testing dpg residual with cholesky factors

fix repo check
fix repo-check
2022-03-22 14:13:56 -07:00 · 2022-03-22 12:08:56 -07:00 · 2022-03-22 12:05:22 -07:00 · 2022-03-22 10:24:38 -07:00 · 2022-03-22 10:19:35 -07:00 · 2022-03-03 13:06:29 -08:00
529 changed files with 18830 additions and 45724 deletions
@@ -1,13 +1,10 @@
 version: '{build}'

 # https://www.appveyor.com/docs/build-environment/#build-worker-images
-image: Visual Studio 2019
+image: Visual Studio 2017

 install:

-# Start from outside clone directory
- cd ..
-
 # Install MS-MPI
 - ps: Start-FileDownload 'https://download.microsoft.com/download/B/2/E/B2EB83FE-98C2-4156-834A-E1711E6884FB/MSMpiSetup.exe'
 - MSMpiSetup.exe -unattend
@@ -18,13 +15,9 @@ install:
 - msmpisdk.msi /passive
 - set PATH=C:\Program Files\Microsoft MPI\Bin;%PATH%

-# Set MSMPI environment variables needed for CMake detection
- set MSMPI_LIB32=C:\Program Files (x86)\Microsoft SDKs\MPI\Lib\x86
- set MSMPI_LIB64=C:\Program Files (x86)\Microsoft SDKs\MPI\Lib\x64
- set MSMPI_INC=C:\Program Files (x86)\Microsoft SDKs\MPI\Include
-
-# Install METIS, use MFEM's mirror because the original source server is often
-# down and we don't support yet the new repo https://github.com/KarypisLab/METIS
+# Install METIS, use a mirror because the original source server is not always
+# up. Original url:
+#    http://glaros.dtc.umn.edu/gkhome/fetch/sw/metis/metis-5.1.0.tar.gz
 - ps: Start-FileDownload 'https://mfem.github.io/tpls/metis-5.1.0.tar.gz'
 - 7z x metis-5.1.0.tar.gz -so | 7z x -si -ttar > nul
 - cd metis-5.1.0
@@ -32,24 +25,20 @@ install:
 - cmake -H. -Bbuild
 # -DCMAKE_BUILD_TYPE=Release
 - cmake --build build
- set METIS_PATH=%cd%
 - cd ..

 # Install hypre
 - ps: Start-FileDownload 'https://github.com/hypre-space/hypre/archive/v2.19.0.tar.gz'
 - 7z x v2.19.0.tar.gz -so | 7z x -si -ttar > nul
 - cd hypre-2.19.0/src
- cmake -H. -Bbuild
+- cmake -H. -Bbuild -DMPI_C_INCLUDE_PATH="C:\Program Files (x86)\Microsoft SDKs\MPI\Include" -DMPI_C_LIBRARIES="C:\Program Files (x86)\Microsoft SDKs\MPI\Lib\x86\msmpi.lib" -DMPI_CXX_LIBRARIES="C:\Program Files (x86)\Microsoft SDKs\MPI\Lib\x86\msmpi.lib" -DMPI_CXX_INCLUDE_PATH="C:\Program Files (x86)\Microsoft SDKs\MPI\Include"
 - cmake --build build
 - cmake --build build --target install
 - cd ../..

-# Return to clone directory
- cd %APPVEYOR_BUILD_FOLDER%
-
 # MFEM
 before_build:
- cmake -H. -DCMAKE_INSTALL_PREFIX=install -Bbuild_parallel -DMFEM_USE_MPI=TRUE -DMFEM_USE_METIS_5=TRUE -DHYPRE_DIR=%cd%\..\hypre-2.19.0\src\hypre -DMETIS_LIBRARIES=%METIS_PATH%\build\libmetis\Debug\metis.lib -DMETIS_INCLUDE_DIRS=%METIS_PATH%\include
+- cmake -H. -DCMAKE_INSTALL_PREFIX=install -Bbuild_parallel -DMFEM_USE_MPI=TRUE -DMFEM_USE_METIS_5=TRUE -DMPI_CXX_LIBRARIES="C:\Program Files (x86)\Microsoft SDKs\MPI\Lib\x86\msmpi.lib" -DMPI_CXX_INCLUDE_PATH="C:\Program Files (x86)\Microsoft SDKs\MPI\Include" -DHYPRE_DIR=%cd%\hypre-2.19.0\src\hypre -DMETIS_LIBRARIES=%cd%\metis-5.1.0\build\libmetis\Debug\metis.lib -DMETIS_INCLUDE_DIRS=%cd%\metis-5.1.0\include
 - cmake -H. -DCMAKE_INSTALL_PREFIX=install -Bbuild_serial -DMFEM_USE_MPI=FALSE

 build_script:
@@ -1,82 +0,0 @@
-name: "Docker"
-
-on:
-
-  # Always have a base image ready to go - this is a nightly build
-  schedule:
-    - cron: 0 3 * * *
-
-  # Allow manual trigger of a build
-  workflow_dispatch:
-
-  # On push to main we build and deploy images
-  push:
-    branches:
-      - master
-
-  # Publish packages on release
-  release:
-    types: [published]
-
-jobs:
-  build:
-    if: github.repository == 'mfem/mfem' # Don't run in forks
-    permissions:
-      packages: write
-    strategy:
-      fail-fast: false
-      matrix:
-
-        # Dockerfiles to build, a matrix supports future expanded builds
-        container: [["config/docker/Dockerfile.base", "ghcr.io/mfem/mfem-ubuntu-base"],
-                    ["config/docker/Dockerfile", "ghcr.io/mfem/mfem-ubuntu"]]
-
-    runs-on: ubuntu-latest
-    name: Build
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-
-      - name: Make Space For Build
-        run: |
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /opt/ghc
-
-       # It's easier to reference named variables than indexes of the matrix
-      - name: Set Environment
-        env:
-          dockerfile: ${{ matrix.container[0] }}
-          uri: ${{ matrix.container[1] }}
-        run: |
-          echo "dockerfile=$dockerfile" >> $GITHUB_ENV
-          echo "uri=$uri" >> $GITHUB_ENV
-
-      - name: Pull previous layers for cache
-        run: docker pull ${uri}:latest || echo "No container to pull"
-
-      - name: Build Container
-        run: |
-           container=$uri:latest
-           docker build -f ${dockerfile} -t ${container} .
-           echo "container=$container" >> $GITHUB_ENV
-
-      - name: GHCR Login
-        if: (github.event_name != 'pull_request')
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Deploy
-        if: (github.event_name != 'pull_request')
-        run: |
-            docker push ${container}
-
-      - name: Tag and Push Release
-        if: (github.event_name == 'release')
-        run: |
-            tag=${GITHUB_REF#refs/tags/}
-            echo "Tagging and releasing ${uri}:${tag}"
-            docker tag ${uri}:latest ${uri}:${tag}
-            docker push ${uri}:${tag}
@@ -10,7 +10,7 @@
 # CONTRIBUTING.md for details.

 # In this CI section, we build different variants of mfem and run test on them.
-name: "Tests"
+name: builds-and-tests

 # Github actions can use the default "GITHUB_TOKEN". By default, this token
 # is set to have permissive access. However, this is not a good practice
@@ -27,7 +27,6 @@ on:
      - master
      - next
  pull_request:
-  workflow_dispatch:

 env:
  HYPRE_ARCHIVE: v2.19.0.tar.gz
@@ -47,18 +46,11 @@ jobs:
  builds-and-tests:
    strategy:
      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-18.04, macos-10.15]
        target: [dbg, opt]
        mpi: [seq, par]
-        build-system: [make, cmake]
+        build-system: [make]
        hypre-target: [int32]
-        exclude:
-          - os: ubuntu-latest
-            build-system: cmake
-          - os: macos-latest
-            build-system: cmake
-          - os: windows-latest
-            build-system: make
        # 'include' allows us to:
        # - Add a variable to all jobs without creating a new matrix dimension.
        #   Codecov is defined that way.
@@ -72,15 +64,13 @@ jobs:
            codecov: NO
          - target: opt
            codecov: YES
-          - os: windows-latest
-            codecov: NO
-          - os: ubuntu-latest
+          - os: ubuntu-18.04
            target: opt
            codecov: NO
            mpi: par
            build-system: cmake
            hypre-target: int32
-          - os: ubuntu-latest
+          - os: ubuntu-18.04
            target: opt
            codecov: NO
            mpi: par
@@ -94,7 +84,7 @@ jobs:
    # This external action allows to interrupt a workflow already running on
    # the same branch to save resource
    - name: Cancel Previous Runs
-      uses: styfle/cancel-workflow-action@0.11.0
+      uses: styfle/cancel-workflow-action@0.9.0
      with:
        access_token: ${{ github.token }}

@@ -102,7 +92,7 @@ jobs:
    # /home/runner/work/mfem/mfem/mfem
    # Note: Done now to access "install-hypre" and "install-metis" actions.
    - name: checkout mfem
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2
      with:
        path: ${{ env.MFEM_TOP_DIR }}
        # Fetch the complete history for codecov to access commits ID
@@ -112,107 +102,71 @@ jobs:
    # 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.
    - name: get MPI (Linux)
-      if: matrix.mpi == 'par' && matrix.os == 'ubuntu-latest'
+      if: matrix.mpi == 'par' && matrix.os == 'ubuntu-18.04'
      run: |
        sudo apt-get install mpich libmpich-dev
+        export MAKE_CXX_FLAG="MPICXX=mpic++"

    - name: get lcov (Linux)
-      if: matrix.codecov == 'YES' && matrix.os == 'ubuntu-latest'
+      if: matrix.codecov == 'YES' && matrix.os == 'ubuntu-18.04'
      run: |
        sudo apt-get install lcov

-    # Keep the following section in case we need it again in the future,
-    # see: https://github.com/mfem/mfem/pull/3385#discussion_r1058013032
-    # - name: Set up Homebrew
-    #   if: ( matrix.mpi == 'par' || matrix.codecov == 'YES' ) && matrix.os == 'macos-latest'
-    #   uses: Homebrew/actions/setup-homebrew@master
+    - name: Set up Homebrew
+      if: ( matrix.mpi == 'par' || matrix.codecov == 'YES' ) && matrix.os == 'macos-10.15'
+      uses: Homebrew/actions/setup-homebrew@c4aafe8c4620bf08883dd4679c374f11e73329d3

    - name: get MPI (MacOS)
-      if: matrix.mpi == 'par' && matrix.os == 'macos-latest'
+      if: matrix.mpi == 'par' && matrix.os == 'macos-10.15'
      run: |
        export HOMEBREW_NO_INSTALL_CLEANUP=1
        brew install openmpi
+        export MAKE_CXX_FLAG="MPICXX=mpic++"

-    - name: get lcov (MacOS)
-      if: matrix.codecov == 'YES' && matrix.os == 'macos-latest'
+    - name: get MPI (MacOS)
+      if: matrix.codecov == 'YES' && matrix.os == 'macos-10.15'
      run: |
        export HOMEBREW_NO_INSTALL_CLEANUP=1
        brew install lcov

-    - name: get MPI (Windows)
-      if: matrix.mpi == 'par' && matrix.os == 'windows-latest'
-      uses: mpi4py/setup-mpi@v1.1.2
-
    # Get Hypre through cache, or build it.
    # Install will only run on cache miss.
    - name: cache hypre
      id: hypre-cache
      if: matrix.mpi == 'par'
-      uses: actions/cache@v3
+      uses: actions/cache@v2
      with:
        path: ${{ env.HYPRE_TOP_DIR }}
-        key: ${{ runner.os }}-build-${{ env.HYPRE_TOP_DIR }}-${{ matrix.hypre-target }}-v2.2
+        key: ${{ runner.os }}-build-${{ env.HYPRE_TOP_DIR }}-${{ matrix.hypre-target }}-v2.0

    - name: get hypre
-      if: matrix.mpi == 'par' && steps.hypre-cache.outputs.cache-hit != 'true' && matrix.os != 'windows-latest'
-      uses: mfem/github-actions/build-hypre@v2.2
+      if: matrix.mpi == 'par' && steps.hypre-cache.outputs.cache-hit != 'true'
+      uses: mfem/github-actions/build-hypre@v2.0
      with:
        archive: ${{ env.HYPRE_ARCHIVE }}
        dir: ${{ env.HYPRE_TOP_DIR }}
        target: ${{ matrix.hypre-target }}
-        build-system: make
-
-    - 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@v2.2
-      with:
-        archive: ${{ env.HYPRE_ARCHIVE }}
-        dir: ${{ env.HYPRE_TOP_DIR }}
-        target: ${{ matrix.hypre-target }}
-        build-system: cmake

    # Get Metis through cache, or build it.
    # Install will only run on cache miss.
    - name: cache metis
      id: metis-cache
-      if: matrix.mpi == 'par' && matrix.os != 'windows-latest'
-      uses: actions/cache@v3
+      if: matrix.mpi == 'par'
+      uses: actions/cache@v2
      with:
        path: ${{ env.METIS_TOP_DIR }}
-        key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.2
+        key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.0

    - name: install metis
-      if: matrix.mpi == 'par' && matrix.os != 'windows-latest' && steps.metis-cache.outputs.cache-hit != 'true'
-      uses: mfem/github-actions/build-metis@v2.2
+      if: matrix.mpi == 'par' && steps.metis-cache.outputs.cache-hit != 'true'
+      uses: mfem/github-actions/build-metis@v2.0
      with:
        archive: ${{ env.METIS_ARCHIVE }}
        dir: ${{ env.METIS_TOP_DIR }}

-    - name: cache vcpkg (Windows)
-      id: vcpkg-cache
-      if: matrix.os == 'windows-latest'
-      uses: actions/cache@v3
-      with:
-        path: vcpkg_cache
-        key: ${{ runner.os }}-${{ matrix.mpi }}-vcpkg-v1
-
-    - name: prepare vcpkg binary cache location (Windows)
-      if: matrix.os == 'windows-latest' && steps.vcpkg-cache.outputs.cache-hit != 'true'
-      run: |
-        mkdir -p vcpkg_cache
-
-    - name: install metis (Windows)
-      if: matrix.mpi == 'par' && matrix.os == 'windows-latest'
-      env:
-        VCPKG_DEFAULT_BINARY_CACHE: ${{ github.workspace }}/vcpkg_cache
-      run: |
-        vcpkg install metis-mfem --triplet=x64-windows-static --overlay-ports=${{ env.MFEM_TOP_DIR }}/config/vcpkg/ports
-
    # MFEM build and test
    - name: build
-      uses: mfem/github-actions/build-mfem@v2.2
-      env:
-        VCPKG_DEFAULT_BINARY_CACHE: ${{ github.workspace }}/vcpkg_cache
+      uses: mfem/github-actions/build-mfem@v2.1
      with:
        os: ${{ matrix.os }}
        target: ${{ matrix.target }}
@@ -222,8 +176,6 @@ jobs:
        hypre-dir: ${{ env.HYPRE_TOP_DIR }}
        metis-dir: ${{ env.METIS_TOP_DIR }}
        mfem-dir: ${{ env.MFEM_TOP_DIR }}
-        config-options: ${{ env.MFEM_EXTRA_CONFIG }}
-        library-only: ${{ matrix.target == 'dbg' }}

    # Run checks (and only checks) on debug targets
    - name: checks
@@ -231,38 +183,25 @@ jobs:
      run: |
        cd ${{ env.MFEM_TOP_DIR }}  && make check

-    # Note: 'tests' include the unit tests
+    - name: unit tests
+      if: matrix.build-system == 'make' && matrix.target == 'opt'
+      run: |
+        cd ${{ env.MFEM_TOP_DIR }} && make unittest
+
    - name: tests
      if: matrix.build-system == 'make' && matrix.target == 'opt'
      run: |
        cd ${{ env.MFEM_TOP_DIR }} && make test

-    - name: cmake checks
-      if: matrix.build-system == 'cmake' && matrix.target == 'dbg'
+    - name: cmake unit tests
+      if: matrix.build-system == 'cmake'
      run: |
-        CTEST_CONFIG="Debug"
-        cd ${{ env.MFEM_TOP_DIR }} && cmake --build build --target check --config ${CTEST_CONFIG}
-      shell: bash
-
-    - name: cmake unit tests (Ubuntu)
-      if: matrix.build-system == 'cmake' && matrix.target == 'opt' && matrix.os == 'ubuntu-latest'
-      run: |
-        CTEST_CONFIG="Release"
-        [[ ${{ matrix.target }} == 'dbg' ]] && CTEST_CONFIG="Debug"
-        cd ${{ env.MFEM_TOP_DIR }}/build/tests/unit && ctest --output-on-failure -C ${CTEST_CONFIG}
-      shell: bash
-
-    - name: cmake tests
-      if: matrix.build-system == 'cmake' && matrix.target == 'opt' && matrix.os != 'ubuntu-latest'
-      run: |
-        CTEST_CONFIG="Release"
-        cd ${{ env.MFEM_TOP_DIR }}/build && ctest --output-on-failure -C ${CTEST_CONFIG}
-      shell: bash
+        cd ${{ env.MFEM_TOP_DIR }}/build/tests/unit && ctest --output-on-failure

    # Code coverage (process and upload reports)
    - name: codecov
      if: matrix.codecov == 'YES'
-      uses: mfem/github-actions/upload-coverage@v2.2
+      uses: mfem/github-actions/upload-coverage@v2.0
      with:
        name: ${{ matrix.os }}-${{ matrix.build-system }}-${{ matrix.target }}-${{ matrix.mpi }}-${{ matrix.hypre-target }}
        project_dir: ${{ env.MFEM_TOP_DIR }}
@@ -1,70 +0,0 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-#
-# ******** NOTE ********
-# We have attempted to detect the languages in your repository. Please check
-# the `language` matrix defined below to confirm you have the correct set of
-# supported CodeQL languages.
-#
-name: "Static Analysis"
-
-on:
-  push:
-    branches: [ "master", "next"]
-  pull_request:
-    # The branches below must be a subset of the branches above
-    branches: [ "master" ]
-
-jobs:
-  analyze:
-    name: Analyze
-    runs-on: ubuntu-latest
-    permissions:
-      actions: read
-      contents: read
-      security-events: write
-
-    strategy:
-      fail-fast: false
-      matrix:
-        language: [ 'cpp' ]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
-        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v3
-
-    # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
-      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.
-        # By default, queries listed here will override any specified in a config file.
-        # Prefix the list here with "+" to use these queries and those in the config file.
-
-        # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
-        # queries: security-extended,security-and-quality
-
-
-    # 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@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
-
-    #   If the Autobuild fails above, remove it and uncomment the following three lines.
-    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
-
-    # - run: |
-    #   echo "Run, Build Application using script"
-    #   ./location_of_script_within_repo/buildscript.sh
-
-    - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
@@ -9,7 +9,7 @@
 # terms of the BSD-3 license. We welcome feedback and contributions, see file
 # CONTRIBUTING.md for details.

-name: "Build Analysis"
+name: build-analysis

 permissions:
  actions: write
@@ -20,7 +20,6 @@ on:
      - master
      - next
  pull_request:
-  workflow_dispatch:

 env:
  HYPRE_ARCHIVE: v2.19.0.tar.gz
@@ -31,33 +30,34 @@ env:

 jobs:
  gitignore:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-18.04

    steps:
    - name: Cancel Previous Runs
-      uses: styfle/cancel-workflow-action@0.11.0
+      uses: styfle/cancel-workflow-action@0.9.0
      with:
        access_token: ${{ github.token }}

    - name: checkout MFEM
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2
      with:
        path: mfem

    - name: Get MPI (Linux)
      run: |
        sudo apt-get install mpich libmpich-dev
+        export MAKE_CXX_FLAG="MPICXX=mpic++"

    - name: Cache Hypre Install
      id: hypre-cache
-      uses: actions/cache@v3
+      uses: actions/cache@v2
      with:
        path: ${{ env.HYPRE_TOP_DIR }}
-        key: ${{ runner.os }}-build-${{ env.HYPRE_TOP_DIR }}-v2.2
+        key: ${{ runner.os }}-build-${{ env.HYPRE_TOP_DIR }}-v2.0

    - name: Get Hypre
      if: steps.hypre-cache.outputs.cache-hit != 'true'
-      uses: mfem/github-actions/build-hypre@v2.2
+      uses: mfem/github-actions/build-hypre@v2.0
      with:
        archive: ${{ env.HYPRE_ARCHIVE }}
        dir: ${{ env.HYPRE_TOP_DIR }}
@@ -65,21 +65,21 @@ jobs:

    - name: Cache Metis Install
      id: metis-cache
-      uses: actions/cache@v3
+      uses: actions/cache@v2
      with:
        path: ${{ env.METIS_TOP_DIR }}
-        key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.2
+        key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.0

    - name: Install Metis
      if: steps.metis-cache.outputs.cache-hit != 'true'
-      uses: mfem/github-actions/build-metis@v2.2
+      uses: mfem/github-actions/build-metis@v2.0
      with:
        archive: ${{ env.METIS_ARCHIVE }}
        dir: ${{ env.METIS_TOP_DIR }}

    # MFEM build and test
    - name: build-mfem
-      uses: mfem/github-actions/build-mfem@v2.2
+      uses: mfem/github-actions/build-mfem@v2.0
      with:
        os: ${{ runner.os }}
        target: opt
@@ -9,37 +9,25 @@
 # terms of the BSD-3 license. We welcome feedback and contributions, see file
 # CONTRIBUTING.md for details.

-name: "Checks"
+name: repo-check

 permissions:
  actions: write

 on:
  push:
-  pull_request:
-  workflow_dispatch:
-
-# This workflow is run on pushes to any branch in the MFEM repo (with or without
-# PRs), as well as on updates to PRs from forks. In particular, we do not
-# duplicate work by running on both pushes and updates to local PRs. We do that
-# 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").

 jobs:
  file-headers-check:
-    runs-on: ubuntu-latest
-    if: |
-      (github.event_name == 'push' ||
-       github.event.pull_request.head.repo.full_name != github.repository)
+    runs-on: ubuntu-18.04
+
    steps:
    - name: Cancel Previous Runs
-      uses: styfle/cancel-workflow-action@0.11.0
+      uses: styfle/cancel-workflow-action@0.9.0
      with:
        access_token: ${{ github.token }}
-
    - name: checkout mfem
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2

    - name: copyright check
      id: copyright
@@ -61,10 +49,7 @@ jobs:
      continue-on-error: true

    - name: wrap-up
-      if: |
-        steps.copyright.outcome != 'success' ||
-        steps.license.outcome != 'success' ||
-        steps.release.outcome != 'success'
+      if: steps.copyright.outcome != 'success' || steps.license.outcome != 'success' || steps.release.outcome != 'success'
      run: |
        if [[ "${{ steps.copyright.outcome }}" != "success" ]]; then
          echo "copyright check failed, unroll log for details"
@@ -78,55 +63,43 @@ jobs:
        exit 1

  code-style:
-    runs-on: ubuntu-latest
-    if: |
-      (github.event_name == 'push' ||
-       github.event.pull_request.head.repo.full_name != github.repository)
+    runs-on: ubuntu-18.04
+
    steps:
    - name: checkout mfem
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2

    - name: get astyle
      run: |
-        sudo apt-get install astyle
+        sudo apt-get install astyle=3.1-1ubuntu2

    - name: style check
      run: |
        ./config/githooks/pre-push --style

  documentation:
-    runs-on: ubuntu-latest
-    if: |
-      (github.event_name == 'push' ||
-       github.event.pull_request.head.repo.full_name != github.repository)
+    runs-on: ubuntu-18.04
+
    steps:
    - name: checkout mfem
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2

    - name: get doxygen and graphviz
      run: |
        sudo apt-get install doxygen graphviz

-    - name: update doxygen config file
-      run: |
-        cd doc
-        doxygen -u CodeDocumentation.conf.in
-
    - name: build documentation
      run: |
        cd tests/scripts
        ./runtest documentation

  branch-history:
-    if: |
-      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
+    if: github.ref != 'refs/heads/next' && github.ref != 'refs/heads/master'
+    runs-on: ubuntu-18.04
+
    steps:
    - name: checkout mfem
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2
      with:
        fetch-depth: 0

@@ -240,7 +240,6 @@ miniapps/navier/navier_kovasznay_vs
 miniapps/navier/navier_tgv
 miniapps/navier/navier_shear
 miniapps/navier/navier_3dfoc
-miniapps/navier/navier_turbchan
 miniapps/navier/tgv_out*.txt
 miniapps/navier/*_output

@@ -261,21 +260,18 @@ miniapps/performance/sol.*

 miniapps/shifted/distance
 miniapps/shifted/ParaViewDistance
-miniapps/shifted/ParaViewLSF
 miniapps/shifted/extrapolate
 miniapps/shifted/ParaViewExtrapolate
 miniapps/shifted/diffusion
 miniapps/shifted/diffusion.mesh
 miniapps/shifted/diffusion.gf
 miniapps/shifted/ParaViewDiffusion
-miniapps/shifted/lsf_integral

 miniapps/tools/display-basis
 miniapps/tools/load-dc
 miniapps/tools/convert-dc
 miniapps/tools/lor-transfer
 miniapps/tools/get-values
-miniapps/tools/check-tmop-metric

 miniapps/toys/automata
 miniapps/toys/life
@@ -308,9 +304,6 @@ miniapps/solvers/sol.*
 miniapps/parelag/MultilevelHcurlHdivSolver
 miniapps/parelag/*.mesh

-miniapps/multidomain/multidomain
-miniapps/hooke/hooke
-
 # Unit test binary and outputs
 tests/unit/output_meshes
 tests/unit/unit_tests
@@ -45,5 +45,5 @@ variables:
    - echo ${MFEM_DATA_DIR}
    - echo ${SPEC}
    # Next script uses 'THREADS': leaving it empty --> it uses 'make all -j'
-    - lalloc 1 -W 45 -q pdebug --atsdisable tests/gitlab/build_and_test --spec "${SPEC}" --data-dir "${MFEM_DATA_DIR}" --data
+    - lalloc 1 -W 30 -q pdebug --atsdisable tests/gitlab/build_and_test --spec "${SPEC}" --data-dir "${MFEM_DATA_DIR}" --data
  needs: [setup]
@@ -52,4 +52,4 @@ variables:
    - echo ${JOBID}
    - echo ${MFEM_DATA_DIR}
    - echo ${SPEC}
-    - srun $( [[ -n "${JOBID}" ]] && echo "--jobid=${JOBID}" ) -t 45 -N 1 tests/gitlab/build_and_test --spec "${SPEC}" --data-dir "${MFEM_DATA_DIR}" --data
+    - srun $( [[ -n "${JOBID}" ]] && echo "--jobid=${JOBID}" ) -t 30 -N 1 tests/gitlab/build_and_test --spec "${SPEC}" --data-dir "${MFEM_DATA_DIR}" --data
@@ -23,7 +23,7 @@ allocate_resource:
  stage: allocate_resource
  script:
    - echo ${ALLOC_NAME}
-    - salloc --exclusive --nodes=1 --partition=mi60 --time=45 --no-shell --job-name=${ALLOC_NAME}
+    - salloc --exclusive --nodes=1 --partition=mi60 --time=30 --no-shell --job-name=${ALLOC_NAME}
  timeout: 6h
  needs: [setup]

@@ -23,7 +23,7 @@ allocate_resource:
  stage: allocate_resource
  script:
    - echo ${ALLOC_NAME}
-    - salloc --exclusive --nodes=1 --partition=pdebug --time=45 --no-shell --job-name=${ALLOC_NAME}
+    - salloc --exclusive --nodes=1 --partition=pdebug --time=30 --no-shell --job-name=${ALLOC_NAME}
  timeout: 6h

 # GitLab jobs for the Quartz machine at LLNL
@@ -8,192 +8,6 @@
                               https://mfem.org


-
-
-Version 4.5.1 (development)
-===========================
-
-Meshing improvements
--------------------
- Added support for pyramids in non-conforming meshes. Currently only isotropic
-  refinement is supported in this case.
-
-Discretization improvements
---------------------------
- TBD
-
-Linear and nonlinear solvers
----------------------------
- Added a fast normalization-based distance solver, see the Distance miniapp
-  in the miniapps/shifted/ directory.
-
-New and updated examples and miniapps
-------------------------------------
- TBD
-
-Integrations, testing and documentation
---------------------------------------
- Removed the support for the Mesquite toolkit. We recommend using MFEM's TMOP
-  functionality instead for mesh optimization. See the mesh-optimizer miniapp.
-
-Miscellaneous
-------------
- VisItDataCollection now correctly handles collection names containing
-  underscores.
-
- VisItDataCollection::SetPadDigits() no longer alters the number of digits
-  used to represent the MPI rank because VisIt seems to require 6 digits.
-  This parameter can still be explicitly overridden with
-  VisItDataCollection::SetPadDigitsRank().
-
-API changes
-----------
- The implicit cast methods of class Vector to 'double *' and 'const double *'
-  have been deprecated and generate deprecation warnings if used. They will be
-  removed in a future release.
-
-
-Version 4.5, released on October 22, 2022
-=========================================
-
-Meshing improvements
--------------------
- Added new SubMesh and ParSubMesh classes that can be used to extract a subset
-  of a given Mesh. These classes have the same functionality as Mesh and ParMesh
-  and work with all existing MFEM interfaces like finite element spaces etc.
-
- Added a method, ParMesh::GetSerialMesh(), that reconstructs a partitioned
-  parallel mesh on a given single rank. Also, added ParMesh::PrintAsSerial(),
-  which saves the reconstructed serial mesh to a C++ stream on rank 0.
-
- Added more 3D TMOP metrics, as well as specialized metrics for mesh
-  untangling and worst-case quality improvement.
-
- Added a new method, Mesh::NodesUpdated, which should be called after the mesh
-  node coordinates have changed, e.g. after the mesh has moved. This is
-  necessary, for example, with device assembly of linear and bilinear forms.
-
- Added support for mixed meshes and pyramids in GSLIB-FindPoints.
-
-Discretization improvements
---------------------------
- Added full assembly and device support for several LinearForm integrators:
-  * DomainLF: (f, v)
-  * VectorDomainLF: ((f1,...,fn), (v1,...,vn))
-  * DomainLFGrad: (f, grad(v))
-  * VectorDomainLFGrad: ((f1x,f1y,f1z,...,fnx,fny,fnz), grad(v1,...,vn))
-  The device assembly of linear forms has to be explicitly enabled by calling
-  LinearForm::UseFastAssembly(true), otherwise the legacy linear form assembly
-  is used by default.
-
- Added support for assembling low-order-refined matrices using a GPU-enabled
-  "batched" algorithm. The lor_solvers and plor_solvers now fully support GPU
-  acceleration with arbitrary user-supplied coefficients.
-
- Added a new class FaceQuadratureSpace that allows for the construction of
-  QuadratureFunctions on the interior or boundary faces of a mesh.
-
- Added a class CoefficientVector for efficient access of variable coefficient
-  values at quadrature points (in particular for GPU/device kernels).
-
- Added WhiteGaussianNoiseDomainLFIntegrator: a LinearFormIntegrator class for
-  spatial Gaussian white noise.
-
- Added a new Zienkiewicz-Zhu patch recovery-based a posteriori error estimator.
-  See fem/estimators.hpp.
-
- Various fixes and improvements in LinearFormExtension.
-
-Linear and nonlinear solvers
----------------------------
- Added a new class DGMassInverse that performs a local element-wise CG
-  iteration to solve systems involving the discontinuous Galerkin mass matrix,
-  including support for device/GPU acceleration.
-
- Added more flexibility to the constrained solver classes:
-  * PenaltyConstrainedSolver now allows for a vector of penalty parameters
-    (necessary for penalty contact)
-  * PenaltyConstrainedSolver and EliminationSolver can use GMRES or PCG
-  * All constraint solver classes can take a user-defined preconditioner
-
- - Added functions to toggle additional options for the SuperLU_Dist and Hypre
-   preconditioners (ParaSails, Euclid, ILU).
-
- Added boundary elimination with device support for `SparseMatrix` and
-  `HypreParMatrix`.
-
-New and updated examples and miniapps
-------------------------------------
- Added a new elasticity miniapp, Hooke, that showcases a low-level approach of
-  using MFEM to solve a nonlinear elasticity problem based on the fundamental
-  finite element operator decomposition. The miniapp also integrates with
-  automatic differentiation tools like a native dual number implementation or a
-  third party library such as Enzyme. See miniapps/elasticity for more details.
-
- Added example for body-fitted volumetric and shape integration using the
-  Algoim library in miniapps/shifted.
-
- Add a new example code, Example 33/33p, to demonstrate the solution of
-  spectral fractional PDEs with MFEM.
-
-Integrations, testing and documentation
---------------------------------------
- Added a Dockerfile for a simple MFEM container, see config/docker/README.md.
-  More sophisticated developer containers are available in the new repo
-  https://github.com/mfem/containers.
-
- Added support for the LLVM-based automatic differentiation tool Enzyme, see
-  https://github.com/EnzymeAD/Enzyme. Build system flags and a convenience
-  header are provided. The functionality and interaction are demonstrated in a
-  new miniapp in miniapps/elasticity.
-
- Added support for partial assembly and fully matrix-free operators on mixed
-  meshes (different element types and p-adaptivity) through libCEED, including
-  device acceleration, e.g. with NVIDIA and AMD GPUs. The p-adaptivity is
-  currently limited to 2D serial meshes. All mixed element topologies are
-  supported in both serial and parallel.
-
- Added support for ParMoonolith, https://bitbucket.org/zulianp/par_moonolith,
-  which provides parallel non-conforming, non-matching, variational, volumetric
-  mesh information transfer. With ParMortarAssember, fields can be exchanged
-  between arbitrarily distributed and unrelated finite element meshes in a
-  variationally consistent way.
-
- Fully encapsulated SUNDIALS `N_Vector` object within the `SundialsNVector`
-  class by removing deprecated (e.g. `HypreParVector::ToNVector`) and
-  non-deprecated (e.g. `Vector::ToNVector`) functions in other classes.
-
- New benchmark for the different assembly levels inspired by the CEED
-  Bake-Off Problems, see tests/benchmarks/bench_assembly_levels.cpp.
-
- Added Windows 2022 CI testing with GitHub actions.
-
-Miscellaneous
-------------
- The method SparseMatrix::EnsureMultTranspose() is now automatically called
-  by the methods AddMultTranspose(), MultTranspose(), and AbsMultTranspose().
-  Added a method with the same name to class HypreParMatrix which is also called
-  automatically by the HypreParMatrix::MultTranspose() methods.
-
- Updated various MemoryUsage methods to return 'std::size_t' instead of 'long'
-  since the latter is 32-bit in Win64 builds.
-
- When using `AssemblyLevel::FULL`, `FABilinearFormExtension::FormSystemMatrix`
-  outputs an `OperatorHandle` containing a `SparseMatrix` in serial, and an
-  `HypreParMatrix` in parallel (instead of a `ConstrainedOperator`).
-
- In various places in the library, replace the use of 'long' with 'long long'
-  to better support Win64 builds where 'long' is 32-bit and 'long long' is
-  64-bit. On Linux and MacOS, both types are typically 64-bit.
-
- The behavior of GridFunction::GetTrueVector() has been changed to not return
-  an empty true vector.
-
- Added support for ordering search points byVDIM in FindPointsGSLIB.
-
- Various other simplifications, extensions, and bugfixes in the code.
-
-
 Version 4.4, released on March 21, 2022
 =======================================

@@ -10,9 +10,7 @@
 # CONTRIBUTING.md for details.

 # The variable CMAKE_CXX_STANDARD and related were introduced in CMake v3.1
-# Version 3.8 fixes the handling of CMAKE_CXX_STANDARD for try_compile.
-# Version 3.8 or newer is required for direct CUDA support.
-cmake_minimum_required(VERSION 3.8)
+cmake_minimum_required(VERSION 3.1)
 set(USER_CONFIG "${CMAKE_CURRENT_SOURCE_DIR}/config/user.cmake" CACHE PATH
  "Path to optional user configuration file.")

@@ -53,7 +51,7 @@ project(mfem NONE)
 # Current version of MFEM, see also `makefile`.
 #   mfem_VERSION = (string)
 #   MFEM_VERSION = (int)   [automatically derived from mfem_VERSION]
-set(${PROJECT_NAME}_VERSION 4.5.1)
+set(${PROJECT_NAME}_VERSION 4.4.0)

 # Prohibit in-source build
 if (${PROJECT_SOURCE_DIR} STREQUAL ${PROJECT_BINARY_DIR})
@@ -68,7 +66,8 @@ set(XSDK_ENABLE_C OFF)
 set(XSDK_ENABLE_Fortran OFF)

 # Check if we need to enable C or Fortran.
-if (MFEM_USE_CONDUIT OR
+if (CMAKE_VERSION VERSION_LESS 3.2 OR
+    MFEM_USE_CONDUIT OR
    MFEM_USE_SIDRE OR
    MFEM_USE_PETSC)
   # This seems to be needed by:
@@ -82,9 +81,7 @@ if (MFEM_USE_STRUMPACK)
  # Just needed to find the MPI_Fortran libraries to link with
  set(XSDK_ENABLE_Fortran ON)
 endif()
-# SUNDIALS, STRUMPACK, and Ginkgo require C++14:
-if ((MFEM_USE_SUNDIALS OR MFEM_USE_STRUMPACK OR MFEM_USE_GINKGO) AND
-    ("${CMAKE_CXX_STANDARD}" LESS "14"))
+if (MFEM_USE_GINKGO AND ("${CMAKE_CXX_STANDARD}" LESS "14"))
  set(CMAKE_CXX_STANDARD 14)
 endif()

@@ -102,6 +99,8 @@ if (MFEM_USE_CUDA)
   if (MFEM_USE_HIP)
      message(FATAL_ERROR " *** MFEM_USE_HIP cannot be combined with MFEM_USE_CUDA.")
   endif()
+   # MFEM_USE_CUDA requires CMake 3.8 or newer (for direct CUDA support)
+   cmake_minimum_required(VERSION 3.8 FATAL_ERROR)
   # Use ${CMAKE_CXX_COMPILER} as the cuda host compiler.
   if (NOT CMAKE_CUDA_HOST_COMPILER)
      set(CMAKE_CUDA_HOST_COMPILER ${CMAKE_CXX_COMPILER})
@@ -137,8 +136,6 @@ if (MFEM_USE_CUDA)
       "CUDA flags set for MFEM" FORCE)
   set(CUSPARSE_FOUND TRUE)
   set(CUSPARSE_LIBRARIES "cusparse")
-   set(CUBLAS_FOUND TRUE)
-   set(CUBLAS_LIBRARIES "cublas")
 endif()

 if (XSDK_ENABLE_C)
@@ -196,35 +193,15 @@ if (MFEM_USE_HIP)
  find_package(HIPSPARSE REQUIRED)
 endif()

-# OpenMP
-if (MFEM_USE_OPENMP OR MFEM_USE_LEGACY_OPENMP)
-  if (NOT MFEM_THREAD_SAFE AND MFEM_USE_LEGACY_OPENMP)
-    message(FATAL_ERROR " *** MFEM_USE_LEGACY_OPENMP requires MFEM_THREAD_SAFE=ON.")
-  endif()
-  find_package(OpenMP REQUIRED)
-  set(OPENMP_LIBRARIES ${OpenMP_CXX_LIBRARIES})
-  if(APPLE)
-    # On macOS, the compiler needs additional help to find the <omp.h> header.
-    # See issue #2642 for more information.
-    set(OPENMP_INCLUDE_DIRS ${OpenMP_CXX_INCLUDE_DIRS})
-  endif(APPLE)
-  if (OPENMP_FOUND)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
-    if (MFEM_USE_CUDA)
-      set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler=${OpenMP_CXX_FLAGS}")
-    endif()
-  endif()
-endif()
-
 # MPI -> hypre; PETSc (optional)
 if (MFEM_USE_MPI)
  find_package(MPI REQUIRED)
  set(MPI_CXX_INCLUDE_DIRS ${MPI_CXX_INCLUDE_PATH})
  if (MFEM_MPIEXEC)
-    string(REPLACE " " ";" MPIEXEC ${MFEM_MPIEXEC})
+    set(MPIEXEC ${MFEM_MPIEXEC})
  endif()
  if (MFEM_MPIEXEC_NP)
-    string(REPLACE " " ";" MPIEXEC_NUMPROC_FLAG ${MFEM_MPIEXEC_NP})
+    set(MPIEXEC_NUMPROC_FLAG ${MFEM_MPIEXEC_NP})
  endif()
  # Parallel MFEM depends on hypre
  find_package(HYPRE REQUIRED)
@@ -281,6 +258,20 @@ if (MFEM_USE_LAPACK)
  find_package(LAPACK REQUIRED)
 endif()

+# OpenMP
+if (MFEM_USE_OPENMP OR MFEM_USE_LEGACY_OPENMP)
+  if (NOT MFEM_THREAD_SAFE AND MFEM_USE_LEGACY_OPENMP)
+    message(FATAL_ERROR " *** MFEM_USE_LEGACY_OPENMP requires MFEM_THREAD_SAFE=ON.")
+  endif()
+  find_package(OpenMP REQUIRED)
+  set(OPENMP_LIBRARIES ${OpenMP_CXX_LIBRARIES})
+  if(APPLE)
+    # On macOS, the compiler needs additional help to find the <omp.h> header.
+    # See issue #2642 for more information.
+    include_directories(${OpenMP_CXX_INCLUDE_DIRS})
+  endif(APPLE)
+endif()
+
 # SuiteSparse (before SUNDIALS which may depend on KLU)
 if (MFEM_USE_SUITESPARSE)
  find_package(SuiteSparse REQUIRED
@@ -299,6 +290,11 @@ if (MFEM_USE_SUNDIALS)
  find_package(SUNDIALS REQUIRED ${SUNDIALS_COMPONENTS})
 endif()

+# Mesquite
+if (MFEM_USE_MESQUITE)
+  find_package(Mesquite REQUIRED)
+endif()
+
 # SuperLU_DIST can only be enabled in parallel
 if (MFEM_USE_SUPERLU)
  if (MFEM_USE_MPI)
@@ -383,21 +379,6 @@ if (MFEM_USE_PUMI)
  endif()
 endif()

-# Moonolith
-if(MFEM_USE_MOONOLITH)
-  find_package(ParMoonolith REQUIRED)
-  if(ParMoonolith_FOUND)
-    get_target_property(
-      MOONOLITH_INCLUDE_DIRS ParMoonolith::par_moonolith
-      INTERFACE_INCLUDE_DIRECTORIES)
-    set(MOONOLITH_FOUND TRUE)
-    set(MOONOLITH_LIBRARIES ParMoonolith::par_moonolith)
-    message(
-      STATUS
-      "MOONOLITH_LIBRARIES=${MOONOLITH_LIBRARIES}, MOONOLITH_INCLUDE_DIRS=${MOONOLITH_INCLUDE_DIRS}")
-  endif()
-endif()
-
 # HiOp optimizer
 if (MFEM_USE_HIOP)
  find_package(HIOP REQUIRED)
@@ -435,11 +416,6 @@ if (MFEM_USE_CALIPER)
  find_package(Caliper REQUIRED)
 endif()

-# Algoim
-if (MFEM_USE_ALGOIM)
-  find_package(Algoim REQUIRED)
-endif()
-
 # ADIOS2 for parallel I/O
 if (MFEM_USE_ADIOS2)
   find_package(ADIOS2 REQUIRED)
@@ -456,11 +432,6 @@ if (MFEM_USE_PARELAG)
   find_package(PARELAG REQUIRED)
 endif()

-# Enzyme
-if (MFEM_USE_ENZYME)
-   find_package(ENZYME REQUIRED)
-endif()
-
 # MFEM_TIMER_TYPE
 if (NOT DEFINED MFEM_TIMER_TYPE)
  if (APPLE)
@@ -479,29 +450,16 @@ if (NOT DEFINED MFEM_TIMER_TYPE)
  endif()
 endif()

-# Without this, CMake 3.21.1 (and 3.20.2) run into CMake Errors like the following:
-# CMake Error at config/cmake/modules/MfemCmakeUtilities.cmake:60 (add_library):
-#   Target "mfem" links to target "Threads::Threads" but the target was not
-#   found.  Perhaps a find_package() call is missing for an IMPORTED target, or
-#   an ALIAS target is missing?
-# Call Stack (most recent call first):
-#   CMakeLists.txt:474 (mfem_add_library)
-#
-# NOTE: We need to figure out which TPL library adds the dependency on
-#       "Threads::Threads" and call the next line only when that TPL library is
-#       enabled.  -V. Dobrev
-find_package(Threads REQUIRED)
-
 # List all possible libraries in order of dependencies.
 # [METIS < SuiteSparse]:
 #    With newer versions of SuiteSparse which include METIS header using 64-bit
 #    integers, the METIS header (with 32-bit indices, as used by mfem) needs to
 #    be before SuiteSparse.
-set(MFEM_TPLS OPENMP HYPRE LAPACK BLAS SuperLUDist STRUMPACK METIS SuiteSparse
-    SUNDIALS PETSC SLEPC MUMPS AXOM FMS CONDUIT Ginkgo GNUTLS GSLIB
+set(MFEM_TPLS OPENMP HYPRE BLAS LAPACK SuperLUDist METIS SuiteSparse SUNDIALS
+    PETSC SLEPC MESQUITE MUMPS STRUMPACK AXOM FMS CONDUIT Ginkgo GNUTLS GSLIB
    NETCDF MPFR PUMI HIOP POSIXCLOCKS MFEMBacktrace ZLIB OCCA CEED RAJA UMPIRE
-    ADIOS2 CUBLAS CUSPARSE MKL_CPARDISO AMGX CALIPER CODIPACK BENCHMARK PARELAG
-    MPI_CXX HIP HIPSPARSE MOONOLITH BLITZ ALGOIM ENZYME)
+    ADIOS2 CUSPARSE MKL_CPARDISO AMGX CALIPER CODIPACK BENCHMARK PARELAG
+    MPI_CXX HIP HIPSPARSE)

 # Add all *_FOUND libraries in the variable TPL_LIBRARIES.
 set(TPL_LIBRARIES "")
@@ -513,11 +471,18 @@ foreach(TPL IN LISTS MFEM_TPLS)
    list(APPEND TPL_INCLUDE_DIRS ${${TPL}_INCLUDE_DIRS})
  endif()
 endforeach(TPL)
-list(REVERSE TPL_LIBRARIES)
 list(REMOVE_DUPLICATES TPL_LIBRARIES)
-list(REVERSE TPL_LIBRARIES)
 list(REMOVE_DUPLICATES TPL_INCLUDE_DIRS)
 # message(STATUS "TPL_INCLUDE_DIRS = ${TPL_INCLUDE_DIRS}")
+include_directories(${TPL_INCLUDE_DIRS})
+
+if (OPENMP_FOUND)
+  message(STATUS "MFEM: using package OpenMP")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
+  if (MFEM_USE_CUDA)
+    set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -Xcompiler=${OpenMP_CXX_FLAGS}")
+  endif()
+endif()

 message(STATUS "MFEM build type: CMAKE_BUILD_TYPE = ${CMAKE_BUILD_TYPE}")
 message(STATUS "MFEM version: v${MFEM_VERSION_STRING}")
@@ -531,11 +496,6 @@ message(STATUS "MFEM git string: ${MFEM_GIT_STRING}")
 set(SOURCES "")
 set(HEADERS "")
 set(MFEM_SOURCE_DIRS general linalg mesh fem)
-
-if(MFEM_USE_MOONOLITH)
-  set(MFEM_SOURCE_DIRS ${MFEM_SOURCE_DIRS} fem/moonolith)
-endif()
-
 foreach(DIR IN LISTS MFEM_SOURCE_DIRS)
  add_subdirectory(${DIR})
 endforeach()
@@ -566,15 +526,6 @@ target_link_libraries(mfem PUBLIC ${TPL_LIBRARIES})
 if (MINGW)
  target_link_libraries(mfem PRIVATE ws2_32)
 endif()
-if (MSVC)
-  target_compile_options(mfem PUBLIC "/wd4819")
-endif()
-message(STATUS "TPL_INCLUDE_DIRS = ${TPL_INCLUDE_DIRS}")
-target_include_directories(mfem
-  PUBLIC
-    $<BUILD_INTERFACE:${CMAKE_CURRENT_BINARY_DIR}>
-    $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
-    ${TPL_INCLUDE_DIRS})
 set_target_properties(mfem PROPERTIES VERSION "${mfem_VERSION}")
 set_target_properties(mfem PROPERTIES SOVERSION "${mfem_VERSION}")

@@ -703,10 +654,6 @@ set(INSTALL_LIB_DIR lib
 set(INSTALL_CMAKE_DIR lib/cmake/mfem
  CACHE PATH "Relative path for installing cmake config files.")

-target_include_directories(mfem
-  PUBLIC
-    $<INSTALL_INTERFACE:${INSTALL_INCLUDE_DIR}>)
-
 # The 'install' target will not depend on 'all'.
 # set(CMAKE_SKIP_INSTALL_ALL_DEPENDENCY TRUE)

@@ -740,7 +687,7 @@ endif()
 if (MFEM_USE_CEED)
  install(DIRECTORY ${MFEM_SOURCE_DIRS}
    DESTINATION ${INSTALL_INCLUDE_DIR}/mfem
-    FILES_MATCHING PATTERN "fem/ceed/integrators/*/*.h")
+    FILES_MATCHING PATTERN "fem/ceed/*.h")
 endif()

 # Install ${HEADERS}
@@ -771,8 +718,14 @@ export(TARGETS ${PROJECT_NAME}
 # TODO: How do we register the install-tree? Replacing the build-tree?
 export(PACKAGE ${PROJECT_NAME})

+# Extract the include directories required to use MFEM
+get_target_property(MFEM_TPL_INCLUDE_DIRS mfem INCLUDE_DIRECTORIES)
+if (NOT MFEM_TPL_INCLUDE_DIRS)
+  set(MFEM_TPL_INCLUDE_DIRS "")
+endif()
+
 # This is the build-tree version
-set(INCLUDE_INSTALL_DIRS ${PROJECT_BINARY_DIR} ${TPL_INCLUDE_DIRS})
+set(INCLUDE_INSTALL_DIRS ${PROJECT_BINARY_DIR} ${MFEM_TPL_INCLUDE_DIRS})
 set(LIB_INSTALL_DIR ${PROJECT_BINARY_DIR})
 configure_package_config_file(config/cmake/MFEMConfig.cmake.in
  ${CMAKE_CURRENT_BINARY_DIR}/MFEMConfig.cmake
@@ -780,7 +733,7 @@ configure_package_config_file(config/cmake/MFEMConfig.cmake.in
  PATH_VARS INCLUDE_INSTALL_DIRS LIB_INSTALL_DIR)

 # This is the version that will be installed
-set(INCLUDE_INSTALL_DIRS ${INSTALL_INCLUDE_DIR}  ${TPL_INCLUDE_DIRS})
+set(INCLUDE_INSTALL_DIRS ${INSTALL_INCLUDE_DIR}  ${MFEM_TPL_INCLUDE_DIRS})
 set(LIB_INSTALL_DIR ${INSTALL_LIB_DIR})
 configure_package_config_file(config/cmake/MFEMConfig.cmake.in
  ${CMAKE_CURRENT_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/MFEMConfig.cmake
@@ -102,9 +102,7 @@ The MFEM source code has the following structure:
  .
  ├── config
  │   ├── cmake
-  │   ├── docker
-  │   ├── githooks
-  │   └── vcpkg
+  │   └── githooks
  ├── data
  ├── doc
  ├── examples
@@ -113,7 +111,6 @@ The MFEM source code has the following structure:
  │   ├── ginkgo
  │   ├── hiop
  │   ├── jupyter
-  │   ├── moonolith
  │   ├── petsc
  │   ├── pumi
  │   ├── sundials
@@ -121,25 +118,20 @@ The MFEM source code has the following structure:
  ├── fem
  │   ├── ceed
  │   ├── fe
-  │   ├── lor
-  │   ├── moonolith
  │   ├── qinterp
  │   └── tmop
  ├── general
  ├── linalg
  │   └── simd
  ├── mesh
-  │   └── submesh
  ├── miniapps
  │   ├── adjoint
  │   ├── autodiff
  │   ├── common
  │   ├── electromagnetics
  │   ├── gslib
-  │   ├── hooke
  │   ├── meshing
  │   ├── mtop
-  │   ├── multidomain
  │   ├── navier
  │   ├── nurbs
  │   ├── parelag
@@ -7,10 +7,6 @@

                               https://mfem.org

-This file provides a detailed description of how to build and install the MFEM
-library. For a simple build, see the step-by-step instructions on the website
-at https://mfem.org/building.
-
 The MFEM library has a serial and an MPI-based parallel version, which largely
 share the same code base. The only prerequisite for building the serial version
 of MFEM is a (modern) C++ compiler, such as g++. The parallel version of MFEM
@@ -20,11 +16,7 @@ requires an MPI C++ compiler, as well as the following external libraries:
  https://github.com/hypre-space/hypre

 - METIS (a family of multilevel partitioning algorithms)
-  https://github.com/mfem/tpls
-
-  Note: We recommend our mirror of metis-4.0.3/5.1.0 above because the METIS
-  webpage, http://glaros.dtc.umn.edu/gkhome/metis/metis/overview, is often down
-  and we don't support yet the new repo https://github.com/KarypisLab/METIS.
+  http://glaros.dtc.umn.edu/gkhome/metis/metis/overview

 The hypre dependency can be downloaded as a tarball from GitHub or from the
 project webpage https://www.llnl.gov/casc/hypre. For example, the 2.24.0 release
@@ -337,6 +329,10 @@ MFEM_USE_SUNDIALS = YES/NO
   library. When enabled, this option uses the SUNDIALS_* library options,
   see below.

+MFEM_USE_MESQUITE = YES/NO
+   Enable MFEM functionality based on the Mesquite library. When enabled, this
+   option uses the MESQUITE_* library options, see below.
+
 MFEM_USE_SUITESPARSE = YES/NO
   Enable MFEM functionality based on the SuiteSparse library. Currently, this
   option adds the classes UMFPackSolver and KLUSolver (both sparse serial
@@ -475,14 +471,6 @@ MFEM_USE_CODIPACK = YES/NO
  Enable automatic differentiation using the CoDiPack library.
  www.scicomp.uni-kl.de/codi/

-MFEM_USE_ALGOIM = YES/NO
-  Enable the usage of Algoim - a collection of high-order accurate numerical
-  methods and C++ algorithms for working with implicitly-defined geometry and
-  level set methods. The Algoim library requires the Blitz++ library. The MFEM
-  provides interface to Algoim v1. Thus, to check out the specific state use:
-  git checkout 9c9ca0ef094d8ab0390ed36367a1151b459bbe0a
-  https://algoim.github.io
-
 MFEM_USE_ADFORWARD = YES/NO
  Enable forward mode for AD packages. This option is valid
  only if the AD package supports two modes (backward/forward).
@@ -532,16 +520,6 @@ MFEM_USE_MKL_CPARDISO = YES/NO
   MFEM_USE_LAPACK=YES, verify that the MKL LAPACK libraries are used. The
   OpenMP capabilities are disabled at link time.

-MFEM_USE_MOONOLITH = YES/NO
-   Enables the ParMoonolith interface for parallel non-conforming, non-matching,
-   variational, volumetric mesh information transfer. It requires the variable
-   MOONOLITH_DIR=<path to installation> to be defined in the environment in
-   order to be used with the Makefile. Makefile users are also required to
-   install moonolith using the command `make install_all`, see
-   https://bitbucket.org/zulianp/par_moonolith for details.
-   Although Moonolith is an MPI-based library, both serial (MFEM_USE_MPI=NO) and
-   parallel (MFEM_USE_MPI=YES) versions of MFEM are supported.
-
 MFEM_USE_CALIPER = YES/NO
   Enables the interface to Caliper. Caliper is a library to integrate
   performance profiling capabilities into applications. To use Caliper,
@@ -554,7 +532,7 @@ MFEM_USE_FMS = YES/NO
   Enables support for the FMS library which consists of the DataCollection
   sub-class mfem::FMSDataCollection for I/O in FMS formats, see the header file
   fem/fmsdatacollection.hpp. In addition, this option enables in-memory
-   conversion routines between FMS's FmsDataCollection structure and MFEM's
+   convetion routines between FMS's FmsDataCollection structure and MFEM's
   DataCollection class, see the header file fem/fmsconvert.hpp.

 MFEM_USE_PARELAG = YES/NO
@@ -562,14 +540,6 @@ MFEM_USE_PARELAG = YES/NO
   use ParELAG. In fact, ParELAG is dependent on MFEM. Therefore, this option
   currently only concerns the miniapps.

-MFEM_USE_ENZYME = YES/NO
-   Enables automatic differentiation support through the LLVM plugin Enzyme.
-   This requires the compiler to be set to clang (>=14.0.0). We also advise to
-   use the link time optimization (LTO) plugin, to enable functions that you
-   define over multiple files (compilation units) and want to be differentiated
-   automatically, to work. This requires to also use LLVM/LLD for linking.
-   Recommended options are in config/defaults.mk.
-
 MFEM_BUILD_TAG = (any value)
   An optional tag to characterize the build. Exported to config/config.mk.
   Can be used to identify the MFEM build from other makefiles.
@@ -601,7 +571,7 @@ The specific libraries and their options are:

 - METIS, used when MFEM_USE_METIS = YES. If using METIS 5, set
  MFEM_USE_METIS_5 = YES (default is to use METIS 4).
-  URL: https://github.com/mfem/tpls (MFEM mirror, see above)
+  URL: http://glaros.dtc.umn.edu/gkhome/metis/metis/overview
  Options: METIS_OPT, METIS_LIB.
  Versions: METIS 4.0.3 or 5.1.0.

@@ -632,6 +602,11 @@ The specific libraries and their options are:
  Options: SUNDIALS_OPT, SUNDIALS_LIB.
  Versions: SUNDIALS >= 5.0.0, SUNDIALS >= 5.4.0 for CUDA support.

+- Mesquite (optional), used when MFEM_USE_MESQUITE = YES.
+  URL: http://trilinos.org/oldsite/packages/mesquite
+  Options: MESQUITE_OPT, MESQUITE_LIB.
+  The Mesquite support is deprecated and will be removed in the future.
+
 - SuiteSparse (optional), used when MFEM_USE_SUITESPARSE = YES.
  URL: http://faculty.cse.tamu.edu/davis/suitesparse.html
  Options: SUITESPARSE_OPT, SUITESPARSE_LIB.
@@ -753,20 +728,6 @@ The specific libraries and their options are:
  Options: GSLIB_OPT, GSLIB_LIB.
  Versions: GSLIB >= 1.0.7.

- ALGOIM (optional), used when MFEM_USE_ALGOIM=YES. The library provides only
-  headers so it just needs to be downloaded at the same level as MFEM. Download
-  the specific version we use as:
-  "git clone https://github.com/algoim/algoim.git;
-   git checkout 9c9ca0ef094d8ab0390ed36367a1151b459bbe0a"
-  ALGOIM depends on BLITZ and the library must be built prior to the MFEM build.
-  Download v1.0.2, untar it at the same level as MFEM and create a symbolic link:
-  "ln -s blitz-1.0.2 blitz".
-  Build Blitz using CMake as:
-  "cmake . -DCMAKE_INSTALL_PREFIX=.; make lib; make install"
-  URL: https://github.com/blitzpp/blitz/archive/refs/tags/1.0.2.tar.gz
-  Options: BLITZ_OPT, BLITZ_LIB
-  Versions: BLITZ = 1.0.2
-
 - MKL CPardiso (optional), used when MFEM_USE_MKL_CPARDISO = YES.
  URL: https://software.intel.com/content/www/us/en/develop/tools/math-kernel-library.html
  Options: MKL_CPARDISO_OPT, MKL_CPARDISO_LIB.
@@ -798,11 +759,6 @@ The specific libraries and their options are:
  Options: RAJA_DIR, RAJA_OPT, RAJA_LIB.
  Versions: RAJA >= 0.14.0.

- Moonolith (optional), use when MFEM_USE_MOONOLITH = YES.
-  URL: https://bitbucket.org/zulianp/par_moonolith
-  Options: MOONOLITH_DIR
-  Versions: MOONOLITH >= 1.1.0.
-
 - Caliper (optional), used when MFEM_USE_CALIPER = YES.
  URL: https://github.com/LLNL/Caliper
  Options: CALIPER_DIR
@@ -843,12 +799,6 @@ The specific libraries and their options are:
  URL: https://github.com/LLNL/parelag
  Options: PARELAG_DIR, PARELAG_OPT, PARELAG_LIB.

- Enzyme, used when MFEM_USE_ENZYME = YES. Requires LLVM/Clang >= 14.0.0.
-  URL: https://github.com/EnzymeAD/Enzyme
-  Options: ENZYME_DIR, ENZYME_OPT, ENZYME_LIB.
-  Versions: Enzyme >= v0.0.33.
-
-
 Building with CMake
 ===================
 The MFEM build system consists of two steps: configuration and compilation.
@@ -960,6 +910,7 @@ MFEM_USE_LEGACY_OPENMP
 MFEM_USE_OPENMP
 MFEM_USE_MEMALLOC
 MFEM_TIMER_TYPE - Set automatically, can be overwritten.
+MFEM_USE_MESQUITE
 MFEM_USE_SUITESPARSE
 MFEM_USE_SUPERLU
 MFEM_USE_MUMPS
@@ -981,12 +932,10 @@ MFEM_USE_CEED
 MFEM_USE_RAJA
 MFEM_USE_UMPIRE
 MFEM_USE_SIDRE
-MFEM_USE_MOONOLITH
 MFEM_USE_CALIPER
 MFEM_USE_FMS
 MFEM_USE_BENCHMARK
 MFEM_USE_PARELAG
-MFEM_USE_ENZYME

 The following options are CMake specific:

@@ -1024,6 +973,7 @@ The CMake build system adds auto-detection for the following packages/libraries:
 - HYPRE
 - METIS - The option MFEM_USE_METIS_5 is auto-detected.
 - ParMETIS
+ - MESQUITE
 - SuiteSparse
 - SuperLUDist, STRUMPACK
 - Ginkgo
@@ -1040,12 +990,10 @@ The CMake build system adds auto-detection for the following packages/libraries:
 - RAJA
 - UMPIRE
 - AXOM - Used when MFEM_USE_SIDRE is enabled
- - MOONOLITH
 - CALIPER
 - FMS
 - BENCHMARK
 - ParELAG
- - Enzyme

 The following built-in CMake packages are also used:

@@ -7,24 +7,21 @@

                               https://mfem.org

-[MFEM](https://mfem.org) is a modular parallel C++ library for finite element
-methods. Its goal is to enable high-performance scalable finite element
-discretization research and application development on a wide variety of
-platforms, ranging from laptops to supercomputers.
+MFEM is a modular parallel C++ library for finite element methods. Its goal is
+to enable high-performance scalable finite element discretization research and
+application development on a wide variety of platforms, ranging from laptops to
+supercomputers.

 We welcome contributions and feedback from the community. Please see the file
-[CONTRIBUTING.md](CONTRIBUTING.md) for additional details about our development
-process.
+CONTRIBUTING.md for additional details about our development process.

-* For building instructions, see the file [INSTALL](INSTALL), or type "make help".
+* For building instructions, see the file INSTALL, or type "make help".

-* Copyright and licensing information can be found in files [LICENSE](LICENSE) and [NOTICE](NOTICE).
+* Copyright and licensing information can be found in files LICENSE and NOTICE.

 * The best starting point for new users interested in MFEM's features is to
  review the examples and miniapps at https://mfem.org/examples.

-* Instructions for learning with Docker are in [config/docker](config/docker).
-
 Conceptually, MFEM can be viewed as a finite element toolbox that provides the
 building blocks for developing finite element algorithms in a manner similar to
 that of MATLAB for linear algebra methods. In particular, MFEM provides support
@@ -61,16 +58,12 @@ solvers from the hypre library. Comprehensive support for other external
 packages, e.g. PETSc, SUNDIALS and libCEED is also included, giving access to
 additional linear and nonlinear solvers, preconditioners, time integrators, etc.

-For examples of using MFEM, see the [examples/](examples) and [miniapps/](miniapps)
-directories, as well as the OpenGL visualization tool GLVis which is available
-at https://glvis.org.
-
-## License
+For examples of using MFEM, see the examples/ and miniapps/ directories, as well
+as the OpenGL visualization tool GLVis which is available at https://glvis.org.

 MFEM is distributed under the terms of the BSD-3 license. All new contributions
-must be made under this license. See [LICENSE](LICENSE) and [NOTICE](NOTICE) for
-details.
+must be made under this license. See LICENSE and NOTICE for details.

-SPDX-License-Identifier: BSD-3-Clause <br>
-LLNL Release Number: LLNL-CODE-806117 <br>
+SPDX-License-Identifier: BSD-3-Clause
+LLNL Release Number: LLNL-CODE-806117
 DOI: 10.11578/dc.20171025.1248
@@ -212,6 +212,10 @@ IF (DEFINED TPL_ENABLE_SUNDIALS)
  SET(MFEM_USE_SUNDIALS ${TPL_ENABLE_SUNDIALS} CACHE BOOL "Enable SUNDIALS usage" FORCE)
 ENDIF()

+IF (DEFINED TPL_ENABLE_MESQUITE)
+  SET(MFEM_USE_MESQUITE ${TPL_ENABLE_MESQUITE} CACHE BOOL "Enable MESQUITE usage" FORCE)
+ENDIF()
+
 IF (DEFINED TPL_ENABLE_SUITESPARSE)
  SET(MFEM_USE_SUITESPARSE ${TPL_ENABLE_SUITESPARSE} CACHE BOOL "Enable SuiteSparse usage" FORCE)
 ENDIF()
@@ -29,6 +29,7 @@ set(MFEM_USE_LEGACY_OPENMP @MFEM_USE_LEGACY_OPENMP@)
 set(MFEM_USE_MEMALLOC @MFEM_USE_MEMALLOC@)
 set(MFEM_TIMER_TYPE @MFEM_TIMER_TYPE@)
 set(MFEM_USE_SUNDIALS @MFEM_USE_SUNDIALS@)
+set(MFEM_USE_MESQUITE @MFEM_USE_MESQUITE@)
 set(MFEM_USE_SUITESPARSE @MFEM_USE_SUITESPARSE@)
 set(MFEM_USE_SUPERLU @MFEM_USE_SUPERLU@)
 set(MFEM_USE_MUMPS @MFEM_USE_MUMPS@)
@@ -53,14 +54,11 @@ set(MFEM_USE_CEED @MFEM_USE_CEED@)
 set(MFEM_USE_UMPIRE @MFEM_USE_UMPIRE@)
 set(MFEM_USE_SIMD @MFEM_USE_SIMD@)
 set(MFEM_USE_ADIOS2 @MFEM_USE_ADIOS2@)
-set(MFEM_USE_MOONOLITH @MFEM_USE_MOONOLITH@)
 set(MFEM_USE_CODIPACK @MFEM_USE_CODIPACK@)
 set(MFEM_USE_ADFORWARD @MFEM_USE_ADFORWARD@)
 set(MFEM_USE_CALIPER @MFEM_USE_CALIPER@)
-set(MFEM_USE_ALGOIM @MFEM_USE_ALGOIM@)
 set(MFEM_USE_BENCHMARK @MFEM_USE_BENCHMARK@)
 set(MFEM_USE_PARELAG @MFEM_USE_PARELAG@)
-set(MFEM_USE_ENZYME @MFEM_USE_ENZYME@)

 set(MFEM_CXX_COMPILER "@CMAKE_CXX_COMPILER@")
 set(MFEM_CXX_FLAGS "@CMAKE_CXX_FLAGS@")
@@ -77,6 +77,9 @@
 // Internal MFEM option: enable group/batch allocation for some small objects.
 #cmakedefine MFEM_USE_MEMALLOC

+// Enable MFEM functionality based on the Mesquite library.
+#cmakedefine MFEM_USE_MESQUITE
+
 // Enable MFEM functionality based on the SuiteSparse library.
 #cmakedefine MFEM_USE_SUITESPARSE

@@ -125,9 +128,6 @@
 // Enable MFEM functionality based on the PUMI library
 #cmakedefine MFEM_USE_PUMI

-// Enable MFEM functionality based on the Moonolith library
-#cmakedefine MFEM_USE_MOONOLITH
-
 // Enable MFEM functionality based on the HiOp library
 #cmakedefine MFEM_USE_HIOP

@@ -157,9 +157,6 @@
 // Enable MFEM functionality based on the Caliper library
 #cmakedefine MFEM_USE_CALIPER

-// Enable MFEM functionality based on the Algoim library
-#cmakedefine MFEM_USE_ALGOIM
-
 // Which library functions to use in class StopWatch for measuring time.
 // For a list of the available options, see INSTALL.
 // If not defined, an option is selected automatically.
@@ -187,7 +184,4 @@
 // Enable MFEM functionality based on the Google Benchmark library.
 #cmakedefine MFEM_USE_BENCHMARK

-// Enable Enzyme for AD
-#cmakedefine MFEM_USE_ENZYME
-
 #endif // MFEM_CONFIG_HEADER
@@ -1,22 +0,0 @@
-# Copyright (c) 2010-2022, 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.
-
-# Defines the following variables:
-#   - ALGOIM_FOUND
-#   - ALGOIM_LIBRARIES
-#   - ALGOIM_INCLUDE_DIRS
-
-include(MfemCmakeUtilities)
-mfem_find_package(Algoim ALGOIM ALGOIM_DIR
-       	"include" "algoim_quad.hpp"
-       	"" ""
-	"Paths to headers required by Algoim."
-	"Libraries required by Algoim.")
@@ -16,22 +16,7 @@

 include(MfemCmakeUtilities)
 mfem_find_package(Caliper CALIPER CALIPER_DIR
-      "include" "caliper/cali.h"
-      "lib" "caliper"
-      "Paths to headers required by Caliper."
-      "Libraries required by Caliper.")
-
-# Append adiak path/lib if the user provided ADIAK_DIR
-if(ADIAK_DIR AND EXISTS ${ADIAK_DIR})
-    find_package(adiak NO_DEFAULT_PATH REQUIRED PATHS ${ADIAK_DIR}/lib/cmake/adiak ${ADIAK_DIR})
-    list(APPEND CALIPER_INCLUDE_DIRS ${adiak_INCLUDE_DIRS})
-    list(APPEND CALIPER_LIBRARIES ${adiak_LIBRARIES})
-endif()
-
-# Append gotcha path/lib if the user provided GOTCHA_DIR
-if(GOTCHA_DIR AND EXISTS ${GOTCHA_DIR})
-    find_package(gotcha NO_DEFAULT_PATH REQUIRED PATHS ${GOTCHA_DIR}/lib/cmake/gotcha ${GOTCHA_DIR})
-    list(APPEND CALIPER_INCLUDE_DIRS ${gotcha_INCLUDE_DIRS})
-    list(APPEND CALIPER_LIBRARIES ${gotcha_LIBRARIES})
-endif()
-
+       	"include" "caliper/cali.h"
+       	"lib" "caliper"
+  	"Paths to headers required by Caliper."
+       	"Libraries required by Caliper.")
@@ -1,27 +0,0 @@
-# Copyright (c) 2010-2022, 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.
-
-message(STATUS "Looking for ENZYME ...")
-message(STATUS "   in ENZYME_DIR = ${ENZYME_DIR}")
-
-# Make sure the directory and version combination works. Do nothing otherwise.
-if(EXISTS "${ENZYME_DIR}/ClangEnzyme-${ENZYME_VERSION}.so")
-  message(STATUS "Found ENZYME: ${ENZYME_DIR}/ClangEnzyme-${ENZYME_VERSION}.so")
-
-  # Set ENZYME_FOUND
-  set(ENZYME_FOUND TRUE CACHE BOOL "ENZYME was found." FORCE)
-
-  # Set CXX flags to accommodate the Enzyme Clang plugin
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xclang -load -Xclang ${ENZYME_DIR}/ClangEnzyme-${ENZYME_VERSION}.so -mllvm -enzyme-loose-types=1")
-  set(MFEM_USE_ENZYME YES)
-else()
-
-endif()
@@ -15,5 +15,5 @@
 #   - GSLIB_INCLUDE_DIRS

 include(MfemCmakeUtilities)
-mfem_find_package(GSLIB GSLIB GSLIB_DIR "include" gslib.h "lib" gs
+mfem_find_package(gslib GSLIB GSLIB_DIR "include" gslib.h "lib" gs
  "Paths to headers required by GSLIB." "Libraries required by GSLIB.")
@@ -1,70 +0,0 @@
-# Copyright (c) 2010-2022, 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.
-
-# Defines the following variables:
-#   - HDF5_FOUND - If HDF5 was found
-#   - HDF5_LIBRARIES - The HDF5 libraries
-#   - HDF5_INCLUDE_DIRS - The HDF5 include directories
-
-# NOTE: Using this FindHDF5.cmake instead of the CMake provided version may lead
-#       to issues with some TPL libraries that depend (or may depend) on HDF5.
-#       For this reason, we should consider removing this file, or at least
-#       making it use the CMake provided version by default and apply the logic
-#       below only when specifically requested by a user.  -V. Dobrev
-
-# First Check for HDF5_DIR
-if(NOT HDF5_DIR)
-  message(FATAL_ERROR
-    "Could not find HDF5. HDF5 support needs explicit HDF5_DIR")
-endif()
-
-if (NOT HDF5_FIND_QUIETLY)
-  message(STATUS "Looking for HDF5 ...")
-  message(STATUS "   in HDF5_DIR = ${HDF5_DIR}")
-endif()
-
-# Find includes
-find_path( HDF5_INCLUDE_DIRS hdf5.h
-           PATHS  ${HDF5_DIR}/include/
-           NO_DEFAULT_PATH
-           NO_CMAKE_ENVIRONMENT_PATH
-           NO_CMAKE_PATH
-           NO_SYSTEM_ENVIRONMENT_PATH
-           NO_CMAKE_SYSTEM_PATH)
-
-find_library( __HDF5_LIBRARY NAMES hdf5 libhdf5 libhdf5_D libhdf5_debug
-              PATHS ${HDF5_DIR}/lib
-              NO_DEFAULT_PATH
-              NO_CMAKE_ENVIRONMENT_PATH
-              NO_CMAKE_PATH
-              NO_SYSTEM_ENVIRONMENT_PATH
-              NO_CMAKE_SYSTEM_PATH)
-
-find_library( __HDF5_HL_LIBRARY NAMES hdf5_hl libhdf5_hl libhdf5_hl_D libhdf5_hl_debug
-              PATHS ${HDF5_DIR}/lib
-              NO_DEFAULT_PATH
-              NO_CMAKE_ENVIRONMENT_PATH
-              NO_CMAKE_PATH
-              NO_SYSTEM_ENVIRONMENT_PATH
-              NO_CMAKE_SYSTEM_PATH)
-
-set(HDF5_LIBRARIES ${__HDF5_HL_LIBRARY} ${__HDF5_LIBRARY})
-
-include(FindPackageHandleStandardArgs)
-
-# Handle the QUIETLY and REQUIRED arguments and set HDF5_FOUND to TRUE if all
-# listed variables are TRUE
-find_package_handle_standard_args(HDF5
-                                  " *** HDF5 not found. Please set HDF5_DIR."
-                                  HDF5_LIBRARIES
-                                  HDF5_INCLUDE_DIRS
-                                  __HDF5_LIBRARY
-                                  __HDF5_HL_LIBRARY)
@@ -10,13 +10,11 @@
 # CONTRIBUTING.md for details.

 # Defines the following variables:
-#   - BLITZ_FOUND
-#   - BLITZ_LIBRARIES
-#   - BLITZ_INCLUDE_DIRS
+#   - MESQUITE_FOUND
+#   - MESQUITE_LIBRARIES
+#   - MESQUITE_INCLUDE_DIRS

 include(MfemCmakeUtilities)
-mfem_find_package(Blitz BLITZ BLITZ_DIR
-       	"include" "blitz/blitz.h"
-       	"lib" "blitz"
-  	"Paths to headers required by Blitz."
-       	"Libraries required by Blitz.")
+mfem_find_package(Mesquite MESQUITE MESQUITE_DIR
+  "include" "Mesquite_all_headers.hpp" "lib" "mesquite"
+  "Paths to headers required by Mesquite." "Libraries required by Mesquite.")
@@ -17,24 +17,18 @@
 include(MfemCmakeUtilities)

 # FindHDF5.cmake uses HDF5_ROOT, so we "translate" from the MFEM convention
-# (MFEM's FindHDF5.cmake does not need HDF5_ROOT)
-# set(HDF5_ROOT ${HDF5_DIR} CACHE PATH "")
-
+set(HDF5_ROOT ${HDF5_DIR} CACHE PATH "")
 # We need to guard against the case where HDF5 was already found but without
 # the HL extensions (in which case mfem_find_package will treat the package
 # as already having been found), so we reset the variable to force FindHDF5.cmake
 # to be called for a second time
 set(HDF5_FOUND OFF)
 enable_language(C) # FindHDF5.cmake uses the C compiler
-
 mfem_find_package(NetCDF NETCDF NETCDF_DIR "include" netcdf.h "lib" netcdf
  "Paths to headers required by NetCDF." "Libraries required by NetCDF.")
-
 # The HL extension libraries are in a separate variable and must precede
 # the "regular" hdf5 library, as hdf5_hl depends on hdf5
 # The netcdf library will always be the first element of NETCDF_LIBRARIES
 # and we need to insert after that library but before the hdf5 library, so
 # position 1 is used
-# (MFEM's FindHDF5.cmake does not set HDF5_C_LIBRARY_hdf5_hl and the HL library
-# is already added to NETCDF_LIBRARIES)
-# list(INSERT NETCDF_LIBRARIES 1 ${HDF5_C_LIBRARY_hdf5_hl})
+list(INSERT NETCDF_LIBRARIES 1 ${HDF5_C_LIBRARY_hdf5_hl})
@@ -14,6 +14,6 @@
 #   - UMPIRE_LIBRARIES
 #   - UMPIRE_INCLUDE_DIRS

-find_package(umpire REQUIRED CONFIG)
-set(UMPIRE_FOUND ${umpire_FOUND})
-set(UMPIRE_LIBRARIES "umpire")
+include(MfemCmakeUtilities)
+mfem_find_package(UMPIRE UMPIRE UMPIRE_DIR "include" "umpire/Umpire.hpp" "lib" "umpire"
+  "Paths to headers required by UMPIRE." "Libraries required by UMPIRE.")
@@ -43,18 +43,22 @@ function(convert_filenames_to_full_paths NAMES)
  set(${NAMES} ${tmp_names} PARENT_SCOPE)
 endfunction()

-# Wrapper for add_executable
+# Wrapper for add_executable that calls the HIP wrapper if applicable
 macro(mfem_add_executable NAME)
-  add_executable(${NAME} ${ARGN})
-  if (MFEM_USE_CUDA)
-    set_target_properties(${NAME} PROPERTIES
-      CUDA_RESOLVE_DEVICE_SYMBOLS ON)
+  if (MFEM_USE_HIP)
+    add_executable(${NAME} ${ARGN})
+  else()
+    add_executable(${NAME} ${ARGN})
  endif()
 endmacro()

-# Wrapper for add_library
+# Wrapper for add_library that calls the HIP wrapper if applicable
 macro(mfem_add_library NAME)
-  add_library(${NAME} ${ARGN})
+  if (MFEM_USE_HIP)
+    add_library(${NAME} ${ARGN})
+  else()
+    add_library(${NAME} ${ARGN})
+  endif()
 endmacro()

 # Simple shortcut to add_custom_target() with option to add the target to the
@@ -162,12 +166,27 @@ macro(add_mfem_miniapp MFEM_EXE_NAME)

  # Append the additional libraries and options
  if (LIBRARIES_LIST)
-    target_link_libraries(${MFEM_EXE_NAME} PRIVATE ${LIBRARIES_LIST})
+    if(CMAKE_VERSION VERSION_GREATER 2.8.11)
+      target_link_libraries(${MFEM_EXE_NAME} PRIVATE ${LIBRARIES_LIST})
+    else()
+      target_link_libraries(${MFEM_EXE_NAME} ${LIBRARIES_LIST})
+    endif()
  endif()
  if (EXTRA_OPTIONS_LIST)
    string(REPLACE ";" " " EXTRA_OPTIONS_STRING "${EXTRA_OPTIONS_LIST}")
    message(STATUS "${MFEM_EXE_NAME}: add flags \"${EXTRA_OPTIONS_STRING}\"")
-    target_compile_options(${MFEM_EXE_NAME} PRIVATE ${EXTRA_OPTIONS_LIST})
+    if(CMAKE_VERSION VERSION_GREATER 2.8.11)
+      target_compile_options(${MFEM_EXE_NAME} PRIVATE ${EXTRA_OPTIONS_LIST})
+    else()
+      get_target_property(THIS_COMPILE_FLAGS ${MFEM_EXE_NAME} COMPILE_FLAGS)
+      if (THIS_COMPILE_FLAGS)
+        set(THIS_COMPILE_FLAGS "${THIS_COMPILE_FLAGS} ${EXTRA_OPTIONS_STRING}")
+      else()
+        set(THIS_COMPILE_FLAGS "${EXTRA_OPTIONS_STRING}")
+      endif()
+      set_target_properties(${MFEM_EXE_NAME}
+        PROPERTIES COMPILE_FLAGS ${THIS_COMPILE_FLAGS})
+    endif()
  endif()
  if (EXTRA_DEFINES_LIST)
    target_compile_definitions(${MFEM_EXE_NAME} PRIVATE ${EXTRA_DEFINES_LIST})
@@ -176,15 +195,17 @@ macro(add_mfem_miniapp MFEM_EXE_NAME)
  # Handle the MPI separately
  if (MFEM_USE_MPI)
    # Add MPI_CXX_LIBRARIES, in case this target does not link with mfem.
-    target_link_libraries(${MFEM_EXE_NAME} PRIVATE ${MPI_CXX_LIBRARIES})
+    if(CMAKE_VERSION VERSION_GREATER 2.8.11)
+      target_link_libraries(${MFEM_EXE_NAME} PRIVATE ${MPI_CXX_LIBRARIES})
+    else()
+      target_link_libraries(${MFEM_EXE_NAME} ${MPI_CXX_LIBRARIES})
+    endif()

    if (MPI_CXX_INCLUDE_PATH)
      target_include_directories(${MFEM_EXE_NAME} PRIVATE ${MPI_CXX_INCLUDE_PATH})
    endif()
    if (MPI_CXX_COMPILE_FLAGS)
-      separate_arguments(MPI_CXX_COMPILE_ARGS UNIX_COMMAND
-        "${MPI_CXX_COMPILE_FLAGS}")
-      target_compile_options(${MFEM_EXE_NAME} PRIVATE ${MPI_CXX_COMPILE_ARGS})
+      target_compile_options(${MFEM_EXE_NAME} PRIVATE ${MPI_CXX_COMPILE_FLAGS})
    endif()

    if (MPI_CXX_LINK_FLAGS)
@@ -865,15 +886,14 @@ function(mfem_export_mk_files)
  set(CONFIG_MK_BOOL_VARS MFEM_USE_MPI MFEM_USE_METIS MFEM_USE_METIS_5
      MFEM_DEBUG MFEM_USE_EXCEPTIONS MFEM_USE_ZLIB MFEM_USE_LIBUNWIND
      MFEM_USE_LAPACK MFEM_THREAD_SAFE MFEM_USE_LEGACY_OPENMP MFEM_USE_OPENMP
-      MFEM_USE_MEMALLOC MFEM_USE_SUNDIALS MFEM_USE_SUITESPARSE
+      MFEM_USE_MEMALLOC MFEM_USE_SUNDIALS MFEM_USE_MESQUITE MFEM_USE_SUITESPARSE
      MFEM_USE_SUPERLU MFEM_USE_SUPERLU5 MFEM_USE_MUMPS MFEM_USE_STRUMPACK
      MFEM_USE_GINKGO MFEM_USE_AMGX MFEM_USE_GNUTLS MFEM_USE_NETCDF
      MFEM_USE_PETSC MFEM_USE_SLEPC MFEM_USE_MPFR MFEM_USE_SIDRE MFEM_USE_FMS
      MFEM_USE_CONDUIT MFEM_USE_PUMI MFEM_USE_HIOP MFEM_USE_GSLIB MFEM_USE_CUDA
      MFEM_USE_HIP MFEM_USE_RAJA MFEM_USE_OCCA MFEM_USE_CEED MFEM_USE_CALIPER
      MFEM_USE_UMPIRE MFEM_USE_SIMD MFEM_USE_ADIOS2 MFEM_USE_MKL_CPARDISO
-      MFEM_USE_ADFORWARD MFEM_USE_CODIPACK MFEM_USE_BENCHMARK MFEM_USE_PARELAG
-      MFEM_USE_MOONOLITH MFEM_USE_ALGOIM MFEM_USE_ENZYME)
+      MFEM_USE_ADFORWARD MFEM_USE_CODIPACK MFEM_USE_BENCHMARK MFEM_USE_PARELAG)
  foreach(var ${CONFIG_MK_BOOL_VARS})
    if (${var})
      set(${var} YES)
@@ -957,11 +977,9 @@ function(mfem_export_mk_files)
      string(REGEX REPLACE "^SCOREC::" "" libname ${pumilib})
      string(FIND "${pumilib}" ".a" staticlib)
      string(FIND "${pumilib}" ".so" sharedlib)
-      string(FIND "${pumilib}" ".dylib" dynamiclib)
      find_library(lib ${libname} PATHS ${PUMI_DIR}/lib NO_DEFAULT_PATH)
      if (NOT "${sharedlib}" MATCHES "-1" OR
-          NOT "${staticlib}" MATCHES "-1" OR
-          NOT "${dynamiclib}" MATCHES "-1"  )
+          NOT "${staticlib}" MATCHES "-1"   )
        set(MFEM_EXT_LIBS "${pumilib} ${MFEM_EXT_LIBS}")
      elseif (NOT "${lib}" MATCHES "lib-NOTFOUND")
        set(MFEM_EXT_LIBS "${lib} ${MFEM_EXT_LIBS}")
@@ -976,7 +994,7 @@ function(mfem_export_mk_files)
  foreach(lib ${TPL_LIBRARIES})
    get_filename_component(suffix ${lib} EXT)
    # handle interfaces (e.g., SCOREC::apf)
-    if ("${lib}" MATCHES "SCOREC::.*" OR "${lib}" MATCHES "Ginkgo::.*" OR "${lib}" MATCHES "ParMoonolith::.*")
+    if ("${lib}" MATCHES "SCOREC::.*" OR "${lib}" MATCHES "Ginkgo::.*")
    elseif (TARGET "${lib}")
      mfem_get_target_options(${lib} CompileOpts LinkOpts)
      # Removing duplicates may lead to issues:
@@ -31,11 +31,9 @@

 // Windows specific options
 #ifdef _WIN32
-#ifndef _USE_MATH_DEFINES
 // Macro needed to get defines like M_PI from <cmath>. (Visual Studio C++ only?)
 #define _USE_MATH_DEFINES
 #endif
-#endif
 // On Cygwin the option -std=c++11 prevents the definition of M_PI. Defining
 // the following macro allows us to get M_PI and some needed functions, e.g.
 // posix_memalign(), strdup(), strerror_r().
@@ -85,6 +85,9 @@
 // Enable MFEM functionality based on the SUNDIALS libraries.
 // #define MFEM_USE_SUNDIALS

+// Enable MFEM functionality based on the Mesquite library.
+// #define MFEM_USE_MESQUITE
+
 // Enable MFEM functionality based on the SuiteSparse library.
 // #define MFEM_USE_SUITESPARSE

@@ -135,9 +138,6 @@
 // Enable MFEM functionality based on the PUMI library
 // #define MFEM_USE_PUMI

-// Enable Moonolith-based general interpolation between finite element spaces.
-// #define MFEM_USE_MOONOLITH
-
 // Enable MFEM functionality based on the HIOP library.
 // #define MFEM_USE_HIOP

@@ -164,9 +164,6 @@
 // Enable functionality based on the Caliper library.
 // #define MFEM_USE_CALIPER

-// Enable functionality based on the Algoim library.
-// #define MFEM_USE_ALGOIM
-
 // Enable functionality based on the Umpire library.
 // #define MFEM_USE_UMPIRE

@@ -192,7 +189,4 @@
 // Enable functionality based on the Google Benchmark library.
 // #define MFEM_USE_BENCHMARK

-// Enable the Enzyme LLVM plugin
-// #define MFEM_USE_ENZYME
-
 #endif // MFEM_CONFIG_HEADER
@@ -29,6 +29,7 @@ MFEM_USE_OPENMP        = @MFEM_USE_OPENMP@
 MFEM_USE_MEMALLOC      = @MFEM_USE_MEMALLOC@
 MFEM_TIMER_TYPE        = @MFEM_TIMER_TYPE@
 MFEM_USE_SUNDIALS      = @MFEM_USE_SUNDIALS@
+MFEM_USE_MESQUITE      = @MFEM_USE_MESQUITE@
 MFEM_USE_SUITESPARSE   = @MFEM_USE_SUITESPARSE@
 MFEM_USE_SUPERLU       = @MFEM_USE_SUPERLU@
 MFEM_USE_SUPERLU5      = @MFEM_USE_SUPERLU5@
@@ -57,12 +58,10 @@ MFEM_USE_UMPIRE        = @MFEM_USE_UMPIRE@
 MFEM_USE_SIMD          = @MFEM_USE_SIMD@
 MFEM_USE_ADIOS2        = @MFEM_USE_ADIOS2@
 MFEM_USE_MKL_CPARDISO  = @MFEM_USE_MKL_CPARDISO@
-MFEM_USE_MOONOLITH     = @MFEM_USE_MOONOLITH@
 MFEM_USE_ADFORWARD     = @MFEM_USE_ADFORWARD@
 MFEM_USE_CODIPACK      = @MFEM_USE_CODIPACK@
 MFEM_USE_BENCHMARK     = @MFEM_USE_BENCHMARK@
 MFEM_USE_PARELAG       = @MFEM_USE_PARELAG@
-MFEM_USE_ENZYME        = @MFEM_USE_ENZYME@

 # Compiler, compile options, and link options
 MFEM_CXX       = @MFEM_CXX@
@@ -30,6 +30,7 @@ option(MFEM_USE_OPENMP "Enable the OpenMP backend" OFF)
 option(MFEM_USE_LEGACY_OPENMP "Enable legacy OpenMP usage" OFF)
 option(MFEM_USE_MEMALLOC "Enable the internal MEMALLOC option." ON)
 option(MFEM_USE_SUNDIALS "Enable SUNDIALS usage" OFF)
+option(MFEM_USE_MESQUITE "Enable MESQUITE usage" OFF)
 option(MFEM_USE_SUITESPARSE "Enable SuiteSparse usage" OFF)
 option(MFEM_USE_SUPERLU "Enable SuperLU_DIST usage" OFF)
 option(MFEM_USE_SUPERLU5 "Use the old SuperLU_DIST 5.1 version" OFF)
@@ -57,13 +58,11 @@ option(MFEM_USE_UMPIRE "Enable Umpire" OFF)
 option(MFEM_USE_SIMD "Enable use of SIMD intrinsics" OFF)
 option(MFEM_USE_ADIOS2 "Enable ADIOS2" OFF)
 option(MFEM_USE_CALIPER "Enable Caliper support" OFF)
-option(MFEM_USE_ALGOIM "Enable Algoim support" OFF)
 option(MFEM_USE_MKL_CPARDISO "Enable MKL CPardiso" OFF)
 option(MFEM_USE_ADFORWARD "Enable forward mode for AD" OFF)
 option(MFEM_USE_CODIPACK "Enable automatic differentiation (AD) using CoDiPack" OFF)
 option(MFEM_USE_BENCHMARK "Enable Google Benchmark" OFF)
 option(MFEM_USE_PARELAG "Enable ParELAG" OFF)
-option(MFEM_USE_ENZYME "Enable Enzyme" OFF)

 # Optional overrides for autodetected MPIEXEC and MPIEXEC_NUMPROC_FLAG
 # set(MFEM_MPIEXEC "mpirun" CACHE STRING "Command for running MPI tests")
@@ -123,6 +122,9 @@ set(SUNDIALS_DIR "${MFEM_DIR}/../sundials-5.0.0/instdir" CACHE PATH
 # set(SUNDIALS_REQUIRED_PACKAGES "SuiteSparse/KLU/AMD/BTF/COLAMD/config"
 #     CACHE STRING "Additional packages required by SUNDIALS.")

+set(MESQUITE_DIR "${MFEM_DIR}/../mesquite-2.99" CACHE PATH
+    "Path to the Mesquite library.")
+
 set(SuiteSparse_DIR "${MFEM_DIR}/../SuiteSparse" CACHE PATH
    "Path to the SuiteSparse library.")
 set(SuiteSparse_REQUIRED_PACKAGES "BLAS" "METIS"
@@ -184,7 +186,6 @@ set(GNUTLS_DIR "" CACHE PATH "Path to the GnuTLS library.")

 set(GSLIB_DIR "" CACHE PATH "Path to the GSLIB library.")

-set(HDF5_DIR "/usr" CACHE PATH "Path to the HDF5 library.")
 set(NETCDF_DIR "" CACHE PATH "Path to the NetCDF library.")
 set(NetCDF_REQUIRED_PACKAGES "HDF5/C/HL" CACHE STRING
    "Additional packages required by NetCDF.")
@@ -235,11 +236,6 @@ set(RAJA_DIR "${MFEM_DIR}/../raja" CACHE PATH "Path to RAJA")
 set(CEED_DIR "${MFEM_DIR}/../libCEED" CACHE PATH "Path to libCEED")
 set(UMPIRE_DIR "${MFEM_DIR}/../umpire" CACHE PATH "Path to Umpire")
 set(CALIPER_DIR "${MFEM_DIR}/../caliper" CACHE PATH "Path to Caliper")
-set(BLITZ_DIR "${MFEM_DIR}/../blitz" CACHE PATH "Path to Blitz")
-set(ALGOIM_DIR "${MFEM_DIR}/../algoim" CACHE PATH "Path to Algoim")
-set(ALGOIM_REQUIRED_PACKAGES "BLITZ" CACHE STRING
-    "Packages that ALGOIM depends on.")
-
 set(BENCHMARK_DIR "${MFEM_DIR}/../google-benchmark" CACHE PATH
    "Path to Google Benchmark")

@@ -42,9 +42,6 @@ STATIC = YES
 SHARED = NO

 # CUDA configuration options
-#
-# If you set MFEM_USE_ENZYME=YES, CUDA_CXX has to be configured to use cuda with
-# clang as its host compiler.
 CUDA_CXX = nvcc
 CUDA_ARCH = sm_60
 CUDA_FLAGS = -x=cu --expt-extended-lambda -arch=$(CUDA_ARCH)
@@ -131,6 +128,7 @@ MFEM_USE_LEGACY_OPENMP = NO
 MFEM_USE_MEMALLOC      = YES
 MFEM_TIMER_TYPE        = $(if $(NOTMAC),2,4)
 MFEM_USE_SUNDIALS      = NO
+MFEM_USE_MESQUITE      = NO
 MFEM_USE_SUITESPARSE   = NO
 MFEM_USE_SUPERLU       = NO
 MFEM_USE_SUPERLU5      = NO
@@ -155,17 +153,14 @@ MFEM_USE_RAJA          = NO
 MFEM_USE_OCCA          = NO
 MFEM_USE_CEED          = NO
 MFEM_USE_CALIPER       = NO
-MFEM_USE_ALGOIM        = NO
 MFEM_USE_UMPIRE        = NO
 MFEM_USE_SIMD          = NO
 MFEM_USE_ADIOS2        = NO
 MFEM_USE_MKL_CPARDISO  = NO
-MFEM_USE_MOONOLITH     = NO
 MFEM_USE_ADFORWARD     = NO
 MFEM_USE_CODIPACK      = NO
 MFEM_USE_BENCHMARK     = NO
 MFEM_USE_PARELAG       = NO
-MFEM_USE_ENZYME        = NO

 # MPI library compile and link flags
 # These settings are used only when building MFEM with MPI + HIP
@@ -178,7 +173,7 @@ ifeq ($(MFEM_USE_MPI)$(MFEM_USE_HIP),YESYES)
 endif

 # ROCM/HIP directory such that ROCM/HIP libraries like rocsparse and rocrand are
-# found in $(HIP_DIR)/lib, usually as links. Typically, this directory is of
+# found in $(HIP_DIR)/lib, usually as links. Typically, this directoory is of
 # the form /opt/rocm-X.Y.Z which is called ROCM_PATH by hipconfig.
 ifeq ($(MFEM_USE_HIP),YES)
   HIP_DIR := $(patsubst %/,%,$(dir $(shell which $(HIP_CXX))))
@@ -206,7 +201,7 @@ HYPRE_OPT = -I$(HYPRE_DIR)/include
 HYPRE_LIB = -L$(HYPRE_DIR)/lib -lHYPRE
 ifeq (YES,$(MFEM_USE_CUDA))
   # This is only necessary when hypre is built with cuda:
-   HYPRE_LIB += -lcusparse -lcurand -lcublas
+   HYPRE_LIB += -lcusparse -lcurand
 endif
 ifeq (YES,$(MFEM_USE_HIP))
   # This is only necessary when hypre is built with hip:
@@ -250,16 +245,12 @@ POSIX_CLOCKS_LIB = -lrt
 # SUNDIALS library configuration
 # For sundials_nvecmpiplusx and nvecparallel remember to build with MPI_ENABLE=ON
 # and modify cmake variables for hypre for sundials
-SUNDIALS_DIR = @MFEM_DIR@/../sundials-5.0.0/instdir
-# SUNDIALS >= 6.4.0 requires C++14:
-ifeq ($(MFEM_USE_SUNDIALS),YES)
-   BASE_FLAGS = -std=c++14
-endif
-SUNDIALS_OPT = -I$(SUNDIALS_DIR)/include
-SUNDIALS_LIB = $(XLINKER)-rpath,$(SUNDIALS_DIR)/lib64\
- $(XLINKER)-rpath,$(SUNDIALS_DIR)/lib\
- -L$(SUNDIALS_DIR)/lib64 -L$(SUNDIALS_DIR)/lib\
+SUNDIALS_DIR    = @MFEM_DIR@/../sundials-5.0.0/instdir
+SUNDIALS_OPT    = -I$(SUNDIALS_DIR)/include
+SUNDIALS_LIBDIR = $(wildcard $(SUNDIALS_DIR)/lib*)
+SUNDIALS_LIB    = $(XLINKER)-rpath,$(SUNDIALS_LIBDIR) -L$(SUNDIALS_LIBDIR)\
 -lsundials_arkode -lsundials_cvodes -lsundials_nvecserial -lsundials_kinsol
+
 ifeq ($(MFEM_USE_MPI),YES)
   SUNDIALS_LIB += -lsundials_nvecparallel -lsundials_nvecmpiplusx
 endif
@@ -269,6 +260,11 @@ endif
 # If SUNDIALS was built with KLU:
 # MFEM_USE_SUITESPARSE = YES

+# MESQUITE library configuration
+MESQUITE_DIR = @MFEM_DIR@/../mesquite-2.99
+MESQUITE_OPT = -I$(MESQUITE_DIR)/include
+MESQUITE_LIB = -L$(MESQUITE_DIR)/lib -lmesquite
+
 # SuiteSparse library configuration
 LIB_RT = $(if $(NOTMAC),-lrt,)
 SUITESPARSE_DIR = @MFEM_DIR@/../SuiteSparse
@@ -307,7 +303,7 @@ SCALAPACK_LIB = -L$(SCALAPACK_DIR)/lib -lscalapack $(LAPACK_LIB)
 MPI_FORTRAN_LIB = -lmpifort
 # OpenMPI:
 # MPI_FORTRAN_LIB = -lmpi_mpifh
-# Additional Fortran library:
+# Additional Fortan library:
 # MPI_FORTRAN_LIB += -lgfortran

 # MUMPS library configuration
@@ -318,9 +314,6 @@ MUMPS_LIB = $(XLINKER)-rpath,$(MUMPS_DIR)/lib -L$(MUMPS_DIR)/lib -ldmumps\

 # STRUMPACK library configuration
 STRUMPACK_DIR = @MFEM_DIR@/../STRUMPACK-build
-ifeq ($(MFEM_USE_STRUMPACK),YES)
-   BASE_FLAGS = -std=c++14
-endif
 STRUMPACK_OPT = -I$(STRUMPACK_DIR)/include $(SCOTCH_OPT)
 # If STRUMPACK was build with OpenMP support, the following may be need:
 # STRUMPACK_OPT += $(OPENMP_OPT)
@@ -394,11 +387,6 @@ ifeq ($(SLEPC_FOUND),YES)
      $(subst $(CXX_XLINKER),$(XLINKER),$(SLEPC_DEP))
 endif

-ifeq ($(MFEM_USE_MOONOLITH),YES)
-  include $(MOONOLITH_DIR)/config/moonolith-config.makefile
-  MOONOLITH_LIB=$(MOONOLITH_LIBRARIES)
-endif
-
 # MPFR library configuration
 MPFR_OPT =
 MPFR_LIB = -lmpfr
@@ -473,27 +461,7 @@ OCCA_LIB = $(XLINKER)-rpath,$(OCCA_DIR)/lib -L$(OCCA_DIR)/lib -locca
 # CALIPER library configuration
 CALIPER_DIR = @MFEM_DIR@/../caliper
 CALIPER_OPT = -I$(CALIPER_DIR)/include
-CALIPER_LIB = $(XLINKER)-rpath,$(CALIPER_DIR)/lib64 $(XLINKER)-rpath,$(CALIPER_DIR)/lib -L$(CALIPER_DIR)/lib64 -L$(CALIPER_DIR)/lib -lcaliper
-
-ifdef ADIAK_DIR
-   CALIPER_OPT += -I$(ADIAK_DIR)/include
-   CALIPER_LIB += $(XLINKER)-rpath,$(ADIAK_DIR)/lib64 $(XLINKER)-rpath,$(ADIAK_DIR)/lib -L$(ADIAK_DIR)/lib64 -L$(ADIAK_DIR)/lib -ladiak
-endif
-ifdef GOTCHA_DIR
-   CALIPER_OPT += -I$(GOTCHA_DIR)/include
-   CALIPER_LIB += $(XLINKER)-rpath,$(GOTCHA_DIR)/lib64 $(XLINKER)-rpath,$(GOTCHA_DIR)/lib -L$(GOTCHA_DIR)/lib64 -L$(GOTCHA_DIR)/lib -lgotcha
-endif
-
-
-# BLITZ library configuration
-BLITZ_DIR = @MFEM_DIR@/../blitz
-BLITZ_OPT = -I$(BLITZ_DIR)/include
-BLITZ_LIB = $(XLINKER)-rpath,$(BLITZ_DIR)/lib -L$(BLITZ_DIR)/lib -lblitz
-
-# ALGOIM library configuration
-ALGOIM_DIR = @MFEM_DIR@/../algoim
-ALGOIM_OPT = -I$(ALGOIM_DIR)/src $(BLITZ_OPT)
-ALGOIM_LIB = $(BLITZ_LIB)
+CALIPER_LIB = $(XLINKER)-rpath,$(CALIPER_DIR)/lib64 -L$(CALIPER_DIR)/lib64 -lcaliper

 # BENCHMARK library configuration
 BENCHMARK_DIR = @MFEM_DIR@/../google-benchmark
@@ -535,22 +503,6 @@ PARELAG_DIR = @MFEM_DIR@/../parelag
 PARELAG_OPT = -I$(PARELAG_DIR)/src -I$(PARELAG_DIR)/build/src
 PARELAG_LIB = -L$(PARELAG_DIR)/build/src -lParELAG

-# Enzyme configuration
-
-# If you want to enable automatic differentiation at compile time, use the
-# options below, adapted to your configuration. To be more flexible, we
-# recommend using the Enzyme plugin during link time optimization. One option is
-# to add your options to the global compiler/linker flags like
-#
-# BASE_FLAGS += -flto
-# CXX_XLINKER += -fuse-ld=lld -Wl,--lto-legacy-pass-manager\
-#                -Wl,-mllvm=-load=$(ENZYME_DIR)/LLDEnzyme-$(ENZYME_VERSION).so -Wl,
-#
-ENZYME_DIR ?= @MFEM_DIR@/../enzyme
-ENZYME_VERSION ?= 14
-ENZYME_OPT = -fno-experimental-new-pass-manager -Xclang -load -Xclang $(ENZYME_DIR)/ClangEnzyme-$(ENZYME_VERSION).so
-ENZYME_LIB = ""
-
 # If YES, enable some informational messages
 VERBOSE = NO

@@ -1,27 +0,0 @@
-FROM ghcr.io/mfem/mfem-ubuntu-base:latest as builder
-
-# docker build -t ghcr.io/mfem/mfem-ubuntu .
-
-COPY ./config/docker/spack.yaml /opt/mfem-env/spack.yaml
-RUN apt-get install -y python3 && \
-    cd /opt/mfem-env && \
-    . /opt/spack/share/spack/setup-env.sh && \
-    spack env activate . && \
-    spack env view regenerate
-
-FROM ubuntu:22.04
-
-COPY --from=builder /opt/view /opt/view
-COPY --from=builder /opt/mfem-view /opt/mfem-view
-
-RUN apt-get update && \
-    apt-get install -y unzip gfortran && \
-    apt-get install -y libcurl4-openssl-dev libssl-dev
-
-ENV PATH=$PATH:/opt/mfem-view/bin
-ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/mfem-view/lib:/opt/mfem-view/lib64
-ENV DEBIAN_FRONTEND=noninteractive
-
-# The user will see the view on shell into the container
-WORKDIR /opt/mfem-view
-ENTRYPOINT ["/bin/bash"]
@@ -1,47 +0,0 @@
-FROM ghcr.io/rse-ops/cuda-ubuntu-20.04:cuda-11.0.3
-
-# docker build -f Dockerfile.base -t ghcr.io/mfem/mfem-ubuntu-base .
-
-RUN apt-get update && \
-    apt-get install -y unzip gfortran && \
-    spack compiler find && \
-    apt-get install -y libcurl4-openssl-dev libssl-dev
-
-# /code is the working directory for code
-WORKDIR /code
-COPY . /code
-
-# This is for a spack environment/view to install from there
-RUN mkdir -p /opt/mfem-env \
-&&  (echo "spack:" \
-&&   echo "  view:" \
-&&   echo "    mfem:" \
-&&   echo "      root: /opt/mfem-view" \
-&&   echo "      link_type: copy" \
-&&   echo "  packages:" \
-&&   echo "    all:" \
-&&   echo "      target:" \
-&&   echo "      - x86_64_v3" \
-&&   echo "  config:" \
-&&   echo "    concretizer: clingo" \
-&&   echo "    compiler:" \
-&&   echo "      target:" \
-&&   echo "      - x86_64_v3" \
-&&   echo "    install_missing_compilers: true" \
-&&   echo "  concretization: together") > /opt/mfem-env/spack.yaml
-
-RUN cd /opt/mfem-env && \
-    . /opt/spack/share/spack/setup-env.sh && \
-    spack env activate . && \
-    spack develop --path /code mfem@master+examples+miniapps && \
-    spack add mfem@master+examples+miniapps # && \
-#    spack install
-
-# ensure mfem always on various paths
-#RUN cd /opt/mfem-env && \
-#    spack env activate --sh -d . >> /etc/profile.d/z10_spack_environment.sh
-
-# Present the software install when we shell in
-# The view is at /opt/mfem-env/.spack-env/view
-#WORKDIR /opt/software
-#ENTRYPOINT ["/bin/bash", "--rcfile", "/etc/profile", "-l", "-c"]
@@ -1,147 +0,0 @@
-# mfem Docker
-
-We provide a [Dockerfile.base](Dockerfile.base) to build an ubuntu base image,
-and a [Dockerfile](Dockerfile) to build a smaller one with a multi-stage build.
-You can use this image for a demo of using mfem! 🎉️
-
-Updated containers are built and deployed on merges to the main branch and releases.
-If you want to request a build on demand, you can [manually run the workflow](https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow) thanks to the workflow dispatch event.
-
-### Usage
-
-Here is how to build the container. Note that we build so it belongs to the same
-namespace as the repository here. "ghcr.io" means "GitHub Container Registry" and
-is the [GitHub packages](https://github.com/features/packages) registry that supports
- Docker images and other OCI artifacts. From the root of the repository:
-
-```bash
-$ docker build -f config/docker/Dockerfile -t ghcr.io/mfem/mfem-ubuntu .
-$ docker build -f config/docker/Dockerfile.base -t ghcr.io/mfem/mfem-ubuntu-base .
-```
-
-### Shell Ubuntu
-
-To shell into the container:
-
-```bash
-$ docker run -it ghcr.io/mfem/mfem-ubuntu
-```
-
-This smaller image has a view where everything is installed.
-
-```bash
-$ ls
-bin  etc  include  lib  libexec  sbin  share  var
-```
-
- - Examples are in share/mfem/examples
- - Examples are in share/mfem/miniapps
-
-You can read more about interaction with these examples and miniapps below.
-
-### Shell Ubuntu Base
-
-To shell into the container:
-
-```bash
-$ docker run -it ghcr.io/mfem/mfem-ubuntu-base bash
-```
-
-Off the bat, you can see mfem libraries are in your path so you can jump into development:
-
-```bash
-env | grep mfem
-```
-```bash
-PKG_CONFIG_PATH=/opt/mfem-env/.spack-env/view/lib/pkgconfig:/opt/mfem-env/.spack-env/view/share/pkgconfig:/opt/mfem-env/.spack-env/view/lib64/pkgconfig
-PWD=/opt/mfem-env
-MANPATH=/opt/mfem-env/.spack-env/view/share/man:/opt/mfem-env/.spack-env/view/man:
-CMAKE_PREFIX_PATH=/opt/mfem-env/.spack-env/view
-SPACK_ENV=/opt/mfem-env
-ACLOCAL_PATH=/opt/mfem-env/.spack-env/view/share/aclocal
-LD_LIBRARY_PATH=/opt/mfem-env/.spack-env/view/lib:/opt/mfem-env/.spack-env/view/lib64
-PATH=/opt/mfem-env/.spack-env/view/bin:/opt/view/bin:/opt/spack/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
-```
-
-#### Examples and MiniApps
-
-If you want to develop a tool that _uses_ mfem, you can find the built libraries in:
-
-```
-$ ls /opt/mfem-env/.spack-env/view/
-bin  etc  include  lib  libexec  sbin  share  var
-```
-
-And yes, this is the working directory when you shell into the container!
-You can find the examples here:
-
-
-```bash
-cd share/mfem/examples
-```
-```bash
-$ ./ex0
-Options used:
-   --mesh ../data/star.mesh
-   --order 1
-Number of unknowns: 101
-   Iteration :   0  (B r, r) = 0.184259
-   Iteration :   1  (B r, r) = 0.102754
-   Iteration :   2  (B r, r) = 0.00558141
-   Iteration :   3  (B r, r) = 1.5247e-05
-   Iteration :   4  (B r, r) = 1.13807e-07
-   Iteration :   5  (B r, r) = 6.27231e-09
-   Iteration :   6  (B r, r) = 3.76268e-11
-   Iteration :   7  (B r, r) = 6.07423e-13
-   Iteration :   8  (B r, r) = 4.10615e-15
-Average reduction factor = 0.140201
-```
-
-Try running a few, and look at the associated .cpp file for the source code!
-You can also explore the "mini apps," also in share/mfem, but under miniapps.
-
-```bash
-# This is run from the examples directory
-$ cd ../miniapps
-```
-```bash
-$ ls
-CMakeLists.txt  common            meshing  nurbs        shifted  toys
-adjoint         electromagnetics  mtop     parelag      solvers
-autodiff        gslib             navier   performance  tools
-```
-
-And an example in "toys"
-
-```bash
-cd toys
-```
-```bash
-$ ./automata -no-vis
-Options used:
-   --num-steps 16
-   --rule 90
-   --no-visualization
-
-Rule:
- 111 110 101 100 011 010 001 000
-  0   1   0   1   1   0   1   0
-
-Applying rule...done.
-```
-
-Have fun!
-
-
-#### Your own App
-If you want to develop with your own code base
-(and mfem as is in the container) you can bind to somewhere else in the container (e.g., src)
-
-```bash
-$ docker run -it ghcr.io/mfem/mfem-ubuntu-base -v $PWD:/src bash
-```
-
-In the above, we can pretend your project is in the present working directory (PWD) and we are
-binding to source. You can then use the mfem in the container for development, and if you
-want to distribute your library or app in a container, you can use the mfem container as the base.
-
@@ -1,11 +0,0 @@
-spack:
-  specs: [mfem@master+examples+miniapps]
-  view: 
-    mfem:
-      root: /opt/mfem-view 
-      link_type: copy
-  concretization: together
-  develop:
-    mfem:
-      path: /code
-      spec: mfem@master+examples+miniapps
@@ -554,14 +554,15 @@ function go()
   local cmd_line="${1##+( )}"
   cmd_line="${cmd_line%%+( )}"
   shopt -u extglob
+   eval local cmd=(${cmd_line})
   local res=""
   echo $sep
   echo "<${group}>" "${cmd_line}"
   echo $sep
   if [ "${timing}" == "yes" ]; then
-      timed_run eval "${cmd_line}"
+      timed_run "${cmd[@]}"
   else
-      eval "${cmd_line}"
+      "${cmd[@]}"
   fi
   if [ "$?" -eq 0 ]; then
      res="${green}  OK  ${none}"
@@ -1,8 +0,0 @@
--- a/CMakeLists.txt	Wed Dec 21 18:24:22 2016
-+++ b/CMakeLists.txt	Wed Dec 21 18:24:26 2016
-@@ -20,4 +20,4 @@
- # Recursively look for CMakeLists.txt in subdirs.
- add_subdirectory("include")
- add_subdirectory("libmetis")
-add_subdirectory("programs")
-+# add_subdirectory("programs")
@@ -1,15 +0,0 @@
--- a/CMakeLists.txt	Sat Mar 30 17:24:45 2013
-+++ b/CMakeLists.txt	Wed Dec 21 18:23:43 2016
-@@ -4,11 +4,7 @@
- set(GKLIB_PATH "GKlib" CACHE PATH "path to GKlib")
- set(SHARED FALSE CACHE BOOL "build a shared library")
- 
-if(MSVC)
-  set(METIS_INSTALL FALSE)
-else()
-  set(METIS_INSTALL TRUE)
-endif()
-+set(METIS_INSTALL TRUE)
- 
- # Configure libmetis library.
- if(SHARED)
@@ -1,34 +0,0 @@
-diff --git a/include/metis.h b/include/metis.h
-index dc5406a..7732437 100644
--- a/include/metis.h
-+++ b/include/metis.h
-@@ -72,10 +72,14 @@ typedef __int64 int64_t;
- #define PRId64       "I64d"
- #define SCNd32       "ld"
- #define SCNd64       "I64d"
-+#ifdef _WIN32
-+#include <stdint.h>
-+#else
- #define INT32_MIN    ((int32_t)_I32_MIN)
- #define INT32_MAX    _I32_MAX
- #define INT64_MIN    ((int64_t)_I64_MIN)
- #define INT64_MAX    _I64_MAX
-+#endif
- #else
- #include <inttypes.h>
- #endif
-diff --git a/GKlib/gk_arch.h b/GKlib/gk_arch.h
-index 78b1431..7258763 100644
--- a/GKlib/gk_arch.h
-+++ b/GKlib/gk_arch.h
-@@ -32,8 +32,8 @@
- 
- 
- #ifdef __MSC__ 
-  #include "ms_stdint.h"
-  #include "ms_inttypes.h"
-+  #include <stdint.h>
-+  #include <inttypes.h>
-   #include "ms_stat.h"
- #else
- #ifndef SUNOS
@@ -1,11 +0,0 @@
--- a/GKlib/gk_arch.h	Wed Dec 21 18:34:18 2016
-+++ b/GKlib/gk_arch.h	Wed Dec 21 18:30:49 2016
-@@ -58,7 +58,7 @@
- #define PTRDIFF_MAX  INT64_MAX
- #endif
- 
-#ifdef __MSC__
-+#if defined(__MSC__) && (_MSC_VER < 1900)
- /* MSC does not have rint() function */
- #define rint(x) ((int)((x)+0.5))  
- 
@@ -1,14 +0,0 @@
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index e94f050..b9613a7 100644
--- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -1,7 +1,8 @@
- cmake_minimum_required(VERSION 2.8)
- project(METIS)
- 
-set(GKLIB_PATH "GKlib" CACHE PATH "path to GKlib")
-+set(GKLIB_PATH "${CMAKE_SOURCE_DIR}/GKlib" CACHE PATH "path to GKlib")
-+
- set(SHARED FALSE CACHE BOOL "build a shared library")
- 
- set(METIS_INSTALL TRUE)
@@ -1,11 +0,0 @@
--- a/libmetis/metislib.h	Sat Mar 30 17:24:45 2013
-+++ b/libmetis/metislib.h	Wed Dec 21 18:30:59 2016
-@@ -31,7 +31,7 @@
- #include <proto.h>
- 
- 
-#if defined(COMPILER_MSC)
-+#if defined(COMPILER_MSC) && (_MSC_VER < 1900)
- #if defined(rint)
-   #undef rint
- #endif
@@ -1,10 +0,0 @@
--- a/libmetis/CMakeLists.txt	Sat Mar 30 17:24:45 2013
-+++ b/libmetis/CMakeLists.txt	Wed Dec 21 17:41:37 2016
-@@ -11,6 +11,6 @@
- if(METIS_INSTALL)
-   install(TARGETS metis
-     LIBRARY DESTINATION lib
-    RUNTIME DESTINATION lib
-+    RUNTIME DESTINATION bin
-     ARCHIVE DESTINATION lib)
- endif()
@@ -1,44 +0,0 @@
-diff --git a/CMakeLists.txt b/CMakeLists.txt
-index b9613a7..e43ffee 100644
--- a/CMakeLists.txt
-+++ b/CMakeLists.txt
-@@ -22,3 +22,23 @@ include_directories(include)
- add_subdirectory("include")
- add_subdirectory("libmetis")
- # add_subdirectory("programs")
-+
-+if(METIS_INSTALL)
-+  set(PRJ_NAME metis)
-+  set(PRJ_VER 5.1.0)
-+  install(EXPORT metisTargets 
-+    FILE ${PRJ_NAME}Targets.cmake
-+    DESTINATION lib/cmake/${PRJ_NAME})
-+  include(CMakePackageConfigHelpers)
-+  write_basic_package_version_file(
-+    ${CMAKE_CURRENT_BINARY_DIR}/${PRJ_NAME}ConfigVersion.cmake
-+    VERSION ${PRJ_VER}
-+    COMPATIBILITY SameMajorVersion)
-+  file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/${PRJ_NAME}Config.cmake
-+    "include(\${CMAKE_CURRENT_LIST_DIR}/${PRJ_NAME}Targets.cmake)")
-+  install(FILES 
-+    ${CMAKE_CURRENT_BINARY_DIR}/${PRJ_NAME}ConfigVersion.cmake
-+    ${CMAKE_CURRENT_BINARY_DIR}/${PRJ_NAME}Config.cmake
-+    DESTINATION lib/cmake/${PRJ_NAME})
-+endif()
-+
-diff --git a/libmetis/CMakeLists.txt b/libmetis/CMakeLists.txt
-index 7a5fc74..5a68cf0 100644
--- a/libmetis/CMakeLists.txt
-+++ b/libmetis/CMakeLists.txt
-@@ -9,8 +9,9 @@ if(UNIX)
- endif()
- 
- if(METIS_INSTALL)
-  install(TARGETS metis
-+  install(TARGETS metis EXPORT metisTargets
-     LIBRARY DESTINATION lib
-     RUNTIME DESTINATION bin
-    ARCHIVE DESTINATION lib)
-+    ARCHIVE DESTINATION lib
-+    INCLUDES DESTINATION include)
- endif()
@@ -1,41 +0,0 @@
-vcpkg_check_linkage(ONLY_STATIC_LIBRARY)
-set(OPTIONS -DSHARED=OFF)
-
-set(METIS_VERSION 5.1.0)
-
-vcpkg_download_distfile(ARCHIVE
-    URLS "https://github.com/mfem/tpls/raw/gh-pages/metis-${METIS_VERSION}.tar.gz"
-    FILENAME "metis-${METIS_VERSION}.tar.gz"
-    SHA512 deea47749d13bd06fbeaf98a53c6c0b61603ddc17a43dae81d72c8015576f6495fd83c11b0ef68d024879ed5415c14ebdbd87ce49c181bdac680573bea8bdb25
-)
-
-vcpkg_extract_source_archive_ex(
-    OUT_SOURCE_PATH SOURCE_PATH
-    ARCHIVE ${ARCHIVE}
-    REF ${METIS_VERSION}
-    PATCHES
-        enable-install.patch
-        disable-programs.patch
-        fix-runtime-install-destination.patch
-        fix-metis-vs14-math.patch
-        fix-gklib-vs14-math.patch
-        fix-linux-build-error.patch
-        install-metisConfig.patch
-        fix-INT_MIN_define.patch
-)
-
-vcpkg_configure_cmake(
-    SOURCE_PATH ${SOURCE_PATH}
-    PREFER_NINJA
-    OPTIONS ${OPTIONS}
-)
-
-vcpkg_install_cmake()
-vcpkg_copy_pdbs()
-vcpkg_fixup_cmake_targets(CONFIG_PATH lib/cmake/metis)
-
-file(REMOVE_RECURSE ${CURRENT_PACKAGES_DIR}/debug/include)
-
-# Handle copyright
-file(COPY ${SOURCE_PATH}/LICENSE.txt DESTINATION ${CURRENT_PACKAGES_DIR}/share/metis)
-file(INSTALL ${SOURCE_PATH}/LICENSE.txt DESTINATION ${CURRENT_PACKAGES_DIR}/share/${PORT} RENAME copyright)
@@ -1,7 +0,0 @@
-{
-  "name": "metis-mfem",
-  "version-string": "5.1.0",
-  "port-version": 0,
-  "description": "Serial Graph Partitioning and Fill-reducing Matrix Ordering",
-  "homepage": "http://glaros.dtc.umn.edu/gkhome/metis/metis/overview"
-}
@@ -1,56 +0,0 @@
-MFEM mesh v1.0
-
-#
-# MFEM Geometry Types (see mesh/geom.hpp):
-#
-# POINT       = 0
-# SEGMENT     = 1
-# TRIANGLE    = 2
-# SQUARE      = 3
-# TETRAHEDRON = 4
-# CUBE        = 5
-# PRISM       = 6
-# PYRAMID     = 7
-
-dimension
-3
-
-elements
-4
-1 5 0 1 4 3 6 7 10 9
-1 6 4 1 5 10 7 11
-1 7 11 7 1 5 8
-1 4 2 5 1 8
-
-boundary
-14
-1 3 0 3 4 1
-1 3 6 7 10 9
-1 3 0 6 9 3
-1 3 0 1 7 6
-1 3 3 9 10 4
-1 2 1 5 2
-1 2 1 4 5
-1 2 1 8 7
-1 2 1 2 8
-1 2 2 5 8
-1 2 5 11 8
-1 2 7 8 11
-1 2 7 11 10
-1 3 4 10 11 5
-
-vertices
-12
-3
-0 0 0
-1 0 0
-2 0 0
-0 1 0
-1 1 0
-2 1 0
-0 0 1
-1 0 1
-2 0 1
-0 1 1
-1 1 1
-2 1 1
@@ -38,7 +38,7 @@ PROJECT_NAME           = "MFEM"
 # could be handy for archiving the generated documentation or if some version
 # control system is used.

-PROJECT_NUMBER         = v4.5.1
+PROJECT_NUMBER         = v4.4.0

 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a
@@ -763,54 +763,33 @@ INPUT                  = @MFEM_SOURCE_DIR@/doc/CodeDocumentation.dox \
                         @MFEM_SOURCE_DIR@/config \
                         @MFEM_SOURCE_DIR@/general \
                         @MFEM_SOURCE_DIR@/linalg \
-                         @MFEM_SOURCE_DIR@/linalg/simd \
                         @MFEM_SOURCE_DIR@/mesh \
-                         @MFEM_SOURCE_DIR@/mesh/submesh \
                         @MFEM_SOURCE_DIR@/fem \
-                         @MFEM_SOURCE_DIR@/fem/ceed \
-                         @MFEM_SOURCE_DIR@/fem/ceed/integrators \
-                         @MFEM_SOURCE_DIR@/fem/ceed/integrators/convection \
-                         @MFEM_SOURCE_DIR@/fem/ceed/integrators/diffusion \
-                         @MFEM_SOURCE_DIR@/fem/ceed/integrators/mass \
-                         @MFEM_SOURCE_DIR@/fem/ceed/integrators/nlconvection \
-                         @MFEM_SOURCE_DIR@/fem/ceed/interface \
-                         @MFEM_SOURCE_DIR@/fem/ceed/solvers \
                         @MFEM_SOURCE_DIR@/fem/fe \
-                         @MFEM_SOURCE_DIR@/fem/lor \
-                         @MFEM_SOURCE_DIR@/fem/moonolith \
-                         @MFEM_SOURCE_DIR@/fem/qinterp \
-                         @MFEM_SOURCE_DIR@/fem/tmop \
                         @MFEM_SOURCE_DIR@/examples \
-                         @MFEM_SOURCE_DIR@/examples/amgx \
                         @MFEM_SOURCE_DIR@/examples/caliper \
+                         @MFEM_SOURCE_DIR@/examples/amgx \
                         @MFEM_SOURCE_DIR@/examples/ginkgo \
                         @MFEM_SOURCE_DIR@/examples/hiop \
-                         @MFEM_SOURCE_DIR@/examples/moonolith \
                         @MFEM_SOURCE_DIR@/examples/petsc \
                         @MFEM_SOURCE_DIR@/examples/pumi \
                         @MFEM_SOURCE_DIR@/examples/sundials \
                         @MFEM_SOURCE_DIR@/examples/superlu \
                         @MFEM_SOURCE_DIR@/miniapps/adjoint \
-                         @MFEM_SOURCE_DIR@/miniapps/autodiff \
                         @MFEM_SOURCE_DIR@/miniapps/common \
                         @MFEM_SOURCE_DIR@/miniapps/electromagnetics \
                         @MFEM_SOURCE_DIR@/miniapps/gslib \
-                         @MFEM_SOURCE_DIR@/miniapps/hooke \
-                         @MFEM_SOURCE_DIR@/miniapps/hooke/kernels \
-                         @MFEM_SOURCE_DIR@/miniapps/hooke/materials \
-                         @MFEM_SOURCE_DIR@/miniapps/hooke/operators \
-                         @MFEM_SOURCE_DIR@/miniapps/hooke/preconditioners \
                         @MFEM_SOURCE_DIR@/miniapps/meshing \
                         @MFEM_SOURCE_DIR@/miniapps/mtop \
-                         @MFEM_SOURCE_DIR@/miniapps/multidomain \
+                         @MFEM_SOURCE_DIR@/miniapps/autodiff \
                         @MFEM_SOURCE_DIR@/miniapps/navier \
                         @MFEM_SOURCE_DIR@/miniapps/nurbs \
-                         @MFEM_SOURCE_DIR@/miniapps/parelag \
                         @MFEM_SOURCE_DIR@/miniapps/performance \
                         @MFEM_SOURCE_DIR@/miniapps/shifted \
                         @MFEM_SOURCE_DIR@/miniapps/solvers \
                         @MFEM_SOURCE_DIR@/miniapps/tools \
-                         @MFEM_SOURCE_DIR@/miniapps/toys
+                         @MFEM_SOURCE_DIR@/miniapps/toys \
+                         @MFEM_SOURCE_DIR@/miniapps/parelag

 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
@@ -2367,7 +2346,7 @@ PLANTUML_INCLUDE_PATH  =
 # Minimum value: 0, maximum value: 10000, default value: 50.
 # This tag requires that the tag HAVE_DOT is set to YES.

-DOT_GRAPH_MAX_NODES    = 100
+DOT_GRAPH_MAX_NODES    = 50

 # The MAX_DOT_GRAPH_DEPTH tag can be used to set the maximum depth of the graphs
 # generated by dot. A depth value of 3 means that only nodes reachable from the
@@ -103,8 +103,6 @@ namespace mfem {
 * - <a class="el" href="ex31_8cpp_source.html">Example 31</a>: Nedelec H(curl) FEM for the definite anisotropic Maxwell problem
 * - <a class="el" href="ex31p_8cpp_source.html">Example 31p</a>: parallel Nedelec H(curl) FEM for the definite anisotropic Maxwell problem
 * - <a class="el" href="ex32p_8cpp_source.html">Example 32p</a>: parallel anisotropic Maxwell eigensolver
- * - <a class="el" href="ex33_8cpp_source.html">Example 33</a>: nodal H1 FEM for the fractional Laplacian problem
- * - <a class="el" href="ex33p_8cpp_source.html">Example 33p</a>: parallel nodal H1 FEM for the fractional Laplacian problem
 *
 * <H4>AmgX Examples</H4>
 * - Variants of Examples
@@ -39,7 +39,6 @@ list(APPEND ALL_EXE_SRCS
  ex29.cpp
  ex30.cpp
  ex31.cpp
-  ex33.cpp
  )

 if (MFEM_USE_MPI)
@@ -76,7 +75,6 @@ if (MFEM_USE_MPI)
    ex30p.cpp
    ex31p.cpp
    ex32p.cpp
-    ex33p.cpp
    )
 endif()

@@ -201,7 +199,3 @@ endif()
 if (MFEM_USE_SUPERLU)
  add_subdirectory(superlu)
 endif()
-
-if(MFEM_USE_MOONOLITH)
-  add_subdirectory(moonolith)
-endif()
@@ -33,13 +33,13 @@ add_mfem_examples(CALIPER_EXE_SRCS ${PREFIX})
 if (MFEM_ENABLE_TESTING)
  foreach(SRC_FILE ${CALIPER_EXE_SRCS})
    get_filename_component(SRC_FILENAME ${SRC_FILE} NAME)
-    string(REPLACE ".cpp" "" TEST_NAME ${PREFIX}${SRC_FILENAME})
+    string(REPLACE ".cpp" "" TEST_NAME ${SRC_FILENAME})

    set(THIS_TEST_OPTIONS "-no-vis")

    if (NOT (${TEST_NAME} MATCHES ".*p$"))
      add_test(NAME ${TEST_NAME}_ser
-        COMMAND $<TARGET_FILE:${TEST_NAME}> ${THIS_TEST_OPTIONS})
+        COMMAND ${TEST_NAME} ${THIS_TEST_OPTIONS})
    else()
      add_test(NAME ${TEST_NAME}_np=${MFEM_MPI_NP}
        COMMAND ${MPIEXEC} ${MPIEXEC_NUMPROC_FLAG} ${MFEM_MPI_NP}
@@ -0,0 +1,294 @@
+//                 MFEM FOSLS acoustics Example
+//
+// Compile with: make fosls
+//
+// Definite/Indefinite Helmholtz
+
+//     - Δ p ± ω^2 p = f̃ ,   in Ω
+//                 p = p_0, on ∂Ω
+
+// First Order System
+
+//   ∇ p - ω u = 0, in Ω
+// - ∇⋅u ± ω p = f, in Ω
+//           p = p_0, in ∂Ω
+// where f:=f̃/ω 
+
+// FOSLS:
+//       minimize  1/2(||∇p - ω u||^2 + ||-∇⋅u ± ω p - f||^2)
+
+// (p,u) ∈ H^1(Ω) × H(div,Ω)
+// -------------------------------------------------------------------
+// |   |            p           |            u             |   RHS    | 
+// -------------------------------------------------------------------
+// | q |  (∇ p,∇ q) + ω^2(p,q)  | ∓ ω (∇⋅u,q) - ω (u, ∇ q) | ± ω(f,q) |
+// |   |                        |                          |          |
+// | v | ∓ ω (p,∇⋅v) - ω (∇ p,v)|  (∇⋅u,∇⋅v) + ω^2 (u,v)   | -(f,∇⋅v) |
+
+// where (q,v) ∈ H^1(Ω) × H(div,Ω)
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+// #define DEFINITE
+
+double p_exact(const Vector &x);
+void u_exact(const Vector &x, Vector & u);
+double rhs_func(const Vector &x);
+void gradp_exact(const Vector &x, Vector &gradu);
+double divu_exact(const Vector &x);
+double d2_exact(const Vector &x);
+
+int dim;
+double omega;
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   bool visualization = true;
+   double rnum=1.0;
+   int sr = 1;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree)");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.AddOption(&rnum, "-rnum", "--number_of_wavelenths",
+                  "Number of wavelengths");      
+   args.AddOption(&sr, "-sr", "--serial_ref",
+                  "Number of serial refinements.");                               
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   omega = 2.0 * M_PI * rnum;
+
+
+   Mesh mesh(mesh_file, 1, 1);
+   dim = mesh.Dimension();
+
+   for (int i = 0; i < sr; i++ )
+   {
+      mesh.UniformRefinement();
+   }
+
+   FiniteElementCollection *H1fec = new H1_FECollection(order, dim);
+   FiniteElementCollection *RTfec = new RT_FECollection(order-1, dim);
+   FiniteElementSpace * H1fes = new FiniteElementSpace(&mesh, H1fec);
+   FiniteElementSpace * RTfes = new FiniteElementSpace(&mesh, RTfec);
+
+   Array<FiniteElementSpace *> fespaces(2);
+   fespaces[0] = H1fes;
+   fespaces[1] = RTfes;
+
+   Array<int> ess_bdr;
+   Array<int> ess_tdof_list;
+   if (mesh.bdr_attributes.Size())
+   {
+      ess_bdr.SetSize(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      fespaces[0]->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   BlockBilinearForm a(fespaces);
+   a.SetDiagonalPolicy(mfem::Operator::DIAG_KEEP);
+   cout << "H1 fespace = " << H1fes->GetTrueVSize() << endl;
+   cout << "RT fespace = " << RTfes->GetTrueVSize() << endl;
+
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient omeg(omega);
+   ConstantCoefficient negomeg(-omega);
+   ConstantCoefficient omeg2(omega*omega);
+
+
+   Array2D<BilinearFormIntegrator * > blfi(2,2);
+
+   // blfi(0,0) = (∇ p,∇ q) + ω^2(p,q)
+   SumIntegrator * integ00 = new SumIntegrator();
+   integ00->AddIntegrator(new DiffusionIntegrator(one));
+   integ00->AddIntegrator(new MassIntegrator(omeg2));
+   blfi(0,0) = integ00;
+
+   // blfi(0,1) = ∓ ω (∇⋅u,q) - ω (u, ∇ q)
+   SumIntegrator * integ01 = new SumIntegrator();
+#ifdef DEFINITE
+   // -ω (∇⋅u,q)
+   integ01->AddIntegrator(new MixedScalarDivergenceIntegrator(negomeg));
+#else   
+   // ω (∇⋅u,q)
+   integ01->AddIntegrator(new MixedScalarDivergenceIntegrator(omeg));
+#endif
+   // - ω (u, ∇ q)
+   integ01->AddIntegrator(new MixedVectorWeakDivergenceIntegrator(omeg));
+   blfi(0,1) = integ01;
+
+   // blfi(1,0) = ∓ ω (p,∇⋅v) - ω (∇ p,v)
+   SumIntegrator * integ10 = new SumIntegrator();
+#ifdef DEFINITE
+   // - ω (p,∇⋅v)
+   integ10->AddIntegrator(new MixedScalarWeakGradientIntegrator(omeg));
+#else
+   // ω (p,∇⋅v)
+   integ10->AddIntegrator(new MixedScalarWeakGradientIntegrator(negomeg));
+#endif
+   // - ω (∇ p,v)
+   integ10->AddIntegrator(new MixedVectorGradientIntegrator(negomeg));
+   blfi(1,0) = integ10;
+
+   // blfi(1,1) = (∇⋅u,∇⋅v) + ω^2 (u,v)
+   SumIntegrator * integ11 = new SumIntegrator();
+   integ11->AddIntegrator(new DivDivIntegrator(one));
+   integ11->AddIntegrator(new VectorFEMassIntegrator(omeg2));
+   blfi(1,1) = integ11;
+
+
+   BlockLinearForm b(fespaces);
+   Array<LinearFormIntegrator * > lfi(2);
+   // ± ω (f,q)
+   FunctionCoefficient f_rhs(rhs_func);
+#ifdef DEFINITE  
+   ProductCoefficient w_f(omeg,f_rhs);
+#else   
+   ProductCoefficient w_f(negomeg,f_rhs);
+#endif   
+   // lfi[0] = new DomainLFIntegrator(w_f);
+   lfi[0] = new DomainLFIntegrator(w_f);
+
+
+   //  -(f,∇⋅v)
+   ProductCoefficient neg_f(negone,f_rhs);
+   // lfi[1] = new VectorFEDomainLFDivIntegrator(f_rhs);
+   lfi[1] = new VectorFEDomainLFDivIntegrator(neg_f);
+
+   TestBlockBilinearFormIntegrator * integ = new TestBlockBilinearFormIntegrator();
+   integ->SetIntegrators(blfi);
+   a.AddDomainIntegrator(integ);
+   a.Assemble();
+
+   TestBlockLinearFormIntegrator * lininteg = new TestBlockLinearFormIntegrator();
+   lininteg->SetIntegrators(lfi);
+   b.AddDomainIntegrator(lininteg);
+   b.Assemble();
+
+   int size = 0;
+   for (int i = 0; i<fespaces.Size(); i++)
+   {
+      size += fespaces[i]->GetVSize();
+   }
+
+   Vector x(size);
+   x = 0.0;
+   FunctionCoefficient p_ex(p_exact);
+   VectorFunctionCoefficient gradp_ex(dim,gradp_exact);
+   VectorFunctionCoefficient u_ex(dim,u_exact);
+   FunctionCoefficient divu_ex(divu_exact);
+   GridFunction p_gf, u_gf;   
+   GridFunction pex_gf(H1fes);   
+
+   p_gf.MakeRef(H1fes,x,0);
+   // p_gf.ProjectBdrCoefficient(p_ex,ess_bdr);
+   p_gf.ProjectCoefficient(p_ex);
+   pex_gf.ProjectCoefficient(p_ex);
+
+   u_gf.MakeRef(RTfes,x,H1fes->GetVSize());
+   u_gf = 0.;
+
+
+   OperatorPtr A;
+   Vector X,B;
+   a.FormLinearSystem(ess_tdof_list,x,b,A,X,B);
+
+   GSSmoother M((SparseMatrix&)(*A));
+   CGSolver cg;
+   cg.SetRelTol(1e-10);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(1);
+   cg.SetPreconditioner(M);
+   cg.SetOperator(*A);
+   cg.Mult(B, X);
+
+   a.RecoverFEMSolution(X,b,x);
+
+   p_gf.MakeRef(H1fes,x,0);
+   u_gf.MakeRef(RTfes,x,H1fes->GetVSize());
+
+
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      socketstream solu_sock(vishost, visport);
+      solu_sock.precision(8);
+      solu_sock << "solution\n" << mesh << p_gf <<
+                "window_title 'Numerical p' "
+                << flush;
+      // socketstream sols_sock(vishost, visport);
+      // sols_sock.precision(8);
+      // sols_sock << "solution\n" << mesh << u_gf <<
+               //  "window_title 'Numerical sigma' "
+               //  << flush;
+
+      socketstream solex_sock(vishost, visport);
+      solex_sock.precision(8);
+      solex_sock << "solution\n" << mesh << pex_gf <<
+                    "window_title 'Exact p' "
+                    << flush;          
+   }
+
+   return 0;
+}
+
+
+double rhs_func(const Vector &x)
+{
+   double p = p_exact(x);
+   double divu = divu_exact(x);
+   // f = - ∇⋅u ± ω p, 
+#ifdef DEFINITE   
+   return -divu + omega * p;
+#else
+   return -divu - omega * p;
+#endif   
+}
+
+double p_exact(const Vector &x)
+{
+   return sin(omega*x.Sum());
+}
+
+void gradp_exact(const Vector &x, Vector &grad)
+{
+   grad.SetSize(x.Size());
+   grad = omega * cos(omega * x.Sum());
+}
+
+void u_exact(const Vector &x, Vector & u)
+{
+   gradp_exact(x,u);
+   u *= 1./omega;
+}
+
+double divu_exact(const Vector &x)
+{
+   return d2_exact(x)/omega;
+}
+
+double d2_exact(const Vector &x)
+{
+   return -dim * omega * omega * sin(omega*x.Sum());
+}
@@ -10,19 +10,17 @@
 # CONTRIBUTING.md for details.

 # Use the MFEM build directory
-MFEM_DIR ?= ../..
-MFEM_BUILD_DIR ?= ../..
-SRC = $(if $(MFEM_DIR:../..=),$(MFEM_DIR)/examples/moonolith/,)
+MFEM_DIR ?= ../../..
+MFEM_BUILD_DIR ?= ../../..
+SRC = $(if $(MFEM_DIR:../../..=),$(MFEM_DIR)/examples/dpg_tests/acoustics,)
 CONFIG_MK = $(MFEM_BUILD_DIR)/config/config.mk
-# Use the MFEM install directory
-# MFEM_INSTALL_DIR = ../../mfem
-# CONFIG_MK = $(MFEM_INSTALL_DIR)/share/mfem/config.mk

 MFEM_LIB_FILE = mfem_is_not_built
 -include $(CONFIG_MK)

-SEQ_EXAMPLES = ex1
-PAR_EXAMPLES = ex1p ex2p
+SEQ_EXAMPLES = fosls uw_dpg  strong_dpg
+PAR_EXAMPLES = uw_dpgp
+
 ifeq ($(MFEM_USE_MPI),NO)
   EXAMPLES = $(SEQ_EXAMPLES)
 else
@@ -31,7 +29,7 @@ endif

 .SUFFIXES:
 .SUFFIXES: .o .cpp .mk
-.PHONY: all clean clean-build
+.PHONY: all clean clean-build clean-exec

 # Remove built-in rule
 %: %.cpp
@@ -40,39 +38,22 @@ endif
 %: $(SRC)%.cpp $(MFEM_LIB_FILE) $(CONFIG_MK)
 	$(MFEM_CXX) $(MFEM_FLAGS) $< -o $@ $(MFEM_LIBS)

-all: $(EXAMPLES)
-
-ifeq ($(MFEM_USE_MOONOLITH),NO)
-$(EXAMPLES):
-	$(error MFEM is not configured with MOONOLITH)
-endif
+all: $(EXAMPLES) 

 MFEM_TESTS = EXAMPLES
 include $(MFEM_TEST_MK)

 # Testing: Parallel vs. serial runs
-RUN_MPI_NP = $(MFEM_MPIEXEC) $(MFEM_MPIEXEC_NP)
-RUN_MPI = $(RUN_MPI_NP) $(MFEM_MPI_NP)
-SERIAL_NAME := Serial MOONOLITH example
-PARALLEL_NAME := Parallel MOONOLITH example
+RUN_MPI = $(MFEM_MPIEXEC) $(MFEM_MPIEXEC_NP) $(MFEM_MPI_NP)
 %-test-par: %
-	@$(call mfem-test,$<, $(RUN_MPI), $(PARALLEL_NAME))
+	@$(call mfem-test,$<, $(RUN_MPI), Parallel example)
 %-test-seq: %
-	@$(call mfem-test,$<,, $(SERIAL_NAME))
+	@$(call mfem-test,$<,, Serial example)

-# Testing: Example-specific execution options:
-ex1-test-par: ex1
-	@$(call mfem-test,$<, $(RUN_MPI_NP) 1, $(PARALLEL_NAME))
-
-# Testing: "test" target and mfem-test* variables are defined in config/test.mk
-
-# Generate an error message if the MFEM library is not built and exit
-$(MFEM_LIB_FILE):
-	$(error The MFEM library is not built)
-
-clean: clean-build
+clean: clean-build clean-exec 

 clean-build:
 	rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
 	rm -rf *.dSYM *.TVD.*breakpoints

+clean-exec:
@@ -0,0 +1,271 @@
+//                 MFEM DPG_strong acoustics Example
+//
+// Compile with: make strong_dpg
+//
+// Definite/Indefinite Helmholtz
+
+//     - Δ p ± ω^2 p = f̃ ,   in Ω
+//                 p = p_0, on ∂Ω
+
+// First Order System
+
+//   ∇ p - ω u = 0, in Ω
+// - ∇⋅u ± ω p = f, in Ω
+//           p = p_0, in ∂Ω
+// where f:=f̃/ω 
+
+// Strong DPG formulation
+// (p,u) ∈ H^1(Ω) × H(div,Ω)
+// 
+//   (∇ p, v) - ω (u,v) = 0,     in Ω, ∀ v ∈ (L^2)^dim
+//  -(∇⋅u, q) ± ω (p,q) = (f,q), in Ω, ∀ q ∈  L^2 
+//                    p = p_0, in ∂Ω
+// 
+// ------------------------------------
+// |   |      p    |     u    |  RHS  | 
+// ------------------------------------
+// | q | ± ω (p,q) | -(∇⋅u,q) | (f,q) |
+// |   |           |          |       |
+// | v | (∇ p, v)  | -ω (u,v) |       |
+
+// where (q,v) ∈ L^2  × (L^2)^dim
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+// #define DEFINITE
+
+double p_exact(const Vector &x);
+void u_exact(const Vector &x, Vector & u);
+double rhs_func(const Vector &x);
+void gradp_exact(const Vector &x, Vector &gradu);
+double divu_exact(const Vector &x);
+double d2_exact(const Vector &x);
+
+int dim;
+double omega;
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   bool visualization = true;
+   double rnum=1.0;
+   int ref = 1;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree)");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.AddOption(&rnum, "-rnum", "--number_of_wavelenths",
+                  "Number of wavelengths");      
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");                  
+   args.AddOption(&ref, "-ref", "--serial_ref",
+                  "Number of serial refinements.");                               
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   omega = 2.0 * M_PI * rnum;
+
+
+   Mesh mesh(mesh_file, 1, 1);
+   dim = mesh.Dimension();
+
+
+   for (int i = 0; i < ref; i++ )
+   {
+      mesh.UniformRefinement();
+   }
+
+   // Define spaces
+   // H1 space for p
+   FiniteElementCollection *p_fec = new H1_FECollection(order, dim);
+   FiniteElementSpace * p_fes = new FiniteElementSpace(&mesh, p_fec);
+
+   // H(div) for u
+   FiniteElementCollection *u_fec = new RT_FECollection(order-1, dim);
+   FiniteElementSpace * u_fes = new FiniteElementSpace(&mesh, u_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * q_fec = new L2_FECollection(test_order-1, dim);
+   FiniteElementCollection * v_fec = new L2_FECollection(test_order-1, dim);
+
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient omeg(omega);
+   ConstantCoefficient negomeg(-omega);
+
+   // Normal equation weak formulation
+   Array<FiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(p_fes);
+   trial_fes.Append(u_fes);
+   test_fec.Append(q_fec);
+   test_fec.Append(v_fec);
+
+   NormalEquations * a = new NormalEquations(trial_fes,test_fec);
+   a->SetTestFECollVdim(1,dim);
+   
+   a->StoreMatrices(true);
+
+//  ± ω (p, q)
+#ifdef DEFINITE
+//  ω (p, q)
+   a->AddTrialIntegrator(new MassIntegrator(omeg),0,0);
+#else
+// -ω (p, q)
+   a->AddTrialIntegrator(new MassIntegrator(negomeg),0,0);
+#endif
+
+// -(∇⋅u, q) 
+   a->AddTrialIntegrator(new MixedScalarDivergenceIntegrator(negone),1,0);
+
+// -ω (u,v)
+   a->AddTrialIntegrator(new VectorFEMassIntegrator(negomeg),1,1);
+
+// (∇ p, v)
+   a->AddTrialIntegrator(new GradientIntegrator(one),0,1);
+
+// (v,δv)
+   a->AddTestIntegrator(new VectorMassIntegrator(one),1,1);
+    
+// (q,δq)
+   a->AddTestIntegrator(new MassIntegrator(one),0,0);
+
+   FunctionCoefficient f_rhs(rhs_func);
+   a->AddDomainLFIntegrator(new DomainLFIntegrator(f_rhs),0);
+
+   Array<int> ess_tdof_list;
+   Array<int> ess_bdr;
+   if (mesh.bdr_attributes.Size())
+   {
+      ess_bdr.SetSize(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      p_fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   FunctionCoefficient p_ex(p_exact);
+   VectorFunctionCoefficient gradp_ex(dim,gradp_exact);
+   VectorFunctionCoefficient u_ex(dim,u_exact);
+   FunctionCoefficient divu_ex(divu_exact);
+   GridFunction p_gf, u_gf;   
+   GridFunction pex_gf(p_fes);   
+
+   Array<int> offsets(3);
+   offsets[0] = 0;
+   offsets[1] = p_fes->GetVSize();
+   offsets[2] = u_fes->GetVSize();
+   offsets.PartialSum();
+   BlockVector x(offsets);
+   x = 0.0;
+
+   p_gf.MakeRef(p_fes,x.GetBlock(0));
+   p_gf.ProjectBdrCoefficient(p_ex,ess_bdr);
+
+   u_gf.MakeRef(u_fes,x.GetBlock(1));
+
+   a->Assemble();
+
+   OperatorPtr Ah;
+   Vector X,B;
+   a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+   BlockMatrix * A = Ah.As<BlockMatrix>();
+
+   BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+   M->owns_blocks = 1;
+   for (int i=0; i<A->NumRowBlocks(); i++)
+   {
+      M->SetDiagonalBlock(i,new UMFPackSolver(A->GetBlock(i,i)));
+   }
+
+   CGSolver cg;
+   cg.SetRelTol(1e-12);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(3);
+   cg.SetPreconditioner(*M);
+   cg.SetOperator(*A);
+   cg.Mult(B, X);
+   delete M;
+
+   a->RecoverFEMSolution(X,x);
+
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      socketstream p_out;
+      socketstream u_out;
+      p_out.open(vishost, visport);
+      u_out.open(vishost, visport);
+      p_out.precision(8);
+      p_out << "solution\n" << mesh << p_gf <<
+               "window_title 'Numerical p' "
+               << flush;
+
+      u_out.precision(8);
+      u_out << "solution\n" << mesh << u_gf <<
+            "window_title 'Numerical flux' "
+            << flush;
+   }
+
+   return 0;
+}
+
+
+double rhs_func(const Vector &x)
+{
+   double p = p_exact(x);
+   double divu = divu_exact(x);
+   // f = - ∇⋅u ± ω p, 
+#ifdef DEFINITE   
+   return -divu + omega * p;
+#else
+   return -divu - omega * p;
+#endif   
+}
+
+double p_exact(const Vector &x)
+{
+   return sin(omega*x.Sum());
+}
+
+void gradp_exact(const Vector &x, Vector &grad)
+{
+   grad.SetSize(x.Size());
+   grad = omega * cos(omega * x.Sum());
+}
+
+void u_exact(const Vector &x, Vector & u)
+{
+   gradp_exact(x,u);
+   u *= 1./omega;
+}
+
+double divu_exact(const Vector &x)
+{
+   return d2_exact(x)/omega;
+}
+
+double d2_exact(const Vector &x)
+{
+   return -dim * omega * omega * sin(omega*x.Sum());
+}
@@ -0,0 +1,546 @@
+//                   MFEM Ultraweak DPG acoustics example
+//
+// Compile with: make uw_dpg
+//
+// ./uw_dpg -m ../../../data/inline-quad.mesh -rnum 40 -theta 0.7 -prob 1 -graph-norm -ref 40 -o 3
+
+//     - Δ p ± ω^2 p = f̃ ,   in Ω
+//                 p = p_0, on ∂Ω
+
+// First Order System
+
+//   ∇ p - ω u = 0, in Ω
+// - ∇⋅u ± ω p = f, in Ω
+//           p = p_0, in ∂Ω
+// where f:=f̃/ω 
+
+// UW-DPG:
+// 
+// p ∈ L^2(Ω), u ∈ (L^2(Ω))^dim 
+// p̂ ∈ H^1/2(Ω), û ∈ H^-1/2(Ω)  
+// -(p,  ∇⋅v) - ω (u , v) + < p̂, v⋅n> = 0,      ∀ v ∈ H(div,Ω)      
+//  (u , ∇ q) ± ω (p , q) + < û, q >  = (f,q)   ∀ q ∈ H^1(Ω)
+//                                  p̂ = p_0     on ∂Ω 
+
+// Note: 
+// p̂ := p on Γ_h (skeleton)
+// û := -u on Γ_h  
+
+// -------------------------------------------------------------
+// |   |     p     |     u     |    p̂      |    û    |  RHS    |
+// -------------------------------------------------------------
+// | v | -(p, ∇⋅v) | - ω (u,v) | < p̂, v⋅n> |         |         |
+// |   |           |           |           |         |         |
+// | q | ± ω (p,q) | (u , ∇ q) |           | < û,q > |  (f,q)  |  
+
+// where (q,v) ∈  H^1(Ω) × H(div,Ω) 
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+// #define DEFINITE
+void acoustics_solution(const Vector & X, double & p, Vector & dp, double & d2p);
+double p_exact(const Vector &x);
+void u_exact(const Vector &x, Vector & u);
+double rhs_func(const Vector &x);
+double divu_exact(const Vector &x);
+double hatp_exact(const Vector & X);
+void hatu_exact(const Vector & X, Vector & hatu);
+
+int dim;
+double omega;
+
+enum prob_type
+{
+   plane_wave,
+   gaussian_beam  
+};
+
+prob_type prob;
+
+int main(int argc, char *argv[])
+{
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   bool visualization = true;
+   double rnum=1.0;
+   int ref = 1;
+   double theta = 0.0;
+   bool adjoint_graph_norm = false;
+   int iprob = 0;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree)");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.AddOption(&rnum, "-rnum", "--number_of_wavelenths",
+                  "Number of wavelengths");      
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");     
+   args.AddOption(&theta, "-theta", "--theta",
+                  "Theta parameter for AMR");    
+   args.AddOption(&iprob, "-prob", "--problem", "Problem case"
+                  " 0: plane wave, 1: Gaussian beam");                                    
+   args.AddOption(&adjoint_graph_norm, "-graph-norm", "--adjoint-graph-norm",
+                  "-no-graph-norm", "--no-adjoint-graph-norm",
+                  "Enable or disable Adjoint Graph Norm on the test space");                                
+   args.AddOption(&ref, "-ref", "--serial_ref",
+                  "Number of serial refinements.");                               
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   if (iprob > 1) { iprob = 0; }
+   prob = (prob_type)iprob;
+
+
+   omega = 2.0 * M_PI * rnum;
+
+
+   Mesh mesh(mesh_file, 1, 1);
+   dim = mesh.Dimension();
+
+
+   // Define spaces
+   // L2 space for p
+   FiniteElementCollection *p_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *p_fes = new FiniteElementSpace(&mesh,p_fec);
+
+   // Vector L2 space for u 
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *u_fes = new FiniteElementSpace(&mesh,u_fec, dim); 
+
+   // H^1/2 space for p̂  
+   FiniteElementCollection * hatp_fec = new H1_Trace_FECollection(order,dim);
+   FiniteElementSpace *hatp_fes = new FiniteElementSpace(&mesh,hatp_fec);
+
+   // H^-1/2 space for û  
+   FiniteElementCollection * hatu_fec = new RT_Trace_FECollection(order-1,dim);   
+   FiniteElementSpace *hatu_fes = new FiniteElementSpace(&mesh,hatu_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * q_fec = new H1_FECollection(test_order, dim);
+   FiniteElementCollection * v_fec = new RT_FECollection(test_order-1, dim);
+
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient zero(0.0);
+   Vector vec0(dim); vec0 = 0.;
+   VectorConstantCoefficient vzero(vec0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient omeg(omega);
+   ConstantCoefficient omeg2(omega*omega);
+   ConstantCoefficient negomeg(-omega);
+
+   // Normal equation weak formulation
+   Array<FiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(p_fes);
+   trial_fes.Append(u_fes);
+   trial_fes.Append(hatp_fes);
+   trial_fes.Append(hatu_fes);
+
+   test_fec.Append(q_fec);
+   test_fec.Append(v_fec);
+
+   NormalEquations * a = new NormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+
+   // ± ω (p,q)
+#ifdef DEFINITE
+   a->AddTrialIntegrator(new MixedScalarMassIntegrator(omeg),0,0);
+#else
+   a->AddTrialIntegrator(new MixedScalarMassIntegrator(negomeg),0,0);
+#endif   
+
+// (u , ∇ q)
+   a->AddTrialIntegrator(new TransposeIntegrator(new GradientIntegrator(one)),1,0);
+
+// -(p, ∇⋅v)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(one),0,1);
+
+// - ω (u,v)
+   a->AddTrialIntegrator(new TransposeIntegrator(new VectorFEMassIntegrator(negomeg)),1,1);
+
+// < p̂, v⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,1);
+
+// < û,q >
+   a->AddTrialIntegrator(new TraceIntegrator,3,0);
+
+
+// test integrators 
+
+   //space-induced norm for H(div) × H1
+   // (∇q,∇δq)
+   a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+   // (q,δq)
+   a->AddTestIntegrator(new MassIntegrator(one),0,0);
+   // (∇⋅v,∇⋅δv)
+   a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+   // (v,δv)
+   a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+
+   // additional integrators for the adjoint graph norm
+   if (adjoint_graph_norm)
+   {   
+      // -ω (∇q,δv)
+      a->AddTestIntegrator(new MixedVectorGradientIntegrator(negomeg),0,1);
+      // -ω (v,δq)
+      a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(omeg),1,0);
+      // ω^2 (v,δv)
+      a->AddTestIntegrator(new VectorFEMassIntegrator(omeg2),1,1);
+
+#ifdef DEFINITE
+      // - ω (∇⋅v,δq)   
+      a->AddTestIntegrator(new VectorFEDivergenceIntegrator(negomeg),1,0);
+      // - ω (q,∇⋅v)   
+      a->AddTestIntegrator(new MixedScalarWeakGradientIntegrator(omeg),0,1);
+#else
+      // ω (∇⋅v,δq)   
+      a->AddTestIntegrator(new VectorFEDivergenceIntegrator(omeg),1,0);
+      // ω (q,∇⋅v)   
+      a->AddTestIntegrator(new MixedScalarWeakGradientIntegrator(negomeg),0,1);
+#endif
+      // ω^2 (q,δq)
+      a->AddTestIntegrator(new MassIntegrator(omeg2),0,0);
+   }
+
+   // RHS
+   FunctionCoefficient f_rhs(rhs_func);
+   a->AddDomainLFIntegrator(new DomainLFIntegrator(f_rhs),0);
+
+
+   FunctionCoefficient hatpex(hatp_exact);
+   FunctionCoefficient pex(p_exact);
+   VectorFunctionCoefficient uex(dim,u_exact);
+   Array<int> elements_to_refine;
+   GridFunction hatp_gf;
+
+
+   socketstream p_out;
+   // socketstream u_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      p_out.open(vishost, visport);
+      // u_out.open(vishost, visport);
+   }
+
+   double res0 = 0.;
+   double err0 = 0.;
+   int dof0;
+   mfem::out << " Refinement |" 
+             << "    Dofs    |" 
+             << "  L2 Error  |" 
+             << " Relative % |" 
+             << "  Rate  |" 
+             << "  Residual  |" 
+             << "  Rate  |" << endl;
+   mfem::out << " --------------------"      
+             <<  "-------------------"    
+             <<  "-------------------"    
+             <<  "-------------------" << endl;   
+
+
+   for (int i = 0; i<ref; i++)
+   {
+      a->Assemble();
+
+      Array<int> ess_tdof_list;
+      Array<int> ess_bdr;
+      if (mesh.bdr_attributes.Size())
+      {
+         ess_bdr.SetSize(mesh.bdr_attributes.Max());
+         ess_bdr = 1;
+         hatp_fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+      }
+
+   // shift the ess_tdofs
+      for (int i = 0; i < ess_tdof_list.Size(); i++)
+      {
+         ess_tdof_list[i] += p_fes->GetTrueVSize() + u_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = p_fes->GetVSize();
+      offsets[2] = u_fes->GetVSize();
+      offsets[3] = hatp_fes->GetVSize();
+      offsets[4] = hatu_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      hatp_gf.MakeRef(hatp_fes,x.GetBlock(2));
+      hatp_gf.ProjectBdrCoefficient(hatpex,ess_bdr);
+
+      OperatorPtr Ah;
+      Vector X,B;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockMatrix * A = Ah.As<BlockMatrix>();
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+      for (int i=0; i<A->NumRowBlocks(); i++)
+      {
+         M->SetDiagonalBlock(i,new UMFPackSolver(A->GetBlock(i,i)));
+      }
+
+      CGSolver cg;
+      cg.SetRelTol(1e-8);
+      cg.SetMaxIter(20000);
+      cg.SetPrintLevel(3);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+
+      elements_to_refine.SetSize(0);
+      double max_resid = residuals.Max();
+      for (int iel = 0; iel<mesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * max_resid)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }
+      
+      GridFunction p_gf;
+      p_gf.MakeRef(p_fes,x.GetBlock(0));
+
+      GridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(1));
+
+      GridFunction pex_gf(p_fes);
+      GridFunction uex_gf(u_fes);
+      pex_gf.ProjectCoefficient(pex);
+      uex_gf.ProjectCoefficient(uex);
+
+
+      // Error
+      int dofs = X.Size();
+      double p_err = p_gf.ComputeL2Error(pex);
+      double p_norm = uex_gf.ComputeL2Error(zero);
+      double u_err = u_gf.ComputeL2Error(uex);
+      double u_norm = u_gf.ComputeL2Error(vzero);
+
+      double L2Error = sqrt(p_err*p_err + u_err*u_err);
+      double L2norm = sqrt(p_norm * p_norm + u_norm * u_norm);
+
+      double rel_error = L2Error/L2norm;
+
+      double rate_err = (i) ? dim*log(err0/L2Error)/log((double)dof0/dofs) : 0.0;
+      double rate_res = (i) ? dim*log(res0/residual)/log((double)dof0/dofs) : 0.0;
+
+      err0 = L2Error;
+      res0 = residual;
+      dof0 = dofs;
+      mfem::out << std::right << std::setw(11) << i << " | " 
+                << std::setw(10) <<  dof0 << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::scientific <<  err0 << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::fixed <<  rel_error * 100. << " | " 
+                << std::setprecision(2) 
+                << std::setw(6) << std::fixed << rate_err << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::scientific <<  res0 << " | " 
+                << std::setprecision(2) 
+                << std::setw(6) << std::fixed << rate_res << " | " 
+                << std::resetiosflags(std::ios::showbase)
+                << std::endl;
+
+      if (visualization)
+      {
+         p_out.precision(8);
+         p_out << "solution\n" << mesh << p_gf <<
+                  "window_title 'Numerical presure' "
+                  << flush;
+
+         // u_out.precision(8);
+         // u_out << "solution\n" << mesh << u_gf <<
+         //       "window_title 'Numerical velocity' "
+         //       << flush;
+      }
+
+      if (i == ref)
+         break;
+
+      mesh.GeneralRefinement(elements_to_refine,1,1);
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+   }
+
+   delete a;
+   delete q_fec;
+   delete v_fec;
+   delete hatp_fes;
+   delete hatp_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete u_fec;
+   delete p_fec;
+   delete u_fes;
+   delete p_fes;
+
+   return 0;
+}
+
+double rhs_func(const Vector &x)
+{
+   double p = p_exact(x);
+   double divu = divu_exact(x);
+   // f = - ∇⋅u ± ω p, 
+#ifdef DEFINITE   
+   return -divu + omega * p;
+#else
+   return -divu - omega * p;
+#endif   
+}
+
+double p_exact(const Vector &x)
+{
+   double p, d2p;
+   Vector dp;
+   acoustics_solution(x,p,dp,d2p);
+   return p;
+}
+
+void u_exact(const Vector &x, Vector & u)
+{
+   double p, d2p;
+   acoustics_solution(x,p,u,d2p);
+   u *= 1./omega;
+}
+
+double divu_exact(const Vector &x)
+{
+   double p, d2p;
+   Vector dp;
+   acoustics_solution(x,p,dp,d2p);
+   return d2p/omega;
+}
+
+double hatp_exact(const Vector & X)
+{
+   return p_exact(X);
+}
+
+void hatu_exact(const Vector & X, Vector & hatu)
+{
+   u_exact(X,hatu);
+   hatu *= -1.;
+}
+
+void acoustics_solution(const Vector & X, double & p, Vector & dp, double & d2p)
+{
+   dp.SetSize(X.Size());
+   switch (prob)
+   {
+   case plane_wave:
+   {
+      p = sin(omega*X.Sum());
+      dp = omega * cos(omega * X.Sum());
+      d2p = -dim * omega * omega * sin(omega*X.Sum());
+   }
+      break;
+   default:
+   {
+      double rk = omega;
+      double alpha = 45 * M_PI/180.;
+      double sina = sin(alpha); 
+      double cosa = cos(alpha);
+      // shift the origin
+      double xprim=X(0) + 0.1; 
+      double yprim=X(1) + 0.1;
+
+      double  x = xprim*sina - yprim*cosa;
+      double  y = xprim*cosa + yprim*sina;
+      double  dxdxprim = sina, dxdyprim = -cosa;
+      double  dydxprim = cosa, dydyprim =  sina;
+      //wavelength
+      double rl = 2.*M_PI/rk;
+
+      // beam waist radius
+      double w0 = 0.05;
+
+      // function w
+      double fact = rl/M_PI/(w0*w0);
+      double aux = 1. + (fact*y)*(fact*y);
+
+      double w = w0*sqrt(aux);
+      double dwdy = w0*fact*fact*y/sqrt(aux);
+      double d2wdydy = w0*fact*fact*(1. - (fact*y)*(fact*y)/aux)/sqrt(aux);
+
+      double phi0 = atan(fact*y);
+      double dphi0dy = cos(phi0)*cos(phi0)*fact;
+      double d2phi0dydy = -2.*cos(phi0)*sin(phi0)*fact*dphi0dy;
+
+      double r = y + 1./y/(fact*fact);
+      double drdy = 1. - 1./(y*y)/(fact*fact);
+      double d2rdydy = 2./(y*y*y)/(fact*fact);
+
+      // pressure
+      complex<double> zi = complex<double>(0., 1.);
+      complex<double> ze = - x*x/(w*w) - zi*rk*y - zi * M_PI * x * x/rl/r + zi*phi0/2.;
+
+      complex<double> zdedx = -2.*x/(w*w) - 2.*zi*M_PI*x/rl/r;
+      complex<double> zdedy = 2.*x*x/(w*w*w)*dwdy - zi*rk + zi*M_PI*x*x/rl/(r*r)*drdy + zi*dphi0dy/2.;
+      complex<double> zd2edxdx = -2./(w*w) - 2.*zi*M_PI/rl/r;
+      complex<double> zd2edxdy = 4.*x/(w*w*w)*dwdy + 2.*zi*M_PI*x/rl/(r*r)*drdy;
+      complex<double> zd2edydx = zd2edxdy;
+      complex<double> zd2edydy = -6.*x*x/(w*w*w*w)*dwdy*dwdy + 2.*x*x/(w*w*w)*d2wdydy - 2.*zi*M_PI*x*x/rl/(r*r*r)*drdy*drdy
+                              + zi*M_PI*x*x/rl/(r*r)*d2rdydy + zi/2.*d2phi0dydy;
+
+      double pf = pow(2.0/M_PI/(w*w),0.25);
+      double dpfdy = -pow(2./M_PI/(w*w),-0.75)/M_PI/(w*w*w)*dwdy;
+      double d2pfdydy = -1./M_PI*pow(2./M_PI,-0.75)*(-1.5*pow(w,-2.5)
+                        *dwdy*dwdy + pow(w,-1.5)*d2wdydy);
+
+
+      complex<double> zp = pf*exp(ze);
+      complex<double> zdpdx = zp*zdedx;
+      complex<double> zdpdy = dpfdy*exp(ze)+zp*zdedy;
+      complex<double> zd2pdxdx = zdpdx*zdedx + zp*zd2edxdx;
+      complex<double> zd2pdxdy = zdpdy*zdedx + zp*zd2edxdy;
+      complex<double> zd2pdydx = dpfdy*exp(ze)*zdedx + zdpdx*zdedy + zp*zd2edydx;
+      complex<double> zd2pdydy = d2pfdydy*exp(ze) + dpfdy*exp(ze)*zdedy + zdpdy*zdedy + zp*zd2edydy;
+
+      p = zp.real();
+      dp[0] = (zdpdx*dxdxprim + zdpdy*dydxprim).real();
+      dp[1] = (zdpdx*dxdyprim + zdpdy*dydyprim).real();
+
+      d2p = (  (zd2pdxdx*dxdxprim + zd2pdydx*dydxprim)*dxdxprim + (zd2pdxdy*dxdxprim + zd2pdydy*dydxprim)*dydxprim
+            + (zd2pdxdx*dxdyprim + zd2pdydx*dydyprim)*dxdyprim + (zd2pdxdy*dxdyprim + zd2pdydy*dydyprim)*dydyprim ).real();
+   }
+   break;
+   }
+
+}
@@ -0,0 +1,507 @@
+//                   MFEM Ultraweak DPG MPI acoustics (Helmholtz) example
+//
+// Compile with: make uw_dpgp
+//
+//     - Δ p ± ω^2 p = f̃ ,   in Ω
+//                 p = p_0, on ∂Ω
+//
+// First Order System
+
+//   ∇ p - ω u = 0, in Ω
+// - ∇⋅u ± ω p = f, in Ω
+//           p = p_0, in ∂Ω
+// where f:=f̃/ω 
+// 
+// UW-DPG:
+// 
+// p ∈ L^2(Ω), u ∈ (L^2(Ω))^dim 
+// p̂ ∈ H^1/2(Ω), û ∈ H^-1/2(Ω)  
+// -(p,  ∇⋅v) - ω (u , v) + < p̂, v⋅n> = 0,      ∀ v ∈ H(div,Ω)      
+//  (u , ∇ q) ± ω (p , q) + < û, q >  = (f,q)   ∀ q ∈ H^1(Ω)
+//                                  p̂ = p_0     on ∂Ω 
+
+// Note: 
+// p̂ := p on Γ_h (skeleton)
+// û := -u on Γ_h  
+
+// -------------------------------------------------------------
+// |   |     p     |     u     |    p̂      |    û    |  RHS    |
+// -------------------------------------------------------------
+// | v | -(p, ∇⋅v) | - ω (u,v) | < p̂, v⋅n> |         |         |
+// |   |           |           |           |         |         |
+// | q | ± ω (p,q) | (u , ∇ q) |           | < û,q > |  (f,q)  |  
+
+// where (q,v) ∈  H^1(Ω) × H(div,Ω) 
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+// #define DEFINITE
+
+double p_exact(const Vector &x);
+void u_exact(const Vector &x, Vector & u);
+double rhs_func(const Vector &x);
+void gradp_exact(const Vector &x, Vector &gradu);
+double divu_exact(const Vector &x);
+double d2_exact(const Vector &x);
+double hatp_exact(const Vector & X);
+void hatu_exact(const Vector & X, Vector & hatu);
+
+int dim;
+double omega;
+
+int main(int argc, char *argv[])
+{
+   MPI_Session mpi;
+   int num_procs = mpi.WorldSize();
+   int myid = mpi.WorldRank();
+
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   bool visualization = true;
+   double rnum=1.0;
+   int ref = 1;
+   double theta = 0.0;
+   bool adjoint_graph_norm = false;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree)");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.AddOption(&rnum, "-rnum", "--number_of_wavelenths",
+                  "Number of wavelengths");      
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");     
+   args.AddOption(&theta, "-theta", "--theta",
+                  "Theta parameter for AMR");                    
+   args.AddOption(&adjoint_graph_norm, "-graph-norm", "--adjoint-graph-norm",
+                  "-no-graph-norm", "--no-adjoint-graph-norm",
+                  "Enable or disable Adjoint Graph Norm on the test space");                                
+   args.AddOption(&ref, "-ref", "--serial_ref",
+                  "Number of serial refinements.");  
+   args.Parse();
+   if (!args.Good())
+   {
+      if (myid == 0)
+      {
+         args.PrintUsage(cout);
+      }
+      return 1;
+   }
+   if (myid == 0)
+   {
+      args.PrintOptions(cout);
+   }
+
+   omega = 2.0 * M_PI * rnum;
+
+   Mesh mesh(mesh_file, 1, 1);
+   dim = mesh.Dimension();
+
+   mesh.EnsureNCMesh();
+
+   ParMesh pmesh(MPI_COMM_WORLD, mesh);
+   mesh.Clear();
+
+   // Define spaces
+   // L2 space for p
+   FiniteElementCollection *p_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *p_fes = new ParFiniteElementSpace(&pmesh,p_fec);
+
+   // Vector L2 space for u 
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *u_fes = new ParFiniteElementSpace(&pmesh,u_fec, dim); 
+
+   // H^1/2 space for p̂  
+   FiniteElementCollection * hatp_fec = new H1_Trace_FECollection(order,dim);
+   ParFiniteElementSpace *hatp_fes = new ParFiniteElementSpace(&pmesh,hatp_fec);
+
+   // H^-1/2 space for û  
+   FiniteElementCollection * hatu_fec = new RT_Trace_FECollection(order-1,dim);   
+   ParFiniteElementSpace *hatu_fes = new ParFiniteElementSpace(&pmesh,hatu_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * q_fec = new H1_FECollection(test_order, dim);
+   FiniteElementCollection * v_fec = new RT_FECollection(test_order-1, dim);
+
+
+   Array<ParFiniteElementSpace * > trial_fes; 
+   trial_fes.Append(p_fes);
+   trial_fes.Append(u_fes);
+   trial_fes.Append(hatp_fes);
+   trial_fes.Append(hatu_fes);
+
+   Array<FiniteElementCollection * > test_fec; 
+   test_fec.Append(q_fec);
+   test_fec.Append(v_fec);
+
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient zero(0.0);
+   Vector vec0(dim); vec0 = 0.;
+   VectorConstantCoefficient vzero(vec0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient omeg(omega);
+   ConstantCoefficient omeg2(omega*omega);
+   ConstantCoefficient negomeg(-omega);
+
+   ParNormalEquations * a = new ParNormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+
+   // Integrators
+
+   // ± ω (p,q)
+#ifdef DEFINITE
+   a->AddTrialIntegrator(new MixedScalarMassIntegrator(omeg),0,0);
+#else
+   a->AddTrialIntegrator(new MixedScalarMassIntegrator(negomeg),0,0);
+#endif   
+
+// (u , ∇ q)
+   a->AddTrialIntegrator(new TransposeIntegrator(new GradientIntegrator(one)),1,0);
+
+// -(p, ∇⋅v)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(one),0,1);
+
+// - ω (u,v)
+   a->AddTrialIntegrator(new TransposeIntegrator(new VectorFEMassIntegrator(negomeg)),1,1);
+
+// < p̂, v⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,1);
+
+// < û,q >
+   a->AddTrialIntegrator(new TraceIntegrator,3,0);
+
+
+   // test integrators 
+
+   //space-induced norm for H(div) × H1
+   // (∇q,∇δq)
+   a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+   // (q,δq)
+   a->AddTestIntegrator(new MassIntegrator(one),0,0);
+   // (∇⋅v,∇⋅δv)
+   a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+   // (v,δv)
+   a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+
+   // additional integrators for the adjoint graph norm
+   if (adjoint_graph_norm)
+   {   
+      // -ω (∇q,δv)
+      a->AddTestIntegrator(new MixedVectorGradientIntegrator(negomeg),0,1);
+      // -ω (v,δq)
+      a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(omeg),1,0);
+      // ω^2 (v,δv)
+      a->AddTestIntegrator(new VectorFEMassIntegrator(omeg2),1,1);
+
+#ifdef DEFINITE
+      // - ω (∇⋅v,δq)   
+      a->AddTestIntegrator(new VectorFEDivergenceIntegrator(negomeg),1,0);
+      // - ω (q,∇⋅v)   
+      a->AddTestIntegrator(new MixedScalarWeakGradientIntegrator(omeg),0,1);
+#else
+      // ω (∇⋅v,δq)   
+      a->AddTestIntegrator(new VectorFEDivergenceIntegrator(omeg),1,0);
+      // ω (q,∇⋅v)   
+      a->AddTestIntegrator(new MixedScalarWeakGradientIntegrator(negomeg),0,1);
+#endif
+      // ω^2 (q,δq)
+      a->AddTestIntegrator(new MassIntegrator(omeg2),0,0);
+   }   
+
+   // RHS
+   FunctionCoefficient f_rhs(rhs_func);
+   a->AddDomainLFIntegrator(new DomainLFIntegrator(f_rhs),0);
+
+
+   FunctionCoefficient hatpex(hatp_exact);
+   FunctionCoefficient pex(p_exact);
+   VectorFunctionCoefficient uex(dim,u_exact);
+   Array<int> elements_to_refine;
+   ParGridFunction hatp_gf;
+
+
+
+
+   socketstream p_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      p_out.open(vishost, visport);
+   }
+   double res0 = 0.;
+   double err0 = 0.;
+   int dof0;
+   if (myid == 0)
+   {
+      mfem::out << " Refinement |" 
+               << "    Dofs    |" 
+               << "  L2 Error  |" 
+               << " Relative % |" 
+               << "  Rate  |" 
+               << "  Residual  |" 
+               << "  Rate  |" << endl;
+      mfem::out << " --------------------"      
+               <<  "-------------------"    
+               <<  "-------------------"    
+               <<  "-------------------" << endl;   
+   }
+
+
+   for (int i = 0; i<ref; i++)
+   {
+      a->Assemble();
+
+      Array<int> ess_tdof_list;
+      Array<int> ess_bdr;
+      if (pmesh.bdr_attributes.Size())
+      {
+         ess_bdr.SetSize(pmesh.bdr_attributes.Max());
+         ess_bdr = 1;
+         hatp_fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+      }
+
+      // shift the ess_tdofs
+      for (int i = 0; i < ess_tdof_list.Size(); i++)
+      {
+         ess_tdof_list[i] += p_fes->GetTrueVSize() + u_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = p_fes->GetVSize();
+      offsets[2] = u_fes->GetVSize();
+      offsets[3] = hatp_fes->GetVSize();
+      offsets[4] = hatu_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      hatp_gf.MakeRef(hatp_fes,x.GetBlock(2));
+      hatp_gf.ProjectBdrCoefficient(hatpex,ess_bdr);
+
+      Vector X,B;
+      OperatorPtr Ah;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockOperator * A = Ah.As<BlockOperator>();
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+
+      HypreBoomerAMG * amg0 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(0,0));
+      HypreBoomerAMG * amg1 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(1,1));
+      HypreBoomerAMG * amg2 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(2,2));
+      amg0->SetPrintLevel(0);
+      amg1->SetPrintLevel(0);
+      amg2->SetPrintLevel(0);
+      amg0->SetRelaxType(16);
+      amg1->SetRelaxType(16);
+      amg2->SetRelaxType(16);
+
+      M->SetDiagonalBlock(0,amg0);
+      M->SetDiagonalBlock(1,amg1);
+      M->SetDiagonalBlock(2,amg2);
+      // for (int i = 0; i < 3; i++)
+      // {
+      //    MUMPSSolver * mumps = new MUMPSSolver;
+      //    mumps->SetOperator(A->GetBlock(i,i));
+      //    M->SetDiagonalBlock(i,mumps);
+      // }
+
+      HypreSolver * prec;
+      if (dim == 2)
+      {
+         prec = new HypreAMS((HypreParMatrix &)A->GetBlock(3,3), hatu_fes);
+      }
+      else
+      {
+         prec = new HypreADS((HypreParMatrix &)A->GetBlock(3,3), hatu_fes);
+      }
+      M->SetDiagonalBlock(3,prec);
+
+      CGSolver cg(MPI_COMM_WORLD);
+      cg.SetRelTol(1e-10);
+      cg.SetMaxIter(20000);
+      cg.SetPrintLevel(-1);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+      
+      double maxresidual = residuals.Max(); 
+      double globalresidual = residual * residual; 
+
+      MPI_Allreduce(MPI_IN_PLACE,&maxresidual,1,MPI_DOUBLE,MPI_MAX,MPI_COMM_WORLD);
+      MPI_Allreduce(MPI_IN_PLACE,&globalresidual,1,MPI_DOUBLE,MPI_SUM,MPI_COMM_WORLD);
+
+      globalresidual = sqrt(globalresidual);
+
+
+      elements_to_refine.SetSize(0);
+      for (int iel = 0; iel<pmesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * maxresidual)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }
+
+
+      ParGridFunction p_gf;
+      p_gf.MakeRef(p_fes,x.GetBlock(0));
+
+      ParGridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(1));
+
+
+      ParGridFunction pex_gf(p_fes);
+      ParGridFunction uex_gf(u_fes);
+      pex_gf.ProjectCoefficient(pex);
+      uex_gf.ProjectCoefficient(uex);
+
+      int dofs = p_fes->GlobalTrueVSize()
+               + u_fes->GlobalTrueVSize()
+               + hatp_fes->GlobalTrueVSize()
+               + hatu_fes->GlobalTrueVSize();
+
+      double p_err = p_gf.ComputeL2Error(pex);
+      double p_norm = pex_gf.ComputeL2Error(zero);
+      double u_err = u_gf.ComputeL2Error(uex);
+      double u_norm = uex_gf.ComputeL2Error(vzero);
+
+      double L2Error = sqrt(p_err*p_err + u_err*u_err);
+      double L2norm = sqrt(p_norm * p_norm + u_norm * u_norm);
+
+      double rel_error = L2Error/L2norm;
+
+      double rate_err = (i) ? dim*log(err0/L2Error)/log((double)dof0/dofs) : 0.0;
+      double rate_res = (i) ? dim*log(res0/globalresidual)/log((double)dof0/dofs) : 0.0;
+
+      err0 = L2Error;
+      res0 = globalresidual;
+      dof0 = dofs;
+
+         std::ios oldState(nullptr);
+      if (myid == 0)
+      {
+         mfem::out << std::right << std::setw(11) << i << " | " 
+                   << std::setw(10) <<  dof0 << " | " 
+                   << std::setprecision(3) 
+                   << std::setw(10) << std::scientific <<  err0 << " | " 
+                   << std::setprecision(3) 
+                   << std::setw(10) << std::fixed <<  rel_error * 100. << " | " 
+                   << std::setprecision(2) 
+                   << std::setw(6) << std::fixed << rate_err << " | " 
+                   << std::setprecision(3) 
+                   << std::setw(10) << std::scientific <<  res0 << " | " 
+                   << std::setprecision(2) 
+                   << std::setw(6) << std::fixed << rate_res << " | " 
+                   << std::setprecision(5) 
+                   << std::scientific 
+                   << std::endl;
+      }   
+
+      if (visualization)
+      {
+         p_out << "parallel " << num_procs << " " << myid << "\n";
+         p_out.precision(8);
+         p_out << "solution\n" << pmesh << p_gf <<
+                  "window_title 'Numerical pressure' "
+                  << flush;
+      }
+
+      if (i == ref)
+         break;
+
+      pmesh.GeneralRefinement(elements_to_refine,1,1);
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+
+   }
+
+   delete a;
+   delete q_fec;
+   delete v_fec;
+   delete hatp_fes;
+   delete hatp_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete u_fec;
+   delete p_fec;
+   delete u_fes;
+   delete p_fes;
+
+   return 0;
+}
+
+double rhs_func(const Vector &x)
+{
+   double p = p_exact(x);
+   double divu = divu_exact(x);
+   // f = - ∇⋅u ± ω p, 
+#ifdef DEFINITE   
+   return -divu + omega * p;
+#else
+   return -divu - omega * p;
+#endif   
+}
+
+double p_exact(const Vector &x)
+{
+   return sin(omega*x.Sum());
+}
+
+void gradp_exact(const Vector &x, Vector &grad)
+{
+   grad.SetSize(x.Size());
+   grad = omega * cos(omega * x.Sum());
+}
+
+void u_exact(const Vector &x, Vector & u)
+{
+   gradp_exact(x,u);
+   u *= 1./omega;
+}
+
+double divu_exact(const Vector &x)
+{
+   return d2_exact(x)/omega;
+}
+
+double d2_exact(const Vector &x)
+{
+   return -dim * omega * omega * sin(omega*x.Sum());
+}
+
+double hatp_exact(const Vector & X)
+{
+   return p_exact(X);
+}
+
+void hatu_exact(const Vector & X, Vector & hatu)
+{
+   u_exact(X,hatu);
+   hatu *= -1.;
+}
@@ -0,0 +1,59 @@
+# Copyright (c) 2010-2022, 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.
+
+# Use the MFEM build directory
+MFEM_DIR ?= ../../..
+MFEM_BUILD_DIR ?= ../../..
+SRC = $(if $(MFEM_DIR:../../..=),$(MFEM_DIR)/examples/dpg_tests/convection-diffusion,)
+CONFIG_MK = $(MFEM_BUILD_DIR)/config/config.mk
+
+MFEM_LIB_FILE = mfem_is_not_built
+-include $(CONFIG_MK)
+
+SEQ_EXAMPLES = uw_dpg
+PAR_EXAMPLES = uw_dpgp
+
+ifeq ($(MFEM_USE_MPI),NO)
+   EXAMPLES = $(SEQ_EXAMPLES)
+else
+   EXAMPLES = $(PAR_EXAMPLES) $(SEQ_EXAMPLES)
+endif
+
+.SUFFIXES:
+.SUFFIXES: .o .cpp .mk
+.PHONY: all clean clean-build clean-exec
+
+# Remove built-in rule
+%: %.cpp
+
+# Replace the default implicit rule for *.cpp files
+%: $(SRC)%.cpp $(MFEM_LIB_FILE) $(CONFIG_MK)
+	$(MFEM_CXX) $(MFEM_FLAGS) $< -o $@ $(MFEM_LIBS)
+
+all: $(EXAMPLES) 
+
+MFEM_TESTS = EXAMPLES
+include $(MFEM_TEST_MK)
+
+# Testing: Parallel vs. serial runs
+RUN_MPI = $(MFEM_MPIEXEC) $(MFEM_MPIEXEC_NP) $(MFEM_MPI_NP)
+%-test-par: %
+	@$(call mfem-test,$<, $(RUN_MPI), Parallel example)
+%-test-seq: %
+	@$(call mfem-test,$<,, Serial example)
+
+clean: clean-build clean-exec 
+
+clean-build:
+	rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
+	rm -rf *.dSYM *.TVD.*breakpoints
+
+clean-exec:
@@ -0,0 +1,649 @@
+//                     MFEM Ultraweak DPG example
+//
+// Compile with: make uw_dpg
+//
+// sample runs 
+// ./uw_dpg  -m ../../../data/inline-quad.mesh -o 3 -ref 10 -test-norm 2 -do 1 -prob 1 -eps 1e-4
+//     - εΔu + ∇⋅(βu) = f,   in Ω
+//                  u = u_0, on ∂Ω
+
+// First Order System
+
+//     - ∇⋅σ + ∇⋅(βu) = f,   in Ω
+//        1/ε σ - ∇u  = 0,   in Ω
+//                  u = u_0, on ∂Ω
+
+// UW-DPG:
+// 
+// u ∈ L^2(Ω), σ ∈ (L^2(Ω))^dim 
+// û ∈ H^1/2, σ̂ ∈ H^-1/2  
+// -(βu , ∇v)  + (σ , ∇v)     + < f̂ ,  v  > = (f,v),   ∀ v ∈ H^1(Ω)      
+//   (u , ∇⋅τ) + 1/ε (σ , τ)  + < û , τ⋅n > = 0,       ∀ τ ∈ H(div,Ω)
+//                                        û = u_0  on ∂Ω 
+
+// Note: 
+// f̂ := βu - σ
+// û := -u
+
+// -------------------------------------------------------------
+// |   |     u     |     σ     |   û       |     f̂    |  RHS    |
+// -------------------------------------------------------------
+// | v |-(βu , ∇v) | (σ , ∇v)  |           | < f̂ ,v > |  (f,v)  |
+// |   |           |           |           |          |         |
+// | τ | (u ,∇⋅τ)  | 1/ε(σ , τ)|  <û,τ⋅n>  |          |    0    |  
+
+// where (v,τ) ∈  H^1(Ω_h) × H(div,Ω_h)  
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+enum prob_type
+{
+   polynomial,
+   EJ,   
+   general  
+};
+
+enum test_norm_type
+{
+   standard,   
+   adjoint_graph,
+   robust  
+};
+
+prob_type prob;
+test_norm_type test_norm;
+Vector beta;
+double epsilon;
+// Function returns the solution u, and gradient du and the Laplacian d2u
+void solution(const Vector & x, double & u, Vector & du, double & d2u);
+double exact_u(const Vector & X);
+void exact_sigma(const Vector & X, Vector & sigma);
+double exact_hatu(const Vector & X);
+void exact_hatf(const Vector & X, Vector & hatf);
+double f_exact(const Vector & X);
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   int ref = 1;
+   bool visualization = true;
+   int iprob = 0;
+   int itest_norm = 0;
+   double theta = 0.7;
+   epsilon = 1e0;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree).");
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");
+   args.AddOption(&epsilon, "-eps", "--epsilon",
+                  "Epsilon coefficient");               
+   args.AddOption(&ref, "-ref", "--num_refinements",
+                  "Number of uniform refinements");        
+   args.AddOption(&theta, "-theta", "--theta",
+                  "Theta parameter for AMR");                             
+   args.AddOption(&iprob, "-prob", "--problem", "Problem case"
+                  " 0: polynomial, 1: EJ ,2: General");           
+   args.AddOption(&itest_norm, "-test-norm", "--test-norm", "Choice of test norm"
+                  " 0: Standard, 1: Adjoint Graph, 2: Robust");       
+   args.AddOption(&beta, "-beta", "--beta",
+                  "Vector Coefficient beta");                                              
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   if (iprob > 2) { iprob = 2; }
+   prob = (prob_type)iprob;
+   test_norm = (test_norm_type)itest_norm;
+
+   if (prob == prob_type::EJ)
+   {
+      mesh_file = "../../../data/inline-quad.mesh";
+   }
+
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   if (beta.Size() == 0)
+   {
+      beta.SetSize(dim);
+      beta[0] = 1.;
+      beta[1] = 0.;
+   }
+
+   // Define spaces
+   // L2 space for u
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *u_fes = new FiniteElementSpace(&mesh,u_fec);
+
+   // Vector L2 space for σ 
+   FiniteElementCollection *sigma_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *sigma_fes = new FiniteElementSpace(&mesh,sigma_fec, dim); 
+
+   // H^1/2 space for û 
+   FiniteElementCollection * hatu_fec = new H1_Trace_FECollection(order,dim);
+   FiniteElementSpace *hatu_fes = new FiniteElementSpace(&mesh,hatu_fec);
+
+   // H^-1/2 space for σ̂ 
+   FiniteElementCollection * hatf_fec = new RT_Trace_FECollection(order-1,dim);   
+   FiniteElementSpace *hatf_fes = new FiniteElementSpace(&mesh,hatf_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * v_fec = new H1_FECollection(test_order, dim);
+   FiniteElementCollection * tau_fec = new RT_FECollection(test_order-1, dim);
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient eps(epsilon);
+   ConstantCoefficient eps1(1./epsilon);
+   ConstantCoefficient negeps1(-1./epsilon);
+   ConstantCoefficient eps2(1/(epsilon*epsilon));
+
+   ConstantCoefficient negeps(-epsilon);
+   VectorConstantCoefficient betacoeff(beta);
+   Vector negbeta = beta;
+   negbeta.Neg();
+
+   ConstantCoefficient zero(0.0);
+   Vector vec0(dim); vec0 = 0.;
+   VectorConstantCoefficient vzero(vec0);
+
+
+   DenseMatrix bbt(beta.Size());
+   MultVVt(beta, bbt); 
+   MatrixConstantCoefficient bbtcoeff(bbt);
+
+
+   VectorConstantCoefficient negbetacoeff(negbeta);
+   // Normal equation weak formulation
+   Array<FiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(u_fes);
+   trial_fes.Append(sigma_fes);
+   trial_fes.Append(hatu_fes);
+   trial_fes.Append(hatf_fes);
+   test_fec.Append(v_fec);
+   test_fec.Append(tau_fec);
+
+
+   FiniteElementCollection *coeff_fec = new L2_FECollection(0,dim);
+   FiniteElementSpace *coeff_fes = new FiniteElementSpace(&mesh,coeff_fec);
+   GridFunction c1_gf, c2_gf;
+   GridFunctionCoefficient c1_coeff(&c1_gf);
+   GridFunctionCoefficient c2_coeff(&c2_gf);
+
+
+   NormalEquations * a = new NormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+   //-(βu , ∇v)
+   a->AddTrialIntegrator(new MixedScalarWeakDivergenceIntegrator(betacoeff),0,0);
+   
+   // (σ,∇ v)
+   a->AddTrialIntegrator(new TransposeIntegrator(new GradientIntegrator(one)),1,0);
+
+   // (u ,∇⋅τ)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(negone),0,1);
+
+   // 1/ε (σ,τ)
+   a->AddTrialIntegrator(new TransposeIntegrator(new VectorFEMassIntegrator(eps1)),1,1);
+
+   //  <û,τ⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,1);
+
+   // <f̂ ,v> 
+   a->AddTrialIntegrator(new TraceIntegrator,3,0);
+
+
+   switch (test_norm)
+   {
+      case standard:
+      {   
+         // (∇v,∇δv)
+         mfem::out << "\n Test norm: Standard" << endl;
+         a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+         // (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(one),0,0);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+         // (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+      }
+      break;
+      case adjoint_graph:
+      {
+         mfem::out << "\n Test norm: Adjoint Graph" << endl;
+         // (∇v,∇δv)
+         a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+         // (β⋅∇v, β⋅∇δv)   
+         a->AddTestIntegrator(new DiffusionIntegrator(bbtcoeff), 0,0);
+         // (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(one),0,0);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+         // (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+         // 1/ε^2 (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(eps2),1,1);
+         // 1/ε (∇v, δτ)
+         a->AddTestIntegrator(new MixedVectorGradientIntegrator(eps1),0,1);
+         // - (β ⋅ ∇v,∇⋅δτ)  
+         a->AddTestIntegrator(new MixedGradDivIntegrator(betacoeff),0,1);
+         // 1/ε (τ,∇δv) 
+         a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(negeps1),1,0);
+         // -(β ∇⋅τ ,∇⋅δv)  
+         a->AddTestIntegrator(new MixedDivGradIntegrator(betacoeff),1,0);
+      }
+      break;
+      default:
+      {
+         mfem::out << "\n Test norm: Robust" << endl;
+         c1_gf.SetSpace(coeff_fes);
+         c2_gf.SetSpace(coeff_fes);
+         Array<int> dofs;
+         for (int i =0; i < mesh.GetNE(); i++)
+         {
+            double volume = mesh.GetElementVolume(i);
+            double c1 = min(epsilon/volume, 1.);
+            double c2 = min(1./epsilon, 1./volume);
+            // double c2 = 1.;
+            coeff_fes->GetElementDofs(i,dofs);
+            c1_gf.SetSubVector(dofs,c1);
+            c2_gf.SetSubVector(dofs,c2);
+         }
+         // c1 (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(c1_coeff),0,0);
+         // ε (∇v,∇δv)
+         a->AddTestIntegrator(new DiffusionIntegrator(eps),0,0);
+         // (β⋅∇v, β⋅∇δv)   
+         a->AddTestIntegrator(new DiffusionIntegrator(bbtcoeff), 0,0);
+         // c2 (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(c2_coeff),1,1);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+      }
+      break;
+   }
+
+
+   FunctionCoefficient f(f_exact);
+   // if (prob != prob_type::EJ)
+   // {
+      a->AddDomainLFIntegrator(new DomainLFIntegrator(f),0);
+   // }
+
+   FunctionCoefficient hatuex(exact_hatu);
+   VectorFunctionCoefficient hatfex(dim,exact_hatf);
+   Array<int> elements_to_refine;
+   FunctionCoefficient uex(exact_u);
+   VectorFunctionCoefficient sigmaex(dim,exact_sigma);
+   GridFunction hatu_gf;
+   GridFunction hatf_gf;
+
+   // socketstream uex_out;
+   socketstream u_out;
+   // socketstream sigma_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      u_out.open(vishost, visport);
+      // uex_out.open(vishost, visport);
+      // sigma_out.open(vishost, visport);
+   }
+
+   double res0 = 0.;
+   double err0 = 0.;
+   int dof0;
+   mfem::out << " Refinement |" 
+             << "    Dofs    |" 
+             << "  L2 Error  |" 
+             << " Relative % |" 
+             << "  Rate  |" 
+             << "  Residual  |" 
+             << "  Rate  |" << endl;
+   mfem::out << " --------------------"      
+             <<  "-------------------"    
+             <<  "-------------------"    
+             <<  "-------------------" << endl;   
+
+
+   for (int i = 0; i<=ref; i++)
+   {
+      a->Assemble();
+
+      Array<int> ess_tdof_list_uhat;
+      Array<int> ess_tdof_list_fhat;
+      Array<int> ess_bdr_uhat;
+      Array<int> ess_bdr_fhat;
+      if (mesh.bdr_attributes.Size())
+      {
+         ess_bdr_uhat.SetSize(mesh.bdr_attributes.Max());
+         ess_bdr_fhat.SetSize(mesh.bdr_attributes.Max());
+         // ess_bdr_uhat = 1;
+         // ess_bdr_fhat = 0;
+         ess_bdr_uhat = 0;
+         ess_bdr_fhat = 1;
+         ess_bdr_uhat[1] = 1;
+         ess_bdr_fhat[1] = 0;
+         hatu_fes->GetEssentialTrueDofs(ess_bdr_uhat, ess_tdof_list_uhat);
+         hatf_fes->GetEssentialTrueDofs(ess_bdr_fhat, ess_tdof_list_fhat);
+      }
+
+      // shift the ess_tdofs
+      int n = ess_tdof_list_uhat.Size();
+      int m = ess_tdof_list_fhat.Size();
+      Array<int> ess_tdof_list(n+m);
+      for (int i = 0; i < n; i++)
+      {
+         ess_tdof_list[i] = ess_tdof_list_uhat[i] 
+                          + u_fes->GetTrueVSize() 
+                          + sigma_fes->GetTrueVSize();
+      }
+      for (int i = 0; i < m; i++)
+      {
+         ess_tdof_list[i+n] = ess_tdof_list_fhat[i] 
+                            + u_fes->GetTrueVSize() 
+                            + sigma_fes->GetTrueVSize()
+                            + hatu_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = u_fes->GetVSize();
+      offsets[2] = sigma_fes->GetVSize();
+      offsets[3] = hatu_fes->GetVSize();
+      offsets[4] = hatf_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      hatu_gf.MakeRef(hatu_fes,x.GetBlock(2));
+
+      hatf_gf.MakeRef(hatf_fes,x.GetBlock(3));
+
+      hatu_gf.ProjectBdrCoefficient(hatuex,ess_bdr_uhat);
+      hatf_gf.ProjectBdrCoefficientNormal(hatfex,ess_bdr_fhat);
+
+      OperatorPtr Ah;
+      Vector X,B;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockMatrix * A = Ah.As<BlockMatrix>();
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+      for (int i=0; i<A->NumRowBlocks(); i++)
+      {
+         M->SetDiagonalBlock(i,new UMFPackSolver(A->GetBlock(i,i)));
+      }
+
+      CGSolver cg;
+      cg.SetRelTol(1e-12);
+      cg.SetMaxIter(200000);
+      cg.SetPrintLevel(0);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+
+      elements_to_refine.SetSize(0);
+      double max_resid = residuals.Max();
+      for (int iel = 0; iel<mesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * max_resid)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }   
+
+      GridFunction uex_gf(u_fes);
+      uex_gf.ProjectCoefficient(uex);
+
+      GridFunction sigmaex_gf(sigma_fes);
+      sigmaex_gf.ProjectCoefficient(sigmaex);
+
+      GridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(0));
+
+      GridFunction sigma_gf;
+      sigma_gf.MakeRef(sigma_fes,x.GetBlock(1));
+
+      int dofs = X.Size();
+      double u_err = u_gf.ComputeL2Error(uex);
+      double u_norm = uex_gf.ComputeL2Error(zero);
+      // mfem::out << "u_err = " << u_err << endl;
+      double sigma_err = sigma_gf.ComputeL2Error(sigmaex);
+      double sigma_norm = sigmaex_gf.ComputeL2Error(vzero);
+      // mfem::out << "sigma_err = " << sigma_err << endl;
+      double L2Error = sqrt(u_err*u_err + sigma_err*sigma_err);
+      double L2norm = sqrt(u_norm * u_norm + sigma_norm * sigma_norm);
+
+      double rel_error = L2Error/L2norm;
+
+      double rate_err = (i) ? dim*log(err0/L2Error)/log((double)dof0/dofs) : 0.0;
+      double rate_res = (i) ? dim*log(res0/residual)/log((double)dof0/dofs) : 0.0;
+
+      err0 = L2Error;
+      res0 = residual;
+      dof0 = dofs;
+      mfem::out << std::right << std::setw(11) << i << " | " 
+                << std::setw(10) <<  dof0 << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::scientific <<  err0 << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::fixed <<  rel_error * 100. << " | " 
+                << std::setprecision(2) 
+                << std::setw(6) << std::fixed << rate_err << " | " 
+                << std::setprecision(3) 
+                << std::setw(10) << std::scientific <<  res0 << " | " 
+                << std::setprecision(2) 
+                << std::setw(6) << std::fixed << rate_res << " | " 
+                << std::resetiosflags(std::ios::showbase)
+                << std::endl;
+
+
+      if (visualization)
+      {
+         // uex_out.precision(8);
+         // uex_out << "solution\n" << mesh << uex_gf <<
+         //          "window_title 'Exact u' "
+         //          << flush;
+         u_out.precision(8);
+         u_out << "solution\n" << mesh << u_gf <<
+                  "window_title 'Numerical u' "
+                  << flush;
+         // sigma_out.precision(8);
+         // sigma_out << "solution\n" << mesh << sigma_gf <<
+         //       "window_title 'Numerical flux' "
+         //       << flush;
+      }
+
+      if (i == ref)
+         break;
+
+      mesh.GeneralRefinement(elements_to_refine,1,1);
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+
+      if (test_norm == test_norm_type::robust)
+      {
+         coeff_fes->Update();
+         c1_gf.Update();
+         c2_gf.Update();
+         Array<int> dofs;
+         for (int i = 0; i < mesh.GetNE(); i++)
+         {
+            double volume = mesh.GetElementVolume(i);
+            double c1 = min(epsilon/volume, 1.);
+            double c2 = min(1./epsilon, 1./volume);
+            // double c2 = 1.;
+            coeff_fes->GetElementDofs(i,dofs);
+            c1_gf.SetSubVector(dofs,c1);
+            c2_gf.SetSubVector(dofs,c2);
+         }
+      }
+
+   }
+
+   delete a;
+   delete tau_fec;
+   delete v_fec;
+   delete hatf_fes;
+   delete hatf_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete sigma_fec;
+   delete u_fec;
+   delete u_fes;
+
+   return 0;
+}
+
+
+void solution(const Vector & X, double & u, Vector & du, double & d2u)
+{
+   double x = X[0];
+   double y = X[1];
+   double z = 0.;
+   if (X.Size() == 3) z = X[2];
+   du.SetSize(X.Size());
+   du = 0.;
+   d2u = 0.;
+
+   switch(prob)
+   {
+      case polynomial:
+      {
+         int n=2;
+         int m=2;
+         u = pow(x,n)*pow(y,m);
+         du[0] = n * pow(x,n-1) * pow(y,m);
+         du[1] = m * pow(x,n) * pow(y,m-1);
+         d2u = n * (n-1) * pow(x,n-2) * pow(y,m)
+             + m * (m-1) * pow(x,n) * pow(y,m-2);
+      }
+      break;
+      case EJ:
+      {
+         double alpha = sqrt(1. + 4. * epsilon * epsilon * M_PI * M_PI);
+         double r1 = (1. + alpha) / (2.*epsilon);
+         double r2 = (1. - alpha) / (2.*epsilon);
+         double denom = exp(-r2) - exp(-r1);
+
+
+         double g1 = exp(r2*(x-1.));
+         double g1_x = r2*g1;
+         double g1_xx = r2*g1_x;
+         double g2 = exp(r1*(x-1.));
+         double g2_x = r1*g2;
+         double g2_xx = r1*g2_x;
+         double g = g1-g2;
+         double g_x = g1_x - g2_x;
+         double g_xx = g1_xx - g2_xx;
+
+
+         u = g * cos(M_PI * y)/denom;
+         double u_x = g_x * cos(M_PI * y)/denom;
+         double u_xx = g_xx * cos(M_PI * y)/denom;
+         double u_y = -M_PI * g * sin(M_PI*y)/denom;
+         double u_yy = -M_PI * M_PI * u;
+         du[0] = u_x;
+         du[1] = u_y;
+         d2u = u_xx + u_yy;
+
+      }
+      break;
+      default:
+      {
+         double alpha = M_PI * (x + y + z);
+         u = sin(alpha);
+         du.SetSize(X.Size());
+         for (int i = 0; i<du.Size(); i++)
+         {
+            du[i] = M_PI * cos(alpha);
+         }
+         d2u = - M_PI*M_PI * u * du.Size();
+      }
+      break;
+   }
+}
+
+
+double exact_u(const Vector & X)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   return u;
+}
+
+void exact_sigma(const Vector & X, Vector & sigma)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   // σ = ε ∇ u
+   sigma = du;
+   sigma *= epsilon;
+}
+
+double exact_hatu(const Vector & X)
+{
+   return -exact_u(X);
+}
+
+void exact_hatf(const Vector & X, Vector & hatf)
+{
+   Vector sigma;
+   exact_sigma(X,sigma);
+   double u = exact_u(X);
+   hatf.SetSize(X.Size());
+   for (int i = 0; i<hatf.Size(); i++)
+   {
+      hatf[i] = beta[i] * u - sigma[i];
+   }
+}
+
+double f_exact(const Vector & X)
+{
+   // f = - εΔu + ∇⋅(βu)
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+
+   double s = 0;
+   for (int i = 0; i<du.Size(); i++)
+   {
+      s += beta[i] * du[i];
+   }
+   return -epsilon * d2u + s;
+}
@@ -0,0 +1,698 @@
+//                                MFEM Ultraweak DPG example
+//
+// Compile with: make  uw_dpgp
+//
+// sample runs 
+// mpirun -np 6 ./uw_dpgp  -m ../../../data/inline-quad.mesh -o 3 -ref 10 -test-norm 2 -do 1 -prob 1 -eps 1e-4
+//     - εΔu + ∇⋅(βu) = f,   in Ω
+//                  u = u_0, on ∂Ω
+
+// First Order System
+
+//     - ∇⋅σ + ∇⋅(βu) = f,   in Ω
+//        1/ε σ - ∇u  = 0,   in Ω
+//                  u = u_0, on ∂Ω
+
+// UW-DPG:
+// 
+// u ∈ L^2(Ω), σ ∈ (L^2(Ω))^dim 
+// û ∈ H^1/2, f̂ ∈ H^-1/2  
+// -(βu , ∇v)  + (σ , ∇v)     + < f̂ ,  v  > = (f,v),   ∀ v ∈ H^1(Ω)      
+//   (u , ∇⋅τ) + 1/ε (σ , τ)  + < û , τ⋅n > = 0,       ∀ τ ∈ H(div,Ω)
+//                                        û = u_0  on ∂Ω 
+
+// Note: 
+// f̂ := βu - σ
+// û := -u
+
+// -------------------------------------------------------------
+// |   |     u     |     σ     |   û       |     f̂    |  RHS    |
+// -------------------------------------------------------------
+// | v |-(βu , ∇v) | (σ , ∇v)  |           | < f̂ ,v > |  (f,v)  |
+// |   |           |           |           |          |         |
+// | τ | (u ,∇⋅τ)  | 1/ε(σ , τ)|  <û,τ⋅n>  |          |    0    |  
+
+// where (v,τ) ∈  H^1(Ω_h) × H(div,Ω_h)  
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+enum prob_type
+{
+   polynomial,
+   EJ,   
+   general  
+};
+
+enum test_norm_type
+{
+   standard,   
+   adjoint_graph,
+   robust  
+};
+
+prob_type prob;
+test_norm_type test_norm;
+Vector beta;
+double epsilon;
+// Function returns the solution u, and gradient du and the Laplacian d2u
+void solution(const Vector & x, double & u, Vector & du, double & d2u);
+double exact_u(const Vector & X);
+void exact_sigma(const Vector & X, Vector & sigma);
+double exact_hatu(const Vector & X);
+void exact_hatf(const Vector & X, Vector & hatf);
+double f_exact(const Vector & X);
+
+
+int main(int argc, char *argv[])
+{
+   MPI_Session mpi;
+   int num_procs = mpi.WorldSize();
+   int myid = mpi.WorldRank();
+
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   int ref = 1;
+   bool visualization = true;
+   int iprob = 0;
+   int itest_norm = 0;
+   double theta = 0.7;
+   bool static_cond = false;
+   epsilon = 1e0;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree).");
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");
+   args.AddOption(&epsilon, "-eps", "--epsilon",
+                  "Epsilon coefficient");               
+   args.AddOption(&ref, "-ref", "--num_refinements",
+                  "Number of uniform refinements");     
+   args.AddOption(&theta, "-theta", "--theta",
+                  "Theta parameter for AMR");                           
+   args.AddOption(&iprob, "-prob", "--problem", "Problem case"
+                  " 0: lshape, 1: General");                         
+   args.AddOption(&itest_norm, "-test-norm", "--test-norm", "Choice of test norm"
+                  " 0: Standard, 1: Adjoint Graph, 2: Robust");     
+   args.AddOption(&beta, "-beta", "--beta",
+                  "Vector Coefficient beta");          
+   args.AddOption(&static_cond, "-sc", "--static-condensation", "-no-sc",
+                  "--no-static-condensation", "Enable static condensation.");                            
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      if (myid == 0)
+      {
+         args.PrintUsage(cout);
+      }
+      return 1;
+   }
+   if (myid == 0)
+   {
+      args.PrintOptions(cout);
+   }
+
+   if (iprob > 2) { iprob = 2; }
+   prob = (prob_type)iprob;
+
+   test_norm = (test_norm_type)itest_norm;
+
+   if (prob == prob_type::EJ)
+   {
+      mesh_file = "../../../data/inline-quad.mesh";
+   }
+
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   if (beta.Size() == 0)
+   {
+      beta.SetSize(dim);
+      beta[0] = 1.;
+      beta[1] = 0.;
+   }
+
+   mesh.EnsureNCMesh();
+
+   ParMesh pmesh(MPI_COMM_WORLD, mesh);
+   mesh.Clear();
+
+   // Define spaces
+   // L2 space for u
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *u_fes = new ParFiniteElementSpace(&pmesh,u_fec);
+
+   // Vector L2 space for σ 
+   FiniteElementCollection *sigma_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *sigma_fes = new ParFiniteElementSpace(&pmesh,sigma_fec, dim); 
+
+   // H^1/2 space for û 
+   FiniteElementCollection * hatu_fec = new H1_Trace_FECollection(order,dim);
+   ParFiniteElementSpace *hatu_fes = new ParFiniteElementSpace(&pmesh,hatu_fec);
+
+   // H^-1/2 space for σ̂ 
+   FiniteElementCollection * hatf_fec = new RT_Trace_FECollection(order-1,dim);   
+   ParFiniteElementSpace *hatf_fes = new ParFiniteElementSpace(&pmesh,hatf_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * v_fec = new H1_FECollection(test_order, dim);
+   FiniteElementCollection * tau_fec = new RT_FECollection(test_order-1, dim);
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+   ConstantCoefficient eps(epsilon);
+   ConstantCoefficient eps1(1./epsilon);
+   ConstantCoefficient negeps1(-1./epsilon);
+   ConstantCoefficient eps2(1/(epsilon*epsilon));
+
+   ConstantCoefficient negeps(-epsilon);
+   VectorConstantCoefficient betacoeff(beta);
+   Vector negbeta = beta;
+   negbeta.Neg();
+
+   DenseMatrix bbt(beta.Size());
+   MultVVt(beta, bbt); 
+   MatrixConstantCoefficient bbtcoeff(bbt);
+
+
+   VectorConstantCoefficient negbetacoeff(negbeta);
+   // Normal equation weak formulation
+   Array<ParFiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(u_fes);
+   trial_fes.Append(sigma_fes);
+   trial_fes.Append(hatu_fes);
+   trial_fes.Append(hatf_fes);
+   test_fec.Append(v_fec);
+   test_fec.Append(tau_fec);
+
+   ParNormalEquations * a = new ParNormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+   //-(βu , ∇v)
+   a->AddTrialIntegrator(new MixedScalarWeakDivergenceIntegrator(betacoeff),0,0);
+   
+   // (σ,∇ v)
+   a->AddTrialIntegrator(new TransposeIntegrator(new GradientIntegrator(one)),1,0);
+
+   // (u ,∇⋅τ)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(negone),0,1);
+
+   // 1/ε (σ,τ)
+   a->AddTrialIntegrator(new TransposeIntegrator(new VectorFEMassIntegrator(eps1)),1,1);
+
+   //  <û,τ⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,1);
+
+   // <f̂ ,v> 
+   a->AddTrialIntegrator(new TraceIntegrator,3,0);
+
+
+   FiniteElementCollection *coeff_fec = new L2_FECollection(0,dim);
+   ParFiniteElementSpace *coeff_fes = new ParFiniteElementSpace(&pmesh,coeff_fec);
+   ParGridFunction c1_gf, c2_gf;
+   GridFunctionCoefficient c1_coeff(&c1_gf);
+   GridFunctionCoefficient c2_coeff(&c2_gf);
+
+   switch (test_norm)
+   {
+      case standard:
+      {   
+         if (myid == 0)
+         {
+            mfem::out << "\n Test norm: Standard" << endl;
+         }
+         // (∇v,∇δv)
+         a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+         // (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(one),0,0);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+         // (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+      }
+      break;
+      case adjoint_graph:
+      {
+         if (myid == 0)
+         {
+            mfem::out << "\n Test norm: Adjoint Graph" << endl;
+         }
+         // (∇v,∇δv)
+         a->AddTestIntegrator(new DiffusionIntegrator(one),0,0);
+         // (β⋅∇v, β⋅∇δv)   
+         a->AddTestIntegrator(new DiffusionIntegrator(bbtcoeff), 0,0);
+         // (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(one),0,0);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+         // (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(one),1,1);
+         // 1/ε^2 (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(eps2),1,1);
+         // 1/ε (∇v, δτ)
+         a->AddTestIntegrator(new MixedVectorGradientIntegrator(eps1),0,1);
+         // - (β ⋅ ∇v,∇⋅δτ)  
+         a->AddTestIntegrator(new MixedGradDivIntegrator(betacoeff),0,1);
+         // 1/ε (τ,∇δv) 
+         a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(negeps1),1,0);
+         // -(β ∇⋅τ ,∇⋅δv)  
+         a->AddTestIntegrator(new MixedDivGradIntegrator(betacoeff),1,0);
+      }
+      break;
+      default:
+      {
+         if (myid == 0)
+         {
+            mfem::out << "\n Test norm: Robust" << endl;
+         }
+         c1_gf.SetSpace(coeff_fes);
+         c2_gf.SetSpace(coeff_fes);
+         Array<int> dofs;
+         for (int i =0; i < pmesh.GetNE(); i++)
+         {
+            double volume = pmesh.GetElementVolume(i);
+            double c1 = min(epsilon/volume, 1.);
+            double c2 = min(1./epsilon, 1./volume);
+            coeff_fes->GetElementDofs(i,dofs);
+            c1_gf.SetSubVector(dofs,c1);
+            c2_gf.SetSubVector(dofs,c2);
+         }
+         // c1 (v,δv)
+         a->AddTestIntegrator(new MassIntegrator(c1_coeff),0,0);
+         // ε (∇v,∇δv)
+         a->AddTestIntegrator(new DiffusionIntegrator(eps),0,0);
+         // (β⋅∇v, β⋅∇δv)   
+         a->AddTestIntegrator(new DiffusionIntegrator(bbtcoeff), 0,0);
+         // c2 (τ,δτ)
+         a->AddTestIntegrator(new VectorFEMassIntegrator(c2_coeff),1,1);
+         // (∇⋅τ,∇⋅δτ)
+         a->AddTestIntegrator(new DivDivIntegrator(one),1,1);
+      }
+      break;
+   }
+
+
+   FunctionCoefficient f(f_exact);
+   // if (prob != prob_type::EJ)
+   // {
+   a->AddDomainLFIntegrator(new DomainLFIntegrator(f),0);
+   // }
+
+   FunctionCoefficient hatuex(exact_hatu);
+   VectorFunctionCoefficient hatfex(dim,exact_hatf);
+   Array<int> elements_to_refine;
+   FunctionCoefficient uex(exact_u);
+   VectorFunctionCoefficient sigmaex(dim,exact_sigma);
+
+   ParGridFunction hatu_gf;
+   ParGridFunction hatf_gf;
+
+   // socketstream uex_out;
+   socketstream u_out;
+   // socketstream sigma_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      u_out.open(vishost, visport);
+      // uex_out.open(vishost, visport);
+      // sigma_out.open(vishost, visport);
+   }
+
+   double res0 = 0.;
+   double err0 = 0.;
+   int dof0;
+   if (myid == 0)
+   {
+      mfem::out << " Refinement |" 
+               << "    Dofs    |" 
+               << "  L2 Error  |" 
+               << "  Rate  |" 
+               << "  Residual  |" 
+               << "  Rate  |" << endl;
+      mfem::out << " --------------------"      
+               <<  "-------------------"    
+               <<  "-------------------"    
+               <<  "-------------------" << endl;   
+   }
+
+
+   for (int i = 0; i<=ref; i++)
+   {
+      if (static_cond) { a->EnableStaticCondensation(); }
+      a->Assemble();
+
+      Array<int> ess_tdof_list_uhat;
+      Array<int> ess_tdof_list_fhat;
+      Array<int> ess_bdr_uhat;
+      Array<int> ess_bdr_fhat;
+      if (pmesh.bdr_attributes.Size())
+      {
+         ess_bdr_uhat.SetSize(pmesh.bdr_attributes.Max());
+         ess_bdr_fhat.SetSize(pmesh.bdr_attributes.Max());
+         // ess_bdr_uhat = 1;
+         // ess_bdr_fhat = 0;
+         ess_bdr_uhat = 0;
+         ess_bdr_fhat = 1;
+         ess_bdr_uhat[1] = 1;
+         ess_bdr_fhat[1] = 0;
+         hatu_fes->GetEssentialTrueDofs(ess_bdr_uhat, ess_tdof_list_uhat);
+         hatf_fes->GetEssentialTrueDofs(ess_bdr_fhat, ess_tdof_list_fhat);
+      }
+
+      // shift the ess_tdofs
+      int n = ess_tdof_list_uhat.Size();
+      int m = ess_tdof_list_fhat.Size();
+      Array<int> ess_tdof_list(n+m);
+      for (int i = 0; i < n; i++)
+      {
+         ess_tdof_list[i] = ess_tdof_list_uhat[i] 
+                          + u_fes->GetTrueVSize() 
+                          + sigma_fes->GetTrueVSize();
+      }
+      for (int i = 0; i < m; i++)
+      {
+         ess_tdof_list[i+n] = ess_tdof_list_fhat[i] 
+                            + u_fes->GetTrueVSize() 
+                            + sigma_fes->GetTrueVSize()
+                            + hatu_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = u_fes->GetVSize();
+      offsets[2] = sigma_fes->GetVSize();
+      offsets[3] = hatu_fes->GetVSize();
+      offsets[4] = hatf_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      hatu_gf.MakeRef(hatu_fes,x.GetBlock(2));
+      hatu_gf.ProjectBdrCoefficient(hatuex,ess_bdr_uhat);
+
+      hatf_gf.MakeRef(hatf_fes,x.GetBlock(3));
+      hatf_gf.ProjectBdrCoefficientNormal(hatfex,ess_bdr_fhat);
+
+      OperatorPtr Ah;
+      Vector X,B;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockOperator * A = Ah.As<BlockOperator>();
+
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+      int skip = 0;
+      if (!static_cond)
+      {
+         HypreBoomerAMG * amg0 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(0,0));
+         HypreBoomerAMG * amg1 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(1,1));
+         amg0->SetPrintLevel(0);
+         amg1->SetPrintLevel(0);
+         M->SetDiagonalBlock(0,amg0);
+         M->SetDiagonalBlock(1,amg1);
+         skip = 2;
+      }
+      HypreBoomerAMG * amg2 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(skip,skip));
+      amg2->SetPrintLevel(0);
+      M->SetDiagonalBlock(skip,amg2);
+
+      HypreSolver * prec;
+      if (dim == 2)
+      {
+         prec = new HypreAMS((HypreParMatrix &)A->GetBlock(skip+1,skip+1), hatf_fes);
+      }
+      else
+      {
+         prec = new HypreADS((HypreParMatrix &)A->GetBlock(skip+1,skip+1), hatf_fes);
+      }
+      M->SetDiagonalBlock(skip+1,prec);
+
+      CGSolver cg(MPI_COMM_WORLD);
+      cg.SetRelTol(1e-6);
+      cg.SetMaxIter(200000);
+      cg.SetPrintLevel(0);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+      double maxresidual = residuals.Max(); 
+
+      double gresidual = residual * residual; 
+
+      MPI_Allreduce(MPI_IN_PLACE,&maxresidual,1,MPI_DOUBLE,MPI_MAX,MPI_COMM_WORLD);
+      MPI_Allreduce(MPI_IN_PLACE,&gresidual,1,MPI_DOUBLE,MPI_SUM,MPI_COMM_WORLD);
+
+      gresidual = sqrt(gresidual);
+
+      elements_to_refine.SetSize(0);
+      for (int iel = 0; iel<pmesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * maxresidual)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }
+
+      ParGridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(0));
+
+      ParGridFunction sigma_gf;
+      sigma_gf.MakeRef(sigma_fes,x.GetBlock(1));
+
+      int dofs = u_fes->GlobalTrueVSize()
+               + sigma_fes->GlobalTrueVSize()
+               + hatu_fes->GlobalTrueVSize()
+               + hatf_fes->GlobalTrueVSize();
+
+      double u_err = u_gf.ComputeL2Error(uex);
+      double sigma_err = sigma_gf.ComputeL2Error(sigmaex);
+      double L2Error = sqrt(u_err*u_err + sigma_err*sigma_err);
+
+      double rate_err = (i) ? dim*log(err0/L2Error)/log((double)dof0/dofs) : 0.0;
+      double rate_res = (i) ? dim*log(res0/gresidual)/log((double)dof0/dofs) : 0.0;
+
+      err0 = L2Error;
+      res0 = gresidual;
+      dof0 = dofs;
+
+      if (myid == 0)
+      {
+         mfem::out << std::right << std::setw(11) << i << " | " 
+                  << std::setw(10) <<  dof0 << " | " 
+                  << std::setprecision(3) 
+                  << std::setw(10) << std::scientific <<  err0 << " | " 
+                  << std::setprecision(2) 
+                  << std::setw(6) << std::fixed << rate_err << " | " 
+                  << std::setprecision(3) 
+                  << std::setw(10) << std::scientific <<  res0 << " | " 
+                  << std::setprecision(2) 
+                  << std::setw(6) << std::fixed << rate_res << " | " 
+                  << std::resetiosflags(std::ios::showbase)
+                  << std::endl;
+      }
+
+
+      if (visualization)
+      {
+         // uex_out.precision(8);
+         // uex_out << "parallel " << num_procs << " " << myid << "\n";
+         // uex_out << "solution\n" << pmesh << uex_gf <<
+         //          "window_title 'Exact u' "
+         //          << flush;
+
+         u_out << "parallel " << num_procs << " " << myid << "\n";
+         u_out.precision(8);
+         u_out << "solution\n" << pmesh << u_gf <<
+                  "window_title 'Numerical u' "
+                  << flush;
+
+         // sigma_out << "parallel " << num_procs << " " << myid << "\n";
+         // sigma_out.precision(8);
+         // sigma_out << "solution\n" << pmesh << sigma_gf <<
+         //       "window_title 'Numerical flux' "
+         //       << flush;
+      }
+
+      if (i == ref)
+         break;
+
+      pmesh.GeneralRefinement(elements_to_refine,1,1);
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+
+      if (test_norm == test_norm_type::robust)
+      {
+         coeff_fes->Update();
+         c1_gf.Update();
+         c2_gf.Update();
+         Array<int> edofs;
+         for (int i = 0; i < pmesh.GetNE(); i++)
+         {
+            double volume = pmesh.GetElementVolume(i);
+            double c1 = min(epsilon/volume, 1.);
+            double c2 = min(1./epsilon, 1./volume);
+            coeff_fes->GetElementDofs(i,edofs);
+            c1_gf.SetSubVector(edofs,c1);
+            c2_gf.SetSubVector(edofs,c2);
+         }
+      }
+   }
+
+
+   delete a;
+   delete tau_fec;
+   delete v_fec;
+   delete hatf_fes;
+   delete hatf_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete sigma_fec;
+   delete u_fec;
+   delete u_fes;
+
+   return 0;
+}
+
+void solution(const Vector & X, double & u, Vector & du, double & d2u)
+{
+   double x = X[0];
+   double y = X[1];
+   double z = 0.;
+   if (X.Size() == 3) z = X[2];
+   du.SetSize(X.Size());
+   du = 0.;
+   d2u = 0.;
+
+   switch(prob)
+   {
+      case polynomial:
+      {
+         int n=2;
+         int m=2;
+         u = pow(x,n)*pow(y,m);
+         du[0] = n * pow(x,n-1) * pow(y,m);
+         du[1] = m * pow(x,n) * pow(y,m-1);
+         d2u = n * (n-1) * pow(x,n-2) * pow(y,m)
+             + m * (m-1) * pow(x,n) * pow(y,m-2);
+      }
+      break;
+      case EJ:
+      {
+         double alpha = sqrt(1. + 4. * epsilon * epsilon * M_PI * M_PI);
+         double r1 = (1. + alpha) / (2.*epsilon);
+         double r2 = (1. - alpha) / (2.*epsilon);
+         double denom = exp(-r2) - exp(-r1);
+
+
+         double g1 = exp(r2*(x-1.));
+         double g1_x = r2*g1;
+         double g1_xx = r2*g1_x;
+         double g2 = exp(r1*(x-1.));
+         double g2_x = r1*g2;
+         double g2_xx = r1*g2_x;
+         double g = g1-g2;
+         double g_x = g1_x - g2_x;
+         double g_xx = g1_xx - g2_xx;
+
+
+         u = g * cos(M_PI * y)/denom;
+         double u_x = g_x * cos(M_PI * y)/denom;
+         double u_xx = g_xx * cos(M_PI * y)/denom;
+         double u_y = -M_PI * g * sin(M_PI*y)/denom;
+         double u_yy = -M_PI * M_PI * u;
+         du[0] = u_x;
+         du[1] = u_y;
+         d2u = u_xx + u_yy;
+
+      }
+      break;
+      default:
+      {
+         double alpha = M_PI * (x + y + z);
+         u = sin(alpha);
+         du.SetSize(X.Size());
+         for (int i = 0; i<du.Size(); i++)
+         {
+            du[i] = M_PI * cos(alpha);
+         }
+         d2u = - M_PI*M_PI * u * du.Size();
+      }
+      break;
+   }
+}
+
+
+double exact_u(const Vector & X)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   return u;
+}
+
+void exact_sigma(const Vector & X, Vector & sigma)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   // σ = ε ∇ u
+   sigma = du;
+   sigma *= epsilon;
+}
+
+double exact_hatu(const Vector & X)
+{
+   return -exact_u(X);
+}
+
+void exact_hatf(const Vector & X, Vector & hatf)
+{
+   Vector sigma;
+   exact_sigma(X,sigma);
+   double u = exact_u(X);
+   hatf.SetSize(X.Size());
+   for (int i = 0; i<hatf.Size(); i++)
+   {
+      hatf[i] = beta[i] * u - sigma[i];
+   }
+}
+
+double f_exact(const Vector & X)
+{
+   // f = - εΔu + ∇⋅(βu)
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+
+   double s = 0;
+   for (int i = 0; i<du.Size(); i++)
+   {
+      s += beta[i] * du[i];
+   }
+   return -epsilon * d2u + s;
+}
@@ -0,0 +1,203 @@
+//                 MFEM Fosls 1
+//
+// Compile with: make blkfosls
+//
+//     - Δ u = f, in Ω
+//         u = 0, on ∂Ω
+
+// First Order System
+
+//   ∇ u - σ = 0, in Ω
+// - ∇⋅σ     = f, in Ω
+//        u  = 0, in ∂Ω
+
+// FOSLS:
+//       minimize  1/2(||∇u - σ||^2 + ||∇ ⋅ σ - f||^2)
+
+
+// -------------------------------------------------
+// |   |    u    |         σ           |    RHS    |
+// -------------------------------------------------
+// | v | (∇u,∇v) |      -(σ,∇v)        |     0     |
+// |   |         |                     |           |
+// | τ | -(∇u,τ) | (∇⋅σ, ∇⋅τ) + (σ,τ)  | -(f,∇⋅τ ) |
+
+// where (u,τ) ∈ H^1(Ω) × H(div,Ω)
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   bool visualization = true;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree) or -1 for"
+                  " isoparametric space.");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   // 3. Read the mesh from the given mesh file. We can handle triangular,
+   //    quadrilateral, tetrahedral, hexahedral, surface and volume meshes with
+   //    the same code.
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   // 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.
+   FiniteElementCollection *fec0 = new H1_FECollection(order, dim);
+   FiniteElementCollection *fec1 = new RT_FECollection(order-1, dim);
+   FiniteElementSpace fespace0(&mesh, fec0);
+   FiniteElementSpace fespace1(&mesh, fec1);
+
+   Array<FiniteElementSpace *> fespaces(2);
+   fespaces[0] = &fespace0;
+   fespaces[1] = &fespace1;
+
+   Array<int> ess_bdr;
+   Array<int> ess_tdof_list;
+   if (mesh.bdr_attributes.Size())
+   {
+      ess_bdr.SetSize(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      fespaces[0]->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   BlockBilinearForm a(fespaces);
+   a.SetDiagonalPolicy(mfem::Operator::DIAG_KEEP);
+
+   cout << "H1 fespace = " << fespace0.GetVSize() << endl;
+   cout << "RT fespace = " << fespace1.GetVSize() << endl;
+
+   FiniteElementCollection *fec2 = new RT_Trace_FECollection(order-1, dim);
+   FiniteElementSpace RT_trace_fes(&mesh, fec2);
+   cout << "RT trace = " << RT_trace_fes.GetVSize() << endl;
+
+   // for (int i = 0; i<mesh.GetNE(); i++)
+   // {
+   //    // const FiniteElement * fe = fespace1.GetFE(i);
+   //    // fespace1.GetTraceElement()
+   //    Array<int> faces, ori;
+   //    mesh.GetElementEdges(i, faces, ori);
+   //    for (int f = 0; f<faces.Size(); f++)
+   //    {
+   //       const FiniteElement * fe_trace = RT_trace_fes.GetFaceElement(faces[f]);
+   //       cout << fe_trace->GetDof() << endl;
+   //       Array<int> face_dofs;
+   //       RT_trace_fes.GetFaceDofs(faces[f],face_dofs);
+   //       cout << "face dofs = " << endl;
+   //       face_dofs.Print();
+   //    }
+
+   //    // cout << fe->GetGeomType() << endl;
+   //    Array<int> vdofs;
+   //    RT_trace_fes.GetElementVDofs(i, vdofs);
+   //    cout << "trace dofs = " << endl;
+   //    vdofs.Print();
+   //    fespace1.GetElementVDofs(i, vdofs);
+   //    cout << "elem dofs = " << endl;
+   //    vdofs.Print();
+   //    cin.get();
+   // }
+
+
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+
+   Array2D<BilinearFormIntegrator * > blfi(2,2);
+   blfi(0,0) = new DiffusionIntegrator(one);
+   blfi(0,1) = new MixedVectorWeakDivergenceIntegrator(one);
+   blfi(1,0) = new MixedVectorGradientIntegrator(negone);
+
+   BilinearFormIntegrator * divdiv = new DivDivIntegrator(one);
+   BilinearFormIntegrator * mass = new VectorFEMassIntegrator(one);
+   SumIntegrator * suminteg = new SumIntegrator();
+   suminteg->AddIntegrator(divdiv);
+   suminteg->AddIntegrator(mass);
+   blfi(1,1) = suminteg;
+
+   TestBlockBilinearFormIntegrator * integ = new TestBlockBilinearFormIntegrator();
+   integ->SetIntegrators(blfi);
+   a.AddDomainIntegrator(integ);
+   a.Assemble();
+
+
+   BlockLinearForm b(fespaces);
+
+   TestBlockLinearFormIntegrator * lininteg = new TestBlockLinearFormIntegrator();
+   Array<LinearFormIntegrator * > lfi(2);
+   lfi[0] = nullptr;
+   lfi[1] = new VectorFEDomainLFDivIntegrator(negone);
+   lininteg->SetIntegrators(lfi);
+   b.AddDomainIntegrator(lininteg);
+   b.Assemble();
+
+
+   // need to implement blkgridfunction later but for now Vector would do
+   int size = 0;
+   for (int i = 0; i<fespaces.Size(); i++)
+   {
+      size += fespaces[i]->GetVSize();
+   }
+
+   Vector x(size);
+   x = 0.0;
+
+   OperatorPtr A;
+   Vector X,B;
+   a.FormLinearSystem(ess_tdof_list,x,b,A,X,B);
+
+   GSSmoother M((SparseMatrix&)(*A));
+   CGSolver cg;
+   cg.SetRelTol(1e-6);
+   cg.SetMaxIter(200);
+   cg.SetPrintLevel(1);
+   cg.SetPreconditioner(M);
+   cg.SetOperator(*A);
+   cg.Mult(B, X);
+
+   a.RecoverFEMSolution(X,b,x);
+
+   GridFunction u_gf, sigma_gf;
+   double *data = x.GetData();
+   u_gf.MakeRef(fespaces[0],&data[0]);
+   sigma_gf.MakeRef(fespaces[1],&data[fespaces[0]->GetVSize()]);
+
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      socketstream solu_sock(vishost, visport);
+      solu_sock.precision(8);
+      solu_sock << "solution\n" << mesh << u_gf <<
+                "window_title 'Numerical u' "
+                << flush;
+      socketstream sols_sock(vishost, visport);
+      sols_sock.precision(8);
+      sols_sock << "solution\n" << mesh << sigma_gf <<
+                "window_title 'Numerical sigma' "
+                << flush;
+   }
+
+   delete fec0;
+
+   return 0;
+}
@@ -0,0 +1,223 @@
+//                   MFEM Fosls example
+//
+// Compile with: make fosls
+//
+//     - Δ u = f, in Ω
+//         u = 0, on ∂Ω
+
+// First Order System
+
+//   ∇ u - σ = 0, in Ω
+// - ∇⋅σ     = f, in Ω
+//        u  = 0, in ∂Ω
+
+// FOSLS:
+//       minimize  1/2(||∇u - σ||^2 + ||∇ ⋅ σ - f||^2)
+
+
+// -------------------------------------------------
+// |   |    u    |         σ           |    RHS    |
+// -------------------------------------------------
+// | v | (∇u,∇v) |      -(σ,∇v)        |     0     |
+// |   |         |                     |           |
+// | τ | -(∇u,τ) | (∇⋅σ, ∇⋅τ) + (σ,τ)  | -(f,∇⋅τ ) |
+
+// where (u,τ) ∈ H^1(Ω) × H(div,Ω)
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   bool visualization = true;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree) or -1 for"
+                  " isoparametric space.");
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   // 3. Read the mesh from the given mesh file. We can handle triangular,
+   //    quadrilateral, tetrahedral, hexahedral, surface and volume meshes with
+   //    the same code.
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   FiniteElementCollection *H1fec = new H1_FECollection(order,dim);
+   FiniteElementSpace *H1fes = new FiniteElementSpace(&mesh, H1fec);
+
+   FiniteElementCollection *RTfec = new RT_FECollection(order-1,dim);
+   FiniteElementSpace *RTfes = new FiniteElementSpace(&mesh, RTfec);
+
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+
+   // Linear forms
+   LinearForm b_0(H1fes);
+   // (f,∇⋅τ )
+   LinearForm b_1(RTfes);
+   b_1.AddDomainIntegrator(new VectorFEDomainLFDivIntegrator(negone));
+
+   // Bilinear forms
+   // (∇u,∇v)
+   BilinearForm a_00(H1fes);
+   a_00.AddDomainIntegrator(new DiffusionIntegrator(one));
+
+   //   -(σ,∇v)
+   MixedBilinearForm a_01(RTfes, H1fes);
+   a_01.AddDomainIntegrator(new MixedVectorWeakDivergenceIntegrator(
+                               one)); // (-1 is included)
+
+   //    // -(∇u,τ)
+   // MixedBilinearForm()
+   MixedBilinearForm a_10(H1fes, RTfes);
+   a_10.AddDomainIntegrator(new MixedVectorGradientIntegrator(negone));
+
+   // (∇⋅σ, ∇⋅τ) + (σ,τ)
+
+   BilinearForm a_11(RTfes);
+   a_11.AddDomainIntegrator(new DivDivIntegrator(one));
+   a_11.AddDomainIntegrator(new VectorFEMassIntegrator(one));
+
+
+   Array<int> ess_bdr;
+   Array<int> ess_tdof_list;
+   if (mesh.bdr_attributes.Size())
+   {
+      ess_bdr.SetSize(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      H1fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   Array<int> block_Toffsets(3);
+   block_Toffsets[0] = 0;
+   block_Toffsets[1] = H1fes->GetTrueVSize();
+   block_Toffsets[2] = RTfes->GetTrueVSize();
+   block_Toffsets.PartialSum();
+
+   Vector rhs_H1(H1fes->GetVSize()); rhs_H1 = 0.;
+   Vector rhs_RT(RTfes->GetVSize()); rhs_RT = 0.;
+
+   Vector x_H1(H1fes->GetVSize()); x_H1 = 0.;
+   Vector x_RT(RTfes->GetVSize()); x_RT = 0.;
+
+
+   Vector RHS_H1(H1fes->GetTrueVSize()); RHS_H1 = 0.0;
+   Vector RHS_RT(RTfes->GetTrueVSize()); RHS_RT = 0.0;
+
+   Vector X_H1(H1fes->GetTrueVSize()); X_H1 = 0.0;
+   Vector X_RT(RTfes->GetTrueVSize()); X_RT = 0.0;
+
+
+   b_0.Update(H1fes,rhs_H1,0);
+   b_0.Assemble();
+
+   b_1.Update(RTfes,rhs_RT,0);
+   b_1.Assemble();
+
+
+   // Assembly and BC
+   a_00.Assemble();
+   SparseMatrix A_00;
+   a_00.FormLinearSystem(ess_tdof_list,x_H1,rhs_H1,
+                         A_00,X_H1,RHS_H1);
+
+   a_01.Assemble();
+   SparseMatrix A_01;
+   Array<int> empty;
+   a_01.FormRectangularSystemMatrix(empty, ess_tdof_list,A_01);
+
+
+   a_10.Assemble();
+   SparseMatrix A_10;
+
+   a_10.FormRectangularLinearSystem(ess_tdof_list,empty,x_H1,rhs_RT,
+                                    A_10,X_H1,RHS_RT);
+
+   a_11.Assemble();
+   SparseMatrix A_11;
+   a_11.FormSystemMatrix(empty,A_11);
+
+
+   BlockMatrix BlockA(block_Toffsets);
+   BlockA.SetBlock(0,0,&A_00);
+   BlockA.SetBlock(0,1,&A_01);
+   BlockA.SetBlock(1,0,&A_10);
+   BlockA.SetBlock(1,1,&A_11);
+
+
+   BlockVector RHS(block_Toffsets);
+   RHS.GetBlock(0) = RHS_H1;
+   RHS.GetBlock(1) = RHS_RT;
+
+   BlockVector X(block_Toffsets);
+   X.GetBlock(0) = X_H1;
+   X.GetBlock(1) = X_RT;
+
+
+   SparseMatrix * A = BlockA.CreateMonolithic();
+
+   GSSmoother M(*A);
+
+   CGSolver cg;
+   cg.SetRelTol(1e-6);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(1);
+   cg.SetPreconditioner(M);
+   cg.SetOperator(*A);
+   cg.Mult(RHS, X);
+
+   GridFunction u_gf(H1fes), sigma_gf(RTfes);
+   u_gf = 0.;
+   sigma_gf = 0.;
+
+   const SparseMatrix * P = H1fes->GetConformingProlongation();
+   if (P)
+   {
+      a_00.RecoverFEMSolution(X.GetBlock(0),rhs_H1,u_gf);
+      a_11.RecoverFEMSolution(X.GetBlock(1),rhs_RT,sigma_gf);
+   }
+   else
+   {
+      u_gf.MakeRef(X.GetBlock(0),0);
+      sigma_gf.MakeRef(X.GetBlock(1),0);
+   }
+
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      socketstream solu_sock(vishost, visport);
+      solu_sock.precision(8);
+      solu_sock << "solution\n" << mesh << u_gf <<
+                "window_title 'Numerical u' "
+                << flush;
+      socketstream sols_sock(vishost, visport);
+      sols_sock.precision(8);
+      sols_sock << "solution\n" << mesh << sigma_gf <<
+                "window_title 'Numerical sigma' "
+                << flush;
+   }
+
+   return 0;
+}
@@ -0,0 +1,61 @@
+# Copyright (c) 2010-2022, 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.
+
+# Use the MFEM build directory
+MFEM_DIR ?= ../../..
+MFEM_BUILD_DIR ?= ../../..
+SRC = $(if $(MFEM_DIR:../../..=),$(MFEM_DIR)/examples/dpg_tests/diffusion,)
+CONFIG_MK = $(MFEM_BUILD_DIR)/config/config.mk
+
+MFEM_LIB_FILE = mfem_is_not_built
+-include $(CONFIG_MK)
+
+SEQ_EXAMPLES = blkfosls fosls primal_dpg \
+	 				uw_dpg 
+PAR_EXAMPLES = uw_dpgp 
+
+ifeq ($(MFEM_USE_MPI),NO)
+   EXAMPLES = $(SEQ_EXAMPLES)
+else
+   EXAMPLES = $(PAR_EXAMPLES) $(SEQ_EXAMPLES)
+endif
+
+.SUFFIXES:
+.SUFFIXES: .o .cpp .mk
+.PHONY: all clean clean-build clean-exec
+
+# Remove built-in rule
+%: %.cpp
+
+# Replace the default implicit rule for *.cpp files
+%: $(SRC)%.cpp $(MFEM_LIB_FILE) $(CONFIG_MK)
+	$(MFEM_CXX) $(MFEM_FLAGS) $< -o $@ $(MFEM_LIBS)
+
+all: $(EXAMPLES) 
+
+MFEM_TESTS = EXAMPLES
+include $(MFEM_TEST_MK)
+
+# Testing: Parallel vs. serial runs
+RUN_MPI = $(MFEM_MPIEXEC) $(MFEM_MPIEXEC_NP) $(MFEM_MPI_NP)
+%-test-par: %
+	@$(call mfem-test,$<, $(RUN_MPI), Parallel example)
+%-test-seq: %
+	@$(call mfem-test,$<,, Serial example)
+
+clean: clean-build clean-exec 
+
+clean-build:
+	rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
+	rm -rf *.dSYM *.TVD.*breakpoints
+	rm -rf ParaView
+
+clean-exec:
@@ -0,0 +1,179 @@
+//                     MFEM primal_dpg example
+//
+// Compile with: make primal_dpg
+//
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command line options
+   const char *mesh_file = "../../../data/star.mesh";
+   int order = 1;
+   bool static_cond = false;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh", "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order", "Finite element polynomial degree");
+   args.AddOption(&static_cond, "-sc", "--static-condensation", "-no-sc",
+                  "--no-static-condensation", "Enable static condensation.");   
+   args.ParseCheck();
+
+   // 2. Read the mesh from the given mesh file, and refine once uniformly.
+   Mesh mesh(mesh_file);
+   // mesh.UniformRefinement();
+
+   // 3. Define a finite element space on the mesh. Here we use H1 continuous
+   //    high-order Lagrange finite elements of the given order.
+   H1_FECollection fec(order, mesh.Dimension());
+   FiniteElementSpace H1fes(&mesh, &fec);
+
+   RT_Trace_FECollection trace_fec(order-1, mesh.Dimension());
+   FiniteElementSpace RTtrace_fes(&mesh, &trace_fec);
+
+   int dim = mesh.Dimension();
+   int test_order = order;
+   if (dim == 2 && (order%2 == 0 || (mesh.MeshGenerator() & 2 && order > 1)))
+   {
+      test_order++;
+   }
+
+   test_order++;
+
+   H1_FECollection test_fec(test_order,mesh.Dimension());
+
+   Array<FiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fecs; 
+
+   trial_fes.Append(&H1fes);
+   trial_fes.Append(&RTtrace_fes);
+   test_fecs.Append(&test_fec);
+
+   NormalEquations * a = new NormalEquations(trial_fes,test_fecs);
+
+
+   ConstantCoefficient one(1.0);
+   a->AddTrialIntegrator(new DiffusionIntegrator(one),0,0);
+   a->AddTrialIntegrator(new TraceIntegrator,1,0);
+
+   BilinearFormIntegrator * diffusion = new DiffusionIntegrator(one);
+   BilinearFormIntegrator * mass = new MassIntegrator(one);
+   a->AddTestIntegrator(diffusion,0,0);
+   a->AddTestIntegrator(mass,0,0);
+
+   a->AddDomainLFIntegrator(new DomainLFIntegrator(one),0);
+   if (static_cond) { a->EnableStaticCondensation(); }
+   a->Assemble();
+
+   Array<int> ess_tdof_list;
+   if (mesh.bdr_attributes.Size())
+   {
+      Array<int> ess_bdr(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      H1fes.GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   Vector X,B;
+   OperatorPtr Ah;
+
+   int size = H1fes.GetVSize() + RTtrace_fes.GetVSize();
+
+   Vector x(size);
+   x = 0.0;
+
+   a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+   BlockMatrix * A = (BlockMatrix *)(Ah.Ptr());
+   BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+   M->owns_blocks = 1;
+   for (int i=0; i<A->NumRowBlocks(); i++)
+   {
+      M->SetDiagonalBlock(i,new UMFPackSolver(A->GetBlock(i,i)));
+   }
+
+   CGSolver cg;
+   cg.SetRelTol(1e-6);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(3);
+   cg.SetPreconditioner(*M);
+   cg.SetOperator(*A);
+   cg.Mult(B, X);
+
+   delete M;
+
+
+   a->RecoverFEMSolution(X,x);
+
+   GridFunction u_gf;
+   double *data = x.GetData();
+   u_gf.MakeRef(&H1fes,data);
+
+   GridFunction s_gf;
+   s_gf.MakeRef(&RTtrace_fes,&data[H1fes.GetVSize()]);
+
+
+
+   RT_FECollection RTfec(order-1, mesh.Dimension());
+   FiniteElementSpace RTfes(&mesh, &RTfec);
+
+   GridFunction sigma_gf(&RTfes);
+   sigma_gf = 0.0;
+   for (int i = 0; i<mesh.GetNE(); i++)
+   {
+      Array<int> strace_dofs;
+      Array<int> trace_dofs;
+      Vector dofs;
+      RTtrace_fes.GetElementDofs(i,trace_dofs);
+      strace_dofs.SetSize(trace_dofs.Size());
+      // shift dofs;
+      for (int j = 0; j< trace_dofs.Size(); j++)
+      {
+         int offset = trace_dofs[j] < 0 ? -H1fes.GetVSize() : H1fes.GetVSize();
+         strace_dofs[j] = offset + trace_dofs[j];
+      }
+      x.GetSubVector(strace_dofs, dofs);
+      sigma_gf.SetSubVector(trace_dofs,dofs);
+
+   }
+
+
+
+
+
+   ParaViewDataCollection paraview_dc("DPG_example", &mesh);
+   paraview_dc.SetPrefixPath("ParaView");
+   paraview_dc.SetLevelsOfDetail(order);
+   paraview_dc.SetCycle(0);
+   paraview_dc.SetDataFormat(VTKFormat::BINARY);
+   paraview_dc.SetHighOrderOutput(true);
+   paraview_dc.SetTime(0.0); // set the time
+   paraview_dc.RegisterField("field",&u_gf);
+   paraview_dc.RegisterField("flux",&sigma_gf);
+   // paraview_dc.RegisterField("flux",&s_gf);
+   paraview_dc.Save();
+
+
+
+
+   char vishost[] = "localhost";
+   int  visport   = 19916;
+   socketstream solu_sock(vishost, visport);
+   solu_sock.precision(8);
+   solu_sock << "solution\n" << mesh << u_gf <<
+             "window_title 'Numerical u' "
+             << flush;
+
+   socketstream soltrace_sock(vishost, visport);
+   soltrace_sock.precision(8);
+   soltrace_sock << "solution\n" << mesh << sigma_gf <<
+                 "window_title 'Flux sigma_n' "
+                 << flush;
+
+
+
+}
@@ -0,0 +1,403 @@
+//                       MFEM Ultraweak DPG example
+//
+// Compile with: make uw_dpg
+//
+// sample runs 
+// ./uw_dpg -m ../lshape2.mesh -o 2 -ref 20 -graph-norm -do 1 -prob 0
+
+//     - Δ u = f,   in Ω
+//         u = u_0, on ∂Ω
+
+// First Order System
+
+//   ∇ u - σ = 0, in Ω
+// - ∇⋅σ     = f, in Ω
+//        u  = 0, in ∂Ω
+
+// UW-DPG:
+// 
+// u ∈ L^2(Ω), σ ∈ (L^2(Ω))^dim 
+// û ∈ H^1/2, σ̂ ∈ H^-1/2  
+// -(u , ∇⋅τ) - (σ , τ) + < û, τ⋅n> = 0,      ∀ τ ∈ H(div,Ω)      
+//  (σ , ∇ v) + < σ̂, v  >           = (f,v)   ∀ v ∈ H^1(Ω)
+//                                û = 0       on ∂Ω 
+
+// Note: 
+// û := u
+// σ̂ := -σ
+
+// -------------------------------------------------------------
+// |   |     u     |     σ     |    û      |    σ̂    |  RHS    |
+// -------------------------------------------------------------
+// | τ | -(u,∇⋅τ)  |  -(σ,τ)   | < û, τ⋅n> |         |    0    |
+// |   |           |           |           |         |         |
+// | v |           |  (σ,∇ v)  |           |  <σ̂,v>  |  (f,v)  |  
+
+// where (τ,v) ∈  H(div,Ω) × H^1(Ω) 
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+enum prob_type
+{
+   lshape,   
+   general  
+};
+
+prob_type prob;
+
+void solution(const Vector & X, double & u, Vector & du, double & d2u);
+
+
+double exact_u(const Vector & X)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   return u;
+}
+
+void exact_sigma(const Vector & X, Vector & sigma)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   // σ = ∇ u
+   sigma = du;
+}
+
+double exact_hatu(const Vector & X)
+{
+   return exact_u(X);
+}
+
+void exact_hatsigma(const Vector & X, Vector & hatsigma)
+{
+   exact_sigma(X,hatsigma);
+   hatsigma *= -1.;
+}
+
+double f_exact(const Vector & X)
+{
+   double u, d2u;
+   Vector du;
+   solution(X,u,du,d2u);
+   return -d2u;
+}
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   int ref = 1;
+   bool adjoint_graph_norm = false;
+   bool visualization = true;
+   int iprob = 0;
+   bool static_cond = false;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree).");
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");
+   args.AddOption(&ref, "-ref", "--num_refinements",
+                  "Number of uniform refinements");               
+   args.AddOption(&adjoint_graph_norm, "-graph-norm", "--adjoint-graph-norm",
+                  "-no-graph-norm", "--no-adjoint-graph-norm",
+                  "Enable or disable Adjoint Graph Norm on the test space"); 
+   args.AddOption(&iprob, "-prob", "--problem", "Problem case"
+                  " 0: lshape, 1: General");
+   args.AddOption(&static_cond, "-sc", "--static-condensation", "-no-sc",
+                  "--no-static-condensation", "Enable static condensation.");                  
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      args.PrintUsage(cout);
+      return 1;
+   }
+   args.PrintOptions(cout);
+
+   if (iprob > 1) { iprob = 1; }
+   prob = (prob_type)iprob;
+
+   if (prob == prob_type::lshape)
+   {
+      mesh_file = "../lshape2.mesh";
+   }
+
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   mesh.UniformRefinement();
+
+   // Define spaces
+   // L2 space for u
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *u_fes = new FiniteElementSpace(&mesh,u_fec);
+
+   // Vector L2 space for σ 
+   FiniteElementCollection *sigma_fec = new L2_FECollection(order-1,dim);
+   FiniteElementSpace *sigma_fes = new FiniteElementSpace(&mesh,sigma_fec, dim); 
+
+   // H^1/2 space for û 
+   FiniteElementCollection * hatu_fec = new H1_Trace_FECollection(order,dim);
+   FiniteElementSpace *hatu_fes = new FiniteElementSpace(&mesh,hatu_fec);
+
+   // H^-1/2 space for σ̂ 
+   FiniteElementCollection * hatsigma_fec = new RT_Trace_FECollection(order-1,dim);   
+   FiniteElementSpace *hatsigma_fes = new FiniteElementSpace(&mesh,hatsigma_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * tau_fec = new RT_FECollection(test_order-1, dim);
+   FiniteElementCollection * v_fec = new H1_FECollection(test_order, dim);
+
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+
+   // Normal equation weak formulation
+   Array<FiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(u_fes);
+   trial_fes.Append(sigma_fes);
+   trial_fes.Append(hatu_fes);
+   trial_fes.Append(hatsigma_fes);
+
+   test_fec.Append(tau_fec);
+   test_fec.Append(v_fec);
+
+   NormalEquations * a = new NormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+   //  -(u,∇⋅τ)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(one),0,0);
+
+   // -(σ,τ) 
+   a->AddTrialIntegrator(new TransposeIntegrator(new VectorFEMassIntegrator(negone)),1,0);
+
+   // (σ,∇ v)
+   a->AddTrialIntegrator(new TransposeIntegrator(new GradientIntegrator(one)),1,1);
+
+   //  <û,τ⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,0);
+
+   //  <σ̂,v> 
+   a->AddTrialIntegrator(new TraceIntegrator,3,1);
+
+   // test integrators (space-induced norm for H(div) × H1)
+   // (∇⋅τ,∇⋅δτ)
+   a->AddTestIntegrator(new DivDivIntegrator(one),0,0);
+   // (τ,δτ)
+   a->AddTestIntegrator(new VectorFEMassIntegrator(one),0,0);
+   // (∇v,∇δv)
+   a->AddTestIntegrator(new DiffusionIntegrator(one),1,1);
+   // (v,δv)
+   a->AddTestIntegrator(new MassIntegrator(one),1,1);
+
+   // additional terms for adjoint graph norm
+   if (adjoint_graph_norm)
+   {
+      // -(∇v,δτ) 
+      a->AddTestIntegrator(new MixedVectorGradientIntegrator(negone),1,0);
+      // -(τ,∇δv) 
+      a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(one),0,1);
+      // (τ,δτ)
+      a->AddTestIntegrator(new VectorFEMassIntegrator(one),0,0);
+   }
+
+   // RHS
+   FunctionCoefficient f(f_exact);
+   if (prob == prob_type::general)
+   {
+      a->AddDomainLFIntegrator(new DomainLFIntegrator(f),1);
+   }
+
+   FunctionCoefficient hatuex(exact_hatu);
+   Array<int> elements_to_refine;
+   GridFunction hatu_gf;
+
+
+   socketstream u_out;
+   // socketstream sigma_out;
+   socketstream mesh_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      u_out.open(vishost, visport);
+      // sigma_out.open(vishost, visport);
+      mesh_out.open(vishost, visport);
+   }
+
+
+   for (int iref = 0; iref<ref; iref++)
+   {
+      if (static_cond) { a->EnableStaticCondensation(); }
+      a->Assemble();
+
+      Array<int> ess_tdof_list;
+      Array<int> ess_bdr;
+      if (mesh.bdr_attributes.Size())
+      {
+         ess_bdr.SetSize(mesh.bdr_attributes.Max());
+         ess_bdr = 1;
+         hatu_fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+      }
+
+   // shift the ess_tdofs
+      for (int i = 0; i < ess_tdof_list.Size(); i++)
+      {
+         ess_tdof_list[i] += u_fes->GetTrueVSize() + sigma_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = u_fes->GetVSize();
+      offsets[2] = sigma_fes->GetVSize();
+      offsets[3] = hatu_fes->GetVSize();
+      offsets[4] = hatsigma_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      hatu_gf.MakeRef(hatu_fes,x.GetBlock(2));
+      hatu_gf.ProjectBdrCoefficient(hatuex,ess_bdr);
+
+      OperatorPtr Ah;
+      Vector X,B;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockMatrix * A = Ah.As<BlockMatrix>();
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+      for (int i=0; i<A->NumRowBlocks(); i++)
+      {
+         M->SetDiagonalBlock(i,new GSSmoother(A->GetBlock(i,i)));
+      }
+
+      CGSolver cg;
+      cg.SetRelTol(1e-12);
+      cg.SetMaxIter(2000);
+      cg.SetPrintLevel(3);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+      cout << "Residual = " << residual << endl;
+
+      elements_to_refine.SetSize(0);
+      double max_resid = residuals.Max();
+      double theta = 0.7;
+      for (int iel = 0; iel<mesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * max_resid)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }
+      
+      GridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(0));
+
+      GridFunction sigma_gf;
+      sigma_gf.MakeRef(sigma_fes,x.GetBlock(1));
+
+      if (visualization)
+      {
+         u_out.precision(8);
+         string keys = (iref == 0) ? "keys em\n" : "keys";
+         u_out << "solution\n" << mesh << u_gf 
+               << "window_title 'Numerical u' "
+                  << flush;
+
+         // sigma_out.precision(8);
+         // sigma_out << "solution\n" << mesh << sigma_gf <<
+         //       "window_title 'Numerical flux' "
+         //       << flush;
+
+         mesh_out.precision(8);
+         mesh_out << "mesh\n" << mesh 
+                  << keys
+                  << "window_title 'Mesh' "
+                  << flush;
+
+      }
+
+      mesh.GeneralRefinement(elements_to_refine);
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+   }
+
+   delete a;
+   delete tau_fec;
+   delete v_fec;
+   delete hatsigma_fes;
+   delete hatsigma_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete sigma_fec;
+   delete sigma_fes;
+   delete u_fec;
+   delete u_fes;
+
+   return 0;
+}
+
+
+void solution(const Vector & X, double & u, Vector & du, double & d2u)
+{
+   double x = X[0];
+   double y = X[1];
+   double z = 0.;
+   if (X.Size() == 3) z = X[2];
+   du.SetSize(X.Size());
+   du = 0.;
+   d2u = 0.;
+
+   switch(prob)
+   {
+      case lshape:
+      {
+         double r = sqrt(x*x + y*y);
+         double alpha = 2./3.;
+         double theta = atan2(y,x);
+         if (theta < 0) theta += 2*M_PI;
+         u = pow(r,alpha) * sin(alpha * theta);
+      }
+      break;
+      default:
+      {
+         double alpha = M_PI * (x + y + z);
+         u = sin(alpha);
+         du.SetSize(X.Size());
+         for (int i = 0; i<du.Size(); i++)
+         {
+            du[i] = M_PI * cos(alpha);
+         }
+         d2u = - M_PI*M_PI * u * du.Size();
+      }
+      break;
+   }
+}
@@ -0,0 +1,404 @@
+//                 MFEM UW DPG parallel example
+//
+// Compile with: make poisson_fosls
+//
+//     - Δ u = f, in Ω
+//         u = 0, on ∂Ω
+
+// First Order System
+
+//   ∇ u - σ = 0, in Ω
+// - ∇⋅σ     = f, in Ω
+//        u  = 0, in ∂Ω
+
+// UW-DPG:
+// 
+// u ∈ L^2(Ω), σ ∈ (L^2(Ω))^dim 
+// û ∈ H^1/2, σ̂ ∈ H^-1/2  
+// -(u , ∇⋅τ) + < û, τ⋅n> - (σ , τ) = 0,      ∀ τ ∈ H(div,Ω)      
+//  (σ , ∇ v) - < σ̂, v  >           = (f,v)   ∀ v ∈ H^1(Ω)
+//            û = 0        on ∂Ω 
+
+// -------------------------------------------------------------
+// |   |     u     |     σ     |    û      |    σ̂    |  RHS    |
+// -------------------------------------------------------------
+// | τ | -(u,∇⋅τ)  |  -(σ,τ)   | < û, τ⋅n> |         |    0    |
+// |   |           |           |           |         |         |
+// | v |           |  (σ,∇ v)  |           | -<σ̂,v>  |  (f,v)  |  
+
+// where (τ,v) ∈  H(div,Ω) × H^1(Ω) 
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+enum prob_type
+{
+   lshape,   
+   general  
+};
+
+prob_type prob;
+
+double exact(const Vector & X)
+{
+   double x = X[0];
+   double y = X[1];
+
+   double r = sqrt(x*x + y*y);
+   double alpha = 2./3.;
+   double theta = atan2(y,x);
+   if (theta < 0) theta += 2*M_PI;
+
+   return pow(r,alpha) * sin(alpha * theta);
+}
+
+void gradexact(const Vector & X, Vector & grad)
+{
+   grad.SetSize(2);
+   double x = X[0];
+   double y = X[1];
+
+   double r = sqrt(x*x + y*y);
+   double alpha = 2./3.;
+   double theta = atan2(y,x);
+   if (theta < 0) theta += 2*M_PI;
+
+   double r_x = x/r;
+   double r_y = y/r;
+   double theta_x = - y / (r*r);
+   double theta_y = x / (r*r);
+   double beta = alpha * pow(r,alpha - 1.);
+   grad[0] = beta*(r_x * sin(alpha*theta) + r * theta_x * cos(alpha*theta));
+   grad[1] = beta*(r_y * sin(alpha*theta) + r * theta_y * cos(alpha*theta));
+}
+
+
+int main(int argc, char *argv[])
+{
+   MPI_Session mpi;
+   int num_procs = mpi.WorldSize();
+   int myid = mpi.WorldRank();
+
+   // 1. Parse command-line options.
+   const char *mesh_file = "../../../data/inline-quad.mesh";
+   int order = 1;
+   int delta_order = 1;
+   int ref = 1;
+   bool adjoint_graph_norm = false;
+   bool visualization = true;
+   int iprob = 0;
+   bool static_cond = false;
+   double theta = 0.7;
+
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh",
+                  "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order",
+                  "Finite element order (polynomial degree).");
+   args.AddOption(&delta_order, "-do", "--delta_order",
+                  "Order enrichment for DPG test space.");
+   args.AddOption(&ref, "-ref", "--num_refinements",
+                  "Number of uniform refinements");    
+   args.AddOption(&theta, "-theta", "--theta_factor",
+                  "Refinement factor");                              
+   args.AddOption(&adjoint_graph_norm, "-graph-norm", "--adjoint-graph-norm",
+                  "-no-graph-norm", "--no-adjoint-graph-norm",
+                  "Enable or disable Adjoint Graph Norm on the test space");   
+   args.AddOption(&iprob, "-prob", "--problem", "Problem case"
+                  " 0: lshape, 1: General");       
+   args.AddOption(&static_cond, "-sc", "--static-condensation", "-no-sc",
+                  "--no-static-condensation", "Enable static condensation.");                                            
+   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
+                  "--no-visualization",
+                  "Enable or disable GLVis visualization.");
+   args.Parse();
+   if (!args.Good())
+   {
+      if (myid == 0)
+      {
+         args.PrintUsage(cout);
+      }
+      return 1;
+   }
+   if (myid == 0)
+   {
+      args.PrintOptions(cout);
+   }
+
+   if (iprob > 1) { iprob = 1; }
+   prob = (prob_type)iprob;
+
+   if (prob == prob_type::lshape)
+   {
+      mesh_file = "../lshape2.mesh";
+   }
+
+   Mesh mesh(mesh_file, 1, 1);
+   int dim = mesh.Dimension();
+
+   mesh.UniformRefinement();
+
+   mesh.EnsureNCMesh();
+
+   ParMesh pmesh(MPI_COMM_WORLD, mesh);
+   mesh.Clear();
+
+   // Define spaces
+   // L2 space for u
+   FiniteElementCollection *u_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *u_fes = new ParFiniteElementSpace(&pmesh,u_fec);
+
+   // Vector L2 space for σ 
+   FiniteElementCollection *sigma_fec = new L2_FECollection(order-1,dim);
+   ParFiniteElementSpace *sigma_fes = new ParFiniteElementSpace(&pmesh,sigma_fec, dim); 
+
+   // H^1/2 space for û 
+   FiniteElementCollection * hatu_fec = new H1_Trace_FECollection(order,dim);
+   ParFiniteElementSpace *hatu_fes = new ParFiniteElementSpace(&pmesh,hatu_fec);
+
+   // H^-1/2 space for σ̂ 
+   FiniteElementCollection * hatsigma_fec = new RT_Trace_FECollection(order-1,dim);   
+   ParFiniteElementSpace *hatsigma_fes = new ParFiniteElementSpace(&pmesh,hatsigma_fec);
+
+   // testspace fe collections
+   int test_order = order+delta_order;
+   FiniteElementCollection * tau_fec = new RT_FECollection(test_order-1, dim);
+   FiniteElementCollection * v_fec = new H1_FECollection(test_order, dim);
+
+   // Coefficients
+   ConstantCoefficient one(1.0);
+   ConstantCoefficient negone(-1.0);
+
+   // Normal equation weak formulation
+   Array<ParFiniteElementSpace * > trial_fes; 
+   Array<FiniteElementCollection * > test_fec; 
+
+   trial_fes.Append(u_fes);
+   trial_fes.Append(sigma_fes);
+   trial_fes.Append(hatu_fes);
+   trial_fes.Append(hatsigma_fes);
+
+   test_fec.Append(tau_fec);
+   test_fec.Append(v_fec);
+
+   ParNormalEquations * a = new ParNormalEquations(trial_fes,test_fec);
+   a->StoreMatrices(true);
+
+   //  -(u,∇⋅τ)
+   a->AddTrialIntegrator(new MixedScalarWeakGradientIntegrator(one),0,0);
+
+   // -(σ,τ) 
+   TransposeIntegrator * mass = new TransposeIntegrator(new VectorFEMassIntegrator(negone));
+   a->AddTrialIntegrator(mass,1,0);
+
+   // (σ,∇ v)
+   TransposeIntegrator * grad = new TransposeIntegrator(new GradientIntegrator(one));
+   a->AddTrialIntegrator(grad,1,1);
+
+   //  <û,τ⋅n>
+   a->AddTrialIntegrator(new NormalTraceIntegrator,2,0);
+
+   // -<σ̂,v> (sign is included in σ̂)
+   a->AddTrialIntegrator(new TraceIntegrator,3,1);
+
+   // test integrators (space-induced norm for H(div) × H1)
+   // (∇⋅τ,∇⋅δτ)
+   a->AddTestIntegrator(new DivDivIntegrator(one),0,0);
+   // (τ,δτ)
+   a->AddTestIntegrator(new VectorFEMassIntegrator(one),0,0);
+   // (∇v,∇δv)
+   a->AddTestIntegrator(new DiffusionIntegrator(one),1,1);
+   // (v,δv)
+   a->AddTestIntegrator(new MassIntegrator(one),1,1);
+
+   // additional terms for adjoint graph norm
+   if (adjoint_graph_norm)
+   {
+      // -(∇v,δτ) 
+      a->AddTestIntegrator(new MixedVectorGradientIntegrator(negone),1,0);
+      // -(τ,∇δv) 
+      a->AddTestIntegrator(new MixedVectorWeakDivergenceIntegrator(one),0,1);
+      // (τ,δτ)
+      a->AddTestIntegrator(new VectorFEMassIntegrator(one),0,0);
+   }
+   // RHS
+   if (prob == prob_type::general)
+   {
+      a->AddDomainLFIntegrator(new DomainLFIntegrator(one),1);
+   }
+
+   FunctionCoefficient uex(exact);
+   Array<int> elements_to_refine;
+   ParGridFunction hatu_gf;
+
+
+   socketstream u_out;
+   socketstream sigma_out;
+   if (visualization)
+   {
+      char vishost[] = "localhost";
+      int  visport   = 19916;
+      u_out.open(vishost, visport);
+      sigma_out.open(vishost, visport);
+   }
+
+   for (int i = 0; i<ref; i++)
+   {
+      if (static_cond) { a->EnableStaticCondensation(); }
+      a->Assemble();
+
+      Array<int> ess_tdof_list;
+      Array<int> ess_bdr;
+      if (pmesh.bdr_attributes.Size())
+      {
+         ess_bdr.SetSize(pmesh.bdr_attributes.Max());
+         ess_bdr = 1;
+         hatu_fes->GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+      }
+
+      // shift the ess_tdofs
+      for (int i = 0; i < ess_tdof_list.Size(); i++)
+      {
+         ess_tdof_list[i] += u_fes->GetTrueVSize() + sigma_fes->GetTrueVSize();
+      }
+
+      Array<int> offsets(5);
+      offsets[0] = 0;
+      offsets[1] = u_fes->GetVSize();
+      offsets[2] = sigma_fes->GetVSize();
+      offsets[3] = hatu_fes->GetVSize();
+      offsets[4] = hatsigma_fes->GetVSize();
+      offsets.PartialSum();
+      BlockVector x(offsets);
+      x = 0.0;
+      if (prob == prob_type::lshape)
+      {
+         hatu_gf.MakeRef(hatu_fes,x.GetBlock(2));
+         hatu_gf.ProjectBdrCoefficient(uex,ess_bdr);
+      }
+
+      Vector X,B;
+      OperatorPtr Ah;
+      a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+      BlockOperator * A = Ah.As<BlockOperator>();
+
+      BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+      M->owns_blocks = 1;
+      int skip = 0;
+      if (!static_cond)
+      {
+         HypreBoomerAMG * amg0 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(0,0));
+         HypreBoomerAMG * amg1 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(1,1));
+         amg0->SetPrintLevel(0);
+         amg1->SetPrintLevel(0);
+         M->SetDiagonalBlock(0,amg0);
+         M->SetDiagonalBlock(1,amg1);
+         skip=2;
+      }
+      HypreBoomerAMG * amg2 = new HypreBoomerAMG((HypreParMatrix &)A->GetBlock(skip,skip));
+      amg2->SetPrintLevel(0);
+      M->SetDiagonalBlock(skip,amg2);
+      HypreSolver * prec;
+      if (dim == 2)
+      {
+         prec = new HypreAMS((HypreParMatrix &)A->GetBlock(skip+1,skip+1), hatsigma_fes);
+      }
+      else
+      {
+         prec = new HypreADS((HypreParMatrix &)A->GetBlock(skip+1,skip+1), hatsigma_fes);
+      }
+      M->SetDiagonalBlock(skip+1,prec);
+
+      CGSolver cg(MPI_COMM_WORLD);
+      cg.SetRelTol(1e-12);
+      cg.SetMaxIter(2000);
+      cg.SetPrintLevel(3);
+      cg.SetPreconditioner(*M);
+      cg.SetOperator(*A);
+      cg.Mult(B, X);
+      delete M;
+
+      a->RecoverFEMSolution(X,x);
+
+      Vector & residuals = a->ComputeResidual(x);
+
+      double residual = residuals.Norml2();
+      
+      double maxresidual = residuals.Max(); 
+      double globalresidual = residual * residual; 
+
+      MPI_Allreduce(MPI_IN_PLACE,&maxresidual,1,MPI_DOUBLE,MPI_MAX,MPI_COMM_WORLD);
+      MPI_Allreduce(MPI_IN_PLACE,&globalresidual,1,MPI_DOUBLE,MPI_SUM,MPI_COMM_WORLD);
+
+      globalresidual = sqrt(globalresidual);
+
+      if (myid == 0)
+      {
+         cout << "Global Residual = " << globalresidual << endl;
+      }
+
+      elements_to_refine.SetSize(0);
+      for (int iel = 0; iel<pmesh.GetNE(); iel++)
+      {
+         if (residuals[iel] > theta * maxresidual)
+         {
+            elements_to_refine.Append(iel);
+         }
+      }
+
+      ParGridFunction u_gf;
+      u_gf.MakeRef(u_fes,x.GetBlock(0));
+
+      ParGridFunction sigma_gf;
+      sigma_gf.MakeRef(sigma_fes,x.GetBlock(1));
+
+      if (visualization)
+      {
+         u_out << "parallel " << num_procs << " " << myid << "\n";
+         u_out.precision(8);
+         u_out << "solution\n" << pmesh << u_gf <<
+                  "window_title 'Numerical u' "
+                  << flush;
+
+         sigma_out << "parallel " << num_procs << " " << myid << "\n";
+         sigma_out.precision(8);
+         sigma_out << "solution\n" << pmesh << sigma_gf <<
+                  "window_title 'Numerical flux' "
+                  << flush;
+      }
+
+
+      if (i == ref-1)
+      {
+         break;
+      }
+
+      pmesh.GeneralRefinement(elements_to_refine);
+
+      for (int i =0; i<trial_fes.Size(); i++)
+      {
+         trial_fes[i]->Update(false);
+      }
+      a->Update();
+   }
+
+   delete a;
+   delete tau_fec;
+   delete v_fec;
+   delete hatsigma_fes;
+   delete hatsigma_fec;
+   delete hatu_fes;
+   delete hatu_fec;
+   delete sigma_fec;
+   delete sigma_fes;
+   delete u_fec;
+   delete u_fes;
+
+   return 0;
+}
@@ -0,0 +1,59 @@
+# Copyright (c) 2010-2022, 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.
+
+# Use the MFEM build directory
+MFEM_DIR ?= ../../..
+MFEM_BUILD_DIR ?= ../../..
+SRC = $(if $(MFEM_DIR:../../..=),$(MFEM_DIR)/examples/dpg_tests/grad-div,)
+CONFIG_MK = $(MFEM_BUILD_DIR)/config/config.mk
+
+MFEM_LIB_FILE = mfem_is_not_built
+-include $(CONFIG_MK)
+
+SEQ_EXAMPLES = primal_dpg 
+PAR_EXAMPLES = 
+
+ifeq ($(MFEM_USE_MPI),NO)
+   EXAMPLES = $(SEQ_EXAMPLES)
+else
+   EXAMPLES = $(PAR_EXAMPLES) $(SEQ_EXAMPLES)
+endif
+
+.SUFFIXES:
+.SUFFIXES: .o .cpp .mk
+.PHONY: all clean clean-build clean-exec
+
+# Remove built-in rule
+%: %.cpp
+
+# Replace the default implicit rule for *.cpp files
+%: $(SRC)%.cpp $(MFEM_LIB_FILE) $(CONFIG_MK)
+	$(MFEM_CXX) $(MFEM_FLAGS) $< -o $@ $(MFEM_LIBS)
+
+all: $(EXAMPLES) 
+
+MFEM_TESTS = EXAMPLES
+include $(MFEM_TEST_MK)
+
+# Testing: Parallel vs. serial runs
+RUN_MPI = $(MFEM_MPIEXEC) $(MFEM_MPIEXEC_NP) $(MFEM_MPI_NP)
+%-test-par: %
+	@$(call mfem-test,$<, $(RUN_MPI), Parallel example)
+%-test-seq: %
+	@$(call mfem-test,$<,, Serial example)
+
+clean: clean-build clean-exec 
+
+clean-build:
+	rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
+	rm -rf *.dSYM *.TVD.*breakpoints
+
+clean-exec:
@@ -0,0 +1,176 @@
+//                                MFEM primal dpg example for grad-dic problem
+//
+// Compile with: make primal_dpg
+//
+
+#include "mfem.hpp"
+#include <fstream>
+#include <iostream>
+
+using namespace std;
+using namespace mfem;
+
+// Exact solution, F, and r.h.s., f. See below for implementation.
+void F_exact(const Vector &, Vector &);
+void f_exact(const Vector &, Vector &);
+double freq = 1.0, kappa;
+
+
+int main(int argc, char *argv[])
+{
+   // 1. Parse command line options
+   const char *mesh_file = "../../../data/star.mesh";
+   int order = 1;
+
+   OptionsParser args(argc, argv);
+   args.AddOption(&mesh_file, "-m", "--mesh", "Mesh file to use.");
+   args.AddOption(&order, "-o", "--order", "Finite element polynomial degree");
+   args.ParseCheck();
+
+   kappa = freq * M_PI;
+
+
+   // 2. Read the mesh from the given mesh file, and refine once uniformly.
+   Mesh mesh(mesh_file);
+   // mesh.UniformRefinement();
+
+   RT_FECollection fec(order-1, mesh.Dimension());
+   FiniteElementSpace RTfes(&mesh, &fec);
+
+   H1_Trace_FECollection trace_fec(order, mesh.Dimension());
+   FiniteElementSpace H1trace_fes(&mesh, &trace_fec);
+
+   int dim = mesh.Dimension();
+   int test_order = order;
+   if (dim == 2 && (order%2 == 0 || (mesh.MeshGenerator() & 2 && order > 1)))
+   {
+      test_order++;
+   }
+
+   test_order++;
+
+   RT_FECollection test_fec(test_order,mesh.Dimension());
+
+   Array<FiniteElementSpace *> trial_fes; 
+   Array<FiniteElementCollection * > test_fecs; 
+   
+   trial_fes.Append(&RTfes);
+   trial_fes.Append(&H1trace_fes);
+   test_fecs.Append(&test_fec);
+
+
+   GridFunction rt_gf(&RTfes);
+   VectorFunctionCoefficient F(dim, F_exact);
+   rt_gf.ProjectCoefficient(F);
+
+   Vector x(RTfes.GetVSize()+H1trace_fes.GetVSize());
+   x = 0.;
+   x.SetVector(rt_gf,0);
+
+
+   ConstantCoefficient alpha(1.0);
+   ConstantCoefficient beta(1.0);
+   NormalEquations * a = new NormalEquations(trial_fes,test_fecs);
+   a->AddTrialIntegrator(new DivDivIntegrator(alpha),0,0);
+   a->AddTrialIntegrator(new VectorFEMassIntegrator(beta),0,0);
+   a->AddTrialIntegrator(new NormalTraceIntegrator,1,0);
+   a->AddTestIntegrator(new DivDivIntegrator(alpha),0,0);
+   a->AddTestIntegrator(new VectorFEMassIntegrator(beta),0,0);
+
+
+   VectorFunctionCoefficient f(dim, f_exact);
+   a->AddDomainLFIntegrator(new VectorFEDomainLFIntegrator(f),0);
+   a->Assemble();
+
+   Array<int> ess_tdof_list;
+   if (mesh.bdr_attributes.Size())
+   {
+      Array<int> ess_bdr(mesh.bdr_attributes.Max());
+      ess_bdr = 1;
+      RTfes.GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
+   }
+
+   Vector X,B;
+
+   OperatorPtr Ah;
+   a->FormLinearSystem(ess_tdof_list,x,Ah,X,B);
+
+   BlockMatrix * A = (BlockMatrix *)(Ah.Ptr());
+   BlockDiagonalPreconditioner * M = new BlockDiagonalPreconditioner(A->RowOffsets());
+   M->owns_blocks = 1;
+   for (int i=0; i<A->NumRowBlocks(); i++)
+   {
+      M->SetDiagonalBlock(i,new UMFPackSolver(A->GetBlock(i,i)));
+   }
+
+   CGSolver cg;
+   cg.SetRelTol(1e-12);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(3);
+   cg.SetPreconditioner(*M);
+   cg.SetOperator(*A);
+   cg.Mult(B, X);
+
+   delete M;
+
+   a->RecoverFEMSolution(X,x);
+
+   // GridFunction u_gf;
+   double *data = x.GetData();
+   rt_gf.MakeRef(&RTfes,data);
+
+   GridFunction exact_gf(&RTfes);
+   exact_gf.ProjectCoefficient(F);
+
+   char vishost[] = "localhost";
+   int  visport   = 19916;
+   socketstream solu_sock(vishost, visport);
+   solu_sock.precision(8);
+   solu_sock << "solution\n" << mesh << rt_gf <<
+             "window_title 'Numerical u' "
+             << flush;
+
+   socketstream soltrace_sock(vishost, visport);
+   soltrace_sock.precision(8);
+   soltrace_sock << "solution\n" << mesh << exact_gf <<
+                 "window_title 'Exact' "
+                 << flush;
+
+}
+
+
+// The exact solution (for non-surface meshes)
+void F_exact(const Vector &p, Vector &F)
+{
+   int dim = p.Size();
+
+   double x = p(0);
+   double y = p(1);
+   // double z = (dim == 3) ? p(2) : 0.0; // Uncomment if F is changed to depend on z
+
+   F(0) = cos(kappa*x)*sin(kappa*y);
+   F(1) = cos(kappa*y)*sin(kappa*x);
+   if (dim == 3)
+   {
+      F(2) = 0.0;
+   }
+}
+
+// The right hand side
+void f_exact(const Vector &p, Vector &f)
+{
+   int dim = p.Size();
+
+   double x = p(0);
+   double y = p(1);
+   // double z = (dim == 3) ? p(2) : 0.0; // Uncomment if f is changed to depend on z
+
+   double temp = 1 + 2*kappa*kappa;
+
+   f(0) = temp*cos(kappa*x)*sin(kappa*y);
+   f(1) = temp*cos(kappa*y)*sin(kappa*x);
+   if (dim == 3)
+   {
+      f(2) = 0;
+   }
+}
@@ -0,0 +1,51 @@
+MFEM mesh v1.0
+
+#
+# MFEM Geometry Types (see mesh/geom.hpp):
+#
+# POINT       = 0
+# SEGMENT     = 1
+# TRIANGLE    = 2
+# SQUARE      = 3
+# TETRAHEDRON = 4
+# CUBE        = 5
+# PRISM       = 6
+#
+
+dimension
+2
+
+elements
+3
+1 3 0 1 4 3
+1 3 3 4 7 6
+1 3 1 2 5 4
+
+boundary
+8
+1 1 0 1
+1 1 1 2
+1 1 2 5
+2 1 5 4
+2 1 4 7
+1 1 7 6
+1 1 6 3
+1 1 3 0
+
+vertices
+8
+
+nodes
+FiniteElementSpace
+FiniteElementCollection: H1_2D_P1
+VDim: 2
+Ordering: 1
+
+-1 1
+-1 -0
+-1 -1
+0 1
+0 -0
+0 -1
+1 1
+1 -0
@@ -30,7 +30,6 @@
 //
 // Device sample runs:
 //               ex1 -pa -d cuda
-//               ex1 -fa -d cuda
 //               ex1 -pa -d raja-cuda
 //             * ex1 -pa -d raja-hip
 //               ex1 -pa -d occa-cuda
@@ -38,13 +37,9 @@
 //               ex1 -pa -d occa-omp
 //               ex1 -pa -d ceed-cpu
 //               ex1 -pa -d ceed-cpu -o 4 -a
-//               ex1 -pa -d ceed-cpu -m ../data/square-mixed.mesh
-//               ex1 -pa -d ceed-cpu -m ../data/fichera-mixed.mesh
 //             * ex1 -pa -d ceed-cuda
 //             * ex1 -pa -d ceed-hip
 //               ex1 -pa -d ceed-cuda:/gpu/cuda/shared
-//               ex1 -pa -d ceed-cuda:/gpu/cuda/shared -m ../data/square-mixed.mesh
-//               ex1 -pa -d ceed-cuda:/gpu/cuda/shared -m ../data/fichera-mixed.mesh
 //               ex1 -m ../data/beam-hex.mesh -pa -d cuda
 //               ex1 -m ../data/beam-tet.mesh -pa -d ceed-cpu
 //               ex1 -m ../data/beam-tet.mesh -pa -d ceed-cuda:/gpu/cuda/ref
@@ -78,7 +73,6 @@ int main(int argc, char *argv[])
   int order = 1;
   bool static_cond = false;
   bool pa = false;
-   bool fa = false;
   const char *device_config = "cpu";
   bool visualization = true;
   bool algebraic_ceed = false;
@@ -93,8 +87,6 @@ int main(int argc, char *argv[])
                  "--no-static-condensation", "Enable static condensation.");
   args.AddOption(&pa, "-pa", "--partial-assembly", "-no-pa",
                  "--no-partial-assembly", "Enable Partial Assembly.");
-   args.AddOption(&fa, "-fa", "--full-assembly", "-no-fa",
-                  "--no-full-assembly", "Enable Full Assembly.");
   args.AddOption(&device_config, "-d", "--device",
                  "Device configuration string, see Device::Configure().");
 #ifdef MFEM_USE_CEED
@@ -192,14 +184,6 @@ int main(int argc, char *argv[])
   //    domain integrator.
   BilinearForm a(&fespace);
   if (pa) { a.SetAssemblyLevel(AssemblyLevel::PARTIAL); }
-   if (fa)
-   {
-      a.SetAssemblyLevel(AssemblyLevel::FULL);
-      // Sort the matrix column indices when running on GPU or with OpenMP (i.e.
-      // when Device::IsEnabled() returns true). This makes the results
-      // bit-for-bit deterministic at the cost of somewhat longer run time.
-      a.EnableSparseMatrixSorting(Device::IsEnabled());
-   }
   a.AddDomainIntegrator(new DiffusionIntegrator(one));

   // 10. Assemble the bilinear form and the corresponding linear system,
@@ -305,8 +305,6 @@ int main(int argc, char *argv[])
         vis_w.precision(8);
         visualize(vis_w, mesh, &x, &w, "Elastic energy density", true);
      }
-      cout << "GLVis visualization paused."
-           << " Press space (in the GLVis window) to resume it.\n";
   }

   double ee0 = oper.ElasticEnergy(x.GetTrueVector());
@@ -351,11 +351,6 @@ int main(int argc, char *argv[])
         vis_w.precision(8);
         visualize(vis_w, pmesh, &x_gf, &w_gf, "Elastic energy density", true);
      }
-      if (myid == 0)
-      {
-         cout << "GLVis visualization paused."
-              << " Press space (in the GLVis window) to resume it.\n";
-      }
   }

   double ee0 = oper.ElasticEnergy(x_gf);
@@ -1,4 +1,4 @@
-//                       MFEM Example 17 - Parallel Version
+//                    MFEM Example 17 - Parallel Version
 //
 // Compile with: make ex17p
 //
@@ -43,7 +43,7 @@
 #include <sstream>
 #include <iostream>

-// Classes FE_Evolution, RiemannSolver, and FaceIntegrator
+// Classes FE_Evolution, RiemannSolver, DomainIntegrator and FaceIntegrator
 // shared between the serial and parallel version of the example.
 #include "ex18.hpp"

@@ -189,7 +189,7 @@ int main(int argc, char *argv[])
   // 7. Set up the nonlinear form corresponding to the DG discretization of the
   //    flux divergence, and assemble the corresponding mass matrix.
   MixedBilinearForm Aflux(&dfes, &fes);
-   Aflux.AddDomainIntegrator(new TransposeIntegrator(new GradientIntegrator()));
+   Aflux.AddDomainIntegrator(new DomainIntegrator(dim));
   Aflux.Assemble();

   NonlinearForm A(&vfes);
@@ -56,6 +56,27 @@ public:
               const Vector &nor, Vector &flux);
 };

+
+// Constant (in time) mixed bilinear form multiplying the flux grid function.
+// The form is (vec(v), grad(w)) where the trial space = vector L2 space (mesh
+// dim) and test space = scalar L2 space.
+class DomainIntegrator : public BilinearFormIntegrator
+{
+private:
+   Vector shape;
+   DenseMatrix flux;
+   DenseMatrix dshapedr;
+   DenseMatrix dshapedx;
+
+public:
+   DomainIntegrator(const int dim);
+
+   virtual void AssembleElementMatrix2(const FiniteElement &trial_fe,
+                                       const FiniteElement &test_fe,
+                                       ElementTransformation &Tr,
+                                       DenseMatrix &elmat);
+};
+
 // Interior face term: <F.n(u),[w]>
 class FaceIntegrator : public NonlinearFormIntegrator
 {
@@ -297,6 +318,60 @@ double RiemannSolver::Eval(const Vector &state1, const Vector &state2,
   return maxE;
 }

+// Implementation of class DomainIntegrator
+DomainIntegrator::DomainIntegrator(const int dim) : flux(num_equation, dim) { }
+
+void DomainIntegrator::AssembleElementMatrix2(const FiniteElement &trial_fe,
+                                              const FiniteElement &test_fe,
+                                              ElementTransformation &Tr,
+                                              DenseMatrix &elmat)
+{
+   // Assemble the form (vec(v), grad(w))
+
+   // Trial space = vector L2 space (mesh dim)
+   // Test space  = scalar L2 space
+
+   const int dof_trial = trial_fe.GetDof();
+   const int dof_test = test_fe.GetDof();
+   const int dim = trial_fe.GetDim();
+
+   shape.SetSize(dof_trial);
+   dshapedr.SetSize(dof_test, dim);
+   dshapedx.SetSize(dof_test, dim);
+
+   elmat.SetSize(dof_test, dof_trial * dim);
+   elmat = 0.0;
+
+   const int maxorder = max(trial_fe.GetOrder(), test_fe.GetOrder());
+   const int intorder = 2 * maxorder;
+   const IntegrationRule *ir = &IntRules.Get(trial_fe.GetGeomType(), intorder);
+
+   for (int i = 0; i < ir->GetNPoints(); i++)
+   {
+      const IntegrationPoint &ip = ir->IntPoint(i);
+
+      // Calculate the shape functions
+      trial_fe.CalcShape(ip, shape);
+      shape *= ip.weight;
+
+      // Compute the physical gradients of the test functions
+      Tr.SetIntPoint(&ip);
+      test_fe.CalcDShape(ip, dshapedr);
+      Mult(dshapedr, Tr.AdjugateJacobian(), dshapedx);
+
+      for (int d = 0; d < dim; d++)
+      {
+         for (int j = 0; j < dof_test; j++)
+         {
+            for (int k = 0; k < dof_trial; k++)
+            {
+               elmat(j, k + d * dof_trial) += shape(k) * dshapedx(j, d);
+            }
+         }
+      }
+   }
+}
+
 // Implementation of class FaceIntegrator
 FaceIntegrator::FaceIntegrator(RiemannSolver &rsolver_, const int dim) :
   rsolver(rsolver_),
@@ -1,4 +1,4 @@
-//                       MFEM Example 18 - Parallel Version
+//                         MFEM Example 18 - Parallel Version
 //
 // Compile with: make ex18
 //
@@ -43,7 +43,7 @@
 #include <sstream>
 #include <iostream>

-// Classes FE_Evolution, RiemannSolver, and FaceIntegrator
+// Classes FE_Evolution, RiemannSolver, DomainIntegrator and FaceIntegrator
 // shared between the serial and parallel version of the example.
 #include "ex18.hpp"

@@ -219,7 +219,7 @@ int main(int argc, char *argv[])
   // 9. Set up the nonlinear form corresponding to the DG discretization of the
   //    flux divergence, and assemble the corresponding mass matrix.
   MixedBilinearForm Aflux(&dfes, &fes);
-   Aflux.AddDomainIntegrator(new TransposeIntegrator(new GradientIntegrator()));
+   Aflux.AddDomainIntegrator(new DomainIntegrator(dim));
   Aflux.Assemble();

   ParNonlinearForm A(&vfes);
@@ -30,18 +30,13 @@
 //
 // Device sample runs:
 //               mpirun -np 4 ex1p -pa -d cuda
-//               mpirun -np 4 ex1p -fa -d cuda
 //               mpirun -np 4 ex1p -pa -d occa-cuda
 //               mpirun -np 4 ex1p -pa -d raja-omp
 //               mpirun -np 4 ex1p -pa -d ceed-cpu
 //               mpirun -np 4 ex1p -pa -d ceed-cpu -o 4 -a
-//               mpirun -np 4 ex1p -pa -d ceed-cpu -m ../data/square-mixed.mesh
-//               mpirun -np 4 ex1p -pa -d ceed-cpu -m ../data/fichera-mixed.mesh
 //             * mpirun -np 4 ex1p -pa -d ceed-cuda
 //             * mpirun -np 4 ex1p -pa -d ceed-hip
 //               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 -m ../data/beam-tet.mesh -pa -d ceed-cpu
 //
 // Description:  This example code demonstrates the use of MFEM to define a
@@ -79,7 +74,6 @@ int main(int argc, char *argv[])
   int order = 1;
   bool static_cond = false;
   bool pa = false;
-   bool fa = false;
   const char *device_config = "cpu";
   bool visualization = true;
   bool algebraic_ceed = false;
@@ -94,8 +88,6 @@ int main(int argc, char *argv[])
                  "--no-static-condensation", "Enable static condensation.");
   args.AddOption(&pa, "-pa", "--partial-assembly", "-no-pa",
                  "--no-partial-assembly", "Enable Partial Assembly.");
-   args.AddOption(&fa, "-fa", "--full-assembly", "-no-fa",
-                  "--no-full-assembly", "Enable Full Assembly.");
   args.AddOption(&device_config, "-d", "--device",
                  "Device configuration string, see Device::Configure().");
 #ifdef MFEM_USE_CEED
@@ -219,14 +211,6 @@ int main(int argc, char *argv[])
   //     Diffusion domain integrator.
   ParBilinearForm a(&fespace);
   if (pa) { a.SetAssemblyLevel(AssemblyLevel::PARTIAL); }
-   if (fa)
-   {
-      a.SetAssemblyLevel(AssemblyLevel::FULL);
-      // Sort the matrix column indices when running on GPU or with OpenMP (i.e.
-      // when Device::IsEnabled() returns true). This makes the results
-      // bit-for-bit deterministic at the cost of somewhat longer run time.
-      a.EnableSparseMatrixSorting(Device::IsEnabled());
-   }
   a.AddDomainIntegrator(new DiffusionIntegrator(one));

   // 12. Assemble the parallel bilinear form and the corresponding linear
@@ -1,4 +1,4 @@
-//                       MFEM Example 21 - Parallel Version
+//                                MFEM Example 21
 //
 // Compile with: make ex21p
 //
@@ -1,4 +1,4 @@
-//                                MFEM Example 22
+//                               MFEM Example 22
 //
 // Compile with: make ex22
 //
@@ -1,4 +1,4 @@
-//                                MFEM Example 24
+//                               MFEM Example 24
 //
 // Compile with: make ex24
 //
@@ -182,7 +182,7 @@ int main(int argc, char *argv[])
   }
   for (int level = 0; level < order_refinements; ++level)
   {
-      collections.Append(new H1_FECollection((int)std::pow(2, level+1), dim));
+      collections.Append(new H1_FECollection(std::pow(2, level+1), dim));
      fespaces.AddOrderRefinedLevel(collections.Last());
   }

@@ -219,7 +219,7 @@ int main(int argc, char *argv[])
   }
   for (int level = 0; level < order_refinements; ++level)
   {
-      collections.Append(new H1_FECollection((int)std::pow(2, level+1), dim));
+      collections.Append(new H1_FECollection(std::pow(2, level+1), dim));
      fespaces->AddOrderRefinedLevel(collections.Last());
   }

@@ -1,4 +1,4 @@
-//                                MFEM Example 27
+//                       MFEM Example 27 - Serial Version
 //
 // Compile with: make ex27
 //
@@ -195,7 +195,7 @@ int main(int argc, char *argv[])
   Array<int> ess_tdof_list(0);
   if (h1 && pmesh.bdr_attributes.Size())
   {
-      // For a continuous basis the linear system must be modified to enforce an
+      // For a continuous basis the linear system must be modifed to enforce an
      // essential (Dirichlet) boundary condition. In the DG case this is not
      // necessary as the boundary condition will only be enforced weakly.
      fespace.GetEssentialTrueDofs(dbc_bdr, ess_tdof_list);
@@ -1,4 +1,4 @@
-//                       MFEM Example 29 - Parallel Version
+//                      MFEM Example 29 - Parallel Version
 //
 // Compile with: make ex29p
 //
@@ -1,4 +1,4 @@
-//                                MFEM Example 30
+//                            MFEM Example 30
 //
 // Compile with: make ex30
 //
@@ -1,4 +1,4 @@
-//                       MFEM Example 30 - Parallel Version
+//                        MFEM Example 30 - Parallel Version
 //
 // Compile with: make ex30p
 //
@@ -45,10 +45,9 @@ int dim;
 int main(int argc, char *argv[])
 {
   // 1. Initialize MPI.
-   Mpi::Init(argc, argv);
-   int num_procs = Mpi::WorldSize();
-   int myid = Mpi::WorldRank();
-   Hypre::Init();
+   MPI_Session mpi;
+   int num_procs = mpi.WorldSize();
+   int myid = mpi.WorldRank();

   // 2. Parse command-line options.
   const char *mesh_file = "../data/inline-quad.mesh";
@@ -120,7 +119,7 @@ int main(int argc, char *argv[])
   }
   ParFiniteElementSpace fespace(&pmesh, fec);
   HYPRE_Int size = fespace.GlobalTrueVSize();
-   if (Mpi::Root()) { cout << "Number of H(Curl) unknowns: " << size << endl; }
+   if (mpi.Root()) { cout << "Number of H(Curl) unknowns: " << size << endl; }

   // 7. Determine the list of true (i.e. parallel conforming) essential
   //    boundary dofs. In this example, the boundary conditions are defined
@@ -182,7 +181,7 @@ int main(int argc, char *argv[])
   // 12. Solve the system AX=B using PCG with the AMS preconditioner from hypre
   if (use_ams)
   {
-      if (Mpi::Root())
+      if (mpi.Root())
      {
         cout << "Size of linear system: "
              << A.As<HypreParMatrix>()->GetGlobalNumRows() << endl;
@@ -200,7 +199,7 @@ int main(int argc, char *argv[])
   else
 #ifdef MFEM_USE_SUPERLU
   {
-      if (Mpi::Root())
+      if (mpi.Root())
      {
         cout << "Size of linear system: "
              << A.As<HypreParMatrix>()->GetGlobalNumRows() << endl;
@@ -213,7 +212,7 @@ int main(int argc, char *argv[])
   }
 #else
   {
-      if (Mpi::Root()) { cout << "No solvers available." << endl; }
+      if (mpi.Root()) { cout << "No solvers available." << endl; }
      return 1;
   }
 #endif
@@ -225,7 +224,7 @@ int main(int argc, char *argv[])
   // 14. Compute and print the H(Curl) norm of the error.
   {
      double error = sol.ComputeHCurlError(&E, &CurlE);
-      if (Mpi::Root())
+      if (mpi.Root())
      {
         cout << "\n|| E_h - E ||_{H(Curl)} = " << error << '\n' << endl;
      }
@@ -41,10 +41,9 @@ double GetScalarMax(const ParGridFunction &x);
 int main(int argc, char *argv[])
 {
   // 1. Initialize MPI.
-   Mpi::Init(argc, argv);
-   int num_procs = Mpi::WorldSize();
-   int myid = Mpi::WorldRank();
-   Hypre::Init();
+   MPI_Session mpi;
+   int num_procs = mpi.WorldSize();
+   int myid = mpi.WorldRank();

   // 2. Parse command-line options.
   const char *mesh_file = "../data/inline-quad.mesh";
@@ -123,7 +122,7 @@ int main(int argc, char *argv[])
   ParFiniteElementSpace fespace_rt(&pmesh, fec_rt);
   HYPRE_Int size_nd = fespace_nd.GlobalTrueVSize();
   HYPRE_Int size_rt = fespace_rt.GlobalTrueVSize();
-   if (Mpi::Root())
+   if (mpi.Root())
   {
      cout << "Number of H(Curl) unknowns: " << size_nd << endl;
      cout << "Number of H(Div) unknowns: " << size_rt << endl;
@@ -165,7 +164,7 @@ int main(int argc, char *argv[])
         // closed surface.
         a.AddDomainIntegrator(new VectorFEMassIntegrator(epsilon));
         shift = 1.0;
-         if (Mpi::Root())
+         if (mpi.Root())
         {
            cout << "Computing eigenvalues shifted by " << shift << endl;
         }
@@ -288,7 +287,7 @@ int main(int argc, char *argv[])

         for (int i=0; i<nev; i++)
         {
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "Eigenmode " << i+1 << '/' << nev
                    << ", Lambda = " << eigenvalues[i] - shift << endl;
@@ -409,7 +408,7 @@ int main(int argc, char *argv[])
               MPI_Barrier(MPI_COMM_WORLD);
            }
            char c;
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "press (q)uit or (c)ontinue --> " << flush;
               cin >> c;
@@ -462,7 +461,7 @@ int main(int argc, char *argv[])

         for (int i=0; i<nev; i++)
         {
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "Eigenmode " << i+1 << '/' << nev
                    << ", Lambda = " << eigenvalues[i] - shift << endl;
@@ -566,7 +565,7 @@ int main(int argc, char *argv[])
               MPI_Barrier(MPI_COMM_WORLD);
            }
            char c;
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "press (q)uit or (c)ontinue --> " << flush;
               cin >> c;
@@ -592,7 +591,7 @@ int main(int argc, char *argv[])

         for (int i=0; i<nev; i++)
         {
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "Eigenmode " << i+1 << '/' << nev
                    << ", Lambda = " << eigenvalues[i] - shift << endl;
@@ -621,7 +620,7 @@ int main(int argc, char *argv[])
            MPI_Barrier(MPI_COMM_WORLD);

            char c;
-            if (Mpi::Root())
+            if (mpi.Root())
            {
               cout << "press (q)uit or (c)ontinue --> " << flush;
               cin >> c;
@@ -1,404 +0,0 @@
-//                                MFEM Example 33
-//
-// Compile with: make ex33
-//
-// Sample runs:  ex33 -m ../data/square-disc.mesh -alpha 0.33 -o 2
-//               ex33 -m ../data/square-disc.mesh -alpha 4.5 -o 3
-//               ex33 -m ../data/star.mesh -alpha 1.4 -o 3
-//               ex33 -m ../data/star.mesh -alpha 0.99 -o 3
-//               ex33 -m ../data/inline-quad.mesh -alpha 0.5 -o 3
-//               ex33 -m ../data/amr-quad.mesh -alpha 1.5 -o 3
-//               ex33 -m ../data/disc-nurbs.mesh -alpha 0.33 -o 3
-//               ex33 -m ../data/disc-nurbs.mesh -alpha 2.4 -o 3 -r 4
-//               ex33 -m ../data/l-shape.mesh -alpha 0.33 -o 3 -r 4
-//               ex33 -m ../data/l-shape.mesh -alpha 1.7 -o 3 -r 5
-//
-// Verification runs:
-//    ex33 -m ../data/inline-segment.mesh -ver -alpha 1.7 -o 2 -r 2
-//    ex33 -m ../data/inline-quad.mesh -ver -alpha 1.2 -o 2 -r 2
-//    ex33 -m ../data/amr-quad.mesh -ver -alpha 2.6 -o 2 -r 2
-//    ex33 -m ../data/inline-hex.mesh -ver -alpha 0.3 -o 2 -r 1
-//
-//  Note: the analytic solution to this problem is u = ∏_{i=0}^{dim-1} sin(π x_i)
-//        for all alpha.
-//
-// Description:
-//
-//  In this example we solve the following fractional PDE with MFEM:
-//
-//    ( - Δ )^α u = f  in Ω,      u = 0  on ∂Ω,      0 < α,
-//
-//  To solve this FPDE, we apply the operator ( - Δ )^(-N), where the integer
-//  N is given by floor(α). By doing so, we obtain
-//
-//    ( - Δ )^(α-N) u = ( - Δ )^(-N) f  in Ω,      u = 0  on ∂Ω,      0 < α.
-//
-//  We first compute the right hand side by solving the integer order PDE
-//
-//   ( - Δ )^N g = f  in Ω, g = ( - Δ )^k g = 0 on ∂Ω, k = 1,..,N-1
-//
-//  The remaining FPDE is then given by
-//
-//  ( - Δ )^(α-N) u = g  in Ω,      u = 0  on ∂Ω.
-//
-//  We rely on a rational approximation [2] of the normal linear operator
-//  A^{-α + N}, where A = - Δ (with associated homogeneous boundary conditions)
-//  and (a-N) in (0,1). We approximate the operator
-//
-//    A^{-α+N} ≈ Σ_{i=0}^M c_i (A + d_i I)^{-1},      d_0 = 0,   d_i > 0,
-//
-//  where I is the L2-identity operator and the coefficients c_i and d_i
-//  are generated offline to a prescribed accuracy in a pre-processing step.
-//  We use the triple-A algorithm [1] to generate the rational approximation
-//  that this partial fractional expansion derives from. We then solve M+1
-//  independent integer-order PDEs,
-//
-//    A u_i + d_i u_i = c_i g  in Ω,      u_i = 0  on ∂Ω,      i=0,...,M,
-//
-//  using MFEM and sum u_i to arrive at an approximate solution of the FPDE
-//
-//    u ≈ Σ_{i=0}^M u_i.
-//
-//  (If alpha is an integer, we stop after the first PDE was solved.)
-//
-// References:
-//
-// [1] Nakatsukasa, Y., Sète, O., & Trefethen, L. N. (2018). The AAA algorithm
-//     for rational approximation. SIAM Journal on Scientific Computing, 40(3),
-//     A1494-A1522.
-//
-// [2] Harizanov, S., Lazarov, R., Margenov, S., Marinov, P., & Pasciak, J.
-//     (2020). Analysis of numerical methods for spectral fractional elliptic
-//     equations based on the best uniform rational approximation. Journal of
-//     Computational Physics, 408, 109285.
-//
-
-#include "mfem.hpp"
-#include <fstream>
-#include <iostream>
-#include <math.h>
-#include <string>
-
-#include "ex33.hpp"
-
-using namespace std;
-using namespace mfem;
-
-int main(int argc, char *argv[])
-{
-   // 1. Parse command-line options.
-   const char *mesh_file = "../data/star.mesh";
-   int order = 1;
-   int num_refs = 3;
-   double alpha = 0.5;
-   bool visualization = true;
-   bool verification = false;
-
-   OptionsParser args(argc, argv);
-   args.AddOption(&mesh_file, "-m", "--mesh",
-                  "Mesh file to use.");
-   args.AddOption(&order, "-o", "--order",
-                  "Finite element order (polynomial degree) or -1 for"
-                  " isoparametric space.");
-   args.AddOption(&num_refs, "-r", "--refs",
-                  "Number of uniform refinements");
-   args.AddOption(&alpha, "-alpha", "--alpha",
-                  "Fractional exponent");
-   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
-                  "--no-visualization",
-                  "Enable or disable GLVis visualization.");
-   args.AddOption(&verification, "-ver", "--verification", "-no-ver",
-                  "--no-verification",
-                  "Use sinusoidal function (f) for analytic comparison.");
-   args.Parse();
-   if (!args.Good())
-   {
-      args.PrintUsage(cout);
-      return 1;
-   }
-   args.PrintOptions(cout);
-
-   Array<double> coeffs, poles;
-   int progress_steps = 1;
-
-   // 2. Compute the rational expansion coefficients that define the
-   //    integer-order PDEs.
-   const int power_of_laplace = floor(alpha);
-   double exponent_to_approximate = alpha - power_of_laplace;
-   bool integer_order = false;
-   // Check if alpha is an integer or not.
-   if (abs(exponent_to_approximate) > 1e-12)
-   {
-      mfem::out << "Approximating the fractional exponent "
-                << exponent_to_approximate
-                << endl;
-      ComputePartialFractionApproximation(exponent_to_approximate, coeffs,
-                                          poles);
-
-      // If the example is build without LAPACK, the exponent_to_approximate
-      // might be modified by the function call above.
-      alpha = exponent_to_approximate + power_of_laplace;
-   }
-   else
-   {
-      integer_order = true;
-      mfem::out << "Treating integer order PDE." << endl;
-   }
-
-   // 3. Read the mesh from the given mesh file.
-   Mesh mesh(mesh_file, 1, 1);
-   int dim = mesh.Dimension();
-
-   // 4. Refine the mesh to increase the resolution.
-   for (int i = 0; i < num_refs; i++)
-   {
-      mesh.UniformRefinement();
-   }
-
-   // 5. Define a finite element space on the mesh.
-   H1_FECollection fec(order, dim);
-   FiniteElementSpace fespace(&mesh, &fec);
-   cout << "Number of finite element unknowns: "
-        << fespace.GetTrueVSize() << endl;
-
-   // 6. Determine the list of true (i.e. conforming) essential boundary dofs.
-   Array<int> ess_tdof_list;
-   if (mesh.bdr_attributes.Size())
-   {
-      Array<int> ess_bdr(mesh.bdr_attributes.Max());
-      ess_bdr = 1;
-      fespace.GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
-   }
-
-   // 7. Define diffusion coefficient, load, and solution GridFunction.
-   auto func = [&alpha](const Vector &x)
-   {
-      double val = 1.0;
-      for (int i=0; i<x.Size(); i++)
-      {
-         val *= sin(M_PI*x(i));
-      }
-      return pow(x.Size()*pow(M_PI,2), alpha) * val;
-   };
-   FunctionCoefficient f(func);
-   ConstantCoefficient one(1.0);
-   GridFunction u(&fespace);
-   GridFunction x(&fespace);
-   GridFunction g(&fespace);
-   u = 0.0;
-   x = 0.0;
-   g = 0.0;
-
-   // 8. Prepare for visualization.
-   char vishost[] = "localhost";
-   int  visport   = 19916;
-
-   // 9. Set up the linear form b(.) for integer-order PDE solves.
-   LinearForm b(&fespace);
-   if (verification)
-   {
-      // This statement is only relevant for the verification of the code. It
-      // uses a different f such that an analytic solution is known and easy
-      // to compare with the numerical one. The FPDE becomes:
-      // (-Δ)^α u = (2\pi ^2)^α sin(\pi x) sin(\pi y) on [0,1]^2
-      // -> u(x,y) = sin(\pi x) sin(\pi y)
-      b.AddDomainIntegrator(new DomainLFIntegrator(f));
-   }
-   else
-   {
-      b.AddDomainIntegrator(new DomainLFIntegrator(one));
-   }
-   b.Assemble();
-
-   // ------------------------------------------------------------------------
-   // 10. Solve the PDE (-Δ)^N g = f, i.e. compute g = (-Δ)^{-1}^N f.
-   // ------------------------------------------------------------------------
-
-   if (power_of_laplace > 0)
-   {
-      // 10.1 Compute Stiffnes Matrix
-      BilinearForm k(&fespace);
-      k.AddDomainIntegrator(new DiffusionIntegrator(one));
-      k.Assemble();
-
-      // 10.2 Compute Mass Matrix
-      BilinearForm m(&fespace);
-      m.AddDomainIntegrator(new MassIntegrator(one));
-      m.Assemble();
-      SparseMatrix mass;
-      Array<int> empty;
-      m.FormSystemMatrix(empty, mass);
-
-      // 10.3 Form the system of equations
-      Vector B, X;
-      OperatorPtr Op;
-      k.FormLinearSystem(ess_tdof_list, g, b, Op, X, B);
-      GSSmoother M((SparseMatrix&)(*Op));
-
-      mfem::out << "\nComputing (-Δ) ^ -" << power_of_laplace
-                << " ( f ) " << endl;
-      for (int i = 0; i < power_of_laplace; i++)
-      {
-         // 10.4 Solve the linear system Op X = B (N times).
-         PCG(*Op, M, B, X, 3, 300, 1e-12, 0.0);
-
-         // 10.5 Visualize the solution g of -Δ ^ N g = f in the last step
-         if (i == power_of_laplace - 1)
-         {
-            // Needed for visualization and solution verification.
-            k.RecoverFEMSolution(X, b, g);
-            if (integer_order && verification)
-            {
-               // For an integer order PDE, g is also our solution u.
-               u+=g;
-            }
-            if (visualization)
-            {
-               socketstream fout;
-               ostringstream oss_f;
-               fout.open(vishost, visport);
-               fout.precision(8);
-               oss_f.str(""); oss_f.clear();
-               oss_f << "Step " << progress_steps++ << ": Solution of PDE -Δ ^ "
-                     << power_of_laplace
-                     << " g = f";
-               fout << "solution\n" << mesh << g
-                    << "window_title '" << oss_f.str() << "'" << flush;
-            }
-         }
-
-         // 10.6 Prepare for next iteration (primal / dual space)
-         mass.Mult(X, B);
-         X.SetSubVectorComplement(ess_tdof_list,0.0);
-      }
-
-      // 10.7 Extract solution for the next step. The b now corresponds to the
-      //      function g in the PDE.
-      const SparseMatrix * R = fespace.GetRestrictionMatrix();
-      if (R)
-      {
-         R->MultTranspose(B,b);
-      }
-      else
-      {
-         b = B;
-      }
-   }
-
-   // ------------------------------------------------------------------------
-   // 11. Solve the fractional PDE by solving M integer order PDEs and adding
-   //     up the solutions.
-   // ------------------------------------------------------------------------
-   if (!integer_order)
-   {
-      // Setup visualization.
-      socketstream xout, uout;
-      ostringstream oss_x, oss_u;
-      if (visualization)
-      {
-         xout.open(vishost, visport);
-         xout.precision(8);
-         uout.open(vishost, visport);
-         uout.precision(8);
-      }
-      // Iterate over all expansion coefficient that contribute to the
-      // solution.
-      for (int i = 0; i < coeffs.Size(); i++)
-      {
-         mfem::out << "\nSolving PDE -Δ u + " << -poles[i]
-                   << " u = " << coeffs[i] << " g " << endl;
-
-
-         // 11.1 Reset GridFunction for integer-order PDE solve.
-         x = 0.0;
-
-         // 11.2 Set up the bilinear form a(.,.) for integer-order PDE solve.
-         BilinearForm a(&fespace);
-         a.AddDomainIntegrator(new DiffusionIntegrator(one));
-         ConstantCoefficient d_i(-poles[i]);
-         a.AddDomainIntegrator(new MassIntegrator(d_i));
-         a.Assemble();
-
-         // 11.3 Assemble the bilinear form and the corresponding linear system.
-         OperatorPtr A;
-         Vector B, X;
-         a.FormLinearSystem(ess_tdof_list, x, b, A, X, B);
-
-         // 11.4 Solve the linear system A X = B.
-         GSSmoother M((SparseMatrix&)(*A));
-
-         PCG(*A, M, B, X, 3, 300, 1e-12, 0.0);
-
-         // 11.5 Recover the solution as a finite element grid function.
-         a.RecoverFEMSolution(X, b, x);
-
-         // 11.6 Accumulate integer-order PDE solutions.
-         x *= coeffs[i];
-         u += x;
-
-         // 11.7 Send fractional PDE solution to a GLVis server.
-         if (visualization)
-         {
-            oss_x.str(""); oss_x.clear();
-            oss_x << "Step " << progress_steps
-                  << ": Solution of PDE -Δ u + " << -poles[i]
-                  << " u = " << coeffs[i] << " g";
-            xout << "solution\n" << mesh << x
-                 << "window_title '" << oss_x.str() << "'" << flush;
-
-            oss_u.str(""); oss_u.clear();
-            oss_u << "Step " << progress_steps + 1
-                  << ": Solution of fractional PDE (-Δ)^" << alpha
-                  << " u = f";
-            uout << "solution\n" << mesh << u
-                 << "window_title '" << oss_u.str() << "'"
-                 << flush;
-         }
-      }
-   }
-
-   // ------------------------------------------------------------------------
-   // 12. (optional) Verify the solution.
-   // ------------------------------------------------------------------------
-   if (verification)
-   {
-      auto solution = [] (const Vector &x)
-      {
-         double val = 1.0;
-         for (int i=0; i<x.Size(); i++)
-         {
-            val *= sin(M_PI*x(i));
-         }
-         return val;
-      };
-      FunctionCoefficient sol(solution);
-      double l2_error = u.ComputeL2Error(sol);
-
-      string analytic_solution,expected_mesh;
-      switch (dim)
-      {
-         case 1:
-            analytic_solution = "sin(π x)";
-            expected_mesh = "inline_segment.mesh";
-            break;
-         case 2:
-            analytic_solution = "sin(π x) sin(π y)";
-            expected_mesh = "inline_quad.mesh";
-            break;
-         default:
-            analytic_solution = "sin(π x) sin(π y) sin(π z)";
-            expected_mesh = "inline_hex.mesh";
-            break;
-      }
-
-      mfem::out << "\n" << string(80,'=')
-                << "\n\nSolution Verification in "<< dim << "D \n\n"
-                << "Analytic solution : " << analytic_solution << "\n"
-                << "Expected mesh     : " << expected_mesh <<"\n"
-                << "Your mesh         : " << mesh_file << "\n"
-                << "L2 error          : " << l2_error << "\n\n"
-                << string(80,'=') << endl;
-   }
-
-   return 0;
-}
@@ -1,401 +0,0 @@
-//                  MFEM Example 33 - Serial/Parallel Shared Code
-//                      (Implementation of the AAA algorithm)
-//
-//  Here, we implement the triple-A algorithm [1] for the rational approximation
-//  of complex-valued functions,
-//
-//          p(z)/q(z) ≈ f(z).
-//
-//  In this file, we always assume f(z) = z^{-α}. The triple-A algorithm
-//  provides a robust, accurate approximation in rational barycentric form.
-//  This representation must be transformed into a partial fraction
-//  representation in order to be used to solve a spectral FPDE.
-//
-//  More specifically, we first expand the numerator in terms of the zeros of
-//  the rational approximation,
-//
-//          p(z) ∝ Π_i (z - z_i),
-//
-//  and expand the denominator in terms of the poles of the rational
-//  approximation,
-//
-//          q(z) ∝ Π_i (z - p_i).
-//
-//  We then use these zeros and poles to derive the partial fraction expansion
-//
-//          f(z) ≈ p(z)/q(z) = Σ_i c_i / (z - p_i).
-//
-//  [1] Nakatsukasa, Y., Sète, O., & Trefethen, L. N. (2018). The AAA algorithm
-//      for rational approximation. SIAM Journal on Scientific Computing, 40(3),
-//      A1494-A1522.
-
-#include "mfem.hpp"
-#include <fstream>
-#include <iostream>
-#include <string>
-
-using namespace std;
-using namespace mfem;
-
-/** RationalApproximation_AAA: compute the rational approximation (RA) of data
-    @a val [in] at the set of points @a pt [in].
-
-    @param[in]  val        Vector of data values
-    @param[in]  pt         Vector of sample points
-    @param[in]  tol        Relative tolerance
-    @param[in]  max_order  Maximum number of terms (order) of the RA
-    @param[out] z          Support points of the RA in rational barycentric form
-    @param[out] f          Data values at support points @a z
-    @param[out] w          Weights of the RA in rational barycentric form
-
-    See pg. A1501 of Nakatsukasa et al. [1]. */
-void RationalApproximation_AAA(const Vector &val, const Vector &pt,
-                               Array<double> &z, Array<double> &f, Vector &w,
-                               double tol, int max_order)
-{
-
-   // number of sample points
-   int size = val.Size();
-   MFEM_VERIFY(pt.Size() == size, "size mismatch");
-
-   // Initializations
-   Array<int> J(size);
-   for (int i = 0; i < size; i++) { J[i] = i; }
-   z.SetSize(0);
-   f.SetSize(0);
-
-   DenseMatrix C, Ctemp, A, Am;
-   // auxiliary arrays and vectors
-   Vector f_vec;
-   Array<double> c_i;
-
-   // mean of the value vector
-   Vector R(val.Size());
-   double mean_val = val.Sum()/size;
-
-   for (int i = 0; i<R.Size(); i++) { R(i) = mean_val; }
-
-   for (int k = 0; k < max_order; k++)
-   {
-      // select next support point
-      int idx = 0;
-      double tmp_max = 0;
-      for (int j = 0; j < size; j++)
-      {
-         double tmp = abs(val(j)-R(j));
-         if (tmp > tmp_max)
-         {
-            tmp_max = tmp;
-            idx = j;
-         }
-      }
-
-      // Append support points and data values
-      z.Append(pt(idx));
-      f.Append(val(idx));
-
-      // Update index vector
-      J.DeleteFirst(idx);
-
-      // next column in Cauchy matrix
-      Array<double> C_tmp(size);
-      for (int j = 0; j < size; j++)
-      {
-         C_tmp[j] = 1.0/(pt(j)-pt(idx));
-      }
-      c_i.Append(C_tmp);
-      int h_C = C_tmp.Size();
-      int w_C = k+1;
-      C.UseExternalData(c_i.GetData(),h_C,w_C);
-
-      Ctemp = C;
-
-      f_vec.SetDataAndSize(f.GetData(),f.Size());
-      Ctemp.InvLeftScaling(val);
-      Ctemp.RightScaling(f_vec);
-
-      A.SetSize(C.Height(), C.Width());
-      Add(C,Ctemp,-1.0,A);
-      A.LeftScaling(val);
-
-      int h_Am = J.Size();
-      int w_Am = A.Width();
-      Am.SetSize(h_Am,w_Am);
-      for (int i = 0; i<h_Am; i++)
-      {
-         int ii = J[i];
-         for (int j = 0; j<w_Am; j++)
-         {
-            Am(i,j) = A(ii,j);
-         }
-      }
-
-#ifdef MFEM_USE_LAPACK
-      DenseMatrixSVD svd(Am,false,true);
-      svd.Eval(Am);
-      DenseMatrix &v = svd.RightSingularvectors();
-      v.GetRow(k,w);
-#else
-      mfem_error("Compiled without LAPACK");
-#endif
-
-      // N = C*(w.*f); D = C*w; % numerator and denominator
-      Vector aux(w);
-      aux *= f_vec;
-      Vector N(C.Height()); // Numerator
-      C.Mult(aux,N);
-      Vector D(C.Height()); // Denominator
-      C.Mult(w,D);
-
-      R = val;
-      for (int i = 0; i<J.Size(); i++)
-      {
-         int ii = J[i];
-         R(ii) = N(ii)/D(ii);
-      }
-
-      Vector verr(val);
-      verr-=R;
-
-      if (verr.Normlinf() <= tol*val.Normlinf()) { break; }
-   }
-}
-
-/** ComputePolesAndZeros: compute the @a poles [out] and @a zeros [out] of the
-    rational function f(z) = C p(z)/q(z) from its ration barycentric form.
-
-    @param[in]  z      Support points in rational barycentric form
-    @param[in]  f      Data values at support points @a z
-    @param[in]  w      Weights in rational barycentric form
-    @param[out] poles  Array of poles (roots of p(z))
-    @param[out] zeros  Array of zeros (roots of q(z))
-    @param[out] scale  Scaling constant in f(z) = C p(z)/q(z)
-
-    See pg. A1501 of Nakatsukasa et al. [1]. */
-void ComputePolesAndZeros(const Vector &z, const Vector &f, const Vector &w,
-                          Array<double> & poles, Array<double> & zeros, double &scale)
-{
-   // Initialization
-   poles.SetSize(0);
-   zeros.SetSize(0);
-
-   // Compute the poles
-   int m = w.Size();
-   DenseMatrix B(m+1); B = 0.;
-   DenseMatrix E(m+1); E = 0.;
-   for (int i = 1; i<=m; i++)
-   {
-      B(i,i) = 1.;
-      E(0,i) = w(i-1);
-      E(i,0) = 1.;
-      E(i,i) = z(i-1);
-   }
-
-#ifdef MFEM_USE_LAPACK
-   DenseMatrixGeneralizedEigensystem eig1(E,B);
-   eig1.Eval();
-   Vector & evalues = eig1.EigenvaluesRealPart();
-   for (int i = 0; i<evalues.Size(); i++)
-   {
-      if (IsFinite(evalues(i)))
-      {
-         poles.Append(evalues(i));
-      }
-   }
-#else
-   mfem_error("Compiled without LAPACK");
-#endif
-   // compute the zeros
-   B = 0.;
-   E = 0.;
-   for (int i = 1; i<=m; i++)
-   {
-      B(i,i) = 1.;
-      E(0,i) = w(i-1) * f(i-1);
-      E(i,0) = 1.;
-      E(i,i) = z(i-1);
-   }
-
-#ifdef MFEM_USE_LAPACK
-   DenseMatrixGeneralizedEigensystem eig2(E,B);
-   eig2.Eval();
-   evalues = eig2.EigenvaluesRealPart();
-   for (int i = 0; i<evalues.Size(); i++)
-   {
-      if (IsFinite(evalues(i)))
-      {
-         zeros.Append(evalues(i));
-      }
-   }
-#else
-   mfem_error("Compiled without LAPACK");
-#endif
-
-   scale = w * f / w.Sum();
-}
-
-/** PartialFractionExpansion: compute the partial fraction expansion of the
-    rational function f(z) = Σ_i c_i / (z - p_i) from its @a poles [in] and
-    @a zeros [in].
-
-    @param[in]  poles   Array of poles (same as p_i above)
-    @param[in]  zeros   Array of zeros
-    @param[in]  scale   Scaling constant
-    @param[out] coeffs  Coefficients c_i */
-void PartialFractionExpansion(double scale, Array<double> & poles,
-                              Array<double> & zeros, Array<double> & coeffs)
-{
-   int psize = poles.Size();
-   int zsize = zeros.Size();
-   coeffs.SetSize(psize);
-   coeffs = scale;
-
-   // Note: C p(z)/q(z) = Σ_i c_i / (z - p_i) results in an system of equations
-   // where the N unknowns are the coefficients c_i. After multiplying the
-   // system with q(z), the coefficients c_i can be computed analytically by
-   // choosing N values for z. Choosing z_j = = p_j diagonalizes the system and
-   // one can obtain an analytic form for the c_i coefficients. The result is
-   // implemented in the code block below.
-
-   for (int i=0; i<psize; i++)
-   {
-      double tmp_numer=1.0;
-      for (int j=0; j<zsize; j++)
-      {
-         tmp_numer *= poles[i]-zeros[j];
-      }
-
-      double tmp_denom=1.0;
-      for (int k=0; k<psize; k++)
-      {
-         if (k != i) { tmp_denom *= poles[i]-poles[k]; }
-      }
-      coeffs[i] *= tmp_numer / tmp_denom;
-   }
-}
-
-
-/** ComputePartialFractionApproximation: compute a rational approximation (RA)
-    in partial fraction form, e.g., f(z) ≈ Σ_i c_i / (z - p_i), from sampled
-    values of the function f(z) = z^{-a}, 0 < a < 1.
-
-    @param[in]  alpha         Exponent a in f(z) = z^-a
-    @param[in] lmax, npoints  f(z) is uniformly sampled @a npoints times in the
-                              interval [ 0, @a lmax ]
-    @param[in]  tol           Relative tolerance
-    @param[in]  max_order     Maximum number of terms (order) of the RA
-    @param[out] coeffs        Coefficients c_i
-    @param[out] poles         Poles p_i
-
-    NOTES: When MFEM is not built with LAPACK support, only @a alpha = 0.33,
-           0.5, and 0.99 are possible. In this case, if @a alpha != 0.33 and
-           @a alpha != 0.99, then @a alpha = 0.5 is used by default.
-
-   See pg. A1501 of Nakatsukasa et al. [1]. */
-void ComputePartialFractionApproximation(double & alpha,
-                                         Array<double> & coeffs, Array<double> & poles,
-                                         double lmax = 1000.,
-                                         double tol=1e-10, int npoints = 1000,
-                                         int max_order = 100)
-{
-   MFEM_VERIFY(alpha < 1., "alpha must be less than 1");
-   MFEM_VERIFY(alpha > 0., "alpha must be greater than 0");
-   MFEM_VERIFY(npoints > 2, "npoints must be greater than 2");
-   MFEM_VERIFY(lmax > 0,  "lmin must be greater than 0");
-   MFEM_VERIFY(tol > 0,  "tol must be greater than 0");
-
-   bool print_warning = true;
-#ifdef MFEM_USE_MPI
-   if ((Mpi::IsInitialized() && !Mpi::Root())) { print_warning = false; }
-#endif
-
-#ifndef MFEM_USE_LAPACK
-   if (print_warning)
-   {
-      mfem::out
-            << "\n" << string(80, '=')
-            << "\nMFEM is compiled without LAPACK."
-            << "\nUsing precomputed values for PartialFractionApproximation."
-            << "\nOnly alpha = 0.33, 0.5, and 0.99 are available."
-            << "\nThe default is alpha = 0.5.\n" << string(80, '=') << "\n"
-            << endl;
-   }
-   const double eps = std::numeric_limits<double>::epsilon();
-
-   if (abs(alpha - 0.33) < eps)
-   {
-      coeffs = Array<double> ({1.821898e+03, 9.101221e+01, 2.650611e+01,
-                               1.174937e+01, 6.140444e+00, 3.441713e+00,
-                               1.985735e+00, 1.162634e+00, 6.891560e-01,
-                               4.111574e-01, 2.298736e-01});
-      poles = Array<double> ({-4.155583e+04, -2.956285e+03, -8.331715e+02,
-                              -3.139332e+02, -1.303448e+02, -5.563385e+01,
-                              -2.356255e+01, -9.595516e+00, -3.552160e+00,
-                              -1.032136e+00, -1.241480e-01});
-   }
-   else if (abs(alpha - 0.99) < eps)
-   {
-      coeffs = Array<double>({2.919591e-02, 1.419750e-02, 1.065798e-02,
-                              9.395094e-03, 8.915329e-03, 8.822991e-03,
-                              9.058247e-03, 9.814521e-03, 1.180396e-02,
-                              1.834554e-02, 9.840482e-01});
-      poles = Array<double> ({-1.069683e+04, -1.769370e+03, -5.718374e+02,
-                              -2.242095e+02, -9.419132e+01, -4.031012e+01,
-                              -1.701525e+01, -6.810088e+00, -2.382810e+00,
-                              -5.700059e-01, -1.384324e-03});
-   }
-   else
-   {
-      if (abs(alpha - 0.5) > eps && print_warning)
-      {
-         alpha = 0.5;
-      }
-      coeffs = Array<double>({2.290262e+02, 2.641819e+01, 1.005566e+01,
-                              5.390411e+00, 3.340725e+00, 2.211205e+00,
-                              1.508883e+00, 1.049474e+00, 7.462709e-01,
-                              5.482686e-01, 4.232510e-01, 3.578967e-01});
-      poles = Array<double>({-3.168211e+04, -3.236077e+03, -9.868287e+02,
-                             -3.945597e+02, -1.738889e+02, -7.925178e+01,
-                             -3.624992e+01, -1.629196e+01, -6.982956e+00,
-                             -2.679984e+00, -7.782607e-01, -7.649166e-02});
-   }
-
-   if (print_warning)
-   {
-      mfem::out << "=> Using precomputed values for alpha = "
-                << alpha << "\n" << std::endl;
-   }
-
-
-   return;
-#endif
-
-   Vector x(npoints);
-   Vector val(npoints);
-   double dx = lmax / (double)(npoints-1);
-   for (int i = 0; i<npoints; i++)
-   {
-      x(i) = dx * (double)i;
-      val(i) = pow(x(i),1.-alpha);
-   }
-
-   // Apply triple-A algorithm to f(x) = x^{1-a}
-   Array<double> z, f;
-   Vector w;
-   RationalApproximation_AAA(val,x,z,f,w,tol,max_order);
-
-   Vector vecz, vecf;
-   vecz.SetDataAndSize(z.GetData(), z.Size());
-   vecf.SetDataAndSize(f.GetData(), f.Size());
-
-   // Compute poles and zeros for RA of f(x) = x^{1-a}
-   double scale;
-   Array<double> zeros;
-   ComputePolesAndZeros(vecz, vecf, w, poles, zeros, scale);
-
-   // Remove the zero at x=0, thus, delivering a RA for f(x) = x^{-a}
-   zeros.DeleteFirst(0.0);
-
-   // Compute partial fraction approximation of f(x) = x^{-a}
-   PartialFractionExpansion(scale, poles, zeros, coeffs);
-}
@@ -1,441 +0,0 @@
-//                       MFEM Example 33 - Parallel Version
-//
-// Compile with: make ex33p
-//
-// Sample runs:  mpirun -np 4 ex33p -m ../data/square-disc.mesh -alpha 0.33 -o 2
-//               mpirun -np 4 ex33p -m ../data/square-disc.mesh -alpha 4.5 -o 3
-//               mpirun -np 4 ex33p -m ../data/star.mesh -alpha 1.4 -o 3
-//               mpirun -np 4 ex33p -m ../data/star.mesh -alpha 0.99 -o 3
-//               mpirun -np 4 ex33p -m ../data/inline-quad.mesh -alpha 0.5 -o 3
-//               mpirun -np 4 ex33p -m ../data/amr-quad.mesh -alpha 1.5 -o 3
-//               mpirun -np 4 ex33p -m ../data/disc-nurbs.mesh -alpha 0.33 -o 3 -r 2
-//               mpirun -np 4 ex33p -m ../data/disc-nurbs.mesh -alpha 2.4 -o 3 -r 4
-//               mpirun -np 4 ex33p -m ../data/l-shape.mesh -alpha 0.33 -o 3 -r 4
-//               mpirun -np 4 ex33p -m ../data/l-shape.mesh -alpha 1.7 -o 3 -r 5
-//
-// Verification runs:
-//    mpirun -np 4 ex33p -m ../data/inline-segment.mesh -ver -alpha 1.7 -o 2 -r 2
-//    mpirun -np 4 ex33p -m ../data/inline-quad.mesh -ver -alpha 1.2 -o 2 -r 2
-//    mpirun -np 4 ex33p -m ../data/amr-quad.mesh -ver -alpha 2.6 -o 2 -r 2
-//    mpirun -np 4 ex33p -m ../data/inline-hex.mesh -ver -alpha 0.3 -o 2 -r 1
-
-//  Note: the analytic solution to this problem is u = ∏_{i=0}^{dim-1} sin(π x_i)
-//        for all alpha.
-//
-// Description:
-//
-//  In this example we solve the following fractional PDE with MFEM:
-//
-//    ( - Δ )^α u = f  in Ω,      u = 0  on ∂Ω,      0 < α,
-//
-//  To solve this FPDE, we apply the operator ( - Δ )^(-N), where the integer
-//  N is given by floor(α). By doing so, we obtain
-//
-//    ( - Δ )^(α-N) u = ( - Δ )^(-N) f  in Ω,      u = 0  on ∂Ω,      0 < α.
-//
-//  We first compute the right hand side by solving the integer order PDE
-//
-//   ( - Δ )^N g = f  in Ω, g = ( - Δ )^k g = 0 on ∂Ω, k = 1,..,N-1
-//
-//  The remaining FPDE is then given by
-//
-//  ( - Δ )^(α-N) u = g  in Ω,      u = 0  on ∂Ω.
-//
-//  We rely on a rational approximation [2] of the normal linear operator
-//  A^{-α + N}, where A = - Δ (with associated homogeneous boundary conditions)
-//  and (a-N) in (0,1). We approximate the operator
-//
-//    A^{-α+N} ≈ Σ_{i=0}^M c_i (A + d_i I)^{-1},      d_0 = 0,   d_i > 0,
-//
-//  where I is the L2-identity operator and the coefficients c_i and d_i
-//  are generated offline to a prescribed accuracy in a pre-processing step.
-//  We use the triple-A algorithm [1] to generate the rational approximation
-//  that this partial fractional expansion derives from. We then solve M+1
-//  independent integer-order PDEs,
-//
-//    A u_i + d_i u_i = c_i g  in Ω,      u_i = 0  on ∂Ω,      i=0,...,M,
-//
-//  using MFEM and sum u_i to arrive at an approximate solution of the FPDE
-//
-//    u ≈ Σ_{i=0}^M u_i.
-//
-//  (If alpha is an integer, we stop after the first PDE was solved.)
-//
-// References:
-//
-// [1] Nakatsukasa, Y., Sète, O., & Trefethen, L. N. (2018). The AAA algorithm
-//     for rational approximation. SIAM Journal on Scientific Computing, 40(3),
-//     A1494-A1522.
-//
-// [2] Harizanov, S., Lazarov, R., Margenov, S., Marinov, P., & Pasciak, J.
-//     (2020). Analysis of numerical methods for spectral fractional elliptic
-//     equations based on the best uniform rational approximation. Journal of
-//     Computational Physics, 408, 109285.
-//
-
-#include "mfem.hpp"
-#include <fstream>
-#include <iostream>
-#include <math.h>
-#include <string>
-
-#include "ex33.hpp"
-
-using namespace std;
-using namespace mfem;
-
-int main(int argc, char *argv[])
-{
-   // 0. Initialize MPI.
-   Mpi::Init(argc, argv);
-   int num_procs = Mpi::WorldSize();
-   int myid = Mpi::WorldRank();
-   Hypre::Init();
-
-   // 1. Parse command-line options.
-   const char *mesh_file = "../data/star.mesh";
-   int order = 1;
-   int num_refs = 3;
-   double alpha = 0.5;
-   bool visualization = true;
-   bool verification = false;
-
-   OptionsParser args(argc, argv);
-   args.AddOption(&mesh_file, "-m", "--mesh",
-                  "Mesh file to use.");
-   args.AddOption(&order, "-o", "--order",
-                  "Finite element order (polynomial degree) or -1 for"
-                  " isoparametric space.");
-   args.AddOption(&num_refs, "-r", "--refs",
-                  "Number of uniform refinements");
-   args.AddOption(&alpha, "-alpha", "--alpha",
-                  "Fractional exponent");
-   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
-                  "--no-visualization",
-                  "Enable or disable GLVis visualization.");
-   args.AddOption(&verification, "-ver", "--verification", "-no-ver",
-                  "--no-verification",
-                  "Use sinusoidal function (f) for analytic comparison.");
-   args.Parse();
-   if (!args.Good())
-   {
-      args.PrintUsage(cout);
-      return 1;
-   }
-   if (Mpi::Root())
-   {
-      args.PrintOptions(cout);
-   }
-
-   Array<double> coeffs, poles;
-   int progress_steps = 1;
-
-   // 2. Compute the rational expansion coefficients that define the
-   //    integer-order PDEs.
-   const int power_of_laplace = floor(alpha);
-   double exponent_to_approximate = alpha - power_of_laplace;
-   bool integer_order = false;
-   // Check if alpha is an integer or not.
-   if (abs(exponent_to_approximate) > 1e-12)
-   {
-      if (Mpi::Root())
-      {
-         mfem::out << "Approximating the fractional exponent "
-                   << exponent_to_approximate
-                   << endl;
-      }
-      ComputePartialFractionApproximation(exponent_to_approximate, coeffs,
-                                          poles);
-
-      // If the example is build without LAPACK, the exponent_to_approximate
-      // might be modified by the function call above.
-      alpha = exponent_to_approximate + power_of_laplace;
-   }
-   else
-   {
-      integer_order = true;
-      if (Mpi::Root())
-      {
-         mfem::out << "Treating integer order PDE." << endl;
-      }
-   }
-
-   // 3. Read the mesh from the given mesh file.
-   Mesh mesh(mesh_file, 1, 1);
-   int dim = mesh.Dimension();
-
-   // 4. Refine the mesh to increase the resolution.
-   for (int i = 0; i < num_refs; i++)
-   {
-      mesh.UniformRefinement();
-   }
-   ParMesh pmesh(MPI_COMM_WORLD, mesh);
-   mesh.Clear();
-
-   // 5. Define a finite element space on the mesh.
-   H1_FECollection fec(order, dim);
-   ParFiniteElementSpace fespace(&pmesh, &fec);
-   if (Mpi::Root())
-   {
-      cout << "Number of finite element unknowns: "
-           << fespace.GetTrueVSize() << endl;
-   }
-
-   // 6. Determine the list of true (i.e. conforming) essential boundary dofs.
-   Array<int> ess_tdof_list;
-   if (pmesh.bdr_attributes.Size())
-   {
-      Array<int> ess_bdr(pmesh.bdr_attributes.Max());
-      ess_bdr = 1;
-      fespace.GetEssentialTrueDofs(ess_bdr, ess_tdof_list);
-   }
-
-   // 7. Define diffusion coefficient, load, and solution GridFunction.
-   auto func = [&alpha](const Vector &x)
-   {
-      double val = 1.0;
-      for (int i=0; i<x.Size(); i++)
-      {
-         val *= sin(M_PI*x(i));
-      }
-      return pow(x.Size()*pow(M_PI,2), alpha) * val;
-   };
-   FunctionCoefficient f(func);
-   ConstantCoefficient one(1.0);
-   ParGridFunction u(&fespace);
-   ParGridFunction x(&fespace);
-   ParGridFunction g(&fespace);
-   u = 0.0;
-   x = 0.0;
-   g = 0.0;
-
-   // 8. Prepare for visualization.
-   char vishost[] = "localhost";
-   int  visport   = 19916;
-
-   // 9. Set up the linear form b(.) for integer-order PDE solves.
-   ParLinearForm b(&fespace);
-   if (verification)
-   {
-      // This statement is only relevant for the verification of the code. It
-      // uses a different f such that an analytic solution is known and easy
-      // to compare with the numerical one. The FPDE becomes:
-      // (-Δ)^α u = (2\pi ^2)^α sin(\pi x) sin(\pi y) on [0,1]^2
-      // -> u(x,y) = sin(\pi x) sin(\pi y)
-      b.AddDomainIntegrator(new DomainLFIntegrator(f));
-   }
-   else
-   {
-      b.AddDomainIntegrator(new DomainLFIntegrator(one));
-   }
-   b.Assemble();
-
-   // ------------------------------------------------------------------------
-   // 10. Solve the PDE (-Δ)^N g = f, i.e. compute g = (-Δ)^{-1}^N f.
-   // ------------------------------------------------------------------------
-
-   if (power_of_laplace > 0)
-   {
-      // 10.1 Compute Stiffnes Matrix
-      ParBilinearForm k(&fespace);
-      k.AddDomainIntegrator(new DiffusionIntegrator(one));
-      k.Assemble();
-
-      // 10.2 Compute Mass Matrix
-      ParBilinearForm m(&fespace);
-      m.AddDomainIntegrator(new MassIntegrator(one));
-      m.Assemble();
-      HypreParMatrix mass;
-      Array<int> empty;
-      m.FormSystemMatrix(empty, mass);
-
-      // 10.3 Form the system of equations
-      Vector B, X;
-      OperatorPtr Op;
-      k.FormLinearSystem(ess_tdof_list, g, b, Op, X, B);
-      HypreBoomerAMG prec;
-      prec.SetPrintLevel(-1);
-      CGSolver cg(MPI_COMM_WORLD);
-      cg.SetRelTol(1e-12);
-      cg.SetMaxIter(2000);
-      cg.SetPrintLevel(3);
-      cg.SetPreconditioner(prec);
-      cg.SetOperator(*Op);
-
-      if (Mpi::Root())
-      {
-         mfem::out << "\nComputing (-Δ) ^ -" << power_of_laplace
-                   << " ( f ) " << endl;
-      }
-      for (int i = 0; i < power_of_laplace; i++)
-      {
-         // 10.4 Solve the linear system Op X = B (N times).
-         cg.Mult(B, X);
-         // 10.5 Visualize the solution g of -Δ ^ N g = f in the last step
-         if (i == power_of_laplace - 1)
-         {
-            // Needed for visualization and solution verification.
-            k.RecoverFEMSolution(X, b, g);
-            if (integer_order && verification)
-            {
-               // For an integer order PDE, g is also our solution u.
-               u+=g;
-            }
-            if (visualization)
-            {
-               socketstream fout;
-               ostringstream oss_f;
-               fout.open(vishost, visport);
-               fout.precision(8);
-               oss_f.str(""); oss_f.clear();
-               oss_f << "Step " << progress_steps++ << ": Solution of PDE -Δ ^ "
-                     << power_of_laplace
-                     << " g = f";
-               fout << "parallel " << num_procs << " " << myid << "\n"
-                    << "solution\n" << pmesh << g
-                    << "window_title '" << oss_f.str() << "'" << flush;
-            }
-         }
-
-         // 10.6 Prepare for next iteration (primal / dual space)
-         mass.Mult(X, B);
-         X.SetSubVectorComplement(ess_tdof_list,0.0);
-      }
-
-      // 10.7 Extract solution for the next step. The b now corresponds to the
-      //      function g in the PDE.
-      const SparseMatrix* rm = fespace.GetRestrictionMatrix();
-      rm->MultTranspose(B, b);
-   }
-
-   // ------------------------------------------------------------------------
-   // 11. Solve the fractional PDE by solving M integer order PDEs and adding
-   //     up the solutions.
-   // ------------------------------------------------------------------------
-   if (!integer_order)
-   {
-      // Setup visualization.
-      socketstream xout, uout;
-      ostringstream oss_x, oss_u;
-      if (visualization)
-      {
-         xout.open(vishost, visport);
-         xout.precision(8);
-         uout.open(vishost, visport);
-         uout.precision(8);
-      }
-      // Iterate over all expansion coefficient that contribute to the
-      // solution.
-      for (int i = 0; i < coeffs.Size(); i++)
-      {
-         if (Mpi::Root())
-         {
-            mfem::out << "\nSolving PDE -Δ u + " << -poles[i]
-                      << " u = " << coeffs[i] << " g " << endl;
-         }
-
-         // 11.1 Reset GridFunction for integer-order PDE solve.
-         x = 0.0;
-
-         // 11.2 Set up the bilinear form a(.,.) for integer-order PDE solve.
-         ParBilinearForm a(&fespace);
-         a.AddDomainIntegrator(new DiffusionIntegrator(one));
-         ConstantCoefficient d_i(-poles[i]);
-         a.AddDomainIntegrator(new MassIntegrator(d_i));
-         a.Assemble();
-
-         // 11.3 Assemble the bilinear form and the corresponding linear system.
-         OperatorPtr A;
-         Vector B, X;
-         a.FormLinearSystem(ess_tdof_list, x, b, A, X, B);
-
-         // 11.4 Solve the linear system A X = B.
-         HypreBoomerAMG prec;
-         prec.SetPrintLevel(-1);
-
-         CGSolver cg(MPI_COMM_WORLD);
-         cg.SetRelTol(1e-12);
-         cg.SetMaxIter(2000);
-         cg.SetPrintLevel(3);
-         cg.SetPreconditioner(prec);
-         cg.SetOperator(*A);
-         cg.Mult(B, X);
-
-         // 11.5 Recover the solution as a finite element grid function.
-         a.RecoverFEMSolution(X, b, x);
-
-         // 11.6 Accumulate integer-order PDE solutions.
-         x *= coeffs[i];
-         u += x;
-
-         // 11.7 Send fractional PDE solution to a GLVis server.
-         if (visualization)
-         {
-            oss_x.str(""); oss_x.clear();
-            oss_x << "Step " << progress_steps
-                  << ": Solution of PDE -Δ u + " << -poles[i]
-                  << " u = " << coeffs[i] << " g";
-            xout << "parallel " << num_procs << " " << myid << "\n"
-                 << "solution\n" << pmesh << x
-                 << "window_title '" << oss_x.str() << "'" << flush;
-
-            oss_u.str(""); oss_u.clear();
-            oss_u << "Step " << progress_steps + 1
-                  << ": Solution of fractional PDE (-Δ)^" << alpha
-                  << " u = f";
-            uout << "parallel " << num_procs << " " << myid << "\n"
-                 << "solution\n" << pmesh << u
-                 << "window_title '" << oss_u.str() << "'"
-                 << flush;
-         }
-      }
-   }
-
-   // ------------------------------------------------------------------------
-   // 12. (optional) Verify the solution.
-   // ------------------------------------------------------------------------
-   if (verification)
-   {
-      auto solution = [] (const Vector &x)
-      {
-         double val = 1.0;
-         for (int i=0; i<x.Size(); i++)
-         {
-            val *= sin(M_PI*x(i));
-         }
-         return val;
-      };
-      FunctionCoefficient sol(solution);
-      double l2_error = u.ComputeL2Error(sol);
-
-      if (Mpi::Root())
-      {
-         string analytic_solution,expected_mesh;
-         switch (dim)
-         {
-            case 1:
-               analytic_solution = "sin(π x)";
-               expected_mesh = "inline_segment.mesh";
-               break;
-            case 2:
-               analytic_solution = "sin(π x) sin(π y)";
-               expected_mesh = "inline_quad.mesh";
-               break;
-            default:
-               analytic_solution = "sin(π x) sin(π y) sin(π z)";
-               expected_mesh = "inline_hex.mesh";
-               break;
-         }
-
-         mfem::out << "\n" << string(80,'=')
-                   << "\n\nSolution Verification in "<< dim << "D \n\n"
-                   << "Analytic solution : " << analytic_solution << "\n"
-                   << "Expected mesh     : " << expected_mesh <<"\n"
-                   << "Your mesh         : " << mesh_file << "\n"
-                   << "L2 error          : " << l2_error << "\n\n"
-                   << string(80,'=') << endl;
-      }
-   }
-
-   return 0;
-}
@@ -197,6 +197,7 @@ int main(int argc, char *argv[])
      SparseMatrix &M(mVarf->SpMat());
      SparseMatrix &B(bVarf->SpMat());
      B *= -1.;
+      B.EnsureMultTranspose();
      Bt = new TransposeOperator(&B);

      darcyOp.SetBlock(0,0, &M);
@@ -55,7 +55,6 @@ int main(int argc, char *argv[])
   bool pa = false;
   const char *device_config = "cpu";
   int max_dofs = 50000;
-   bool LSZZ = false;
   bool visualization = true;

   OptionsParser args(argc, argv);
@@ -69,9 +68,6 @@ int main(int argc, char *argv[])
                  "Device configuration string, see Device::Configure().");
   args.AddOption(&max_dofs, "-md", "--max-dofs",
                  "Stop after reaching this many degrees of freedom.");
-   args.AddOption(&LSZZ, "-ls", "--ls-zz", "-no-ls",
-                  "--no-ls-zz",
-                  "Switch to least-squares ZZ estimator.");
   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
                  "--no-visualization",
                  "Enable or disable GLVis visualization.");
@@ -155,29 +151,15 @@ int main(int argc, char *argv[])
   //     recover a smoothed flux (gradient) that is subtracted from the element
   //     flux to get an error indicator. We need to supply the space for the
   //     smoothed flux: an (H1)^sdim (i.e., vector-valued) space is used here.
-   ErrorEstimator *estimator{nullptr};
-
-   if (LSZZ)
-   {
-      estimator = new LSZienkiewiczZhuEstimator(*integ, x);
-      if (dim == 3 && mesh.GetElementType(0) != Element::HEXAHEDRON)
-      {
-         dynamic_cast<LSZienkiewiczZhuEstimator *>
-         (estimator)->SetTichonovRegularization();
-      }
-   }
-   else
-   {
-      auto flux_fes = new FiniteElementSpace(&mesh, &fec, sdim);
-      estimator = new ZienkiewiczZhuEstimator(*integ, x, flux_fes);
-      dynamic_cast<ZienkiewiczZhuEstimator *>(estimator)->SetAnisotropic();
-   }
+   FiniteElementSpace flux_fespace(&mesh, &fec, sdim);
+   ZienkiewiczZhuEstimator estimator(*integ, x, flux_fespace);
+   estimator.SetAnisotropic();

   // 11. A refiner selects and refines elements based on a refinement strategy.
   //     The strategy here is to refine elements with errors larger than a
   //     fraction of the maximum element error. Other strategies are possible.
   //     The refiner will call the given error estimator.
-   ThresholdRefiner refiner(*estimator);
+   ThresholdRefiner refiner(estimator);
   refiner.SetTotalErrorFraction(0.7);

   // 12. The main AMR loop. In each iteration we solve the problem on the
@@ -274,6 +256,5 @@ int main(int argc, char *argv[])
      b.Update();
   }

-   delete estimator;
   return 0;
 }
@@ -72,8 +72,8 @@ int main(int argc, char *argv[])
   //    largest number that gives a final mesh with no more than 10,000
   //    elements.
   {
-      int ref_levels =
-         (int)floor(log(10000./mesh->GetNE())/log(2.)/dim);
+      int ref_levels = 1;
+      // (int)floor(log(10000./mesh->GetNE())/log(2.)/dim);
      for (int l = 0; l < ref_levels; l++)
      {
         mesh->UniformRefinement();
@@ -147,6 +147,8 @@ int main(int argc, char *argv[])
   F.AddDomainIntegrator(new DomainLFIntegrator(one));
   F.Assemble();

+
+
   // 7. Set up the mixed bilinear form for the primal trial unknowns, B0,
   //    the mixed bilinear form for the interfacial unknowns, Bhat,
   //    the inverse stiffness matrix on the discontinuous test space, Sinv,
@@ -187,10 +189,17 @@ int main(int argc, char *argv[])
   // 8. Set up the 1x2 block Least Squares DPG operator, B = [B0  Bhat],
   //    the normal equation operator, A = B^t Sinv B, and
   //    the normal equation right-hand-size, b = B^t Sinv F.
-   BlockOperator B(offsets_test, offsets);
+   // BlockOperator B(offsets_test, offsets);
+
+   BlockMatrix B(offsets_test, offsets);
   B.SetBlock(0,0,&matB0);
   B.SetBlock(0,1,&matBhat);
-   RAPOperator A(B, matSinv, B);
+   SparseMatrix * Bh = B.CreateMonolithic();
+
+   SparseMatrix * A = RAP(*Bh, matSinv, *Bh);
+
+
+   // RAPOperator A(B, matSinv, B);
   {
      Vector SinvF(s_test);
      matSinv.Mult(F,SinvF);
@@ -234,7 +243,20 @@ int main(int argc, char *argv[])
   // 10. Solve the normal equation system using the PCG iterative solver.
   //     Check the weighted norm of residual for the DPG least square problem.
   //     Wrap the primal variable in a GridFunction for visualization purposes.
-   PCG(A, P, b, x, 1, 200, 1e-12, 0.0);
+
+
+   // PCG(*A, P, b, x, 1, 200, 1e-12, 0.0);
+
+   GSSmoother M(*A);
+
+   CGSolver cg;
+   cg.SetRelTol(1e-12);
+   cg.SetMaxIter(2000);
+   cg.SetPrintLevel(3);
+   cg.SetPreconditioner(M);
+   cg.SetOperator(*A);
+   cg.Mult(b, x);
+

   {
      Vector LSres(s_test);
@@ -23,10 +23,10 @@ MFEM_LIB_FILE = mfem_is_not_built

 SEQ_EXAMPLES = ex0 ex1 ex2 ex3 ex4 ex5 ex6 ex7 ex8 ex9 ex10 ex14 ex15 ex16 \
  ex17 ex18 ex19 ex20 ex21 ex22 ex23 ex24 ex25 ex26 ex27 ex28 ex29 ex30 \
-  ex31 ex33
+  ex31
 PAR_EXAMPLES = ex0p ex1p ex2p ex3p ex4p ex5p ex6p ex7p ex8p ex9p ex10p ex11p \
  ex12p ex13p ex14p ex15p ex16p ex17p ex18p ex19p ex20p ex21p ex22p ex24p \
-  ex25p ex26p ex27p ex28p ex29p ex30p ex31p ex32p ex33p
+  ex25p ex26p ex27p ex28p ex29p ex30p ex31p ex32p
 SEQ_DEVICE_EXAMPLES = ex1 ex3 ex4 ex5 ex6 ex9 ex22 ex24 ex25 ex26
 PAR_DEVICE_EXAMPLES = ex1p ex2p ex3p ex4p ex5p ex6p ex7p ex9p ex13p ex22p \
  ex24p ex25p ex26p
@@ -58,9 +58,6 @@ endif
 ifeq ($(MFEM_USE_SUPERLU),YES)
   SUBDIRS += superlu
 endif
-ifeq ($(MFEM_USE_MOONOLITH),YES)
-   SUBDIRS += moonolith
-endif
 ifeq ($(MFEM_USE_CALIPER),YES)
   SUBDIRS += caliper
 endif
@@ -91,11 +88,8 @@ $(SUBDIRS_TPRINT):

 # Additional dependencies
 ex18: $(SRC)ex18.hpp
-ex33: $(SRC)ex33.hpp
-
 ifeq ($(MFEM_USE_MPI),YES)
 ex18p: $(SRC)ex18.hpp
-ex33p: $(SRC)ex33.hpp
 endif

 MFEM_TESTS = EXAMPLES
@@ -1,57 +0,0 @@
-# Copyright (c) 2010-2022, 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.
-
-set(MOONOLITH_EXAMPLES_SRCS)
-list(APPEND MOONOLITH_EXAMPLES_SRCS ex1.cpp)
-
-if (MFEM_USE_MPI)
-  list(APPEND MOONOLITH_EXAMPLES_SRCS ex1p.cpp ex2p.cpp)
-endif()
-
-# Include the source directory where mfem.hpp and mfem-performance.hpp are.
-include_directories(BEFORE ${PROJECT_BINARY_DIR})
-
-# Add "test_moonolith" target, see below.
-add_custom_target(test_moonolith
-  ${CMAKE_CTEST_COMMAND} -R moonolith USES_TERMINAL)
-
-# Add one executable per cpp file, adding "moonolith_" as prefix. Sets
-# "test_moonolith" as a target that depends on the given examples.
-set(PFX moonolith_)
-add_mfem_examples(MOONOLITH_EXAMPLES_SRCS ${PFX} "" test_moonolith)
-
-# Testing.
-# The MOONOLITH tests can be run separately using the target "test_moonolith"
-# which builds the examples and runs:
-#   ctest -R moonolith
-
-# Add the tests: one test per source file.
-foreach(SRC_FILE ${MOONOLITH_EXAMPLES_SRCS})
-  get_filename_component(SRC_FILENAME ${SRC_FILE} NAME)
-  string(REPLACE ".cpp" "" TEST_NAME ${SRC_FILENAME})
-  string(TOUPPER ${TEST_NAME} UP_TEST_NAME)
-  set(TEST_NAME ${PFX}${TEST_NAME})
-
-  set(THIS_TEST_OPTIONS "-no-vis")
-  list(APPEND THIS_TEST_OPTIONS ${${UP_TEST_NAME}_TEST_OPTS})
-  # message(STATUS "Test ${TEST_NAME} options: ${THIS_TEST_OPTIONS}")
-
-  if (NOT (${TEST_NAME} MATCHES ".*p$"))
-    add_test(NAME ${TEST_NAME}_ser
-      COMMAND ${TEST_NAME} ${THIS_TEST_OPTIONS})
-  else()
-    add_test(NAME ${TEST_NAME}_np=4
-      COMMAND ${MPIEXEC} ${MPIEXEC_NUMPROC_FLAG} 4
-      ${MPIEXEC_PREFLAGS}
-      $<TARGET_FILE:${TEST_NAME}> ${THIS_TEST_OPTIONS}
-      ${MPIEXEC_POSTFLAGS})
-  endif()
-endforeach()
@@ -1,18 +0,0 @@
-                    Finite Element Discretization Library
-                                   __
-                       _ __ ___   / _|  ___  _ __ ___
-                      | '_ ` _ \ | |_  / _ \| '_ ` _ \
-                      | | | | | ||  _||  __/| | | | | |
-                      |_| |_| |_||_|   \___||_| |_| |_|
-
-                               https://mfem.org
-
-This directory contains modifications of the example codes that illustrate the
-use of MFEM features based on ParMoonolith library for variational information
-transfer between non-matching meshes.
-
-To build these examples, make sure that MFEM is configured with the option
-"MFEM_USE_MOONOLITH = YES".
-
-For the parallel version add also the options MFEM_USE_MPI = YES", and
-MFEM_USE_METIS = YES". See the top-level INSTALL file for details.
@@ -1,229 +0,0 @@
-//                         MFEM + Moonolith Example 1
-//
-// Compile with: make ex1
-//
-// Moonolith sample runs:
-//   ex1
-//   ex1 --source_refinements 1 --dest_refinements 2
-//   ex1 --source_refinements 1 --dest_refinements 2 --use_vector_fe
-//   ex1 -s ../../data/inline-hex.mesh -d ../../data/inline-tet.mesh
-//
-// Description:  This example code demonstrates the use of MFEM for transferring
-//               discrete fields from one finite element mesh to another. The
-//               meshes can be of arbitrary shape and completely unrelated with
-//               each other. This feature can be used for implementing immersed
-//               domain methods for fluid-structure interaction or general
-//               multi-physics applications.
-//
-//               This particular example is only for serial runtimes.
-
-#include "example_utils.hpp"
-#include "mfem.hpp"
-
-using namespace mfem;
-using namespace std;
-
-int main(int argc, char *argv[])
-{
-   // Init transfer library context
-   InitTransfer(argc, argv);
-
-   const char *source_mesh_file = "../../data/inline-tri.mesh";
-   const char *destination_mesh_file = "../../data/inline-quad.mesh";
-
-   int src_n_refinements = 0;
-   int dest_n_refinements = 0;
-   int source_fe_order = 1;
-   int dest_fe_order = 1;
-   bool visualization = true;
-   bool use_vector_fe = false;
-   bool verbose = false;
-
-   OptionsParser args(argc, argv);
-   args.AddOption(&source_mesh_file, "-s", "--source_mesh",
-                  "Mesh file to use for src.");
-   args.AddOption(&destination_mesh_file, "-d", "--destination_mesh",
-                  "Mesh file to use for dest.");
-   args.AddOption(&src_n_refinements, "-sr", "--source_refinements",
-                  "Number of src refinements");
-   args.AddOption(&dest_n_refinements, "-dr", "--dest_refinements",
-                  "Number of dest refinements");
-   args.AddOption(&visualization, "-vis", "--visualization", "-no-vis",
-                  "--no-visualization",
-                  "Enable or disable GLVis visualization.");
-   args.AddOption(&source_fe_order, "-so", "--source_fe_order",
-                  "Order of the src finite elements");
-   args.AddOption(&dest_fe_order, "-do", "--dest_fe_order",
-                  "Order of the dest finite elements");
-   args.AddOption(&verbose, "-verb", "--verbose", "--no-verb", "--no-verbose",
-                  "Enable/Disable verbose output");
-   args.AddOption(&use_vector_fe, "-vfe", "--use_vector_fe", "-no-vfe",
-                  "--no-vector_fe", "Use vector finite elements");
-   args.Parse();
-   check_options(args);
-
-   shared_ptr<Mesh> src_mesh, dest_mesh;
-
-   ifstream imesh;
-
-   imesh.open(destination_mesh_file);
-   if (imesh)
-   {
-      dest_mesh = make_shared<Mesh>(imesh, 1, 1);
-      imesh.close();
-   }
-   else
-   {
-      mfem::err << "WARNING: Destination mesh file not found: "
-                << destination_mesh_file << "\n"
-                << "Using default 2D quad mesh.";
-
-      dest_mesh = make_shared<Mesh>(4, 4, Element::QUADRILATERAL);
-   }
-
-   const int dim = dest_mesh->Dimension();
-
-   Vector box_min(dim), box_max(dim), range(dim);
-   dest_mesh->GetBoundingBox(box_min, box_max);
-   range = box_max;
-   range -= box_min;
-
-   imesh.open(source_mesh_file);
-
-   if (imesh)
-   {
-      src_mesh = make_shared<Mesh>(imesh, 1, 1);
-      imesh.close();
-   }
-   else
-   {
-      mfem::err << "WARNING: Source mesh file not found: " << source_mesh_file
-                << "\n"
-                << "Using default box mesh.\n";
-
-      if (dim == 2)
-      {
-         src_mesh =
-            make_shared<Mesh>(4, 4, Element::TRIANGLE, 1, range[0], range[1]);
-      }
-      else if (dim == 3)
-      {
-         src_mesh = make_shared<Mesh>(4, 4, 4, Element::TETRAHEDRON, 1, range[0],
-                                      range[1], range[2]);
-      }
-
-      for (int i = 0; i < src_mesh->GetNV(); ++i)
-      {
-         double *v = src_mesh->GetVertex(i);
-
-         for (int d = 0; d < dim; ++d)
-         {
-            v[d] += box_min[d];
-         }
-      }
-   }
-
-   for (int i = 0; i < src_n_refinements; ++i)
-   {
-      src_mesh->UniformRefinement();
-   }
-
-   for (int i = 0; i < dest_n_refinements; ++i)
-   {
-      dest_mesh->UniformRefinement();
-   }
-
-   shared_ptr<FiniteElementCollection> src_fe_coll, dest_fe_coll;
-
-   if (use_vector_fe)
-   {
-      src_fe_coll =
-         make_shared<RT_FECollection>(source_fe_order, src_mesh->Dimension());
-      dest_fe_coll =
-         make_shared<RT_FECollection>(dest_fe_order, dest_mesh->Dimension());
-   }
-   else
-   {
-      src_fe_coll =
-         make_shared<L2_FECollection>(source_fe_order, src_mesh->Dimension());
-      dest_fe_coll =
-         make_shared<L2_FECollection>(dest_fe_order, dest_mesh->Dimension());
-   }
-
-   auto src_fe =
-      make_shared<FiniteElementSpace>(src_mesh.get(), src_fe_coll.get());
-
-   auto dest_fe =
-      make_shared<FiniteElementSpace>(dest_mesh.get(), dest_fe_coll.get());
-
-   GridFunction src_fun(src_fe.get());
-   GridFunction dest_fun(dest_fe.get());
-   src_fun = 1.0;
-
-   // To be used with standard fe
-   FunctionCoefficient coeff(example_fun);
-
-   // To be used with vector fe
-   VectorFunctionCoefficient vector_coeff(dim, &vector_fun);
-
-   if (use_vector_fe)
-   {
-      src_fun.ProjectCoefficient(vector_coeff);
-      src_fun.Update();
-   }
-   else
-   {
-      src_fun.ProjectCoefficient(coeff);
-      src_fun.Update();
-   }
-
-   dest_fun = 0.0;
-   dest_fun.Update();
-
-   MortarAssembler assembler(src_fe, dest_fe);
-   assembler.SetVerbose(verbose);
-
-   if (use_vector_fe)
-   {
-      assembler.AddMortarIntegrator(make_shared<VectorL2MortarIntegrator>());
-   }
-   else
-   {
-      assembler.AddMortarIntegrator(make_shared<L2MortarIntegrator>());
-   }
-
-   if (assembler.Transfer(src_fun, dest_fun))
-   {
-      if (visualization)
-      {
-         dest_fun.Update();
-
-         double src_err = 0;
-         double dest_err = 0;
-
-         if (use_vector_fe)
-         {
-            src_err = src_fun.ComputeL2Error(vector_coeff);
-            dest_err = dest_fun.ComputeL2Error(vector_coeff);
-         }
-         else
-         {
-            src_err = src_fun.ComputeL2Error(coeff);
-            dest_err = dest_fun.ComputeL2Error(coeff);
-         }
-
-         mfem::out << "l2 error: src: " << src_err << ", dest: " << dest_err
-                   << std::endl;
-
-         plot(*src_mesh, src_fun, "source");
-         plot(*dest_mesh, dest_fun, "destination");
-      }
-   }
-   else
-   {
-      mfem::out << "No intersection -> no transfer!" << std::endl;
-   }
-
-   // Finalize transfer library context
-   return FinalizeTransfer();
-}
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Socratis Petrides	d322228504	testing dpg residual with cholesky factors	2022-03-22 14:13:56 -07:00
Socratis Petrides	2cc8c18250	fix repo check	2022-03-22 12:08:56 -07:00
Socratis Petrides	48c54c0bbc	fix repo-check	2022-03-22 12:05:22 -07:00
Socratis Petrides	aa9a4887f7	change to 2022	2022-03-22 10:24:38 -07:00
Socratis Petrides	757369beb3	Merge branch 'master' into dpg-dev	2022-03-22 10:19:35 -07:00
Socratis Petrides	6967342813	minor	2022-03-03 13:06:29 -08:00
Socratis Petrides	ba94547c4d	fixing residual computation	2022-03-01 19:20:44 -08:00
Socratis Petrides	58f7aacce9	fix acoustics graph norm	2022-02-25 17:45:49 -08:00
psocratis	66e0c79b3f	small valgrind fix in the parallel case	2022-02-11 09:50:52 -08:00
psocratis	8b5f9f7720	resolving conflicts	2022-02-09 19:50:00 -08:00
psocratis	98739f8c09	fix valgrind complaints in the serial case	2022-02-09 19:41:48 -08:00
Socratis Petrides	84129a1f83	finished Block-sc in the parallel case, uw_dpgp passes initial tests	2022-02-09 17:04:01 -08:00
Socratis Petrides	b6ea025795	cleanup, started on par sc case	2022-02-02 20:18:19 -08:00
Socratis Petrides	d528e9d63e	filling blockstaticcond destructor	2022-02-01 10:19:19 -08:00
Socratis Petrides	d18f11e6c7	blockstatic-cond passes tests for primal-dpg	2022-01-31 17:56:37 -08:00
Socratis Petrides	efeb400b27	Block sc FormSystemMatrix. Started on ReduceSystem	2022-01-28 20:01:07 -08:00
Socratis Petrides	1451c3c483	small bug-fix in assembly if doftrans is not null	2022-01-27 17:33:04 -08:00
Socratis Petrides	f12d46bdf9	Shur complement assembly and conforming assembly	2022-01-27 17:31:55 -08:00
Socratis Petrides	6dfb809f97	changing GetSubMatrix to const	2022-01-27 17:30:38 -08:00
Socratis Petrides	ef8785b852	computing indices for interior/interface local dofs for block-static-cond	2022-01-26 18:24:56 -08:00
Socratis Petrides	efd182ec4c	visualize mesh in amr for the l-shape problem	2022-01-26 18:23:12 -08:00
Socratis Petrides	e7856b982a	style	2022-01-26 10:59:38 -08:00
Socratis Petrides	4f4d1f9d2d	adding function signatures in blockstaticcond	2022-01-26 10:59:19 -08:00
Socratis Petrides	1a89d5af02	started on static condensation for DPG (block) systems	2022-01-25 19:45:40 -08:00
Socratis Petrides	c71b02a915	fix print format	2022-01-21 14:37:21 -08:00
Socratis Petrides	5576f3653e	style	2022-01-21 13:45:29 -08:00
Socratis Petrides	7f316dd07b	changing strong_dpg to use vdim>1 test space	2022-01-21 13:45:00 -08:00
Socratis Petrides	19b5ae6b9a	parallel examples acoustics uw_dpg	2022-01-21 13:44:17 -08:00
Socratis Petrides	94cd8859b2	adding adjoint graphnorm in uw_dpg for acoustics	2022-01-21 13:43:56 -08:00
Socratis Petrides	8ea8b97fc8	adding vdim>1 for test spaces in normalequations	2022-01-21 13:43:00 -08:00
Socratis Petrides	f9abc77026	clean up	2022-01-20 16:45:43 -08:00
Socratis Petrides	68e3f9aeb9	adding traditional fosls formulation for acoustics (real)	2022-01-20 16:34:51 -08:00
Socratis Petrides	08f018c299	adding uw dpg formulation for acoustics (real)	2022-01-20 16:33:58 -08:00
Socratis Petrides	69e57546d4	adding 'strong' dpg formulation for acoustics	2022-01-20 16:33:35 -08:00
Socratis Petrides	433a29c9e3	fixing comment in diffusion fosls	2022-01-20 16:32:47 -08:00
Socratis Petrides	92ee7099a4	reorganizing examples	2022-01-19 11:05:16 -08:00
Socratis Petrides	808c9cd2c4	Merge branch 'master' into dpg-dev	2022-01-19 10:10:05 -08:00
Socratis Petrides	f3cd0a10e7	minor	2022-01-17 11:30:23 -08:00
Socratis Petrides	e6bb8c8976	small bugfix in updating mesh dependent coefficient	2022-01-05 18:09:49 -08:00
Socratis Petrides	4718577810	bug-fix serial AMR in normalequations P/R Mult in RHS and Sol vector	2021-12-30 19:59:14 -08:00
Socratis Petrides	9e520183c8	Merge branch 'master' into dpg-dev	2021-12-30 09:26:52 -08:00
Socratis Petrides	95a40d7377	clean up convection-diffusion	2021-12-22 14:40:11 -08:00
Socratis Petrides	036846bcd6	adding parallel convection-diffusion with AMR example	2021-12-21 17:59:56 -08:00
Socratis Petrides	6c2968156f	Merge branch 'master' into dpg-dev	2021-12-21 10:01:43 -08:00
Socratis Petrides	9ba650f2fd	adding Erikson Johnson problem for convection-diffusion UW-DPG	2021-12-17 16:34:22 -08:00
Socratis Petrides	ee6cb39ee0	Merge branch 'pncmesh-getessvdof-fix' into dpg-dev	2021-12-16 09:46:14 -08:00
Socratis Petrides	1701a6e84c	Merge branch 'master' into dpg-dev	2021-12-16 09:45:02 -08:00
Socratis Petrides	f500e5220a	Parallel AMR for lshape	2021-12-15 18:28:31 -08:00
Socratis Petrides	e078288ecb	title fix	2021-12-15 12:40:42 -08:00
Socratis Petrides	e46c7ac0e7	fix sample run and title in the example	2021-12-15 12:39:33 -08:00
Socratis Petrides	c2b133f3c8	minor visualization edits	2021-12-15 12:37:46 -08:00
Socratis Petrides	373379fbdd	lshape mesh	2021-12-15 12:20:41 -08:00
Socratis Petrides	bfc3835a1d	adding AMR l-shape example in diffusion_uwdpg	2021-12-15 12:20:08 -08:00
Socratis Petrides	ab8578a728	add element residual computation to NormalEquations	2021-12-15 12:19:30 -08:00
Socratis Petrides	fdaaacfdf3	Started residual based error estimator. Done some refactoring	2021-12-13 17:36:52 -08:00
Socratis Petrides	5d7ebbb51a	fixed small size bug in DenseMatrix::GetSubMatrix	2021-12-13 17:35:26 -08:00
Socratis Petrides	fe0821413a	adding parallel test for uw diffusion	2021-12-09 15:16:49 -08:00
Socratis Petrides	695a5adcb2	ParNormalEquations cleanup	2021-12-09 15:16:15 -08:00
Socratis Petrides	b2dfc76f1a	minor changes in serial example	2021-12-09 15:13:54 -08:00
Socratis Petrides	76c700b41e	adding BlockOperator and BlockMatrix in OpType	2021-12-09 15:13:05 -08:00
Socratis Petrides	dc3f10fa63	Passing first tests in parallel for ParNormalEquations	2021-12-08 17:36:34 -08:00
Socratis Petrides	420bb73d6c	minor change in normal equations constructor	2021-12-08 17:36:11 -08:00
Socratis Petrides	13648768ae	removing unused code	2021-12-08 17:34:00 -08:00
Socratis Petrides	7bfda36bca	Starting ParNormalEquations -> adding class methods signatures	2021-12-07 18:48:24 -08:00
Socratis Petrides	46fc3ce9c2	remove not used code	2021-12-07 18:47:20 -08:00
Socratis Petrides	b3086ce754	Merge branch 'master' into dpg-dev	2021-12-07 13:05:01 -08:00
Socratis Petrides	d1312d354a	minor bug-fix in the adjoint graph norm	2021-12-03 20:04:49 -08:00
Socratis Petrides	16fcc3f970	Fixing P and R null diagonal blocks to act as Identity for L2 Space and AMR	2021-12-03 20:04:23 -08:00
Socratis Petrides	a6caab3bed	PartMult and AddPartMult for BlockMatrix	2021-12-03 19:53:27 -08:00
Socratis Petrides	172b5bdcc9	Modifying DPG examples to use block-diagonal preconditioners	2021-12-02 17:25:03 -08:00
Socratis Petrides	72f83c132d	Changing normalequations to use only BlockMatrix	2021-12-02 17:24:25 -08:00
Socratis Petrides	911e394d80	adding EliminateRowCols with saving Ae to BlockMatrix class	2021-12-02 17:22:36 -08:00
Socratis Petrides	4ff29e40c9	Refactoring NormalEquations assemble to use BlockMatrix	2021-12-01 19:00:07 -08:00
Socratis Petrides	dac7808875	style	2021-11-30 18:23:31 -08:00
Socratis Petrides	246fd8e6fe	started element residual calculation for AMR	2021-11-30 18:23:09 -08:00
Socratis Petrides	5e243e01f8	clean up	2021-11-30 18:22:31 -08:00
Socratis Petrides	56b83ea538	UW-DPG with AMR: fixing Block Prolongation/Restriction Operators	2021-11-30 16:41:21 -08:00
Socratis Petrides	cd7371896a	removing no longer needed test	2021-11-29 17:30:01 -08:00
Socratis Petrides	3fdd3e2450	style	2021-11-29 17:28:42 -08:00
Socratis Petrides	303ccefd83	completing the descructor	2021-11-29 17:28:17 -08:00
Socratis Petrides	48bcc332f7	fix piola map bug in NormalTraceIntegrator	2021-11-29 17:19:05 -08:00
Socratis Petrides	0c23d23874	new diffusion uw-dpg with adjoint graph norm	2021-11-29 17:17:54 -08:00
Socratis Petrides	e76cef225d	UW-DPG for diffusion works on quad meshes	2021-11-28 15:03:34 -08:00
Socratis Petrides	6f49201e62	Ultraweak-DPG for poisson prototype	2021-11-27 14:23:24 -08:00
Socratis Petrides	1cb75f7730	adding diffusion UW-DPG	2021-11-24 16:56:15 -08:00
Socratis Petrides	ef14d682c5	bug-fix ElementTrasformation	2021-11-24 16:55:45 -08:00
Socratis Petrides	54eb78e0df	adding block primal test	2021-11-23 17:13:22 -08:00
Socratis Petrides	cd1a3a4fc7	fixing minor bug in B^T G^-1 l	2021-11-23 17:12:02 -08:00
Socratis Petrides	ffb50c2416	example tests cleanup	2021-11-23 10:05:44 -08:00
Socratis Petrides	f568ca3c6e	bug fix on accumulating domain integrators	2021-11-23 10:03:13 -08:00
Socratis Petrides	c7fb058051	adding NormalTraceIntegrator and AssembleElementMatrix2 for DivDivIntegrator	2021-11-23 09:58:11 -08:00
Socratis Petrides	a4d87d936b	Adding NormalEquations Assembly for multiple spaces and integrators. Tested succesfully for primal DPG	2021-11-19 19:52:27 -08:00
Socratis Petrides	f26bd4bea1	generalizing NormalEquations assembly for multiple fespaces and integrators	2021-11-18 17:20:30 -08:00
Socratis Petrides	6c001c3f9a	adding example test for primal DPG	2021-11-15 17:57:09 -08:00
Socratis Petrides	82573af316	new Primal DPG reproduces ex8	2021-11-15 17:56:16 -08:00
Socratis Petrides	4bfb2d62d9	first primal dpg test runs	2021-11-15 13:41:57 -08:00
Socratis Petrides	0bf7a715db	minor cleanup	2021-11-12 20:04:01 -08:00
Socratis Petrides	ad68c8f245	Fixing doc complaints	2021-11-12 18:52:48 -08:00
Socratis Petrides	0b430fa5f6	Started NormalEquationsWeakFormulation::Assemble	2021-11-12 18:49:06 -08:00
Socratis Petrides	238d1921c7	adding TraceIntegrator and AssembleTraceFaceMatrix	2021-11-12 18:48:05 -08:00
Socratis Petrides	a25783e3b4	Simplifying P and R in BlockBilinearForm	2021-11-04 09:43:40 -07:00
Socratis Petrides	3aa8d49ca8	started implementation of trace_elem_integrators for DPG	2021-11-03 18:29:08 -07:00
Socratis Petrides	4ed6a4a014	fixing minor bug in reference BlockFOSLS case	2021-11-03 15:11:20 -07:00
Socratis Petrides	08f910343b	AMR for reference Block FOSLS	2021-11-03 11:16:59 -07:00
Socratis Petrides	9fb0340206	fixing minor bug in P/R for AMR with blockforms	2021-11-03 09:03:18 -07:00
Socratis Petrides	db40e8125e	Setting Prolongation/Restriction for BlockBilinearForm. Tested for 2D AMR	2021-11-02 18:56:07 -07:00
Socratis Petrides	3e46fce65f	simplifying BlockBilinearFrom::Assembly()	2021-11-02 17:53:50 -07:00
Socratis Petrides	f649ed6b62	investigating possible bug in high order 3D runs wrt to essential BC elimination (example 1 hexa mesh)	2021-11-01 17:34:59 -07:00
Socratis Petrides	a1a3a51d86	simplifying offset calculation wrt neg orientation	2021-11-01 17:34:05 -07:00
Socratis Petrides	6728fc7eda	make style	2021-11-01 16:44:38 -07:00
Socratis Petrides	71e9d4e1d9	poisson_fosls - reference implementation	2021-11-01 16:44:00 -07:00
Socratis Petrides	7feb560f9b	testing blockbilinearform with FOSLS poisson	2021-11-01 16:43:28 -07:00
Socratis Petrides	aa9eadfcdf	fixing orientation (sign) bug in blockbilinearform assemble	2021-11-01 16:42:59 -07:00
Socratis Petrides	82122f05cf	testing block integrator by borrowing (bi)linearIntegrators	2021-11-01 16:42:20 -07:00
Socratis Petrides	2d64fa2162	fix bug in blocklinearform assemble	2021-11-01 16:41:21 -07:00
Socratis Petrides	8041734755	adding DenseMatrix::SetSubMatrix functions	2021-11-01 16:40:24 -07:00
Socratis Petrides	523891f05f	adding BlockLinearForm (assemble) with testblocklinearinteg	2021-10-29 18:32:31 -07:00
Socratis Petrides	b3fc46b6f2	Merge branch 'master' into dpg-dev	2021-10-29 16:43:38 -07:00
Socratis Petrides	9271494723	Merge branch 'master' into dpg-dev	2021-10-27 08:45:53 -07:00
Socratis Petrides	f2dbcecb92	debugging BlockBilinearForm::Assemble()	2021-10-25 16:47:32 -07:00
Socratis Petrides	f2af9748c4	fixing offset computation in BlockBilinearForm::Assemble()	2021-10-22 19:39:51 -07:00
Socratis Petrides	9813dd7722	fix doxygen complaint	2021-10-22 19:28:52 -07:00
Socratis Petrides	3806e68ed1	adding new classes (block(bi)linearForms(integ) in support for DPG methods	2021-10-22 17:58:52 -07:00