Compare commits
47
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9bef1cc28f | ||
|
|
6b45d9a69b | ||
|
|
db32ae9807 | ||
|
|
545a257ab5 | ||
|
|
4b4aff736d | ||
|
|
727339e0ae | ||
|
|
d8d4d5b874 | ||
|
|
5a7a017a4e | ||
|
|
224aff5ac9 | ||
|
|
e42762365f | ||
|
|
765fb4a608 | ||
|
|
591156be2f | ||
|
|
8e2478f964 | ||
|
|
06c485bb3e | ||
|
|
1cd27605f0 | ||
|
|
547fd02911 | ||
|
|
aa92498033 | ||
|
|
024576620a | ||
|
|
5b670bda3f | ||
|
|
6b0e135bdb | ||
|
|
204b9df2d6 | ||
|
|
8b49379f87 | ||
|
|
d32a00fb2f | ||
|
|
59c9ca70e4 | ||
|
|
9646ce4d1a | ||
|
|
f46a81bf3a | ||
|
|
460e5ba483 | ||
|
|
34593dccac | ||
|
|
248ab78e77 | ||
|
|
6b9bdb11df | ||
|
|
505d2e5123 | ||
|
|
47cff96e2e | ||
|
|
010f455382 | ||
|
|
acebc322b8 | ||
|
|
25ec78df9a | ||
|
|
8c78387136 | ||
|
|
8684d9d5d1 | ||
|
|
2375953e95 | ||
|
|
ecbb196551 | ||
|
|
90ca758a98 | ||
|
|
93d674a7a2 | ||
|
|
03ec3f739b | ||
|
|
a3eb9c8e6b | ||
|
|
30f3e123cd | ||
|
|
4d4c2325f9 | ||
|
|
db84abedfc | ||
|
|
2609e3af6e |
@@ -94,16 +94,6 @@ inputs:
|
||||
description: If true, do not set any CXXFLAGS or LDFLAGS.
|
||||
default: false
|
||||
|
||||
# Unfortunately, "uses:" fields cannot have references to variables like
|
||||
# ${{env.MFEM_ACTIONS_VERSION}}, so the branch/tag name has to be hard coded.
|
||||
# Therefore, in the future, when updating the version of the
|
||||
# mfem/github-actions to use, we'll have to replace:
|
||||
# - all definitions of MFEM_ACTIONS_VERSION and
|
||||
# - all "uses:" fields that refer to mfem/github-actions.
|
||||
MFEM_ACTIONS_VERSION:
|
||||
description: Version (branch or tag) of the mfem/github-actions to use.
|
||||
default: v2.7
|
||||
|
||||
runs:
|
||||
using: 'composite'
|
||||
steps:
|
||||
@@ -128,7 +118,6 @@ runs:
|
||||
echo UBSAN_LDFLAGS=${{inputs.UBSAN_LDFLAGS}} >> $GITHUB_ENV
|
||||
echo MSAN_CXXFLAGS=${{inputs.MSAN_CXXFLAGS}} >> $GITHUB_ENV
|
||||
echo MSAN_LDFLAGS=${{inputs.MSAN_LDFLAGS}} >> $GITHUB_ENV
|
||||
echo MFEM_ACTIONS_VERSION=${{inputs.MFEM_ACTIONS_VERSION}} >> $GITHUB_ENV
|
||||
shell: bash
|
||||
|
||||
- name: Env (dir)
|
||||
|
||||
@@ -25,7 +25,7 @@ runs:
|
||||
steps:
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
|
||||
- uses: actions/cache@v5
|
||||
- uses: actions/cache@v4
|
||||
if: ${{env.DEBUG == 'true'}}
|
||||
id: debug
|
||||
with:
|
||||
@@ -53,7 +53,7 @@ runs:
|
||||
run: echo CXXFLAGS=${{env.CXXFLAGS}} ${{env.UBSAN_CXXFLAGS}} >> $GITHUB_ENV
|
||||
shell: bash
|
||||
|
||||
- uses: mfem/github-actions/build-mfem@v2.7
|
||||
- uses: mfem/github-actions/build-mfem@v2.5
|
||||
if: ${{steps.debug.outputs.cache-hit != 'true'}}
|
||||
env:
|
||||
CXXFLAGS: ${{env.CXXFLAGS}}
|
||||
@@ -82,7 +82,7 @@ runs:
|
||||
run: find . -type f -name '*.o' -delete
|
||||
shell: bash
|
||||
|
||||
- uses: actions/upload-artifact@v7
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: build-${{inputs.par}}-${{inputs.sanitizer}}
|
||||
path: mfem/build
|
||||
|
||||
@@ -12,11 +12,6 @@
|
||||
name: 'Install MPI'
|
||||
description: 'Installs MPI and set up its environment variables'
|
||||
|
||||
inputs:
|
||||
NO_FLAGS:
|
||||
description: If true, do not set any CXXFLAGS or LDFLAGS.
|
||||
default: false
|
||||
|
||||
runs:
|
||||
using: 'composite'
|
||||
steps:
|
||||
@@ -32,7 +27,6 @@ runs:
|
||||
shell: bash
|
||||
|
||||
- name: Env (bis)
|
||||
if: ${{ inputs.NO_FLAGS != 'true' }}
|
||||
run: |
|
||||
echo CXXFLAGS=${{env.CXXFLAGS}} ${{env.MPI_INC}} >> $GITHUB_ENV
|
||||
echo LDFLAGS=${{env.LDFLAGS}} ${{env.MPI_LIB}} >> $GITHUB_ENV
|
||||
|
||||
@@ -36,7 +36,7 @@ runs:
|
||||
steps:
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
|
||||
- uses: actions/cache@v5
|
||||
- uses: actions/cache@v4
|
||||
if: ${{env.DEBUG == 'true' && inputs.cache-skip != 'true'}}
|
||||
id: debug
|
||||
with:
|
||||
@@ -49,7 +49,7 @@ runs:
|
||||
par: ${{inputs.par}}
|
||||
sanitizer: ${{inputs.sanitizer}}
|
||||
|
||||
- uses: actions/download-artifact@v8
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
name: build-${{inputs.par}}-${{inputs.sanitizer}}
|
||||
path: mfem/build
|
||||
|
||||
@@ -23,7 +23,7 @@ inputs:
|
||||
runs:
|
||||
using: 'composite'
|
||||
steps:
|
||||
- uses: actions/cache/restore@v5 # Cache for LLVM libcxx
|
||||
- uses: actions/cache/restore@v4 # Cache for LLVM libcxx
|
||||
with:
|
||||
path: ${{env.LLVM_DIR}}
|
||||
fail-on-cache-miss: true
|
||||
@@ -32,32 +32,32 @@ runs:
|
||||
- uses: ./.github/actions/sanitize/mpi
|
||||
if: ${{inputs.par == 'true'}}
|
||||
|
||||
- uses: actions/cache/restore@v5 # Cache for Hypre
|
||||
- uses: actions/cache/restore@v4 # Cache for Hypre
|
||||
if: ${{inputs.par == 'true'}}
|
||||
with:
|
||||
path: ${{env.HYPRE_DIR}}
|
||||
fail-on-cache-miss: true
|
||||
key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-${{env.MFEM_ACTIONS_VERSION}}
|
||||
key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-v2.5
|
||||
|
||||
- uses: actions/cache/restore@v5 # Cache for Metis
|
||||
- uses: actions/cache/restore@v4 # Cache for Metis
|
||||
if: ${{inputs.par == 'true'}}
|
||||
with:
|
||||
path: ${{env.METIS_DIR}}
|
||||
fail-on-cache-miss: true
|
||||
key: ${{runner.os}}-build-${{env.METIS_DIR}}-${{env.MFEM_ACTIONS_VERSION}}
|
||||
key: ${{runner.os}}-build-${{env.METIS_DIR}}-v2.5
|
||||
|
||||
- name: Hypre/Metis links
|
||||
if: ${{inputs.par == 'true'}}
|
||||
run: ln -s -f ${{env.HYPRE_DIR}} hypre && ln -s -f ${{env.METIS_DIR}} metis-4.0
|
||||
shell: bash
|
||||
|
||||
- uses: actions/cache/restore@v5 # Cache for LSAN suppression file
|
||||
- uses: actions/cache/restore@v4 # Cache for LSAN suppression file
|
||||
with:
|
||||
path: ${{env.LSAN_DIR}}
|
||||
fail-on-cache-miss: true
|
||||
key: build-lsan-suppression-file
|
||||
|
||||
- uses: actions/checkout@v6 # Checkout the repository
|
||||
- uses: actions/checkout@v4 # Checkout the repository
|
||||
with:
|
||||
path: mfem
|
||||
# ref: ${{env.BRANCH}}
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
# MFEM Pull Request Review Agent Guide
|
||||
|
||||
## Purpose and scope
|
||||
Review MFEM PRs for correctness, maintainability, performance, portability, test coverage, and MFEM consistency. Use the diff and PR context; reference source files, tests, and CI results when available. Follow `CONTRIBUTING.md`, especially Developer Guidelines, PR rules, checklist, and testing.
|
||||
|
||||
## Critical review pillars
|
||||
- Correctness and numerical behavior
|
||||
- API and user-facing impact
|
||||
- Performance implications
|
||||
- Maintainability and portability
|
||||
|
||||
## Review workflow
|
||||
1. Read the PR description, linked issues, and intended behavior.
|
||||
2. Inspect the diff before commenting.
|
||||
3. Identify affected MFEM components, examples, tests, build or docs changes, and downstream APIs.
|
||||
4. Analyze the code against the critical review pillars.
|
||||
5. Compare the change against nearby code and MFEM patterns; flag unmotivated deviations.
|
||||
6. Check whether tests and documentation were updated appropriately.
|
||||
7. Review CI results and suggest actions.
|
||||
8. Produce a structured review with prioritized findings.
|
||||
9. Always limit conclusions to available evidence.
|
||||
|
||||
## MFEM-specific review checklist
|
||||
- Component-aware scope: identify the touched subsystem (FEM, solvers, preconditioners, linear algebra, mesh, examples, miniapps, build, or docs) and assess its impact against the review pillars.
|
||||
- Numerical and algorithmic behavior: assess issues in convergence, stability, tolerances, precision, iteration limits, and failure handling. If clear opportunities exist to improve the algorithmic approach, call them out with expected impact.
|
||||
- API and user-facing impact: assess backward compatibility, user-visible behavior and default changes, migration impact, deprecations, and whether documentation clearly explains user-facing API changes.
|
||||
- Data structure and memory semantics: assess ownership, lifetime, aliasing, container behavior, and device-host synchronization.
|
||||
- Parallel and serial behavior: assess whether the change preserves equivalent semantics in serial and parallel modes where applicable; if logic is currently mode-specific, check whether extension to the other mode is straightforward (clear abstractions, no hard-wired assumptions), document constraints, and call out expected behavior differences explicitly.
|
||||
- Backend and portability impact: assess likely cross-backend risks in CPU, CUDA, HIP, OCCA, RAJA, partial assembly, fallback paths, compiler compatibility, and platform assumptions.
|
||||
- Build, dependency, and configuration impact: assess CMake or make changes, optional dependency behavior, and feature-flag interactions.
|
||||
- Tests and docs alignment: check available regression or unit coverage evidence for changed behavior, and ensure docs are updated for new flags, APIs, options, or behavior changes.
|
||||
- MFEM developer-guideline fit: keep code lean, simple, general, logically separated, and portable; suggest C++17 improvements when they clearly improve safety, clarity, or maintainability.
|
||||
- New source files, examples, or miniapps: if a PR adds source/header files, verify they are properly wired into the relevant `makefile` and `CMakeLists.txt`, referenced in docs where applicable (including `doc/CodeDocumentation.dox`), and added to top-level `.gitignore` only when generated artifacts require it.
|
||||
- Changelog: verify `CHANGELOG` is updated if the PR introduces significant new features or user-facing changes.
|
||||
- MFEM conventions: use `real_t`; use `mfem::out`/`mfem::err` instead of `std::cout`/`std::cerr` in library code; flag large/binary files; if AI assistance is apparent but undisclosed, suggest following `CONTRIBUTING.md`.
|
||||
- Edge cases: if the PR touches complex or error-prone areas, suggest additional tests for edge cases, failure modes, and parallel behavior.
|
||||
|
||||
## Commenting guidelines
|
||||
- Keep comments concise, actionable, and grounded in the diff.
|
||||
- Focus on correctness, behavior changes, and user impact over style nits.
|
||||
- Be professional, concise, collaborative, technically precise, and avoid unsupported assumptions.
|
||||
|
||||
@@ -13,7 +13,7 @@ Note that some of these scripts use the shared MFEM GitHub Actions from the exte
|
||||
|
||||
<https://github.com/mfem/github-actions>
|
||||
|
||||
For a particular action, e.g. `mfem/github-actions/build-mfem@v2.5`, the `v2.5` suffix denotes the branch (or tag) in the above from which the action is taken.
|
||||
For a particular action, e.g. `mfem/github-actions/build-mfem@v2.5`, the `v2.5` suffix denotes the branch in the above from which the action is taken.
|
||||
|
||||
The current CI workflows are:
|
||||
|
||||
@@ -29,12 +29,16 @@ Runs a number of static repository-level sanity checks.
|
||||
|
||||
- `branch-history` guards against accidental commits of large files using the `--history` option of the `config/githooks/pre-push` script.
|
||||
|
||||
## `mfem-analysis.yml` (`build-analysis`)
|
||||
|
||||
Checks if the code builds and satisfies minimal requirements.
|
||||
|
||||
- `gitignore` builds hypre, METIS, and MFEM using `mfem/github-actions/build-hypre`, `mfem/github-actions/build-metis`, and `mfem/github-actions/build-mfem` and checks for correct `.gitignore` settings by running the `tests/scripts/gitignore` script.
|
||||
|
||||
## `builds-and-tests.yml`
|
||||
|
||||
Runs a matrix of builds and tests runs with different compilers, OS, mfem/hypre settings, etc. Also processes and upload Codecov reports.
|
||||
|
||||
One matrix job runs `tests/scripts/gitignore` after `make test-noclean` to check generated artifacts against `.gitignore`.
|
||||
|
||||
Uses the following GitHub Actions from <https://github.com/mfem/github-actions>:
|
||||
|
||||
- `mfem/github-actions/build-hypre`
|
||||
|
||||
@@ -43,7 +43,7 @@ jobs:
|
||||
remove-docker-images: 'true'
|
||||
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
|
||||
# It's easier to reference named variables than indexes of the matrix
|
||||
- name: Set Environment
|
||||
|
||||
@@ -40,7 +40,6 @@ env:
|
||||
METIS_ARCHIVE_MAC: metis-4.0.3-mac.tgz
|
||||
METIS_TOP_DIR: metis-4.0.3
|
||||
MFEM_TOP_DIR: mfem
|
||||
MFEM_ACTIONS_VERSION: v2.7
|
||||
|
||||
# Note for future improvements:
|
||||
#
|
||||
@@ -111,7 +110,6 @@ jobs:
|
||||
build-system: make
|
||||
hypre-target: int64
|
||||
precision: fp64
|
||||
gitignore-check: YES
|
||||
- os: ubuntu-latest
|
||||
target: opt
|
||||
codecov: NO
|
||||
@@ -142,10 +140,6 @@ jobs:
|
||||
|
||||
continue-on-error: ${{ matrix.enzyme && true || false }}
|
||||
|
||||
# Enable ccache for all jobs except Windows (would need sccache).
|
||||
env:
|
||||
USE_CCACHE: ${{ matrix.os != 'windows-latest' }}
|
||||
|
||||
steps:
|
||||
# Fix 'No space left on device' errors for Ubuntu builds.
|
||||
- name: Run Actions Cleaner
|
||||
@@ -159,7 +153,7 @@ jobs:
|
||||
# /home/runner/work/mfem/mfem/mfem
|
||||
# Note: Done now to access "install-hypre" and "install-metis" actions.
|
||||
- name: checkout mfem
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
path: ${{ env.MFEM_TOP_DIR }}
|
||||
# Fetch the complete history for codecov to access commits ID
|
||||
@@ -176,6 +170,20 @@ jobs:
|
||||
env
|
||||
shell: bash
|
||||
|
||||
# For info on Xcode see:
|
||||
# - https://github.com/actions/runner-images/issues/12541
|
||||
# - https://github.com/actions/runner-images/blob/releases/macos-15-arm64/20250811/images/macos/macos-15-arm64-Readme.md#xcode
|
||||
- name: Xcode version setup (MacOS)
|
||||
if: matrix.os == 'macos-latest'
|
||||
run: |
|
||||
XCODE_PATH="/Applications/Xcode_16.4.app"
|
||||
echo "> sudo xcode-select -s ${XCODE_PATH}"
|
||||
sudo xcode-select -s ${XCODE_PATH}
|
||||
echo "> g++ -v"
|
||||
g++ -v
|
||||
echo "> clang++ -v"
|
||||
clang++ -v
|
||||
|
||||
# Only get MPI if defined for the job.
|
||||
# TODO: It would be nice to have only one step, e.g. with a dedicated
|
||||
# action, but I (@adrienbernede) don't see how at the moment.
|
||||
@@ -217,14 +225,14 @@ jobs:
|
||||
- name: cache hypre
|
||||
id: hypre-cache
|
||||
if: matrix.mpi == 'par'
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ env.HYPRE_TOP_DIR }}
|
||||
key: ${{ runner.os }}-ompi-build-${{ env.HYPRE_TOP_DIR }}-${{ matrix.hypre-target }}-${{ matrix.precision }}-${{ env.MFEM_ACTIONS_VERSION }}
|
||||
key: ${{ runner.os }}-ompi-build-${{ env.HYPRE_TOP_DIR }}-${{ matrix.hypre-target }}-${{ matrix.precision }}-v2.5
|
||||
|
||||
- name: get hypre
|
||||
if: matrix.mpi == 'par' && steps.hypre-cache.outputs.cache-hit != 'true' && matrix.os != 'windows-latest'
|
||||
uses: mfem/github-actions/build-hypre@v2.7
|
||||
uses: mfem/github-actions/build-hypre@v2.5
|
||||
with:
|
||||
archive: ${{ env.HYPRE_ARCHIVE }}
|
||||
dir: ${{ env.HYPRE_TOP_DIR }}
|
||||
@@ -234,7 +242,7 @@ jobs:
|
||||
|
||||
- name: get hypre (Windows)
|
||||
if: matrix.mpi == 'par' && steps.hypre-cache.outputs.cache-hit != 'true' && matrix.os == 'windows-latest'
|
||||
uses: mfem/github-actions/build-hypre@v2.7
|
||||
uses: mfem/github-actions/build-hypre@v2.5
|
||||
with:
|
||||
archive: ${{ env.HYPRE_ARCHIVE }}
|
||||
dir: ${{ env.HYPRE_TOP_DIR }}
|
||||
@@ -247,14 +255,14 @@ jobs:
|
||||
- name: cache metis
|
||||
id: metis-cache
|
||||
if: matrix.mpi == 'par' && matrix.os != 'windows-latest'
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ env.METIS_TOP_DIR }}
|
||||
key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-${{ env.MFEM_ACTIONS_VERSION }}
|
||||
key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.5
|
||||
|
||||
- name: install metis
|
||||
if: matrix.mpi == 'par' && matrix.os != 'windows-latest' && steps.metis-cache.outputs.cache-hit != 'true'
|
||||
uses: mfem/github-actions/build-metis@v2.7
|
||||
uses: mfem/github-actions/build-metis@v2.5
|
||||
with:
|
||||
archive: ${{ matrix.os != 'macos-latest' && env.METIS_ARCHIVE || env.METIS_ARCHIVE_MAC }}
|
||||
dir: ${{ env.METIS_TOP_DIR }}
|
||||
@@ -262,7 +270,7 @@ jobs:
|
||||
- name: cache vcpkg (Windows)
|
||||
id: vcpkg-cache
|
||||
if: matrix.os == 'windows-latest'
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: vcpkg_cache
|
||||
key: ${{ runner.os }}-${{ matrix.mpi }}-vcpkg-v1
|
||||
@@ -287,62 +295,15 @@ jobs:
|
||||
export HOMEBREW_NO_INSTALL_CLEANUP=1
|
||||
brew update
|
||||
brew install enzyme
|
||||
ENZYME_LLVM=$(brew info enzyme | sed -n 's/^Required.*:.*\(llvm[^ ]*\).*/\1/p')
|
||||
echo "ENZYME_LLVM=$ENZYME_LLVM"
|
||||
ENZYME_LLVM=$(brew info enzyme | sed -n 's/^Required:.*\(llvm[^ ]*\).*/\1/p')
|
||||
LLVM_PREFIX=$(brew --prefix $ENZYME_LLVM)
|
||||
echo "LLVM_PREFIX=$LLVM_PREFIX" >> $GITHUB_ENV
|
||||
echo "OMPI_CC=$LLVM_PREFIX/bin/clang" >> $GITHUB_ENV
|
||||
echo "OMPI_CXX=$LLVM_PREFIX/bin/clang++" >> $GITHUB_ENV
|
||||
|
||||
# Restore the compiler cache (ccache). The key embeds the run id, so new
|
||||
# runs save a fresh snapshot; the restore-keys prefix warm-starts from the
|
||||
# most recent prior run (incl. the base branch for PRs).
|
||||
- name: cache ccache
|
||||
if: ${{ env.USE_CCACHE == 'true' }}
|
||||
uses: actions/cache@v5
|
||||
with:
|
||||
path: .ccache
|
||||
key: ccache-${{ matrix.os }}-${{ matrix.build-system }}-${{ matrix.target }}-${{ matrix.mpi }}-${{ matrix.hypre-target }}-${{ matrix.precision }}${{ matrix.enzyme && '-enzyme' || '' }}-${{ github.run_id }}
|
||||
restore-keys: |
|
||||
ccache-${{ matrix.os }}-${{ matrix.build-system }}-${{ matrix.target }}-${{ matrix.mpi }}-${{ matrix.hypre-target }}-${{ matrix.precision }}${{ matrix.enzyme && '-enzyme' || '' }}-
|
||||
|
||||
# Configure ccache and select how it is injected into the MFEM build:
|
||||
# - make: set CXX="ccache g++"; for MPI, OMPI_CXX="ccache g++" so mpicxx
|
||||
# runs ccache around g++ (not ccache around the mpicxx wrapper).
|
||||
# - cmake: set CMAKE_<LANG>_COMPILER_LAUNCHER=ccache.
|
||||
# - enzyme: wrap the brew clang++ via OMPI_CXX.
|
||||
# The chosen options are passed through build-mfem's 'config-options'
|
||||
# input (see the build step below).
|
||||
- name: configure ccache
|
||||
if: ${{ env.USE_CCACHE == 'true' }}
|
||||
run: |
|
||||
command -v ccache >/dev/null 2>&1 || {
|
||||
if [[ "${{ runner.os }}" == "Linux" ]]; then
|
||||
sudo apt-get update && sudo apt-get install -y ccache
|
||||
else
|
||||
brew install ccache
|
||||
fi
|
||||
}
|
||||
echo "CCACHE_DIR=${{ github.workspace }}/.ccache" >> $GITHUB_ENV
|
||||
echo "CCACHE_MAXSIZE=1G" >> $GITHUB_ENV
|
||||
echo "CCACHE_COMPILERCHECK=content" >> $GITHUB_ENV
|
||||
# Ignore header timestamps (restamped by each checkout) so direct mode hits.
|
||||
echo "CCACHE_SLOPPINESS=include_file_mtime,include_file_ctime,time_macros" >> $GITHUB_ENV
|
||||
# Hash absolute paths relative to the workspace.
|
||||
echo "CCACHE_BASEDIR=${{ github.workspace }}" >> $GITHUB_ENV
|
||||
if [[ "${{ matrix.enzyme }}" == "true" ]]; then
|
||||
echo "OMPI_CXX=ccache $LLVM_PREFIX/bin/clang++" >> $GITHUB_ENV
|
||||
elif [[ "${{ matrix.build-system }}" == "cmake" ]]; then
|
||||
echo 'CCACHE_CONFIG_OPTS=-DCMAKE_CXX_COMPILER_LAUNCHER=ccache -DCMAKE_C_COMPILER_LAUNCHER=ccache' >> $GITHUB_ENV
|
||||
else
|
||||
echo "OMPI_CXX=ccache g++" >> $GITHUB_ENV
|
||||
echo 'CCACHE_CONFIG_OPTS=CXX="ccache g++" MPICXX="mpicxx"' >> $GITHUB_ENV
|
||||
fi
|
||||
shell: bash
|
||||
|
||||
# MFEM build and test
|
||||
- name: build
|
||||
uses: mfem/github-actions/build-mfem@v2.7
|
||||
uses: mfem/github-actions/build-mfem@v2.5
|
||||
env:
|
||||
VCPKG_DEFAULT_BINARY_CACHE: ${{ github.workspace }}/vcpkg_cache
|
||||
with:
|
||||
@@ -355,14 +316,9 @@ jobs:
|
||||
metis-dir: ${{ env.METIS_TOP_DIR }}
|
||||
mfem-dir: ${{ env.MFEM_TOP_DIR }}
|
||||
precision: ${{ matrix.precision }}
|
||||
config-options: ${{ matrix.config-opts }} ${{ env.CCACHE_CONFIG_OPTS }}
|
||||
config-options: ${{ matrix.config-opts }}
|
||||
library-only: ${{ matrix.target == 'dbg' && matrix.os != 'ubuntu-latest' }}
|
||||
|
||||
- name: ccache stats
|
||||
if: ${{ env.USE_CCACHE == 'true' }}
|
||||
run: ccache -s
|
||||
shell: bash
|
||||
|
||||
# Run checks (and only checks) on debug targets
|
||||
- name: checks
|
||||
if: matrix.build-system == 'make' && matrix.target == 'dbg'
|
||||
@@ -373,13 +329,7 @@ jobs:
|
||||
- name: tests
|
||||
if: matrix.build-system == 'make' && (matrix.target == 'opt' || matrix.os == 'ubuntu-latest')
|
||||
run: |
|
||||
cd ${{ env.MFEM_TOP_DIR }}
|
||||
if [[ "${{ matrix.gitignore-check }}" == "YES" ]]; then
|
||||
make test-noclean
|
||||
else
|
||||
make test
|
||||
fi
|
||||
shell: bash
|
||||
cd ${{ env.MFEM_TOP_DIR }} && make test
|
||||
|
||||
- name: cmake checks
|
||||
if: matrix.build-system == 'cmake' && matrix.target == 'dbg'
|
||||
@@ -424,16 +374,8 @@ jobs:
|
||||
# Code coverage (process and upload reports)
|
||||
- name: codecov
|
||||
if: matrix.codecov == 'YES'
|
||||
uses: mfem/github-actions/upload-coverage@v2.7
|
||||
uses: mfem/github-actions/upload-coverage@v2.5
|
||||
with:
|
||||
name: ${{ matrix.os }}-${{ matrix.build-system }}-${{ matrix.target }}-${{ matrix.mpi }}-${{ matrix.hypre-target }}-${{ matrix.precision }}
|
||||
name: ${{ matrix.os }}-${{ matrix.build-system }}-${{ matrix.target }}-${{ matrix.mpi }}-${{ matrix.hypre-target }}
|
||||
project_dir: ${{ env.MFEM_TOP_DIR }}
|
||||
directories: "fem general linalg mesh"
|
||||
env:
|
||||
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
|
||||
|
||||
- name: gitignore
|
||||
if: matrix.gitignore-check == 'YES'
|
||||
run: |
|
||||
cd ${{ env.MFEM_TOP_DIR }}/tests/scripts
|
||||
./runtest gitignore
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
# Copyright (c) 2010-2025, Lawrence Livermore National Security, LLC. Produced
|
||||
# at the Lawrence Livermore National Laboratory. All Rights reserved. See files
|
||||
# LICENSE and NOTICE for details. LLNL-CODE-806117.
|
||||
#
|
||||
# This file is part of the MFEM library. For more information and source code
|
||||
# availability visit https://mfem.org.
|
||||
#
|
||||
# MFEM is free software; you can redistribute it and/or modify it under the
|
||||
# terms of the BSD-3 license. We welcome feedback and contributions, see file
|
||||
# CONTRIBUTING.md for details.
|
||||
---
|
||||
# A closed PR's caches can never be restored again, so delete them to free
|
||||
# space against the 10 GB per-repo cache limit.
|
||||
name: Cleanup PR caches
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [closed]
|
||||
|
||||
permissions:
|
||||
actions: write
|
||||
|
||||
jobs:
|
||||
cleanup:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Delete caches for the closed PR
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
GH_REPO: ${{ github.repository }}
|
||||
PR_REF: refs/pull/${{ github.event.pull_request.number }}/merge
|
||||
run: |
|
||||
echo "Deleting caches for $PR_REF"
|
||||
while :; do
|
||||
ids=$(gh cache list --ref "$PR_REF" --limit 100 --json id --jq '.[].id')
|
||||
[ -n "$ids" ] || break
|
||||
echo "$ids" | while read -r id; do
|
||||
[ -n "$id" ] || continue
|
||||
echo "Deleting cache $id"
|
||||
gh cache delete "$id" || echo " (already gone)"
|
||||
done
|
||||
done
|
||||
@@ -14,19 +14,9 @@ name: "Static Analysis"
|
||||
on:
|
||||
push:
|
||||
branches: ["master", "next"]
|
||||
paths-ignore: &docs-only-paths
|
||||
- "**/*.md"
|
||||
- "doc/**"
|
||||
- ".binder/**"
|
||||
- "CITATION.cff"
|
||||
- "LICENSE"
|
||||
- "NOTICE"
|
||||
- "CHANGELOG"
|
||||
- "INSTALL"
|
||||
pull_request:
|
||||
# The branches below must be a subset of the branches above
|
||||
branches: ["master"]
|
||||
paths-ignore: *docs-only-paths
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
@@ -50,11 +40,11 @@ jobs:
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
|
||||
# Initializes the CodeQL tools for scanning.
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@v4
|
||||
uses: github/codeql-action/init@v2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# If you wish to specify custom queries, you can do so here or in a config file.
|
||||
@@ -67,7 +57,7 @@ jobs:
|
||||
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
|
||||
# If this step fails, then you should remove it and run the build manually (see below)
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@v4
|
||||
uses: github/codeql-action/autobuild@v2
|
||||
|
||||
# ℹ️ Command-line programs to run using the OS shell.
|
||||
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
|
||||
@@ -80,4 +70,4 @@ jobs:
|
||||
# ./location_of_script_within_repo/buildscript.sh
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@v4
|
||||
uses: github/codeql-action/analyze@v2
|
||||
|
||||
@@ -0,0 +1,100 @@
|
||||
# Copyright (c) 2010-2025, Lawrence Livermore National Security, LLC. Produced
|
||||
# at the Lawrence Livermore National Laboratory. All Rights reserved. See files
|
||||
# LICENSE and NOTICE for details. LLNL-CODE-806117.
|
||||
#
|
||||
# This file is part of the MFEM library. For more information and source code
|
||||
# availability visit https://mfem.org.
|
||||
#
|
||||
# MFEM is free software; you can redistribute it and/or modify it under the
|
||||
# terms of the BSD-3 license. We welcome feedback and contributions, see file
|
||||
# CONTRIBUTING.md for details.
|
||||
|
||||
name: "Build Analysis"
|
||||
|
||||
permissions:
|
||||
actions: write
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
- next
|
||||
pull_request:
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
env:
|
||||
HYPRE_ARCHIVE: v2.19.0.tar.gz
|
||||
HYPRE_TOP_DIR: hypre-2.19.0
|
||||
METIS_ARCHIVE: metis-4.0.3.tar.gz
|
||||
METIS_TOP_DIR: metis-4.0.3
|
||||
COVERAGE_ENV: mfem-coverage
|
||||
|
||||
jobs:
|
||||
gitignore:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: checkout MFEM
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
path: mfem
|
||||
|
||||
- name: Get MPI (Linux)
|
||||
run: |
|
||||
sudo apt-get install openmpi-bin libopenmpi-dev
|
||||
export OMPI_MCA_rmaps_base_oversubscribe=1
|
||||
|
||||
- name: Cache Hypre Install
|
||||
id: hypre-cache
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ env.HYPRE_TOP_DIR }}
|
||||
key: ${{ runner.os }}-ompi-build-${{ env.HYPRE_TOP_DIR }}-v2.5
|
||||
|
||||
- name: Get Hypre
|
||||
if: steps.hypre-cache.outputs.cache-hit != 'true'
|
||||
uses: mfem/github-actions/build-hypre@v2.5
|
||||
with:
|
||||
archive: ${{ env.HYPRE_ARCHIVE }}
|
||||
dir: ${{ env.HYPRE_TOP_DIR }}
|
||||
target: int32
|
||||
|
||||
- name: Cache Metis Install
|
||||
id: metis-cache
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{ env.METIS_TOP_DIR }}
|
||||
key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.5
|
||||
|
||||
- name: Install Metis
|
||||
if: steps.metis-cache.outputs.cache-hit != 'true'
|
||||
uses: mfem/github-actions/build-metis@v2.5
|
||||
with:
|
||||
archive: ${{ env.METIS_ARCHIVE }}
|
||||
dir: ${{ env.METIS_TOP_DIR }}
|
||||
|
||||
# MFEM build and test
|
||||
- name: build-mfem
|
||||
uses: mfem/github-actions/build-mfem@v2.5
|
||||
with:
|
||||
os: ${{ runner.os }}
|
||||
target: opt
|
||||
codecov: NO
|
||||
mpi: par
|
||||
build-system: make
|
||||
hypre-dir: ${{ env.HYPRE_TOP_DIR }}
|
||||
metis-dir: ${{ env.METIS_TOP_DIR }}
|
||||
mfem-dir: mfem
|
||||
|
||||
- name: test (no clean)
|
||||
run: |
|
||||
cd mfem && make test-noclean
|
||||
|
||||
- name: gitignore
|
||||
run: |
|
||||
cd mfem/tests/scripts
|
||||
./runtest gitignore
|
||||
@@ -13,7 +13,6 @@ name: "Checks"
|
||||
|
||||
permissions:
|
||||
actions: write
|
||||
pull-requests: read
|
||||
|
||||
on:
|
||||
push:
|
||||
@@ -30,11 +29,6 @@ concurrency:
|
||||
# by checking if the workflow trigger is 'push' ("github.event_name == 'push'")
|
||||
# and if we are in a fork ("github.event.pull_request.head.repo.full_name !=
|
||||
# github.repository").
|
||||
#
|
||||
# The logic for the branch-history check is slightly different, since that check
|
||||
# also inspects the PR's labels to allow for overriding failures. In this case,
|
||||
# we run on all 'pull_request' triggers, but only run for 'push' triggers that
|
||||
# do not correspond to any open PRs.
|
||||
|
||||
jobs:
|
||||
file-headers-check:
|
||||
@@ -44,7 +38,7 @@ jobs:
|
||||
github.event.pull_request.head.repo.full_name != github.repository)
|
||||
steps:
|
||||
- name: checkout mfem
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: copyright check
|
||||
id: copyright
|
||||
@@ -99,7 +93,7 @@ jobs:
|
||||
github.event.pull_request.head.repo.full_name != github.repository)
|
||||
steps:
|
||||
- name: checkout mfem
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: get astyle
|
||||
run: |
|
||||
@@ -116,7 +110,7 @@ jobs:
|
||||
github.event.pull_request.head.repo.full_name != github.repository)
|
||||
steps:
|
||||
- name: checkout mfem
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: get doxygen and graphviz
|
||||
run: |
|
||||
@@ -134,35 +128,18 @@ jobs:
|
||||
|
||||
branch-history:
|
||||
if: |
|
||||
github.ref != 'refs/heads/next' && github.ref != 'refs/heads/master'
|
||||
github.ref != 'refs/heads/next' &&
|
||||
github.ref != 'refs/heads/master' &&
|
||||
(github.event_name == 'push' ||
|
||||
github.event.pull_request.head.repo.full_name != github.repository)
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: checkout mfem
|
||||
uses: actions/checkout@v6
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: check for pull request
|
||||
id: check_pr
|
||||
if: github.event_name == 'push'
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
run: |
|
||||
pr_exists=$(gh pr list --repo "$GITHUB_REPOSITORY" \
|
||||
--head "$GITHUB_REF_NAME" \
|
||||
--state open \
|
||||
--json number \
|
||||
--jq 'length > 0')
|
||||
echo "pr_exists=$pr_exists" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: branch-history
|
||||
id: branch_history
|
||||
if: |
|
||||
(github.event_name == 'pull_request' ||
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
steps.check_pr.outputs.pr_exists == 'false')
|
||||
continue-on-error: ${{ contains(github.event.pull_request.labels.*.name,
|
||||
'branch-history-override') }}
|
||||
run: |
|
||||
# We override origin to make sure we point to the main repo.
|
||||
# This is to have consistent test results on PRs from forks.
|
||||
@@ -170,9 +147,3 @@ jobs:
|
||||
git remote add origin https://github.com/mfem/mfem.git
|
||||
git checkout -b gh-actions-branch-history
|
||||
./config/githooks/pre-push --history
|
||||
|
||||
- name: report branch-history override
|
||||
if: steps.branch_history.outcome == 'failure'
|
||||
run: |
|
||||
echo "::warning::branch-history check failed, but the" \
|
||||
"'branch-history-override' label is set."
|
||||
|
||||
@@ -17,24 +17,20 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
name: 2.19.0
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
with:
|
||||
NO_FLAGS: true
|
||||
- name: Cache
|
||||
id: cache
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{env.HYPRE_DIR}}
|
||||
key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-${{ env.MFEM_ACTIONS_VERSION }}
|
||||
key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-v2.5
|
||||
- name: Setup
|
||||
if: steps.cache.outputs.cache-hit != 'true'
|
||||
uses: ./.github/actions/sanitize/mpi
|
||||
with:
|
||||
NO_FLAGS: true
|
||||
- name: Build
|
||||
if: steps.cache.outputs.cache-hit != 'true'
|
||||
uses: mfem/github-actions/build-hypre@v2.7
|
||||
uses: mfem/github-actions/build-hypre@v2.5
|
||||
with:
|
||||
archive: ${{env.HYPRE_TGZ}}
|
||||
dir: ${{env.HYPRE_DIR}}
|
||||
|
||||
@@ -27,13 +27,13 @@ jobs:
|
||||
llvm_use_sanitizer: "Undefined"
|
||||
name: ${{matrix.sanitizer}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
with:
|
||||
NO_FLAGS: true
|
||||
- name: Cache
|
||||
id: cache
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{env.LLVM_DIR}}
|
||||
key: build-libcxx-${{env.LLVM_VER}}-${{matrix.sanitizer}}
|
||||
|
||||
@@ -17,11 +17,11 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
name: lsan.supp
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
- name: Cache
|
||||
id: cache
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{env.LSAN_DIR}}
|
||||
key: build-lsan-suppression-file
|
||||
|
||||
@@ -17,24 +17,20 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
name: 4.0.3
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/config
|
||||
with:
|
||||
NO_FLAGS: true
|
||||
- name: Cache
|
||||
id: cache
|
||||
uses: actions/cache@v5
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ${{env.METIS_DIR}}
|
||||
key: ${{runner.os}}-build-${{env.METIS_DIR}}-${{env.MFEM_ACTIONS_VERSION}}
|
||||
key: ${{runner.os}}-build-${{env.METIS_DIR}}-v2.5
|
||||
- name: Setup
|
||||
if: steps.cache.outputs.cache-hit != 'true'
|
||||
uses: ./.github/actions/sanitize/mpi
|
||||
with:
|
||||
NO_FLAGS: true
|
||||
- name: Build
|
||||
if: steps.cache.outputs.cache-hit != 'true'
|
||||
uses: mfem/github-actions/build-metis@v2.7
|
||||
uses: mfem/github-actions/build-metis@v2.5
|
||||
with:
|
||||
archive: ${{env.METIS_TGZ}}
|
||||
dir: ${{env.METIS_DIR}}
|
||||
|
||||
@@ -28,7 +28,7 @@ jobs:
|
||||
build:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/mfem
|
||||
with:
|
||||
par: ${{inputs.par}}
|
||||
@@ -40,7 +40,7 @@ jobs:
|
||||
env:
|
||||
ex: ${{inputs.par && 'ex1p' || 'ex1'}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
@@ -58,7 +58,7 @@ jobs:
|
||||
env:
|
||||
exclude: ${{inputs.par && '-E "_ser"' || ''}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
@@ -82,7 +82,7 @@ jobs:
|
||||
env:
|
||||
exclude: ${{inputs.par && '-E "_ser"' || ''}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
@@ -107,7 +107,7 @@ jobs:
|
||||
run: ${{inputs.par && '-R "_cpu_np"' || ''}}
|
||||
exclude: ${{inputs.par && '"unit_tests|debug"' || '"^unit_tests$|debug"'}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
@@ -131,7 +131,7 @@ jobs:
|
||||
env:
|
||||
unit_tests: ${{inputs.par && 'punit_tests' || 'unit_tests'}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
@@ -146,7 +146,7 @@ jobs:
|
||||
if: ${{steps.restore.outputs.cache-hit != 'true'}}
|
||||
working-directory: mfem/build/tests/unit
|
||||
run: find . -type f -name '*.o' -delete
|
||||
- uses: actions/upload-artifact@v7
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: tests-${{inputs.par}}-${{inputs.sanitizer}}
|
||||
path: mfem/build/tests/unit/${{env.unit_tests}}
|
||||
@@ -165,14 +165,14 @@ jobs:
|
||||
unit_tests: ${{inputs.par && 'punit_tests' || 'unit_tests'}}
|
||||
np: ${{inputs.par && '_np=2' || ''}}
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
- uses: actions/checkout@v4
|
||||
- uses: ./.github/actions/sanitize/restore
|
||||
id: restore
|
||||
with:
|
||||
par: ${{inputs.par}}
|
||||
sanitizer: ${{inputs.sanitizer}}
|
||||
cache-path: mfem/build/tests/unit/${{env.unit_tests}}
|
||||
- uses: actions/download-artifact@v8
|
||||
- uses: actions/download-artifact@v4
|
||||
if: ${{steps.restore.outputs.cache-hit != 'true'}}
|
||||
with:
|
||||
name: tests-${{inputs.par}}-${{inputs.sanitizer}}
|
||||
|
||||
@@ -17,17 +17,7 @@ permissions:
|
||||
on:
|
||||
push:
|
||||
branches: ["master", "next"]
|
||||
paths-ignore: &docs-only-paths
|
||||
- "**/*.md"
|
||||
- "doc/**"
|
||||
- ".binder/**"
|
||||
- "CITATION.cff"
|
||||
- "LICENSE"
|
||||
- "NOTICE"
|
||||
- "CHANGELOG"
|
||||
- "INSTALL"
|
||||
pull_request:
|
||||
paths-ignore: *docs-only-paths
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
|
||||
@@ -260,7 +260,6 @@ miniapps/meshing/polar-nc
|
||||
miniapps/meshing/mesh-quality
|
||||
miniapps/meshing/hpref
|
||||
miniapps/meshing/phpref
|
||||
miniapps/meshing/pref321
|
||||
miniapps/meshing/mobius-strip.mesh
|
||||
miniapps/meshing/klein-bottle.mesh
|
||||
miniapps/meshing/toroid-*.mesh
|
||||
@@ -444,10 +443,6 @@ miniapps/diag-smoothers/mg-abs-l1-jacobi
|
||||
miniapps/contact/contact
|
||||
miniapps/contact/ParaView
|
||||
|
||||
miniapps/plasma/pic/electrostatic-*
|
||||
!miniapps/plasma/pic/electrostatic-*.cpp
|
||||
miniapps/plasma/pic/*.csv
|
||||
|
||||
# Unit test binary and outputs
|
||||
tests/unit/output_meshes
|
||||
tests/unit/unit_tests
|
||||
|
||||
@@ -102,14 +102,12 @@ report_baseline:
|
||||
mkdir -p ${MACHINE_NAME}
|
||||
rundir="${MACHINE_NAME}/$(date +%Y-%m-%d)-gitlab-${BASELINE_TEST}-${CI_COMMIT_REF_SLUG}"
|
||||
rundir=$(${CI_PROJECT_DIR}/.gitlab/scripts/safe_create_rundir ${rundir})
|
||||
status=0
|
||||
cp ${CI_PROJECT_DIR}/${ARTIFACTS_DIR}/* ${rundir} || { status=1; }
|
||||
cp ${CI_PROJECT_DIR}/${ARTIFACTS_DIR}/* ${rundir}
|
||||
printf "%s\n" "" "Pipeline URL:" "$CI_PIPELINE_URL" \
|
||||
>> ${rundir}/pipeline.txt
|
||||
# We create an autotest-email.html file, because that's how we signal
|
||||
# that there was an error / diff (temporary).
|
||||
if [[ $status -ne 0 ]] || \
|
||||
[[ -f ${rundir}/${BASELINE_TEST}.err ]] || \
|
||||
if [[ -f ${rundir}/${BASELINE_TEST}.err ]] || \
|
||||
[[ -f ${rundir}/${BASELINE_TEST}-${MACHINE_NAME}.diff ]]; then
|
||||
cp ${rundir}/pipeline.txt ${rundir}/autotest-email.html
|
||||
fi
|
||||
|
||||
@@ -85,8 +85,3 @@ opt_par_gcc_10_pumi:
|
||||
extends: .mfem_job_on_dane
|
||||
variables:
|
||||
SPEC: "%gcc@10.3.1 +pumi"
|
||||
|
||||
opt_par_gcc_10_gslib:
|
||||
extends: .mfem_job_on_dane
|
||||
variables:
|
||||
SPEC: "%gcc@10.3.1 +gslib"
|
||||
|
||||
@@ -63,8 +63,3 @@ opt_mpi_cuda_hypre_cuda_gcc:
|
||||
extends: .mfem_job_on_matrix
|
||||
variables:
|
||||
SPEC: "%gcc@10.3.1 +mpi +cuda cuda_arch=90 ^hypre+cuda"
|
||||
|
||||
opt_mpi_cuda_gcc_gslib:
|
||||
extends: .mfem_job_on_matrix
|
||||
variables:
|
||||
SPEC: "%gcc@10.3.1 +mpi +cuda +gslib cuda_arch=90 ^hypre+cuda"
|
||||
|
||||
@@ -32,9 +32,9 @@ mkdir _${BASELINE_TEST} && cd _${BASELINE_TEST}
|
||||
|
||||
# run
|
||||
if [[ "${MACHINE_NAME}" == "dane" ]]; then
|
||||
srun --nodes=1 -t 60 --exclusive --reservation=ci ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
|
||||
salloc --nodes=1 -t 60 --exclusive --reservation=ci ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
|
||||
elif [[ ${MACHINE_NAME} == "corona" ]]; then
|
||||
srun --nodes=1 -t 60 -p pbatch ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
|
||||
salloc --nodes=1 -t 60 -p pbatch ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
|
||||
else
|
||||
echo "Unknown machine: MACHINE_NAME=$MACHINE_NAME"
|
||||
exit 1
|
||||
|
||||
@@ -11,160 +11,24 @@
|
||||
Version 4.9.1 (development)
|
||||
===========================
|
||||
|
||||
- Added policy for AI-assisted contribution to CONTRIBUTING.md.
|
||||
|
||||
Discretization improvements
|
||||
---------------------------
|
||||
- Improved FindPointsGSLIB surface mesh capability with support for simplices
|
||||
and an option to specify axis-aligned bounding box padding for near-surface
|
||||
point queries.
|
||||
|
||||
- Added GPU-enabled partial assembly for simplicial Bernstein H1 basis based on
|
||||
ragged tensor algorithms (see DOI: 10.1137/11082539X) for mass and diffusion
|
||||
integrators.
|
||||
|
||||
- Replaced legacy simplex quadrature rules with symmetric positive weight rules
|
||||
for triangles (orders 0-25) and tetrahedra (orders 0-20). These rules
|
||||
guarantee all-positive weights and interior quadrature points, improving
|
||||
numerical stability. Higher orders fall back to Grundmann-Moller.
|
||||
* Triangle rules: Witherden and Vincent, DOI: 10.1016/j.camwa.2015.03.017
|
||||
* Tet rules (d=1-13): Witherden and Vincent (same as above)
|
||||
* Tet rules (d=14-20): Chuluunbaatar et al., DOI: 10.1016/j.camwa.2022.08.016
|
||||
|
||||
- Added support for general 1D Gauss-Jacobi quadrature rules and Stroud conical
|
||||
quadrature rules on triangles and tetrahedra.
|
||||
|
||||
- Improved the GridFunction projection routines. Projections work for Scalar,
|
||||
- Improved the gridfunction projection routines. Projections work for Scalar,
|
||||
Vector and VectorFE, also NURBS versions. Optionally different types of
|
||||
projections can be selected, default behavior has not changed.
|
||||
projections can be selected, default behaviour has not changed.
|
||||
|
||||
- Added GridFunction projection methods for trace spaces, i.e., project
|
||||
coefficients on the mesh skeleton.
|
||||
|
||||
- Added methods to estimate function extremum using piecewise linear bounds plus
|
||||
- Added methods to estimate function extremum using piecewise linear bounds +
|
||||
recursive subdivision.
|
||||
|
||||
- Extend FindPointsGSLIB to support surface meshes.
|
||||
|
||||
- Added support for complex-valued mixed bilinear forms via the new classes
|
||||
MixedSesquilinearForm and ParMixedSesquilinearForm, mirroring the existing
|
||||
SesquilinearForm classes. Rectangular complex operators are now also
|
||||
handled correctly by ComplexSparseMatrix::GetSystemMatrix and
|
||||
ComplexHypreParMatrix::GetSystemMatrix, which previously assumed equal
|
||||
trial and test spaces.
|
||||
|
||||
- Added FiniteElementSpace::GetBoundaryLoopEdgeDofs to extract the edge DOFs on
|
||||
the perimeter loop of a set of boundary elements, with a ParFiniteElementSpace
|
||||
overload that reconciles the selection across processor boundaries so the
|
||||
result is partition invariant. This is useful for imposing boundary conditions
|
||||
on boundary edge DOFs.
|
||||
|
||||
- Added a MaxAbs reduction to GroupCommunicator that selects the signed value of
|
||||
largest magnitude across a group, keeping its sign. Equal-magnitude ties
|
||||
resolve deterministically to the positive value.
|
||||
|
||||
Meshing improvements
|
||||
--------------------
|
||||
- Added support for nonuniform anisotropic mesh refinement on parallel quad/hex
|
||||
meshes with arbitrary spacing in each direction. This enables in particular
|
||||
3:1 refinement in parallel, as demonstrated in the new meshing miniapp pref321.
|
||||
|
||||
- Added option to guarantee mesh validity during TMOP-based r-adaptivity, using
|
||||
bounds on the determinant of the mesh transformation Jacobian.
|
||||
|
||||
- Added PA support for TMOP's adaptive limiting functionality. Multiple
|
||||
GridFunctions and Coefficients can be combined to form a composite term.
|
||||
|
||||
- Improved support for 1D NURBS meshes with variable order, including using
|
||||
the patches construct for 1D NURBS meshes.
|
||||
|
||||
- Added the option to include material interfaces (faces separating elements
|
||||
with different element attributes) as additional boundary elements, for
|
||||
parallel visualization, e.g. with GLVis. This is supported by both the Print
|
||||
and PrintAsOne methods of ParMesh. See ParMesh::SetPrintInterfaces().
|
||||
|
||||
Linear and nonlinear solvers
|
||||
----------------------------
|
||||
- Added support for trace spaces in PRefinementTransferOperator. This is used in
|
||||
PRefinement multigrid methods for problems posed on trace spaces (see e.g. the
|
||||
DPG miniapps).
|
||||
|
||||
- Added new class MultiVector: an array of Vectors of different sizes where each
|
||||
Vector can be allocated independently. Also, added associated methods in class
|
||||
Operator: MultMV, MultTransposeMV, and GetGradientMV, that use MultiVector
|
||||
objects for input and/or output parameters. [PR #5249]
|
||||
|
||||
GPU computing
|
||||
-------------
|
||||
- Improved partial assembly for VectorDivergenceIntegrator with shared-memory
|
||||
kernels, kernel registration, and transpose support.
|
||||
|
||||
- Improved partial-assembly diagonal kernels for VectorMassIntegrator (shared-
|
||||
memory specializations) and ElasticityIntegrator (no scratch Q-vector).
|
||||
|
||||
- Added PA gradient and diagonal support for VectorConvectionNLFIntegrator
|
||||
(AssembleGradPA, AddMultGradPA, AssembleGradDiagonalPA).
|
||||
|
||||
- Added device assembly support for 3D H(curl) VectorFEDomainLFIntegrator.
|
||||
|
||||
- Added partial assembly support for MixedScalarWeakGradientIntegrator.
|
||||
|
||||
- Added partial assembly support for MixedDotProductIntegrator.
|
||||
|
||||
- Added partial assembly support for MixedScalarCrossProductIntegrator.
|
||||
|
||||
- Added partial assembly support for MixedScalarWeakCrossProductIntegrator.
|
||||
|
||||
- Added partial assembly support for MixedVectorGradientIntegrator for H1->RT.
|
||||
|
||||
- Added support for device partial assembly CurlInterpolator.
|
||||
This supports 2D and 3D variants:
|
||||
2D H1 (out-of-plane) to RT (in-plane)
|
||||
2D ND (in-plane) to Integral L2 (out-of-plane)
|
||||
3D ND to RT
|
||||
|
||||
- Added NVIDIA cuDSS library interface. Implementation examples have been
|
||||
added to ex1 and ex1p. See https://developer.nvidia.com/cudss for more
|
||||
details. Supported versions >= 0.6.0.
|
||||
|
||||
- Allow specifying GPU kernel launch bounds for native and RAJA GPU backends.
|
||||
|
||||
- Changed VectorFEMassIntegrator to use kernel specialization dispatch for
|
||||
partial assembly.
|
||||
|
||||
- Added support for FiniteElement::MapType::INTEGRAL spaces to
|
||||
QuadratureInterpolator.
|
||||
|
||||
- Added support for FiniteElement::MapType::INTEGRAL spaces to
|
||||
MixedScalarCurlIntegrator.
|
||||
|
||||
New and updated examples and miniapps
|
||||
-------------------------------------
|
||||
- The Lorentz miniapp (in miniapps/electromagnetics) has been updated to
|
||||
leverage the ParticleSet capability.
|
||||
|
||||
- Added (Complex)PRefinementMultigrid solver option in the DPG miniapps.
|
||||
|
||||
Miscellaneous
|
||||
-------------
|
||||
- Fixed signed DOF handling in ParGridFunction reading (read constructor) and
|
||||
saving via SaveAsOne(). Simplified the process of applying the DOF signs by
|
||||
using the new method ApplyDofSigns() in class ParFiniteElementSpace: the
|
||||
method will return immediately if no sign flips are needed.
|
||||
|
||||
- Added support for coefficient-weighted LOR transfer in
|
||||
L2ProjectionGridTransfer. The transfer conserves the weighted mass, for
|
||||
example when transferring velocity while conserving density-weighted momentum.
|
||||
This is illustrated in the lor-transfer and plor-transfer miniapps.
|
||||
|
||||
- Added support for saving DataCollection output on the node-local storage,
|
||||
instead of requiring that the filesystem is shared among all the ranks.
|
||||
|
||||
API changes
|
||||
-----------
|
||||
- Removed ProjectGrad from 2D RT elements. Users should use ProjectCurl instead.
|
||||
This also fixes a bug where ProjectCurl was returning the negative curl,
|
||||
identical to ProjectGrad.
|
||||
- Electromagnetics/lorentz miniapp has been updated to leverage the ParticleSet
|
||||
capability.
|
||||
|
||||
|
||||
Version 4.9, released on Dec 11, 2025
|
||||
|
||||
+14
-25
@@ -88,9 +88,18 @@ if (MFEM_USE_STRUMPACK OR MFEM_USE_MUMPS)
|
||||
# Just needed to find the MPI_Fortran libraries to link with
|
||||
set(XSDK_ENABLE_Fortran ON)
|
||||
endif()
|
||||
# RAJA requires C++20:
|
||||
if ((MFEM_USE_UMPIRE OR MFEM_USE_RAJA) AND ("${CMAKE_CXX_STANDARD}" LESS "20"))
|
||||
set(CMAKE_CXX_STANDARD 20 CACHE STRING "C++ standard to use." FORCE)
|
||||
# Ginkgo requires C++17:
|
||||
if ((MFEM_USE_GINKGO) AND ("${CMAKE_CXX_STANDARD}" LESS "17"))
|
||||
set(CMAKE_CXX_STANDARD 17 CACHE STRING "C++ standard to use." FORCE)
|
||||
# Google Benchmark, SUNDIALS, STRUMPACK, Tribol, RAJA and Umpire require C++14:
|
||||
elseif ((MFEM_USE_BENCHMARK OR
|
||||
MFEM_USE_SUNDIALS OR
|
||||
MFEM_USE_STRUMPACK OR
|
||||
MFEM_USE_TRIBOL OR
|
||||
MFEM_USE_RAJA OR
|
||||
MFEM_USE_UMPIRE) AND
|
||||
("${CMAKE_CXX_STANDARD}" LESS "14"))
|
||||
set(CMAKE_CXX_STANDARD 14 CACHE STRING "C++ standard to use." FORCE)
|
||||
endif()
|
||||
|
||||
# Include xSDK default CMake file.
|
||||
@@ -230,13 +239,6 @@ else()
|
||||
set(MFEM_DEBUG OFF)
|
||||
endif()
|
||||
|
||||
# Shadow warnings for clang only; GCC's -Wshadow flags more.
|
||||
if (CMAKE_CXX_COMPILER_ID MATCHES "Clang")
|
||||
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -pedantic -Wall -Wshadow")
|
||||
elseif (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
|
||||
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -pedantic -Wall")
|
||||
endif()
|
||||
|
||||
# Shared build on Windows
|
||||
if (WIN32 AND BUILD_SHARED_LIBS)
|
||||
# CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS works only with MSVC?
|
||||
@@ -431,15 +433,6 @@ if (MFEM_USE_STRUMPACK)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# cuDSS can only be enabled in CUDA
|
||||
if (MFEM_USE_CUDSS)
|
||||
if (MFEM_USE_CUDA)
|
||||
find_package(CUDSS REQUIRED)
|
||||
else()
|
||||
message(FATAL_ERROR " *** cuDSS requires that CUDA be enabled.")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# GnuTLS
|
||||
if (MFEM_USE_GNUTLS)
|
||||
find_package(_GnuTLS REQUIRED)
|
||||
@@ -638,7 +631,7 @@ find_package(Threads REQUIRED)
|
||||
set(MFEM_TPLS OPENMP HYPRE LAPACK BLAS SuperLUDist STRUMPACK METIS SuiteSparse
|
||||
SUNDIALS PETSC SLEPC MUMPS AXOM FMS CONDUIT Ginkgo GNUTLS GSLIB HDF5
|
||||
NETCDF MPFR PUMI HIOP POSIXCLOCKS MFEMBacktrace ZLIB OCCA CEED RAJA UMPIRE
|
||||
ADIOS2 MKL_CPARDISO MKL_PARDISO AMGX MAGMA CUSPARSE CUBLAS CUDSS CALIPER CODIPACK
|
||||
ADIOS2 MKL_CPARDISO MKL_PARDISO AMGX MAGMA CUSPARSE CUBLAS CALIPER CODIPACK
|
||||
BENCHMARK PARELAG TRIBOL MPI_CXX HIP HIPBLAS HIPSPARSE MOONOLITH BLITZ
|
||||
ALGOIM ENZYME CUDA::cudart)
|
||||
|
||||
@@ -659,8 +652,6 @@ foreach(TPL IN LISTS MFEM_TPLS)
|
||||
endif()
|
||||
endforeach(TPL)
|
||||
|
||||
# reverse to remove the first instance of entries in TPL_LIBRARIES
|
||||
# so later duplicates are kept (for dependency ordering)
|
||||
list(REVERSE TPL_LIBRARIES)
|
||||
list(REMOVE_DUPLICATES TPL_LIBRARIES)
|
||||
list(REVERSE TPL_LIBRARIES)
|
||||
@@ -1024,7 +1015,5 @@ install(DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/data
|
||||
# Create 'config.mk' from 'config.mk.in' for the build and install locations and
|
||||
# define install rules for 'config.mk' and 'test.mk'
|
||||
#-------------------------------------------------------------------------------
|
||||
if (MFEM_USE_CUDA OR MFEM_USE_HIP)
|
||||
option(MFEM_EXPORT_GPU_CONFIG "Export config.mk for GPU-enabled downstream packages" ON)
|
||||
endif()
|
||||
|
||||
mfem_export_mk_files()
|
||||
|
||||
+65
-72
@@ -3,12 +3,12 @@
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/mfem/mfem/blob/master/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-BSD-blue.svg"></a>
|
||||
<a href="https://github.com/mfem/mfem/releases/latest"><img alt="GitHub release" src="https://img.shields.io/github/v/release/mfem/mfem"></a>
|
||||
<a href="https://github.com/mfem/mfem/actions/workflows/repo-check.yml?query=branch%3Amaster"><img alt="Repo check" src="https://github.com/mfem/mfem/actions/workflows/repo-check.yml/badge.svg?branch=master"></a>
|
||||
<a href="https://github.com/mfem/mfem/actions/workflows/builds-and-tests.yml?query=branch%3Amaster"><img alt="Builds and Tests" src="https://github.com/mfem/mfem/actions/workflows/builds-and-tests.yml/badge.svg?branch=master"></a>
|
||||
<a href="https://github.com/mfem/mfem/blob/master/LICENSE"><img alt="License" src="https://img.shields.io/badge/License-BSD-brightgreen.svg"></a>
|
||||
<a href="https://github.com/mfem/mfem/actions?query=workflow%3Arepo-check+branch%3Amaster"><img alt="Repo check" src="https://github.com/mfem/mfem/actions/workflows/repo-check.yml/badge.svg?branch=master"></a>
|
||||
<a href="https://github.com/mfem/mfem/actions?query=workflow%3Abuild-analysis+branch%3Amaster"><img alt="Build Analysis" src="https://github.com/mfem/mfem/actions/workflows/mfem-analysis.yml/badge.svg?branch=master"></a>
|
||||
<a href="https://github.com/mfem/mfem/actions?query=workflow%3Abuilds-and-tests+branch%3Amaster"><img alt="Builds and Tests" src="https://github.com/mfem/mfem/actions/workflows/builds-and-tests.yml/badge.svg?branch=master"></a>
|
||||
<a href="https://ci.appveyor.com/project/mfem/mfem"><img alt="Build Status" src="https://ci.appveyor.com/api/projects/status/19non9sqm6msi2wy?svg=true"></a>
|
||||
<a href="https://docs.mfem.org/html/index.html"><img alt="Documentation" src="https://img.shields.io/badge/code-documented-brightgreen.svg"></a>
|
||||
<a href="https://docs.mfem.org/html/index.html"><img alt="Doxygen" src="https://img.shields.io/badge/code-documented-brightgreen.svg"></a>
|
||||
</p>
|
||||
|
||||
|
||||
@@ -24,14 +24,6 @@ must be made under this license.
|
||||
Note also that MFEM has a [Code of Conduct](CODE_OF_CONDUCT.md). By participating
|
||||
in the MFEM community, you agree to abide by its rules.
|
||||
|
||||
## AI Policy
|
||||
- Use of AI code generation in MFEM is allowed but must be disclosed, e.g. by
|
||||
selecting the `AI-assisted` label on the PR.
|
||||
- By submitting a PR, the author acknowledges that they have reviewed and
|
||||
understand the changes they are proposing.
|
||||
- PR authors are still responsible for correctness, licensing, and attribution
|
||||
of all changes.
|
||||
|
||||
If you plan on contributing to MFEM, consider reviewing the
|
||||
[issue tracker](https://github.com/mfem/mfem/issues) first to check if a thread
|
||||
already exists for your desired feature or the bug you ran into. Use a pull
|
||||
@@ -84,7 +76,7 @@ Origin](#developers-certificate-of-origin-11) at the end of this file.*
|
||||
follow the [MFEM PR Rules](#mfem-pr-rules).
|
||||
- When your contribution is fully working and ready to be reviewed, add
|
||||
the `ready-for-review` label.
|
||||
- PRs are treated similarly to journal submission, with an "editor" assigning two
|
||||
- PRs are treated similarly to journal submission with an "editor" assigning two
|
||||
reviewers to evaluate the changes.
|
||||
- The reviewers have 3 weeks to evaluate the PR and work with the author to
|
||||
fix issues and implement improvements.
|
||||
@@ -125,7 +117,7 @@ The MFEM source code has the following structure:
|
||||
│ ├── petsc
|
||||
│ ├── pumi
|
||||
│ ├── sundials
|
||||
│ └── superlu
|
||||
| └── superlu
|
||||
├── fem
|
||||
│ ├── ceed
|
||||
│ ├── dfem
|
||||
@@ -137,6 +129,10 @@ The MFEM source code has the following structure:
|
||||
│ ├── moonolith
|
||||
│ ├── qinterp
|
||||
│ └── tmop
|
||||
│ | ├── assemble
|
||||
│ | ├── metrics
|
||||
│ | ├── mult
|
||||
│ | └── tools
|
||||
├── general
|
||||
├── linalg
|
||||
│ ├── batched
|
||||
@@ -149,10 +145,11 @@ The MFEM source code has the following structure:
|
||||
│ ├── common
|
||||
│ ├── contact
|
||||
│ ├── dfem
|
||||
│ ├── diag-smoothers
|
||||
│ ├── dpg
|
||||
│ ├── electromagnetics
|
||||
│ ├── fluids
|
||||
│ │ ├── navier
|
||||
│ │ └── schrodinger-flow
|
||||
│ ├── gslib
|
||||
│ ├── hdiv-linear-solver
|
||||
│ ├── hooke
|
||||
@@ -162,7 +159,6 @@ The MFEM source code has the following structure:
|
||||
│ ├── nurbs
|
||||
│ ├── parelag
|
||||
│ ├── performance
|
||||
│ ├── plasma
|
||||
│ ├── shifted
|
||||
│ ├── solvers
|
||||
│ ├── spde
|
||||
@@ -193,15 +189,15 @@ respectively.
|
||||
|
||||
- The main finite element classes are:
|
||||
+ [`FiniteElement`](https://docs.mfem.org/html/classmfem_1_1FiniteElement.html)
|
||||
+ [`FiniteElementCollection`](https://docs.mfem.org/html/classmfem_1_1FiniteElementCollection.html)
|
||||
+ [`FiniteElementCollection`](https://docs.mfem.org/html/classmfem_1_1FiniteElement.html)
|
||||
+ [`FiniteElementSpace`](https://docs.mfem.org/html/classmfem_1_1FiniteElementSpace.html)
|
||||
+ [`GridFunction`](https://docs.mfem.org/html/classmfem_1_1GridFunction.html)
|
||||
+ [`BilinearFormIntegrator`](https://docs.mfem.org/html/classmfem_1_1BilinearFormIntegrator.html) and [`LinearFormIntegrator`](https://docs.mfem.org/html/classmfem_1_1LinearFormIntegrator.html)
|
||||
+ [`LinearForm`](https://docs.mfem.org/html/classmfem_1_1LinearForm.html), [`BilinearForm`](https://docs.mfem.org/html/classmfem_1_1BilinearForm.html) and [`MixedBilinearForm`](https://docs.mfem.org/html/classmfem_1_1MixedBilinearForm.html)
|
||||
+ [`LinearForm`](https://docs.mfem.org/html/classmfem_1_1LinearFormIntegrator.html), [`BilinearForm`](https://docs.mfem.org/html/classmfem_1_1BilinearForm.html) and [`MixedBilinearForm`](https://docs.mfem.org/html/classmfem_1_1MixedBilinearForm.html)
|
||||
|
||||
- The main linear algebra classes and sources are
|
||||
+ [`Operator`](https://docs.mfem.org/html/classmfem_1_1Operator.html) and [`BilinearForm`](https://docs.mfem.org/html/classmfem_1_1BilinearForm.html)
|
||||
+ [`Vector`](https://docs.mfem.org/html/classmfem_1_1Vector.html) and [`LinearForm`](https://docs.mfem.org/html/classmfem_1_1LinearForm.html)
|
||||
+ [`Vector`](https://docs.mfem.org/html/classmfem_1_1BilinearForm.html) and [`LinearForm`](https://docs.mfem.org/html/classmfem_1_1LinearForm.html)
|
||||
+ [`DenseMatrix`](https://docs.mfem.org/html/classmfem_1_1DenseMatrix.html) and [`SparseMatrix`](https://docs.mfem.org/html/classmfem_1_1SparseMatrix.html)
|
||||
+ Sparse [smoothers](https://docs.mfem.org/html/sparsesmoothers_8hpp.html) and linear [solvers](https://docs.mfem.org/html/solvers_8hpp.html)
|
||||
|
||||
@@ -213,8 +209,8 @@ shared geometric entities between different tasks. The parallel source files
|
||||
have a `p` prefix, e.g. `pmesh.cpp` vs. the serial `mesh.cpp`.
|
||||
|
||||
- The main parallel classes are
|
||||
+ [`ParMesh`](https://docs.mfem.org/html/classmfem_1_1ParMesh.html)
|
||||
+ [`ParNCMesh`](https://docs.mfem.org/html/classmfem_1_1ParNCMesh.html)
|
||||
+ [`ParMesh`](https://docs.mfem.org/html/solvers_8hpp.html)
|
||||
+ [`ParNCMesh`](https://docs.mfem.org/html/classmfem_1_1ParMesh.html)
|
||||
+ [`ParFiniteElementSpace`](https://docs.mfem.org/html/classmfem_1_1ParFiniteElementSpace.html)
|
||||
+ [`ParGridFunction`](https://docs.mfem.org/html/classmfem_1_1ParGridFunction.html)
|
||||
+ [`ParBilinearForm`](https://docs.mfem.org/html/classmfem_1_1ParBilinearForm.html) and [`ParLinearForm`](https://docs.mfem.org/html/classmfem_1_1ParLinearForm.html)
|
||||
@@ -224,14 +220,14 @@ have a `p` prefix, e.g. `pmesh.cpp` vs. the serial `mesh.cpp`.
|
||||
#### GPU and general device support
|
||||
|
||||
GPU and multi-core CPU support is based on device kernels supporting different
|
||||
backends (CUDA, HIP, OCCA, RAJA, OpenMP, etc.) and an internal lightweight
|
||||
backends (CUDA, OCCA, RAJA, OpenMP, etc.) and an internal lightweight
|
||||
device/host memory manager.
|
||||
|
||||
- The main device-relevant classes and sources are:
|
||||
+ [`Device`](https://docs.mfem.org/html/device_8hpp.html)
|
||||
+ [`MemoryManager`](https://docs.mfem.org/html/mem_manager_8hpp.html)
|
||||
+ the [`mfem::forall`](https://docs.mfem.org/html/forall_8hpp.html) function
|
||||
+ the [`cuda.hpp`](https://docs.mfem.org/html/cuda_8hpp.html), [`hip.hpp`](https://docs.mfem.org/html/hip_8hpp.html) and [`occa.hpp`](https://docs.mfem.org/html/occa_8hpp.html) files
|
||||
+ the [`cuda.hpp`](https://docs.mfem.org/html/cuda_8hpp.html) and [`occa.hpp`](https://docs.mfem.org/html/occa_8hpp.html) files
|
||||
|
||||
#### Utilities, building and documentation
|
||||
- The `general/` directory contains C++ classes that serve as utilities for
|
||||
@@ -245,8 +241,8 @@ device/host memory manager.
|
||||
- `examples` and `miniapps` respectively gather simple and more fully-featured
|
||||
demonstrations of the usage on MFEM. They both rely on `data/` for the
|
||||
collection of meshes.
|
||||
- The `tests/` directory contains a unit test suite, additional tests, and
|
||||
benchmarks.
|
||||
- The `tests/` directory contains a unit test suite and will later contain more
|
||||
tests that run example codes.
|
||||
|
||||
See also the [code overview](https://mfem.org/code-overview/) section on the MFEM
|
||||
website.
|
||||
@@ -280,8 +276,8 @@ Before you can start, you need a GitHub account, here are a few suggestions:
|
||||
the top of https://github.com/mfem.
|
||||
- Consider making your membership public by going to https://github.com/orgs/mfem/people
|
||||
and clicking on the organization visibility drop box next to your name.
|
||||
- Project discussions and announcements will be posted at https://github.com/orgs/mfem/discussions,
|
||||
tagging the `@mfem/everyone` team when appropriate.
|
||||
- Project discussions and announcements will be posted at
|
||||
https://github.com/orgs/mfem/teams/everyone.
|
||||
|
||||
#### Structure
|
||||
- The MFEM source code is in the [mfem](https://github.com/mfem/mfem)
|
||||
@@ -341,12 +337,11 @@ Before you can start, you need a GitHub account, here are a few suggestions:
|
||||
- Well-designed simple code is frequently more general and powerful.
|
||||
- Lean code base is easier to understand by new collaborators.
|
||||
- New features should be added only if they are necessary or generally useful.
|
||||
- Introduction of language constructs not currently used in MFEM should be
|
||||
- Introduction of language constructions not currently used in MFEM should be
|
||||
justified and generally avoided (to maintain portability to various systems
|
||||
and compilers, including early access hardware).
|
||||
- We prefer basic C++. Use C++17 features judiciously, prioritizing readability,
|
||||
consistency with existing MFEM code, and portability to different systems,
|
||||
compilers and device backends.
|
||||
- We prefer basic C++ and the C++03 standard, to keep the code readable by
|
||||
a large audience and to make sure it compiles anywhere.
|
||||
|
||||
- *Keep the code general and reasonably efficient*
|
||||
- The main goal is fast prototyping for research and application development.
|
||||
@@ -389,7 +384,7 @@ Before you can start, you need a GitHub account, here are a few suggestions:
|
||||
- When your branch is ready for other developers to review / comment on
|
||||
the code, create a pull request towards `mfem:master`.
|
||||
|
||||
- Pull requests typically have titles like:
|
||||
- Pull request typically have titles like:
|
||||
|
||||
`Description [new-feature-dev]`
|
||||
|
||||
@@ -410,12 +405,12 @@ Before you can start, you need a GitHub account, here are a few suggestions:
|
||||
- Add a description, appropriate labels and assign yourself to the PR. The MFEM
|
||||
team will add reviewers as appropriate.
|
||||
|
||||
- List outstanding TODO items in the description.
|
||||
- List outstanding TODO items in the description, see PR #222 for an example.
|
||||
|
||||
- When your contribution is fully working and ready to be reviewed, add
|
||||
or request the `ready-for-review` label.
|
||||
the `ready-for-review` label.
|
||||
|
||||
- PRs are treated similarly to journal submission, with an "editor" assigning
|
||||
- PRs are treated similarly to journal submission with an "editor" assigning
|
||||
two reviewers to evaluate the changes. The reviewers have 3 weeks to evaluate
|
||||
the PR and work with the author to implement improvements and fix issues.
|
||||
|
||||
@@ -441,7 +436,7 @@ Before you can start, you need a GitHub account, here are a few suggestions:
|
||||
checks in GitHub Actions enforce MFEM-specific rules which are explained in
|
||||
the error messages and the `tests/scripts` directory.
|
||||
|
||||
- Also note that the tests `branch-history` and `repo-check` found in GitHub
|
||||
- Also note that the tests `branch-history` and `repos-checks` found in GitHub
|
||||
Actions can be triggered automatically before each push using git hooks. See
|
||||
the [git hooks README](config/githooks/README.md) for a detailed explanation.
|
||||
|
||||
@@ -498,15 +493,15 @@ Everyone on the MFEM team can be asked to serve as a reviewer on a PR in their a
|
||||
|
||||
3. To ensure the quality of the PR by making sure that the code adheres to the [Developer Guidelines](#developer-guidelines), e.g. all methods, data members, and functions have documentation, including data ownership and lifetime, new examples/miniapps have a corresponding PR in mfem/web, major features have `CHANGELOG` entries, etc.
|
||||
|
||||
4. To seek help from the editors in case of difficulties.
|
||||
3. To seek help from the editors in case of difficulties.
|
||||
|
||||
5. To complete the review in a timely manner: 3 weeks from assignment.
|
||||
4. To complete the review in a timely manner: 3 weeks from assignment.
|
||||
|
||||
6. To test the PR thoroughly before merging in *next*. The PR author is also encouraged to perform testing and inform the reviewers about the results.
|
||||
5. To test the PR thoroughly before merging in *next*. The PR author is also encouraged to perform testing and inform the reviewers about the results.
|
||||
|
||||
7. To monitor the PR impact on the testing in the *next* branch and alert the editors that the PR is ready for merging in *master*.
|
||||
6. To monitor the PR impact on the testing in the *next* branch and alert the editors that the PR is ready for merging in *master*.
|
||||
|
||||
8. The review of bugfixes should be expedited proportional to their importance. The review window can be much less than three weeks in such cases.
|
||||
7. The review of bugfixes should be expedited proportional to their importance. The review window can be much less than three weeks in such cases.
|
||||
|
||||
#### Responsibilities of Authors
|
||||
|
||||
@@ -532,30 +527,30 @@ Before a PR can be merged, it should satisfy the following:
|
||||
- [ ] Code builds.
|
||||
- [ ] Code passes `make style`.
|
||||
- [ ] Update `CHANGELOG`:
|
||||
- [ ] Is this a new feature users need to be aware of? New or updated example or miniapp?
|
||||
- [ ] Does it make sense to create a new section in the `CHANGELOG` to group with other related features?
|
||||
- [ ] Is this a new feature users need to be aware of? New or updated example or miniapp?
|
||||
- [ ] Does it make sense to create a new section in the `CHANGELOG` to group with other related features?
|
||||
- [ ] Update `INSTALL`:
|
||||
- [ ] Has a new optional library been added? If so, what range of versions of this library are required? (*Make sure the external library is compatible with our BSD license, e.g. it is not licensed under GPL!*)
|
||||
- [ ] Have the version ranges for any required or optional libraries changed?
|
||||
- [ ] Does `make` or `cmake` have a new target?
|
||||
- [ ] Did the requirements or the installation process change? *(rare)*
|
||||
- [ ] Had a new optional library been added? If so, what range of versions of this library are required? (*Make sure the external library is compatible with our BSD license, e.g. it is not licensed under GPL!*)
|
||||
- [ ] Have the version ranges for any required or optional libraries changed?
|
||||
- [ ] Does `make` or `cmake` have a new target?
|
||||
- [ ] Did the requirements or the installation process change? *(rare)*
|
||||
- [ ] Update continuous integration server configurations if necessary (e.g. with new version requirements for each of MFEM's dependencies)
|
||||
- [ ] `.github`
|
||||
- [ ] `.appveyor.yml`
|
||||
- [ ] `.github`
|
||||
- [ ] `.appveyor.yml`
|
||||
- [ ] Update `.gitignore`:
|
||||
- [ ] Check if `make distclean; git status` shows any files that were generated from the source by the project (not an IDE) but we don't want to track in the repository.
|
||||
- [ ] Add new patterns (just for the new files above) and re-run the above test.
|
||||
- [ ] Check if `make distclean; git status` shows any files that were generated from the source by the project (not an IDE) but we don't want to track in the repository.
|
||||
- [ ] Add new patterns (just for the new files above) and re-run the above test.
|
||||
- [ ] New examples:
|
||||
- [ ] All sample runs at the top of the example source file work.
|
||||
- [ ] Update `examples/makefile`:
|
||||
- [ ] All sample runs at the top of the example source file work.
|
||||
- [ ] Update `examples/makefile`:
|
||||
- [ ] Add the example code to the appropriate `SEQ_EXAMPLES` and `PAR_EXAMPLES` variables.
|
||||
- [ ] Add any files generated by it to the `clean` target.
|
||||
- [ ] Add the example binary and any files generated by it to the top-level `.gitignore` file.
|
||||
- [ ] Update `examples/CMakeLists.txt`:
|
||||
- [ ] Update `examples/CMakeLists.txt`:
|
||||
- [ ] Add the example code to the `ALL_EXE_SRCS` variable.
|
||||
- [ ] Make sure `THIS_TEST_OPTIONS` is set correctly for the new example.
|
||||
- [ ] List the new example in `doc/CodeDocumentation.dox`.
|
||||
- [ ] If new examples directory (e.g. `examples/pumi`), list it in `doc/CodeDocumentation.conf.in`
|
||||
- [ ] If new examples directory (e.g.`examples/pumi`), list it in `doc/CodeDocumentation.conf.in`
|
||||
- [ ] Companion pull request for documentation in [mfem/web](https://github.com/mfem/web) repo:
|
||||
- [ ] Update or add example-specific documentation, see e.g. the `src/examples.md`.
|
||||
- [ ] Add the description, labels and screenshots in `src/examples.md` and `src/img`.
|
||||
@@ -572,13 +567,13 @@ Before a PR can be merged, it should satisfy the following:
|
||||
- [ ] Add/update the `CMakeLists.txt` file in the new miniapp directory.
|
||||
- [ ] Consider adding a new test for the new miniapp.
|
||||
- [ ] List the new miniapp in `doc/CodeDocumentation.dox`
|
||||
- [ ] If new miniapps directory (e.g. `miniapps/nurbs`), add it to `MINIAPP_SUBDIRS` in the `makefile`.
|
||||
- [ ] If new miniapps directory (e.g. `miniapps/nurbs`), list it in `doc/CodeDocumentation.conf.in`
|
||||
- [ ] If new miniapps directory (e.g.`miniapps/nurbs`), add it to `MINIAPP_SUBDIRS` in the `makefile`.
|
||||
- [ ] If new miniapps directory (e.g.`miniapps/nurbs`), list it in `doc/CodeDocumentation.conf.in`
|
||||
- [ ] Companion pull request for documentation in [mfem/web](https://github.com/mfem/web) repo:
|
||||
- [ ] Update or add miniapp-specific documentation, see e.g. the `src/meshing.md` and `src/electromagnetics.md` files.
|
||||
- [ ] Add the description, labels and screenshots in `src/examples.md` and `src/img`.
|
||||
- [ ] The miniapps go at the end of the page, and are usually listed only under a specific "Application (PDE)" category.
|
||||
- [ ] Add a short description of the miniapp in the "Extensive Examples" section of `features.md`.
|
||||
- [ ] Update or add miniapp-specific documentation, see e.g. the `src/meshing.md` and `src/electromagnetics.md` files.
|
||||
- [ ] Add the description, labels and screenshots in `src/examples.md` and `src/img`.
|
||||
- [ ] The miniapps go at the end of the page, and are usually listed only under a specific "Application (PDE)" category.
|
||||
- [ ] Add a short description of the miniapp in the "Extensive Examples" section of `features.md`.
|
||||
- [ ] New capability:
|
||||
- [ ] All new public, protected, and private classes, methods, data members, and functions have full Doxygen-style documentation in source comments. Documentation should include descriptions of member data, function arguments and return values, template parameters, and prerequisites for calling new functions.
|
||||
- [ ] Pointer arguments and return values must specify whether ownership is being transferred or lent with the call.
|
||||
@@ -680,7 +675,7 @@ MFEM uses a `master`/`next`-branch workflow as described below:
|
||||
- [ ] Update URL shortlinks:
|
||||
- [ ] Create a shortlink at [http://bit.ly/](http://bit.ly/) for the release tarball, e.g. https://mfem.github.io/releases/mfem-3.1.tgz.
|
||||
- [ ] (LLNL only) Add and commit the new shortlink in the `links` and `links-mfem` files of the internal `mfem/downloads` repo.
|
||||
- [ ] Add the new shortlinks to the MFEM package in `spack`.
|
||||
- [ ] Add the new shortlinks to the MFEM packages in `spack`, `homebrew/science`, `VisIt`, etc.
|
||||
- [ ] Update website in `mfem/web` repo:
|
||||
- Update version and shortlinks in `src/index.md` and `src/download.md`.
|
||||
- Use [cloc-1.62.pl](http://cloc.sourceforge.net/) and `ls -lh` to estimate the SLOC and the tarball size in `src/download.md`.
|
||||
@@ -732,24 +727,22 @@ commit or push, see the [README](config/githooks/README.md) in the `config/githo
|
||||
directory.
|
||||
|
||||
|
||||
### GitHub Actions smoke tests
|
||||
|
||||
### Linux and Mac smoke tests
|
||||
We use GitHub Actions to drive the default tests on the `master` and `next`
|
||||
branches. See the `.github/workflows` files and the logs at
|
||||
[https://github.com/mfem/mfem/actions](https://github.com/mfem/mfem/actions).
|
||||
|
||||
GitHub Actions testing should be kept lightweight, as there is a time
|
||||
constraint on jobs. The current workflows cover Linux, macOS, and Windows
|
||||
configurations.
|
||||
Testing using GitHub Actions should be kept lightweight, as there is a time
|
||||
constraint on jobs. Two virtual machines are configured - Mac (OS X) and Linux.
|
||||
|
||||
- Tests on the `master` branch are triggered whenever a PR is issued on this branch.
|
||||
- Tests on the `next` branch are currently scheduled to run each night.
|
||||
|
||||
### Additional Windows smoke test
|
||||
|
||||
We also use Appveyor to test building with the MS Visual C++ compiler in a Windows
|
||||
environment, as well as to test the CMake build. See the `.appveyor.yml` file
|
||||
and the build logs at
|
||||
### Windows smoke test
|
||||
We use Appveyor to test building with the MS Visual C++ compiler in a Windows
|
||||
environment, as well as to test the CMake build. See the `.appveyor` file and the
|
||||
build logs at
|
||||
[https://ci.appveyor.com/project/mfem/mfem](https://ci.appveyor.com/project/mfem/mfem).
|
||||
|
||||
CMake is used to generate the MSVC Project files and drive the build. A release
|
||||
|
||||
@@ -38,13 +38,14 @@ the option MFEM_USE_METIS.
|
||||
MFEM also includes support for devices such as GPUs, and programming models such
|
||||
as CUDA, HIP, OCCA, OpenMP and RAJA.
|
||||
|
||||
- Starting with version 4.9, MFEM requires a C++17 compiler.
|
||||
- Starting with version 4.0, MFEM requires a C++11 compiler. We recommend using
|
||||
a newer compiler, e.g. GCC version 4.9 or higher.
|
||||
|
||||
- CUDA support requires an NVIDIA GPU and an installation of the CUDA Toolkit
|
||||
https://developer.nvidia.com/cuda-toolkit
|
||||
|
||||
- HIP support requires an AMD GPU and an installation of the ROCm software stack
|
||||
https://rocm.docs.amd.com
|
||||
https://rocmdocs.amd.com
|
||||
|
||||
- OCCA support requires the OCCA library
|
||||
https://libocca.org
|
||||
@@ -82,9 +83,9 @@ Serial build:
|
||||
Parallel build:
|
||||
(download hypre and METIS 4 from above URLs)
|
||||
(build METIS 4 in ../metis-4.0 relative to mfem/)
|
||||
(for METIS 5, see https://mfem.org/building/#parallel-build-using-metis-5)
|
||||
(build hypre in ../hypre relative to mfem/)
|
||||
make parallel -j 4
|
||||
(For METIS 5, see https://mfem.org/building/#parallel-build-using-metis-5)
|
||||
|
||||
CUDA build:
|
||||
make cuda -j 4
|
||||
@@ -114,14 +115,14 @@ Serial build:
|
||||
Parallel build:
|
||||
(download hypre and METIS 4 from above URLs)
|
||||
(build METIS 4 in ../metis-4.0 relative to mfem/)
|
||||
(for METIS 5, see https://mfem.org/building/#parallel-build-using-metis-5)
|
||||
(build hypre in ../hypre relative to mfem/)
|
||||
mkdir <mfem-build-dir> ; cd <mfem-build-dir>
|
||||
cmake <mfem-source-dir> -DMFEM_USE_MPI=YES
|
||||
make -j 4
|
||||
(For METIS 5, see https://mfem.org/building/#parallel-build-using-metis-5)
|
||||
|
||||
Parallel build with fetching of hypre and METIS:
|
||||
mkdir <mfem-build-dir> ; cd <mfem-build-dir>
|
||||
mkdir <mfem-buil-dir> ; cd <mfem-build-dir>
|
||||
cmake <mfem-source-dir> -DMFEM_USE_MPI=YES -DMFEM_FETCH_TPLS=YES
|
||||
make -j 4
|
||||
|
||||
@@ -133,8 +134,7 @@ CUDA build:
|
||||
|
||||
HIP build:
|
||||
mkdir <mfem-build-dir> ; cd <mfem-build-dir>
|
||||
cmake <mfem-source-dir> -DMFEM_USE_HIP=YES -DHIP_ARCH=gfx942 \
|
||||
-DCMAKE_CXX_COMPILER=amdclang++ -DCMAKE_HIP_COMPILER=amdclang++
|
||||
cmake <mfem-source-dir> -DMFEM_USE_HIP=YES -DHIP_ARCH=gfx942 -DCMAKE_CXX_COMPILER=amdclang++ -DCMAKE_HIP_COMPILER=amdclang++
|
||||
make -j 4
|
||||
|
||||
Example codes (serial/parallel, depending on the build):
|
||||
@@ -269,7 +269,6 @@ Compilers:
|
||||
CXX - C++ compiler, serial build
|
||||
MPICXX - MPI C++ compiler, parallel build
|
||||
CUDA_CXX - The CUDA compiler, 'nvcc' or 'clang++'
|
||||
HIP_CXX - The HIP compiler, e.g. 'hipcc'
|
||||
|
||||
Compiler options:
|
||||
OPTIM_FLAGS - Options for optimized build
|
||||
@@ -396,11 +395,6 @@ MFEM_USE_STRUMPACK = YES/NO
|
||||
classes. When enabled, this option uses the STRUMPACK_* library options, see
|
||||
below.
|
||||
|
||||
MFEM_USE_CUDSS = YES/NO
|
||||
Enable MFEM functionality based on the cuDSS library. When using cuDSS, CUDA
|
||||
support must be also enabled in MFEM, i.e. MFEM_USE_CUDA=YES must be set.
|
||||
When enabled, this option uses the CUDSS_* library options, see below.
|
||||
|
||||
MFEM_USE_GINKGO = YES/NO
|
||||
Enable MFEM functionality based on the Ginkgo library, which provides
|
||||
iterative linear solvers and preconditioners with OpenMP, CUDA backends, see
|
||||
@@ -560,13 +554,13 @@ MFEM_USE_RAJA = YES/NO
|
||||
MFEM_USE_OCCA = YES/NO
|
||||
Enables support for the OCCA library in MFEM. OCCA is an open-source library
|
||||
which aims to make it easy to program different types of devices (e.g. CPU,
|
||||
GPU, FPGA) by providing a unified API for interacting with JIT-compiled
|
||||
GPU, FPGA) by providing an unified API for interacting with JIT-compiled
|
||||
backends. In order to use the OCCA CUDA backend, CUDA support must be enabled
|
||||
in MFEM as well, i.e. MFEM_USE_CUDA=YES must be set.
|
||||
|
||||
MFEM_USE_GSLIB = YES/NO
|
||||
Enables MFEM functionality based on the GSLIB library, and specifically its
|
||||
FindPoints component, which provides robust algorithms to evaluate finite
|
||||
FindPoints component, which provides a robust algorithms to evaluate finite
|
||||
element functions in a collection of points in physical space. When enabled,
|
||||
the user can use the GSLIB-FindPoints methods as shown in miniapps/gslib.
|
||||
|
||||
@@ -725,18 +719,9 @@ The specific libraries and their options are:
|
||||
Options: STRUMPACK_OPT, STRUMPACK_LIB.
|
||||
Versions: STRUMPACK >= 3.0.0.
|
||||
|
||||
- CUDSS (optional), used when MFEM_USE_CUDSS = YES. Note that CUDSS requires
|
||||
CUDA 12.x toolkit and the cuDSS libraries. The supported communication backend
|
||||
is OpenMPI 4.x (default), and OpenMPI 4.x or a later version must be pre-built.
|
||||
The source files in the cuDSS tarball provide guidance for developing custom
|
||||
MPI implementations.
|
||||
URL: https://developer.nvidia.com/cudss
|
||||
https://docs.nvidia.com/cuda/cudss/advanced_features.html#communication-layer-library-in-cudss
|
||||
Options: CUDSS_OPT, CUDSS_LIB.
|
||||
Versions: cuDSS >= 0.6.0.
|
||||
|
||||
- Ginkgo (optional), used when MFEM_USE_GINKGO = YES. Ginkgo may have additional
|
||||
requirements and module-specific dependencies; see the webpage below.
|
||||
- Ginkgo (optional), used when MFEM_USE_GINKGO = YES. Note that Ginkgo needs a
|
||||
C++ compiler that supports the C++-17 standard. For additional requirements
|
||||
and dependencies of specific modules, see the Ginkgo webpage below.
|
||||
URL: https://ginkgo-project.github.io
|
||||
Options: GINKGO_OPT, GINKGO_LIB, GINKGO_DIR, GINKGO_BUILD_TYPE (Release or
|
||||
Debug).
|
||||
@@ -808,7 +793,7 @@ The specific libraries and their options are:
|
||||
Options: CONDUIT_OPT, CONDUIT_LIB.
|
||||
Versions: Conduit >= 0.3.1.
|
||||
|
||||
- ADIOS2 (optional), used when MFEM_USE_ADIOS2 = YES.
|
||||
- ADIOS2 (optional) used when MFEM_USE_ADIOS2 = YES.
|
||||
URL: https://adios2.readthedocs.io/
|
||||
Versions: ADIOS >= 2.5.0.
|
||||
|
||||
@@ -884,7 +869,7 @@ The specific libraries and their options are:
|
||||
Options: RAJA_DIR, RAJA_OPT, RAJA_LIB.
|
||||
Versions: RAJA >= 2022.10.3.
|
||||
|
||||
- Moonolith (optional), used when MFEM_USE_MOONOLITH = YES.
|
||||
- Moonolith (optional), use when MFEM_USE_MOONOLITH = YES.
|
||||
URL: https://bitbucket.org/zulianp/par_moonolith
|
||||
Options: MOONOLITH_DIR
|
||||
Versions: MOONOLITH >= 1.1.0.
|
||||
@@ -972,7 +957,7 @@ CMAKE_BUILD_TYPE which can be set to standard values like "Debug", and "Release"
|
||||
To use a specific generator use the "-G <generator>" option of cmake:
|
||||
|
||||
cmake <mfem-source-dir> -G "Xcode"
|
||||
cmake <mfem-source-dir> -G "Visual Studio 17 2022"
|
||||
cmake <mfem-source-dir> -G "Visual Studio 12 2013"
|
||||
cmake <mfem-source-dir> -G "MinGW Makefiles"
|
||||
|
||||
With CMake it is possible to build MFEM as a shared library using the standard
|
||||
@@ -1217,7 +1202,7 @@ larger problems, there are two options:
|
||||
Specific options for HIP
|
||||
========================
|
||||
MFEM expects the `ROCM_PATH` environment variable to be set to the path of the
|
||||
ROCm install, as well as having `$ROCM_PATH/bin` in `PATH`.
|
||||
ROCM install, as well as having `$ROCM_PATH/bin` in `PATH`.
|
||||
|
||||
Specific options for RAJA+HIP+MPI
|
||||
=================================
|
||||
|
||||
@@ -28,7 +28,6 @@ license files. These software products and their licenses are as follows:
|
||||
* AmgXWrapper (linalg/amgxsolver.{hpp,cpp}) -- MIT license
|
||||
* Catch++ (tests/unit/catch.hpp) -- Boost 1.0 license
|
||||
* Gecko (general/gecko.{cpp,hpp}) -- BSD 3-clause license
|
||||
* gslib (fem/gslib.{cpp,hpp}, mesh/bb_grid_map.{cpp,hpp}) -- BSD 3-clause license
|
||||
* Picojson (fem/picojson.h) -- Custom 2-clause license
|
||||
* TinyXML2 (general/tinyxml2.{cpp,h}) -- zlib license
|
||||
* Zstr (general/zstr.hpp) -- MIT license
|
||||
|
||||
@@ -35,7 +35,6 @@ set(MFEM_USE_SUITESPARSE @MFEM_USE_SUITESPARSE@)
|
||||
set(MFEM_USE_SUPERLU @MFEM_USE_SUPERLU@)
|
||||
set(MFEM_USE_MUMPS @MFEM_USE_MUMPS@)
|
||||
set(MFEM_USE_STRUMPACK @MFEM_USE_STRUMPACK@)
|
||||
set(MFEM_USE_CUDSS @MFEM_USE_CUDSS@)
|
||||
set(MFEM_USE_GINKGO @MFEM_USE_GINKGO@)
|
||||
set(MFEM_USE_AMGX @MFEM_USE_AMGX@)
|
||||
set(MFEM_USE_MAGMA @MFEM_USE_MAGMA@)
|
||||
@@ -110,14 +109,6 @@ if (MFEM_USE_RAJA)
|
||||
find_dependency(RAJA)
|
||||
endif()
|
||||
|
||||
if (MFEM_USE_CUDSS)
|
||||
find_dependency(cudss)
|
||||
endif (MFEM_USE_CUDSS)
|
||||
|
||||
if (MFEM_USE_UMPIRE)
|
||||
find_dependency(umpire)
|
||||
endif()
|
||||
|
||||
if (NOT TARGET mfem)
|
||||
include(${CMAKE_CURRENT_LIST_DIR}/MFEMTargets.cmake)
|
||||
endif (NOT TARGET mfem)
|
||||
|
||||
@@ -108,15 +108,6 @@
|
||||
// Enable MFEM functionality based on the STRUMPACK library.
|
||||
#cmakedefine MFEM_USE_STRUMPACK
|
||||
|
||||
// Enable MFEM functionality based on the cuDSS library.
|
||||
#cmakedefine MFEM_USE_CUDSS
|
||||
|
||||
// CUDSS communication layer library path
|
||||
#cmakedefine MFEM_CUDSS_COMM_LIB "@MFEM_CUDSS_COMM_LIB@"
|
||||
|
||||
// CUDSS threading layer library path
|
||||
#cmakedefine MFEM_CUDSS_THREADING_LIB "@MFEM_CUDSS_THREADING_LIB@"
|
||||
|
||||
// Enable functionality based on the Ginkgo library.
|
||||
#cmakedefine MFEM_USE_GINKGO
|
||||
|
||||
|
||||
@@ -1,68 +0,0 @@
|
||||
if (NOT cudss_DIR AND CUDSS_DIR)
|
||||
set(cudss_DIR ${CUDSS_DIR}/lib/cmake/cudss)
|
||||
endif()
|
||||
message(STATUS "Looking for CUDSS ...")
|
||||
message(STATUS " in CUDSS_DIR = ${CUDSS_DIR}")
|
||||
message(STATUS " cudss_DIR = ${cudss_DIR}")
|
||||
find_package(cudss)
|
||||
set(CUDSS_FOUND ${cudss_FOUND})
|
||||
set(CUDSS_LIBRARIES "cudss")
|
||||
if (CUDSS_FOUND)
|
||||
message(STATUS
|
||||
"Found CUDSS target: ${CUDSS_LIBRARIES} (version: ${cudss_VERSION})")
|
||||
else()
|
||||
set(msg STATUS)
|
||||
if (CUDSS_FIND_REQUIRED)
|
||||
set(msg FATAL_ERROR)
|
||||
endif()
|
||||
message(${msg}
|
||||
"CUDSS not found. Please set CUDSS_DIR to the install prefix.")
|
||||
endif()
|
||||
|
||||
if(CUDSS_FOUND AND TARGET cudss)
|
||||
get_target_property(CUDSS_LIBRARY_LOCATION cudss IMPORTED_LOCATION)
|
||||
if(NOT CUDSS_LIBRARY_LOCATION)
|
||||
get_target_property(CUDSS_LIBRARY_LOCATION cudss IMPORTED_LOCATION_RELEASE)
|
||||
endif()
|
||||
if(CUDSS_LIBRARY_LOCATION)
|
||||
get_filename_component(CUDSS_LIBRARY_DIR "${CUDSS_LIBRARY_LOCATION}" DIRECTORY)
|
||||
else()
|
||||
message(WARNING "Could not determine the location of the cuDSS library.")
|
||||
endif()
|
||||
else()
|
||||
message(WARNING "cuDSS target not available; cannot determine library directory.")
|
||||
endif()
|
||||
|
||||
# Set the full name of the cuDSS threading library if OpenMP is enabled.
|
||||
# The threading layer library (libcudss_mtlayer_gomp.so) is located under the
|
||||
# cuDSS library directory by default.
|
||||
if (MFEM_USE_OPENMP)
|
||||
find_file(
|
||||
CUDSS_THREADING_LIB
|
||||
NAMES libcudss_mtlayer_gomp.so
|
||||
PATHS ${CUDSS_LIBRARY_DIR}
|
||||
NO_DEFAULT_PATH
|
||||
)
|
||||
if (NOT DEFINED MFEM_CUDSS_THREADING_LIB AND CUDSS_THREADING_LIB)
|
||||
set(MFEM_CUDSS_THREADING_LIB "${CUDSS_THREADING_LIB}")
|
||||
endif()
|
||||
message(STATUS "CUDSS threading layer library: ${MFEM_CUDSS_THREADING_LIB}")
|
||||
endif()
|
||||
|
||||
# Set the full name of the cuDSS communication library if MFEM use OpenMPI.
|
||||
# The communication layer library (libcudss_commlayer_mpi.so) is located under the
|
||||
# cuDSS library directory by default.
|
||||
# The communication layer library is used pre-built communication layers for OpenMPI
|
||||
# by default.
|
||||
if (MFEM_USE_MPI)
|
||||
find_file(
|
||||
CUDSS_COMM_LIB
|
||||
NAMES libcudss_commlayer_openmpi.so
|
||||
PATHS ${CUDSS_LIBRARY_DIR}
|
||||
NO_DEFAULT_PATH
|
||||
)
|
||||
if (NOT DEFINED MFEM_CUDSS_COMM_LIB AND CUDSS_COMM_LIB)
|
||||
set(MFEM_CUDSS_COMM_LIB "${CUDSS_COMM_LIB}")
|
||||
endif()
|
||||
message(STATUS "CUDSS communication layer library: ${MFEM_CUDSS_COMM_LIB}")
|
||||
endif()
|
||||
@@ -18,17 +18,19 @@
|
||||
|
||||
if (MFEM_FETCH_GSLIB OR MFEM_FETCH_TPLS)
|
||||
enable_language(C)
|
||||
set(GSLIB_FETCH_VERSION 1.0.9)
|
||||
add_library(GSLIB STATIC IMPORTED)
|
||||
# set options (technically flags because GSLIB does not use cmake)
|
||||
string(TOUPPER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
|
||||
set(GSLIB_FLAGS "${CMAKE_C_FLAGS} ${CMAKE_C_FLAGS_${BUILD_TYPE}}")
|
||||
if (BUILD_SHARED_LIBS)
|
||||
set(GSLIB_FLAGS "${GSLIB_FLAGS} -fPIC")
|
||||
set(GSLIB_FETCH_VERSION 1.0.9)
|
||||
set(GSLIB_C_FLAGS ${CMAKE_C_FLAGS_${BUILD_TYPE}})
|
||||
if (CMAKE_C_FLAGS)
|
||||
set(GSLIB_C_FLAGS "${CMAKE_C_FLAGS} ${CMAKE_C_FLAGS_${BUILD_TYPE}}")
|
||||
endif()
|
||||
if (BUILD_SHARED_LIBS)
|
||||
set(GSLIB_C_FLAGS "${GSLIB_C_FLAGS} -fPIC")
|
||||
endif()
|
||||
add_library(GSLIB STATIC IMPORTED)
|
||||
# define external project and create future include directory so it is present
|
||||
# to pass CMake checks at end of MFEM configuration step
|
||||
message(STATUS "Will fetch GSLIB ${GSLIB_FETCH_VERSION} to be built with ${GSLIB_FLAGS}")
|
||||
message(STATUS "Will fetch GSLIB ${GSLIB_FETCH_VERSION} to be built with ${GSLIB_C_FLAGS}")
|
||||
set(PREFIX ${CMAKE_BINARY_DIR}/fetch/gslib)
|
||||
include(ExternalProject)
|
||||
ExternalProject_Add(gslib
|
||||
@@ -38,7 +40,7 @@ if (MFEM_FETCH_GSLIB OR MFEM_FETCH_TPLS)
|
||||
UPDATE_DISCONNECTED TRUE
|
||||
PREFIX ${PREFIX}
|
||||
CONFIGURE_COMMAND ""
|
||||
BUILD_COMMAND cd ${PREFIX}/src/gslib && $(MAKE) clean && $(MAKE) DESTDIR=${PREFIX} MPI=$<BOOL:${MFEM_USE_MPI}> "CFLAGS=${GSLIB_FLAGS}"
|
||||
BUILD_COMMAND cd ${PREFIX}/src/gslib && $(MAKE) clean && $(MAKE) DESTDIR=${PREFIX} MPI=$<BOOL:${MFEM_USE_MPI}> "CFLAGS= ${GSLIB_C_FLAGS}"
|
||||
INSTALL_COMMAND "")
|
||||
file(MAKE_DIRECTORY ${PREFIX}/include)
|
||||
# set imported library target properties
|
||||
|
||||
@@ -44,9 +44,6 @@ if (MFEM_FETCH_HYPRE OR MFEM_FETCH_TPLS)
|
||||
# set options and associated dependencies
|
||||
set(HYPRE_CMAKE_OPTIONS "")
|
||||
list(APPEND HYPRE_CMAKE_OPTIONS -DCMAKE_BUILD_TYPE:STRING=${CMAKE_BUILD_TYPE})
|
||||
if (BUILD_SHARED_LIBS)
|
||||
list(APPEND HYPRE_CMAKE_OPTIONS -DCMAKE_POSITION_INDEPENDENT_CODE:BOOL=ON)
|
||||
endif()
|
||||
# collect all HYPRE_ENABLE variables and pass them to hypre, assuming they are BOOL.
|
||||
get_cmake_property(all_vars VARIABLES)
|
||||
foreach(var ${all_vars})
|
||||
@@ -98,6 +95,7 @@ if (MFEM_FETCH_HYPRE OR MFEM_FETCH_TPLS)
|
||||
UPDATE_DISCONNECTED TRUE
|
||||
SOURCE_SUBDIR src
|
||||
PREFIX ${HYPRE_INSTALL}
|
||||
BUILD_COMMAND ${CMAKE_COMMAND} --build . -- -j${CMAKE_BUILD_PARALLEL_LEVEL}
|
||||
CMAKE_CACHE_ARGS -DCMAKE_INSTALL_PREFIX:PATH=${HYPRE_INSTALL} -DCMAKE_INSTALL_LIBDIR:PATH=lib ${HYPRE_CMAKE_OPTIONS})
|
||||
file(MAKE_DIRECTORY ${HYPRE_INSTALL}/include)
|
||||
# set imported library target properties
|
||||
|
||||
@@ -19,18 +19,10 @@
|
||||
# - METIS_VERSION_5 (cache variable)
|
||||
|
||||
if (MFEM_FETCH_METIS OR MFEM_FETCH_TPLS)
|
||||
enable_language(C)
|
||||
set(METIS_FETCH_VERSION 4.0.3)
|
||||
add_library(METIS STATIC IMPORTED)
|
||||
# set options (technically flags because METIS does not use cmake)
|
||||
set(METIS_FLAGS "-Wno-implicit-int -Wno-incompatible-pointer-types")
|
||||
string(TOUPPER "${CMAKE_BUILD_TYPE}" BUILD_TYPE)
|
||||
set(METIS_FLAGS "${METIS_FLAGS} ${CMAKE_C_FLAGS} ${CMAKE_C_FLAGS_${BUILD_TYPE}}")
|
||||
if (BUILD_SHARED_LIBS)
|
||||
set(METIS_FLAGS "${METIS_FLAGS} -fPIC")
|
||||
endif()
|
||||
# define external project
|
||||
message(STATUS "Will fetch METIS ${METIS_FETCH_VERSION} to be built with ${METIS_FLAGS}")
|
||||
message(STATUS "Will fetch METIS ${METIS_FETCH_VERSION} to be built with default options")
|
||||
set(PREFIX ${CMAKE_BINARY_DIR}/fetch/metis)
|
||||
include(ExternalProject)
|
||||
ExternalProject_Add(metis
|
||||
@@ -40,7 +32,7 @@ if (MFEM_FETCH_METIS OR MFEM_FETCH_TPLS)
|
||||
UPDATE_DISCONNECTED TRUE
|
||||
PREFIX ${PREFIX}
|
||||
CONFIGURE_COMMAND tar -xzf ../metis/metis-${METIS_FETCH_VERSION}-mac.tgz --strip=1
|
||||
BUILD_COMMAND $(MAKE) clean && $(MAKE) "OPTFLAGS=${METIS_FLAGS}"
|
||||
BUILD_COMMAND $(MAKE) COPTIONS=-Wno-incompatible-pointer-types
|
||||
INSTALL_COMMAND mkdir -p ${PREFIX}/lib && cp libmetis.a ${PREFIX}/lib/)
|
||||
# set imported library target properties
|
||||
add_dependencies(METIS metis)
|
||||
|
||||
@@ -22,15 +22,15 @@ include(MfemCmakeUtilities)
|
||||
mfem_find_package(SuiteSparse SuiteSparse SuiteSparse_DIR "" "" "" ""
|
||||
"Paths to headers required by SuiteSparse."
|
||||
"Libraries required by SuiteSparse."
|
||||
ADD_COMPONENT "UMFPACK" "include;include/suitesparse;suitesparse" umfpack.h "lib" umfpack
|
||||
ADD_COMPONENT "KLU" "include;include/suitesparse;suitesparse" klu.h "lib" klu
|
||||
ADD_COMPONENT "AMD" "include;include/suitesparse;suitesparse" amd.h "lib" amd
|
||||
ADD_COMPONENT "BTF" "include;include/suitesparse;suitesparse" btf.h "lib" btf
|
||||
ADD_COMPONENT "CHOLMOD" "include;include/suitesparse;suitesparse" cholmod.h "lib" cholmod
|
||||
ADD_COMPONENT "COLAMD" "include;include/suitesparse;suitesparse" colamd.h "lib" colamd
|
||||
ADD_COMPONENT "CAMD" "include;include/suitesparse;suitesparse" camd.h "lib" camd
|
||||
ADD_COMPONENT "CCOLAMD" "include;include/suitesparse;suitesparse" ccolamd.h "lib" ccolamd
|
||||
ADD_COMPONENT "config" "include;include/suitesparse;suitesparse" SuiteSparse_config.h "lib"
|
||||
ADD_COMPONENT "UMFPACK" "include;suitesparse" umfpack.h "lib" umfpack
|
||||
ADD_COMPONENT "KLU" "include;suitesparse" klu.h "lib" klu
|
||||
ADD_COMPONENT "AMD" "include;suitesparse" amd.h "lib" amd
|
||||
ADD_COMPONENT "BTF" "include;suitesparse" btf.h "lib" btf
|
||||
ADD_COMPONENT "CHOLMOD" "include;suitesparse" cholmod.h "lib" cholmod
|
||||
ADD_COMPONENT "COLAMD" "include;suitesparse" colamd.h "lib" colamd
|
||||
ADD_COMPONENT "CAMD" "include;suitesparse" camd.h "lib" camd
|
||||
ADD_COMPONENT "CCOLAMD" "include;suitesparse" ccolamd.h "lib" ccolamd
|
||||
ADD_COMPONENT "config" "include;suitesparse" SuiteSparse_config.h "lib"
|
||||
suitesparseconfig)
|
||||
|
||||
if (SuiteSparse_FOUND AND METIS_VERSION_5)
|
||||
|
||||
@@ -14,12 +14,12 @@
|
||||
# - UMPIRE_LIBRARIES
|
||||
# - UMPIRE_INCLUDE_DIRS
|
||||
|
||||
if (NOT umpire_ROOT AND UMPIRE_DIR)
|
||||
set(umpire_ROOT ${UMPIRE_DIR})
|
||||
if (NOT umpire_DIR AND UMPIRE_DIR)
|
||||
set(umpire_DIR ${UMPIRE_DIR}/lib/cmake/umpire)
|
||||
endif()
|
||||
message(STATUS "Looking for UMPIRE ...")
|
||||
message(STATUS " in UMPIRE_DIR = ${UMPIRE_DIR}")
|
||||
message(STATUS " umpire_ROOT = ${umpire_ROOT}")
|
||||
message(STATUS " umpire_DIR = ${umpire_DIR}")
|
||||
find_package(umpire CONFIG)
|
||||
set(UMPIRE_FOUND ${umpire_FOUND})
|
||||
set(UMPIRE_LIBRARIES "umpire")
|
||||
|
||||
@@ -701,6 +701,7 @@ endfunction(mfem_find_library)
|
||||
# Extract compile and link options needed by the given target.
|
||||
#
|
||||
function(mfem_get_target_options Target CompileOptsVar LinkOptsVar)
|
||||
|
||||
if (NOT TARGET ${Target})
|
||||
return()
|
||||
endif()
|
||||
@@ -798,12 +799,7 @@ function(mfem_get_target_options Target CompileOptsVar LinkOptsVar)
|
||||
# message(STATUS "Lib = ${Lib}")
|
||||
# Filter-out generator expressions
|
||||
if (NOT ("${Lib}" MATCHES "^\\$"))
|
||||
if(NOT ("${Lib}" STREQUAL "dl"))
|
||||
list(APPEND LinkOpts "${Lib}")
|
||||
else()
|
||||
# for some reason libdl doesn't include the "-l"
|
||||
list(APPEND LinkOpts "-ldl")
|
||||
endif()
|
||||
list(APPEND LinkOpts "${Lib}")
|
||||
endif()
|
||||
else()
|
||||
mfem_get_target_options(${Lib} COpts LOpts)
|
||||
@@ -892,18 +888,9 @@ function(mfem_export_mk_files)
|
||||
set(${var} NO)
|
||||
endif()
|
||||
endforeach()
|
||||
if (MFEM_USE_CUDA AND MFEM_EXPORT_GPU_CONFIG)
|
||||
set(MFEM_CXX ${CMAKE_CUDA_COMPILER})
|
||||
if(MFEM_CUDA_COMPILER_IS_NVCC)
|
||||
set(MFEM_HOST_CXX ${CMAKE_CUDA_HOST_COMPILER})
|
||||
else()
|
||||
set(MFEM_HOST_CXX ${CMAKE_CXX_COMPILER})
|
||||
endif()
|
||||
else()
|
||||
# mfem doesn't use enable_language(HIP)
|
||||
set(MFEM_CXX ${CMAKE_CXX_COMPILER})
|
||||
set(MFEM_HOST_CXX ${CMAKE_CXX_COMPILER})
|
||||
endif()
|
||||
# TODO: Add support for MFEM_USE_CUDA=YES
|
||||
set(MFEM_CXX ${CMAKE_CXX_COMPILER})
|
||||
set(MFEM_HOST_CXX ${MFEM_CXX})
|
||||
set(MFEM_CPPFLAGS "")
|
||||
get_target_property(cxx_std mfem CXX_STANDARD)
|
||||
# For now, we ignore the setting of the CXX_EXTENSIONS property. If this
|
||||
@@ -913,50 +900,6 @@ function(mfem_export_mk_files)
|
||||
string(STRIP
|
||||
"${cxx_std_flag} ${CMAKE_CXX_FLAGS_${BUILD_TYPE}} ${CMAKE_CXX_FLAGS}"
|
||||
MFEM_CXXFLAGS)
|
||||
if(MFEM_EXPORT_GPU_CONFIG)
|
||||
if (MFEM_USE_CUDA)
|
||||
set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} ${CMAKE_CUDA_FLAGS}")
|
||||
if (MFEM_CUDA_COMPILER_IS_NVCC)
|
||||
set(MFEM_CXXFLAGS "-x=cu ${MFEM_CXXFLAGS} -ccbin ${CMAKE_CXX_COMPILER} --forward-unknown-to-host-compiler")
|
||||
# The following intentionally hides CUDA deprecation warnings
|
||||
foreach(ENTRY IN LISTS CUDAToolkit_INCLUDE_DIRS)
|
||||
set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -isystem ${ENTRY}")
|
||||
endforeach()
|
||||
if (CMAKE_VERSION VERSION_GREATER_EQUAL 3.18.0)
|
||||
# architecture flags not part of CMAKE_CUDA_FLAGS
|
||||
if ("all" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
|
||||
OR "native" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
|
||||
OR "all-major" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}")
|
||||
set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -arch=${CMAKE_CUDA_ARCHITECTURES}")
|
||||
else()
|
||||
foreach (ENTRY IN LISTS CMAKE_CUDA_ARCHITECTURES)
|
||||
set(MFEM_CXXFLAGS
|
||||
"${MFEM_CXXFLAGS} -gencode arch=compute_${ENTRY},code=sm_${ENTRY}")
|
||||
endforeach()
|
||||
endif()
|
||||
endif()
|
||||
else()
|
||||
set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -xcuda --cuda-path=${CUDAToolkit_LIBRARY_ROOT}")
|
||||
if (CMAKE_VERSION VERSION_GREATER_EQUAL 3.18.0)
|
||||
# architecture flags not part of CMAKE_CUDA_FLAGS
|
||||
if ("all" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
|
||||
OR "native" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
|
||||
OR "all-major" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}")
|
||||
# TODO: not supported
|
||||
else()
|
||||
foreach(ENTRY IN LISTS CMAKE_CUDA_ARCHITECTURES)
|
||||
set(MFEM_CXXFLAGS "-cuda-gpu-arch=sm_${ENTRY} ${MFEM_CXXFLAGS}")
|
||||
endforeach()
|
||||
endif()
|
||||
endif()
|
||||
endif()
|
||||
elseif (MFEM_USE_HIP)
|
||||
set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -xhip")
|
||||
foreach(ENTRY IN LISTS CMAKE_HIP_ARCHITECTURES)
|
||||
set(MFEM_CXXFLAGS "--offload-arch=${ENTRY} ${MFEM_CXXFLAGS}")
|
||||
endforeach()
|
||||
endif()
|
||||
endif()
|
||||
set(MFEM_TPLFLAGS "")
|
||||
foreach(dir ${TPL_INCLUDE_DIRS})
|
||||
set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} -I${dir}")
|
||||
@@ -987,9 +930,6 @@ function(mfem_export_mk_files)
|
||||
set(MFEM_SHARED NO)
|
||||
set(MFEM_STATIC YES)
|
||||
endif()
|
||||
if (MFEM_USE_CUDA)
|
||||
set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} -lcudart")
|
||||
endif()
|
||||
set(MFEM_BUILD_TAG "${CMAKE_SYSTEM}")
|
||||
set(MFEM_PREFIX "${CMAKE_INSTALL_PREFIX}")
|
||||
# For the next 4 variables, these are the values for the build-tree version of
|
||||
@@ -998,15 +938,8 @@ function(mfem_export_mk_files)
|
||||
set(MFEM_LIB_DIR "${PROJECT_BINARY_DIR}")
|
||||
set(MFEM_TEST_MK "${PROJECT_SOURCE_DIR}/config/test.mk")
|
||||
set(MFEM_CONFIG_EXTRA "MFEM_BUILD_DIR ?= ${PROJECT_BINARY_DIR}")
|
||||
if (MFEM_USE_CUDA AND MFEM_EXPORT_GPU_CONFIG)
|
||||
if (MFEM_CUDA_COMPILER_IS_NVCC)
|
||||
set(MFEM_XLINKER "-Xlinker=")
|
||||
else()
|
||||
set(MFEM_XLINKER "${CMAKE_CUDA_LINKER_WRAPPER_FLAG}")
|
||||
endif()
|
||||
else()
|
||||
set(MFEM_XLINKER "${CMAKE_CXX_LINKER_WRAPPER_FLAG}")
|
||||
endif()
|
||||
# TODO: CUDA/HIP support:
|
||||
set(MFEM_XLINKER "${CMAKE_CXX_LINKER_WRAPPER_FLAG}")
|
||||
set(MFEM_MPIEXEC ${MPIEXEC})
|
||||
if (NOT MFEM_MPIEXEC)
|
||||
set(MFEM_MPIEXEC "mpirun")
|
||||
@@ -1054,21 +987,16 @@ function(mfem_export_mk_files)
|
||||
# handle interfaces (e.g., SCOREC::apf)
|
||||
if ("${lib}" MATCHES "SCOREC::.*" OR "${lib}" MATCHES "Ginkgo::.*" OR "${lib}" MATCHES "ParMoonolith::.*")
|
||||
elseif (TARGET "${lib}")
|
||||
mfem_get_target_options(${lib} CompileOpts2 LinkOpts2)
|
||||
# remove generator expressions
|
||||
string(GENEX_STRIP "${CompileOpts2}" CompileOpts)
|
||||
string(GENEX_STRIP "${LinkOpts2}" LinkOpts)
|
||||
mfem_get_target_options(${lib} CompileOpts LinkOpts)
|
||||
# Removing duplicates may lead to issues:
|
||||
# list(REMOVE_DUPLICATES CompileOpts)
|
||||
# list(REMOVE_DUPLICATES LinkOpts)
|
||||
# message(WARNING "${lib}[LinkOpts]: ${LinkOpts}")
|
||||
# message(WARNING "${lib}[CompileOpts]: ${CompileOpts}")
|
||||
foreach(LOpt IN LISTS LinkOpts)
|
||||
set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${LOpt}")
|
||||
endforeach()
|
||||
foreach(COpt IN LISTS CompileOpts)
|
||||
set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} ${COpt}")
|
||||
endforeach()
|
||||
string(REPLACE ";" " " COpts "${CompileOpts}")
|
||||
string(REPLACE ";" " " LOpts "${LinkOpts}")
|
||||
# message(STATUS "${lib}[COpts]: '${COpts}'")
|
||||
# message(STATUS "${lib}[LOpts]: '${LOpts}'")
|
||||
set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} ${COpts}")
|
||||
set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${LOpts}")
|
||||
# message(FATAL_ERROR "***** interface lib found ... exiting *****")
|
||||
# handle static and shared libs
|
||||
elseif ("${suffix}" STREQUAL "${CMAKE_SHARED_LIBRARY_SUFFIX}")
|
||||
@@ -1076,7 +1004,7 @@ function(mfem_export_mk_files)
|
||||
get_filename_component(fullLibName ${lib} NAME_WE)
|
||||
string(REGEX REPLACE "^lib" "" libname ${fullLibName})
|
||||
set(MFEM_EXT_LIBS
|
||||
"${MFEM_EXT_LIBS} ${shared_link_flag}${dir} -L${dir} -l${libname}")
|
||||
"${MFEM_EXT_LIBS} ${shared_link_flag}${dir} -L${dir} -l${libname}")
|
||||
else()
|
||||
set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${lib}")
|
||||
endif()
|
||||
@@ -1085,7 +1013,7 @@ function(mfem_export_mk_files)
|
||||
# Create the build-tree version of 'config.mk'
|
||||
configure_file(
|
||||
"${PROJECT_SOURCE_DIR}/config/config.mk.in"
|
||||
"${PROJECT_BINARY_DIR}/config/config.mk" @ONLY)
|
||||
"${PROJECT_BINARY_DIR}/config/config.mk")
|
||||
# Copy 'test.mk' from the source-tree to the build-tree
|
||||
configure_file(
|
||||
"${PROJECT_SOURCE_DIR}/config/test.mk"
|
||||
@@ -1103,7 +1031,7 @@ function(mfem_export_mk_files)
|
||||
# Create the install-tree version of 'config.mk'
|
||||
configure_file(
|
||||
"${PROJECT_SOURCE_DIR}/config/config.mk.in"
|
||||
"${PROJECT_BINARY_DIR}/config/config-install.mk" @ONLY)
|
||||
"${PROJECT_BINARY_DIR}/config/config-install.mk")
|
||||
|
||||
# Install rules for 'config.mk' and 'test.mk'
|
||||
install(FILES ${PROJECT_SOURCE_DIR}/config/test.mk
|
||||
|
||||
@@ -157,10 +157,4 @@ constexpr real_t operator""_r(unsigned long long v)
|
||||
#endif
|
||||
#endif // MFEM_USE_MPI not defined
|
||||
|
||||
#ifndef MFEM_USE_CUDA
|
||||
#ifdef MFEM_USE_CUDSS
|
||||
#error Building with cuDSS (MFEM_USE_CUDSS=YES) requires CUDA (MFEM_USE_CUDA=YES)
|
||||
#endif
|
||||
#endif // MFEM_USE_CUDSS not defined
|
||||
|
||||
#endif // MFEM_CONFIG_HPP
|
||||
|
||||
@@ -108,15 +108,6 @@
|
||||
// Enable MFEM functionality based on the STRUMPACK library.
|
||||
// #define MFEM_USE_STRUMPACK
|
||||
|
||||
// Enable MFEM functionality based on the cuDSS library.
|
||||
// #define MFEM_USE_CUDSS
|
||||
|
||||
// CUDSS communication layer library path
|
||||
// #define MFEM_CUDSS_COMM_LIB "@MFEM_CUDSS_COMM_LIB@"
|
||||
|
||||
// CUDSS threading layer library path
|
||||
// #define MFEM_CUDSS_THREADING_LIB "@MFEM_CUDSS_THREADING_LIB@"
|
||||
|
||||
// Enable MFEM features based on the Ginkgo library.
|
||||
// #define MFEM_USE_GINKGO
|
||||
|
||||
|
||||
@@ -36,9 +36,6 @@ MFEM_USE_SUPERLU = @MFEM_USE_SUPERLU@
|
||||
MFEM_USE_SUPERLU5 = @MFEM_USE_SUPERLU5@
|
||||
MFEM_USE_MUMPS = @MFEM_USE_MUMPS@
|
||||
MFEM_USE_STRUMPACK = @MFEM_USE_STRUMPACK@
|
||||
MFEM_USE_CUDSS = @MFEM_USE_CUDSS@
|
||||
MFEM_CUDSS_COMM_LIB = @MFEM_CUDSS_COMM_LIB@
|
||||
MFEM_CUDSS_THREADING_LIB = @MFEM_CUDSS_THREADING_LIB@
|
||||
MFEM_USE_GINKGO = @MFEM_USE_GINKGO@
|
||||
MFEM_USE_AMGX = @MFEM_USE_AMGX@
|
||||
MFEM_USE_MAGMA = @MFEM_USE_MAGMA@
|
||||
|
||||
@@ -38,7 +38,6 @@ option(MFEM_USE_SUPERLU "Enable SuperLU_DIST usage" OFF)
|
||||
option(MFEM_USE_SUPERLU5 "Use the old SuperLU_DIST 5.1 version" OFF)
|
||||
option(MFEM_USE_MUMPS "Enable MUMPS usage" OFF)
|
||||
option(MFEM_USE_STRUMPACK "Enable STRUMPACK usage" OFF)
|
||||
option(MFEM_USE_CUDSS "Enable cuDSS usage" OFF)
|
||||
option(MFEM_USE_GINKGO "Enable Ginkgo usage" OFF)
|
||||
option(MFEM_USE_AMGX "Enable AmgX usage" OFF)
|
||||
option(MFEM_USE_MAGMA "Enable MAGMA usage" OFF)
|
||||
|
||||
+4
-49
@@ -27,10 +27,7 @@ MPICXX = mpicxx
|
||||
|
||||
BASE_FLAGS = -std=c++17
|
||||
OPTIM_FLAGS = -O3 $(BASE_FLAGS)
|
||||
|
||||
# The variable WARNING_FLAGS depends on which compiler is used, and is defined
|
||||
# later in this file.
|
||||
DEBUG_FLAGS = $(strip -g $(addprefix $(XCOMPILER),$(WARNING_FLAGS)) $(BASE_FLAGS))
|
||||
DEBUG_FLAGS = -g $(XCOMPILER)-Wall $(BASE_FLAGS)
|
||||
|
||||
# Prefixes for passing flags to the compiler and linker when using CXX or MPICXX
|
||||
CXX_XCOMPILER =
|
||||
@@ -49,10 +46,6 @@ SHARED = NO
|
||||
#
|
||||
# If you set MFEM_USE_ENZYME=YES, must use CUDA_CXX=clang++
|
||||
CUDA_CXX = nvcc
|
||||
# CUDA compute capability used during compilation, e.g. sm_60. Multiple
|
||||
# architectures can be requested as a comma-separated list, e.g. sm_70,sm_80.
|
||||
# A single value may also be one of the nvcc special values "all",
|
||||
# "all-major", or "native".
|
||||
CUDA_ARCH = sm_60
|
||||
# Base CUDA install directory, only needed if building with clang+cuda:
|
||||
# The default setting is:
|
||||
@@ -61,23 +54,11 @@ CUDA_ARCH = sm_60
|
||||
# 3. Use /usr/local/cuda
|
||||
CUDA_DIR = $(or $(CUDA_HOME),$(patsubst %/,%,$(dir \
|
||||
$(patsubst %/,%,$(dir $(shell command -v nvcc))))),/usr/local/cuda)
|
||||
# Derive nvcc/clang architecture flags from CUDA_ARCH. A comma-separated list
|
||||
# expands into one -gencode / --cuda-gpu-arch flag per architecture; otherwise
|
||||
# use the -arch / --cuda-gpu-arch shorthand.
|
||||
MFEM_COMMA := ,
|
||||
CUDA_ARCH_NUMS = $(patsubst sm_%,%,$(subst $(MFEM_COMMA), ,$(CUDA_ARCH)))
|
||||
NVCC_ARCH_FLAGS = $(strip $(if $(findstring $(MFEM_COMMA),$(CUDA_ARCH)),\
|
||||
$(foreach arch,$(CUDA_ARCH_NUMS),\
|
||||
-gencode arch=compute_$(arch)$(MFEM_COMMA)code=sm_$(arch)),\
|
||||
-arch=$(CUDA_ARCH)))
|
||||
CLANG_ARCH_FLAGS = $(strip $(if $(findstring $(MFEM_COMMA),$(CUDA_ARCH)),\
|
||||
$(foreach arch,$(CUDA_ARCH_NUMS),--cuda-gpu-arch=sm_$(arch)),\
|
||||
--cuda-gpu-arch=$(CUDA_ARCH)))
|
||||
# flags for clang+cuda
|
||||
CLANG_CUDA_FLAGS = -xcuda --cuda-path=$(CUDA_DIR) $(CLANG_ARCH_FLAGS)
|
||||
CLANG_CUDA_FLAGS = -xcuda --cuda-path=$(CUDA_DIR) --cuda-gpu-arch=$(CUDA_ARCH)
|
||||
# flags for nvcc
|
||||
NVCC_FLAGS = -x=cu --expt-extended-lambda --expt-relaxed-constexpr \
|
||||
$(NVCC_ARCH_FLAGS) -isystem "$(CUDA_DIR)/include"
|
||||
-arch=$(CUDA_ARCH) -isystem "$(CUDA_DIR)/include"
|
||||
# Prefixes for passing flags to the host compiler and linker when using
|
||||
# CUDA_CXX=nvcc
|
||||
CUDA_XCOMPILER = -Xcompiler=
|
||||
@@ -172,7 +153,6 @@ MFEM_USE_SUPERLU = NO
|
||||
MFEM_USE_SUPERLU5 = NO
|
||||
MFEM_USE_MUMPS = NO
|
||||
MFEM_USE_STRUMPACK = NO
|
||||
MFEM_USE_CUDSS = NO
|
||||
MFEM_USE_GINKGO = NO
|
||||
MFEM_USE_AMGX = NO
|
||||
MFEM_USE_MAGMA = NO
|
||||
@@ -388,19 +368,6 @@ STRUMPACK_OPT = -I$(STRUMPACK_DIR)/include $(SCOTCH_OPT)
|
||||
STRUMPACK_LIB = -L$(STRUMPACK_DIR)/lib -lstrumpack $(MPI_FORTRAN_LIB)\
|
||||
$(SCOTCH_LIB) $(SCALAPACK_LIB)
|
||||
|
||||
# CUDSS library configuration
|
||||
CUDSS_DIR = @MFEM_DIR@/../cudss
|
||||
CUDSS_INCLUDE_DIR = $(CUDSS_DIR)/include
|
||||
CUDSS_LIBRARY_DIR = $(CUDSS_DIR)/lib
|
||||
CUDSS_OPT = -I$(CUDSS_INCLUDE_DIR)
|
||||
CUDSS_LIB = \
|
||||
$(XLINKER)-rpath,$(CUDSS_LIBRARY_DIR) -L$(CUDSS_LIBRARY_DIR) -lcudss
|
||||
# The cuDSS communication and threading libraries.
|
||||
MFEM_CUDSS_COMM_LIB = $(abspath $(wildcard $(or $(CUDSS_COMM_LIB),\
|
||||
$(subst @MFEM_DIR@,$(MFEM_DIR), $(CUDSS_LIBRARY_DIR)/libcudss_commlayer_openmpi.so))))
|
||||
MFEM_CUDSS_THREADING_LIB = $(abspath $(wildcard $(or $(CUDSS_THREADING_LIB),\
|
||||
$(subst @MFEM_DIR@,$(MFEM_DIR),$(CUDSS_LIBRARY_DIR)/libcudss_mtlayer_gomp.so))))
|
||||
|
||||
# Ginkgo library configuration
|
||||
GINKGO_DIR = @MFEM_DIR@/../ginkgo/install
|
||||
GINKGO_SEARCH_DIR = $(subst @MFEM_DIR@,$(MFEM_DIR),$(GINKGO_DIR))
|
||||
@@ -654,7 +621,7 @@ PARELAG_LIB = -L$(PARELAG_DIR)/build/src -lParELAG
|
||||
AXOM_DIR = @MFEM_DIR@/../axom
|
||||
TRIBOL_DIR = @MFEM_DIR@/../tribol
|
||||
TRIBOL_OPT = -I$(TRIBOL_DIR)/include -I$(AXOM_DIR)/include
|
||||
TRIBOL_LIB = -L$(TRIBOL_DIR)/lib -ltribol -ltribol_shared -lredecomp -L$(AXOM_DIR)/lib -laxom_mint\
|
||||
TRIBOL_LIB = -L$(TRIBOL_DIR)/lib -ltribol -lredecomp -L$(AXOM_DIR)/lib -laxom_mint\
|
||||
-laxom_slam -laxom_slic -laxom_core
|
||||
|
||||
# Enzyme configuration
|
||||
@@ -678,15 +645,3 @@ VERBOSE = NO
|
||||
|
||||
# Optional build tag
|
||||
MFEM_BUILD_TAG = $(shell uname -snm)
|
||||
|
||||
# Enable -pedantic flag only for gcc or clang. nvcc complains with -pedantic
|
||||
# because of line directives.
|
||||
PEDANTIC_FLAG = $(if \
|
||||
$(findstring NVIDIA,$(shell $(MFEM_CXX) --version 2>&1)),, \
|
||||
$(if $(or \
|
||||
$(findstring gcc version,$(shell $(MFEM_CXX) -v 2>&1)), \
|
||||
$(findstring clang version,$(shell $(MFEM_CXX) -v 2>&1))),-pedantic,))
|
||||
# Enable shadow warnings for clang only; GCC's -Wshadow flags more.
|
||||
SHADOW_WARNING_FLAG = $(if $(findstring clang,\
|
||||
$(shell $(MFEM_HOST_CXX) --version 2>/dev/null)),-Wshadow,)
|
||||
WARNING_FLAGS = $(PEDANTIC_FLAG) -Wall $(SHADOW_WARNING_FLAG)
|
||||
|
||||
@@ -39,8 +39,3 @@ when a picture was added for documentation.
|
||||
If that is the case, make sure the failure is indeed justified, and rerun the
|
||||
push command with the `--no-verify` option. This will skip the hooks, allowing
|
||||
you to push those changes.
|
||||
|
||||
The `branch-history` check is run automatically through GitHub Actions. If a
|
||||
branch is known to have a large number of changes that are legitimate, the
|
||||
check can be overridden by setting the label 'branch-history-override' on the
|
||||
pull request.
|
||||
|
||||
@@ -1,131 +0,0 @@
|
||||
// Define the cube sizes
|
||||
L_outer = 1.0;
|
||||
L_inner = 0.5;
|
||||
|
||||
// Set mesh size and algorithm
|
||||
mesh_size = 0.4;
|
||||
Mesh.Algorithm3D = 1; // Delaunay algorithm for 3D mesh
|
||||
Mesh.CharacteristicLengthFactor = 1.0;
|
||||
Mesh.MshFileVersion = 2.2;
|
||||
|
||||
// Define center point for concentric cubes
|
||||
cx = 0.5;
|
||||
cy = 0.5;
|
||||
cz = 0.5;
|
||||
|
||||
// Define the points (vertices of the outer cube)
|
||||
Point(1) = {cx-L_outer/2, cy-L_outer/2, cz-L_outer/2, mesh_size};
|
||||
Point(2) = {cx+L_outer/2, cy-L_outer/2, cz-L_outer/2, mesh_size};
|
||||
Point(3) = {cx+L_outer/2, cy+L_outer/2, cz-L_outer/2, mesh_size};
|
||||
Point(4) = {cx-L_outer/2, cy+L_outer/2, cz-L_outer/2, mesh_size};
|
||||
Point(5) = {cx-L_outer/2, cy-L_outer/2, cz+L_outer/2, mesh_size};
|
||||
Point(6) = {cx+L_outer/2, cy-L_outer/2, cz+L_outer/2, mesh_size};
|
||||
Point(7) = {cx+L_outer/2, cy+L_outer/2, cz+L_outer/2, mesh_size};
|
||||
Point(8) = {cx-L_outer/2, cy+L_outer/2, cz+L_outer/2, mesh_size};
|
||||
|
||||
// Define the points (vertices of the inner cube)
|
||||
Point(9) = {cx-L_inner/2, cy-L_inner/2, cz-L_inner/2, mesh_size};
|
||||
Point(10) = {cx+L_inner/2, cy-L_inner/2, cz-L_inner/2, mesh_size};
|
||||
Point(11) = {cx+L_inner/2, cy+L_inner/2, cz-L_inner/2, mesh_size};
|
||||
Point(12) = {cx-L_inner/2, cy+L_inner/2, cz-L_inner/2, mesh_size};
|
||||
Point(13) = {cx-L_inner/2, cy-L_inner/2, cz+L_inner/2, mesh_size};
|
||||
Point(14) = {cx+L_inner/2, cy-L_inner/2, cz+L_inner/2, mesh_size};
|
||||
Point(15) = {cx+L_inner/2, cy+L_inner/2, cz+L_inner/2, mesh_size};
|
||||
Point(16) = {cx-L_inner/2, cy+L_inner/2, cz+L_inner/2, mesh_size};
|
||||
|
||||
// Define the lines (edges of the outer cube)
|
||||
Line(1) = {1, 2};
|
||||
Line(2) = {2, 3};
|
||||
Line(3) = {3, 4};
|
||||
Line(4) = {4, 1};
|
||||
Line(5) = {5, 6};
|
||||
Line(6) = {6, 7};
|
||||
Line(7) = {7, 8};
|
||||
Line(8) = {8, 5};
|
||||
Line(9) = {1, 5};
|
||||
Line(10) = {2, 6};
|
||||
Line(11) = {3, 7};
|
||||
Line(12) = {4, 8};
|
||||
|
||||
// Define the lines (edges of the inner cube)
|
||||
Line(13) = {9, 10};
|
||||
Line(14) = {10, 11};
|
||||
Line(15) = {11, 12};
|
||||
Line(16) = {12, 9};
|
||||
Line(17) = {13, 14};
|
||||
Line(18) = {14, 15};
|
||||
Line(19) = {15, 16};
|
||||
Line(20) = {16, 13};
|
||||
Line(21) = {9, 13};
|
||||
Line(22) = {10, 14};
|
||||
Line(23) = {11, 15};
|
||||
Line(24) = {12, 16};
|
||||
|
||||
// Define the surfaces (faces of the outer cube)
|
||||
Line Loop(1) = {1, 2, 3, 4};
|
||||
Plane Surface(1) = {1};
|
||||
|
||||
Line Loop(2) = {5, 6, 7, 8};
|
||||
Plane Surface(2) = {2};
|
||||
|
||||
Line Loop(3) = {9, 5, -10, -1};
|
||||
Plane Surface(3) = {3};
|
||||
|
||||
Line Loop(4) = {10, 6, -11, -2};
|
||||
Plane Surface(4) = {4};
|
||||
|
||||
Line Loop(5) = {11, 7, -12, -3};
|
||||
Plane Surface(5) = {5};
|
||||
|
||||
Line Loop(6) = {12, 8, -9, -4};
|
||||
Plane Surface(6) = {6};
|
||||
|
||||
// Define the surfaces (faces of the inner cube)
|
||||
Line Loop(7) = {13, 14, 15, 16};
|
||||
Plane Surface(7) = {7};
|
||||
|
||||
Line Loop(8) = {17, 18, 19, 20};
|
||||
Plane Surface(8) = {8};
|
||||
|
||||
Line Loop(9) = {21, 17, -22, -13};
|
||||
Plane Surface(9) = {9};
|
||||
|
||||
Line Loop(10) = {22, 18, -23, -14};
|
||||
Plane Surface(10) = {10};
|
||||
|
||||
Line Loop(11) = {23, 19, -24, -15};
|
||||
Plane Surface(11) = {11};
|
||||
|
||||
Line Loop(12) = {24, 20, -21, -16};
|
||||
Plane Surface(12) = {12};
|
||||
|
||||
// Define the volumes
|
||||
Surface Loop(1) = {1, 2, 3, 4, 5, 6};
|
||||
Surface Loop(2) = {7, 8, 9, 10, 11, 12};
|
||||
Volume(1) = {1, 2}; // Outer volume with inner hole
|
||||
Volume(2) = {2}; // Inner volume
|
||||
|
||||
// Assign physical groups
|
||||
Physical Volume(1) = {1}; // Outer volume
|
||||
Physical Volume(2) = {2}; // Inner volume
|
||||
|
||||
// Outer cube surfaces
|
||||
Physical Surface(1) = {1}; // Outer bottom
|
||||
Physical Surface(2) = {2}; // Outer top
|
||||
Physical Surface(3) = {3}; // Outer front
|
||||
Physical Surface(4) = {4}; // Outer right
|
||||
Physical Surface(5) = {5}; // Outer back
|
||||
Physical Surface(6) = {6}; // Outer left
|
||||
|
||||
// Inner cube surfaces
|
||||
Physical Surface(7) = {7}; // Inner bottom (-xy)
|
||||
Physical Surface(8) = {8}; // Inner top (+xy)
|
||||
Physical Surface(9) = {9}; // Inner front (-xz)
|
||||
Physical Surface(10) = {10}; // Inner right (+yz)
|
||||
Physical Surface(11) = {11}; // Inner back (+xz)
|
||||
Physical Surface(12) = {12}; // Inner left (-yz)
|
||||
|
||||
// Mesh control
|
||||
Mesh.OptimizeNetgen = 1;
|
||||
Mesh.Optimize = 1;
|
||||
Mesh.ElementOrder = 1;
|
||||
@@ -1,907 +0,0 @@
|
||||
$MeshFormat
|
||||
2.2 0 8
|
||||
$EndMeshFormat
|
||||
$Nodes
|
||||
138
|
||||
1 0 0 0
|
||||
2 1 0 0
|
||||
3 1 1 0
|
||||
4 0 1 0
|
||||
5 0 0 1
|
||||
6 1 0 1
|
||||
7 1 1 1
|
||||
8 0 1 1
|
||||
9 0.25 0.25 0.25
|
||||
10 0.75 0.25 0.25
|
||||
11 0.75 0.75 0.25
|
||||
12 0.25 0.75 0.25
|
||||
13 0.25 0.25 0.75
|
||||
14 0.75 0.25 0.75
|
||||
15 0.75 0.75 0.75
|
||||
16 0.25 0.75 0.75
|
||||
17 0.3333333333325025 0 0
|
||||
18 0.6666666666657889 0 0
|
||||
19 1 0.3333333333325025 0
|
||||
20 1 0.6666666666657889 0
|
||||
21 0.6666666666675911 1 0
|
||||
22 0.3333333333347203 1 0
|
||||
23 0 0.6666666666675911 0
|
||||
24 0 0.3333333333347203 0
|
||||
25 0.3333333333325025 0 1
|
||||
26 0.6666666666657889 0 1
|
||||
27 1 0.3333333333325025 1
|
||||
28 1 0.6666666666657889 1
|
||||
29 0.6666666666675911 1 1
|
||||
30 0.3333333333347203 1 1
|
||||
31 0 0.6666666666675911 1
|
||||
32 0 0.3333333333347203 1
|
||||
33 0 0 0.3333333333325025
|
||||
34 0 0 0.6666666666657889
|
||||
35 1 0 0.3333333333325025
|
||||
36 1 0 0.6666666666657889
|
||||
37 1 1 0.3333333333325025
|
||||
38 1 1 0.6666666666657889
|
||||
39 0 1 0.3333333333325025
|
||||
40 0 1 0.6666666666657889
|
||||
41 0.5000000000003468 0.25 0.25
|
||||
42 0.75 0.5000000000003468 0.25
|
||||
43 0.5000000000013763 0.75 0.25
|
||||
44 0.25 0.5000000000013763 0.25
|
||||
45 0.5000000000003468 0.25 0.75
|
||||
46 0.75 0.5000000000003468 0.75
|
||||
47 0.5000000000013763 0.75 0.75
|
||||
48 0.25 0.5000000000013763 0.75
|
||||
49 0.25 0.25 0.5000000000003468
|
||||
50 0.75 0.25 0.5000000000003468
|
||||
51 0.75 0.75 0.5000000000003468
|
||||
52 0.25 0.75 0.5000000000003468
|
||||
53 0.7113248654055673 0.4999999999991457 0
|
||||
54 0.2886751345942123 0.5000000000011557 0
|
||||
55 0.5000000000006117 0.7525600817161773 0
|
||||
56 0.4999999999993867 0.2474399182839603 0
|
||||
57 0.2423197548524782 0.7576802451481532 0
|
||||
58 0.757680245147464 0.2423197548520695 0
|
||||
59 0.2423197548507857 0.2423197548513912 0
|
||||
60 0.7576802451491019 0.7576802451486099 0
|
||||
61 0.7113248654055673 0.4999999999991457 1
|
||||
62 0.2886751345942123 0.5000000000011557 1
|
||||
63 0.5000000000006117 0.7525600817161773 1
|
||||
64 0.4999999999993867 0.2474399182839603 1
|
||||
65 0.2423197548524782 0.7576802451481532 1
|
||||
66 0.757680245147464 0.2423197548520695 1
|
||||
67 0.2423197548507857 0.2423197548513912 1
|
||||
68 0.7576802451491019 0.7576802451486099 1
|
||||
69 0.4999999999993203 0 0.301447615129799
|
||||
70 0.4999999999992795 0 0.7028666213189801
|
||||
71 0.7525600817158393 0 0.5007190394076877
|
||||
72 0.2474399182836191 0 0.5007190394076877
|
||||
73 0.7576802451479793 0 0.7576802451479793
|
||||
74 0.2423197548517962 0 0.7576802451477375
|
||||
75 0.7576802451484569 0 0.2423197548510767
|
||||
76 0.2423197548513188 0 0.2423197548513187
|
||||
77 1 0.4999999999993203 0.301447615129799
|
||||
78 1 0.4999999999992795 0.7028666213189801
|
||||
79 1 0.7525600817158394 0.5007190394076877
|
||||
80 1 0.2474399182836191 0.5007190394076877
|
||||
81 1 0.7576802451479794 0.7576802451479794
|
||||
82 1 0.2423197548517962 0.7576802451477376
|
||||
83 1 0.7576802451484569 0.2423197548510768
|
||||
84 1 0.2423197548513188 0.2423197548513188
|
||||
85 0.5000000000008327 1 0.3014476151298047
|
||||
86 0.500000000000961 1 0.7028666213191928
|
||||
87 0.2474399182842484 1 0.5007190394077241
|
||||
88 0.7525600817164384 1 0.5007190394078933
|
||||
89 0.2423197548520873 1 0.7576802451480517
|
||||
90 0.7576802451481496 1 0.2423197548518761
|
||||
91 0.2423197548516099 1 0.2423197548510044
|
||||
92 0.7576802451486874 1 0.7576802451481952
|
||||
93 0 0.5000000000008327 0.3014476151298047
|
||||
94 0 0.500000000000961 0.7028666213191928
|
||||
95 0 0.2474399182842484 0.5007190394077241
|
||||
96 0 0.7525600817164384 0.5007190394078933
|
||||
97 0 0.2423197548520873 0.7576802451480517
|
||||
98 0 0.7576802451481496 0.2423197548518761
|
||||
99 0 0.2423197548516099 0.2423197548510044
|
||||
100 0 0.7576802451486874 0.7576802451481952
|
||||
101 0.3968750000003409 0.603125000000244 0.25
|
||||
102 0.4374999999998713 0.4375000000001287 0.25
|
||||
103 0.5739583333335919 0.5718750000001767 0.25
|
||||
104 0.6093749999999631 0.3906250000003402 0.25
|
||||
105 0.3968750000003409 0.603125000000244 0.75
|
||||
106 0.4374999999998713 0.4375000000001287 0.75
|
||||
107 0.5739583333335919 0.5718750000001767 0.75
|
||||
108 0.6093749999999631 0.3906250000003402 0.75
|
||||
109 0.3806942419826734 0.25 0.3806942419826734
|
||||
110 0.5625000000001735 0.25 0.4375000000000001
|
||||
111 0.4254282069971791 0.25 0.5712615403304835
|
||||
112 0.6093749999998808 0.25 0.6093749999998808
|
||||
113 0.75 0.3806942419826734 0.3806942419826734
|
||||
114 0.75 0.5625000000001735 0.4375000000000001
|
||||
115 0.75 0.4254282069971791 0.5712615403304835
|
||||
116 0.75 0.6093749999998808 0.6093749999998808
|
||||
117 0.3968750000004991 0.75 0.3968750000002804
|
||||
118 0.4375000000000001 0.75 0.5625000000004308
|
||||
119 0.5739583333336153 0.75 0.4281250000000707
|
||||
120 0.6093749999998166 0.75 0.6093749999993661
|
||||
121 0.25 0.3968750000004991 0.3968750000002804
|
||||
122 0.25 0.4375000000000001 0.5625000000004308
|
||||
123 0.25 0.5739583333336153 0.4281250000000707
|
||||
124 0.25 0.6093749999998166 0.6093749999993661
|
||||
125 0.4962939304035875 0.5214350017087855 0.4925553109323813
|
||||
126 0.3432581985549767 0.6471275530923523 0.3554206606168006
|
||||
127 0.6442168181713744 0.5929232373214773 0.3593785632300704
|
||||
128 0.625174517421737 0.3491579444372839 0.3604636129462503
|
||||
129 0.6130544111091688 0.6576364353993367 0.5046720648819553
|
||||
130 0.4281518698369243 0.3632662294430484 0.3548726263205102
|
||||
131 0.3639383531355198 0.3520949250221278 0.4978389662613994
|
||||
132 0.629585530087249 0.3489878162230438 0.5124654846339122
|
||||
133 0.3710853378652663 0.6517586292698121 0.6382643241302075
|
||||
134 0.5917018263727056 0.6522525456211955 0.6390764961119443
|
||||
135 0.3530810314228338 0.4582477062424107 0.6430239639637545
|
||||
136 0.6571010904289998 0.5300774811423468 0.6603970500567977
|
||||
137 0.6484596018596915 0.361399676127967 0.6360267588157177
|
||||
138 0.4782020887035478 0.3534611476388013 0.6141275027013793
|
||||
$EndNodes
|
||||
$Elements
|
||||
760
|
||||
1 2 2 1 1 1 17 59
|
||||
2 2 2 1 1 24 1 59
|
||||
3 2 2 1 1 18 2 58
|
||||
4 2 2 1 1 2 19 58
|
||||
5 2 2 1 1 20 3 60
|
||||
6 2 2 1 1 3 21 60
|
||||
7 2 2 1 1 22 4 57
|
||||
8 2 2 1 1 4 23 57
|
||||
9 2 2 1 1 17 18 56
|
||||
10 2 2 1 1 17 56 59
|
||||
11 2 2 1 1 56 18 58
|
||||
12 2 2 1 1 19 20 53
|
||||
13 2 2 1 1 19 53 58
|
||||
14 2 2 1 1 53 20 60
|
||||
15 2 2 1 1 21 22 55
|
||||
16 2 2 1 1 21 55 60
|
||||
17 2 2 1 1 55 22 57
|
||||
18 2 2 1 1 23 24 54
|
||||
19 2 2 1 1 23 54 57
|
||||
20 2 2 1 1 54 24 59
|
||||
21 2 2 1 1 54 53 55
|
||||
22 2 2 1 1 53 54 56
|
||||
23 2 2 1 1 55 53 60
|
||||
24 2 2 1 1 53 56 58
|
||||
25 2 2 1 1 54 55 57
|
||||
26 2 2 1 1 56 54 59
|
||||
27 2 2 2 2 5 25 67
|
||||
28 2 2 2 2 32 5 67
|
||||
29 2 2 2 2 26 6 66
|
||||
30 2 2 2 2 6 27 66
|
||||
31 2 2 2 2 28 7 68
|
||||
32 2 2 2 2 7 29 68
|
||||
33 2 2 2 2 30 8 65
|
||||
34 2 2 2 2 8 31 65
|
||||
35 2 2 2 2 25 26 64
|
||||
36 2 2 2 2 25 64 67
|
||||
37 2 2 2 2 64 26 66
|
||||
38 2 2 2 2 27 28 61
|
||||
39 2 2 2 2 27 61 66
|
||||
40 2 2 2 2 61 28 68
|
||||
41 2 2 2 2 29 30 63
|
||||
42 2 2 2 2 29 63 68
|
||||
43 2 2 2 2 63 30 65
|
||||
44 2 2 2 2 31 32 62
|
||||
45 2 2 2 2 31 62 65
|
||||
46 2 2 2 2 62 32 67
|
||||
47 2 2 2 2 62 61 63
|
||||
48 2 2 2 2 61 62 64
|
||||
49 2 2 2 2 63 61 68
|
||||
50 2 2 2 2 61 64 66
|
||||
51 2 2 2 2 62 63 65
|
||||
52 2 2 2 2 64 62 67
|
||||
53 2 2 3 3 17 1 76
|
||||
54 2 2 3 3 1 33 76
|
||||
55 2 2 3 3 2 18 75
|
||||
56 2 2 3 3 35 2 75
|
||||
57 2 2 3 3 5 25 74
|
||||
58 2 2 3 3 34 5 74
|
||||
59 2 2 3 3 26 6 73
|
||||
60 2 2 3 3 6 36 73
|
||||
61 2 2 3 3 18 17 69
|
||||
62 2 2 3 3 69 17 76
|
||||
63 2 2 3 3 18 69 75
|
||||
64 2 2 3 3 25 26 70
|
||||
65 2 2 3 3 25 70 74
|
||||
66 2 2 3 3 70 26 73
|
||||
67 2 2 3 3 33 34 72
|
||||
68 2 2 3 3 33 72 76
|
||||
69 2 2 3 3 72 34 74
|
||||
70 2 2 3 3 36 35 71
|
||||
71 2 2 3 3 71 35 75
|
||||
72 2 2 3 3 36 71 73
|
||||
73 2 2 3 3 69 70 71
|
||||
74 2 2 3 3 70 69 72
|
||||
75 2 2 3 3 69 71 75
|
||||
76 2 2 3 3 72 69 76
|
||||
77 2 2 3 3 71 70 73
|
||||
78 2 2 3 3 70 72 74
|
||||
79 2 2 4 4 19 2 84
|
||||
80 2 2 4 4 2 35 84
|
||||
81 2 2 4 4 3 20 83
|
||||
82 2 2 4 4 37 3 83
|
||||
83 2 2 4 4 6 27 82
|
||||
84 2 2 4 4 36 6 82
|
||||
85 2 2 4 4 28 7 81
|
||||
86 2 2 4 4 7 38 81
|
||||
87 2 2 4 4 20 19 77
|
||||
88 2 2 4 4 77 19 84
|
||||
89 2 2 4 4 20 77 83
|
||||
90 2 2 4 4 27 28 78
|
||||
91 2 2 4 4 27 78 82
|
||||
92 2 2 4 4 78 28 81
|
||||
93 2 2 4 4 35 36 80
|
||||
94 2 2 4 4 35 80 84
|
||||
95 2 2 4 4 80 36 82
|
||||
96 2 2 4 4 38 37 79
|
||||
97 2 2 4 4 79 37 83
|
||||
98 2 2 4 4 38 79 81
|
||||
99 2 2 4 4 77 78 79
|
||||
100 2 2 4 4 78 77 80
|
||||
101 2 2 4 4 77 79 83
|
||||
102 2 2 4 4 80 77 84
|
||||
103 2 2 4 4 79 78 81
|
||||
104 2 2 4 4 78 80 82
|
||||
105 2 2 5 5 21 3 90
|
||||
106 2 2 5 5 3 37 90
|
||||
107 2 2 5 5 4 22 91
|
||||
108 2 2 5 5 39 4 91
|
||||
109 2 2 5 5 7 29 92
|
||||
110 2 2 5 5 38 7 92
|
||||
111 2 2 5 5 30 8 89
|
||||
112 2 2 5 5 8 40 89
|
||||
113 2 2 5 5 22 21 85
|
||||
114 2 2 5 5 85 21 90
|
||||
115 2 2 5 5 22 85 91
|
||||
116 2 2 5 5 29 30 86
|
||||
117 2 2 5 5 29 86 92
|
||||
118 2 2 5 5 86 30 89
|
||||
119 2 2 5 5 37 38 88
|
||||
120 2 2 5 5 37 88 90
|
||||
121 2 2 5 5 88 38 92
|
||||
122 2 2 5 5 40 39 87
|
||||
123 2 2 5 5 87 39 91
|
||||
124 2 2 5 5 40 87 89
|
||||
125 2 2 5 5 85 86 87
|
||||
126 2 2 5 5 86 85 88
|
||||
127 2 2 5 5 85 87 91
|
||||
128 2 2 5 5 88 85 90
|
||||
129 2 2 5 5 87 86 89
|
||||
130 2 2 5 5 86 88 92
|
||||
131 2 2 6 6 1 24 99
|
||||
132 2 2 6 6 33 1 99
|
||||
133 2 2 6 6 23 4 98
|
||||
134 2 2 6 6 4 39 98
|
||||
135 2 2 6 6 32 5 97
|
||||
136 2 2 6 6 5 34 97
|
||||
137 2 2 6 6 8 31 100
|
||||
138 2 2 6 6 40 8 100
|
||||
139 2 2 6 6 24 23 93
|
||||
140 2 2 6 6 93 23 98
|
||||
141 2 2 6 6 24 93 99
|
||||
142 2 2 6 6 31 32 94
|
||||
143 2 2 6 6 31 94 100
|
||||
144 2 2 6 6 94 32 97
|
||||
145 2 2 6 6 34 33 95
|
||||
146 2 2 6 6 95 33 99
|
||||
147 2 2 6 6 34 95 97
|
||||
148 2 2 6 6 39 40 96
|
||||
149 2 2 6 6 39 96 98
|
||||
150 2 2 6 6 96 40 100
|
||||
151 2 2 6 6 93 94 95
|
||||
152 2 2 6 6 94 93 96
|
||||
153 2 2 6 6 93 95 99
|
||||
154 2 2 6 6 96 93 98
|
||||
155 2 2 6 6 95 94 97
|
||||
156 2 2 6 6 94 96 100
|
||||
157 2 2 7 7 9 41 102
|
||||
158 2 2 7 7 44 9 102
|
||||
159 2 2 7 7 41 10 104
|
||||
160 2 2 7 7 10 42 104
|
||||
161 2 2 7 7 42 11 103
|
||||
162 2 2 7 7 11 43 103
|
||||
163 2 2 7 7 43 12 101
|
||||
164 2 2 7 7 12 44 101
|
||||
165 2 2 7 7 102 41 104
|
||||
166 2 2 7 7 42 103 104
|
||||
167 2 2 7 7 43 101 103
|
||||
168 2 2 7 7 101 44 102
|
||||
169 2 2 7 7 101 102 103
|
||||
170 2 2 7 7 103 102 104
|
||||
171 2 2 8 8 13 45 106
|
||||
172 2 2 8 8 48 13 106
|
||||
173 2 2 8 8 45 14 108
|
||||
174 2 2 8 8 14 46 108
|
||||
175 2 2 8 8 46 15 107
|
||||
176 2 2 8 8 15 47 107
|
||||
177 2 2 8 8 47 16 105
|
||||
178 2 2 8 8 16 48 105
|
||||
179 2 2 8 8 106 45 108
|
||||
180 2 2 8 8 46 107 108
|
||||
181 2 2 8 8 47 105 107
|
||||
182 2 2 8 8 105 48 106
|
||||
183 2 2 8 8 105 106 107
|
||||
184 2 2 8 8 107 106 108
|
||||
185 2 2 9 9 41 9 109
|
||||
186 2 2 9 9 9 49 109
|
||||
187 2 2 9 9 10 41 110
|
||||
188 2 2 9 9 50 10 110
|
||||
189 2 2 9 9 13 45 111
|
||||
190 2 2 9 9 49 13 111
|
||||
191 2 2 9 9 45 14 112
|
||||
192 2 2 9 9 14 50 112
|
||||
193 2 2 9 9 41 109 110
|
||||
194 2 2 9 9 111 45 112
|
||||
195 2 2 9 9 109 49 111
|
||||
196 2 2 9 9 50 110 112
|
||||
197 2 2 9 9 110 109 111
|
||||
198 2 2 9 9 110 111 112
|
||||
199 2 2 10 10 42 10 113
|
||||
200 2 2 10 10 10 50 113
|
||||
201 2 2 10 10 11 42 114
|
||||
202 2 2 10 10 51 11 114
|
||||
203 2 2 10 10 14 46 115
|
||||
204 2 2 10 10 50 14 115
|
||||
205 2 2 10 10 46 15 116
|
||||
206 2 2 10 10 15 51 116
|
||||
207 2 2 10 10 42 113 114
|
||||
208 2 2 10 10 115 46 116
|
||||
209 2 2 10 10 113 50 115
|
||||
210 2 2 10 10 51 114 116
|
||||
211 2 2 10 10 114 113 115
|
||||
212 2 2 10 10 114 115 116
|
||||
213 2 2 11 11 43 11 119
|
||||
214 2 2 11 11 11 51 119
|
||||
215 2 2 11 11 12 43 117
|
||||
216 2 2 11 11 52 12 117
|
||||
217 2 2 11 11 15 47 120
|
||||
218 2 2 11 11 51 15 120
|
||||
219 2 2 11 11 47 16 118
|
||||
220 2 2 11 11 16 52 118
|
||||
221 2 2 11 11 117 43 119
|
||||
222 2 2 11 11 47 118 120
|
||||
223 2 2 11 11 119 51 120
|
||||
224 2 2 11 11 52 117 118
|
||||
225 2 2 11 11 118 117 119
|
||||
226 2 2 11 11 118 119 120
|
||||
227 2 2 12 12 9 44 121
|
||||
228 2 2 12 12 49 9 121
|
||||
229 2 2 12 12 44 12 123
|
||||
230 2 2 12 12 12 52 123
|
||||
231 2 2 12 12 48 13 122
|
||||
232 2 2 12 12 13 49 122
|
||||
233 2 2 12 12 16 48 124
|
||||
234 2 2 12 12 52 16 124
|
||||
235 2 2 12 12 121 44 123
|
||||
236 2 2 12 12 48 122 124
|
||||
237 2 2 12 12 49 121 122
|
||||
238 2 2 12 12 123 52 124
|
||||
239 2 2 12 12 122 121 123
|
||||
240 2 2 12 12 122 123 124
|
||||
241 4 2 1 1 105 62 106 107
|
||||
242 4 2 1 1 102 54 101 103
|
||||
243 4 2 1 1 118 86 120 119
|
||||
244 4 2 1 1 124 94 123 122
|
||||
245 4 2 1 1 52 39 12 96
|
||||
246 4 2 1 1 52 12 39 87
|
||||
247 4 2 1 1 88 38 15 51
|
||||
248 4 2 1 1 79 15 38 51
|
||||
249 4 2 1 1 80 14 50 36
|
||||
250 4 2 1 1 71 50 14 36
|
||||
251 4 2 1 1 120 88 15 51
|
||||
252 4 2 1 1 116 15 79 51
|
||||
253 4 2 1 1 50 14 112 71
|
||||
254 4 2 1 1 52 117 12 87
|
||||
255 4 2 1 1 111 69 109 110
|
||||
256 4 2 1 1 114 77 115 113
|
||||
257 4 2 1 1 124 123 94 96
|
||||
258 4 2 1 1 120 86 88 119
|
||||
259 4 2 1 1 14 45 64 108
|
||||
260 4 2 1 1 103 54 101 55
|
||||
261 4 2 1 1 62 105 63 107
|
||||
262 4 2 1 1 63 29 15 47
|
||||
263 4 2 1 1 14 45 26 64
|
||||
264 4 2 1 1 51 11 88 37
|
||||
265 4 2 1 1 80 50 10 35
|
||||
266 4 2 1 1 49 33 9 72
|
||||
267 4 2 1 1 71 10 50 35
|
||||
268 4 2 1 1 79 11 51 37
|
||||
269 4 2 1 1 49 9 33 95
|
||||
270 4 2 1 1 12 123 52 96
|
||||
271 4 2 1 1 96 16 52 40
|
||||
272 4 2 1 1 49 13 34 72
|
||||
273 4 2 1 1 87 52 16 40
|
||||
274 4 2 1 1 13 49 34 95
|
||||
275 4 2 1 1 43 101 12 55
|
||||
276 4 2 1 1 43 12 22 55
|
||||
277 4 2 1 1 106 61 108 107
|
||||
278 4 2 1 1 102 103 104 53
|
||||
279 4 2 1 1 50 115 14 80
|
||||
280 4 2 1 1 80 10 50 113
|
||||
281 4 2 1 1 9 109 49 72
|
||||
282 4 2 1 1 47 15 63 107
|
||||
283 4 2 1 1 124 16 52 96
|
||||
284 4 2 1 1 49 121 9 95
|
||||
285 4 2 1 1 15 28 68 46
|
||||
286 4 2 1 1 81 28 15 46
|
||||
287 4 2 1 1 92 15 29 47
|
||||
288 4 2 1 1 27 82 14 46
|
||||
289 4 2 1 1 14 66 27 46
|
||||
290 4 2 1 1 26 45 14 73
|
||||
291 4 2 1 1 78 115 116 114
|
||||
292 4 2 1 1 112 70 111 110
|
||||
293 4 2 1 1 79 11 114 51
|
||||
294 4 2 1 1 71 50 10 110
|
||||
295 4 2 1 1 10 41 104 56
|
||||
296 4 2 1 1 77 80 115 113
|
||||
297 4 2 1 1 69 109 72 111
|
||||
298 4 2 1 1 63 16 30 47
|
||||
299 4 2 1 1 25 45 13 64
|
||||
300 4 2 1 1 52 16 118 87
|
||||
301 4 2 1 1 95 13 49 122
|
||||
302 4 2 1 1 57 12 23 44
|
||||
303 4 2 1 1 119 11 88 51
|
||||
304 4 2 1 1 41 17 9 56
|
||||
305 4 2 1 1 18 41 10 56
|
||||
306 4 2 1 1 21 11 43 55
|
||||
307 4 2 1 1 63 105 16 47
|
||||
308 4 2 1 1 13 45 106 64
|
||||
309 4 2 1 1 9 102 41 56
|
||||
310 4 2 1 1 72 49 13 111
|
||||
311 4 2 1 1 11 103 43 55
|
||||
312 4 2 1 1 70 112 71 110
|
||||
313 4 2 1 1 116 79 78 114
|
||||
314 4 2 1 1 32 13 48 67
|
||||
315 4 2 1 1 16 89 30 47
|
||||
316 4 2 1 1 32 48 13 97
|
||||
317 4 2 1 1 48 16 100 31
|
||||
318 4 2 1 1 121 123 93 122
|
||||
319 4 2 1 1 119 117 118 85
|
||||
320 4 2 1 1 10 19 42 84
|
||||
321 4 2 1 1 17 9 76 41
|
||||
322 4 2 1 1 24 9 59 44
|
||||
323 4 2 1 1 42 19 10 58
|
||||
324 4 2 1 1 10 41 18 75
|
||||
325 4 2 1 1 20 83 11 42
|
||||
326 4 2 1 1 90 11 43 21
|
||||
327 4 2 1 1 53 104 102 56
|
||||
328 4 2 1 1 106 61 64 108
|
||||
329 4 2 1 1 87 118 117 85
|
||||
330 4 2 1 1 95 121 93 122
|
||||
331 4 2 1 1 80 50 115 113
|
||||
332 4 2 1 1 109 49 72 111
|
||||
333 4 2 1 1 78 27 28 46
|
||||
334 4 2 1 1 31 94 48 32
|
||||
335 4 2 1 1 19 77 20 42
|
||||
336 4 2 1 1 23 24 44 93
|
||||
337 4 2 1 1 123 124 52 96
|
||||
338 4 2 1 1 88 120 119 51
|
||||
339 4 2 1 1 91 43 85 117
|
||||
340 4 2 1 1 39 98 12 96
|
||||
341 4 2 1 1 12 91 39 87
|
||||
342 4 2 1 1 15 92 38 88
|
||||
343 4 2 1 1 38 81 15 79
|
||||
344 4 2 1 1 36 80 14 82
|
||||
345 4 2 1 1 14 71 36 73
|
||||
346 4 2 1 1 103 102 54 53
|
||||
347 4 2 1 1 61 106 62 107
|
||||
348 4 2 1 1 86 29 30 47
|
||||
349 4 2 1 1 26 45 70 25
|
||||
350 4 2 1 1 21 85 22 43
|
||||
351 4 2 1 1 94 93 123 122
|
||||
352 4 2 1 1 119 118 86 85
|
||||
353 4 2 1 1 12 96 93 123
|
||||
354 4 2 1 1 115 78 77 114
|
||||
355 4 2 1 1 69 111 70 110
|
||||
356 4 2 1 1 28 27 61 46
|
||||
357 4 2 1 1 48 62 31 32
|
||||
358 4 2 1 1 88 15 92 120
|
||||
359 4 2 1 1 79 81 15 116
|
||||
360 4 2 1 1 71 14 112 73
|
||||
361 4 2 1 1 114 116 79 51
|
||||
362 4 2 1 1 112 50 71 110
|
||||
363 4 2 1 1 91 12 117 87
|
||||
364 4 2 1 1 80 115 14 82
|
||||
365 4 2 1 1 63 15 29 68
|
||||
366 4 2 1 1 64 26 14 66
|
||||
367 4 2 1 1 47 63 105 107
|
||||
368 4 2 1 1 43 103 101 55
|
||||
369 4 2 1 1 35 10 80 84
|
||||
370 4 2 1 1 33 76 9 72
|
||||
371 4 2 1 1 37 11 88 90
|
||||
372 4 2 1 1 35 71 10 75
|
||||
373 4 2 1 1 37 79 11 83
|
||||
374 4 2 1 1 9 99 33 95
|
||||
375 4 2 1 1 68 63 15 107
|
||||
376 4 2 1 1 99 44 93 121
|
||||
377 4 2 1 1 18 69 41 17
|
||||
378 4 2 1 1 10 35 2 84
|
||||
379 4 2 1 1 15 7 28 81
|
||||
380 4 2 1 1 3 37 90 11
|
||||
381 4 2 1 1 108 64 14 66
|
||||
382 4 2 1 1 51 38 79 37
|
||||
383 4 2 1 1 12 4 23 98
|
||||
384 4 2 1 1 12 39 91 4
|
||||
385 4 2 1 1 49 33 72 34
|
||||
386 4 2 1 1 10 71 110 75
|
||||
387 4 2 1 1 114 11 79 83
|
||||
388 4 2 1 1 40 96 16 100
|
||||
389 4 2 1 1 34 13 74 72
|
||||
390 4 2 1 1 16 87 40 89
|
||||
391 4 2 1 1 34 97 13 95
|
||||
392 4 2 1 1 20 19 42 53
|
||||
393 4 2 1 1 54 23 24 44
|
||||
394 4 2 1 1 87 16 118 89
|
||||
395 4 2 1 1 95 97 13 122
|
||||
396 4 2 1 1 57 22 12 55
|
||||
397 4 2 1 1 41 102 104 56
|
||||
398 4 2 1 1 64 45 106 108
|
||||
399 4 2 1 1 101 57 12 55
|
||||
400 4 2 1 1 74 13 5 25
|
||||
401 4 2 1 1 13 34 74 5
|
||||
402 4 2 1 1 8 40 16 100
|
||||
403 4 2 1 1 16 31 65 8
|
||||
404 4 2 1 1 82 36 6 14
|
||||
405 4 2 1 1 102 9 59 56
|
||||
406 4 2 1 1 106 67 13 64
|
||||
407 4 2 1 1 119 88 11 90
|
||||
408 4 2 1 1 95 49 121 122
|
||||
409 4 2 1 1 52 118 117 87
|
||||
410 4 2 1 1 124 16 96 100
|
||||
411 4 2 1 1 80 10 113 84
|
||||
412 4 2 1 1 109 9 76 72
|
||||
413 4 2 1 1 72 13 70 111
|
||||
414 4 2 1 1 99 9 121 95
|
||||
415 4 2 1 1 30 65 16 63
|
||||
416 4 2 1 1 13 67 25 64
|
||||
417 4 2 1 1 11 55 53 103
|
||||
418 4 2 1 1 123 12 44 93
|
||||
419 4 2 1 1 56 104 10 58
|
||||
420 4 2 1 1 10 18 56 58
|
||||
421 4 2 1 1 21 60 11 55
|
||||
422 4 2 1 1 17 59 9 56
|
||||
423 4 2 1 1 16 63 62 105
|
||||
424 4 2 1 1 48 105 16 62
|
||||
425 4 2 1 1 111 45 13 70
|
||||
426 4 2 1 1 119 86 88 85
|
||||
427 4 2 1 1 123 93 94 96
|
||||
428 4 2 1 1 115 78 80 77
|
||||
429 4 2 1 1 111 72 69 70
|
||||
430 4 2 1 1 55 103 54 53
|
||||
431 4 2 1 1 63 61 62 107
|
||||
432 4 2 1 1 14 27 66 6
|
||||
433 4 2 1 1 99 9 1 24
|
||||
434 4 2 1 1 49 33 34 95
|
||||
435 4 2 1 1 96 52 39 40
|
||||
436 4 2 1 1 22 12 91 4
|
||||
437 4 2 1 1 20 11 83 3
|
||||
438 4 2 1 1 29 15 92 7
|
||||
439 4 2 1 1 18 10 75 2
|
||||
440 4 2 1 1 36 50 80 35
|
||||
441 4 2 1 1 18 17 41 56
|
||||
442 4 2 1 1 51 88 38 37
|
||||
443 4 2 1 1 62 31 16 48
|
||||
444 4 2 1 1 62 16 31 65
|
||||
445 4 2 1 1 26 45 25 64
|
||||
446 4 2 1 1 104 58 42 10
|
||||
447 4 2 1 1 29 63 30 47
|
||||
448 4 2 1 1 77 78 79 114
|
||||
449 4 2 1 1 71 69 70 110
|
||||
450 4 2 1 1 42 103 11 53
|
||||
451 4 2 1 1 93 94 95 122
|
||||
452 4 2 1 1 118 87 86 85
|
||||
453 4 2 1 1 61 62 106 64
|
||||
454 4 2 1 1 53 102 54 56
|
||||
455 4 2 1 1 78 82 27 46
|
||||
456 4 2 1 1 94 48 32 97
|
||||
457 4 2 1 1 86 30 89 47
|
||||
458 4 2 1 1 78 28 81 46
|
||||
459 4 2 1 1 26 70 45 73
|
||||
460 4 2 1 1 100 94 48 31
|
||||
461 4 2 1 1 86 92 29 47
|
||||
462 4 2 1 1 76 69 17 41
|
||||
463 4 2 1 1 42 19 77 84
|
||||
464 4 2 1 1 77 83 20 42
|
||||
465 4 2 1 1 18 41 69 75
|
||||
466 4 2 1 1 43 85 90 21
|
||||
467 4 2 1 1 91 43 117 12
|
||||
468 4 2 1 1 48 62 32 67
|
||||
469 4 2 1 1 27 66 61 46
|
||||
470 4 2 1 1 68 28 61 46
|
||||
471 4 2 1 1 54 24 59 44
|
||||
472 4 2 1 1 19 42 53 58
|
||||
473 4 2 1 1 23 54 57 44
|
||||
474 4 2 1 1 12 93 96 98
|
||||
475 4 2 1 1 99 44 121 9
|
||||
476 4 2 1 1 42 58 104 53
|
||||
477 4 2 1 1 21 43 22 55
|
||||
478 4 2 1 1 53 20 11 42
|
||||
479 4 2 1 1 53 11 20 60
|
||||
480 4 2 1 1 106 67 48 13
|
||||
481 4 2 1 1 36 71 50 35
|
||||
482 4 2 1 1 52 87 39 40
|
||||
483 4 2 1 1 48 67 106 62
|
||||
484 4 2 1 1 72 70 13 74
|
||||
485 4 2 1 1 9 33 99 1
|
||||
486 4 2 1 1 3 37 11 83
|
||||
487 4 2 1 1 13 34 5 97
|
||||
488 4 2 1 1 12 39 4 98
|
||||
489 4 2 1 1 14 36 6 73
|
||||
490 4 2 1 1 15 38 92 7
|
||||
491 4 2 1 1 8 40 89 16
|
||||
492 4 2 1 1 75 35 2 10
|
||||
493 4 2 1 1 30 16 65 8
|
||||
494 4 2 1 1 14 27 6 82
|
||||
495 4 2 1 1 26 14 66 6
|
||||
496 4 2 1 1 16 31 8 100
|
||||
497 4 2 1 1 32 13 67 5
|
||||
498 4 2 1 1 13 67 5 25
|
||||
499 4 2 1 1 68 7 28 15
|
||||
500 4 2 1 1 29 15 7 68
|
||||
501 4 2 1 1 57 4 23 12
|
||||
502 4 2 1 1 22 12 4 57
|
||||
503 4 2 1 1 10 19 84 2
|
||||
504 4 2 1 1 9 59 1 24
|
||||
505 4 2 1 1 17 9 59 1
|
||||
506 4 2 1 1 18 10 2 58
|
||||
507 4 2 1 1 11 21 90 3
|
||||
508 4 2 1 1 20 11 3 60
|
||||
509 4 2 1 1 16 62 63 65
|
||||
510 4 2 1 1 11 53 55 60
|
||||
511 4 2 1 1 78 81 79 116
|
||||
512 4 2 1 1 71 112 70 73
|
||||
513 4 2 1 1 86 88 92 120
|
||||
514 4 2 1 1 96 94 124 100
|
||||
515 4 2 1 1 94 97 95 122
|
||||
516 4 2 1 1 89 118 87 86
|
||||
517 4 2 1 1 15 38 7 81
|
||||
518 4 2 1 1 102 44 59 9
|
||||
519 4 2 1 1 59 44 102 54
|
||||
520 4 2 1 1 110 71 69 75
|
||||
521 4 2 1 1 79 77 114 83
|
||||
522 4 2 1 1 76 69 109 72
|
||||
523 4 2 1 1 113 77 80 84
|
||||
524 4 2 1 1 93 99 121 95
|
||||
525 4 2 1 1 87 117 91 85
|
||||
526 4 2 1 1 90 119 43 11
|
||||
527 4 2 1 1 80 78 115 82
|
||||
528 4 2 1 1 88 119 85 90
|
||||
529 4 2 1 1 90 43 119 85
|
||||
530 4 2 1 1 46 108 66 61
|
||||
531 4 2 1 1 46 66 108 14
|
||||
532 4 2 1 1 26 14 6 73
|
||||
533 4 2 1 1 44 101 57 12
|
||||
534 4 2 1 1 44 57 101 54
|
||||
535 4 2 1 1 46 107 68 15
|
||||
536 4 2 1 1 46 68 107 61
|
||||
537 4 2 1 1 9 33 1 76
|
||||
538 4 2 1 1 100 124 48 94
|
||||
539 4 2 1 1 100 48 124 16
|
||||
540 4 2 1 1 25 70 13 45
|
||||
541 4 2 1 1 56 53 104 58
|
||||
542 4 2 1 1 61 64 108 66
|
||||
543 4 2 1 1 106 62 67 64
|
||||
544 4 2 1 1 102 59 54 56
|
||||
545 4 2 1 1 32 13 5 97
|
||||
546 4 2 1 1 30 16 8 89
|
||||
547 4 2 1 1 13 70 25 74
|
||||
548 4 2 1 1 97 122 48 13
|
||||
549 4 2 1 1 75 110 41 69
|
||||
550 4 2 1 1 54 57 101 55
|
||||
551 4 2 1 1 97 48 122 94
|
||||
552 4 2 1 1 47 118 89 86
|
||||
553 4 2 1 1 47 89 118 16
|
||||
554 4 2 1 1 17 9 1 76
|
||||
555 4 2 1 1 11 21 3 60
|
||||
556 4 2 1 1 10 19 2 58
|
||||
557 4 2 1 1 75 41 110 10
|
||||
558 4 2 1 1 61 63 68 107
|
||||
559 4 2 1 1 70 111 45 112
|
||||
560 4 2 1 1 78 115 46 116
|
||||
561 4 2 1 1 77 114 42 113
|
||||
562 4 2 1 1 69 41 109 110
|
||||
563 4 2 1 1 107 61 108 46
|
||||
564 4 2 1 1 103 42 104 53
|
||||
565 4 2 1 1 118 86 47 120
|
||||
566 4 2 1 1 94 124 48 122
|
||||
567 4 2 1 1 117 119 43 85
|
||||
568 4 2 1 1 123 44 121 93
|
||||
569 4 2 1 1 101 54 102 44
|
||||
570 4 2 1 1 48 105 62 106
|
||||
571 4 2 1 1 91 43 12 22
|
||||
572 4 2 1 1 91 43 22 85
|
||||
573 4 2 1 1 93 12 23 98
|
||||
574 4 2 1 1 93 23 12 44
|
||||
575 4 2 1 1 46 81 116 15
|
||||
576 4 2 1 1 46 116 81 78
|
||||
577 4 2 1 1 92 47 120 15
|
||||
578 4 2 1 1 120 47 92 86
|
||||
579 4 2 1 1 46 82 115 78
|
||||
580 4 2 1 1 46 115 82 14
|
||||
581 4 2 1 1 73 45 112 70
|
||||
582 4 2 1 1 73 112 45 14
|
||||
583 4 2 1 1 99 44 9 24
|
||||
584 4 2 1 1 99 44 24 93
|
||||
585 4 2 1 1 84 42 113 77
|
||||
586 4 2 1 1 84 113 42 10
|
||||
587 4 2 1 1 76 41 109 69
|
||||
588 4 2 1 1 109 41 76 9
|
||||
589 4 2 1 1 42 83 114 77
|
||||
590 4 2 1 1 42 114 83 11
|
||||
591 4 2 2 2 135 13 122 131
|
||||
592 4 2 2 2 132 138 125 110
|
||||
593 4 2 2 2 138 108 125 106
|
||||
594 4 2 2 2 136 108 125 137
|
||||
595 4 2 2 2 110 138 125 131
|
||||
596 4 2 2 2 136 107 134 125
|
||||
597 4 2 2 2 122 135 131 125
|
||||
598 4 2 2 2 13 49 122 131
|
||||
599 4 2 2 2 136 108 137 46
|
||||
600 4 2 2 2 110 138 131 111
|
||||
601 4 2 2 2 132 138 110 112
|
||||
602 4 2 2 2 106 107 108 125
|
||||
603 4 2 2 2 138 112 137 45
|
||||
604 4 2 2 2 104 127 125 128
|
||||
605 4 2 2 2 113 115 114 125
|
||||
606 4 2 2 2 131 122 125 121
|
||||
607 4 2 2 2 112 45 14 137
|
||||
608 4 2 2 2 110 131 125 130
|
||||
609 4 2 2 2 115 116 114 125
|
||||
610 4 2 2 2 132 138 112 137
|
||||
611 4 2 2 2 50 137 115 132
|
||||
612 4 2 2 2 104 127 128 42
|
||||
613 4 2 2 2 105 134 125 133
|
||||
614 4 2 2 2 129 120 51 119
|
||||
615 4 2 2 2 104 130 128 125
|
||||
616 4 2 2 2 105 134 133 47
|
||||
617 4 2 2 2 135 106 138 125
|
||||
618 4 2 2 2 106 105 107 125
|
||||
619 4 2 2 2 138 108 106 45
|
||||
620 4 2 2 2 104 130 125 102
|
||||
621 4 2 2 2 104 127 42 103
|
||||
622 4 2 2 2 109 131 49 111
|
||||
623 4 2 2 2 106 135 48 105
|
||||
624 4 2 2 2 126 101 43 125
|
||||
625 4 2 2 2 138 137 125 108
|
||||
626 4 2 2 2 104 127 103 125
|
||||
627 4 2 2 2 116 114 129 51
|
||||
628 4 2 2 2 136 108 46 107
|
||||
629 4 2 2 2 136 108 107 125
|
||||
630 4 2 2 2 52 124 123 125
|
||||
631 4 2 2 2 132 112 110 50
|
||||
632 4 2 2 2 44 121 125 123
|
||||
633 4 2 2 2 131 122 121 49
|
||||
634 4 2 2 2 105 134 47 107
|
||||
635 4 2 2 2 106 13 135 138
|
||||
636 4 2 2 2 52 133 125 118
|
||||
637 4 2 2 2 103 43 101 125
|
||||
638 4 2 2 2 117 43 119 125
|
||||
639 4 2 2 2 105 134 107 125
|
||||
640 4 2 2 2 137 115 132 125
|
||||
641 4 2 2 2 50 137 132 112
|
||||
642 4 2 2 2 106 135 105 125
|
||||
643 4 2 2 2 102 101 44 125
|
||||
644 4 2 2 2 104 130 102 41
|
||||
645 4 2 2 2 138 45 13 111
|
||||
646 4 2 2 2 131 138 135 13
|
||||
647 4 2 2 2 138 112 45 111
|
||||
648 4 2 2 2 131 138 13 111
|
||||
649 4 2 2 2 107 134 15 136
|
||||
650 4 2 2 2 118 52 117 125
|
||||
651 4 2 2 2 101 126 12 44
|
||||
652 4 2 2 2 104 130 41 128
|
||||
653 4 2 2 2 138 137 108 45
|
||||
654 4 2 2 2 133 118 16 47
|
||||
655 4 2 2 2 44 101 126 125
|
||||
656 4 2 2 2 133 134 118 47
|
||||
657 4 2 2 2 133 134 125 118
|
||||
658 4 2 2 2 124 122 123 125
|
||||
659 4 2 2 2 129 118 119 125
|
||||
660 4 2 2 2 102 104 103 125
|
||||
661 4 2 2 2 135 48 13 106
|
||||
662 4 2 2 2 123 122 121 125
|
||||
663 4 2 2 2 103 127 43 125
|
||||
664 4 2 2 2 106 45 13 138
|
||||
665 4 2 2 2 103 11 127 42
|
||||
666 4 2 2 2 127 51 129 114
|
||||
667 4 2 2 2 13 49 131 111
|
||||
668 4 2 2 2 137 108 14 46
|
||||
669 4 2 2 2 15 47 134 107
|
||||
670 4 2 2 2 10 41 128 104
|
||||
671 4 2 2 2 16 118 133 52
|
||||
672 4 2 2 2 46 107 15 136
|
||||
673 4 2 2 2 41 102 9 130
|
||||
674 4 2 2 2 128 50 132 110
|
||||
675 4 2 2 2 10 41 110 128
|
||||
676 4 2 2 2 50 137 112 14
|
||||
677 4 2 2 2 130 102 9 44
|
||||
678 4 2 2 2 105 133 16 47
|
||||
679 4 2 2 2 127 11 103 43
|
||||
680 4 2 2 2 128 130 41 110
|
||||
681 4 2 2 2 116 134 15 51
|
||||
682 4 2 2 2 137 45 14 108
|
||||
683 4 2 2 2 12 126 101 43
|
||||
684 4 2 2 2 133 48 135 105
|
||||
685 4 2 2 2 128 42 10 104
|
||||
686 4 2 2 2 131 9 109 49
|
||||
687 4 2 2 2 118 117 119 125
|
||||
688 4 2 2 2 102 103 101 125
|
||||
689 4 2 2 2 129 118 125 134
|
||||
690 4 2 2 2 125 129 116 114
|
||||
691 4 2 2 2 117 126 43 125
|
||||
692 4 2 2 2 126 117 12 52
|
||||
693 4 2 2 2 52 126 117 125
|
||||
694 4 2 2 2 12 117 126 43
|
||||
695 4 2 2 2 127 51 114 11
|
||||
696 4 2 2 2 114 129 127 125
|
||||
697 4 2 2 2 127 119 43 125
|
||||
698 4 2 2 2 119 11 127 43
|
||||
699 4 2 2 2 127 113 114 125
|
||||
700 4 2 2 2 127 113 42 114
|
||||
701 4 2 2 2 128 130 110 125
|
||||
702 4 2 2 2 15 47 120 134
|
||||
703 4 2 2 2 127 11 114 42
|
||||
704 4 2 2 2 120 47 118 134
|
||||
705 4 2 2 2 44 130 102 125
|
||||
706 4 2 2 2 44 126 12 123
|
||||
707 4 2 2 2 123 44 126 125
|
||||
708 4 2 2 2 129 118 134 120
|
||||
709 4 2 2 2 110 132 128 125
|
||||
710 4 2 2 2 128 127 125 113
|
||||
711 4 2 2 2 128 127 113 42
|
||||
712 4 2 2 2 128 50 110 10
|
||||
713 4 2 2 2 113 42 10 128
|
||||
714 4 2 2 2 129 134 125 116
|
||||
715 4 2 2 2 127 51 11 119
|
||||
716 4 2 2 2 129 134 116 51
|
||||
717 4 2 2 2 127 51 119 129
|
||||
718 4 2 2 2 129 119 127 125
|
||||
719 4 2 2 2 110 131 130 109
|
||||
720 4 2 2 2 109 130 9 131
|
||||
721 4 2 2 2 121 130 9 44
|
||||
722 4 2 2 2 122 48 13 135
|
||||
723 4 2 2 2 44 121 130 125
|
||||
724 4 2 2 2 110 138 111 112
|
||||
725 4 2 2 2 131 138 125 135
|
||||
726 4 2 2 2 115 137 14 46
|
||||
727 4 2 2 2 126 52 12 123
|
||||
728 4 2 2 2 123 126 52 125
|
||||
729 4 2 2 2 50 137 14 115
|
||||
730 4 2 2 2 136 137 115 46
|
||||
731 4 2 2 2 121 9 131 49
|
||||
732 4 2 2 2 121 131 130 125
|
||||
733 4 2 2 2 131 130 9 121
|
||||
734 4 2 2 2 113 132 115 125
|
||||
735 4 2 2 2 113 50 115 132
|
||||
736 4 2 2 2 128 50 10 113
|
||||
737 4 2 2 2 132 113 128 125
|
||||
738 4 2 2 2 128 50 113 132
|
||||
739 4 2 2 2 133 105 135 125
|
||||
740 4 2 2 2 52 124 125 133
|
||||
741 4 2 2 2 133 48 105 16
|
||||
742 4 2 2 2 16 133 124 52
|
||||
743 4 2 2 2 136 137 125 115
|
||||
744 4 2 2 2 132 138 137 125
|
||||
745 4 2 2 2 41 130 9 109
|
||||
746 4 2 2 2 134 120 15 51
|
||||
747 4 2 2 2 129 118 120 119
|
||||
748 4 2 2 2 129 120 134 51
|
||||
749 4 2 2 2 135 122 124 125
|
||||
750 4 2 2 2 135 48 124 122
|
||||
751 4 2 2 2 133 48 16 124
|
||||
752 4 2 2 2 133 135 124 125
|
||||
753 4 2 2 2 133 48 124 135
|
||||
754 4 2 2 2 116 136 134 125
|
||||
755 4 2 2 2 115 136 116 125
|
||||
756 4 2 2 2 46 115 136 116
|
||||
757 4 2 2 2 136 134 15 116
|
||||
758 4 2 2 2 46 136 15 116
|
||||
759 4 2 2 2 109 41 130 110
|
||||
760 4 2 2 2 110 131 109 111
|
||||
$EndElements
|
||||
@@ -1,77 +0,0 @@
|
||||
// Square-in-square 2D geometry for MFEM
|
||||
// Creates concentric squares with different material attributes
|
||||
|
||||
// Define the square sizes
|
||||
L_outer = 2.0;
|
||||
L_inner = 0.5;
|
||||
|
||||
// Set mesh size and algorithm
|
||||
mesh_size = 1.0;
|
||||
Mesh.Algorithm = 6; // Frontal-Delaunay for 2D triangular mesh
|
||||
Mesh.CharacteristicLengthFactor = 1.0;
|
||||
Mesh.MshFileVersion = 2.2;
|
||||
|
||||
// Define center point for concentric squares
|
||||
cx = 0.0;
|
||||
cy = 0.0;
|
||||
|
||||
// Define the points (vertices of the outer square)
|
||||
Point(1) = {cx-L_outer/2, cy-L_outer/2, 0, mesh_size}; // bottom-left outer
|
||||
Point(2) = {cx+L_outer/2, cy-L_outer/2, 0, mesh_size}; // bottom-right outer
|
||||
Point(3) = {cx+L_outer/2, cy+L_outer/2, 0, mesh_size}; // top-right outer
|
||||
Point(4) = {cx-L_outer/2, cy+L_outer/2, 0, mesh_size}; // top-left outer
|
||||
|
||||
// Define the points (vertices of the inner square)
|
||||
Point(5) = {cx-L_inner/2, cy-L_inner/2, 0, mesh_size}; // bottom-left inner
|
||||
Point(6) = {cx+L_inner/2, cy-L_inner/2, 0, mesh_size}; // bottom-right inner
|
||||
Point(7) = {cx+L_inner/2, cy+L_inner/2, 0, mesh_size}; // top-right inner
|
||||
Point(8) = {cx-L_inner/2, cy+L_inner/2, 0, mesh_size}; // top-left inner
|
||||
|
||||
// Define the lines (edges of the outer square)
|
||||
Line(1) = {1, 2}; // bottom edge
|
||||
Line(2) = {2, 3}; // right edge
|
||||
Line(3) = {3, 4}; // top edge
|
||||
Line(4) = {4, 1}; // left edge
|
||||
|
||||
// Define the lines (edges of the inner square)
|
||||
Line(5) = {5, 6}; // bottom edge
|
||||
Line(6) = {6, 7}; // right edge
|
||||
Line(7) = {7, 8}; // top edge
|
||||
Line(8) = {8, 5}; // left edge
|
||||
|
||||
// Define the surfaces
|
||||
// Outer square boundary
|
||||
Line Loop(1) = {1, 2, 3, 4};
|
||||
|
||||
// Inner square boundary (hole in the outer region)
|
||||
Line Loop(2) = {5, 6, 7, 8};
|
||||
|
||||
// Define the surface areas
|
||||
// Outer region (annular region between squares)
|
||||
Plane Surface(1) = {1, 2}; // Outer loop minus inner loop (creates hole)
|
||||
|
||||
// Inner region (solid inner square)
|
||||
Plane Surface(2) = {2}; // Inner loop only
|
||||
|
||||
// Assign physical groups for materials
|
||||
Physical Surface(1) = {1}; // Outer material (annular region)
|
||||
Physical Surface(2) = {2}; // Inner material (solid square)
|
||||
|
||||
// Physical lines for boundary conditions
|
||||
// Outer square boundary edges
|
||||
Physical Line(1) = {1}; // outer bottom
|
||||
Physical Line(2) = {2}; // outer right
|
||||
Physical Line(3) = {3}; // outer top
|
||||
Physical Line(4) = {4}; // outer left
|
||||
|
||||
// Inner square boundary edges
|
||||
Physical Line(5) = {5}; // inner bottom
|
||||
Physical Line(6) = {6}; // inner right
|
||||
Physical Line(7) = {7}; // inner top
|
||||
Physical Line(8) = {8}; // inner left
|
||||
|
||||
// Mesh control for quality
|
||||
Mesh.OptimizeNetgen = 1;
|
||||
Mesh.Optimize = 1;
|
||||
Mesh.ElementOrder = 1;
|
||||
Mesh.RecombineAll = 0; // Keep triangular elements (don't recombine to quads)
|
||||
@@ -1,50 +0,0 @@
|
||||
$MeshFormat
|
||||
2.2 0 8
|
||||
$EndMeshFormat
|
||||
$Nodes
|
||||
13
|
||||
1 -1 -1 0
|
||||
2 1 -1 0
|
||||
3 1 1 0
|
||||
4 -1 1 0
|
||||
5 -0.25 -0.25 0
|
||||
6 0.25 -0.25 0
|
||||
7 0.25 0.25 0
|
||||
8 -0.25 0.25 0
|
||||
9 -2.752797989558076e-12 -1 0
|
||||
10 1 -2.752797989558076e-12 0
|
||||
11 2.752797989558076e-12 1 0
|
||||
12 -1 2.752797989558076e-12 0
|
||||
13 0 0 0
|
||||
$EndNodes
|
||||
$Elements
|
||||
28
|
||||
1 1 2 1 1 1 9
|
||||
2 1 2 1 1 9 2
|
||||
3 1 2 2 2 2 10
|
||||
4 1 2 2 2 10 3
|
||||
5 1 2 3 3 3 11
|
||||
6 1 2 3 3 11 4
|
||||
7 1 2 4 4 4 12
|
||||
8 1 2 4 4 12 1
|
||||
9 1 2 5 5 5 6
|
||||
10 1 2 6 6 6 7
|
||||
11 1 2 7 7 7 8
|
||||
12 1 2 8 8 8 5
|
||||
13 2 2 1 1 6 5 9
|
||||
14 2 2 1 1 5 8 12
|
||||
15 2 2 1 1 7 6 10
|
||||
16 2 2 1 1 8 7 11
|
||||
17 2 2 1 1 9 5 1
|
||||
18 2 2 1 1 5 12 1
|
||||
19 2 2 1 1 6 9 2
|
||||
20 2 2 1 1 10 6 2
|
||||
21 2 2 1 1 7 10 3
|
||||
22 2 2 1 1 11 7 3
|
||||
23 2 2 1 1 8 11 4
|
||||
24 2 2 1 1 8 4 12
|
||||
25 2 2 2 2 5 6 13
|
||||
26 2 2 2 2 8 5 13
|
||||
27 2 2 2 2 6 7 13
|
||||
28 2 2 2 2 7 8 13
|
||||
$EndElements
|
||||
@@ -1,38 +0,0 @@
|
||||
MFEM mesh v1.0
|
||||
|
||||
#
|
||||
# MFEM Geometry Types (see fem/geom.hpp):
|
||||
#
|
||||
# POINT = 0
|
||||
# SEGMENT = 1
|
||||
# TRIANGLE = 2
|
||||
# SQUARE = 3
|
||||
# TETRAHEDRON = 4
|
||||
# CUBE = 5
|
||||
# PRISM = 6
|
||||
# PYRAMID = 7
|
||||
|
||||
dimension
|
||||
2
|
||||
|
||||
elements
|
||||
2
|
||||
1 3 0 1 4 3
|
||||
1 2 1 2 4
|
||||
|
||||
boundary
|
||||
5
|
||||
1 1 0 1
|
||||
1 1 1 2
|
||||
1 1 2 4
|
||||
1 1 4 3
|
||||
1 1 3 0
|
||||
|
||||
vertices
|
||||
5
|
||||
2
|
||||
0 0
|
||||
1 0
|
||||
2 0
|
||||
0 1
|
||||
1 1
|
||||
@@ -1083,8 +1083,7 @@ EXCLUDE_PATTERNS =
|
||||
# ANamespace::AClass, ANamespace::*Test
|
||||
|
||||
EXCLUDE_SYMBOLS = mfem::internal \
|
||||
mfem::kernels::internal \
|
||||
mfem::future::detail
|
||||
mfem::kernels::internal
|
||||
|
||||
# The EXAMPLE_PATH tag can be used to specify one or more files or directories
|
||||
# that contain example code fragments that are included (see the \include
|
||||
|
||||
@@ -201,7 +201,6 @@ namespace mfem {
|
||||
* - <a class="el" href="nurbs__naca__cmesh_8cpp_source.html">NURBS NACA Mesher</a>: generate NURBS based mesh around a NACA foil
|
||||
* - <a class="el" href="nurbs__printfunc_8cpp_source.html">NURBS Printer</a>: print the NURBS-basis
|
||||
* - <a class="el" href="nurbs__mesh_info_8cpp_source.html">NURBS Mesh info</a>: print the info of a NURBS mesh
|
||||
* - <a class="el" href="nurbs__surface_8cpp_source.html">NURBS Surface</a>: interpolate a 3D Surface in a NURBS Patch
|
||||
*
|
||||
* <H3>Miniapps</H3>
|
||||
* - <a class="el" href="volta_8cpp_source.html">Volta</a>: simple electrostatics simulation code
|
||||
@@ -246,9 +245,6 @@ namespace mfem {
|
||||
* - <a class="el" href="pdiffusion_8cpp_source.html">DPG Diffusion example</a>: DPG formulation for the diffusion problem
|
||||
* - <a class="el" href="pmaxwell_8cpp_source.html">DPG Maxwell example</a>: DPG formulation for the indefinite Maxwell problem
|
||||
* - <a class="el" href="lor__elast_8cpp_source.html">LOR Elasticity</a>: solve linear elasticity with LOR preconditioning on GPUs
|
||||
* - <a class="el" href="reflector_8cpp_source.html">Reflector Miniapp</a>: reflect a mesh about a plane
|
||||
* - <a class="el" href="ref321_8cpp_source.html">3:1 Refinement Miniapp</a>: perform 3:1 anisotropic mesh refinements
|
||||
* - <a class="el" href="pref321_8cpp_source.html">3:1 Refinement Miniapp</a>: parallel 3:1 anisotropic mesh refinements
|
||||
*
|
||||
* See also the <a class="el" href="https://mfem.org/examples/">examples documentation</a> online.
|
||||
*/
|
||||
|
||||
@@ -215,7 +215,7 @@ if (MFEM_ENABLE_TESTING)
|
||||
add_test(NAME ex1p_ceed_np=${MFEM_MPI_NP}
|
||||
COMMAND ${MPIEXEC} ${MPIEXEC_NUMPROC_FLAG} ${MFEM_MPI_NP}
|
||||
${MPIEXEC_PREFLAGS}
|
||||
$<TARGET_FILE:ex1p> "-no-vis" "-d" "ceed-cpu" "-pa" "-a"
|
||||
$<TARGET_FILE:ex1p> "-no-vis" "-d ceed-cpu" "-pa" "-a"
|
||||
${MPIEXEC_POSTFLAGS})
|
||||
endif()
|
||||
endif()
|
||||
|
||||
@@ -64,7 +64,7 @@ PARALLEL_NAME := Parallel AMGX example
|
||||
$(MFEM_LIB_FILE):
|
||||
$(error The MFEM library is not build)
|
||||
|
||||
clean: clean-build clean-exec
|
||||
clean: clean-build
|
||||
|
||||
clean-build:
|
||||
rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
|
||||
|
||||
@@ -64,12 +64,12 @@ ex1p-test-par: ex1p
|
||||
$(MFEM_LIB_FILE):
|
||||
$(error The MFEM library is not built)
|
||||
|
||||
clean: clean-build clean-exec
|
||||
clean: clean-build clean-exec $(SUBDIRS_CLEAN)
|
||||
|
||||
clean-build:
|
||||
rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
|
||||
rm -rf *.dSYM *.TVD.*breakpoints
|
||||
|
||||
clean-exec:
|
||||
@rm -f refined.mesh mesh.*
|
||||
@rm -f sol.*
|
||||
@rm -f refined.mesh displaced.mesh mesh.* ex5.mesh
|
||||
@rm -f sphere_refined.* sol.* sol_u.* sol_p.* sol_r.* sol_i.*
|
||||
|
||||
+21
-34
@@ -50,10 +50,6 @@
|
||||
// ex1 -m ../data/beam-tet.mesh -pa -d ceed-cpu
|
||||
// ex1 -m ../data/beam-tet.mesh -pa -d ceed-cuda:/gpu/cuda/ref
|
||||
//
|
||||
// Device simplices sample runs:
|
||||
// ex1 -pa -d gpu -m ../data/inline-tet.mesh
|
||||
// ex1 -pa -d gpu -m ../data/inline-tri.mesh
|
||||
//
|
||||
// Description: This example code demonstrates the use of MFEM to define a
|
||||
// simple finite element discretization of the Poisson problem
|
||||
// -Delta u = 1 with homogeneous Dirichlet boundary conditions.
|
||||
@@ -142,25 +138,25 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
|
||||
// 5. Define a finite element space on the mesh. Here we use continuous
|
||||
// Lagrange finite elements of the specified order.
|
||||
// - If order < 1, we instead use an isoparametric/isogeometric space.
|
||||
// - If the mesh is simplicial and partial assembly is requested,
|
||||
// we use the positive basis, which supports device execution.
|
||||
// Lagrange finite elements of the specified order. If order < 1, we
|
||||
// instead use an isoparametric/isogeometric space.
|
||||
FiniteElementCollection *fec;
|
||||
auto basis_type = (pa && mesh.IsSimplexMesh()) ?
|
||||
BasisType::Positive : BasisType::GaussLobatto;
|
||||
bool delete_fec;
|
||||
if (order > 0)
|
||||
{
|
||||
fec = new H1_FECollection(order, dim, basis_type);
|
||||
fec = new H1_FECollection(order, dim);
|
||||
delete_fec = true;
|
||||
}
|
||||
else if (mesh.GetNodes())
|
||||
{
|
||||
fec = mesh.GetNodes()->OwnFEC();
|
||||
delete_fec = false;
|
||||
cout << "Using isoparametric FEs: " << fec->Name() << endl;
|
||||
}
|
||||
else
|
||||
{
|
||||
fec = new H1_FECollection(order = 1, dim, basis_type);
|
||||
fec = new H1_FECollection(order = 1, dim);
|
||||
delete_fec = true;
|
||||
}
|
||||
FiniteElementSpace fespace(&mesh, fec);
|
||||
cout << "Number of finite element unknowns: "
|
||||
@@ -228,29 +224,17 @@ int main(int argc, char *argv[])
|
||||
// 11. Solve the linear system A X = B.
|
||||
if (!pa)
|
||||
{
|
||||
#ifdef MFEM_USE_CUDSS
|
||||
if (Device::Allows(Backend::CUDA_MASK))
|
||||
{
|
||||
// Use cuDSS to solve the system.
|
||||
CuDSSSolver cudss_solver;
|
||||
cudss_solver.SetOperator(*A);
|
||||
cudss_solver.Mult(B, X);
|
||||
}
|
||||
else
|
||||
#endif
|
||||
{
|
||||
#ifndef MFEM_USE_SUITESPARSE
|
||||
// Use a simple symmetric Gauss-Seidel preconditioner with PCG.
|
||||
GSSmoother M((SparseMatrix&)(*A));
|
||||
PCG(*A, M, B, X, 1, 200, 1e-12, 0.0);
|
||||
// Use a simple symmetric Gauss-Seidel preconditioner with PCG.
|
||||
GSSmoother M((SparseMatrix&)(*A));
|
||||
PCG(*A, M, B, X, 1, 200, 1e-12, 0.0);
|
||||
#else
|
||||
// If MFEM was compiled with SuiteSparse, use UMFPACK to solve the system.
|
||||
UMFPackSolver umf_solver;
|
||||
umf_solver.Control[UMFPACK_ORDERING] = UMFPACK_ORDERING_METIS;
|
||||
umf_solver.SetOperator(*A);
|
||||
umf_solver.Mult(B, X);
|
||||
// If MFEM was compiled with SuiteSparse, use UMFPACK to solve the system.
|
||||
UMFPackSolver umf_solver;
|
||||
umf_solver.Control[UMFPACK_ORDERING] = UMFPACK_ORDERING_METIS;
|
||||
umf_solver.SetOperator(*A);
|
||||
umf_solver.Mult(B, X);
|
||||
#endif
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -289,14 +273,17 @@ int main(int argc, char *argv[])
|
||||
if (visualization)
|
||||
{
|
||||
char vishost[] = "localhost";
|
||||
int visport = 19916;
|
||||
int visport = 19916;
|
||||
socketstream sol_sock(vishost, visport);
|
||||
sol_sock.precision(8);
|
||||
sol_sock << "solution\n" << mesh << x << flush;
|
||||
}
|
||||
|
||||
// 15. Free the used memory.
|
||||
if (order > 0) { delete fec; }
|
||||
if (delete_fec)
|
||||
{
|
||||
delete fec;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
+2
-2
@@ -5,9 +5,9 @@
|
||||
// Sample runs:
|
||||
// mpirun -np 4 ex12p -m ../data/beam-tri.mesh
|
||||
// mpirun -np 4 ex12p -m ../data/beam-quad.mesh
|
||||
// mpirun -np 4 ex12p -m ../data/beam-tet.mesh -s 464 -n 10 -o 2 -elast
|
||||
// mpirun -np 4 ex12p -m ../data/beam-tet.mesh -s 462 -n 10 -o 2 -elast
|
||||
// mpirun -np 4 ex12p -m ../data/beam-hex.mesh -s 3878
|
||||
// mpirun -np 4 ex12p -m ../data/beam-wedge.mesh -s 82
|
||||
// mpirun -np 4 ex12p -m ../data/beam-wedge.mesh -s 81
|
||||
// mpirun -np 4 ex12p -m ../data/beam-tri.mesh -s 3877 -o 2 -sys
|
||||
// mpirun -np 4 ex12p -m ../data/beam-quad.mesh -s 4544 -n 6 -o 3 -elast
|
||||
// mpirun -np 4 ex12p -m ../data/beam-quad-nurbs.mesh
|
||||
|
||||
+34
-60
@@ -42,11 +42,7 @@
|
||||
// mpirun -np 4 ex1p -pa -d ceed-cuda:/gpu/cuda/shared
|
||||
// mpirun -np 4 ex1p -pa -d ceed-cuda:/gpu/cuda/shared -m ../data/square-mixed.mesh
|
||||
// mpirun -np 4 ex1p -pa -d ceed-cuda:/gpu/cuda/shared -m ../data/fichera-mixed.mesh
|
||||
// mpirun -np 4 ex1p -pa -d ceed-cpu -m ../data/beam-tet.mesh
|
||||
//
|
||||
// Device simplices sample runs:
|
||||
// mpirun -np 4 ex1p -pa -d gpu -m ../data/inline-tet.mesh
|
||||
// mpirun -np 4 ex1p -pa -d gpu -m ../data/inline-tri.mesh
|
||||
// mpirun -np 4 ex1p -m ../data/beam-tet.mesh -pa -d ceed-cpu
|
||||
//
|
||||
// Description: This example code demonstrates the use of MFEM to define a
|
||||
// simple finite element discretization of the Poisson problem
|
||||
@@ -87,9 +83,6 @@ int main(int argc, char *argv[])
|
||||
const char *device_config = "cpu";
|
||||
bool visualization = true;
|
||||
bool algebraic_ceed = false;
|
||||
#ifdef MFEM_USE_CUDSS
|
||||
bool cudss_solver = false;
|
||||
#endif
|
||||
|
||||
OptionsParser args(argc, argv);
|
||||
args.AddOption(&mesh_file, "-m", "--mesh",
|
||||
@@ -109,10 +102,6 @@ int main(int argc, char *argv[])
|
||||
args.AddOption(&algebraic_ceed, "-a", "--algebraic",
|
||||
"-no-a", "--no-algebraic",
|
||||
"Use algebraic Ceed solver");
|
||||
#endif
|
||||
#ifdef MFEM_USE_CUDSS
|
||||
args.AddOption(&cudss_solver, "-cudss", "--cudss-solver", "-no-cudss",
|
||||
"--no-cudss-solver", "Use the cuDSS Solver.");
|
||||
#endif
|
||||
args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
|
||||
"--no-visualization",
|
||||
@@ -169,20 +158,19 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
|
||||
// 7. Define a parallel finite element space on the parallel mesh. Here we
|
||||
// use continuous Lagrange finite elements of the specified order.
|
||||
// - If order < 1, we instead use an isoparametric/isogeometric space.
|
||||
// - If the mesh is simplicial and partial assembly is requested,
|
||||
// we use the positive basis, which supports device execution.
|
||||
// use continuous Lagrange finite elements of the specified order. If
|
||||
// order < 1, we instead use an isoparametric/isogeometric space.
|
||||
FiniteElementCollection *fec;
|
||||
auto basis_type = (pa && pmesh.IsSimplexMesh()) ?
|
||||
BasisType::Positive : BasisType::GaussLobatto;
|
||||
bool delete_fec;
|
||||
if (order > 0)
|
||||
{
|
||||
fec = new H1_FECollection(order, dim, basis_type);
|
||||
fec = new H1_FECollection(order, dim);
|
||||
delete_fec = true;
|
||||
}
|
||||
else if (pmesh.GetNodes())
|
||||
{
|
||||
fec = pmesh.GetNodes()->OwnFEC();
|
||||
delete_fec = false;
|
||||
if (myid == 0)
|
||||
{
|
||||
cout << "Using isoparametric FEs: " << fec->Name() << endl;
|
||||
@@ -190,7 +178,8 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
else
|
||||
{
|
||||
fec = new H1_FECollection(order = 1, dim, basis_type);
|
||||
fec = new H1_FECollection(order = 1, dim);
|
||||
delete_fec = true;
|
||||
}
|
||||
ParFiniteElementSpace fespace(&pmesh, fec);
|
||||
HYPRE_BigInt size = fespace.GlobalTrueVSize();
|
||||
@@ -259,51 +248,33 @@ int main(int argc, char *argv[])
|
||||
// 13. Solve the linear system A X = B.
|
||||
// * With full assembly, use the BoomerAMG preconditioner from hypre.
|
||||
// * With partial assembly, use Jacobi smoothing, for now.
|
||||
#ifdef MFEM_USE_CUDSS
|
||||
if (!pa && (Device::Allows(Backend::CUDA_MASK) && cudss_solver))
|
||||
Solver *prec = NULL;
|
||||
if (pa)
|
||||
{
|
||||
// Solve using a direct solver with cuDSS
|
||||
CuDSSSolver cudss_solver(MPI_COMM_WORLD);
|
||||
cudss_solver.SetMatrixSymType(
|
||||
CuDSSSolver::SYMMETRIC_POSITIVE_DEFINITE);
|
||||
cudss_solver.SetMatrixViewType(CuDSSSolver::UPPER);
|
||||
cudss_solver.SetOperator(*A);
|
||||
cudss_solver.Mult(B, X);
|
||||
}
|
||||
else
|
||||
#endif
|
||||
{
|
||||
Solver *prec = NULL;
|
||||
if (pa)
|
||||
if (UsesTensorBasis(fespace))
|
||||
{
|
||||
if (UsesTensorBasis(fespace))
|
||||
if (algebraic_ceed)
|
||||
{
|
||||
if (algebraic_ceed)
|
||||
{
|
||||
prec = new ceed::AlgebraicSolver(a, ess_tdof_list);
|
||||
}
|
||||
else
|
||||
{
|
||||
prec = new OperatorJacobiSmoother(a, ess_tdof_list);
|
||||
}
|
||||
prec = new ceed::AlgebraicSolver(a, ess_tdof_list);
|
||||
}
|
||||
else
|
||||
{
|
||||
prec = new OperatorJacobiSmoother(a, ess_tdof_list);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
prec = new HypreBoomerAMG;
|
||||
}
|
||||
CGSolver cg(MPI_COMM_WORLD);
|
||||
cg.SetRelTol(1e-12);
|
||||
cg.SetMaxIter(2000);
|
||||
cg.SetPrintLevel(1);
|
||||
if (prec)
|
||||
{
|
||||
cg.SetPreconditioner(*prec);
|
||||
}
|
||||
cg.SetOperator(*A);
|
||||
cg.Mult(B, X);
|
||||
delete prec;
|
||||
}
|
||||
else
|
||||
{
|
||||
prec = new HypreBoomerAMG;
|
||||
}
|
||||
CGSolver cg(MPI_COMM_WORLD);
|
||||
cg.SetRelTol(1e-12);
|
||||
cg.SetMaxIter(2000);
|
||||
cg.SetPrintLevel(1);
|
||||
if (prec) { cg.SetPreconditioner(*prec); }
|
||||
cg.SetOperator(*A);
|
||||
cg.Mult(B, X);
|
||||
delete prec;
|
||||
|
||||
// 14. Recover the parallel grid function corresponding to X. This is the
|
||||
// local finite element solution on each processor.
|
||||
@@ -337,7 +308,10 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
|
||||
// 17. Free the used memory.
|
||||
if (order > 0) { delete fec; }
|
||||
if (delete_fec)
|
||||
{
|
||||
delete fec;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
+9
-27
@@ -302,21 +302,15 @@ int main(int argc, char *argv[])
|
||||
char vishost[] = "localhost";
|
||||
int visport = 19916;
|
||||
socketstream sol_sock_r(vishost, visport);
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_r.precision(8);
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_r << "solution\n" << *pmesh << u_exact->real()
|
||||
<< "window_title 'Exact: Real Part'" << flush;
|
||||
// Make sure all ranks have sent their real solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_i << "solution\n" << *pmesh << u_exact->imag()
|
||||
<< "window_title 'Exact: Imaginary Part'" << flush;
|
||||
// Make sure all ranks have sent their imaginary solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
}
|
||||
|
||||
// 11. Set up the parallel sesquilinear form a(.,.) on the finite element
|
||||
@@ -540,21 +534,15 @@ int main(int argc, char *argv[])
|
||||
char vishost[] = "localhost";
|
||||
int visport = 19916;
|
||||
socketstream sol_sock_r(vishost, visport);
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_r.precision(8);
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_r << "solution\n" << *pmesh << u.real()
|
||||
<< "window_title 'Solution: Real Part'" << flush;
|
||||
// Make sure all ranks have sent their real solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_i << "solution\n" << *pmesh << u.imag()
|
||||
<< "window_title 'Solution: Imaginary Part'" << flush;
|
||||
// Make sure all ranks have sent their imaginary solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
}
|
||||
if (visualization && exact_sol)
|
||||
{
|
||||
@@ -563,21 +551,15 @@ int main(int argc, char *argv[])
|
||||
char vishost[] = "localhost";
|
||||
int visport = 19916;
|
||||
socketstream sol_sock_r(vishost, visport);
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_r.precision(8);
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_r << "solution\n" << *pmesh << u_exact->real()
|
||||
<< "window_title 'Error: Real Part'" << flush;
|
||||
// Make sure all ranks have sent their real solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
socketstream sol_sock_i(vishost, visport);
|
||||
sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
|
||||
sol_sock_i.precision(8);
|
||||
sol_sock_i << "solution\n" << *pmesh << u_exact->imag()
|
||||
<< "window_title 'Error: Imaginary Part'" << flush;
|
||||
// Make sure all ranks have sent their imaginary solution before initiating
|
||||
// another set of GLVis connections (one from each rank):
|
||||
MPI_Barrier(pmesh->GetComm());
|
||||
}
|
||||
if (visualization)
|
||||
{
|
||||
|
||||
@@ -95,15 +95,6 @@ int main(int argc, char *argv[])
|
||||
args.PrintOptions(cout);
|
||||
}
|
||||
|
||||
if (amg_elast && !static_cond && reorder_space)
|
||||
{
|
||||
if (myid == 0)
|
||||
cerr << "\nThe AMG elasticity solver requires ordering byVDIM! "
|
||||
<< "Ignoring the specified option -nodes/--by-nodes.\n"
|
||||
<< endl;
|
||||
reorder_space = false;
|
||||
}
|
||||
|
||||
// 3. Enable hardware devices such as GPUs, and programming models such as
|
||||
// CUDA, OCCA, RAJA and OpenMP based on command line options.
|
||||
Device device(device_config);
|
||||
|
||||
+52
-11
@@ -5,8 +5,8 @@
|
||||
// Sample runs:
|
||||
// ex37 -alpha 10
|
||||
// ex37 -alpha 10 -pv
|
||||
// ex37 -lambda 0.1 -mu 0.1 -growth 1
|
||||
// ex37 -o 2 -alpha 10.0 -mi 50 -vf 0.4 -ntol 1e-5 -growth 1.5
|
||||
// ex37 -lambda 0.1 -mu 0.1
|
||||
// ex37 -o 2 -alpha 5.0 -mi 50 -vf 0.4 -ntol 1e-5
|
||||
// ex37 -r 6 -o 1 -alpha 25.0 -epsilon 0.02 -mi 50 -ntol 1e-5
|
||||
//
|
||||
// Description: This example code demonstrates the use of MFEM to solve a
|
||||
@@ -55,6 +55,53 @@
|
||||
using namespace std;
|
||||
using namespace mfem;
|
||||
|
||||
/**
|
||||
* @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
|
||||
* ∫_Ω ρ dx = θ vol(Ω) as follows:
|
||||
*
|
||||
* 1. Compute the root of the R → R function
|
||||
* f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
|
||||
* 2. Set ψ ← ψ + c.
|
||||
*
|
||||
* @param psi a GridFunction to be updated
|
||||
* @param target_volume θ vol(Ω)
|
||||
* @param tol Newton iteration tolerance
|
||||
* @param max_its Newton maximum iteration number
|
||||
* @return real_t Final volume, ∫_Ω sigmoid(ψ)
|
||||
*/
|
||||
real_t proj(GridFunction &psi, real_t target_volume, real_t tol=1e-12,
|
||||
int max_its=10)
|
||||
{
|
||||
MappedGridFunctionCoefficient sigmoid_psi(&psi, sigmoid);
|
||||
MappedGridFunctionCoefficient der_sigmoid_psi(&psi, der_sigmoid);
|
||||
|
||||
LinearForm int_sigmoid_psi(psi.FESpace());
|
||||
int_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
|
||||
LinearForm int_der_sigmoid_psi(psi.FESpace());
|
||||
int_der_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(
|
||||
der_sigmoid_psi));
|
||||
bool done = false;
|
||||
for (int k=0; k<max_its; k++) // Newton iteration
|
||||
{
|
||||
int_sigmoid_psi.Assemble(); // Recompute f(c) with updated ψ
|
||||
const real_t f = int_sigmoid_psi.Sum() - target_volume;
|
||||
|
||||
int_der_sigmoid_psi.Assemble(); // Recompute df(c) with updated ψ
|
||||
const real_t df = int_der_sigmoid_psi.Sum();
|
||||
|
||||
const real_t dc = -f/df;
|
||||
psi += dc;
|
||||
if (abs(dc) < tol) { done = true; break; }
|
||||
}
|
||||
if (!done)
|
||||
{
|
||||
mfem_warning("Projection reached maximum iteration without converging. "
|
||||
"Result may not be accurate.");
|
||||
}
|
||||
int_sigmoid_psi.Assemble();
|
||||
return int_sigmoid_psi.Sum();
|
||||
}
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------
|
||||
* ALGORITHM PREAMBLE
|
||||
@@ -133,11 +180,10 @@ int main(int argc, char *argv[])
|
||||
int ref_levels = 5;
|
||||
int order = 2;
|
||||
real_t alpha = 1.0;
|
||||
real_t growth = 2;
|
||||
real_t epsilon = 0.01;
|
||||
real_t vol_fraction = 0.5;
|
||||
int max_it = 1e3;
|
||||
real_t itol = 1e-2;
|
||||
real_t itol = 1e-1;
|
||||
real_t ntol = 1e-4;
|
||||
real_t rho_min = 1e-6;
|
||||
real_t lambda = 1.0;
|
||||
@@ -152,8 +198,6 @@ int main(int argc, char *argv[])
|
||||
"Order (degree) of the finite elements.");
|
||||
args.AddOption(&alpha, "-alpha", "--alpha-step-length",
|
||||
"Step length for gradient descent.");
|
||||
args.AddOption(&growth, "-growth", "--alpha-growth-rate",
|
||||
"Growth rate of step length for gradient descent.");
|
||||
args.AddOption(&epsilon, "-epsilon", "--epsilon-thickness",
|
||||
"Length scale for ρ.");
|
||||
args.AddOption(&max_it, "-mi", "--max-it",
|
||||
@@ -288,7 +332,6 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
FilterSolver->SetEssentialBoundary(ess_bdr_filter);
|
||||
FilterSolver->SetupFEM();
|
||||
FilterSolver->AssembleDiffusionBilinear();
|
||||
|
||||
BilinearForm mass(&control_fes);
|
||||
mass.AddDomainIntegrator(new InverseIntegrator(new MassIntegrator(one)));
|
||||
@@ -342,7 +385,7 @@ int main(int argc, char *argv[])
|
||||
// 11. Iterate:
|
||||
for (int k = 1; k <= max_it; k++)
|
||||
{
|
||||
if (k > 1) { alpha = std::pow((real_t) k,growth); }
|
||||
if (k > 1) { alpha *= ((real_t) k) / ((real_t) k-1); }
|
||||
|
||||
mfem::out << "\nStep = " << k << std::endl;
|
||||
|
||||
@@ -379,9 +422,7 @@ int main(int argc, char *argv[])
|
||||
|
||||
// Step 5 - Update design variable ψ ← proj(ψ - αG)
|
||||
psi.Add(-alpha, grad);
|
||||
GridFunction alpha_grad(grad);
|
||||
alpha_grad *= alpha;
|
||||
const real_t material_volume = proj(psi, alpha_grad, target_volume);
|
||||
const real_t material_volume = proj(psi, target_volume);
|
||||
|
||||
// Compute ||ρ - ρ_old|| in control fes.
|
||||
real_t norm_increment = zerogf.ComputeL1Error(succ_diff_rho);
|
||||
|
||||
+23
-183
@@ -137,7 +137,7 @@ public:
|
||||
exponent(exponent_), rho_min(rho_min_)
|
||||
{
|
||||
MFEM_ASSERT(rho_min_ >= 0.0, "rho_min must be >= 0");
|
||||
MFEM_ASSERT(rho_min_ < 1.0, "rho_min must be < 1");
|
||||
MFEM_ASSERT(rho_min_ < 1.0, "rho_min must be > 1");
|
||||
MFEM_ASSERT(u, "displacement field is not set");
|
||||
MFEM_ASSERT(rho_filter, "density field is not set");
|
||||
}
|
||||
@@ -231,12 +231,9 @@ private:
|
||||
FiniteElementCollection * fec = nullptr;
|
||||
FiniteElementSpace * fes = nullptr;
|
||||
Array<int> ess_bdr;
|
||||
Array<int> ess_tdof_list;
|
||||
Array<int> neumann_bdr;
|
||||
GridFunction * u = nullptr;
|
||||
LinearForm * b = nullptr;
|
||||
BilinearForm * a = nullptr;
|
||||
OperatorPtr A;
|
||||
bool parallel;
|
||||
#ifdef MFEM_USE_MPI
|
||||
ParMesh * pmesh = nullptr;
|
||||
@@ -270,8 +267,6 @@ public:
|
||||
void ResetFEM();
|
||||
void SetupFEM();
|
||||
|
||||
void UpdateEssentialTDofs();
|
||||
void AssembleDiffusionBilinear(bool update_ess_tdofs=true);
|
||||
void Solve();
|
||||
GridFunction * GetFEMSolution();
|
||||
LinearForm * GetLinearForm() {return b;}
|
||||
@@ -376,130 +371,6 @@ public:
|
||||
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
|
||||
* ∫_Ω ρ dx = θ vol(Ω) as follows:
|
||||
*
|
||||
* 1. Compute the root of the R → R function
|
||||
* f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
|
||||
* using the Illinois method
|
||||
* 2. Set ψ ← ψ + c.
|
||||
*
|
||||
* @param psi a GridFunction to be updated
|
||||
* @param alpha_grad alpha multiplied by gradient
|
||||
* @param target_volume θ vol(Ω)
|
||||
* @param tol Illinois iteration tolerance
|
||||
* @param max_its Illinois maximum iteration number
|
||||
* @return real_t Final volume (∫_Ω sigmoid(ψ) dx)
|
||||
*/
|
||||
real_t proj(GridFunction &psi, GridFunction &alpha_grad, real_t target_volume,
|
||||
real_t tol = 1e-12, int max_its = 100)
|
||||
{
|
||||
#ifdef MFEM_USE_MPI
|
||||
FiniteElementSpace *fes = psi.FESpace();
|
||||
ParFiniteElementSpace *pfes = dynamic_cast<ParFiniteElementSpace*>(fes);
|
||||
#endif
|
||||
ConstantCoefficient zero_cf(0.0);
|
||||
real_t a = -alpha_grad.ComputeMaxError(zero_cf);
|
||||
real_t b = -a;
|
||||
real_t y = 0.0;
|
||||
|
||||
MappedGridFunctionCoefficient sigmoid_psi(
|
||||
&psi, [&y](const real_t x) { return sigmoid(x + y); });
|
||||
std::unique_ptr<LinearForm> int_sigmoid_psi;
|
||||
#ifdef MFEM_USE_MPI
|
||||
ParGridFunction *par_psi = dynamic_cast<ParGridFunction *>(&psi);
|
||||
if (par_psi)
|
||||
{
|
||||
int_sigmoid_psi.reset(new ParLinearForm(par_psi->ParFESpace()));
|
||||
}
|
||||
else
|
||||
{
|
||||
int_sigmoid_psi.reset(new LinearForm(psi.FESpace()));
|
||||
}
|
||||
#else
|
||||
int_sigmoid_psi.reset(new LinearForm(psi.FESpace()));
|
||||
#endif
|
||||
int_sigmoid_psi->AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
|
||||
|
||||
y = a;
|
||||
int_sigmoid_psi->Assemble();
|
||||
real_t f_a = int_sigmoid_psi->Sum(); // f_a := f(a) + θ vol(Ω)
|
||||
|
||||
y = b;
|
||||
int_sigmoid_psi->Assemble();
|
||||
real_t f_b = int_sigmoid_psi->Sum(); // f_b := f(b) + θ vol(Ω)
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (pfes)
|
||||
{
|
||||
MPI_Allreduce(MPI_IN_PLACE, &f_a, 1, MPITypeMap<real_t>::mpi_type,
|
||||
MPI_SUM, MPI_COMM_WORLD);
|
||||
MPI_Allreduce(MPI_IN_PLACE, &f_b, 1, MPITypeMap<real_t>::mpi_type,
|
||||
MPI_SUM, MPI_COMM_WORLD);
|
||||
}
|
||||
#endif
|
||||
f_a -= target_volume; // f_a := f(a)
|
||||
f_b -= target_volume; // f_b := f(b)
|
||||
real_t c = 0.0;
|
||||
real_t f_c = 0.0;
|
||||
int side = 0;
|
||||
|
||||
bool done = false;
|
||||
for (int k=0; k < max_its; k++)
|
||||
{
|
||||
c = (f_a * b - f_b * a) / (f_a - f_b);
|
||||
|
||||
if (abs(b - a) < tol * abs(b + a)) { done = true; break; }
|
||||
|
||||
y = c;
|
||||
int_sigmoid_psi->Assemble();
|
||||
f_c = int_sigmoid_psi->Sum(); // f_c := f(c) + θ vol(Ω)
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (pfes)
|
||||
{
|
||||
MPI_Allreduce(MPI_IN_PLACE, &f_c, 1, MPITypeMap<real_t>::mpi_type,
|
||||
MPI_SUM, MPI_COMM_WORLD);
|
||||
}
|
||||
#endif
|
||||
f_c -= target_volume; // f_c := f(c)
|
||||
|
||||
if (f_c * f_b > 0)
|
||||
{
|
||||
b = c;
|
||||
f_b = f_c;
|
||||
if (side == -1) { f_a /= 2.0; }
|
||||
side = -1;
|
||||
}
|
||||
else if (f_c * f_a > 0)
|
||||
{
|
||||
a = c;
|
||||
f_a = f_c;
|
||||
if (side == 1) { f_b /= 2.0; }
|
||||
side = 1;
|
||||
}
|
||||
else
|
||||
{
|
||||
done = true; break;
|
||||
}
|
||||
}
|
||||
if (!done)
|
||||
{
|
||||
mfem_warning("Projection reached maximum iteration without converging. "
|
||||
"Result may not be accurate.");
|
||||
}
|
||||
y = 0.0;
|
||||
psi += c;
|
||||
int_sigmoid_psi->Assemble();
|
||||
real_t material_volume = int_sigmoid_psi->Sum();
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (pfes)
|
||||
{
|
||||
MPI_Allreduce(MPI_IN_PLACE, &material_volume, 1,
|
||||
MPITypeMap<real_t>::mpi_type, MPI_SUM, MPI_COMM_WORLD);
|
||||
}
|
||||
#endif
|
||||
return material_volume;
|
||||
}
|
||||
|
||||
// Poisson solver
|
||||
|
||||
@@ -551,8 +422,12 @@ void DiffusionSolver::SetupFEM()
|
||||
}
|
||||
}
|
||||
|
||||
void DiffusionSolver::UpdateEssentialTDofs()
|
||||
void DiffusionSolver::Solve()
|
||||
{
|
||||
OperatorPtr A;
|
||||
Vector B, X;
|
||||
Array<int> ess_tdof_list;
|
||||
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (parallel)
|
||||
{
|
||||
@@ -565,39 +440,7 @@ void DiffusionSolver::UpdateEssentialTDofs()
|
||||
#else
|
||||
fes->GetEssentialTrueDofs(ess_bdr,ess_tdof_list);
|
||||
#endif
|
||||
}
|
||||
|
||||
void DiffusionSolver::AssembleDiffusionBilinear(bool update_ess_tdofs)
|
||||
{
|
||||
if (update_ess_tdofs)
|
||||
{
|
||||
UpdateEssentialTDofs();
|
||||
}
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (parallel)
|
||||
{
|
||||
a = new ParBilinearForm(pfes);
|
||||
}
|
||||
else
|
||||
{
|
||||
a = new BilinearForm(fes);
|
||||
}
|
||||
#else
|
||||
a = new BilinearForm(fes);
|
||||
#endif
|
||||
a->AddDomainIntegrator(new DiffusionIntegrator(*diffcf));
|
||||
if (masscf)
|
||||
{
|
||||
a->AddDomainIntegrator(new MassIntegrator(*masscf));
|
||||
}
|
||||
a->Assemble();
|
||||
a->FormSystemMatrix(ess_tdof_list, A);
|
||||
}
|
||||
|
||||
void DiffusionSolver::Solve()
|
||||
{
|
||||
Vector B, X;
|
||||
|
||||
*u=0.0;
|
||||
if (b)
|
||||
{
|
||||
delete b;
|
||||
@@ -632,33 +475,31 @@ void DiffusionSolver::Solve()
|
||||
|
||||
b->Assemble();
|
||||
|
||||
*u=0.0;
|
||||
if (essbdr_cf)
|
||||
{
|
||||
u->ProjectBdrCoefficient(*essbdr_cf,ess_bdr);
|
||||
}
|
||||
BilinearForm * a = nullptr;
|
||||
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (parallel)
|
||||
{
|
||||
X.SetSize(pfes->TrueVSize());
|
||||
B.SetSize(pfes->TrueVSize());
|
||||
dynamic_cast<ParGridFunction*>(u)->ParallelAssemble(X);
|
||||
dynamic_cast<ParLinearForm*>(b)->ParallelAssemble(B);
|
||||
dynamic_cast<ParBilinearForm*>(a)->ParallelEliminateTDofsInRHS(
|
||||
ess_tdof_list, X, B);
|
||||
a = new ParBilinearForm(pfes);
|
||||
}
|
||||
else
|
||||
{
|
||||
X.NewDataAndSize(u->GetData(), u->Size());
|
||||
B.NewDataAndSize(b->GetData(), b->Size());
|
||||
a->EliminateVDofsInRHS(ess_tdof_list, X, B);
|
||||
a = new BilinearForm(fes);
|
||||
}
|
||||
#else
|
||||
X.NewDataAndSize(u->GetData(), u->Size());
|
||||
B.NewDataAndSize(b->GetData(), b->Size());
|
||||
a->EliminateVDofsInRHS(ess_tdof_list, X, B);
|
||||
a = new BilinearForm(fes);
|
||||
#endif
|
||||
a->AddDomainIntegrator(new DiffusionIntegrator(*diffcf));
|
||||
if (masscf)
|
||||
{
|
||||
a->AddDomainIntegrator(new MassIntegrator(*masscf));
|
||||
}
|
||||
a->Assemble();
|
||||
if (essbdr_cf)
|
||||
{
|
||||
u->ProjectBdrCoefficient(*essbdr_cf,ess_bdr);
|
||||
}
|
||||
a->FormLinearSystem(ess_tdof_list, *u, *b, A, X, B);
|
||||
|
||||
CGSolver * cg = nullptr;
|
||||
Solver * M = nullptr;
|
||||
@@ -687,6 +528,7 @@ void DiffusionSolver::Solve()
|
||||
delete M;
|
||||
delete cg;
|
||||
a->RecoverFEMSolution(X, *b, *u);
|
||||
delete a;
|
||||
}
|
||||
|
||||
GridFunction * DiffusionSolver::GetFEMSolution()
|
||||
@@ -718,8 +560,6 @@ DiffusionSolver::~DiffusionSolver()
|
||||
#endif
|
||||
delete fec; fec = nullptr;
|
||||
delete b;
|
||||
A.Clear();
|
||||
delete a;
|
||||
}
|
||||
|
||||
|
||||
|
||||
+60
-11
@@ -4,8 +4,8 @@
|
||||
//
|
||||
// Sample runs:
|
||||
// mpirun -np 4 ex37p -alpha 10 -pv
|
||||
// mpirun -np 4 ex37p -lambda 0.1 -mu 0.1 -growth 1
|
||||
// mpirun -np 4 ex37p -o 2 -alpha 10.0 -mi 50 -vf 0.4 -ntol 1e-5 -growth 1.5
|
||||
// mpirun -np 4 ex37p -lambda 0.1 -mu 0.1
|
||||
// mpirun -np 4 ex37p -o 2 -alpha 5.0 -mi 50 -vf 0.4 -ntol 1e-5
|
||||
// mpirun -np 4 ex37p -r 6 -o 2 -alpha 10.0 -epsilon 0.02 -mi 50 -ntol 1e-5
|
||||
//
|
||||
// Description: This example code demonstrates the use of MFEM to solve a
|
||||
@@ -54,6 +54,61 @@
|
||||
using namespace std;
|
||||
using namespace mfem;
|
||||
|
||||
/**
|
||||
* @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
|
||||
* ∫_Ω ρ dx = θ vol(Ω) as follows:
|
||||
*
|
||||
* 1. Compute the root of the R → R function
|
||||
* f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
|
||||
* 2. Set ψ ← ψ + c.
|
||||
*
|
||||
* @param psi a GridFunction to be updated
|
||||
* @param target_volume θ vol(Ω)
|
||||
* @param tol Newton iteration tolerance
|
||||
* @param max_its Newton maximum iteration number
|
||||
* @return real_t Final volume, ∫_Ω sigmoid(ψ)
|
||||
*/
|
||||
real_t proj(ParGridFunction &psi, real_t target_volume, real_t tol=1e-12,
|
||||
int max_its=10)
|
||||
{
|
||||
MappedGridFunctionCoefficient sigmoid_psi(&psi, sigmoid);
|
||||
MappedGridFunctionCoefficient der_sigmoid_psi(&psi, der_sigmoid);
|
||||
|
||||
ParLinearForm int_sigmoid_psi(psi.ParFESpace());
|
||||
int_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
|
||||
ParLinearForm int_der_sigmoid_psi(psi.ParFESpace());
|
||||
int_der_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(
|
||||
der_sigmoid_psi));
|
||||
bool done = false;
|
||||
for (int k=0; k<max_its; k++) // Newton iteration
|
||||
{
|
||||
int_sigmoid_psi.Assemble(); // Recompute f(c) with updated ψ
|
||||
real_t f = int_sigmoid_psi.Sum();
|
||||
MPI_Allreduce(MPI_IN_PLACE, &f, 1, MPITypeMap<real_t>::mpi_type,
|
||||
MPI_SUM, MPI_COMM_WORLD);
|
||||
f -= target_volume;
|
||||
|
||||
int_der_sigmoid_psi.Assemble(); // Recompute df(c) with updated ψ
|
||||
real_t df = int_der_sigmoid_psi.Sum();
|
||||
MPI_Allreduce(MPI_IN_PLACE, &df, 1, MPITypeMap<real_t>::mpi_type,
|
||||
MPI_SUM, MPI_COMM_WORLD);
|
||||
|
||||
const real_t dc = -f/df;
|
||||
psi += dc;
|
||||
if (abs(dc) < tol) { done = true; break; }
|
||||
}
|
||||
if (!done)
|
||||
{
|
||||
mfem_warning("Projection reached maximum iteration without converging. "
|
||||
"Result may not be accurate.");
|
||||
}
|
||||
int_sigmoid_psi.Assemble();
|
||||
real_t material_volume = int_sigmoid_psi.Sum();
|
||||
MPI_Allreduce(MPI_IN_PLACE, &material_volume, 1,
|
||||
MPITypeMap<real_t>::mpi_type, MPI_SUM, MPI_COMM_WORLD);
|
||||
return material_volume;
|
||||
}
|
||||
|
||||
/*
|
||||
* ---------------------------------------------------------------
|
||||
* ALGORITHM PREAMBLE
|
||||
@@ -138,11 +193,10 @@ int main(int argc, char *argv[])
|
||||
int ref_levels = 5;
|
||||
int order = 2;
|
||||
real_t alpha = 1.0;
|
||||
real_t growth = 2;
|
||||
real_t epsilon = 0.01;
|
||||
real_t vol_fraction = 0.5;
|
||||
int max_it = 1e3;
|
||||
real_t itol = 1e-2;
|
||||
real_t itol = 1e-1;
|
||||
real_t ntol = 1e-4;
|
||||
real_t rho_min = 1e-6;
|
||||
real_t lambda = 1.0;
|
||||
@@ -157,8 +211,6 @@ int main(int argc, char *argv[])
|
||||
"Order (degree) of the finite elements.");
|
||||
args.AddOption(&alpha, "-alpha", "--alpha-step-length",
|
||||
"Step length for gradient descent.");
|
||||
args.AddOption(&growth, "-growth", "--alpha-growth-rate",
|
||||
"Growth rate of step length for gradient descent.");
|
||||
args.AddOption(&epsilon, "-epsilon", "--epsilon-thickness",
|
||||
"Length scale for ρ.");
|
||||
args.AddOption(&max_it, "-mi", "--max-it",
|
||||
@@ -307,7 +359,6 @@ int main(int argc, char *argv[])
|
||||
}
|
||||
FilterSolver->SetEssentialBoundary(ess_bdr_filter);
|
||||
FilterSolver->SetupFEM();
|
||||
FilterSolver->AssembleDiffusionBilinear();
|
||||
|
||||
ParBilinearForm mass(&control_fes);
|
||||
mass.AddDomainIntegrator(new InverseIntegrator(new MassIntegrator(one)));
|
||||
@@ -361,7 +412,7 @@ int main(int argc, char *argv[])
|
||||
// 11. Iterate:
|
||||
for (int k = 1; k <= max_it; k++)
|
||||
{
|
||||
if (k > 1) { alpha = std::pow((real_t) k,growth); }
|
||||
if (k > 1) { alpha *= ((real_t) k) / ((real_t) k-1); }
|
||||
|
||||
if (myid == 0)
|
||||
{
|
||||
@@ -401,9 +452,7 @@ int main(int argc, char *argv[])
|
||||
|
||||
// Step 5 - Update design variable ψ ← proj(ψ - αG)
|
||||
psi.Add(-alpha, grad);
|
||||
ParGridFunction alpha_grad(grad);
|
||||
alpha_grad *= alpha;
|
||||
const real_t material_volume = proj(psi, alpha_grad, target_volume);
|
||||
const real_t material_volume = proj(psi, target_volume);
|
||||
|
||||
// Compute ||ρ - ρ_old|| in control fes.
|
||||
real_t norm_increment = zerogf.ComputeL1Error(succ_diff_rho);
|
||||
|
||||
@@ -76,4 +76,4 @@ clean-build:
|
||||
rm -rf *.dSYM *.TVD.*breakpoints
|
||||
|
||||
clean-exec:
|
||||
@rm -f refined.mesh sol.gf mesh.* sol.*
|
||||
@rm -f refined.mesh sol.gf
|
||||
|
||||
+2
-7
@@ -71,7 +71,6 @@ endif
|
||||
|
||||
SUBDIRS_ALL = $(addsuffix /all,$(SUBDIRS))
|
||||
SUBDIRS_TEST = $(addsuffix /test,$(SUBDIRS))
|
||||
SUBDIRS_TEST_NOCLEAN = $(addsuffix /test-noclean,$(SUBDIRS))
|
||||
SUBDIRS_CLEAN = $(addsuffix /clean,$(SUBDIRS))
|
||||
SUBDIRS_TPRINT = $(addsuffix /test-print,$(SUBDIRS))
|
||||
|
||||
@@ -88,9 +87,8 @@ SUBDIRS_TPRINT = $(addsuffix /test-print,$(SUBDIRS))
|
||||
|
||||
all: $(EXAMPLES) $(SUBDIRS_ALL)
|
||||
|
||||
.PHONY: $(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_TEST_NOCLEAN) \
|
||||
$(SUBDIRS_CLEAN) $(SUBDIRS_TPRINT)
|
||||
$(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_TEST_NOCLEAN) $(SUBDIRS_CLEAN):
|
||||
.PHONY: $(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_CLEAN) $(SUBDIRS_TPRINT)
|
||||
$(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_CLEAN):
|
||||
$(MAKE) -C $(@D) $(@F)
|
||||
$(SUBDIRS_TPRINT):
|
||||
@$(MAKE) -C $(@D) $(@F)
|
||||
@@ -109,7 +107,6 @@ endif
|
||||
MFEM_TESTS = EXAMPLES
|
||||
include $(MFEM_TEST_MK)
|
||||
test: $(SUBDIRS_TEST)
|
||||
test-noclean: $(SUBDIRS_TEST_NOCLEAN)
|
||||
test-print: $(SUBDIRS_TPRINT)
|
||||
|
||||
# Testing: Parallel vs. serial runs
|
||||
@@ -160,8 +157,6 @@ ex37-test-seq: ex37
|
||||
@$(call mfem-test,$<,, Serial example,-mi 3)
|
||||
ex37p-test-par: ex37p
|
||||
@$(call mfem-test,$<, $(RUN_MPI), Parallel example,-mi 3)
|
||||
ex39-test-seq: ex39
|
||||
@$(call mfem-test,$<,, Serial example,-m ../data/compass.mesh)
|
||||
ex41-test-seq: ex41
|
||||
@$(call mfem-test,$<,, Serial example,-tf 1.0)
|
||||
ex41p-test-par: ex41p
|
||||
|
||||
+1
-14
@@ -57,8 +57,6 @@ set(SRCS
|
||||
integ/lininteg_domain_grad.cpp
|
||||
integ/lininteg_domain_vectorfe.cpp
|
||||
integ/nonlininteg_vecconvection_pa.cpp
|
||||
integ/nonlininteg_vecconvection_pa_diag.cpp
|
||||
integ/nonlininteg_vecconvection_pa_grad.cpp
|
||||
integ/nonlininteg_vecconvection_mf.cpp
|
||||
coefficient.cpp
|
||||
complex_fem.cpp
|
||||
@@ -135,7 +133,7 @@ set(SRCS
|
||||
tmop/assemble/diag2.cpp
|
||||
tmop/assemble/grad2_limit.cpp
|
||||
tmop/assemble/grad2.cpp
|
||||
tmop/assemble/diag3_limit.cpp
|
||||
tmop/assemble/diag3_limit.cpp
|
||||
tmop/assemble/diag3.cpp
|
||||
tmop/assemble/grad3_limit.cpp
|
||||
tmop/assemble/grad3.cpp
|
||||
@@ -173,12 +171,8 @@ set(SRCS
|
||||
tmop_tools.cpp
|
||||
tmop_amr.cpp
|
||||
gslib.cpp
|
||||
gslib/findptsedge_local_2.cpp
|
||||
gslib/findptsedge_local_3.cpp
|
||||
gslib/findptssurf_local_3.cpp
|
||||
gslib/findpts_local_2.cpp
|
||||
gslib/findpts_local_3.cpp
|
||||
gslib/interpolate_local_1.cpp
|
||||
gslib/interpolate_local_2.cpp
|
||||
gslib/interpolate_local_3.cpp
|
||||
transfer.cpp
|
||||
@@ -197,20 +191,14 @@ set(HDRS
|
||||
integ/bilininteg_dgtrace_kernels.hpp
|
||||
integ/bilininteg_vecdiffusion_kernels.hpp
|
||||
integ/bilininteg_convection_kernels.hpp
|
||||
integ/bilininteg_diffusion_pa_simplices.hpp
|
||||
integ/bilininteg_diffusion_kernels.hpp
|
||||
integ/bilininteg_elasticity_kernels.hpp
|
||||
integ/bilininteg_hcurl_kernels.hpp
|
||||
integ/bilininteg_hdiv_kernels.hpp
|
||||
integ/bilininteg_hcurlhdiv_kernels.hpp
|
||||
integ/bilininteg_mass_kernels.hpp
|
||||
integ/bilininteg_mass_pa_simplices.hpp
|
||||
integ/bilininteg_vecdiffusion_pa.hpp
|
||||
integ/bilininteg_vecdiv_pa.hpp
|
||||
integ/bilininteg_vecmass_pa.hpp
|
||||
integ/nonlininteg_vecconvection_pa.hpp
|
||||
integ/nonlininteg_vecconvection_pa_diag.hpp
|
||||
integ/nonlininteg_vecconvection_pa_grad.hpp
|
||||
coefficient.hpp
|
||||
complex_fem.hpp
|
||||
convergence.hpp
|
||||
@@ -317,7 +305,6 @@ set(HDRS
|
||||
tmop_tools.hpp
|
||||
tmop_amr.hpp
|
||||
gslib.hpp
|
||||
gslib/gslib_kernel_helpers.hpp
|
||||
transfer.hpp
|
||||
hyperbolic.hpp
|
||||
integrator.hpp
|
||||
|
||||
+3
-32
@@ -729,8 +729,7 @@ void BilinearForm::Assemble(int skip_zeros)
|
||||
tr = mesh -> GetBdrFaceTransformations (i);
|
||||
if (tr != NULL)
|
||||
{
|
||||
mfem::DofTransformation doftrans;
|
||||
fes -> GetElementVDofs (tr -> Elem1No, vdofs, doftrans);
|
||||
fes -> GetElementVDofs (tr -> Elem1No, vdofs);
|
||||
fe1 = fes -> GetFE (tr -> Elem1No);
|
||||
// The fe2 object is really a dummy and not used on the boundaries,
|
||||
// but we can't dereference a NULL pointer, and we don't want to
|
||||
@@ -744,7 +743,6 @@ void BilinearForm::Assemble(int skip_zeros)
|
||||
|
||||
boundary_face_integs[k] -> AssembleFaceMatrix (*fe1, *fe2, *tr,
|
||||
elemmat);
|
||||
doftrans.TransformDual(elemmat);
|
||||
mat -> AddSubMatrix (vdofs, vdofs, elemmat, skip_zeros);
|
||||
}
|
||||
}
|
||||
@@ -1255,31 +1253,6 @@ void BilinearForm::Mult(const Vector &x, Vector &y) const
|
||||
}
|
||||
}
|
||||
|
||||
void BilinearForm::AddMult(const Vector &x, Vector &y, const real_t a) const
|
||||
{
|
||||
if (ext)
|
||||
{
|
||||
ext->AddMult(x, y, a);
|
||||
}
|
||||
else
|
||||
{
|
||||
mat->AddMult(x, y, a);
|
||||
}
|
||||
}
|
||||
|
||||
void BilinearForm::AddMultTranspose(const Vector &x, Vector &y,
|
||||
const real_t a) const
|
||||
{
|
||||
if (ext)
|
||||
{
|
||||
ext->AddMultTranspose(x, y, a);
|
||||
}
|
||||
else
|
||||
{
|
||||
mat->AddMultTranspose(x, y, a);
|
||||
}
|
||||
}
|
||||
|
||||
void BilinearForm::MultTranspose(const Vector & x, Vector & y) const
|
||||
{
|
||||
if (ext)
|
||||
@@ -1750,7 +1723,6 @@ void MixedBilinearForm::Assemble(int skip_zeros)
|
||||
}
|
||||
}
|
||||
|
||||
DofTransformation dom_dof_trans, ran_dof_trans;
|
||||
for (int i = 0; i < trial_fes -> GetNBE(); i++)
|
||||
{
|
||||
const int bdr_attr = mesh->GetBdrAttribute(i);
|
||||
@@ -1759,8 +1731,8 @@ void MixedBilinearForm::Assemble(int skip_zeros)
|
||||
ftr = mesh -> GetBdrFaceTransformations (i);
|
||||
if (ftr != NULL)
|
||||
{
|
||||
trial_fes->GetElementVDofs(ftr->Elem1No, trial_vdofs, dom_dof_trans);
|
||||
test_fes->GetElementVDofs(ftr->Elem1No, test_vdofs, ran_dof_trans);
|
||||
trial_fes->GetElementVDofs(ftr->Elem1No, trial_vdofs);
|
||||
test_fes->GetElementVDofs(ftr->Elem1No, test_vdofs);
|
||||
trial_fe1 = trial_fes->GetFE(ftr->Elem1No);
|
||||
test_fe1 = test_fes->GetFE(ftr->Elem1No);
|
||||
// The test_fe2 object is really a dummy and not used on the
|
||||
@@ -1776,7 +1748,6 @@ void MixedBilinearForm::Assemble(int skip_zeros)
|
||||
boundary_face_integs[k]->AssembleFaceMatrix(*trial_fe1, *test_fe1, *trial_fe2,
|
||||
*test_fe2,
|
||||
*ftr, elemmat);
|
||||
TransformDual(ran_dof_trans, dom_dof_trans, elemmat);
|
||||
mat->AddSubMatrix(test_vdofs, trial_vdofs, elemmat, skip_zeros);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -307,8 +307,8 @@ public:
|
||||
{ mat->Mult(x, y); mat_e->AddMult(x, y); }
|
||||
|
||||
/// Add the matrix vector multiple to a vector: $ y += a M x $
|
||||
void AddMult(const Vector &x, Vector &y,
|
||||
const real_t a = 1.0) const override;
|
||||
void AddMult(const Vector &x, Vector &y, const real_t a = 1.0) const override
|
||||
{ mat -> AddMult (x, y, a); }
|
||||
|
||||
/** @brief Add the original uneliminated matrix vector multiple to a vector.
|
||||
The original matrix is $ M + Me $ so we have:
|
||||
@@ -318,7 +318,8 @@ public:
|
||||
|
||||
/// Add the matrix transpose vector multiplication: $ y += a M^T x $
|
||||
void AddMultTranspose(const Vector & x, Vector & y,
|
||||
const real_t a = 1.0) const override;
|
||||
const real_t a = 1.0) const override
|
||||
{ mat->AddMultTranspose(x, y, a); }
|
||||
|
||||
/** @brief Add the original uneliminated matrix transpose vector
|
||||
multiple to a vector. The original matrix is $ M + M_e $
|
||||
|
||||
@@ -1997,11 +1997,7 @@ void PADiscreteLinearOperatorExtension::Assemble()
|
||||
}
|
||||
else
|
||||
{
|
||||
const L2ElementRestriction* l2_elem_restrict =
|
||||
dynamic_cast<const L2ElementRestriction*>(elem_restrict_test);
|
||||
MFEM_VERIFY(l2_elem_restrict,
|
||||
"A real ElementRestriction is required in this setting!");
|
||||
test_multiplicity = 1.0;
|
||||
mfem_error("A real ElementRestriction is required in this setting!");
|
||||
}
|
||||
|
||||
auto tm = test_multiplicity.ReadWrite();
|
||||
@@ -2040,13 +2036,7 @@ void PADiscreteLinearOperatorExtension::AddMult(
|
||||
}
|
||||
else
|
||||
{
|
||||
const L2ElementRestriction* l2_elem_restrict =
|
||||
dynamic_cast<const L2ElementRestriction*>(elem_restrict_test);
|
||||
MFEM_VERIFY(l2_elem_restrict,
|
||||
"In this setting you need a real ElementRestriction!");
|
||||
tempY.SetSize(y.Size());
|
||||
l2_elem_restrict->MultTranspose(localTest, tempY);
|
||||
y += tempY;
|
||||
mfem_error("In this setting you need a real ElementRestriction!");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+4
-22
@@ -1345,8 +1345,7 @@ real_t DiffusionIntegrator::ComputeFluxEnergy
|
||||
}
|
||||
|
||||
const IntegrationRule &DiffusionIntegrator::GetRule(
|
||||
const FiniteElement &trial_fe, const FiniteElement &test_fe,
|
||||
const bool stroud)
|
||||
const FiniteElement &trial_fe, const FiniteElement &test_fe)
|
||||
{
|
||||
int order;
|
||||
if (trial_fe.Space() == FunctionSpace::Pk)
|
||||
@@ -1363,15 +1362,7 @@ const IntegrationRule &DiffusionIntegrator::GetRule(
|
||||
{
|
||||
return RefinedIntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
|
||||
if (stroud)
|
||||
{
|
||||
return StroudIntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
else
|
||||
{
|
||||
return IntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
return IntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
|
||||
MassIntegrator::MassIntegrator(const IntegrationRule *ir)
|
||||
@@ -1458,8 +1449,7 @@ void MassIntegrator::AssembleElementMatrix2(
|
||||
|
||||
const IntegrationRule &MassIntegrator::GetRule(const FiniteElement &trial_fe,
|
||||
const FiniteElement &test_fe,
|
||||
const ElementTransformation &Trans,
|
||||
const bool stroud)
|
||||
const ElementTransformation &Trans)
|
||||
{
|
||||
// int order = trial_fe.GetOrder() + test_fe.GetOrder();
|
||||
const int order = trial_fe.GetOrder() + test_fe.GetOrder() + Trans.OrderW();
|
||||
@@ -1468,15 +1458,7 @@ const IntegrationRule &MassIntegrator::GetRule(const FiniteElement &trial_fe,
|
||||
{
|
||||
return RefinedIntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
|
||||
if (stroud)
|
||||
{
|
||||
return StroudIntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
else
|
||||
{
|
||||
return IntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
return IntRules.Get(trial_fe.GetGeomType(), order);
|
||||
}
|
||||
|
||||
|
||||
|
||||
+335
-535
File diff suppressed because it is too large
Load Diff
@@ -54,8 +54,6 @@ void Coefficient::Project(QuadratureFunction &qf)
|
||||
QuadratureSpaceBase &qspace = *qf.GetSpace();
|
||||
const int ne = qspace.GetNE();
|
||||
Vector values;
|
||||
// GetValues makes a reference, but we need it to be valid on Host
|
||||
qf.HostWrite();
|
||||
for (int iel = 0; iel < ne; ++iel)
|
||||
{
|
||||
qf.GetValues(iel, values);
|
||||
@@ -329,8 +327,6 @@ void VectorCoefficient::Project(QuadratureFunction &qf)
|
||||
const int ne = qspace.GetNE();
|
||||
DenseMatrix values;
|
||||
Vector col;
|
||||
// GetValues makes a reference, but we need it to be valid on Host
|
||||
qf.HostWrite();
|
||||
for (int iel = 0; iel < ne; ++iel)
|
||||
{
|
||||
qf.GetValues(iel, values);
|
||||
@@ -699,8 +695,6 @@ void MatrixCoefficient::Project(QuadratureFunction &qf, bool transpose)
|
||||
QuadratureSpaceBase &qspace = *qf.GetSpace();
|
||||
const int ne = qspace.GetNE();
|
||||
DenseMatrix values, matrix;
|
||||
// GetValues makes a reference, but we need it to be valid on Host
|
||||
qf.HostWrite();
|
||||
for (int iel = 0; iel < ne; ++iel)
|
||||
{
|
||||
qf.GetValues(iel, values);
|
||||
|
||||
+1
-8
@@ -52,9 +52,6 @@ public:
|
||||
/// Get the time for time dependent coefficients
|
||||
real_t GetTime() { return time; }
|
||||
|
||||
/// Returns dimension of the vector.
|
||||
int GetVDim() { return 1; }
|
||||
|
||||
/** @brief Evaluate the coefficient in the element described by @a T at the
|
||||
point @a ip. */
|
||||
/** @note When this method is called, the caller must make sure that the
|
||||
@@ -1055,8 +1052,7 @@ public:
|
||||
|
||||
typedef VectorCoefficient DiagonalMatrixCoefficient;
|
||||
|
||||
/** Base class for matrix-valued coefficients that optionally depend on time
|
||||
and space. */
|
||||
/// Base class for Matrix Coefficients that optionally depend on time and space.
|
||||
class MatrixCoefficient
|
||||
{
|
||||
protected:
|
||||
@@ -1103,9 +1099,6 @@ public:
|
||||
/// the quadrature points. The matrix will be transposed or not according to
|
||||
/// the boolean argument @a transpose.
|
||||
///
|
||||
/// The stored entries use the same row/column convention as `Eval()`,
|
||||
/// unless `transpose == true`, in which case `K^T` is stored instead.
|
||||
///
|
||||
/// The @a vdim of the QuadratureFunction should be equal to the height times
|
||||
/// the width of the matrix.
|
||||
virtual void Project(QuadratureFunction &qf, bool transpose=false);
|
||||
|
||||
+164
-1049
File diff suppressed because it is too large
Load Diff
@@ -82,25 +82,6 @@ public:
|
||||
/// underlying #fes
|
||||
int VectorDim() const;
|
||||
|
||||
/// Copy assignment. Only the data of the base class Vector is copied.
|
||||
/** It is assumed that this object and @a rhs use FiniteElementSpace%s that
|
||||
have the same size.
|
||||
|
||||
@note Defining this method overwrites the implicitly defined copy
|
||||
assignment operator. */
|
||||
ComplexGridFunction &operator=(const ComplexGridFunction &rhs)
|
||||
{ return operator=((const Vector &)rhs); }
|
||||
|
||||
/// Copy the data from @a v.
|
||||
/** The size of @a v must be equal to double of the size of the associated
|
||||
FiniteElementSpace #fes. */
|
||||
ComplexGridFunction &operator=(const Vector &v)
|
||||
{
|
||||
MFEM_ASSERT(fes && v.Size() == 2*fes->GetVSize(), "");
|
||||
Vector::operator=(v);
|
||||
return *this;
|
||||
}
|
||||
|
||||
/// Assign constant values to the ComplexGridFunction data.
|
||||
ComplexGridFunction &operator=(const std::complex<real_t> & value)
|
||||
{ *gfr = value.real(); *gfi = value.imag(); return *this; }
|
||||
@@ -166,75 +147,6 @@ public:
|
||||
return sqrt(err_r * err_r + err_i * err_i);
|
||||
}
|
||||
|
||||
/// @brief Returns Max|u_ex - u_h| error for complex-valued H1 or L2 elements
|
||||
///
|
||||
/// Compute the $L_\infty$ error across the entire domain.
|
||||
///
|
||||
/// @param[in] exsolr Coefficient object reproducing the real part of the
|
||||
/// anticipated values of the scalar field, Re(u_ex).
|
||||
/// @param[in] exsoli Coefficient object reproducing the imaginary part of
|
||||
/// the anticipated values of the scalar field, Im(u_ex).
|
||||
/// @param[in] irs Optional pointer to an array of custom integration
|
||||
/// rules e.g. higher order than the default rules. If
|
||||
/// present the array will be indexed by
|
||||
/// Geometry::Type.
|
||||
///
|
||||
/// @note Uses ComputeLpError internally. See the ComputeLpError
|
||||
/// documentation for generalizations of this error computation.
|
||||
///
|
||||
/// @note If an array of integration rules is provided through @a irs, be
|
||||
/// sure to include valid rules for each element type that may occur
|
||||
/// in the list of elements.
|
||||
///
|
||||
virtual real_t ComputeMaxError(Coefficient &exsolr,
|
||||
Coefficient &exsoli,
|
||||
const IntegrationRule *irs[] = NULL) const
|
||||
{
|
||||
return ComputeLpError(infinity(), exsolr, exsoli, NULL, irs);
|
||||
}
|
||||
|
||||
/// @brief Returns ||u_ex - u_h||_Lp for complex-valued H1 or L2 elements
|
||||
///
|
||||
/// Computes:
|
||||
/// $$(\sum_{elems} \int_{elem} w \, |u_{ex} - u_h|^p)^{1/p}$$
|
||||
/// Where:
|
||||
/// $$|u_{ex} - u_h| = \sqrt{Re(u_{ex} - u_h)^2 + Im(u_{ex} - u_h)^2}$$
|
||||
///
|
||||
/// @param[in] p Real value indicating the exponent of the $L^p$ norm.
|
||||
/// To avoid domain errors p should have a positive value,
|
||||
/// either finite or infinite.
|
||||
/// @param[in] exsolr Coefficient object reproducing the real part of the
|
||||
/// anticipated values of the scalar field, Re(u_ex).
|
||||
/// @param[in] exsoli Coefficient object reproducing the imaginary part of
|
||||
/// the anticipated values of the scalar field, Im(u_ex).
|
||||
/// @param[in] weight Optional pointer to a Coefficient object reproducing
|
||||
/// a weighting function, w.
|
||||
/// @param[in] irs Optional pointer to an array of custom integration
|
||||
/// rules e.g. higher order than the default rules. If
|
||||
/// present the array will be indexed by Geometry::Type.
|
||||
/// @param[in] elems Optional pointer to a marker array, with a length
|
||||
/// equal to the number of local elements, indicating
|
||||
/// which elements to integrate over. Only those elements
|
||||
/// corresponding to non-zero entries in @a elems will
|
||||
/// contribute to the computed L2 error.
|
||||
///
|
||||
/// @note If an array of integration rules is provided through @a irs, be
|
||||
/// sure to include valid rules for each element type that may occur
|
||||
/// in the list of elements.
|
||||
///
|
||||
/// @note Quadratures with negative weights (as in some simplex integration
|
||||
/// rules in MFEM) can produce negative integrals even with
|
||||
/// non-negative integrands. To avoid returning negative errors this
|
||||
/// function uses the absolute values of the element-wise integrals.
|
||||
/// This may lead to results which are not entirely consistent with
|
||||
/// such integration rules.
|
||||
virtual real_t ComputeLpError(const real_t p,
|
||||
Coefficient &exsolr,
|
||||
Coefficient &exsoli,
|
||||
Coefficient *weight = NULL,
|
||||
const IntegrationRule *irs[] = NULL,
|
||||
const Array<int> *elems = NULL) const;
|
||||
|
||||
/// Save the ComplexGridFunction to an output stream.
|
||||
virtual void Save(std::ostream &out) const;
|
||||
|
||||
@@ -392,9 +304,6 @@ private:
|
||||
bool RealInteg();
|
||||
bool ImagInteg();
|
||||
|
||||
void BuildComplexOperator(OperatorHandle &A_r, OperatorHandle &A_i,
|
||||
OperatorHandle &A) const;
|
||||
|
||||
public:
|
||||
SesquilinearForm(FiniteElementSpace *fes,
|
||||
ComplexOperator::Convention
|
||||
@@ -508,186 +417,6 @@ public:
|
||||
virtual ~SesquilinearForm();
|
||||
};
|
||||
|
||||
/** Class for a mixed sesquilinear form
|
||||
|
||||
A mixed sesquilinear form is a generalization of a mixed bilinear form to
|
||||
complex-valued fields. Mixed sesquilinear forms are linear in the second
|
||||
argument but the first argument involves a complex conjugate in the sense
|
||||
that:
|
||||
|
||||
a(alpha u, beta v) = conj(alpha) beta a(u, v)
|
||||
|
||||
The @a convention argument in the class's constructor is documented in the
|
||||
mfem::ComplexOperator class found in linalg/complex_operator.hpp.
|
||||
|
||||
When supplying integrators to the MixedSesquilinearForm either the real or
|
||||
imaginary integrator can be NULL. This indicates that the corresponding
|
||||
portion of the complex-valued material coefficient is equal to zero.
|
||||
*/
|
||||
class MixedSesquilinearForm
|
||||
{
|
||||
private:
|
||||
ComplexOperator::Convention conv;
|
||||
|
||||
MixedBilinearForm * mblfr;
|
||||
MixedBilinearForm * mblfi;
|
||||
|
||||
/* These methods check if the real/imag parts of the sesqulinear form are not
|
||||
empty */
|
||||
bool RealInteg();
|
||||
bool ImagInteg();
|
||||
|
||||
public:
|
||||
MixedSesquilinearForm(
|
||||
FiniteElementSpace * trial_fes,
|
||||
FiniteElementSpace * test_fes,
|
||||
ComplexOperator::Convention convention = ComplexOperator::HERMITIAN);
|
||||
|
||||
/** @brief Create a MixedSesquilinearForm on the given trial and test
|
||||
FiniteElementSpaces, using the same integrators as the
|
||||
MixedBilinearForms @a bfr and @a bfi.
|
||||
|
||||
The FiniteElementSpace pointers are not owned by the newly constructed
|
||||
object.
|
||||
|
||||
The integrators are copied as pointers and they are not owned by the
|
||||
newly constructed MixedSesquilinearForm. */
|
||||
MixedSesquilinearForm(
|
||||
FiniteElementSpace * trial_fes,
|
||||
FiniteElementSpace * test_fes,
|
||||
MixedBilinearForm * bfr,
|
||||
MixedBilinearForm * bfi,
|
||||
ComplexOperator::Convention convention = ComplexOperator::HERMITIAN);
|
||||
|
||||
ComplexOperator::Convention GetConvention() const { return conv; }
|
||||
void SetConvention(const ComplexOperator::Convention & convention) { conv = convention; }
|
||||
|
||||
/// Set the desired assembly level.
|
||||
/** Valid choices are:
|
||||
|
||||
- AssemblyLevel::LEGACY (default)
|
||||
- AssemblyLevel::FULL
|
||||
- AssemblyLevel::PARTIAL
|
||||
- AssemblyLevel::ELEMENT
|
||||
- AssemblyLevel::NONE
|
||||
|
||||
This method must be called before assembly. */
|
||||
void SetAssemblyLevel(AssemblyLevel assembly_level)
|
||||
{
|
||||
mblfr->SetAssemblyLevel(assembly_level);
|
||||
mblfi->SetAssemblyLevel(assembly_level);
|
||||
}
|
||||
|
||||
MixedBilinearForm & real() { return *mblfr; }
|
||||
MixedBilinearForm & imag() { return *mblfi; }
|
||||
const MixedBilinearForm & real() const { return *mblfr; }
|
||||
const MixedBilinearForm & imag() const { return *mblfi; }
|
||||
|
||||
/// Adds new Domain Integrator.
|
||||
void AddDomainIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds new Domain Integrator, restricted to specific attributes.
|
||||
void AddDomainIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & elem_marker);
|
||||
|
||||
/// Adds new Boundary Integrator.
|
||||
void AddBoundaryIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/** @brief Adds new boundary Integrator, restricted to specific boundary
|
||||
attributes.
|
||||
|
||||
Assumes ownership of @a bfi.
|
||||
|
||||
The mfem::array @a bdr_marker is stored internally as a pointer to the given
|
||||
mfem::Array<int> object. */
|
||||
void AddBoundaryIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & bdr_marker);
|
||||
|
||||
/// Adds new interior Face Integrator. Assumes ownership of @a bfi.
|
||||
void AddInteriorFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds new boundary Face Integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/** @brief Adds new boundary Face Integrator, restricted to specific boundary
|
||||
attributes.
|
||||
|
||||
Assumes ownership of @a bfi.
|
||||
|
||||
The mfem::array @a bdr_marker is stored internally as a pointer to the given
|
||||
mfem::Array<int> object. */
|
||||
void AddBdrFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & bdr_marker);
|
||||
|
||||
/** @brief Add a trace face integrator. Assumes ownership of @a bfi.
|
||||
|
||||
This type of integrator assembles terms over all faces of the mesh using
|
||||
the face FE from the trial space and the two adjacent volume FEs from
|
||||
the test space. */
|
||||
void AddTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds a boundary trace face integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds a boundary trace face integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> &bdr_marker);
|
||||
|
||||
/// Assemble the local matrix
|
||||
void Assemble(int skip_zeros = 1);
|
||||
|
||||
/// Finalizes the matrix initialization.
|
||||
void Finalize(int skip_zeros = 1);
|
||||
|
||||
/// Updates the internal mixed forms with the new finite element space.
|
||||
virtual void Update();
|
||||
|
||||
/** @brief Return a ComplexSparseMatrix wrapping the local (L-dof) real
|
||||
and imaginary matrices of the form.
|
||||
|
||||
The returned wrapper has to be deleted by the caller, but it does not
|
||||
own the wrapped real and imaginary matrices, which remain owned by
|
||||
this form. */
|
||||
ComplexSparseMatrix *AssembleComplexSparseMatrix();
|
||||
|
||||
/// Return the trial FE space associated with the MixedSesquilinearForm.
|
||||
FiniteElementSpace *TrialFESpace() { return mblfr->TrialFESpace(); }
|
||||
|
||||
/// Read-only access to the associated trial FiniteElementSpace.
|
||||
const FiniteElementSpace *TrialFESpace() const { return mblfr->TrialFESpace(); }
|
||||
|
||||
/// Return the test FE space associated with the MixedSesquilinearForm.
|
||||
FiniteElementSpace *TestFESpace() { return mblfr->TestFESpace(); }
|
||||
|
||||
/// Read-only access to the associated test FiniteElementSpace.
|
||||
const FiniteElementSpace *TestFESpace() const { return mblfr->TestFESpace(); }
|
||||
|
||||
|
||||
void FormRectangularLinearSystem(const Array<int> & ess_trial_tdof_list,
|
||||
const Array<int> & ess_test_tdof_list,
|
||||
Vector & x,
|
||||
Vector & b,
|
||||
OperatorHandle & A,
|
||||
Vector & X,
|
||||
Vector & B);
|
||||
|
||||
void FormRectangularSystemMatrix(const Array<int> & ess_trial_tdof_list,
|
||||
const Array<int> & ess_test_tdof_list,
|
||||
OperatorHandle & A);
|
||||
|
||||
virtual ~MixedSesquilinearForm();
|
||||
};
|
||||
|
||||
#ifdef MFEM_USE_MPI
|
||||
|
||||
/// Class for parallel complex-valued grid function - real + imaginary part
|
||||
@@ -989,12 +718,6 @@ private:
|
||||
bool RealInteg();
|
||||
bool ImagInteg();
|
||||
|
||||
void SetImaginaryEssentialDiagonalToZero(
|
||||
const Array<int> &ess_tdof_list, OperatorHandle &A);
|
||||
|
||||
void BuildComplexOperator(OperatorHandle &A_r, OperatorHandle &A_i,
|
||||
OperatorHandle &A) const;
|
||||
|
||||
public:
|
||||
ParSesquilinearForm(ParFiniteElementSpace *pf,
|
||||
ComplexOperator::Convention
|
||||
@@ -1110,169 +833,6 @@ public:
|
||||
virtual ~ParSesquilinearForm();
|
||||
};
|
||||
|
||||
/** Class for a parallel mixed sesquilinear form
|
||||
|
||||
A mixed sesquilinear form is a generalization of a mixed bilinear form to
|
||||
complex-valued fields. Mixed sesquilinear forms are linear in the second
|
||||
argument but the first argument involves a complex conjugate in the sense
|
||||
that:
|
||||
|
||||
a(alpha u, beta v) = conj(alpha) beta a(u, v)
|
||||
|
||||
The @a convention argument in the class's constructor is documented in the
|
||||
mfem::ComplexOperator class found in linalg/complex_operator.hpp.
|
||||
|
||||
When supplying integrators to the ParMixedSesquilinearForm either the real
|
||||
or imaginary integrator can be NULL. This indicates that the corresponding
|
||||
portion of the complex-valued material coefficient is equal to zero.
|
||||
*/
|
||||
class ParMixedSesquilinearForm
|
||||
{
|
||||
private:
|
||||
ComplexOperator::Convention conv;
|
||||
|
||||
ParMixedBilinearForm * pmblfr;
|
||||
ParMixedBilinearForm * pmblfi;
|
||||
|
||||
/* These methods check if the real/imag parts of the sesqulinear form are
|
||||
not empty */
|
||||
bool RealInteg();
|
||||
bool ImagInteg();
|
||||
|
||||
public:
|
||||
ParMixedSesquilinearForm(
|
||||
ParFiniteElementSpace * trial_fes,
|
||||
ParFiniteElementSpace * test_fes,
|
||||
ComplexOperator::Convention convention = ComplexOperator::HERMITIAN);
|
||||
|
||||
/** @brief Create a ParMixedSesquilinearForm on the given trial and test
|
||||
ParFiniteElementSpaces, using the same integrators as the
|
||||
ParMixedBilinearForms @a pbfr and @a pbfi.
|
||||
|
||||
The ParFiniteElementSpace pointers are not owned by the newly
|
||||
constructed object.
|
||||
|
||||
The integrators are copied as pointers and they are not owned by the
|
||||
newly constructed ParMixedSesquilinearForm. */
|
||||
ParMixedSesquilinearForm(
|
||||
ParFiniteElementSpace * trial_fes,
|
||||
ParFiniteElementSpace * test_fes,
|
||||
ParMixedBilinearForm * pbfr,
|
||||
ParMixedBilinearForm * pbfi,
|
||||
ComplexOperator::Convention convention = ComplexOperator::HERMITIAN);
|
||||
|
||||
ComplexOperator::Convention GetConvention() const { return conv; }
|
||||
void SetConvention(const ComplexOperator::Convention & convention) { conv = convention; }
|
||||
|
||||
/// Set the desired assembly level.
|
||||
/** Valid choices are:
|
||||
|
||||
- AssemblyLevel::LEGACY (default)
|
||||
- AssemblyLevel::FULL
|
||||
- AssemblyLevel::PARTIAL
|
||||
- AssemblyLevel::ELEMENT
|
||||
- AssemblyLevel::NONE
|
||||
|
||||
This method must be called before assembly. */
|
||||
void SetAssemblyLevel(AssemblyLevel assembly_level)
|
||||
{
|
||||
pmblfr->SetAssemblyLevel(assembly_level);
|
||||
pmblfi->SetAssemblyLevel(assembly_level);
|
||||
}
|
||||
|
||||
ParMixedBilinearForm & real() { return *pmblfr; }
|
||||
ParMixedBilinearForm & imag() { return *pmblfi; }
|
||||
const ParMixedBilinearForm & real() const { return *pmblfr; }
|
||||
const ParMixedBilinearForm & imag() const { return *pmblfi; }
|
||||
|
||||
/// Adds new Domain Integrator.
|
||||
void AddDomainIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds new Domain Integrator, restricted to specific attributes.
|
||||
void AddDomainIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & elem_marker);
|
||||
|
||||
/// Adds new Boundary Integrator.
|
||||
void AddBoundaryIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/** @brief Adds new boundary Integrator, restricted to specific boundary
|
||||
attributes.
|
||||
|
||||
Assumes ownership of @a bfi.
|
||||
|
||||
The mfem::array @a bdr_marker is stored internally as a pointer to the given
|
||||
mfem::Array<int> object. */
|
||||
void AddBoundaryIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & bdr_marker);
|
||||
|
||||
/// Adds new interior Face Integrator. Assumes ownership of @a bfi.
|
||||
void AddInteriorFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds new boundary Face Integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/** @brief Adds new boundary Face Integrator, restricted to specific boundary
|
||||
attributes.
|
||||
|
||||
Assumes ownership of @a bfi.
|
||||
|
||||
The mfem::array @a bdr_marker is stored internally as a pointer to the given
|
||||
mfem::Array<int> object. */
|
||||
void AddBdrFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> & bdr_marker);
|
||||
|
||||
/** @brief Add a trace face integrator. Assumes ownership of @a bfi.
|
||||
|
||||
This type of integrator assembles terms over all faces of the mesh using
|
||||
the face FE from the trial space and the two adjacent volume FEs from
|
||||
the test space. */
|
||||
void AddTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds a boundary trace face integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag);
|
||||
|
||||
/// Adds a boundary trace face integrator. Assumes ownership of @a bfi.
|
||||
void AddBdrTraceFaceIntegrator(BilinearFormIntegrator * bfi_real,
|
||||
BilinearFormIntegrator * bfi_imag,
|
||||
Array<int> &bdr_marker);
|
||||
|
||||
/// Assemble the local matrix
|
||||
void Assemble(int skip_zeros = 1);
|
||||
|
||||
/// Finalizes the matrix initialization.
|
||||
void Finalize(int skip_zeros = 1);
|
||||
|
||||
/// Updates the internal mixed forms with the new finite element space.
|
||||
virtual void Update();
|
||||
|
||||
/// Returns the matrix assembled on the true dofs, i.e. P^t A P.
|
||||
/** The returned matrix has to be deleted by the caller. */
|
||||
ComplexHypreParMatrix * ParallelAssemble();
|
||||
|
||||
void FormRectangularLinearSystem(const Array<int> & ess_trial_tdof_list,
|
||||
const Array<int> & ess_test_tdof_list,
|
||||
Vector & x,
|
||||
Vector & b,
|
||||
OperatorHandle & A,
|
||||
Vector & X,
|
||||
Vector & B);
|
||||
|
||||
void FormRectangularSystemMatrix(const Array<int> & ess_trial_tdof_list,
|
||||
const Array<int> & ess_test_tdof_list,
|
||||
OperatorHandle & A);
|
||||
|
||||
virtual ~ParMixedSesquilinearForm();
|
||||
};
|
||||
|
||||
#endif // MFEM_USE_MPI
|
||||
|
||||
}
|
||||
|
||||
@@ -114,10 +114,6 @@ void ConduitDataCollection::Save()
|
||||
n_mesh["fields"][name]);
|
||||
}
|
||||
|
||||
// TODO: in parallel, we need to call ParFiniteElementSpace::ApplyDofSigns
|
||||
// for all ParGridFunction objects before and after saving, see
|
||||
// ParGridFunction::Save.
|
||||
|
||||
// save mesh data
|
||||
SaveMeshAndFields(myid,
|
||||
n_mesh,
|
||||
|
||||
+10
-41
@@ -38,24 +38,9 @@ int DataCollection::create_directory(const std::string &dir_name,
|
||||
// create directories recursively
|
||||
const char path_delim = '/';
|
||||
std::string::size_type pos = 0;
|
||||
int err_flag = 0;
|
||||
int err_flag;
|
||||
#ifdef MFEM_USE_MPI
|
||||
const ParMesh *pmesh = dynamic_cast<const ParMesh*>(mesh);
|
||||
// In addition to the global root, let the lowest rank on each shared-memory
|
||||
// node create the directory too, so that node-local (non-shared) filesystems
|
||||
// get it on every node rather than only where the global root lives. On a
|
||||
// shared filesystem the extra mkdir() hits EEXIST and is tolerated below.
|
||||
bool node_root = true;
|
||||
if (pmesh)
|
||||
{
|
||||
MPI_Comm node_comm;
|
||||
MPI_Comm_split_type(pmesh->GetComm(), MPI_COMM_TYPE_SHARED, myid,
|
||||
MPI_INFO_NULL, &node_comm);
|
||||
int node_rank;
|
||||
MPI_Comm_rank(node_comm, &node_rank);
|
||||
node_root = (node_rank == 0);
|
||||
MPI_Comm_free(&node_comm);
|
||||
}
|
||||
#endif
|
||||
|
||||
do
|
||||
@@ -67,7 +52,7 @@ int DataCollection::create_directory(const std::string &dir_name,
|
||||
err_flag = mkdir(subdir.c_str(), 0777);
|
||||
err_flag = (err_flag && (errno != EEXIST)) ? 1 : 0;
|
||||
#else
|
||||
if (node_root || pmesh == NULL)
|
||||
if (myid == 0 || pmesh == NULL)
|
||||
{
|
||||
err_flag = mkdir(subdir.c_str(), 0777);
|
||||
err_flag = (err_flag && (errno != EEXIST)) ? 1 : 0;
|
||||
@@ -79,8 +64,7 @@ int DataCollection::create_directory(const std::string &dir_name,
|
||||
#ifdef MFEM_USE_MPI
|
||||
if (pmesh)
|
||||
{
|
||||
MPI_Allreduce(MPI_IN_PLACE, &err_flag, 1, MPI_INT, MPI_MAX,
|
||||
pmesh->GetComm());
|
||||
MPI_Bcast(&err_flag, 1, MPI_INT, 0, pmesh->GetComm());
|
||||
}
|
||||
#endif
|
||||
|
||||
@@ -508,8 +492,6 @@ void VisItDataCollection::SaveRootFile()
|
||||
to_padded_string(cycle, pad_digits_cycle) +
|
||||
".mfem_root";
|
||||
std::ofstream root_file(root_name);
|
||||
MFEM_VERIFY(root_file.is_open(),
|
||||
"Failed to open ofstream " << root_name);
|
||||
root_file << GetVisItRootString();
|
||||
if (!root_file)
|
||||
{
|
||||
@@ -825,7 +807,7 @@ ParaViewDataCollectionBase::ParaViewDataCollectionBase(
|
||||
|
||||
void ParaViewDataCollectionBase::SetLevelsOfDetail(int levels_of_detail_)
|
||||
{
|
||||
levels_of_detail = std::max(levels_of_detail_, 1);
|
||||
levels_of_detail = levels_of_detail_;
|
||||
}
|
||||
|
||||
void ParaViewDataCollectionBase::SetHighOrderOutput(bool high_order_output_)
|
||||
@@ -995,10 +977,7 @@ void ParaViewDataCollection::Save()
|
||||
// Save the local part of the mesh and grid functions fields to the local
|
||||
// VTU file. Also save coefficient fields.
|
||||
{
|
||||
std::string os_str = vtu_prefix + GenerateVTUFileName("proc", myid);
|
||||
std::ofstream os(os_str);
|
||||
MFEM_VERIFY(os.is_open(),
|
||||
"Failed to open ofstream " << os_str);
|
||||
std::ofstream os(vtu_prefix + GenerateVTUFileName("proc", myid));
|
||||
os.precision(precision);
|
||||
SaveDataVTU(os, levels_of_detail);
|
||||
}
|
||||
@@ -1010,10 +989,7 @@ void ParaViewDataCollection::Save()
|
||||
"QuadratureFunction output is not supported for "
|
||||
"ParaViewDataCollection on domain boundary!");
|
||||
const std::string &field_name = qfield.first;
|
||||
std::string os_str = vtu_prefix + GenerateVTUFileName(field_name, myid);
|
||||
std::ofstream os(os_str);
|
||||
MFEM_VERIFY(os.is_open(),
|
||||
"Failed to open ofstream " << os_str);
|
||||
std::ofstream os(vtu_prefix + GenerateVTUFileName(field_name, myid));
|
||||
qfield.second->SaveVTU(os, pv_data_format, GetCompressionLevel(), field_name);
|
||||
}
|
||||
|
||||
@@ -1024,10 +1000,7 @@ void ParaViewDataCollection::Save()
|
||||
{
|
||||
// Create the main PVTU file
|
||||
{
|
||||
std::string os_str = vtu_prefix + GeneratePVTUFileName("data");
|
||||
std::ofstream pvtu_out(os_str);
|
||||
MFEM_VERIFY(pvtu_out.is_open(),
|
||||
"Failed to open ofstream " << os_str);
|
||||
std::ofstream pvtu_out(vtu_prefix + GeneratePVTUFileName("data"));
|
||||
WritePVTUHeader(pvtu_out);
|
||||
|
||||
// Grid function fields and coefficient fields
|
||||
@@ -1082,10 +1055,8 @@ void ParaViewDataCollection::Save()
|
||||
const std::string &q_field_name = q_field.first;
|
||||
std::string q_fname = GeneratePVTUPath() + "/"
|
||||
+ GeneratePVTUFileName(q_field_name);
|
||||
std::string os_str = col_path + "/" + q_fname;
|
||||
std::ofstream pvtu_out(os_str);
|
||||
MFEM_VERIFY(pvtu_out.is_open(),
|
||||
"Failed to open ofstream " << os_str);
|
||||
|
||||
std::ofstream pvtu_out(col_path + "/" + q_fname);
|
||||
WritePVTUHeader(pvtu_out);
|
||||
int vec_dim = q_field.second->GetVDim();
|
||||
pvtu_out << "<PPointData>\n";
|
||||
@@ -1197,14 +1168,12 @@ void ParaViewDataCollection::SaveGFieldVTU(std::ostream &os, int ref_,
|
||||
DenseMatrix vval, pmat;
|
||||
std::vector<char> buf;
|
||||
int vec_dim = it->second->VectorDim();
|
||||
int map_type = it->second->FESpace()->GetTypicalFE()->GetMapType();
|
||||
os << "<DataArray type=\"" << GetDataTypeString()
|
||||
<< "\" Name=\"" << it->first
|
||||
<< "\" NumberOfComponents=\"" << vec_dim << "\" "
|
||||
<< VTKComponentLabels(vec_dim) << " "
|
||||
<< "format=\"" << GetDataFormatString() << "\" >" << '\n';
|
||||
if (vec_dim == 1 && (map_type == FiniteElement::VALUE ||
|
||||
map_type == FiniteElement::INTEGRAL))
|
||||
if (vec_dim == 1)
|
||||
{
|
||||
for (int i = 0; i < mesh->GetNE(); i++)
|
||||
{
|
||||
|
||||
@@ -51,52 +51,4 @@ DifferentiableOperator::DifferentiableOperator(
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
void FDJacobian::Mult(const Vector &v, Vector &y) const
|
||||
{
|
||||
// See [1] for choice of eps.
|
||||
//
|
||||
// [1] Woodward, C.S., Gardner, D.J. and Evans, K.J., 2015. On the use of
|
||||
// finite difference matrix-vector products in Newton-Krylov solvers for
|
||||
// implicit climate dynamics with spectral elements. Procedia Computer
|
||||
// Science, 51, pp.2036-2045.
|
||||
real_t eps;
|
||||
if (fixed_eps > 0.0)
|
||||
{
|
||||
eps = fixed_eps;
|
||||
}
|
||||
else
|
||||
{
|
||||
const real_t vnorm_local = v.Norml2();
|
||||
real_t vnorm;
|
||||
MPI_Allreduce(&vnorm_local, &vnorm, 1, MPITypeMap<real_t>::mpi_type, MPI_SUM,
|
||||
MPI_COMM_WORLD);
|
||||
eps = lambda * (lambda + xnorm / vnorm);
|
||||
}
|
||||
|
||||
// x + eps * v
|
||||
{
|
||||
const auto d_v = v.Read();
|
||||
const auto d_x = x.Read();
|
||||
auto d_xpev = xpev.Write();
|
||||
mfem::forall(x.Size(), [=] MFEM_HOST_DEVICE (int i)
|
||||
{
|
||||
d_xpev[i] = d_x[i] + eps * d_v[i];
|
||||
});
|
||||
}
|
||||
|
||||
// y = f(x + eps * v)
|
||||
op.Mult(xpev, y);
|
||||
|
||||
// y = (f(x + eps * v) - f(x)) / eps
|
||||
{
|
||||
const auto d_f = f.Read();
|
||||
auto d_y = y.ReadWrite();
|
||||
mfem::forall(f.Size(), [=] MFEM_HOST_DEVICE (int i)
|
||||
{
|
||||
d_y[i] = (d_y[i] - d_f[i]) / eps;
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
#endif // MFEM_USE_MPI
|
||||
|
||||
+237
-64
@@ -84,29 +84,33 @@ public:
|
||||
const std::vector<derivative_action_t> &derivative_actions,
|
||||
const FieldDescriptor &direction,
|
||||
const int &daction_l_size,
|
||||
const std::vector<derivative_action_t> &derivative_actions_transpose,
|
||||
const int &derivative_action_tr_l_size,
|
||||
const std::vector<derivative_action_t> &derivative_tr_actions,
|
||||
const FieldDescriptor &transpose_direction,
|
||||
const int &daction_transpose_l_size,
|
||||
const std::vector<Vector *> &solutions_l,
|
||||
const std::vector<Vector *> ¶meters_l,
|
||||
const restriction_callback_t &restriction_callback,
|
||||
const std::function<void(Vector &, Vector &)> &prolongation_transpose,
|
||||
const std::function<void(Vector &, Vector &)> &tr_prolongation_transpose,
|
||||
const std::vector<assemble_derivative_sparsematrix_callback_t>
|
||||
&assemble_derivative_sparsematrix_callbacks,
|
||||
const std::vector<assemble_derivative_hypreparmatrix_callback_t>
|
||||
&assemble_derivative_hypreparmatrix_callbacks) :
|
||||
const assemble_derivative_hypreparmatrix_callback_t
|
||||
&assemble_derivative_hypreparmatrix_callback) :
|
||||
Operator(height, width),
|
||||
derivative_actions(derivative_actions),
|
||||
direction(direction),
|
||||
daction_l(daction_l_size),
|
||||
daction_l_size(daction_l_size),
|
||||
derivative_actions_transpose(derivative_actions_transpose),
|
||||
derivative_action_tr_l_size(derivative_action_tr_l_size),
|
||||
derivative_tr_actions(derivative_tr_actions),
|
||||
transpose_direction(transpose_direction),
|
||||
prolongation_transpose(prolongation_transpose),
|
||||
tr_prolongation_transpose(tr_prolongation_transpose),
|
||||
assemble_derivative_sparsematrix_callbacks(
|
||||
assemble_derivative_sparsematrix_callbacks),
|
||||
assemble_derivative_hypreparmatrix_callbacks(
|
||||
assemble_derivative_hypreparmatrix_callbacks)
|
||||
assemble_derivative_hypreparmatrix_callback(
|
||||
assemble_derivative_hypreparmatrix_callback)
|
||||
{
|
||||
std::vector<Vector> s_l(solutions_l.size());
|
||||
for (size_t i = 0; i < s_l.size(); i++)
|
||||
@@ -156,18 +160,18 @@ public:
|
||||
/// direction_t on T-dofs.
|
||||
void MultTranspose(const Vector &direction_t, Vector &result_t) const override
|
||||
{
|
||||
MFEM_ASSERT(!derivative_actions_transpose.empty(),
|
||||
MFEM_ASSERT(!derivative_tr_actions.empty(),
|
||||
"derivative can't be used to be multiplied in transpose mode");
|
||||
|
||||
daction_l.SetSize(width);
|
||||
daction_l.SetSize(derivative_action_tr_l_size);
|
||||
daction_l = 0.0;
|
||||
|
||||
prolongation(transpose_direction, direction_t, direction_l);
|
||||
for (const auto &f : derivative_actions_transpose)
|
||||
for (const auto &f : derivative_tr_actions)
|
||||
{
|
||||
f(fields_e, direction_l, daction_l);
|
||||
}
|
||||
prolongation_transpose(daction_l, result_t);
|
||||
tr_prolongation_transpose(daction_l, result_t);
|
||||
};
|
||||
|
||||
/// @brief Assemble the derivative operator into a SparseMatrix.
|
||||
@@ -183,6 +187,10 @@ public:
|
||||
{
|
||||
f(fields_e, A);
|
||||
}
|
||||
|
||||
// SparseMatrix A is finalized after all callbacks have contributed to
|
||||
// it.
|
||||
A->Finalize();
|
||||
}
|
||||
|
||||
/// @brief Assemble the derivative operator into a HypreParMatrix.
|
||||
@@ -191,13 +199,7 @@ public:
|
||||
/// be an uninitialized object.
|
||||
void Assemble(HypreParMatrix *&A)
|
||||
{
|
||||
MFEM_ASSERT(!assemble_derivative_hypreparmatrix_callbacks.empty(),
|
||||
"derivative can't be assembled into a HypreParMatrix");
|
||||
|
||||
for (const auto &f : assemble_derivative_hypreparmatrix_callbacks)
|
||||
{
|
||||
f(fields_e, A);
|
||||
}
|
||||
assemble_derivative_hypreparmatrix_callback(fields_e, A);
|
||||
}
|
||||
|
||||
private:
|
||||
@@ -212,10 +214,12 @@ private:
|
||||
|
||||
const int daction_l_size;
|
||||
|
||||
const int derivative_action_tr_l_size;
|
||||
|
||||
/// Transpose Derivative action callbacks. Depending on the requested
|
||||
/// derivatives in DifferentiableOperator the callbacks represent certain
|
||||
/// combinations of actions of derivatives of the forward operator.
|
||||
std::vector<derivative_action_t> derivative_actions_transpose;
|
||||
std::vector<derivative_action_t> derivative_tr_actions;
|
||||
|
||||
FieldDescriptor transpose_direction;
|
||||
|
||||
@@ -225,13 +229,15 @@ private:
|
||||
|
||||
std::function<void(Vector &, Vector &)> prolongation_transpose;
|
||||
|
||||
std::function<void(Vector &, Vector &)> tr_prolongation_transpose;
|
||||
|
||||
/// Callbacks that assemble derivatives into a SparseMatrix.
|
||||
std::vector<assemble_derivative_sparsematrix_callback_t>
|
||||
assemble_derivative_sparsematrix_callbacks;
|
||||
|
||||
/// Callbacks that assemble derivatives into a HypreParMatrix.
|
||||
std::vector<assemble_derivative_hypreparmatrix_callback_t>
|
||||
assemble_derivative_hypreparmatrix_callbacks;
|
||||
assemble_derivative_hypreparmatrix_callback_t
|
||||
assemble_derivative_hypreparmatrix_callback;
|
||||
};
|
||||
|
||||
/// Class representing a differentiable operator which acts on solution and
|
||||
@@ -457,7 +463,10 @@ public:
|
||||
dir_l = s_l[derivative_idx];
|
||||
}
|
||||
|
||||
derivative_setup_callbacks[derivative_id][0](fields_e, dir_l);
|
||||
for (size_t i = 0; i < derivative_setup_callbacks[derivative_id].size(); i++)
|
||||
{
|
||||
derivative_setup_callbacks[derivative_id][i](fields_e, dir_l);
|
||||
}
|
||||
|
||||
return std::make_shared<DerivativeOperator>(
|
||||
height,
|
||||
@@ -465,15 +474,17 @@ public:
|
||||
derivative_action_callbacks[derivative_id],
|
||||
fields[derivative_idx],
|
||||
residual_l.Size(),
|
||||
daction_transpose_callbacks[derivative_id],
|
||||
derivative_action_tr_l_size[derivative_id],
|
||||
derivative_action_tr_callbacks[derivative_id],
|
||||
fields[test_space_field_idx],
|
||||
GetVSize(fields[test_space_field_idx]),
|
||||
sol_l,
|
||||
par_l,
|
||||
restriction_callback,
|
||||
prolongation_transpose,
|
||||
derivative_tr_prolongation_transpose[derivative_id],
|
||||
assemble_derivative_sparsematrix_callbacks[derivative_id],
|
||||
assemble_derivative_hypreparmatrix_callbacks[derivative_id]);
|
||||
assemble_derivative_hypreparmatrix_callback[derivative_id]);
|
||||
}
|
||||
|
||||
private:
|
||||
@@ -486,13 +497,15 @@ private:
|
||||
std::map<size_t,
|
||||
std::vector<derivative_action_t>> derivative_action_callbacks;
|
||||
std::map<size_t,
|
||||
std::vector<derivative_action_t>> daction_transpose_callbacks;
|
||||
std::vector<derivative_action_t>> derivative_action_tr_callbacks;
|
||||
std::map<size_t,
|
||||
std::function<void(Vector &, Vector &)>> derivative_tr_prolongation_transpose;
|
||||
std::map<size_t, int> derivative_action_tr_l_size;
|
||||
std::map<size_t,
|
||||
std::vector<assemble_derivative_sparsematrix_callback_t>>
|
||||
assemble_derivative_sparsematrix_callbacks;
|
||||
std::map<size_t,
|
||||
std::vector<assemble_derivative_hypreparmatrix_callback_t>>
|
||||
assemble_derivative_hypreparmatrix_callbacks;
|
||||
std::map<size_t, assemble_derivative_hypreparmatrix_callback_t>
|
||||
assemble_derivative_hypreparmatrix_callback;
|
||||
|
||||
std::vector<FieldDescriptor> solutions;
|
||||
std::vector<FieldDescriptor> parameters;
|
||||
@@ -510,7 +523,7 @@ private:
|
||||
std::function<void(Vector &, Vector &)> output_restriction_transpose;
|
||||
restriction_callback_t restriction_callback;
|
||||
|
||||
std::map<size_t, Vector> derivative_qp_caches;
|
||||
std::map<size_t, std::vector<Vector>> derivative_qp_caches;
|
||||
|
||||
std::map<size_t, size_t> assembled_vector_sizes;
|
||||
|
||||
@@ -697,18 +710,17 @@ void DifferentiableOperator::AddIntegrator(
|
||||
|
||||
// The explicit captures are necessary to avoid dependency on
|
||||
// the specific instance of this class (this pointer).
|
||||
restriction_callback = [element_dof_ordering,
|
||||
solutions_ = this->solutions,
|
||||
parameters_ = this->parameters]
|
||||
(std::vector<Vector> &sol,
|
||||
const std::vector<Vector> &par,
|
||||
std::vector<Vector> &f)
|
||||
restriction_callback =
|
||||
[=, solutions = this->solutions, parameters = this->parameters]
|
||||
(std::vector<Vector> &sol,
|
||||
const std::vector<Vector> &par,
|
||||
std::vector<Vector> &f)
|
||||
{
|
||||
restriction<entity_t>(solutions_, sol, f,
|
||||
restriction<entity_t>(solutions, sol, f,
|
||||
element_dof_ordering);
|
||||
restriction<entity_t>(parameters_, par, f,
|
||||
restriction<entity_t>(parameters, par, f,
|
||||
element_dof_ordering,
|
||||
solutions_.size());
|
||||
solutions.size());
|
||||
};
|
||||
|
||||
prolongation_transpose = get_prolongation_transpose(
|
||||
@@ -770,9 +782,10 @@ void DifferentiableOperator::AddIntegrator(
|
||||
auto input_size_on_qp =
|
||||
get_input_size_on_qp(inputs, std::make_index_sequence<num_inputs> {});
|
||||
|
||||
// printf("calculate shmem action info\n");
|
||||
auto action_shmem_info =
|
||||
get_shmem_info<entity_t, num_fields, num_inputs, num_outputs>
|
||||
(input_dtq_maps, output_dtq_maps, fields, num_entities, inputs, num_qp,
|
||||
(input_dtq_maps, output_dtq_maps, fields, num_entities, num_qp,
|
||||
input_size_on_qp, residual_size_on_qp, element_dof_ordering);
|
||||
|
||||
Vector shmem_cache(action_shmem_info.total_size);
|
||||
@@ -836,19 +849,19 @@ void DifferentiableOperator::AddIntegrator(
|
||||
|
||||
// capture by ref:
|
||||
&restriction_cb = this->restriction_callback,
|
||||
&fields_e_ = this->fields_e,
|
||||
&residual_e_ = this->residual_e,
|
||||
&output_restriction_transpose_ = this->output_restriction_transpose
|
||||
&fields_e = this->fields_e,
|
||||
&residual_e = this->residual_e,
|
||||
&output_restriction_transpose = this->output_restriction_transpose
|
||||
]
|
||||
(std::vector<Vector> &sol, const std::vector<Vector> &par, Vector &res)
|
||||
mutable // mutable: needed to modify 'shmem_cache'
|
||||
{
|
||||
restriction_cb(sol, par, fields_e_);
|
||||
restriction_cb(sol, par, fields_e);
|
||||
|
||||
residual_e_ = 0.0;
|
||||
auto ye = Reshape(residual_e_.ReadWrite(), test_vdim, num_test_dof, num_entities);
|
||||
residual_e = 0.0;
|
||||
auto ye = Reshape(residual_e.ReadWrite(), test_vdim, num_test_dof, num_entities);
|
||||
|
||||
auto wrapped_fields_e = wrap_fields(fields_e_,
|
||||
auto wrapped_fields_e = wrap_fields(fields_e,
|
||||
action_shmem_info.field_sizes,
|
||||
num_entities);
|
||||
|
||||
@@ -879,7 +892,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
y, fhat, output_fop, output_dtq_shmem[0],
|
||||
scratch_shmem, dimension, use_sum_factorization);
|
||||
}, num_entities, thread_blocks, action_shmem_info.total_size, shmem_cache.ReadWrite());
|
||||
output_restriction_transpose_(residual_e_, res);
|
||||
output_restriction_transpose(residual_e, res);
|
||||
});
|
||||
|
||||
// Without this compile-time check, some valid instantiations of this method
|
||||
@@ -895,9 +908,10 @@ void DifferentiableOperator::AddIntegrator(
|
||||
const int da_size_on_qp =
|
||||
GetSizeOnQP<entity_t>(output_fop, fields[test_space_field_idx]);
|
||||
|
||||
// printf("calculate shmem derivative action info\n");
|
||||
auto shmem_info =
|
||||
get_shmem_info<entity_t, num_fields, num_inputs, num_outputs>(
|
||||
input_dtq_maps, output_dtq_maps, fields, num_entities, inputs,
|
||||
input_dtq_maps, output_dtq_maps, fields, num_entities,
|
||||
num_qp, input_size_on_qp, residual_size_on_qp,
|
||||
element_dof_ordering, d_field_idx);
|
||||
|
||||
@@ -969,9 +983,12 @@ void DifferentiableOperator::AddIntegrator(
|
||||
// Quadrature point local derivative cache for each element, with data
|
||||
// layout:
|
||||
// [test_vdim, test_op_dim, trial_vdim, trial_op_dim, qp, num_entities].
|
||||
derivative_qp_caches[derivative_id] = Vector(test_vdim * test_op_dim *
|
||||
trial_vdim *
|
||||
total_trial_op_dim * num_qp * num_entities);
|
||||
derivative_qp_caches[derivative_id].push_back(
|
||||
Vector(test_vdim * test_op_dim * trial_vdim * total_trial_op_dim * num_qp *
|
||||
num_entities));
|
||||
|
||||
const int cache_index = this->derivative_qp_caches[derivative_id].size() - 1;
|
||||
|
||||
// Create local references for MSVC lambda capture compatibility
|
||||
auto& fields_ref = this->fields;
|
||||
auto& derivative_qp_caches_ref = this->derivative_qp_caches[derivative_id];
|
||||
@@ -1013,6 +1030,8 @@ void DifferentiableOperator::AddIntegrator(
|
||||
trial_vdim,
|
||||
inputs_trial_op_dim,
|
||||
|
||||
qpdc_idx = cache_index,
|
||||
|
||||
// capture by ref:
|
||||
&qpdc_mem = derivative_qp_caches_ref
|
||||
](std::vector<Vector> &f_e, const Vector &dir_l) mutable
|
||||
@@ -1025,7 +1044,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
shmem_info.direction_size,
|
||||
num_entities);
|
||||
|
||||
auto qpdc = Reshape(qpdc_mem.ReadWrite(), test_vdim, test_op_dim,
|
||||
auto qpdc = Reshape(qpdc_mem[qpdc_idx].ReadWrite(), test_vdim, test_op_dim,
|
||||
trial_vdim, total_trial_op_dim, num_qp, num_entities);
|
||||
|
||||
auto itod = Reshape(inputs_trial_op_dim.Read(), num_inputs);
|
||||
@@ -1096,6 +1115,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
inputs_trial_op_dim,
|
||||
total_trial_op_dim,
|
||||
trial_vdim,
|
||||
qpdc_idx = cache_index,
|
||||
// capture by ref:
|
||||
&qpdc_mem = derivative_qp_caches_ref,
|
||||
&or_transpose
|
||||
@@ -1113,7 +1133,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
shmem_info.direction_size,
|
||||
num_entities);
|
||||
|
||||
auto qpdc = Reshape(qpdc_mem.Read(), test_vdim, test_op_dim,
|
||||
auto qpdc = Reshape(qpdc_mem[qpdc_idx].Read(), test_vdim, test_op_dim,
|
||||
trial_vdim, total_trial_op_dim, num_qp, num_entities);
|
||||
|
||||
auto itod = Reshape(inputs_trial_op_dim.Read(), num_inputs);
|
||||
@@ -1158,6 +1178,154 @@ void DifferentiableOperator::AddIntegrator(
|
||||
or_transpose(derivative_action_e, der_action_l);
|
||||
});
|
||||
|
||||
// This prevents Sum/Identity. These are invalid
|
||||
// as input FieldOperators anyways.
|
||||
constexpr auto dummy_fop = Value<0> {};
|
||||
|
||||
auto [input_rt,
|
||||
input_e_sz] = get_restriction_transpose<entity_t>
|
||||
(fields[d_field_idx],
|
||||
element_dof_ordering, dummy_fop);
|
||||
|
||||
const auto input_restriction_transpose = input_rt;
|
||||
|
||||
derivative_tr_prolongation_transpose[derivative_id] =
|
||||
get_prolongation_transpose(
|
||||
fields[d_field_idx], dummy_fop, mesh.GetComm());
|
||||
|
||||
const auto d_tr_field_idx = test_space_field_idx;
|
||||
const auto direction_tr = fields[d_tr_field_idx];
|
||||
|
||||
auto output_size_on_qp =
|
||||
get_input_size_on_qp(outputs, std::make_index_sequence<num_outputs> {});
|
||||
|
||||
const int residual_tr_size_on_qp = trial_vdim * total_trial_op_dim;
|
||||
|
||||
auto shmem_tr_info =
|
||||
get_shmem_info<entity_t, num_fields, num_outputs, num_inputs>(
|
||||
output_dtq_maps, input_dtq_maps, fields, num_entities,
|
||||
num_qp, output_size_on_qp, residual_tr_size_on_qp,
|
||||
element_dof_ordering, test_space_field_idx);
|
||||
|
||||
// print_shared_memory_info(shmem_tr_info);
|
||||
|
||||
// TODO: this is a hack to extend the shared memory with a known
|
||||
// offset for a temp variable
|
||||
Vector shmem_tr_cache(shmem_tr_info.total_size + residual_tr_size_on_qp *
|
||||
num_qp);
|
||||
|
||||
Vector direction_tr_e(get_restriction<entity_t>(
|
||||
fields[test_space_field_idx],
|
||||
element_dof_ordering)->Height());
|
||||
|
||||
derivative_action_tr_l_size[derivative_id] =
|
||||
get_restriction<entity_t>(fields[d_field_idx],
|
||||
element_dof_ordering)->Width();
|
||||
|
||||
Vector derivative_action_tr_e(input_e_sz);
|
||||
derivative_action_tr_e = 0.0;
|
||||
|
||||
derivative_action_tr_callbacks[derivative_id].push_back(
|
||||
[
|
||||
// capture by copy:
|
||||
dimension, // int
|
||||
num_entities, // int
|
||||
num_trial_dof, // int
|
||||
num_qp, // int
|
||||
q1d, // int
|
||||
test_vdim, // int (= output_fop.vdim)
|
||||
test_op_dim, // int (derived from output_fop)
|
||||
inputs, // mfem::future::tuple
|
||||
outputs, // mfem::future::tuple
|
||||
attributes, // Array<int>
|
||||
ir_weights, // DeviceTensor
|
||||
use_sum_factorization, // bool
|
||||
input_dtq_maps, // std::array<DofToQuadMap, num_fields>
|
||||
output_dtq_maps, // std::array<DofToQuadMap, num_fields>
|
||||
// output_fop, // class derived from FieldOperator
|
||||
thread_blocks, // ThreadBlocks
|
||||
shmem_tr_cache, // Vector (local)
|
||||
shmem_tr_info, // SharedMemoryInfo
|
||||
// TODO: make this Array<int> a member of the DifferentiableOperator
|
||||
// and capture it by ref.
|
||||
elem_attributes, // Array<int>
|
||||
|
||||
input_is_dependent,
|
||||
direction_tr, // FieldDescriptor
|
||||
direction_tr_e, // Vector
|
||||
derivative_action_tr_e, // Vector
|
||||
element_dof_ordering, // ElementDofOrdering
|
||||
inputs_trial_op_dim,
|
||||
total_trial_op_dim,
|
||||
trial_vdim,
|
||||
input_restriction_transpose,
|
||||
qpdc_idx = cache_index,
|
||||
// capture by ref:
|
||||
&qpdc_mem = derivative_qp_caches_ref
|
||||
](
|
||||
std::vector<Vector> &f_e, const Vector &dir_tr_l,
|
||||
Vector &derivative_action_tr_l) mutable
|
||||
{
|
||||
restriction<entity_t>(direction_tr, dir_tr_l, direction_tr_e,
|
||||
element_dof_ordering);
|
||||
auto ye = Reshape(derivative_action_tr_e.ReadWrite(), num_trial_dof,
|
||||
trial_vdim, num_entities);
|
||||
auto wrapped_fields_e = wrap_fields(f_e, shmem_tr_info.field_sizes,
|
||||
num_entities);
|
||||
auto wrapped_direction_e = Reshape(direction_tr_e.ReadWrite(),
|
||||
shmem_tr_info.direction_size,
|
||||
num_entities);
|
||||
|
||||
auto qpdc = Reshape(qpdc_mem[qpdc_idx].Read(), test_vdim, test_op_dim,
|
||||
trial_vdim, total_trial_op_dim, num_qp, num_entities);
|
||||
|
||||
auto itod = Reshape(inputs_trial_op_dim.Read(), num_inputs);
|
||||
|
||||
const bool has_attr = attributes.Size() > 0;
|
||||
const auto d_attr = attributes.Read();
|
||||
const auto d_elem_attr = elem_attributes->Read();
|
||||
|
||||
derivative_action_tr_e = 0.0;
|
||||
forall([=] MFEM_HOST_DEVICE (int e, real_t *shmem)
|
||||
{
|
||||
if (has_attr && !d_attr[d_elem_attr[e] - 1]) { return; }
|
||||
|
||||
auto [output_dtq_shmem, input_dtq_shmem, fields_shmem,
|
||||
direction_shmem, input_shmem,
|
||||
shadow_shmem_, residual_shmem,
|
||||
scratch_shmem] =
|
||||
unpack_shmem(shmem, shmem_tr_info, output_dtq_maps, input_dtq_maps,
|
||||
wrapped_fields_e, wrapped_direction_e, num_qp, e);
|
||||
auto &shadow_shmem = shadow_shmem_;
|
||||
|
||||
std::array<bool, num_outputs> all_true{true};
|
||||
map_direction_to_quadrature_data_conditional(
|
||||
shadow_shmem, direction_shmem, output_dtq_shmem, outputs,
|
||||
ir_weights, scratch_shmem, all_true, dimension,
|
||||
use_sum_factorization);
|
||||
|
||||
auto fhat = Reshape(&residual_shmem(0, 0), trial_vdim,
|
||||
total_trial_op_dim, num_qp);
|
||||
|
||||
auto qpdce = Reshape(&qpdc(0, 0, 0, 0, 0, e), test_vdim, test_op_dim,
|
||||
trial_vdim, total_trial_op_dim, num_qp);
|
||||
|
||||
constexpr bool transpose = true;
|
||||
apply_qpdc(fhat, shadow_shmem, qpdce, itod, q1d, dimension,
|
||||
use_sum_factorization, transpose);
|
||||
|
||||
auto y = Reshape(&ye(0, 0, e), num_trial_dof, trial_vdim);
|
||||
auto fi_shmem = Reshape(shmem + shmem_tr_info.total_size, trial_vdim,
|
||||
total_trial_op_dim, num_qp);
|
||||
|
||||
map_quadrature_data_to_fields_conditional(
|
||||
y, fhat, inputs, itod, input_dtq_shmem, scratch_shmem, fi_shmem,
|
||||
input_is_dependent, dimension, use_sum_factorization);
|
||||
}, num_entities, thread_blocks, shmem_tr_info.total_size,
|
||||
shmem_tr_cache.ReadWrite());
|
||||
input_restriction_transpose(derivative_action_tr_e, derivative_action_tr_l);
|
||||
});
|
||||
|
||||
assemble_derivative_sparsematrix_callbacks[derivative_id].push_back(
|
||||
[
|
||||
// capture by copy:
|
||||
@@ -1191,10 +1359,10 @@ void DifferentiableOperator::AddIntegrator(
|
||||
inputs_trial_op_dim,
|
||||
Ae_mem,
|
||||
output_to_field,
|
||||
|
||||
qpdc_idx = cache_index,
|
||||
// capture by ref:
|
||||
&qpdc_mem = derivative_qp_caches_ref,
|
||||
&fields_ = fields_ref
|
||||
&fields = fields_ref
|
||||
](std::vector<Vector> &f_e, SparseMatrix *&A) mutable
|
||||
{
|
||||
auto wrapped_fields_e = wrap_fields(f_e, shmem_info.field_sizes,
|
||||
@@ -1203,7 +1371,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
shmem_info.direction_size,
|
||||
num_entities);
|
||||
|
||||
auto qpdc = Reshape(qpdc_mem.Read(), test_vdim, test_op_dim,
|
||||
auto qpdc = Reshape(qpdc_mem[qpdc_idx].Read(), test_vdim, test_op_dim,
|
||||
trial_vdim, total_trial_op_dim, num_qp, num_entities);
|
||||
|
||||
auto itod = Reshape(inputs_trial_op_dim.Read(), num_inputs);
|
||||
@@ -1242,16 +1410,19 @@ void DifferentiableOperator::AddIntegrator(
|
||||
{
|
||||
if (input_is_dependent[s])
|
||||
{
|
||||
trial_field = &fields_[input_to_field[s]];
|
||||
trial_field = &fields[input_to_field[s]];
|
||||
}
|
||||
}
|
||||
|
||||
auto trial_fes = *std::get_if<const ParFiniteElementSpace *>
|
||||
(&trial_field->data);
|
||||
auto test_fes = *std::get_if<const ParFiniteElementSpace *>
|
||||
(&fields_[output_to_field[0]].data);
|
||||
(&fields[output_to_field[0]].data);
|
||||
|
||||
A = new SparseMatrix(test_fes->GetVSize(), trial_fes->GetVSize());
|
||||
if (A == nullptr)
|
||||
{
|
||||
A = new SparseMatrix(test_fes->GetVSize(), trial_fes->GetVSize());
|
||||
}
|
||||
|
||||
auto tmp = Reshape(Ae_mem.HostReadWrite(), num_test_dof * test_vdim,
|
||||
num_trial_dof * trial_vdim, num_entities);
|
||||
@@ -1322,20 +1493,21 @@ void DifferentiableOperator::AddIntegrator(
|
||||
A->AddSubMatrix(test_vdofs, trial_vdofs, Aee, 1);
|
||||
}
|
||||
}
|
||||
A->Finalize();
|
||||
// Don't finalize here since multiple callbacks might contribute to the same matrix
|
||||
// A->Finalize() will be called after all callbacks have contributed
|
||||
});
|
||||
|
||||
// Create local references for MSVC lambda capture compatibility
|
||||
auto& assemble_derivative_sparsematrix_callbacks_ref =
|
||||
this->assemble_derivative_sparsematrix_callbacks[derivative_id];
|
||||
|
||||
assemble_derivative_hypreparmatrix_callbacks[derivative_id].push_back(
|
||||
assemble_derivative_hypreparmatrix_callback[derivative_id] =
|
||||
[
|
||||
input_is_dependent,
|
||||
input_to_field,
|
||||
output_to_field,
|
||||
&spmatcb = assemble_derivative_sparsematrix_callbacks_ref,
|
||||
&fields_ = fields_ref
|
||||
&fields = fields_ref
|
||||
](std::vector<Vector> &f_e, HypreParMatrix *&A) mutable
|
||||
{
|
||||
SparseMatrix *spmat = nullptr;
|
||||
@@ -1343,6 +1515,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
{
|
||||
f(f_e, spmat);
|
||||
}
|
||||
spmat->Finalize();
|
||||
|
||||
if (spmat == nullptr)
|
||||
{
|
||||
@@ -1367,14 +1540,14 @@ void DifferentiableOperator::AddIntegrator(
|
||||
{
|
||||
if (input_is_dependent[s])
|
||||
{
|
||||
trial_field = &fields_[input_to_field[s]];
|
||||
trial_field = &fields[input_to_field[s]];
|
||||
}
|
||||
}
|
||||
|
||||
auto trial_fes = *std::get_if<const ParFiniteElementSpace *>
|
||||
(&trial_field->data);
|
||||
auto test_fes = *std::get_if<const ParFiniteElementSpace *>
|
||||
(&fields_[output_to_field[0]].data);
|
||||
(&fields[output_to_field[0]].data);
|
||||
|
||||
if (same_test_and_trial)
|
||||
{
|
||||
@@ -1396,7 +1569,7 @@ void DifferentiableOperator::AddIntegrator(
|
||||
trial_fes->Dof_TrueDof_Matrix());
|
||||
}
|
||||
delete spmat;
|
||||
});
|
||||
};
|
||||
}, derivative_ids);
|
||||
}
|
||||
}
|
||||
|
||||
+69
-11
@@ -90,8 +90,8 @@ void map_quadrature_data_to_fields_impl(
|
||||
}
|
||||
else
|
||||
{
|
||||
MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
|
||||
" for this field descriptor");
|
||||
MFEM_ABORT("quadrature data mapping to field is not implemented for"
|
||||
" this field descriptor");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -169,9 +169,8 @@ void map_quadrature_data_to_fields_tensor_impl_1d(
|
||||
}
|
||||
else
|
||||
{
|
||||
MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
|
||||
"for this field descriptor with sum factorization on"
|
||||
" tensor product elements");
|
||||
MFEM_ABORT("quadrature data mapping to field is not implemented for"
|
||||
" this field descriptor with sum factorization on tensor product elements");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -307,9 +306,8 @@ void map_quadrature_data_to_fields_tensor_impl_2d(
|
||||
}
|
||||
else
|
||||
{
|
||||
MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
|
||||
" for this field descriptor with sum factorization on"
|
||||
" tensor product elements");
|
||||
MFEM_ABORT("quadrature data mapping to field is not implemented for"
|
||||
" this field descriptor with sum factorization on tensor product elements");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -494,9 +492,8 @@ void map_quadrature_data_to_fields_tensor_impl_3d(
|
||||
}
|
||||
else
|
||||
{
|
||||
MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
|
||||
" for this field descriptor with sum factorization on"
|
||||
" tensor product elements");
|
||||
MFEM_ABORT("quadrature data mapping to field is not implemented for"
|
||||
" this field descriptor with sum factorization on tensor product elements");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -533,4 +530,65 @@ void map_quadrature_data_to_fields(
|
||||
}
|
||||
}
|
||||
|
||||
template <size_t N, typename field_operator_ts>
|
||||
MFEM_HOST_DEVICE
|
||||
void map_quadrature_data_to_fields_conditional(
|
||||
DeviceTensor<2, real_t> &y,
|
||||
const DeviceTensor<3, real_t> &f,
|
||||
const field_operator_ts &fops,
|
||||
const DeviceTensor<1, const real_t> &op_dims,
|
||||
const std::array<DofToQuadMap, N> &dtqmaps,
|
||||
std::array<DeviceTensor<1>, 6> &scratch_mem,
|
||||
const DeviceTensor<3> &fi_shmem,
|
||||
const std::array<bool, N> &conditions,
|
||||
const int &dimension,
|
||||
const bool &use_sum_factorization)
|
||||
{
|
||||
int offset = 0;
|
||||
for_constexpr<N>([&](auto i)
|
||||
{
|
||||
if (conditions[i])
|
||||
{
|
||||
[[maybe_unused]] const auto [K, unused, M] = f.GetShape();
|
||||
const int L = static_cast<int>(op_dims(static_cast<size_t>(i)));
|
||||
auto fi = Reshape(&fi_shmem(0, 0, 0), K, L, M);
|
||||
for (int k = 0; k < K; k++)
|
||||
{
|
||||
for (int l = 0; l < L; l++)
|
||||
{
|
||||
for (int m = 0; m < M; m++)
|
||||
{
|
||||
fi(k, l, m) = f(k, l + offset, m);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (use_sum_factorization)
|
||||
{
|
||||
if (dimension == 1)
|
||||
{
|
||||
map_quadrature_data_to_fields_tensor_impl_1d(
|
||||
y, fi, get<i>(fops), dtqmaps[i], scratch_mem);
|
||||
}
|
||||
else if (dimension == 2)
|
||||
{
|
||||
map_quadrature_data_to_fields_tensor_impl_2d(
|
||||
y, fi, get<i>(fops), dtqmaps[i], scratch_mem);
|
||||
}
|
||||
else if (dimension == 3)
|
||||
{
|
||||
map_quadrature_data_to_fields_tensor_impl_3d(
|
||||
y, fi, get<i>(fops), dtqmaps[i], scratch_mem);
|
||||
}
|
||||
else { MFEM_ABORT_KERNEL("dimension not supported"); }
|
||||
}
|
||||
else
|
||||
{
|
||||
map_quadrature_data_to_fields_impl(y, fi, get<i>(fops), dtqmaps[i]);
|
||||
}
|
||||
offset += L;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
} // namespace mfem::future
|
||||
|
||||
+12
-17
@@ -505,13 +505,13 @@ void map_field_to_quadrature_data(
|
||||
}
|
||||
}
|
||||
|
||||
template <typename field_operator_ts, size_t num_inputs, size_t num_fields>
|
||||
template <typename field_operator_ts, size_t N, size_t M>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void map_fields_to_quadrature_data(
|
||||
std::array<DeviceTensor<2>, num_inputs> &fields_qp,
|
||||
const std::array<DeviceTensor<1>, num_fields> &fields_e,
|
||||
const std::array<DofToQuadMap, num_inputs> &dtqmaps,
|
||||
const std::array<size_t, num_inputs> &input_to_field,
|
||||
std::array<DeviceTensor<2>, N> &fields_qp,
|
||||
const std::array<DeviceTensor<1>, M> &fields_e,
|
||||
const std::array<DofToQuadMap, N> &dtqmaps,
|
||||
const std::array<size_t, N> &input_to_field,
|
||||
const field_operator_ts &fops,
|
||||
const DeviceTensor<1, const real_t> &integration_weights,
|
||||
const std::array<DeviceTensor<1>, 6> &scratch_mem,
|
||||
@@ -523,7 +523,7 @@ void map_fields_to_quadrature_data(
|
||||
// attached to them and we create a dummy field which is not accessed
|
||||
// inside the functions it is passed to.
|
||||
const auto dummy_field_weight = DeviceTensor<1>(nullptr, 0);
|
||||
for_constexpr<num_inputs>([&](auto i)
|
||||
for_constexpr<N>([&](auto i)
|
||||
{
|
||||
const DeviceTensor<1> &field_e =
|
||||
(input_to_field[i] == SIZE_MAX) ? dummy_field_weight :
|
||||
@@ -549,12 +549,7 @@ void map_fields_to_quadrature_data(
|
||||
fields_qp[i], dtqmaps[i], field_e, get<i>(fops),
|
||||
integration_weights, scratch_mem);
|
||||
}
|
||||
else
|
||||
{
|
||||
#if !(defined(MFEM_USE_CUDA) || defined(MFEM_USE_HIP))
|
||||
MFEM_ABORT("unsupported dimension");
|
||||
#endif
|
||||
}
|
||||
else { MFEM_ABORT_KERNEL("unsupported dimension"); }
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -627,20 +622,20 @@ void map_fields_to_quadrature_data_conditional(
|
||||
});
|
||||
}
|
||||
|
||||
template <size_t num_inputs, typename field_operator_ts>
|
||||
template <size_t N, typename field_operator_ts>
|
||||
MFEM_HOST_DEVICE
|
||||
void map_direction_to_quadrature_data_conditional(
|
||||
std::array<DeviceTensor<2>, num_inputs> &directions_qp,
|
||||
std::array<DeviceTensor<2>, N> &directions_qp,
|
||||
const DeviceTensor<1> &direction_e,
|
||||
const std::array<DofToQuadMap, num_inputs> &dtqmaps,
|
||||
const std::array<DofToQuadMap, N> &dtqmaps,
|
||||
field_operator_ts fops,
|
||||
const DeviceTensor<1, const real_t> &integration_weights,
|
||||
const std::array<DeviceTensor<1>, 6> &scratch_mem,
|
||||
const std::array<bool, num_inputs> &conditions,
|
||||
const std::array<bool, N> &conditions,
|
||||
const int &dimension,
|
||||
const bool &use_sum_factorization)
|
||||
{
|
||||
for_constexpr<num_inputs>([&](auto i)
|
||||
for_constexpr<N>([&](auto i)
|
||||
{
|
||||
if (conditions[i])
|
||||
{
|
||||
|
||||
@@ -82,7 +82,7 @@ protected:
|
||||
};
|
||||
|
||||
/// @brief Uniform parameter space
|
||||
class UniformParameterSpace : public ParameterSpace
|
||||
class UniformParameterSpace final : public ParameterSpace
|
||||
{
|
||||
public:
|
||||
/// @brief Constructor for a uniform parameter space
|
||||
|
||||
@@ -379,54 +379,102 @@ namespace detail
|
||||
/// @param shadow_shmem the shadow shared memory.
|
||||
/// @param qpdc the quadrature point data cache holding the resulting
|
||||
/// Jacobians on each quadrature point.
|
||||
/// @param itod inputs trial operator dimension.
|
||||
/// If input is dependent the value corresponds to the spatial dimension, otherwise
|
||||
/// a zero indicates non-dependence on the variable.
|
||||
/// @param op_dims operator dimensions.
|
||||
/// If an operator is dependent, the value corresponds to the spatial dimension.
|
||||
/// Otherwise a zero indicates indepence on the variable.
|
||||
/// @param q the current quadrature point index.
|
||||
template <size_t num_fields>
|
||||
/// @param transpose switch to use transpose action.
|
||||
template <size_t N>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void apply_qpdc(
|
||||
DeviceTensor<3> &fhat,
|
||||
const std::array<DeviceTensor<2>, num_fields> &shadow_shmem,
|
||||
const std::array<DeviceTensor<2>, N> &shadow_shmem,
|
||||
const DeviceTensor<5, const real_t> &qpdc,
|
||||
const DeviceTensor<1, const real_t> &itod,
|
||||
const int &q)
|
||||
const DeviceTensor<1, const real_t> &op_dims,
|
||||
const int &q,
|
||||
bool transpose)
|
||||
{
|
||||
const size_t num_ops = op_dims.GetShape()[0];
|
||||
|
||||
const int test_vdim = qpdc.GetShape()[0];
|
||||
const int test_op_dim = qpdc.GetShape()[1];
|
||||
const int trial_vdim = qpdc.GetShape()[2];
|
||||
const int num_qp = qpdc.GetShape()[4];
|
||||
const size_t num_inputs = itod.GetShape()[0];
|
||||
const int total_trial_op_dim = qpdc.GetShape()[3];
|
||||
|
||||
for (int i = 0; i < test_vdim; i++)
|
||||
const int num_qp = qpdc.GetShape()[4];
|
||||
|
||||
if (transpose)
|
||||
{
|
||||
for (int k = 0; k < test_op_dim; k++)
|
||||
for (int j = 0; j < trial_vdim; j++)
|
||||
{
|
||||
real_t sum = 0.0;
|
||||
int m_offset = 0;
|
||||
for (size_t s = 0; s < num_inputs; s++)
|
||||
for (int m = 0; m < total_trial_op_dim; m++)
|
||||
{
|
||||
const int trial_op_dim = static_cast<int>(itod(s));
|
||||
if (trial_op_dim == 0)
|
||||
{
|
||||
continue;
|
||||
}
|
||||
const auto d_qp =
|
||||
Reshape(&(shadow_shmem[s])[0], trial_vdim, trial_op_dim, num_qp);
|
||||
for (int j = 0; j < trial_vdim; j++)
|
||||
{
|
||||
for (int m = 0; m < trial_op_dim; m++)
|
||||
{
|
||||
sum += qpdc(i, k, j, m + m_offset, q) * d_qp(j, m, q);
|
||||
}
|
||||
}
|
||||
m_offset += trial_op_dim;
|
||||
fhat(j, m, q) = 0.0;
|
||||
}
|
||||
}
|
||||
|
||||
// Since we don't support more than output space right now
|
||||
// shadow_shmem will always be of size 1.
|
||||
constexpr int shadow_idx_tr = 0;
|
||||
auto d_qp = Reshape(&(shadow_shmem[shadow_idx_tr])[0], test_vdim, test_op_dim,
|
||||
num_qp);
|
||||
|
||||
int m_offset = 0;
|
||||
for (size_t s = 0; s < num_ops; s++)
|
||||
{
|
||||
const int trial_op_dim = static_cast<int>(op_dims(s));
|
||||
if (trial_op_dim == 0) { continue; }
|
||||
|
||||
for (int j = 0; j < trial_vdim; j++)
|
||||
{
|
||||
for (int m = 0; m < trial_op_dim; m++)
|
||||
{
|
||||
real_t sum = 0.0;
|
||||
for (int i = 0; i < test_vdim; i++)
|
||||
{
|
||||
for (int k = 0; k < test_op_dim; k++)
|
||||
{
|
||||
const real_t contrib = qpdc(i, k, j, m + m_offset, q) * d_qp(i, k, q);
|
||||
sum += contrib;
|
||||
}
|
||||
}
|
||||
fhat(j, m + m_offset, q) += sum;
|
||||
}
|
||||
}
|
||||
m_offset += trial_op_dim;
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
for (int i = 0; i < test_vdim; i++)
|
||||
{
|
||||
for (int k = 0; k < test_op_dim; k++)
|
||||
{
|
||||
real_t sum = 0.0;
|
||||
int m_offset = 0;
|
||||
for (size_t s = 0; s < num_ops; s++)
|
||||
{
|
||||
const int trial_op_dim = static_cast<int>(op_dims(s));
|
||||
if (trial_op_dim == 0) { continue; }
|
||||
|
||||
const auto d_qp =
|
||||
Reshape(&(shadow_shmem[s])[0], trial_vdim, trial_op_dim, num_qp);
|
||||
for (int j = 0; j < trial_vdim; j++)
|
||||
{
|
||||
for (int m = 0; m < trial_op_dim; m++)
|
||||
{
|
||||
sum += qpdc(i, k, j, m + m_offset, q) * d_qp(j, m, q);
|
||||
}
|
||||
}
|
||||
m_offset += trial_op_dim;
|
||||
}
|
||||
fhat(i, k, q) = sum;
|
||||
}
|
||||
fhat(i, k, q) = sum;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace detail
|
||||
|
||||
/// @brief Apply the quadrature point data cache (qpdc) to a vector
|
||||
/// (usually a direction).
|
||||
@@ -445,16 +493,18 @@ void apply_qpdc(
|
||||
/// @param q1d number of quadrature points in 1D.
|
||||
/// @param dimension spatial dimension.
|
||||
/// @param use_sum_factorization whether to use sum factorization.
|
||||
template <size_t num_fields>
|
||||
/// @param T switch to use transpose application.
|
||||
template <size_t N>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void apply_qpdc(
|
||||
DeviceTensor<3> &fhat,
|
||||
const std::array<DeviceTensor<2>, num_fields> &shadow_shmem,
|
||||
const std::array<DeviceTensor<2>, N> &shadow_shmem,
|
||||
const DeviceTensor<5, const real_t> &qpdc,
|
||||
const DeviceTensor<1, const real_t> &itod,
|
||||
const int &q1d,
|
||||
const int &dimension,
|
||||
const bool &use_sum_factorization)
|
||||
const bool &use_sum_factorization,
|
||||
const bool T = false)
|
||||
{
|
||||
if (use_sum_factorization)
|
||||
{
|
||||
@@ -462,7 +512,7 @@ void apply_qpdc(
|
||||
{
|
||||
MFEM_FOREACH_THREAD_DIRECT(q, x, q1d)
|
||||
{
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q);
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q, T);
|
||||
}
|
||||
}
|
||||
else if (dimension == 2)
|
||||
@@ -472,7 +522,7 @@ void apply_qpdc(
|
||||
MFEM_FOREACH_THREAD_DIRECT(qy, y, q1d)
|
||||
{
|
||||
const int q = qx + q1d * qy;
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q);
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q, T);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -485,7 +535,7 @@ void apply_qpdc(
|
||||
MFEM_FOREACH_THREAD_DIRECT(qz, z, q1d)
|
||||
{
|
||||
const int q = qx + q1d * (qy + q1d * qz);
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q);
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q, T);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -500,7 +550,7 @@ void apply_qpdc(
|
||||
const int num_qp = qpdc.GetShape()[4];
|
||||
MFEM_FOREACH_THREAD_DIRECT(q, x, num_qp)
|
||||
{
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q);
|
||||
detail::apply_qpdc(fhat, shadow_shmem, qpdc, itod, q, T);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -243,6 +243,35 @@ void process_qf_arg(
|
||||
}
|
||||
}
|
||||
|
||||
template <typename T, int n>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void process_qf_arg(
|
||||
const DeviceTensor<1, T> &u,
|
||||
const DeviceTensor<1, T> &v,
|
||||
tensor<T, n> &arg)
|
||||
{
|
||||
for (int i = 0; i < n; i++)
|
||||
{
|
||||
arg(i) = u(i);
|
||||
}
|
||||
}
|
||||
|
||||
template <typename T, int n, int m>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void process_qf_arg(
|
||||
const DeviceTensor<1, T> &u,
|
||||
const DeviceTensor<1, T> &v,
|
||||
tensor<T, n, m> &arg)
|
||||
{
|
||||
for (int i = 0; i < m; i++)
|
||||
{
|
||||
for (int j = 0; j < n; j++)
|
||||
{
|
||||
arg(j, i) = u((i * n) + j);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
template <typename arg_type>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void process_qf_arg(const DeviceTensor<2> &u, arg_type &arg, int qp)
|
||||
@@ -327,20 +356,4 @@ void process_qf_result(
|
||||
}
|
||||
}
|
||||
|
||||
template <typename T, int n, int m>
|
||||
MFEM_HOST_DEVICE inline
|
||||
void process_qf_arg(
|
||||
const DeviceTensor<1, T> &u,
|
||||
const DeviceTensor<1, T> &v,
|
||||
tensor<T, n, m> &arg)
|
||||
{
|
||||
for (int i = 0; i < m; i++)
|
||||
{
|
||||
for (int j = 0; j < n; j++)
|
||||
{
|
||||
arg(j, i) = u((i * n) + j);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace mfem::future
|
||||
|
||||
+768
-742
File diff suppressed because it is too large
Load Diff
+61
-12
@@ -597,7 +597,7 @@ struct ThreadBlocks
|
||||
int z = 1;
|
||||
};
|
||||
|
||||
#if defined(MFEM_USE_CUDA_OR_HIP_LANG)
|
||||
#if defined(MFEM_USE_CUDA_OR_HIP)
|
||||
template <typename func_t>
|
||||
__global__ void forall_kernel_shmem(func_t f, int n)
|
||||
{
|
||||
@@ -617,11 +617,10 @@ void forall(func_t f,
|
||||
int num_shmem = 0,
|
||||
real_t *shmem = nullptr)
|
||||
{
|
||||
internal::RequireKernelCompilation();
|
||||
|
||||
#if defined(MFEM_USE_CUDA_OR_HIP_LANG)
|
||||
if (Device::Allows(Backend::CUDA_MASK | Backend::HIP_MASK))
|
||||
if (Device::Allows(Backend::CUDA_MASK) ||
|
||||
Device::Allows(Backend::HIP_MASK))
|
||||
{
|
||||
#if defined(MFEM_USE_CUDA_OR_HIP)
|
||||
// int gridsize = (N + Z - 1) / Z;
|
||||
int num_bytes = num_shmem * sizeof(decltype(shmem));
|
||||
dim3 block_size(blocks.x, blocks.y, blocks.z);
|
||||
@@ -632,10 +631,9 @@ void forall(func_t f,
|
||||
MFEM_GPU_CHECK(hipGetLastError());
|
||||
#endif
|
||||
MFEM_DEVICE_SYNC;
|
||||
return;
|
||||
}
|
||||
#endif
|
||||
if (Device::Allows(Backend::CPU_MASK))
|
||||
}
|
||||
else if (Device::Allows(Backend::CPU_MASK))
|
||||
{
|
||||
MFEM_ASSERT(!((bool)num_shmem != (bool)shmem),
|
||||
"Backend::CPU needs a pre-allocated shared memory block");
|
||||
@@ -673,7 +671,52 @@ public:
|
||||
MPI_COMM_WORLD);
|
||||
}
|
||||
|
||||
void Mult(const Vector &v, Vector &y) const override;
|
||||
void Mult(const Vector &v, Vector &y) const override
|
||||
{
|
||||
// See [1] for choice of eps.
|
||||
//
|
||||
// [1] Woodward, C.S., Gardner, D.J. and Evans, K.J., 2015. On the use of
|
||||
// finite difference matrix-vector products in Newton-Krylov solvers for
|
||||
// implicit climate dynamics with spectral elements. Procedia Computer
|
||||
// Science, 51, pp.2036-2045.
|
||||
real_t eps;
|
||||
if (fixed_eps > 0.0)
|
||||
{
|
||||
eps = fixed_eps;
|
||||
}
|
||||
else
|
||||
{
|
||||
const real_t vnorm_local = v.Norml2();
|
||||
real_t vnorm;
|
||||
MPI_Allreduce(&vnorm_local, &vnorm, 1, MPITypeMap<real_t>::mpi_type, MPI_SUM,
|
||||
MPI_COMM_WORLD);
|
||||
eps = lambda * (lambda + xnorm / vnorm);
|
||||
}
|
||||
|
||||
// x + eps * v
|
||||
{
|
||||
const auto d_v = v.Read();
|
||||
const auto d_x = x.Read();
|
||||
auto d_xpev = xpev.Write();
|
||||
mfem::forall(x.Size(), [=] MFEM_HOST_DEVICE (int i)
|
||||
{
|
||||
d_xpev[i] = d_x[i] + eps * d_v[i];
|
||||
});
|
||||
}
|
||||
|
||||
// y = f(x + eps * v)
|
||||
op.Mult(xpev, y);
|
||||
|
||||
// y = (f(x + eps * v) - f(x)) / eps
|
||||
{
|
||||
const auto d_f = f.Read();
|
||||
auto d_y = y.ReadWrite();
|
||||
mfem::forall(f.Size(), [=] MFEM_HOST_DEVICE (int i)
|
||||
{
|
||||
d_y[i] = (d_y[i] - d_f[i]) / eps;
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
virtual MemoryClass GetMemoryClass() const override
|
||||
{
|
||||
@@ -1159,7 +1202,14 @@ std::function<void(const Vector&, Vector&)> get_prolongation_transpose(
|
||||
const Operator *P = get_prolongation(f);
|
||||
auto PT = [=](const Vector &r_local, Vector &y)
|
||||
{
|
||||
P->MultTranspose(r_local, y);
|
||||
if (P)
|
||||
{
|
||||
P->MultTranspose(r_local, y);
|
||||
}
|
||||
else
|
||||
{
|
||||
y = r_local;
|
||||
}
|
||||
};
|
||||
return PT;
|
||||
}
|
||||
@@ -1537,14 +1587,13 @@ struct SharedMemoryInfo
|
||||
std::array<int, 6> temp_sizes;
|
||||
};
|
||||
|
||||
template <typename entity_t, std::size_t num_fields, std::size_t num_inputs, std::size_t num_outputs, typename input_t>
|
||||
template <typename entity_t, std::size_t num_fields, std::size_t num_inputs, std::size_t num_outputs>
|
||||
SharedMemoryInfo<num_fields, num_inputs, num_outputs>
|
||||
get_shmem_info(
|
||||
const std::array<DofToQuadMap, num_inputs> &input_dtq_maps,
|
||||
const std::array<DofToQuadMap, num_outputs> &output_dtq_maps,
|
||||
const std::vector<FieldDescriptor> &fields,
|
||||
const int &num_entities,
|
||||
const input_t &inputs,
|
||||
const int &num_qp,
|
||||
const std::vector<int> &input_size_on_qp,
|
||||
const int &residual_size_on_qp,
|
||||
|
||||
@@ -57,7 +57,7 @@ void DGMassApply(const int e,
|
||||
}
|
||||
else if (DIM == 3)
|
||||
{
|
||||
SmemPAMassApply3D_Element<TD1D,TQ1D,NBZ,ACCUM>(e, NE, B, pa_data, x, y);
|
||||
SmemPAMassApply3D_Element<TD1D,TQ1D,ACCUM>(e, NE, B, pa_data, x, y);
|
||||
}
|
||||
else
|
||||
{
|
||||
|
||||
+6
-6
@@ -320,8 +320,8 @@ public:
|
||||
error estimation procedure where the flux averaging is replaced by a global
|
||||
L2 projection (requiring a mass matrix solve).
|
||||
|
||||
The required BilinearFormIntegrator must implement the method
|
||||
ComputeElementFlux().
|
||||
The required BilinearFormIntegrator must implement the methods
|
||||
ComputeElementFlux() and ComputeFluxEnergy().
|
||||
|
||||
Implemented for the parallel case only.
|
||||
*/
|
||||
@@ -357,8 +357,8 @@ protected:
|
||||
|
||||
public:
|
||||
/** @brief Construct a new L2ZienkiewiczZhuEstimator object.
|
||||
@param integ This BilinearFormIntegrator must implement the method
|
||||
ComputeElementFlux().
|
||||
@param integ This BilinearFormIntegrator must implement the methods
|
||||
ComputeElementFlux() and ComputeFluxEnergy().
|
||||
@param sol The solution field whose error is to be estimated.
|
||||
@param flux_fes The L2ZienkiewiczZhuEstimator assumes ownership of this
|
||||
FiniteElementSpace and will call its Update() method when
|
||||
@@ -382,8 +382,8 @@ public:
|
||||
{ }
|
||||
|
||||
/** @brief Construct a new L2ZienkiewiczZhuEstimator object.
|
||||
@param integ This BilinearFormIntegrator must implement the method
|
||||
ComputeElementFlux().
|
||||
@param integ This BilinearFormIntegrator must implement the methods
|
||||
ComputeElementFlux() and ComputeFluxEnergy().
|
||||
@param sol The solution field whose error is to be estimated.
|
||||
@param flux_fes The L2ZienkiewiczZhuEstimator does NOT assume ownership
|
||||
of this FiniteElementSpace; will call its Update() method
|
||||
|
||||
+10
-88
@@ -1044,50 +1044,9 @@ void VectorFiniteElement::SetDerivMembers()
|
||||
switch (map_type)
|
||||
{
|
||||
case H_DIV:
|
||||
switch (dim)
|
||||
{
|
||||
case 3: // div: 3D H_DIV -> 3D INTEGRAL
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
case 2: // div: 2D H_DIV -> 2D INTEGRAL
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
break;
|
||||
case H_DIV_R2D:
|
||||
switch (dim)
|
||||
{
|
||||
case 2: // div: 2D H_DIV_R2D -> 2D INTEGRAL
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
case 1: // div: 1D H_DIV_R2D -> 1D INTEGRAL
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
break;
|
||||
case H_DIV_R1D:
|
||||
switch (dim)
|
||||
{
|
||||
case 1: // div: 1D H_DIV_R1D -> 1D INTEGRAL
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
deriv_type = DIV;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
case H_CURL:
|
||||
switch (dim)
|
||||
@@ -1105,49 +1064,13 @@ void VectorFiniteElement::SetDerivMembers()
|
||||
break;
|
||||
case 1:
|
||||
deriv_type = NONE;
|
||||
deriv_range_type = UNKNOWN_RANGE_TYPE;
|
||||
deriv_map_type = UNKNOWN_MAP_TYPE;
|
||||
deriv_range_type = SCALAR;
|
||||
deriv_map_type = INTEGRAL;
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
break;
|
||||
case H_CURL_R2D:
|
||||
switch (dim)
|
||||
{
|
||||
case 2:
|
||||
// curl: 2D H_CURL_R2D -> H_DIV_R2D
|
||||
deriv_type = CURL;
|
||||
deriv_range_type = VECTOR;
|
||||
deriv_map_type = H_DIV_R2D;
|
||||
break;
|
||||
case 1:
|
||||
// curl: 1D H_CURL_R2D -> H_DIV_R2D
|
||||
deriv_type = CURL;
|
||||
deriv_range_type = VECTOR;
|
||||
deriv_map_type = H_DIV_R2D;
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
break;
|
||||
case H_CURL_R1D:
|
||||
switch (dim)
|
||||
{
|
||||
case 1:
|
||||
// curl: 1D H_CURL_R1D -> H_DIV_R1D
|
||||
deriv_type = CURL;
|
||||
deriv_range_type = VECTOR;
|
||||
deriv_map_type = H_DIV_R1D;
|
||||
break;
|
||||
case 0:
|
||||
deriv_type = NONE;
|
||||
deriv_range_type = UNKNOWN_RANGE_TYPE;
|
||||
deriv_map_type = UNKNOWN_MAP_TYPE;
|
||||
default:
|
||||
MFEM_ABORT("Invalid dimension, Dim = " << dim);
|
||||
}
|
||||
break;
|
||||
default:
|
||||
MFEM_ABORT("Invalid MapType = " << map_type);
|
||||
}
|
||||
@@ -1316,14 +1239,13 @@ void VectorFiniteElement::Project_RT(
|
||||
}
|
||||
}
|
||||
|
||||
void VectorFiniteElement::ProjectCurl2D_RT(
|
||||
void VectorFiniteElement::ProjectGrad_RT(
|
||||
const real_t *nk, const Array<int> &d2n, const FiniteElement &fe,
|
||||
ElementTransformation &Trans, DenseMatrix &grad) const
|
||||
{
|
||||
// 2D "ProjectCurl_RT"
|
||||
if (dim != 2)
|
||||
{
|
||||
mfem_error("VectorFiniteElement::ProjectCurl2D_RT works only in 2D!");
|
||||
mfem_error("VectorFiniteElement::ProjectGrad_RT works only in 2D!");
|
||||
}
|
||||
|
||||
DenseMatrix dshape(fe.GetDof(), fe.GetDim());
|
||||
@@ -1334,8 +1256,8 @@ void VectorFiniteElement::ProjectCurl2D_RT(
|
||||
for (int k = 0; k < dof; k++)
|
||||
{
|
||||
fe.CalcDShape(Nodes.IntPoint(k), dshape);
|
||||
tk[0] = -nk[d2n[k]*dim+1];
|
||||
tk[1] = nk[d2n[k]*dim];
|
||||
tk[0] = nk[d2n[k]*dim+1];
|
||||
tk[1] = -nk[d2n[k]*dim];
|
||||
dshape.Mult(tk, grad_k);
|
||||
for (int j = 0; j < grad_k.Size(); j++)
|
||||
{
|
||||
@@ -1382,7 +1304,7 @@ void VectorFiniteElement::ProjectCurl_ND(
|
||||
}
|
||||
}
|
||||
|
||||
void VectorFiniteElement::ProjectCurl3D_RT(
|
||||
void VectorFiniteElement::ProjectCurl_RT(
|
||||
const real_t *nk, const Array<int> &d2n, const FiniteElement &fe,
|
||||
ElementTransformation &Trans, DenseMatrix &curl) const
|
||||
{
|
||||
|
||||
+11
-83
@@ -167,15 +167,7 @@ public:
|
||||
/** @brief Full multidimensional representation which does not use tensor
|
||||
product structure. The ordering of the degrees of freedom is the
|
||||
same as TENSOR, but the sizes of B and G are the same as FULL.*/
|
||||
LEXICOGRAPHIC_FULL,
|
||||
|
||||
/** @brief Ragged tensor product representation using 1D matrices/tensors
|
||||
with dimensions using 1D number of quadrature points and ragged tensor degrees of
|
||||
freedom. */
|
||||
/** Used only for partial assembly of the H1 positive basis. The
|
||||
size of B is d1d x qnpt x dim. Since different Gauss-Jacobi quadrature rules
|
||||
are employed in each dimension, we need to store dim arrays. */
|
||||
RAGGED_TENSOR
|
||||
LEXICOGRAPHIC_FULL
|
||||
};
|
||||
|
||||
/// Describes the contents of the #B, #Bt, #G, and #Gt arrays, see #Mode.
|
||||
@@ -236,39 +228,6 @@ public:
|
||||
const Array<DofToQuad*> &dof2quad_array,
|
||||
const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode);
|
||||
|
||||
virtual ~DofToQuad() = default;
|
||||
};
|
||||
|
||||
/** @brief Structure representing the matrices/tensors needed to evaluate (in
|
||||
reference space) the values, gradients, divergences, or curls of a positive
|
||||
FiniteElement on simplices at the quadrature points of Stroud conical quadrature. */
|
||||
class RaggedDofToQuad : public DofToQuad
|
||||
{
|
||||
public:
|
||||
/** @brief Special basis function structures for positive (Bernstein) basis with
|
||||
partial assembly. The storage layout of Ba1 is ndof x nqpt for scalar elements.
|
||||
The storage layout of Ba2 is ndof x ndof x nqpt. In particular, we have
|
||||
Ba2(iqpt, a1, a2) = B^{p-a1}_{a2}(x_{iqpt}). */
|
||||
Array<real_t> Ba1, Ba2, Ba3;
|
||||
Array<real_t> Ba1t, Ba2t, Ba3t;
|
||||
|
||||
/** @brief Special structures for gradients of positive basis with partial assembly.
|
||||
The gradient arrays exploit properties of the Bernstein basis which allow grad(B^p_alpha)
|
||||
to be expressed as the sum of products of B^{p-1}_alpha and the barycentric coordinates.
|
||||
Thus, Ga1 and Ga2 simply contain the ragged tensor product components of B^{p-1}_alpha */
|
||||
Array<real_t> Ga1, Ga2, Ga3;
|
||||
Array<real_t> Ga1t, Ga2t, Ga3t;
|
||||
|
||||
/** @brief Mapping from the Bernstein multi-index (a_1, ..., a_d) to the lexicographic
|
||||
dof index. */
|
||||
Array<int> lex_map;
|
||||
|
||||
Array<int> forward_map2d_diff, forward_map3d_diff;
|
||||
Array<int> inverse_map2d_diff, inverse_map3d_diff;
|
||||
|
||||
Array<int> forward_map2d_mass, forward_map3d_mass;
|
||||
Array<int> inverse_map2d_mass, inverse_map3d_mass;
|
||||
};
|
||||
|
||||
/// Describes the function space on each element
|
||||
@@ -336,20 +295,10 @@ public:
|
||||
$ u(x) = (1/w) \hat u(\hat x) $ */
|
||||
H_DIV, /**< For vector fields; preserves surface integrals of the
|
||||
normal component $ u(x) = (J/w) \hat u(\hat x) $ */
|
||||
H_CURL, /**< For vector fields; preserves line integrals of the
|
||||
H_CURL /**< For vector fields; preserves line integrals of the
|
||||
tangential component
|
||||
$ u(x) = J^{-t} \hat u(\hat x) $ (square J),
|
||||
$ u(x) = J(J^t J)^{-1} \hat u(\hat x) $ (general J) */
|
||||
H_DIV_R2D, /**< For 3-component vector fields in 2D; equivalent to a
|
||||
direct sum of an H_DIV basis and an INTEGRAL basis */
|
||||
H_CURL_R2D,/**< For 3-component vector fields in 2D; equivalent to a
|
||||
direct sum of an H_CURL basis and a VALUE basis */
|
||||
H_DIV_R1D, /**< For 3-component vector fields in 1D; equivalent to a
|
||||
direct sum of a VALUE basis and a pair of INTEGRAL
|
||||
bases */
|
||||
H_CURL_R1D /**< For 3-component vector fields in 1D; equivalent to a
|
||||
direct sum of an INTEGRAL basis and a pair of VALUE
|
||||
bases */
|
||||
};
|
||||
|
||||
/** @brief Enumeration for DerivType: defines which derivative method
|
||||
@@ -381,28 +330,12 @@ public:
|
||||
int GetDim() const { return dim; }
|
||||
|
||||
/** @brief Returns the vector dimension for vector-valued finite elements,
|
||||
which is also the dimension of the interpolation operation and the
|
||||
width of the DenseMatrix argument in
|
||||
CalcVShape(const IntegrationPoint &ip, DenseMatrix &shape). */
|
||||
which is also the dimension of the interpolation operation. */
|
||||
int GetRangeDim() const { return vdim; }
|
||||
|
||||
/** @brief Returns the vector dimension, in physical space, for
|
||||
vector-valued finite elements, which is also the width of the
|
||||
DenseMatrix argument in
|
||||
CalcPhysVShape(ElementTransformation &Trans, DenseMatrix &shape). */
|
||||
virtual int GetPhysRangeDim(int /* space_dim */) const { return vdim; }
|
||||
|
||||
/** Returns the dimension of the curl for vector-valued finite elements,
|
||||
which is also the width of the DenseMatrix argument in
|
||||
CalcCurlShape(const IntegrationPoint &ip, DenseMatrix &curl_shape). */
|
||||
/// Returns the dimension of the curl for vector-valued finite elements.
|
||||
int GetCurlDim() const { return cdim; }
|
||||
|
||||
/** Returns the dimension, in physical space, of the curl for vector-valued
|
||||
finite elements, which is also the width of the DenseMatrix argument in
|
||||
CalcPhysCurlShape(ElementTransformation &Trans, DenseMatrix &curl_shape).
|
||||
*/
|
||||
virtual int GetPhysCurlDim(int /* space_dim */) const { return cdim; }
|
||||
|
||||
/// Returns the Geometry::Type of the reference element.
|
||||
Geometry::Type GetGeomType() const { return geom_type; }
|
||||
|
||||
@@ -957,11 +890,10 @@ protected:
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &I) const;
|
||||
|
||||
// Input is a scalar representing the Z (out of plane) component, Output is
|
||||
// the X-Y (in-plane) RT curl
|
||||
void ProjectCurl2D_RT(const real_t *nk, const Array<int> &d2n,
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &grad) const;
|
||||
// rotated gradient in 2D
|
||||
void ProjectGrad_RT(const real_t *nk, const Array<int> &d2n,
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &grad) const;
|
||||
|
||||
// Compute the curl as a discrete operator from ND FE (fe) to ND FE (this).
|
||||
// The natural FE for the range is RT, so this is an approximation.
|
||||
@@ -969,9 +901,9 @@ protected:
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &curl) const;
|
||||
|
||||
void ProjectCurl3D_RT(const real_t *nk, const Array<int> &d2n,
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &curl) const;
|
||||
void ProjectCurl_RT(const real_t *nk, const Array<int> &d2n,
|
||||
const FiniteElement &fe, ElementTransformation &Trans,
|
||||
DenseMatrix &curl) const;
|
||||
|
||||
/** @brief Project a vector coefficient onto the ND basis functions
|
||||
@param tk Edge tangent vectors for this element type
|
||||
@@ -1058,8 +990,6 @@ protected:
|
||||
public:
|
||||
VectorFiniteElement(int D, Geometry::Type G, int Do, int O, int M,
|
||||
int F = FunctionSpace::Pk);
|
||||
|
||||
int GetPhysRangeDim(int space_dim) const override { return space_dim; }
|
||||
};
|
||||
|
||||
/// @brief Class for computing 1D special polynomials and their associated basis
|
||||
@@ -1447,8 +1377,6 @@ public:
|
||||
dof2quad_array_open);
|
||||
}
|
||||
|
||||
const Poly_1D::Basis &GetOpenBasis1D() const { return obasis1d; }
|
||||
|
||||
virtual ~VectorTensorFiniteElement();
|
||||
};
|
||||
|
||||
|
||||
@@ -307,12 +307,12 @@ public:
|
||||
|
||||
/** @brief virtual function which evaluates the values of all
|
||||
shape functions at a given point ip and stores
|
||||
them in the vector shape of dimension Dof (6) */
|
||||
them in the vector shape of dimension Dof (4) */
|
||||
void CalcShape(const IntegrationPoint &ip, Vector &shape) const override;
|
||||
|
||||
/** @brief virtual function which evaluates the values of all
|
||||
partial derivatives of all shape functions at a given
|
||||
point ip and stores them in the matrix dshape (Dof x Dim) (6 x 3)
|
||||
point ip and stores them in the matrix dshape (Dof x Dim) (4 x 3)
|
||||
so that each row contains the derivatives of one shape function */
|
||||
void CalcDShape(const IntegrationPoint &ip,
|
||||
DenseMatrix &dshape) const override;
|
||||
@@ -336,12 +336,12 @@ public:
|
||||
|
||||
/** @brief virtual function which evaluates the values of all
|
||||
shape functions at a given point ip and stores
|
||||
them in the vector shape of dimension Dof (5) */
|
||||
them in the vector shape of dimension Dof (4) */
|
||||
void CalcShape(const IntegrationPoint &ip, Vector &shape) const override;
|
||||
|
||||
/** @brief virtual function which evaluates the values of all
|
||||
partial derivatives of all shape functions at a given
|
||||
point ip and stores them in the matrix dshape (Dof x Dim) (5 x 3)
|
||||
point ip and stores them in the matrix dshape (Dof x Dim) (4 x 3)
|
||||
so that each row contains the derivatives of one shape function */
|
||||
void CalcDShape(const IntegrationPoint &ip,
|
||||
DenseMatrix &dshape) const override;
|
||||
|
||||
+57
-130
@@ -1757,45 +1757,22 @@ H1_BergotPyramidElement::H1_BergotPyramidElement(const int p, const int btype)
|
||||
real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the basis functions as z->1 with x and y on the
|
||||
// line between the center of the base and the apex
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
T(o++, m) = ((k + 3.) * k + 2.) / 2.;
|
||||
}
|
||||
else
|
||||
{
|
||||
T(o++, m) = 0.;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
{
|
||||
T(o++, m) = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
{
|
||||
T(o++, m) = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1816,44 +1793,25 @@ void H1_BergotPyramidElement::CalcShape(const IntegrationPoint &ip,
|
||||
Vector u(dof);
|
||||
#endif
|
||||
|
||||
const real_t x = (ip.z < 1.0) ? (ip.x / (1.0 - ip.z)) : 0.0;
|
||||
const real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
const real_t z = ip.z;
|
||||
real_t x = (ip.z < 1.0) ? (ip.x / (1.0 - ip.z)) : 0.0;
|
||||
real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the basis functions as z->1 with x and y on the
|
||||
// line between the center of the base and the apex
|
||||
u = 0.;
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
u(o) = ((k + 3.) * k + 2.) / 2.;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0), z, 1.0,
|
||||
shape_z);
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
u[o++] = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
u[o++] = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
}
|
||||
Ti.Mult(u, shape);
|
||||
}
|
||||
|
||||
@@ -1872,68 +1830,37 @@ void H1_BergotPyramidElement::CalcDShape(const IntegrationPoint &ip,
|
||||
Vector dshape_z(order+1);
|
||||
Vector dshape_z_dt(order+1);
|
||||
#endif
|
||||
const real_t x = (ip.z < 1.0) ? (ip.x / (1.0 - ip.z)) : 0.0;
|
||||
const real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
const real_t z = ip.z;
|
||||
real_t x = (ip.z < 1.0) ? (ip.x / (1.0 - ip.z)) : 0.0;
|
||||
real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the gradients of the basis functions as
|
||||
// z->1 with x and y on the line between the center of the base and the
|
||||
// apex
|
||||
du = 0.;
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData(), dshape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData(), dshape_y.GetData());
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0), z, 1.0,
|
||||
shape_z, dshape_z, dshape_z_dt);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
du(o,2) = (((k + 6.) * k + 11.) * k + 6.) * k / 6.;
|
||||
}
|
||||
else if (i == 1 && j == 0)
|
||||
{
|
||||
du(o,0) = ((((k + 10.) * k + 35.) * k + 50.) * k + 24.) / 24.;
|
||||
}
|
||||
else if (i == 0 && j == 1)
|
||||
{
|
||||
du(o,1) = ((((k + 10.) * k + 35.) * k + 50.) * k + 24.) / 24.;
|
||||
}
|
||||
}
|
||||
du(o,0) = dshape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,1) = shape_x(i) * dshape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,2) = shape_x(i) * shape_y(j) * dshape_z(k) *
|
||||
pow(1.0 - ip.z, maxij) +
|
||||
(ip.x * dshape_x(i) * shape_y(j) +
|
||||
ip.y * shape_x(i) * dshape_y(j)) *
|
||||
shape_z(k) * pow(1.0 - ip.z, maxij - 2) -
|
||||
maxij * shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData(), dshape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData(), dshape_y.GetData());
|
||||
}
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0,
|
||||
shape_z, dshape_z, dshape_z_dt);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
du(o,0) = dshape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,1) = shape_x(i) * dshape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,2) = shape_x(i) * shape_y(j) * dshape_z(k) *
|
||||
pow(1.0 - ip.z, maxij) +
|
||||
(ip.x * dshape_x(i) * shape_y(j) +
|
||||
ip.y * shape_x(i) * dshape_y(j)) *
|
||||
shape_z(k) * pow(1.0 - ip.z, maxij - 2) -
|
||||
maxij * shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
(maxij > 0 ? pow(1.0 - ip.z, maxij - 1) : 0.0);
|
||||
}
|
||||
}
|
||||
}
|
||||
Ti.Mult(du, dshape);
|
||||
}
|
||||
|
||||
|
||||
@@ -208,8 +208,6 @@ private:
|
||||
#endif
|
||||
DenseMatrixInverse Ti;
|
||||
|
||||
static constexpr real_t apex_tol = 1e-8;
|
||||
|
||||
public:
|
||||
H1_BergotPyramidElement(const int p,
|
||||
const int btype = BasisType::GaussLobatto);
|
||||
|
||||
+57
-131
@@ -1106,16 +1106,9 @@ L2_BergotPyramidElement::L2_BergotPyramidElement(const int p, const int btype)
|
||||
{
|
||||
const real_t wik = op[i] + op[k] + op[p-i-k];
|
||||
const real_t w = wik * wjk * op[p-k];
|
||||
if (std::abs(w) < apex_tol)
|
||||
{
|
||||
Nodes.IntPoint(o++).Set3(0.,0.,1.);
|
||||
}
|
||||
else
|
||||
{
|
||||
Nodes.IntPoint(o++).Set3(op[i] * (op[j] + op[p-j-k]) / w,
|
||||
op[j] * (op[i] + op[p-i-k]) / w,
|
||||
op[k] * op[p-k] / w);
|
||||
}
|
||||
Nodes.IntPoint(o++).Set3(op[i] * (op[j] + op[p-j-k]) / w,
|
||||
op[j] * (op[j] + op[p-j-k]) / w,
|
||||
op[k] * op[p-k] / w);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1132,45 +1125,22 @@ L2_BergotPyramidElement::L2_BergotPyramidElement(const int p, const int btype)
|
||||
const real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
const real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the basis functions as z->1 with x and y on the
|
||||
// line between the center of the base and the apex
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
T(o++, m) = ((k + 3.) * k + 2.) / 2.;
|
||||
}
|
||||
else
|
||||
{
|
||||
T(o++, m) = 0.;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
{
|
||||
T(o++, m) = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
{
|
||||
T(o++, m) = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1195,41 +1165,26 @@ void L2_BergotPyramidElement::CalcShape(const IntegrationPoint &ip,
|
||||
const real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
const real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the basis functions as z->1 with x and y on the
|
||||
// line between the center of the base and the apex
|
||||
u = 0.;
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
u(o) = ((k + 3.) * k + 2.) / 2.;
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
poly1d.CalcLegendre(p, x, shape_x.GetData());
|
||||
poly1d.CalcLegendre(p, y, shape_y.GetData());
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0, shape_z);
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0), z, 1.0,
|
||||
shape_z);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
u[o++] = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
for (int k = 0; k <= p - maxij; k++)
|
||||
{
|
||||
u[o++] = shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ti.Mult(u, shape);
|
||||
}
|
||||
|
||||
@@ -1253,64 +1208,35 @@ void L2_BergotPyramidElement::CalcDShape(const IntegrationPoint &ip,
|
||||
const real_t y = (ip.z < 1.0) ? (ip.y / (1.0 - ip.z)) : 0.0;
|
||||
const real_t z = ip.z;
|
||||
|
||||
if (std::abs(z - 1.0) < apex_tol)
|
||||
{
|
||||
// Compute the limit of the gradients of the basis functions as
|
||||
// z->1 with x and y on the line between the center of the base and the
|
||||
// apex
|
||||
du = 0.;
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
if (i == 0 && j == 0)
|
||||
{
|
||||
du(o,2) = (((k + 6.) * k + 11.) * k + 6.) * k / 6.;
|
||||
}
|
||||
else if (i == 1 && j == 0)
|
||||
{
|
||||
du(o,0) = ((((k + 10.) * k + 35.) * k + 50.) * k + 24.) / 24.;
|
||||
}
|
||||
else if (i == 0 && j == 1)
|
||||
{
|
||||
du(o,1) = ((((k + 10.) * k + 35.) * k + 50.) * k + 24.) / 24.;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
Poly_1D::CalcLegendre(p, x, shape_x.GetData(), dshape_x.GetData());
|
||||
Poly_1D::CalcLegendre(p, y, shape_y.GetData(), dshape_y.GetData());
|
||||
Poly_1D::CalcLegendre(p, x, shape_x.GetData(), dshape_x.GetData());
|
||||
Poly_1D::CalcLegendre(p, y, shape_y.GetData(), dshape_y.GetData());
|
||||
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0),
|
||||
z, 1.0,
|
||||
shape_z, dshape_z, dshape_z_dt);
|
||||
int o = 0;
|
||||
for (int i = 0; i <= p; i++)
|
||||
{
|
||||
for (int j = 0; j <= p; j++)
|
||||
{
|
||||
int maxij = std::max(i, j);
|
||||
FuentesPyramid::CalcScaledJacobi(p-maxij, 2.0 * (maxij + 1.0), z, 1.0,
|
||||
shape_z, dshape_z, dshape_z_dt);
|
||||
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
du(o,0) = dshape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,1) = shape_x(i) * dshape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,2) = shape_x(i) * shape_y(j) * dshape_z(k) *
|
||||
pow(1.0 - ip.z, maxij) +
|
||||
(ip.x * dshape_x(i) * shape_y(j) +
|
||||
ip.y * shape_x(i) * dshape_y(j)) *
|
||||
shape_z(k) * pow(1.0 - ip.z, maxij - 2) -
|
||||
maxij * shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
(maxij > 0 ? pow(1.0 - ip.z, maxij - 1) : 0.0);
|
||||
}
|
||||
for (int k = 0; k <= p - maxij; k++, o++)
|
||||
{
|
||||
du(o,0) = dshape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,1) = shape_x(i) * dshape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1);
|
||||
du(o,2) = shape_x(i) * shape_y(j) * dshape_z(k) *
|
||||
pow(1.0 - ip.z, maxij) +
|
||||
(ip.x * dshape_x(i) * shape_y(j) +
|
||||
ip.y * shape_x(i) * dshape_y(j)) *
|
||||
shape_z(k) * pow(1.0 - ip.z, maxij - 2) -
|
||||
((maxij > 0) ? (maxij * shape_x(i) * shape_y(j) * shape_z(k) *
|
||||
pow(1.0 - ip.z, maxij - 1)) : 0.0);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ti.Mult(du, dshape);
|
||||
}
|
||||
|
||||
|
||||
@@ -225,8 +225,6 @@ private:
|
||||
#endif
|
||||
DenseMatrixInverse Ti;
|
||||
|
||||
static constexpr real_t apex_tol = 1e-8;
|
||||
|
||||
public:
|
||||
/// Construct the L2_PyramidElement of order @a p and BasisType @a btype
|
||||
L2_BergotPyramidElement(const int p,
|
||||
|
||||
+5
-42
@@ -1282,49 +1282,12 @@ ND_SegmentElement::ND_SegmentElement(const int p, const int ob_type)
|
||||
}
|
||||
}
|
||||
|
||||
void ND_SegmentElement::CalcShape(const IntegrationPoint &ip,
|
||||
Vector &shape) const
|
||||
{
|
||||
if (obasis1d.IsIntegratedType()) { obasis1d.ScaleIntegrated(false); }
|
||||
obasis1d.Eval(ip.x, shape);
|
||||
}
|
||||
|
||||
void ND_SegmentElement::CalcVShape(const IntegrationPoint &ip,
|
||||
DenseMatrix &shape) const
|
||||
{
|
||||
Vector vshape(shape.Data(), dof);
|
||||
|
||||
CalcShape(ip, vshape);
|
||||
}
|
||||
|
||||
void ND_SegmentElement::ProjectIntegrated(VectorCoefficient &vc,
|
||||
ElementTransformation &Trans,
|
||||
Vector &dofs) const
|
||||
{
|
||||
MFEM_ASSERT(obasis1d.IsIntegratedType(), "Not integrated type");
|
||||
real_t vk[Geometry::MaxDim];
|
||||
Vector xk(vk, vc.GetVDim());
|
||||
|
||||
const real_t *cp = poly1d.ClosedPoints(dof, BasisType::GaussLobatto);
|
||||
const IntegrationRule &ir = IntRules.Get(Geometry::SEGMENT, dof);
|
||||
IntegrationPoint ip;
|
||||
|
||||
for (int i = 0; i < dof; i++)
|
||||
{
|
||||
const real_t h = cp[i+1] - cp[i];
|
||||
real_t val = 0.0;
|
||||
|
||||
for (int q = 0; q < ir.GetNPoints(); q++)
|
||||
{
|
||||
const IntegrationPoint &ip1d = ir.IntPoint(q);
|
||||
ip.x = cp[i] + h*ip1d.x;
|
||||
Trans.SetIntPoint(&ip);
|
||||
vc.Eval(xk, Trans, ip);
|
||||
val += ip1d.weight*Trans.Jacobian().InnerProduct(tk, vk);
|
||||
}
|
||||
|
||||
dofs(i) = val*h;
|
||||
}
|
||||
obasis1d.Eval(ip.x, vshape);
|
||||
}
|
||||
|
||||
const real_t ND_WedgeElement::tk[15] =
|
||||
@@ -2568,7 +2531,7 @@ void ND_FuentesPyramidElement::calcCurlBasis(const int p,
|
||||
|
||||
ND_R1D_PointElement::ND_R1D_PointElement(int p)
|
||||
: VectorFiniteElement(1, Geometry::POINT, 2, p,
|
||||
H_CURL_R1D, FunctionSpace::Pk)
|
||||
H_CURL, FunctionSpace::Pk)
|
||||
{
|
||||
// VectorFiniteElement::SetDerivMembers doesn't support 0D H_CURL elements
|
||||
// so we mimic a 1D element and then correct the dimension here.
|
||||
@@ -2599,7 +2562,7 @@ ND_R1D_SegmentElement::ND_R1D_SegmentElement(const int p,
|
||||
const int cb_type,
|
||||
const int ob_type)
|
||||
: VectorFiniteElement(1, Geometry::SEGMENT, 3 * p + 2, p,
|
||||
H_CURL_R1D, FunctionSpace::Pk),
|
||||
H_CURL, FunctionSpace::Pk),
|
||||
dof2tk(dof),
|
||||
cbasis1d(poly1d.GetBasis(p, VerifyClosed(cb_type))),
|
||||
obasis1d(poly1d.GetBasis(p - 1, VerifyOpen(ob_type)))
|
||||
@@ -2876,7 +2839,7 @@ ND_R2D_SegmentElement::ND_R2D_SegmentElement(const int p,
|
||||
const int cb_type,
|
||||
const int ob_type)
|
||||
: VectorFiniteElement(1, Geometry::SEGMENT, 2 * p + 1, p,
|
||||
H_CURL_R2D, FunctionSpace::Pk),
|
||||
H_CURL, FunctionSpace::Pk),
|
||||
dof2tk(dof),
|
||||
cbasis1d(poly1d.GetBasis(p, VerifyClosed(cb_type))),
|
||||
obasis1d(poly1d.GetBasis(p - 1, VerifyOpen(ob_type)))
|
||||
@@ -3060,7 +3023,7 @@ void ND_R2D_SegmentElement::Project(VectorCoefficient &vc,
|
||||
ND_R2D_FiniteElement::ND_R2D_FiniteElement(int p, Geometry::Type G, int Do,
|
||||
const real_t *tk_fe)
|
||||
: VectorFiniteElement(2, G, Do, p,
|
||||
H_CURL_R2D, FunctionSpace::Pk),
|
||||
H_CURL, FunctionSpace::Pk),
|
||||
tk(tk_fe),
|
||||
dof_map(dof),
|
||||
dof2tk(dof)
|
||||
|
||||
+3
-16
@@ -303,7 +303,8 @@ public:
|
||||
/** @brief Construct the ND_SegmentElement of order @a p and open
|
||||
BasisType @a ob_type */
|
||||
ND_SegmentElement(const int p, const int ob_type = BasisType::GaussLegendre);
|
||||
void CalcShape(const IntegrationPoint &ip, Vector &shape) const override;
|
||||
void CalcShape(const IntegrationPoint &ip, Vector &shape) const override
|
||||
{ obasis1d.Eval(ip.x, shape); }
|
||||
void CalcVShape(const IntegrationPoint &ip,
|
||||
DenseMatrix &shape) const override;
|
||||
void CalcVShape(ElementTransformation &Trans,
|
||||
@@ -324,10 +325,7 @@ public:
|
||||
using FiniteElement::Project;
|
||||
void Project(VectorCoefficient &vc,
|
||||
ElementTransformation &Trans, Vector &dofs) const override
|
||||
{
|
||||
if (obasis1d.IsIntegratedType()) { ProjectIntegrated(vc, Trans, dofs); }
|
||||
else { Project_ND(tk, dof2tk, vc, Trans, dofs); }
|
||||
}
|
||||
{ Project_ND(tk, dof2tk, vc, Trans, dofs); }
|
||||
void ProjectMatrixCoefficient(MatrixCoefficient &mc,
|
||||
ElementTransformation &T,
|
||||
Vector &dofs) const override
|
||||
@@ -340,11 +338,6 @@ public:
|
||||
ElementTransformation &Trans,
|
||||
DenseMatrix &grad) const override
|
||||
{ ProjectGrad_ND(tk, dof2tk, fe, Trans, grad); }
|
||||
|
||||
protected:
|
||||
void ProjectIntegrated(VectorCoefficient &vc,
|
||||
ElementTransformation &Trans,
|
||||
Vector &dofs) const;
|
||||
};
|
||||
|
||||
class ND_WedgeElement : public VectorFiniteElement
|
||||
@@ -670,9 +663,6 @@ public:
|
||||
const int cb_type = BasisType::GaussLobatto,
|
||||
const int ob_type = BasisType::GaussLegendre);
|
||||
|
||||
int GetPhysRangeDim(int space_dim) const override { return 2; }
|
||||
int GetPhysCurlDim(int space_dim) const override { return 1; }
|
||||
|
||||
void CalcVShape(const IntegrationPoint &ip,
|
||||
DenseMatrix &shape) const override;
|
||||
|
||||
@@ -715,9 +705,6 @@ private:
|
||||
DenseMatrix &I) const;
|
||||
|
||||
public:
|
||||
int GetPhysRangeDim(int space_dim) const override { return 3; }
|
||||
int GetPhysCurlDim(int space_dim) const override { return 3; }
|
||||
|
||||
using FiniteElement::CalcVShape;
|
||||
using FiniteElement::CalcPhysCurlShape;
|
||||
|
||||
|
||||
@@ -557,101 +557,6 @@ H1Pos_TriangleElement::H1Pos_TriangleElement(const int p)
|
||||
}
|
||||
}
|
||||
|
||||
const DofToQuad &H1Pos_TriangleElement::GetRaggedTensorDofToQuad(
|
||||
const FiniteElement &fe, const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode,
|
||||
Array<DofToQuad*> &dof2quad_array)
|
||||
{
|
||||
DofToQuad *d2q = nullptr;
|
||||
MFEM_VERIFY(mode == DofToQuad::RAGGED_TENSOR, "invalid mode requested");
|
||||
|
||||
#if defined(MFEM_THREAD_SAFE) && defined(MFEM_USE_OPENMP)
|
||||
#pragma omp critical (DofToQuad)
|
||||
#endif
|
||||
{
|
||||
for (int i = 0; i < dof2quad_array.Size(); i++)
|
||||
{
|
||||
d2q = dof2quad_array[i];
|
||||
if (d2q->IntRule != &ir || d2q->mode != mode) { d2q = nullptr; }
|
||||
}
|
||||
if (!d2q)
|
||||
{
|
||||
d2q = new RaggedDofToQuad;
|
||||
const int ndof = fe.GetOrder() + 1; // verify
|
||||
const int nqpt = (int)floor(pow(ir.GetNPoints(), 1.0/fe.GetDim()) + 0.5);
|
||||
d2q->FE = &fe;
|
||||
d2q->IntRule = &ir;
|
||||
d2q->mode = mode;
|
||||
d2q->ndof = ndof;
|
||||
d2q->nqpt = nqpt;
|
||||
|
||||
RaggedDofToQuad *rd2q = static_cast<RaggedDofToQuad*>(d2q);
|
||||
rd2q->Ba1.SetSize(nqpt*ndof);
|
||||
// second component of ragged tensor basis, technically dof*(dof-1)/2 entries
|
||||
rd2q->Ba2.SetSize((int)nqpt*ndof*ndof);
|
||||
rd2q->Ba1t.SetSize(nqpt*ndof);
|
||||
rd2q->Ba2t.SetSize((int)nqpt*ndof*ndof);
|
||||
// stores first component of ragged tensor basis with order p-1, for gradients only
|
||||
rd2q->Ga1.SetSize(nqpt*(ndof -1));
|
||||
// stores second component of ragged tensor basis with order p-1
|
||||
rd2q->Ga2.SetSize(nqpt*(ndof-1)*(ndof -1));
|
||||
rd2q->Ga1t.SetSize(nqpt*(ndof -1));
|
||||
rd2q->Ga2t.SetSize(nqpt*(ndof-1)*(ndof -1));
|
||||
rd2q->lex_map.SetSize(ndof * ndof);
|
||||
Vector shape_a1(ndof), shape_a2(ndof * ndof);
|
||||
Vector shape_Ga1(ndof-1), shape_Ga2((ndof-1) * (ndof-1));
|
||||
for (int i = 0; i < nqpt; i++)
|
||||
{
|
||||
// The first 'nqpt' points in the first dimension 'ir' have the same x-coordinates as those
|
||||
// of the 1D rule (ie. (2,0) Gauss-Jacobi rule). The first 'nqpt' points in the second dimension
|
||||
// 'ir' have the same y-coordinates as those of the 1D rule for second dimension (i.e. (1,0)
|
||||
// Gauss-Jacobi rule). Additionally, the Bernstein PA algorithms expect evaluation of the
|
||||
// component 1D bases at the Stroud nodes pulled back to the unit square, so perform the pullback
|
||||
// on the fly.
|
||||
const real_t x = ir.IntPoint(i).x;
|
||||
const real_t y = ir.IntPoint(nqpt*i).y / (1.0 - ir.IntPoint(nqpt*i).x);
|
||||
|
||||
Poly_1D::CalcBernstein(ndof-1, x, shape_a1);
|
||||
Poly_1D::CalcBernstein(ndof-2, x, shape_Ga1);
|
||||
for (int j = 0; j < ndof; j++)
|
||||
{
|
||||
rd2q->Ba1t[i+nqpt*j] = rd2q->Ba1[j+ndof*i] = shape_a1(j);
|
||||
if (j < ndof-1)
|
||||
{
|
||||
rd2q->Ga1t[i+nqpt*j] = rd2q->Ga1[j+(ndof-1)*i] = shape_Ga1(j);
|
||||
Poly_1D::CalcBernstein(ndof-2-j, y, shape_Ga2);
|
||||
}
|
||||
|
||||
Poly_1D::CalcBernstein(ndof-1-j, y, shape_a2);
|
||||
for (int k = 0; k < ndof-j; k++)
|
||||
{
|
||||
rd2q->Ba2t[i + nqpt*(j + ndof*k)] = rd2q->Ba2[k + ndof*(j + ndof*i)] = shape_a2(
|
||||
k);
|
||||
if (j < ndof-1 && k < ndof-j-1)
|
||||
{
|
||||
rd2q->Ga2t[i + nqpt*(j + (ndof-1)*k)] = rd2q->Ga2[k + (ndof-1)*(j +
|
||||
(ndof-1)*i)] = shape_Ga2(k);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// stores the mapping from 2D Bernstein multi-index (i,j,p-i-j) to the
|
||||
// lexicographic DOF ordering
|
||||
for (int i = 0; i < ndof; i++)
|
||||
{
|
||||
for (int j = 0; j < ndof-i; j++)
|
||||
{
|
||||
int idx = ((2 * (ndof-1) + 3) - j) * j / 2 + i;
|
||||
rd2q->lex_map[j + ndof*i] = idx;
|
||||
}
|
||||
}
|
||||
dof2quad_array.Append(d2q);
|
||||
}
|
||||
}
|
||||
return *d2q;
|
||||
}
|
||||
|
||||
// static method
|
||||
void H1Pos_TriangleElement::CalcShape(
|
||||
const int p, const real_t l1, const real_t l2, real_t *shape)
|
||||
@@ -844,213 +749,6 @@ H1Pos_TetrahedronElement::H1Pos_TetrahedronElement(const int p)
|
||||
}
|
||||
}
|
||||
|
||||
const DofToQuad &H1Pos_TetrahedronElement::GetRaggedTensorDofToQuad(
|
||||
const FiniteElement &fe, const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode,
|
||||
Array<DofToQuad*> &dof2quad_array)
|
||||
{
|
||||
DofToQuad *d2q = nullptr;
|
||||
MFEM_VERIFY(mode == DofToQuad::RAGGED_TENSOR, "invalid mode requested");
|
||||
|
||||
#if defined(MFEM_THREAD_SAFE) && defined(MFEM_USE_OPENMP)
|
||||
#pragma omp critical (DofToQuad)
|
||||
#endif
|
||||
{
|
||||
for (int i = 0; i < dof2quad_array.Size(); i++)
|
||||
{
|
||||
d2q = dof2quad_array[i];
|
||||
if (d2q->IntRule != &ir || d2q->mode != mode) { d2q = nullptr; }
|
||||
}
|
||||
if (!d2q)
|
||||
{
|
||||
d2q = new RaggedDofToQuad;
|
||||
const int ndof = fe.GetOrder() + 1; // verify
|
||||
const int nqpt = (int)floor(pow(ir.GetNPoints(), 1.0/fe.GetDim()) + 0.5);
|
||||
const int basis_dim2d = ndof*(ndof+1) / 2;
|
||||
const int basis_dim3d = ndof*(ndof+1)*(ndof+2) / 6;
|
||||
const int basis_dim2d_diff = (ndof-1)*(ndof) / 2;
|
||||
const int basis_dim3d_diff = (ndof-1)*(ndof)*(ndof+1) / 6;
|
||||
d2q->FE = &fe;
|
||||
d2q->IntRule = &ir;
|
||||
d2q->mode = mode;
|
||||
d2q->ndof = ndof;
|
||||
d2q->nqpt = nqpt;
|
||||
|
||||
RaggedDofToQuad *rd2q = static_cast<RaggedDofToQuad*>(d2q);
|
||||
rd2q->Ba1.SetSize(nqpt * ndof);
|
||||
// second component of ragged tensor basis, technically dof*(dof-1)/2 entries
|
||||
rd2q->Ba2.SetSize(nqpt * basis_dim2d);
|
||||
// third component of ragged tensor basis, technically dof*(dof-1)/2 entries
|
||||
rd2q->Ba3.SetSize(nqpt * basis_dim3d);
|
||||
rd2q->Ba1t.SetSize(nqpt * ndof);
|
||||
rd2q->Ba2t.SetSize(nqpt * basis_dim2d);
|
||||
rd2q->Ba3t.SetSize(nqpt * basis_dim3d);
|
||||
// stores first component of ragged tensor basis with order p-1, for gradients only
|
||||
rd2q->Ga1.SetSize(nqpt * (ndof-1));
|
||||
// stores second component of ragged tensor basis with order p-1
|
||||
rd2q->Ga2.SetSize(nqpt * basis_dim2d_diff);
|
||||
// stores third component of ragged tensor basis with order p-1
|
||||
rd2q->Ga3.SetSize(nqpt * basis_dim3d_diff);
|
||||
rd2q->Ga1t.SetSize(nqpt * (ndof-1));
|
||||
rd2q->Ga2t.SetSize(nqpt * basis_dim2d_diff);
|
||||
rd2q->Ga3t.SetSize(nqpt * basis_dim3d_diff);
|
||||
rd2q->lex_map.SetSize(ndof * ndof * ndof);
|
||||
|
||||
rd2q->forward_map2d_diff.SetSize((ndof-1) * (ndof-1));
|
||||
rd2q->forward_map3d_diff.SetSize((ndof-1) * (ndof-1) * (ndof-1));
|
||||
rd2q->inverse_map2d_diff.SetSize(2 * basis_dim2d_diff);
|
||||
rd2q->inverse_map3d_diff.SetSize(3 * basis_dim3d_diff);
|
||||
|
||||
rd2q->forward_map2d_mass.SetSize(ndof * ndof);
|
||||
rd2q->forward_map3d_mass.SetSize(ndof * ndof * ndof);
|
||||
rd2q->inverse_map2d_mass.SetSize(2 * basis_dim2d);
|
||||
rd2q->inverse_map3d_mass.SetSize(2 * basis_dim3d);
|
||||
|
||||
// forward and inverse maps for multi-index to collpased 1d index for diffusion, can combine
|
||||
// these four loops, but need four idx's and clause for shorter diff loops
|
||||
int idx = 0;
|
||||
for (int i = 0; i < ndof-1; i++)
|
||||
{
|
||||
for (int j = 0; j < ndof-i-1; j++)
|
||||
{
|
||||
rd2q->forward_map2d_diff[j + (ndof-1)*i] = idx;
|
||||
rd2q->inverse_map2d_diff[2*idx] = i;
|
||||
rd2q->inverse_map2d_diff[1 + 2*idx] = j;
|
||||
idx++;
|
||||
}
|
||||
}
|
||||
|
||||
idx = 0;
|
||||
for (int k = 0; k < ndof-1; k++)
|
||||
{
|
||||
for (int j = 0; j < ndof-k-1; j++)
|
||||
{
|
||||
for (int i = 0; i < ndof-k-j-1; i++)
|
||||
{
|
||||
rd2q->forward_map3d_diff[k + (ndof-1)*(j + (ndof-1)*i)] = idx;
|
||||
rd2q->inverse_map3d_diff[3*idx] = i;
|
||||
rd2q->inverse_map3d_diff[1 + 3*idx] = j;
|
||||
rd2q->inverse_map3d_diff[2 + 3*idx] = k;
|
||||
idx++;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// forward and inverse maps for multi-index to collpased 1d index for mass
|
||||
idx = 0;
|
||||
for (int j = 0; j < ndof; j++)
|
||||
{
|
||||
for (int i = 0; i < ndof-j; i++)
|
||||
{
|
||||
rd2q->forward_map2d_mass[j + ndof*i] = idx;
|
||||
rd2q->inverse_map2d_mass[2*idx] = i;
|
||||
rd2q->inverse_map2d_mass[1 + 2*idx] = j;
|
||||
idx++;
|
||||
}
|
||||
}
|
||||
|
||||
idx = 0;
|
||||
for (int k = 0; k < ndof; k++)
|
||||
{
|
||||
for (int j = 0; j < ndof-k; j++)
|
||||
{
|
||||
for (int i = 0; i < ndof-k-j; i++)
|
||||
{
|
||||
rd2q->forward_map3d_mass[k + ndof*(j + ndof*i)] = idx;
|
||||
rd2q->inverse_map3d_mass[2*idx] = i;
|
||||
rd2q->inverse_map3d_mass[1 + 2*idx] = j;
|
||||
// d2q->inverse_map3d_mass[2 + 3*idx] = k;
|
||||
idx++;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Vector shape_a1(ndof), shape_a2(ndof * ndof), shape_a3(ndof * ndof * ndof);
|
||||
Vector shape_Ga1(ndof-1), shape_Ga2(ndof-1), shape_Ga3(ndof-1);
|
||||
for (int i = 0; i < nqpt; i++)
|
||||
{
|
||||
// The first 'nqpt' points in the first dimension 'ir' have the same x-coordinates as those
|
||||
// of the 1D rule (ie. (2,0) Gauss-Jacobi rule). The first 'nqpt' points in the second dimension
|
||||
// 'ir' have the same y-coordinates as those of the 1D rule for second dimension (i.e. (1,0)
|
||||
// Gauss-Jacobi rule). The first 'nqpt' points in the third dimension have the same z-coordinates
|
||||
// as those of the 1D rule for the third dimension (i.e. Gauss-Legendre rule). Additionally,
|
||||
// the Bernstein PA algorithms expect evaluation of the component 1D bases at the Stroud nodes
|
||||
// pulled back to the unit cube, so perform the pullback on the fly.
|
||||
const real_t x = ir.IntPoint(i).x;
|
||||
const real_t y = ir.IntPoint(nqpt*i).y / (1.0 - ir.IntPoint(nqpt*i).x);
|
||||
const real_t z = ir.IntPoint(nqpt*nqpt*i).z / (1.0 - ir.IntPoint(
|
||||
nqpt*nqpt*i).x - ir.IntPoint(nqpt*nqpt*i).y);
|
||||
Poly_1D::CalcBernstein(ndof-1, x, shape_a1);
|
||||
Poly_1D::CalcBernstein(ndof-2, x, shape_Ga1);
|
||||
for (int j = 0; j < ndof; j++)
|
||||
{
|
||||
rd2q->Ba1t[i+nqpt*j] = rd2q->Ba1[j+ndof*i] = shape_a1(j);
|
||||
if (j < ndof-1)
|
||||
{
|
||||
rd2q->Ga1t[i+nqpt*j] = rd2q->Ga1[j+(ndof-1)*i] = shape_Ga1(j);
|
||||
Poly_1D::CalcBernstein(ndof-2-j, y, shape_Ga2);
|
||||
}
|
||||
|
||||
Poly_1D::CalcBernstein(ndof-1-j, y, shape_a2);
|
||||
for (int k = 0; k < ndof-j; k++)
|
||||
{
|
||||
const int a_2d_mass = rd2q->forward_map2d_mass[k + ndof*j];
|
||||
rd2q->Ba2t[i + nqpt*a_2d_mass] = rd2q->Ba2[a_2d_mass + basis_dim2d*i] =
|
||||
shape_a2(
|
||||
k);
|
||||
if (j < ndof-1 && k < ndof-j-1)
|
||||
{
|
||||
const int a_2d_diff = rd2q->forward_map2d_diff[k + (ndof-1)*j];
|
||||
rd2q->Ga2t[i + nqpt*a_2d_diff] = rd2q->Ga2[a_2d_diff + basis_dim2d_diff*i] =
|
||||
shape_Ga2(k);
|
||||
Poly_1D::CalcBernstein(ndof-2-j-k, z, shape_Ga3);
|
||||
}
|
||||
|
||||
Poly_1D::CalcBernstein(ndof-1-j-k, z, shape_a3);
|
||||
for (int m = 0; m < ndof-j-k; m++)
|
||||
{
|
||||
const int a_3d_mass = rd2q->forward_map3d_mass[m + ndof*(k + ndof*j)];
|
||||
rd2q->Ba3t[i + nqpt*a_3d_mass] = rd2q->Ba3[a_3d_mass + basis_dim3d*i] =
|
||||
shape_a3(
|
||||
m);
|
||||
if (j < ndof-1 && k < ndof-j-1 && m < ndof-j-k-1)
|
||||
{
|
||||
// // collapsed 1D access
|
||||
// d2q->Ga3[i + nqpt*(m + d2q->offset3d[k + (ndof-1)*j])] = shape_Ga3(m);
|
||||
// collapsed 1D access with forward mapping
|
||||
const int a_3d_diff = rd2q->forward_map3d_diff[m + (ndof-1)*(k + (ndof-1)*j)];
|
||||
rd2q->Ga3t[i + nqpt*a_3d_diff] = rd2q->Ga3[a_3d_diff + basis_dim3d_diff*i] =
|
||||
shape_Ga3(m);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// stores the mapping from 3D Bernstein multi-index (i,j,k,p-i-j-k) to the
|
||||
// lexicographic DOF ordering
|
||||
int p = ndof - 1;
|
||||
for (int i = 0; i < ndof; i++)
|
||||
{
|
||||
for (int j = 0; j < ndof-i; j++)
|
||||
{
|
||||
for (int k = 0; k < ndof-i-j; k++)
|
||||
{
|
||||
int dof = (p+1)*(p+2)*(p+3) / 6;
|
||||
int tet = (p-k)*(p-k+1)*(p-k+2) / 6;
|
||||
int tri = (p+1-k-j)*(p+2-k-j)/2;
|
||||
int multi_idx = dof - tet - tri + i;
|
||||
rd2q->lex_map[k + ndof*(j + ndof*i)] = multi_idx;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
dof2quad_array.Append(d2q);
|
||||
}
|
||||
}
|
||||
return *d2q;
|
||||
}
|
||||
|
||||
// static method
|
||||
void H1Pos_TetrahedronElement::CalcShape(
|
||||
const int p, const real_t l1, const real_t l2, const real_t l3,
|
||||
|
||||
@@ -191,21 +191,6 @@ public:
|
||||
/// Construct the H1Pos_TriangleElement of order @a p
|
||||
H1Pos_TriangleElement(const int p);
|
||||
|
||||
const DofToQuad &GetDofToQuad(const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode) const override
|
||||
{
|
||||
return (mode == DofToQuad::RAGGED_TENSOR) ?
|
||||
GetRaggedTensorDofToQuad(*this, ir, mode, dof2quad_array) :
|
||||
FiniteElement::GetDofToQuad(ir, mode);
|
||||
}
|
||||
|
||||
static const DofToQuad &GetRaggedTensorDofToQuad(
|
||||
const FiniteElement &fe, const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode,
|
||||
Array<DofToQuad*> &dof2quad_array);
|
||||
|
||||
const Array<int> &GetDofMap() const { return dof_map; }
|
||||
|
||||
// The size of shape is (p+1)(p+2)/2 (dof).
|
||||
static void CalcShape(const int p, const real_t x, const real_t y,
|
||||
real_t *shape);
|
||||
@@ -235,21 +220,6 @@ public:
|
||||
/// Construct the H1Pos_TetrahedronElement of order @a p
|
||||
H1Pos_TetrahedronElement(const int p);
|
||||
|
||||
const DofToQuad &GetDofToQuad(const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode) const override
|
||||
{
|
||||
return (mode == DofToQuad::RAGGED_TENSOR) ?
|
||||
GetRaggedTensorDofToQuad(*this, ir, mode, dof2quad_array) :
|
||||
FiniteElement::GetDofToQuad(ir, mode);
|
||||
}
|
||||
|
||||
static const DofToQuad &GetRaggedTensorDofToQuad(
|
||||
const FiniteElement &fe, const IntegrationRule &ir,
|
||||
DofToQuad::Mode mode,
|
||||
Array<DofToQuad*> &dof2quad_array);
|
||||
|
||||
const Array<int> &GetDofMap() const { return dof_map; }
|
||||
|
||||
// The size of shape is (p+1)(p+2)(p+3)/6 (dof).
|
||||
static void CalcShape(const int p, const real_t x, const real_t y,
|
||||
const real_t z, real_t *shape);
|
||||
|
||||
@@ -17,12 +17,6 @@
|
||||
namespace mfem
|
||||
{
|
||||
|
||||
struct ScalarPyramid
|
||||
{
|
||||
// Default basis type for H1 and L2 pyramids
|
||||
static inline int DefaultType = 1; // Bergot(0) or Fuentes(1)
|
||||
};
|
||||
|
||||
/** Base class for arbitrary order basis functions on pyramid-shaped elements
|
||||
|
||||
This base class provides a common class to store temporary vectors,
|
||||
|
||||
+3
-3
@@ -2006,7 +2006,7 @@ RT_R1D_SegmentElement::RT_R1D_SegmentElement(const int p,
|
||||
const int cb_type,
|
||||
const int ob_type)
|
||||
: VectorFiniteElement(1, Geometry::SEGMENT, 3 * p + 4, p + 1,
|
||||
H_DIV_R1D, FunctionSpace::Pk),
|
||||
H_DIV, FunctionSpace::Pk),
|
||||
dof2nk(dof),
|
||||
cbasis1d(poly1d.GetBasis(p + 1, VerifyClosed(cb_type))),
|
||||
obasis1d(poly1d.GetBasis(p, VerifyOpen(ob_type)))
|
||||
@@ -2281,7 +2281,7 @@ const real_t RT_R2D_SegmentElement::nk[2] = { 0.,1.};
|
||||
RT_R2D_SegmentElement::RT_R2D_SegmentElement(const int p,
|
||||
const int ob_type)
|
||||
: VectorFiniteElement(1, Geometry::SEGMENT, p + 1, p + 1,
|
||||
H_DIV_R2D, FunctionSpace::Pk),
|
||||
H_DIV, FunctionSpace::Pk),
|
||||
dof2nk(dof),
|
||||
obasis1d(poly1d.GetBasis(p, VerifyOpen(ob_type)))
|
||||
{
|
||||
@@ -2392,7 +2392,7 @@ void RT_R2D_SegmentElement::LocalInterpolation(const VectorFiniteElement &cfe,
|
||||
RT_R2D_FiniteElement::RT_R2D_FiniteElement(int p, Geometry::Type G, int Do,
|
||||
const real_t *nk_fe)
|
||||
: VectorFiniteElement(2, G, Do, p + 1,
|
||||
H_DIV_R2D, FunctionSpace::Pk),
|
||||
H_DIV, FunctionSpace::Pk),
|
||||
nk(nk_fe),
|
||||
dof_map(dof),
|
||||
dof2nk(dof)
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user