Trilinos merge requestshttps://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests2019-05-07T03:24:16Zhttps://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5118Tpetra: Attempt to Fix #51172019-05-07T03:24:16ZJames WillenbringTpetra: Attempt to Fix #5117*Created by: mhoemmen*
@trilinos/tpetra
## Description
First attempt at fixing #5117. NOT ALL THE TESTS PASS with the current changes! The following TpetraCore tests still fail:
```
35 - TpetraCore_CrsGraph_UnitTests0_MPI_4...*Created by: mhoemmen*
@trilinos/tpetra
## Description
First attempt at fixing #5117. NOT ALL THE TESTS PASS with the current changes! The following TpetraCore tests still fail:
```
35 - TpetraCore_CrsGraph_UnitTests0_MPI_4 (Failed)
51 - TpetraCore_CrsMatrix_NonlocalAfterResume_MPI_4 (Failed)
62 - TpetraCore_CrsMatrix_Bug6171_MPI_2 (Failed)
72 - TpetraCore_Albany182_MPI_4 (Failed)
97 - TpetraCore_ImportExport2_UnitTests_MPI_4 (Failed)
99 - TpetraCore_MatrixMarket_Tpetra_CrsMatrix_InOutTest_MPI_4 (Failed)
100 - TpetraCore_MatrixMarket_Tpetra_CrsGraph_InOutTest_MPI_4 (Failed)
101 - TpetraCore_MatrixMarket_Operator_Test_MPI_4 (Failed)
132 - TpetraCore_MatrixMatrix_UnitTests_MPI_4 (Failed)
133 - TpetraCore_AddProfiling_UnitTests_MPI_4 (Failed)
135 - TpetraCore_MultiVector_UnitTests_MPI_4 (Failed)
161 - TpetraCore_RowMatrixTransposer_test_MPI_4 (Failed)
171 - TpetraCore_lesson05_redistribution_MPI_4 (Failed)
175 - TpetraCore_FEMAssembly_InsertGlobalIndicesDP_MPI_4 (Failed)
176 - TpetraCore_FEMAssembly_LocalElementLoopDP_MPI_4 (Failed)
177 - TpetraCore_FEMAssembly_TotalElementLoopDP_MPI_4 (Failed)
189 - TpetraCore_guide_power_method_1_MPI_4 (Failed)
190 - TpetraCore_guide_matrix_fill_1_MPI_4 (Failed)
193 - TpetraCore_guide_data_redist_1_MPI_4 (Failed)
```
## Related Issues
* Closes #5117
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5115Tpetra: "New RTI" (Reduction Transform Interface), Part 1 (for_each, transform)2019-05-07T08:30:28ZJames WillenbringTpetra: "New RTI" (Reduction Transform Interface), Part 1 (for_each, transform)*Created by: mhoemmen*
@trilinos/tpetra
## Description
Tpetra once had something called the Reduction Transform Interface (RTI). It let users apply a function to each entry of one or two (or three, I think) `Tpetra::Vector`s, an...*Created by: mhoemmen*
@trilinos/tpetra
## Description
Tpetra once had something called the Reduction Transform Interface (RTI). It let users apply a function to each entry of one or two (or three, I think) `Tpetra::Vector`s, and then possibly end with a reduction over the output Vector.
This commit starts anew with RTI, by adding the following features:
1. `withLocalAccess`: Access the local data of a `Tpetra::)Multi)Vector` in a given memory space -- a declarative replacement for DualView-style functions
2. `for_each`: Works like `std::for_each`, but for `Tpetra::(Multi)Vector`
3. `transform`: Works like unary or binary `std::transform`, but for `Tpetra::(Multi)Vector`
(2) and (3) use (1). All of these have extension points so that they can be adapted for other objects, such as CrsGraph or CrsMatrix.
## Motivation and Context
Users want to apply functions entrywise to a Vector or MultiVector. They want to get at the local data, and they want Tpetra to handle the sync and modify flag stuff for them. Tpetra wants the power to do things like lazy allocation (see #333) that go beyond what `Kokkos::DualView` allows. Tpetra wants to protect users from holding on to owning `Kokkos::View` that really belong to Tpetra objects, because that can cause bugs (e.g., if the mesh that produced the linear system has changed) and unnecessary memory usage.
## Next steps
1. Add `transform_reduce` (the "R" in "RTI")
2. Think about how to do kernel fusion with a mixture of Vector and CrsMatrix (or at least provide a "residual" interface)
## Related Issues
* Closes: #3471
* Related to #333, #364, #381, #415, #768, #1424, #1896https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5113Clean up a warning & set Werror for Pamgen2019-05-07T04:08:54ZJames WillenbringClean up a warning & set Werror for Pamgen*Created by: ZUUL42*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` wi...*Created by: ZUUL42*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` will be ignored.
Provide a general summary of your changes in the Title above. If this pull
request pertains to a particular package in Trilinos, it's worthwhile to start
the title with "PackageName: ".
Note that anything between these delimiters is a comment that will not appear
in the pull request description once created. Most areas in this message are
commented out and can be easily added by removing the comment delimiters.
Please make sure to mark:
* Reviewers
* Assignees
* Labels
Replace <teamName> below with the appropriate Trilinos package/team name.
-->
@trilinos/pamgen @trilinos/framework
## Description
<!--- Please describe your changes in detail. -->
This removes a couple of lines that are unused variables and sets Werror for Pamgen.
## Motivation and Context
<!--- Why is this change required? What problem does it solve? -->
This is work towards #3178 and takes care of #5104.
<!---
If applicable, let us know how this merge request is related to any other open
issues or pull requests:
## Related Issues
* Closes
* Blocks
* Is blocked by
* Follows
* Precedes
* Related to
* Part of
* Composed of
-->
<!---
## Screenshots
Not obligatory, but is there anything pertinent that we should see?
-->
<!---
Go over all the following points, and put an `x` in all the boxes that apply.
If you are unsure about any of these, please ask—we are here to help.
-->
## Checklist
- [x] My commit messages mention the appropriate GitHub issue numbers.
- [x] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [x] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [x] All new and existing tests passed.
- [x] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.
<!---
## Additional Information
Anything else we need to know in evaluating this merge request?
-->
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5111Move the gcc 4.8.4 build to use static libraries2019-05-06T19:40:38ZJames WillenbringMove the gcc 4.8.4 build to use static libraries*Created by: prwolfe*
@trilinos/framework
## Description
This is the changes needed to the PR environment and scripts to get the gcc 4.8.4 build to use static libraries. Note that the build still fails on some missing template inst...*Created by: prwolfe*
@trilinos/framework
## Description
This is the changes needed to the PR environment and scripts to get the gcc 4.8.4 build to use static libraries. Note that the build still fails on some missing template instantiations so this cannot merge until those issues are resolved.
## Motivation and Context
Builds for external customers should work withe either shared or static libraries
## Related Issues
* Closes #5058
## How Has This Been Tested?
I used the instructions at https://github.com/trilinos/Trilinos/wiki/Reproducing-PR-Testing-Errors to build this locally.
## Checklist
- [ x ] My commit messages mention the appropriate GitHub issue numbers.
- [ ] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [ ] I have updated the documentation accordingly.
- [ ] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [ ] I have added tests to cover my changes.
- [ x ] All new and existing tests passed.
- [ ] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.
Additional issues for the template problems will be created directly.https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5085Teuchos: ostream deprecation -- corrections for 12.16 release branch2019-05-04T01:17:12ZJames WillenbringTeuchos: ostream deprecation -- corrections for 12.16 release branch*Created by: kddevin*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` w...*Created by: kddevin*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` will be ignored.
Provide a general summary of your changes in the Title above. If this pull
request pertains to a particular package in Trilinos, it's worthwhile to start
the title with "PackageName: ".
Note that anything between these delimiters is a comment that will not appear
in the pull request description once created. Most areas in this message are
commented out and can be easily added by removing the comment delimiters.
Please make sure to mark:
* Reviewers
* Assignees
* Labels
Replace <teamName> below with the appropriate Trilinos package/team name.
-->
@trilinos/teuchos @rhoope @mseldre
## Description
The ostream operator of serial dense matrix was deprecated in release 12.6.
This PR adds the TEUCHOS_DEPRECATION flags and fixes upstream packages.
## Motivation and Context
<!--- Why is this change required? What problem does it solve? -->
#4430 #4330
<!---
If applicable, let us know how this merge request is related to any other open
issues or pull requests:
## Related Issues
* Closes
* Blocks
* Is blocked by
* Follows
* Precedes
* Related to
* Part of
* Composed of
-->
## How Has This Been Tested?
On Mac with TEUCHOS_HIDE_DEPRECATED_CODE=ON.
```
cmake \
-D Trilinos_ENABLE_EXPLICIT_INSTANTIATION:BOOL=ON \
-D CMAKE_BUILD_TYPE:STRING="DEBUG" \
-D CMAKE_VERBOSE_MAKEFILE:BOOL=OFF \
\
-D MPI_BIN_DIR:PATH="/Users/kddevin/InstalledSoftware/openmpi-1.8.3_clang/bin" \
-D TPL_ENABLE_MPI:BOOL=ON \
-D MPI_EXEC_MAX_NUMPROCS:STRING=11 \
\
-D TPL_ENABLE_BinUtils:BOOL=OFF \
-D TPL_ENABLE_Pthread:BOOL=OFF \
\
-D CMAKE_C_FLAGS:STRING="-Wall -pedantic -Wno-unknown-pragmas -Wno-narrowing -Wno-inline -Wshadow -Wdeprecated-declarations -Wempty-body -Wignored-qualifiers -Wmissing-field-initializers -Wsign-compare -Wtype-limits -Wuninitialized -Winit-self -fstrict-aliasing -Wno-long-long" \
-D CMAKE_CXX_FLAGS:STRING="-DTPETRA_ENABLE_DEPRECATED_CODE -Wall -pedantic -Wno-unknown-pragmas -Wno-narrowing -Wno-delete-non-virtual-dtor -Wno-inline -Wshadow -Wdeprecated-declarations -Wempty-body -Wignored-qualifiers -Wmissing-field-initializers -Wsign-compare -Wtype-limits -Wuninitialized -Winit-self -fstrict-aliasing" \
\
-D Trilinos_ENABLE_ALL_OPTIONAL_PACKAGES:BOOL=ON \
-D Trilinos_ENABLE_TESTS:BOOL=ON \
-D Trilinos_ENABLE_EXAMPLES:BOOL=ON \
\
-D Trilinos_ENABLE_SHADOW_WARNINGS:BOOL=ON \
-D Trilinos_VERBOSE_CONFIGURE:BOOL=OFF \
-D Trilinos_ENABLE_Fortran:BOOL=OFF \
\
-D Teuchos_HIDE_DEPRECATED_CODE:BOOL=ON \
\
-D Trilinos_ENABLE_Stokhos:BOOL=ON \
-D Trilinos_ENABLE_Nox:BOOL=ON \
-D Trilinos_ENABLE_ROL:BOOL=ON \
-D ROL_ENABLE_EXAMPLES:BOOL=OFF \
-D Trilinos_ENABLE_MiniTensor:BOOL=OFF \
-D ROL_ENABLE_MiniTensor:BOOL=OFF \
-D Trilinos_ENABLE_Panzer:BOOL=ON \
-D Trilinos_ENABLE_Tempus:BOOL=ON \
-D Trilinos_ENABLE_PanzerAdaptersSTK:BOOL=OFF \
-D Trilinos_ENABLE_PanzerAdaptersIOSS:BOOL=OFF \
-D Trilinos_ENABLE_Thyra:BOOL=ON \
-D Trilinos_ENABLE_MueLu:BOOL=ON \
-D Trilinos_ENABLE_Anasazi:BOOL=ON \
-D Trilinos_ENABLE_Belos:BOOL=ON \
-D Trilinos_ENABLE_TrilinosCouplings:BOOL=ON \
-D Trilinos_ENABLE_STKIO:BOOL=OFF \
-D Trilinos_ENABLE_STKUtil:BOOL=OFF \
\
-D Teuchos_ENABLE_STACKTRACE:BOOL=OFF \
..
```
<!---
## Screenshots
Not obligatory, but is there anything pertinent that we should see?
-->
<!---
Go over all the following points, and put an `x` in all the boxes that apply.
If you are unsure about any of these, please ask—we are here to help.
-->
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [ ] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [ ] I have updated the documentation accordingly.
- [ ] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [ ] I have added tests to cover my changes.
- [ ] All new and existing tests passed.
- [ ] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.
<!---
## Additional Information
Anything else we need to know in evaluating this merge request?
-->
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5054WIP: Improve 'mutrino' test run-times some (ATDV-131, TRIL-219)2019-05-03T14:54:43ZJames WillenbringWIP: Improve 'mutrino' test run-times some (ATDV-131, TRIL-219)*Created by: bartlettroscoe*
CC: @fryeguy52
These improvements are based on the work by Brad King at Kitware in:
* https://gitlab.kitware.com/snl/project-1/issues/91
Also see [ATDV-131](https://sems-atlassian-srn.sandia.gov/br...*Created by: bartlettroscoe*
CC: @fryeguy52
These improvements are based on the work by Brad King at Kitware in:
* https://gitlab.kitware.com/snl/project-1/issues/91
Also see [ATDV-131](https://sems-atlassian-srn.sandia.gov/browse/ATDV-131)
## How was this tested?
I ran this on 'mutrino' in some extensive testing in summarized in [ATDV-131](https://sems-atlassian-srn.sandia.gov/browse/ATDV-131?focusedCommentId=34363&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-34363). The final commit to use `ctest -j4` for both the builds was verified on 'mutrino' with:
```
$ env \
Trilinos_PACKAGES=Panzer \
CTEST_START_WITH_EMPTY_BINARY_DIRECTORY=FALSE \
CTEST_DO_CONFIGURE=OFF \
CTEST_DO_BUILD=FALSE \
./ctest-s-local-test-driver.sh intel-opt-openmp-HSW intel-opt-openmp-KNL
***
*** ./ctest-s-local-test-driver.sh intel-opt-openmp-HSW intel-opt-openmp-KNL
***
ATDM_TRILINOS_DIR = '/home/rabartl/Trilinos.base/Trilinos'
Load some env to get python, cmake, etc ...
Hostname 'mutrino' matches known ATDM host 'mutrino' and system 'mutrino'
Setting compiler and build options for buld name 'default'
Using mutrino compiler stack INTEL to build DEBUG code with Kokkos node type SERIAL and KOKKOS_ARCH=HSW
Running builds:
intel-opt-openmp-HSW
intel-opt-openmp-KNL
Running Jenkins driver Trilinos-atdm-mutrino-intel-opt-openmp-HSW.sh ...
real 6m15.261s
user 0m2.926s
sys 0m0.814s
Running Jenkins driver Trilinos-atdm-mutrino-intel-opt-openmp-KNL.sh ...
real 14m15.213s
user 0m2.558s
sys 0m0.617s
```
which posted to CDash builds:
* HSW: https://testing.sandia.gov/cdash/index.php?project=Trilinos&parentid=4976653
* KNL: https://testing.sandia.gov/cdash/index.php?project=Trilinos&parentid=4976655
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/5026NOX: use similarity transform Jacobian when computing row sums2019-05-01T14:25:42ZJames WillenbringNOX: use similarity transform Jacobian when computing row sums*Created by: rppawlo*
*Created by: rppawlo*
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4947Adding the unit tests for the clean_workspace tool2019-04-29T17:12:16ZJames WillenbringAdding the unit tests for the clean_workspace tool*Created by: prwolfe*
As we discussed getting these to always run is vital.
I will be working on python 2/3 coexistence next.
@trilinos/framework
## Description
Just adding the make spec to get these python tests running.
##...*Created by: prwolfe*
As we discussed getting these to always run is vital.
I will be working on python 2/3 coexistence next.
@trilinos/framework
## Description
Just adding the make spec to get these python tests running.
## Motivation and Context
All testing should happen at PR time as well as by hand.
## How Has This Been Tested?
Built as if in a PR test and ran the python tests by hand.
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4918Tpetra: Adding Dirichlet condition helper routine2019-04-24T15:53:31ZJames WillenbringTpetra: Adding Dirichlet condition helper routine*Created by: csiefer2*
Auto-PR for SHA 6c3776f*Created by: csiefer2*
Auto-PR for SHA 6c3776fhttps://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4884Tempus: Add Ability to Integrate Auxiliary Variables #48832019-04-15T04:45:26ZJames WillenbringTempus: Add Ability to Integrate Auxiliary Variables #4883*Created by: ccober6*
@trilinos/tempus
## Description
See #4883
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [ ] My code follows the code style of the affected package(s).
- [ ] I...*Created by: ccober6*
@trilinos/tempus
## Description
See #4883
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [ ] My code follows the code style of the affected package(s).
- [ ] I have added tests to cover my changes.
- [ ] All new and existing tests passed.
- [ ] No new compiler warnings were introduced.https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4782WIP Tpetra: persistent MPI requests2019-04-04T16:31:51ZJames WillenbringWIP Tpetra: persistent MPI requests*Created by: cgcgcg*
@trilinos/tpetra
## Description
This PR adds the option to use persistent MPI communication in Tpetra. The defaults communication option is not changed. I tested this using MueLu, where this can be switched on ...*Created by: cgcgcg*
@trilinos/tpetra
## Description
This PR adds the option to use persistent MPI communication in Tpetra. The defaults communication option is not changed. I tested this using MueLu, where this can be switched on for the solve phase only. There are probably quite a lot of cases where this will not work correctly, so I appreciate feedback! https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4781Muelu: Allow to change distributor options2019-04-03T11:26:41ZJames WillenbringMuelu: Allow to change distributor options*Created by: cgcgcg*
@trilinos/muelu @trilinos/xpetra
## Description
This PR adds the option to set a new sublist "matvec params" in the xml interface. The content of the sublist will be applied to the underlying Tpetra::Distributo...*Created by: cgcgcg*
@trilinos/muelu @trilinos/xpetra
## Description
This PR adds the option to set a new sublist "matvec params" in the xml interface. The content of the sublist will be applied to the underlying Tpetra::Distributors for the solve phase. In particular, this allows to choose different communication options apart from the default Irecv-Send pattern.https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4683Spack environment for ATDM trilinos2019-03-28T21:45:07ZJames WillenbringSpack environment for ATDM trilinos*Created by: fryeguy52*
Spack environment for ATDM trilinos*Created by: fryeguy52*
Spack environment for ATDM trilinoshttps://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4620Tpetra MV: Use specialized KokkosBlas::dot in multiply()2019-03-18T23:33:14ZJames WillenbringTpetra MV: Use specialized KokkosBlas::dot in multiply()*Created by: cgcgcg*
@trilinos/tpetra
## Description
Use a specialized KokkosKernels function in `multiply` when either one of the two factors has only one column.*Created by: cgcgcg*
@trilinos/tpetra
## Description
Use a specialized KokkosKernels function in `multiply` when either one of the two factors has only one column.https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4400Xpetra: fixed dependency on Tpetra instantations2019-04-12T20:25:54ZJames WillenbringXpetra: fixed dependency on Tpetra instantations*Created by: brian-kelley*
Satisfy dependency of Xpetra EpetraMap on
Tpetra::Details::FixedHashTable with int/long and
int/longlong as LO/GO. These dependencies always exist
as long as Tpetra is enabled, but regardless of whether
th...*Created by: brian-kelley*
Satisfy dependency of Xpetra EpetraMap on
Tpetra::Details::FixedHashTable with int/long and
int/longlong as LO/GO. These dependencies always exist
as long as Tpetra is enabled, but regardless of whether
these LO/GO combinations are enabled in Tpetra ETI.
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` will be ignored.
Provide a general summary of your changes in the Title above. If this pull
request pertains to a particular package in Trilinos, it's worthwhile to start
the title with "PackageName: ".
Note that anything between these delimiters is a comment that will not appear
in the pull request description once created. Most areas in this message are
commented out and can be easily added by removing the comment delimiters.
Please make sure to mark:
* Reviewers
* Assignees
* Labels
Replace <teamName> below with the appropriate Trilinos package/team name.
-->
@trilinos/xpetra
## Description
<!--- Please describe your changes in detail. -->
Xpetra_EpetraMap.cpp now includes the def of
FixedHashTable so that these instantiations can be made, even if int/long
and/or int/longlong haven't been enabled in ETI. The include is only done if
Tpetra and Xpetra kokkos refactor are both enabled, because Xpetra::EpetraMap
only uses FixedHashTable in this case.
## Motivation and Context
<!--- Why is this change required? What problem does it solve? -->
This fixes an "undefined symbol" error during the final link of Albany (or any other app executable). Without this code change, the only workaround is to enable both TPETRA_INST_INT_LONG and TPETRA_INST_INT_LONG_LONG in configuration (huge code size increase). Only the instantiation of FixedHashTable is needed, not all of Tpetra.
<!---
If applicable, let us know how this merge request is related to any other open
issues or pull requests:
## Related Issues
* Closes
* Blocks
* Is blocked by
* Follows
* Precedes
* Part of
* Composed of
-->
* Related to #4038
## How Has This Been Tested?
<!---
Please describe in detail how you tested your changes. Include details of your
testing environment and the tests you ran to see how your change affects other
areas of the code. Consider including configure, build, and test log files.
-->
Tested by successfully building Trilinos/Albany without TPETRA_INST_INT_LONG.
<!---
## Screenshots
Not obligatory, but is there anything pertinent that we should see?
-->
<!---
Go over all the following points, and put an `x` in all the boxes that apply.
If you are unsure about any of these, please ask—we are here to help.
-->
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [x] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [ ] I have updated the documentation accordingly.
- [ ] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [ ] I have added tests to cover my changes.
- [ ] All new and existing tests passed.
- [x] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.
<!---
## Additional Information
Anything else we need to know in evaluating this merge request?
-->
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4390ShyLU: FROSch Repeated Map2019-03-04T18:47:42ZJames WillenbringShyLU: FROSch Repeated Map*Created by: roeverf*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` w...*Created by: roeverf*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` will be ignored.
Provide a general summary of your changes in the Title above. If this pull
request pertains to a particular package in Trilinos, it's worthwhile to start
the title with "PackageName: ".
Note that anything between these delimiters is a comment that will not appear
in the pull request description once created. Most areas in this message are
commented out and can be easily added by removing the comment delimiters.
Please make sure to mark:
* Reviewers
* Assignees
* Labels
Replace <teamName> below with the appropriate Trilinos package/team name.
-->
@trilinos/shylu
## Description
<!--- Please describe your changes in detail. -->
This PR follows PR #4324.
It adds a function to FROSch_Tools_decl/def.hpp calculating a repeated map from the dual graph and an element node list.
The graph ist partitioned using Zoltan2. The new column-map is used to obtain the repeated map from the element node list.
The function is used to calculate a repeated map for the coarse level. The calculation of the repeated map can be switched on and off in the parameterlist.
For the coarse level: The required graph is build using the getConnectivityEntities function from the DDInterface class . The element node list is built from the initial row map of the coarse matrix.
So far the calculation of the repeated map for the coarse matrix is only possible if the underlying is Tpetra.
This PR also adds the option Thyra to FROSch_SubdomainSolver.
## Motivation and Context
<!--- Why is this change required? What problem does it solve? -->
<!---
If applicable, let us know how this merge request is related to any other open
issues or pull requests:
## Related Issues
* Closes
* Blocks
* Is blocked by
* Follows
* Precedes
* Related to
* Part of
* Composed of
-->
## How Has This Been Tested?
All prior existing ShyLu-DD/FROSch test were passed. For specific tests concerning the repeated map for the coarse space new parameter lists were added to the Thyra_Xpetra_Laplace test switching on the calculation of the repeated map. Iteration counts are equal to the existing tests solving the same problem.
All test were run on a Mac OS X, compiled with MPICH version 3.2.1.
<!---
Please describe in detail how you tested your changes. Include details of your
testing environment and the tests you ran to see how your change affects other
areas of the code. Consider including configure, build, and test log files.
-->
<!---
## Screenshots
Not obligatory, but is there anything pertinent that we should see?
-->
<!---
Go over all the following points, and put an `x` in all the boxes that apply.
If you are unsure about any of these, please ask—we are here to help.
-->
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [x] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [ ] I have updated the documentation accordingly.
- [ ] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [x] I have added tests to cover my changes.
- [x] All new and existing tests passed.
- [x] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.
<!---
## Additional Information
Anything else we need to know in evaluating this merge request?
-->
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/4230WIP: Panzer - Changes to workset interface2019-03-21T20:12:53ZJames WillenbringWIP: Panzer - Changes to workset interface*Created by: seamill*
This is a WIP-PR to discuss changes to the workset interface - for review purposes only.
Closes #4205.
@trilinos/panzer
## Description
See #4205.
## Motivation and Context
See #4205.
*Created by: seamill*
This is a WIP-PR to discuss changes to the workset interface - for review purposes only.
Closes #4205.
@trilinos/panzer
## Description
See #4205.
## Motivation and Context
See #4205.
https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/3745MueLu: adding easy xml for coordinates transfer using the toggle factory2018-10-29T18:01:29ZJames WillenbringMueLu: adding easy xml for coordinates transfer using the toggle factory*Created by: lucbv*
@trilinos/muelu
Most changes happen in the parameter list interpreter and the toggle coordinates transfer factory.
Adding a check in ToggleCoordinatesTransferFactory in case no coordinates are available on level...*Created by: lucbv*
@trilinos/muelu
Most changes happen in the parameter list interpreter and the toggle coordinates transfer factory.
Adding a check in ToggleCoordinatesTransferFactory in case no coordinates are available on level 0.
## Description
This PR adds some logic to the easy xml interface providing capabilities for the toggle and semi-coarsening.
## Motivation and Context
This feature is requested by @ikalash for ice sheet simulationshttps://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/3581Tpetra::Distributor: Fix #35802019-01-23T23:40:53ZJames WillenbringTpetra::Distributor: Fix #3580*Created by: mhoemmen*
@trilinos/tpetra @jjellio
## Description
Fix #3580, by making all instances of the "slow path" in Distributor use a buffer long enough for all the messages, not just one at a time. Ignore the "Send type" a...*Created by: mhoemmen*
@trilinos/tpetra @jjellio
## Description
Fix #3580, by making all instances of the "slow path" in Distributor use a buffer long enough for all the messages, not just one at a time. Ignore the "Send type" and "Barrier between..." options, and always use `MPI_Isend` for sends.
* Closes #3580
## How Has This Been Tested?
Mac, Clang, OpenMPI.https://gitlab.osti.gov/jmwille/Trilinos/-/merge_requests/3457MueLu: Aggregate quality estimate2019-02-14T15:21:53ZJames WillenbringMueLu: Aggregate quality estimate*Created by: eepperly*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` ...*Created by: eepperly*
<!---
Be sure to select `develop` as the `base` branch against which to create this
pull request. Only pull requests against `develop` will undergo Trilinos'
automated testing. Pull requests against `master` will be ignored.
Provide a general summary of your changes in the Title above. If this pull
request pertains to a particular package in Trilinos, it's worthwhile to start
the title with "PackageName: ".
Note that anything between these delimiters is a comment that will not appear
in the pull request description once created. Most areas in this message are
commented out and can be easily added by removing the comment delimiters.
Please make sure to mark:
* Reviewers
* Assignees
* Labels
Replace <teamName> below with the appropriate Trilinos package/team name.
-->
@trilinos/muelu
## Description
A method for estimating qualities of the aggregates generated by MueLu for use as a
diagnostic tool was implemented. While originally proposed by Napov and Notay (2012)
as a method for tailoring aggregate generation in the context of unsmoothed
aggregation, the quality metric has also been found to be instructive in diagnosing
poorly made aggregates in the context of smoothed aggregation as well. The method
has been implemented in a new "AggregateQualityEstimateFactory", and has been
integrated into the XML interface.
## How Has This Been Tested?
Unit tests were written to test the new functionality and interface tests were written
to test the new functionality with the XML interface. New functionality was tested by
comparing against a MATLAB implementation of the same functionality. All new and
existing MueLu unit tests passed on a Linux machine.
## Checklist
- [ ] My commit messages mention the appropriate GitHub issue numbers.
- [x] My code follows the code style of the affected package(s).
- [ ] My change requires a change to the documentation.
- [ ] I have updated the documentation accordingly.
- [x] I have read the [code contribution guidelines](../blob/master/CONTRIBUTING.md) for this project.
- [x] I have added tests to cover my changes.
- [x] All new and existing tests passed.
- [x] No new compiler warnings were introduced.
- [ ] These changes break backwards compatibility.