
since we care about the memory usage. Some symbolic algorithms such as heap is really good since
it does not take a global size, but it is attached with MatMatMultNumeric_SeqAIJ_SeqAIJ_Sorted
show more ...
|
| #
df97dc6d
|
| 19-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
Refactored MatMatMult_SeqAIJ_SeqAIJ so that we can choose different
algorithms during runtime for MPIPtAP
|
| #
a3bb6f32
|
| 16-Mar-2019 |
Fande Kong <fdkong.jd@gmail.com> |
MPIPtAP: Enable large-scale simulations
The old code uses a global size of columns when creating the local matrix
This uses a lot of memory when calling MatMatMultSymbolic_SeqAIJ_SeqAIJ
We here co
MPIPtAP: Enable large-scale simulations
The old code uses a global size of columns when creating the local matrix
This uses a lot of memory when calling MatMatMultSymbolic_SeqAIJ_SeqAIJ
We here compact out many extra columns, and construct a new local size.
show more ...
|
| #
8000f006
|
| 15-Mar-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Merge branch 'master' of bitbucket.org:petsc/petsc
|
| #
a8d7486b
|
| 13-Mar-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
Merged in hzhang/fix-matview-duplicate-product (pull request #1437)
Hzhang/fix matview duplicate product
Approved-by: BarryFSmith <bsmith@mcs.anl.gov>
|
| #
baa1ba78
|
| 12-Mar-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
bugfix for MatView_MPIAIJ_PtAP() as reported by Stefano Zampini.
When MatView a matrix Amat which is a duplicate PtAP, it should call base MatView_MPIAIJ() because MatDuplicate only creates base matr
bugfix for MatView_MPIAIJ_PtAP() as reported by Stefano Zampini.
When MatView a matrix Amat which is a duplicate PtAP, it should call base MatView_MPIAIJ() because MatDuplicate only creates base matrix (see Note). However, it calls MatGetOperation(mat,MATOP_VIEW,&viewf); MatSetOperation(B,MATOP_VIEW,viewf); i.e., it copies old matview ops. This patch fix the bug.
show more ...
|
| #
a041468a
|
| 06-Mar-2019 |
Lawrence Mitchell <lawrence@wence.uk> |
Merge branch 'master' into wence/feature-patch-all-at-once
|
| #
b0f52d29
|
| 28-Jan-2019 |
Joseph Pusztay <josephpusztay@Josephs-MacBook-Pro.local> |
Merge branch 'master' into jpusztay/feature-swarm-symplectic-example
|
| #
940dfb0a
|
| 28-Jan-2019 |
Joseph Pusztay <josephpu@buffalo.edu> |
Merged petsc/petsc into master
|
| #
30faf514
|
| 27-Jan-2019 |
m_diehl <m.diehl@mpie.de> |
Merged petsc/petsc into master
|
| #
65b4dda0
|
| 22-Jan-2019 |
Barry Smith <bsmith@mcs.anl.gov> |
Merge branch 'hzhang/matptap-noreuse'
|
| #
ddad275a
|
| 21-Jan-2019 |
Patrick Farrell <patrick@pefarrell.org> |
Merge branch 'master' into knepley/feature-snes-patch
|
| #
6a85650d
|
| 21-Jan-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
bugfix for hypre build as reported by regression test on next branch
|
| #
7d0a89b7
|
| 18-Jan-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
mv checking "-mat_freeintermediatedatastructures" from XXXNumeric_() to driver XXX_() routine.
|
| #
715a5346
|
| 18-Jan-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
replace PetscObjectOptionsBegin() with PetscOptionsBegin() as suggested by Barry. This prevents flooding -help output as complained by Jed.
|
| #
60552cea
|
| 17-Jan-2019 |
Hong Zhang <hzhang@mcs.anl.gov> |
fix memory leak reported by regression tests
|