Updated apps to use new architecture

Added field tracking by ID and generalized interface
fixed cmake
2026-02-25 15:19:10 -08:00 · 2026-01-27 10:24:09 -07:00 · 2026-01-06 18:59:44 -08:00 · 2026-01-06 18:53:05 -08:00 · 2026-01-06 18:49:38 -08:00 · 2025-11-19 14:28:38 -08:00
238 changed files with 9556 additions and 15906 deletions
@@ -25,7 +25,7 @@ runs:
  steps:
    - uses: ./.github/actions/sanitize/config

-    - uses: actions/cache@v5
+    - uses: actions/cache@v4
      if: ${{env.DEBUG == 'true'}}
      id: debug
      with:
@@ -36,7 +36,7 @@ runs:
  steps:
    - uses: ./.github/actions/sanitize/config

-    - uses: actions/cache@v5
+    - uses: actions/cache@v4
      if: ${{env.DEBUG == 'true' && inputs.cache-skip != 'true'}}
      id: debug
      with:
@@ -23,7 +23,7 @@ inputs:
 runs:
  using: 'composite'
  steps:
-    - uses: actions/cache/restore@v5  # Cache for LLVM libcxx
+    - uses: actions/cache/restore@v4  # Cache for LLVM libcxx
      with:
        path: ${{env.LLVM_DIR}}
        fail-on-cache-miss: true
@@ -32,14 +32,14 @@ runs:
    - uses: ./.github/actions/sanitize/mpi
      if: ${{inputs.par == 'true'}}

-    - uses: actions/cache/restore@v5  # Cache for Hypre
+    - uses: actions/cache/restore@v4  # Cache for Hypre
      if: ${{inputs.par == 'true'}}
      with:
        path: ${{env.HYPRE_DIR}}
        fail-on-cache-miss: true
        key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-v2.5

-    - uses: actions/cache/restore@v5  # Cache for Metis
+    - uses: actions/cache/restore@v4  # Cache for Metis
      if: ${{inputs.par == 'true'}}
      with:
        path: ${{env.METIS_DIR}}
@@ -51,13 +51,13 @@ runs:
      run: ln -s -f ${{env.HYPRE_DIR}} hypre && ln -s -f ${{env.METIS_DIR}} metis-4.0
      shell: bash

-    - uses: actions/cache/restore@v5  # Cache for LSAN suppression file
+    - uses: actions/cache/restore@v4  # Cache for LSAN suppression file
      with:
        path: ${{env.LSAN_DIR}}
        fail-on-cache-miss: true
        key: build-lsan-suppression-file

-    - uses: actions/checkout@v6  # Checkout the repository
+    - uses: actions/checkout@v4  # Checkout the repository
      with:
        path: mfem
        # ref: ${{env.BRANCH}}
@@ -43,7 +43,7 @@ jobs:
          remove-docker-images: 'true'

      - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4

      # It's easier to reference named variables than indexes of the matrix
      - name: Set Environment
@@ -153,7 +153,7 @@ jobs:
      # /home/runner/work/mfem/mfem/mfem
      # Note: Done now to access "install-hypre" and "install-metis" actions.
      - name: checkout mfem
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          path: ${{ env.MFEM_TOP_DIR }}
          # Fetch the complete history for codecov to access commits ID
@@ -225,7 +225,7 @@ jobs:
      - name: cache hypre
        id: hypre-cache
        if: matrix.mpi == 'par'
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{ env.HYPRE_TOP_DIR }}
          key: ${{ runner.os }}-ompi-build-${{ env.HYPRE_TOP_DIR }}-${{ matrix.hypre-target }}-${{ matrix.precision }}-v2.5
@@ -255,7 +255,7 @@ jobs:
      - name: cache metis
        id: metis-cache
        if: matrix.mpi == 'par' && matrix.os != 'windows-latest'
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{ env.METIS_TOP_DIR }}
          key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.5
@@ -270,7 +270,7 @@ jobs:
      - name: cache vcpkg (Windows)
        id: vcpkg-cache
        if: matrix.os == 'windows-latest'
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: vcpkg_cache
          key: ${{ runner.os }}-${{ matrix.mpi }}-vcpkg-v1
@@ -295,8 +295,7 @@ jobs:
          export HOMEBREW_NO_INSTALL_CLEANUP=1
          brew update
          brew install enzyme
-          ENZYME_LLVM=$(brew info enzyme | sed -n 's/^Required.*:.*\(llvm[^ ]*\).*/\1/p')
-          echo "ENZYME_LLVM=$ENZYME_LLVM"
+          ENZYME_LLVM=$(brew info enzyme | sed -n 's/^Required:.*\(llvm[^ ]*\).*/\1/p')
          LLVM_PREFIX=$(brew --prefix $ENZYME_LLVM)
          echo "LLVM_PREFIX=$LLVM_PREFIX" >> $GITHUB_ENV
          echo "OMPI_CC=$LLVM_PREFIX/bin/clang" >> $GITHUB_ENV
@@ -40,11 +40,11 @@ jobs:

    steps:
      - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4

      # Initializes the CodeQL tools for scanning.
      - name: Initialize CodeQL
-        uses: github/codeql-action/init@v4
+        uses: github/codeql-action/init@v2
        with:
          languages: ${{ matrix.language }}
          # If you wish to specify custom queries, you can do so here or in a config file.
@@ -57,7 +57,7 @@ jobs:
      # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
      # If this step fails, then you should remove it and run the build manually (see below)
      - name: Autobuild
-        uses: github/codeql-action/autobuild@v4
+        uses: github/codeql-action/autobuild@v2

      # ℹ️ Command-line programs to run using the OS shell.
      # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
@@ -70,4 +70,4 @@ jobs:
      #   ./location_of_script_within_repo/buildscript.sh

      - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v4
+        uses: github/codeql-action/analyze@v2
@@ -39,7 +39,7 @@ jobs:

    steps:
      - name: checkout MFEM
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          path: mfem

@@ -50,7 +50,7 @@ jobs:

      - name: Cache Hypre Install
        id: hypre-cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{ env.HYPRE_TOP_DIR }}
          key: ${{ runner.os }}-ompi-build-${{ env.HYPRE_TOP_DIR }}-v2.5
@@ -65,7 +65,7 @@ jobs:

      - name: Cache Metis Install
        id: metis-cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{ env.METIS_TOP_DIR }}
          key: ${{ runner.os }}-build-${{ env.METIS_TOP_DIR }}-v2.5
@@ -38,7 +38,7 @@ jobs:
       github.event.pull_request.head.repo.full_name != github.repository)
    steps:
      - name: checkout mfem
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4

      - name: copyright check
        id: copyright
@@ -93,7 +93,7 @@ jobs:
       github.event.pull_request.head.repo.full_name != github.repository)
    steps:
      - name: checkout mfem
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4

      - name: get astyle
        run: |
@@ -110,7 +110,7 @@ jobs:
       github.event.pull_request.head.repo.full_name != github.repository)
    steps:
      - name: checkout mfem
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4

      - name: get doxygen and graphviz
        run: |
@@ -135,7 +135,7 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - name: checkout mfem
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
        with:
          fetch-depth: 0

@@ -17,11 +17,11 @@ jobs:
    runs-on: ubuntu-latest
    name: 2.19.0
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/config
      - name: Cache
        id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{env.HYPRE_DIR}}
          key: ${{runner.os}}-ompi-build-${{env.HYPRE_DIR}}-int32-fp64-v2.5
@@ -27,13 +27,13 @@ jobs:
            llvm_use_sanitizer: "Undefined"
    name: ${{matrix.sanitizer}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/config
        with:
          NO_FLAGS: true
      - name: Cache
        id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{env.LLVM_DIR}}
          key: build-libcxx-${{env.LLVM_VER}}-${{matrix.sanitizer}}
@@ -17,11 +17,11 @@ jobs:
    runs-on: ubuntu-latest
    name: lsan.supp
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/config
      - name: Cache
        id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{env.LSAN_DIR}}
          key: build-lsan-suppression-file
@@ -17,11 +17,11 @@ jobs:
    runs-on: ubuntu-latest
    name: 4.0.3
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/config
      - name: Cache
        id: cache
-        uses: actions/cache@v5
+        uses: actions/cache@v4
        with:
          path: ${{env.METIS_DIR}}
          key: ${{runner.os}}-build-${{env.METIS_DIR}}-v2.5
@@ -28,7 +28,7 @@ jobs:
  build:
    runs-on: ubuntu-latest
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/mfem
        with:
          par: ${{inputs.par}}
@@ -40,7 +40,7 @@ jobs:
    env:
      ex: ${{inputs.par && 'ex1p' || 'ex1'}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -58,7 +58,7 @@ jobs:
    env:
      exclude: ${{inputs.par && '-E "_ser"' || ''}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -82,7 +82,7 @@ jobs:
    env:
      exclude: ${{inputs.par && '-E "_ser"' || ''}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -107,7 +107,7 @@ jobs:
      run: ${{inputs.par && '-R "_cpu_np"' || ''}}
      exclude: ${{inputs.par && '"unit_tests|debug"' || '"^unit_tests$|debug"'}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -131,7 +131,7 @@ jobs:
    env:
      unit_tests: ${{inputs.par && 'punit_tests' || 'unit_tests'}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -165,7 +165,7 @@ jobs:
      unit_tests: ${{inputs.par && 'punit_tests' || 'unit_tests'}}
      np: ${{inputs.par && '_np=2' || ''}}
    steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
      - uses: ./.github/actions/sanitize/restore
        id: restore
        with:
@@ -313,8 +313,6 @@ miniapps/nurbs/nurbs_ex1
 miniapps/nurbs/nurbs_ex1p
 miniapps/nurbs/nurbs_ex3
 miniapps/nurbs/nurbs_ex5
-miniapps/nurbs/nurbs_ex10
-miniapps/nurbs/nurbs_ex10p
 miniapps/nurbs/nurbs_ex11p
 miniapps/nurbs/nurbs_ex24
 miniapps/nurbs/nurbs_solenoidal
@@ -340,14 +338,7 @@ miniapps/nurbs/nurbs_naca_cmesh
 miniapps/nurbs/naca-cmesh.mesh
 miniapps/nurbs/glvis_naca-cmesh.mesh
 miniapps/nurbs/Naca_cmesh
-miniapps/nurbs/nurbs_mesh_info
-miniapps/nurbs/k*_*.dat
 miniapps/nurbs/*-Surface.mesh
-miniapps/nurbs/*.mesh
-miniapps/nurbs/*.sol
-miniapps/nurbs/deformed.*
-miniapps/nurbs/elastic_energy.*
-miniapps/nurbs/velocity.*

 miniapps/performance/ex1
 miniapps/performance/ex1p
@@ -369,7 +360,6 @@ miniapps/shifted/lsf_integral
 miniapps/tools/display-basis
 miniapps/tools/load-dc
 miniapps/tools/convert-dc
-miniapps/tools/compare-dc
 miniapps/tools/gridfunction-bounds
 miniapps/tools/lor-transfer
 miniapps/tools/plor-transfer
@@ -443,10 +433,6 @@ miniapps/diag-smoothers/mg-abs-l1-jacobi
 miniapps/contact/contact
 miniapps/contact/ParaView

-miniapps/plasma/pic/electrostatic-*
-!miniapps/plasma/pic/electrostatic-*.cpp
-miniapps/plasma/pic/*.csv
-
 # Unit test binary and outputs
 tests/unit/output_meshes
 tests/unit/unit_tests
@@ -85,8 +85,3 @@ opt_par_gcc_10_pumi:
  extends: .mfem_job_on_dane
  variables:
    SPEC: "%gcc@10.3.1 +pumi"
-
-opt_par_gcc_10_gslib:
-  extends: .mfem_job_on_dane
-  variables:
-    SPEC: "%gcc@10.3.1 +gslib"
@@ -63,8 +63,3 @@ opt_mpi_cuda_hypre_cuda_gcc:
  extends: .mfem_job_on_matrix
  variables:
    SPEC: "%gcc@10.3.1 +mpi +cuda cuda_arch=90 ^hypre+cuda"
-
-opt_mpi_cuda_gcc_gslib:
-  extends: .mfem_job_on_matrix
-  variables:
-    SPEC: "%gcc@10.3.1 +mpi +cuda +gslib cuda_arch=90 ^hypre+cuda"
@@ -32,9 +32,9 @@ mkdir _${BASELINE_TEST} && cd _${BASELINE_TEST}

 # run
 if [[ "${MACHINE_NAME}" == "dane" ]]; then
-  srun --nodes=1 -t 60 --exclusive --reservation=ci ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
+  salloc --nodes=1 -t 60 --exclusive --reservation=ci ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
 elif [[ ${MACHINE_NAME} == "corona" ]]; then
-  srun --nodes=1 -t 60 -p pbatch ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
+  salloc --nodes=1 -t 60 -p pbatch ../runtest ../../mfem "${BASELINE_TEST} ${TPLS_DIR}"
 else
  echo "Unknown machine: MACHINE_NAME=$MACHINE_NAME"
  exit 1
@@ -11,37 +11,6 @@
 Version 4.9.1 (development)
 ===========================

- Policy for AI-assisted contribution added to CONTRIBUTING.md
-
-Discretization improvements
---------------------------
- Replaced legacy simplex quadrature rules with symmetric positive-weight
-  rules for triangles (orders 0-25) and tetrahedra (orders 0-20). These
-  rules guarantee all-positive weights and interior quadrature points,
-  improving numerical stability. Higher orders fall back to Grundmann-Moller.
-  Triangle rules: Witherden & Vincent, Comput. Math. Appl. 69(10):1232-1241,
-  2015.
-  Tet rules (d=1-13): Witherden & Vincent (ibid).
-  Tet rules (d=14-20): Chuluunbaatar et al., Comput. Math. Appl. 124:89-97,
-  2022.
-
- Improved the gridfunction projection routines. Projections work for Scalar,
-  Vector and VectorFE, also NURBS versions. Optionally different types of
-  projections can be selected, default behaviour has not changed.
-
- Added methods to estimate function extremum using piecewise linear bounds +
-  recursive subdivision.
-
-Meshing improvements
--------------------
- Improved support for 1D NURBS meshes with variable order, including using
-  the patches construct for 1D NURBS meshes.
-
-New and updated examples and miniapps
-------------------------------------
- Electromagnetics/lorentz miniapp has been updated to leverage the ParticleSet
-  capability.
-

 Version 4.9, released on Dec 11, 2025
 =====================================
@@ -126,23 +95,6 @@ Linear and nonlinear solvers
  Filtering (AMGF), providing robust preconditioning for linear systems arising
  in constrained optimization problems such as frictionless contact.

-  Added 'GetResiduals' and 'GetFinalAbsResidualNorm' to 'HyprePCG',
-  'HypreGMRES', and 'HypreFGMRES' to get 'r' and '|r|_p'. Note that the latter
-  computes '|r|_p' from 'r' instead of returning a cached value like the
-  relative 'GetFinalResidualNorm'. These require Hypre >= 2.15.0.
-
-  Changed the default solver parameters for 'HyprePCG' to 'tol=1e-6' and
-  'max_iter=1000'. This matches the default parameters in Hypre 3.0.
-
-  Added various helper functions for querying/modifying Hypre solvers:
-  'HypreSmoother::GetType', 'HypreSmoother::GetSOROptions',
-  'HypreSmoother::GetPolyOptions', 'HypreSmoother::GetWindowParameters',
-  'HypreSmoother::IsOperatorSymmetric', 'HyprePCG::GetTol',
-  'HyprePCG::GetAbsTol', 'HyprePCG::GetMaxIter', 'HyprePCG::SetUseTwoNorm',
-  'HypreGMRES::GetTol', 'HypreGMRES::GetAbsTol', 'HypreGMRES::GetMaxIter',
-  'HypreGMRES::GetKDim', 'HypreFGMRES::GetTol', 'HypreFGMRES::GetMaxIter',
-  'HypreFGMRES::GetKDim', and 'HypreBoomerAMG::GetMaxIter'.
-
 GPU computing
 -------------
 - Added the 'gpu', 'raja-gpu', and 'ceed-gpu' backend aliases/shortcuts which
@@ -652,8 +652,6 @@ foreach(TPL IN LISTS MFEM_TPLS)
  endif()
 endforeach(TPL)

-# reverse to remove the first instance of entries in TPL_LIBRARIES
-# so later duplicates are kept (for dependency ordering)
 list(REVERSE TPL_LIBRARIES)
 list(REMOVE_DUPLICATES TPL_LIBRARIES)
 list(REVERSE TPL_LIBRARIES)
@@ -872,12 +870,11 @@ add_dependencies(exec
 #  - https://cmake.org/Bug/view.php?id=8438

 # Add a target to copy the mfem data directory to the build directory
-# Implementable as a single copy_directory_if_different command w/ CMake >= 3.26
-file(GLOB DATA_FILES CONFIGURE_DEPENDS ${PROJECT_SOURCE_DIR}/data/*)
-add_custom_target(copy_data
-  COMMAND ${CMAKE_COMMAND} -E make_directory data
-  COMMAND ${CMAKE_COMMAND} -E copy_if_different ${DATA_FILES} data
-  COMMENT "Syncing the data directory ...")
+add_custom_command(OUTPUT data_is_copied
+  COMMAND ${CMAKE_COMMAND} -E copy_directory ${PROJECT_SOURCE_DIR}/data data
+  COMMAND ${CMAKE_COMMAND} -E touch data_is_copied
+  COMMENT "Copying the data directory ...")
+add_custom_target(copy_data DEPENDS data_is_copied)
 # Add 'copy_data' as a prerequisite for all executables, if the source and the
 # build directories are not the same.
 if (NOT ("${PROJECT_SOURCE_DIR}" STREQUAL "${PROJECT_BINARY_DIR}"))
@@ -1009,15 +1006,9 @@ install(FILES
 install(EXPORT ${PROJECT_NAME_UC}Targets
    DESTINATION ${INSTALL_CMAKE_DIR})

-# Install the data directory if present, i.e. if the copy_data target is built
-install(DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/data
-  DESTINATION ${MFEM_INSTALL_DIR} OPTIONAL)
-
 #-------------------------------------------------------------------------------
 # Create 'config.mk' from 'config.mk.in' for the build and install locations and
 # define install rules for 'config.mk' and 'test.mk'
 #-------------------------------------------------------------------------------
-if (MFEM_USE_CUDA OR MFEM_USE_HIP)
-  option(MFEM_EXPORT_GPU_CONFIG "Export config.mk for GPU-enabled downstream packages" ON)
-endif()
+
 mfem_export_mk_files()
@@ -24,14 +24,6 @@ must be made under this license.
 Note also that MFEM has a [Code of Conduct](CODE_OF_CONDUCT.md). By participating
 in the MFEM community, you agree to abide by its rules.

-## AI Policy
- Use of AI code generation in MFEM is allowed but must be disclosed, e.g. by
-  selecting the `AI-assisted` label on the PR.
- By submitting a PR, the author acknowledges that they have reviewed and
-  understand the changes they are proposing.
- PR authors are still responsible for correctness, licensing, and attribution
-  of all changes.
-
 If you plan on contributing to MFEM, consider reviewing the
 [issue tracker](https://github.com/mfem/mfem/issues) first to check if a thread
 already exists for your desired feature or the bug you ran into. Use a pull
@@ -109,10 +109,6 @@ if (MFEM_USE_RAJA)
   find_dependency(RAJA)
 endif()

-if (MFEM_USE_UMPIRE)
-   find_dependency(umpire)
-endif()
-
 if (NOT TARGET mfem)
  include(${CMAKE_CURRENT_LIST_DIR}/MFEMTargets.cmake)
 endif (NOT TARGET mfem)
@@ -14,12 +14,12 @@
 #   - UMPIRE_LIBRARIES
 #   - UMPIRE_INCLUDE_DIRS

-if (NOT umpire_ROOT AND UMPIRE_DIR)
-  set(umpire_ROOT ${UMPIRE_DIR})
+if (NOT umpire_DIR AND UMPIRE_DIR)
+  set(umpire_DIR ${UMPIRE_DIR}/lib/cmake/umpire)
 endif()
 message(STATUS "Looking for UMPIRE ...")
 message(STATUS "   in UMPIRE_DIR = ${UMPIRE_DIR}")
-message(STATUS "      umpire_ROOT = ${umpire_ROOT}")
+message(STATUS "      umpire_DIR = ${umpire_DIR}")
 find_package(umpire CONFIG)
 set(UMPIRE_FOUND ${umpire_FOUND})
 set(UMPIRE_LIBRARIES "umpire")
@@ -701,6 +701,7 @@ endfunction(mfem_find_library)
 # Extract compile and link options needed by the given target.
 #
 function(mfem_get_target_options Target CompileOptsVar LinkOptsVar)
+
  if (NOT TARGET ${Target})
    return()
  endif()
@@ -798,12 +799,7 @@ function(mfem_get_target_options Target CompileOptsVar LinkOptsVar)
          # message(STATUS "Lib = ${Lib}")
          # Filter-out generator expressions
          if (NOT ("${Lib}" MATCHES "^\\$"))
-            if(NOT ("${Lib}" STREQUAL "dl"))
-              list(APPEND LinkOpts "${Lib}")
-            else()
-              # for some reason libdl doesn't include the "-l"
-              list(APPEND LinkOpts "-ldl")
-            endif()
+            list(APPEND LinkOpts "${Lib}")
          endif()
        else()
          mfem_get_target_options(${Lib} COpts LOpts)
@@ -892,18 +888,9 @@ function(mfem_export_mk_files)
      set(${var} NO)
    endif()
  endforeach()
-  if (MFEM_USE_CUDA AND MFEM_EXPORT_GPU_CONFIG)
-    set(MFEM_CXX ${CMAKE_CUDA_COMPILER})
-    if(MFEM_CUDA_COMPILER_IS_NVCC)
-      set(MFEM_HOST_CXX ${CMAKE_CUDA_HOST_COMPILER})
-    else()
-      set(MFEM_HOST_CXX ${CMAKE_CXX_COMPILER})
-    endif()
-  else()
-    # mfem doesn't use enable_language(HIP)
-    set(MFEM_CXX ${CMAKE_CXX_COMPILER})
-    set(MFEM_HOST_CXX ${CMAKE_CXX_COMPILER})
-  endif()
+  # TODO: Add support for MFEM_USE_CUDA=YES
+  set(MFEM_CXX ${CMAKE_CXX_COMPILER})
+  set(MFEM_HOST_CXX ${MFEM_CXX})
  set(MFEM_CPPFLAGS "")
  get_target_property(cxx_std mfem CXX_STANDARD)
  # For now, we ignore the setting of the CXX_EXTENSIONS property. If this
@@ -913,50 +900,6 @@ function(mfem_export_mk_files)
  string(STRIP
         "${cxx_std_flag} ${CMAKE_CXX_FLAGS_${BUILD_TYPE}} ${CMAKE_CXX_FLAGS}"
         MFEM_CXXFLAGS)
-  if(MFEM_EXPORT_GPU_CONFIG)
-    if (MFEM_USE_CUDA)
-      set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} ${CMAKE_CUDA_FLAGS}")
-      if (MFEM_CUDA_COMPILER_IS_NVCC)
-        set(MFEM_CXXFLAGS "-x=cu ${MFEM_CXXFLAGS} -ccbin ${CMAKE_CXX_COMPILER} --forward-unknown-to-host-compiler")
-        # The following intentionally hides CUDA deprecation warnings
-        foreach(ENTRY IN LISTS CUDAToolkit_INCLUDE_DIRS)
-          set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -isystem ${ENTRY}")
-        endforeach()
-        if (CMAKE_VERSION VERSION_GREATER_EQUAL 3.18.0)
-          # architecture flags not part of CMAKE_CUDA_FLAGS
-          if ("all" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
-              OR "native" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
-              OR "all-major" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}")
-            set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -arch=${CMAKE_CUDA_ARCHITECTURES}")
-          else()
-            foreach (ENTRY IN LISTS CMAKE_CUDA_ARCHITECTURES)
-              set(MFEM_CXXFLAGS
-                "${MFEM_CXXFLAGS} -gencode arch=compute_${ENTRY},code=sm_${ENTRY}")
-            endforeach()
-          endif()
-        endif()
-      else()
-        set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -xcuda --cuda-path=${CUDAToolkit_LIBRARY_ROOT}")
-        if (CMAKE_VERSION VERSION_GREATER_EQUAL 3.18.0)
-          # architecture flags not part of CMAKE_CUDA_FLAGS
-          if ("all" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
-              OR "native" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}"
-              OR "all-major" STREQUAL "${CMAKE_CUDA_ARCHITECTURES}")
-            # TODO: not supported
-          else()
-            foreach(ENTRY IN LISTS CMAKE_CUDA_ARCHITECTURES)
-              set(MFEM_CXXFLAGS "-cuda-gpu-arch=sm_${ENTRY} ${MFEM_CXXFLAGS}")
-            endforeach()
-          endif()
-        endif()
-      endif()
-    elseif (MFEM_USE_HIP)
-      set(MFEM_CXXFLAGS "${MFEM_CXXFLAGS} -xhip")
-      foreach(ENTRY IN LISTS CMAKE_HIP_ARCHITECTURES)
-        set(MFEM_CXXFLAGS "--offload-arch=${ENTRY} ${MFEM_CXXFLAGS}")
-      endforeach()
-    endif()
-  endif()
  set(MFEM_TPLFLAGS "")
  foreach(dir ${TPL_INCLUDE_DIRS})
    set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} -I${dir}")
@@ -987,9 +930,6 @@ function(mfem_export_mk_files)
    set(MFEM_SHARED NO)
    set(MFEM_STATIC YES)
  endif()
-  if (MFEM_USE_CUDA)
-    set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} -lcudart")
-  endif()
  set(MFEM_BUILD_TAG "${CMAKE_SYSTEM}")
  set(MFEM_PREFIX "${CMAKE_INSTALL_PREFIX}")
  # For the next 4 variables, these are the values for the build-tree version of
@@ -998,15 +938,8 @@ function(mfem_export_mk_files)
  set(MFEM_LIB_DIR "${PROJECT_BINARY_DIR}")
  set(MFEM_TEST_MK "${PROJECT_SOURCE_DIR}/config/test.mk")
  set(MFEM_CONFIG_EXTRA "MFEM_BUILD_DIR ?= ${PROJECT_BINARY_DIR}")
-  if (MFEM_USE_CUDA AND MFEM_EXPORT_GPU_CONFIG)
-    if (MFEM_CUDA_COMPILER_IS_NVCC)
-      set(MFEM_XLINKER "-Xlinker=")
-    else()
-      set(MFEM_XLINKER "${CMAKE_CUDA_LINKER_WRAPPER_FLAG}")
-    endif()
-  else()
-    set(MFEM_XLINKER "${CMAKE_CXX_LINKER_WRAPPER_FLAG}")
-  endif()
+  # TODO: CUDA/HIP support:
+  set(MFEM_XLINKER "${CMAKE_CXX_LINKER_WRAPPER_FLAG}")
  set(MFEM_MPIEXEC ${MPIEXEC})
  if (NOT MFEM_MPIEXEC)
    set(MFEM_MPIEXEC "mpirun")
@@ -1054,21 +987,16 @@ function(mfem_export_mk_files)
    # handle interfaces (e.g., SCOREC::apf)
    if ("${lib}" MATCHES "SCOREC::.*" OR "${lib}" MATCHES "Ginkgo::.*" OR "${lib}" MATCHES "ParMoonolith::.*")
    elseif (TARGET "${lib}")
-      mfem_get_target_options(${lib} CompileOpts2 LinkOpts2)
-      # remove generator expressions
-      string(GENEX_STRIP "${CompileOpts2}" CompileOpts)
-      string(GENEX_STRIP "${LinkOpts2}" LinkOpts)
+      mfem_get_target_options(${lib} CompileOpts LinkOpts)
      # Removing duplicates may lead to issues:
      # list(REMOVE_DUPLICATES CompileOpts)
      # list(REMOVE_DUPLICATES LinkOpts)
-      # message(WARNING "${lib}[LinkOpts]: ${LinkOpts}")      
-      # message(WARNING "${lib}[CompileOpts]: ${CompileOpts}")
-      foreach(LOpt IN LISTS LinkOpts)
-        set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${LOpt}")
-      endforeach()
-      foreach(COpt IN LISTS CompileOpts)
-        set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} ${COpt}")
-      endforeach()
+      string(REPLACE ";" " " COpts "${CompileOpts}")
+      string(REPLACE ";" " " LOpts "${LinkOpts}")
+      # message(STATUS "${lib}[COpts]: '${COpts}'")
+      # message(STATUS "${lib}[LOpts]: '${LOpts}'")
+      set(MFEM_TPLFLAGS "${MFEM_TPLFLAGS} ${COpts}")
+      set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${LOpts}")
      # message(FATAL_ERROR "***** interface lib found ... exiting *****")
      # handle static and shared libs
    elseif ("${suffix}" STREQUAL "${CMAKE_SHARED_LIBRARY_SUFFIX}")
@@ -1076,7 +1004,7 @@ function(mfem_export_mk_files)
      get_filename_component(fullLibName ${lib} NAME_WE)
      string(REGEX REPLACE "^lib" "" libname ${fullLibName})
      set(MFEM_EXT_LIBS
-        "${MFEM_EXT_LIBS} ${shared_link_flag}${dir} -L${dir} -l${libname}")
+          "${MFEM_EXT_LIBS} ${shared_link_flag}${dir} -L${dir} -l${libname}")
    else()
      set(MFEM_EXT_LIBS "${MFEM_EXT_LIBS} ${lib}")
    endif()
@@ -1085,7 +1013,7 @@ function(mfem_export_mk_files)
  # Create the build-tree version of 'config.mk'
  configure_file(
    "${PROJECT_SOURCE_DIR}/config/config.mk.in"
-    "${PROJECT_BINARY_DIR}/config/config.mk" @ONLY)
+    "${PROJECT_BINARY_DIR}/config/config.mk")
  # Copy 'test.mk' from the source-tree to the build-tree
  configure_file(
    "${PROJECT_SOURCE_DIR}/config/test.mk"
@@ -1103,7 +1031,7 @@ function(mfem_export_mk_files)
  # Create the install-tree version of 'config.mk'
  configure_file(
    "${PROJECT_SOURCE_DIR}/config/config.mk.in"
-    "${PROJECT_BINARY_DIR}/config/config-install.mk" @ONLY)
+    "${PROJECT_BINARY_DIR}/config/config-install.mk")

  # Install rules for 'config.mk' and 'test.mk'
  install(FILES ${PROJECT_SOURCE_DIR}/config/test.mk
@@ -18,7 +18,6 @@
 # Some choices below are based on the OS type:
 NOTMAC := $(subst Darwin,,$(shell uname -s))

-ASTYLE_BIN = astyle
 ETAGS_BIN = $(shell command -v etags 2> /dev/null)
 EGREP_BIN = $(shell command -v egrep 2> /dev/null)

@@ -1,86 +0,0 @@
-MFEM NURBS mesh v1.0
-
-dimension
-1
-
-# Four segments with different NURBS orders, described via patches.
-elements
-4
-1 1 0 1
-2 1 2 3
-3 1 4 5
-4 1 6 7
-
-boundary
-0
-
-edges
-4
-0 0 1
-1 2 3
-2 4 5
-3 6 7
-
-vertices
-8
-
-patches
-
-# Patch 0: linear (order 1, 3 spans)
-knotvectors
-1
-1 4  0 0  .4 .6 1 1
-
-dimension
-2
-
-controlpoints
-0.0  0.0  1.0
-0.6  0.4  1.0
-0.4  0.6  1.0
-1.0  1.0  1.0
-
-# Patch 1: quadratic (order 2, 2 spans)
-knotvectors
-1
-2 4  0 0 0  .5 1 1 1
-
-dimension
-2
-
-controlpoints
-1.0  0.0  1.0
-1.9  0.0  1.21
-2.0  0.9  1.22
-2.0  1.0  1.0
-
-# Patch 2: cubic (order 3, 3 spans)
-knotvectors
-1
-3 6  0 0 0 0 .33 .66 1 1 1 1
-
-dimension
-2
-
-controlpoints
-2.0   0.0  1.0
-2.1   0.2  1.31
-3.5   0.4  1.32
-2.5   0.6  1.33
-2.9   1.0  1.34
-3.0   1.0  1.0
-
-# Patch 3: quartic (order 4, 1 span)
-knotvectors
-1
-4 5  0 0 0 0 0 1 1 1 1 1
-
-dimension
-2
-
-controlpoints
-3.0    0.0  1.0
-3.45   0.5  1.41
-3.50   1.0  1.42
-3.75   0.8  1.43
-4.0    0.0  1.0
@@ -1,79 +0,0 @@
-MFEM NURBS mesh v1.0
-
-#
-# MFEM Geometry Types (see fem/geom.hpp):
-#
-# SEGMENT     = 1
-# SQUARE      = 3
-# CUBE        = 5
-#
-
-dimension
-1
-
-# Three segments with different NURBS orders, described via patches.
-elements
-3
-1 1 0 1
-2 1 2 3
-3 1 4 5
-
-boundary
-6
-1 0 0
-1 0 1
-1 0 2
-1 0 3
-1 0 4
-1 0 5
-
-edges
-3
-0 0 1
-1 2 3
-2 4 5
-
-vertices
-6
-
-patches
-
-# Patch 0: linear (order 1, 2 control points)
-knotvectors
-1
-1 2  0 0  1 1
-
-dimension
-2
-
-controlpoints
-0.0  0.0  1.0
-1.0  1.0  1.0
-
-# Patch 1: quadratic (order 2, 3 control points)
-knotvectors
-1
-2 3  0 0 0  1 1 1
-
-dimension
-2
-
-controlpoints
-1.0  0.0   1.0
-1.02 1.02  1.2
-2.0  1.0   1.0
-
-# Patch 2: cubic (order 3, 4 control points)
-knotvectors
-1
-3 4  0 0 0 0  1 1 1 1
-
-dimension
-2
-
-controlpoints
-2.0   0.0   1.0
-2.03  0.83  1.31
-2.33  1.03  1.32
-3.0   1.0   1.0
-
@@ -1,72 +0,0 @@
-MFEM NURBS mesh v1.0
-
-#
-# MFEM Geometry Types (see fem/geom.hpp):
-#
-# SEGMENT     = 1
-# SQUARE      = 3
-# CUBE        = 5
-#
-
-dimension
-1
-
-elements
-3
-1 1 0 1
-2 1 2 3
-3 1 4 5
-
-boundary
-6
-1 0 0
-1 0 1
-1 0 2
-1 0 3
-1 0 4
-1 0 5
-
-edges
-3
-0 0 1
-1 2 3
-2 4 5
-
-vertices
-6
-
-# Edge 0: linear (order 1, 2 control points)
-# Edge 1: quadratic (order 2, 3 control points)
-# Edge 2: cubic (order 3, 4 control points)
-knotvectors
-3
-1 2  0 0  1 1
-2 3  0 0 0  1 1 1
-3 4  0 0 0 0  1 1 1 1
-
-# One weight per control point, in the same order as the control points; (2 + 3 + 4) = 9 weights total
-weights
-1
-1
-1
-1
-1
-1
-1.2
-1.31
-1.32
-
-FiniteElementSpace
-FiniteElementCollection: NURBS
-VDim: 2
-Ordering: 1
-
-0.0  0.0
-1.0  1.0
-1.0  0.0
-2.0  1.0
-2.0  0.0
-3.0  1.0
-1.02 1.02
-2.03 0.83
-2.33 1.03
@@ -1,79 +0,0 @@
-MFEM NURBS mesh v1.0
-
-#
-# MFEM Geometry Types (see fem/geom.hpp):
-#
-# SEGMENT     = 1
-# SQUARE      = 3
-# CUBE        = 5
-#
-
-dimension
-1
-
-# Three segments with different NURBS orders, described via patches.
-elements
-3
-1 1 0 1
-2 1 2 3
-3 1 4 5
-
-boundary
-6
-1 0 0
-1 0 1
-1 0 2
-1 0 3
-1 0 4
-1 0 5
-
-edges
-3
-0 0 1
-1 2 3
-2 4 5
-
-vertices
-6
-
-patches
-
-# Patch 0: linear (order 1, 2 control points)
-knotvectors
-1
-1 2  0 0  1 1
-
-dimension
-3
-
-controlpoints
-0.0  0.0  0.01 1.0
-1.0  1.0  1.01 1.0
-
-# Patch 1: quadratic (order 2, 3 control points)
-knotvectors
-1
-2 3  0 0 0  1 1 1
-
-dimension
-3
-
-controlpoints
-1.0  0.0   0.02 1.0
-1.02 1.02  0.52 1.2
-2.0  1.0   1.02 1.0
-
-# Patch 2: cubic (order 3, 4 control points)
-knotvectors
-1
-3 4  0 0 0 0  1 1 1 1
-
-dimension
-3
-
-controlpoints
-2.0   0.0   0.03 1.0
-2.03  0.83  0.33 1.31
-2.33  1.03  0.63 1.32
-3.0   1.0   1.03 1.0
-
@@ -1,72 +0,0 @@
-MFEM NURBS mesh v1.0
-
-#
-# MFEM Geometry Types (see fem/geom.hpp):
-#
-# SEGMENT     = 1
-# SQUARE      = 3
-# CUBE        = 5
-#
-
-dimension
-1
-
-elements
-3
-1 1 0 1
-2 1 2 3
-3 1 4 5
-
-boundary
-6
-1 0 0
-1 0 1
-1 0 2
-1 0 3
-1 0 4
-1 0 5
-
-edges
-3
-0 0 1
-1 2 3
-2 4 5
-
-vertices
-6
-
-# Edge 0: linear (order 1, 2 control points)
-# Edge 1: quadratic (order 2, 3 control points)
-# Edge 2: cubic (order 3, 4 control points)
-knotvectors
-3
-1 2  0 0  1 1
-2 3  0 0 0  1 1 1
-3 4  0 0 0 0  1 1 1 1
-
-# One weight per control point, in the same order as the control points; (2 + 3 + 4) = 9 weights total
-weights
-1
-1
-1
-1
-1
-1
-1.2
-1.31
-1.32
-
-FiniteElementSpace
-FiniteElementCollection: NURBS
-VDim: 3
-Ordering: 1
-
-0.0  0.0   0.01
-1.0  1.0   1.01
-1.0  0.0   0.02
-2.0  1.0   1.02
-2.0  0.0   0.03
-3.0  1.0   1.03
-1.02 1.02  0.52
-2.03 0.83  0.33
-2.33 1.03  0.63
@@ -190,8 +190,6 @@ namespace mfem {
 *  <a class="el" href="nurbs__ex1p_8cpp_source.html">1p</a>,
 *  <a class="el" href="nurbs__ex3_8cpp_source.html">3</a>,
 *  <a class="el" href="nurbs__ex5_8cpp_source.html">5</a>,
- *  <a class="el" href="nurbs__ex10_8cpp_source.html">10</a>,
- *  <a class="el" href="nurbs__ex10p_8cpp_source.html">10p</a>,
 *  <a class="el" href="nurbs__ex11p_8cpp_source.html">11p</a>, and
 *  <a class="el" href="nurbs__ex24_8cpp_source.html">24</a>,
 *   demonstrating howto perform NURBS-based Isogeometric Analysis.
@@ -200,7 +198,6 @@ namespace mfem {
 * - <a class="el" href="nurbs__curveint_8cpp_source.html">NURBS Interpolation</a>: NURBS interpolation of given geometry
 * - <a class="el" href="nurbs__naca__cmesh_8cpp_source.html">NURBS NACA Mesher</a>: generate NURBS based mesh around a NACA foil
 * - <a class="el" href="nurbs__printfunc_8cpp_source.html">NURBS Printer</a>: print the NURBS-basis
- * - <a class="el" href="nurbs__mesh_info_8cpp_source.html">NURBS Mesh info</a>: print the info of a NURBS mesh
 *
 * <H3>Miniapps</H3>
 * - <a class="el" href="volta_8cpp_source.html">Volta</a>: simple electrostatics simulation code
@@ -215,7 +215,7 @@ if (MFEM_ENABLE_TESTING)
    add_test(NAME ex1p_ceed_np=${MFEM_MPI_NP}
      COMMAND ${MPIEXEC} ${MPIEXEC_NUMPROC_FLAG} ${MFEM_MPI_NP}
      ${MPIEXEC_PREFLAGS}
-      $<TARGET_FILE:ex1p> "-no-vis" "-d" "ceed-cpu" "-pa" "-a"
+      $<TARGET_FILE:ex1p> "-no-vis" "-d ceed-cpu" "-pa" "-a"
      ${MPIEXEC_POSTFLAGS})
  endif()
 endif()
@@ -64,7 +64,7 @@ PARALLEL_NAME := Parallel AMGX example
 $(MFEM_LIB_FILE):
 	$(error The MFEM library is not build)

-clean: clean-build clean-exec
+clean: clean-build

 clean-build:
 	rm -f *.o *~ $(SEQ_EXAMPLES) $(PAR_EXAMPLES)
@@ -64,12 +64,12 @@ ex1p-test-par: ex1p
 $(MFEM_LIB_FILE):
 	$(error The MFEM library is not built)

-clean: clean-build clean-exec
+clean: clean-build clean-exec $(SUBDIRS_CLEAN)

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

 clean-exec:
-	@rm -f refined.mesh mesh.*
-	@rm -f sol.*
+	@rm -f refined.mesh displaced.mesh mesh.* ex5.mesh
+	@rm -f sphere_refined.* sol.* sol_u.* sol_p.* sol_r.* sol_i.*
@@ -5,9 +5,9 @@
 // Sample runs:
 //    mpirun -np 4 ex12p -m ../data/beam-tri.mesh
 //    mpirun -np 4 ex12p -m ../data/beam-quad.mesh
-//    mpirun -np 4 ex12p -m ../data/beam-tet.mesh -s 464 -n 10 -o 2 -elast
+//    mpirun -np 4 ex12p -m ../data/beam-tet.mesh -s 462 -n 10 -o 2 -elast
 //    mpirun -np 4 ex12p -m ../data/beam-hex.mesh -s 3878
-//    mpirun -np 4 ex12p -m ../data/beam-wedge.mesh -s 82
+//    mpirun -np 4 ex12p -m ../data/beam-wedge.mesh -s 81
 //    mpirun -np 4 ex12p -m ../data/beam-tri.mesh -s 3877 -o 2 -sys
 //    mpirun -np 4 ex12p -m ../data/beam-quad.mesh -s 4544 -n 6 -o 3 -elast
 //    mpirun -np 4 ex12p -m ../data/beam-quad-nurbs.mesh
@@ -119,7 +119,7 @@ int main(int argc, char *argv[])
   }

   LinearForm b(&fespace);
-   b.AddBoundaryIntegrator(new VectorBoundaryLFIntegrator(f));
+   b.AddDomainIntegrator(new VectorBoundaryLFIntegrator(f));

   // 6. Set up the bilinear form a(.,.) on the finite element space
   //    corresponding to the linear elasticity integrator with piece-wise
@@ -140,7 +140,7 @@ int main(int argc, char *argv[])
   }

   ParLinearForm b(&fespace);
-   b.AddBoundaryIntegrator(new VectorBoundaryLFIntegrator(f));
+   b.AddDomainIntegrator(new VectorBoundaryLFIntegrator(f));

   // 6. Set up the bilinear form a(.,.) on the finite element space
   //    corresponding to the linear elasticity integrator with piece-wise
@@ -302,21 +302,15 @@ int main(int argc, char *argv[])
      char vishost[] = "localhost";
      int  visport   = 19916;
      socketstream sol_sock_r(vishost, visport);
+      socketstream sol_sock_i(vishost, visport);
      sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
+      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
      sol_sock_r.precision(8);
+      sol_sock_i.precision(8);
      sol_sock_r << "solution\n" << *pmesh << u_exact->real()
                 << "window_title 'Exact: Real Part'" << flush;
-      // Make sure all ranks have sent their real solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
-      socketstream sol_sock_i(vishost, visport);
-      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
-      sol_sock_i.precision(8);
      sol_sock_i << "solution\n" << *pmesh << u_exact->imag()
                 << "window_title 'Exact: Imaginary Part'" << flush;
-      // Make sure all ranks have sent their imaginary solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
   }

   // 11. Set up the parallel sesquilinear form a(.,.) on the finite element
@@ -540,21 +534,15 @@ int main(int argc, char *argv[])
      char vishost[] = "localhost";
      int  visport   = 19916;
      socketstream sol_sock_r(vishost, visport);
+      socketstream sol_sock_i(vishost, visport);
      sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
+      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
      sol_sock_r.precision(8);
+      sol_sock_i.precision(8);
      sol_sock_r << "solution\n" << *pmesh << u.real()
                 << "window_title 'Solution: Real Part'" << flush;
-      // Make sure all ranks have sent their real solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
-      socketstream sol_sock_i(vishost, visport);
-      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
-      sol_sock_i.precision(8);
      sol_sock_i << "solution\n" << *pmesh << u.imag()
                 << "window_title 'Solution: Imaginary Part'" << flush;
-      // Make sure all ranks have sent their imaginary solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
   }
   if (visualization && exact_sol)
   {
@@ -563,21 +551,15 @@ int main(int argc, char *argv[])
      char vishost[] = "localhost";
      int  visport   = 19916;
      socketstream sol_sock_r(vishost, visport);
+      socketstream sol_sock_i(vishost, visport);
      sol_sock_r << "parallel " << num_procs << " " << myid << "\n";
+      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
      sol_sock_r.precision(8);
+      sol_sock_i.precision(8);
      sol_sock_r << "solution\n" << *pmesh << u_exact->real()
                 << "window_title 'Error: Real Part'" << flush;
-      // Make sure all ranks have sent their real solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
-      socketstream sol_sock_i(vishost, visport);
-      sol_sock_i << "parallel " << num_procs << " " << myid << "\n";
-      sol_sock_i.precision(8);
      sol_sock_i << "solution\n" << *pmesh << u_exact->imag()
                 << "window_title 'Error: Imaginary Part'" << flush;
-      // Make sure all ranks have sent their imaginary solution before initiating
-      // another set of GLVis connections (one from each rank):
-      MPI_Barrier(pmesh->GetComm());
   }
   if (visualization)
   {
@@ -5,8 +5,8 @@
 // Sample runs:
 //     ex37 -alpha 10
 //     ex37 -alpha 10 -pv
-//     ex37 -lambda 0.1 -mu 0.1 -growth 1
-//     ex37 -o 2 -alpha 10.0 -mi 50 -vf 0.4 -ntol 1e-5 -growth 1.5
+//     ex37 -lambda 0.1 -mu 0.1
+//     ex37 -o 2 -alpha 5.0 -mi 50 -vf 0.4 -ntol 1e-5
 //     ex37 -r 6 -o 1 -alpha 25.0 -epsilon 0.02 -mi 50 -ntol 1e-5
 //
 // Description: This example code demonstrates the use of MFEM to solve a
@@ -55,6 +55,53 @@
 using namespace std;
 using namespace mfem;

+/**
+ * @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
+ *        ∫_Ω ρ dx = θ vol(Ω) as follows:
+ *
+ *        1. Compute the root of the R → R function
+ *            f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
+ *        2. Set ψ ← ψ + c.
+ *
+ * @param psi a GridFunction to be updated
+ * @param target_volume θ vol(Ω)
+ * @param tol Newton iteration tolerance
+ * @param max_its Newton maximum iteration number
+ * @return real_t Final volume, ∫_Ω sigmoid(ψ)
+ */
+real_t proj(GridFunction &psi, real_t target_volume, real_t tol=1e-12,
+            int max_its=10)
+{
+   MappedGridFunctionCoefficient sigmoid_psi(&psi, sigmoid);
+   MappedGridFunctionCoefficient der_sigmoid_psi(&psi, der_sigmoid);
+
+   LinearForm int_sigmoid_psi(psi.FESpace());
+   int_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
+   LinearForm int_der_sigmoid_psi(psi.FESpace());
+   int_der_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(
+                                              der_sigmoid_psi));
+   bool done = false;
+   for (int k=0; k<max_its; k++) // Newton iteration
+   {
+      int_sigmoid_psi.Assemble(); // Recompute f(c) with updated ψ
+      const real_t f = int_sigmoid_psi.Sum() - target_volume;
+
+      int_der_sigmoid_psi.Assemble(); // Recompute df(c) with updated ψ
+      const real_t df = int_der_sigmoid_psi.Sum();
+
+      const real_t dc = -f/df;
+      psi += dc;
+      if (abs(dc) < tol) { done = true; break; }
+   }
+   if (!done)
+   {
+      mfem_warning("Projection reached maximum iteration without converging. "
+                   "Result may not be accurate.");
+   }
+   int_sigmoid_psi.Assemble();
+   return int_sigmoid_psi.Sum();
+}
+
 /*
 * ---------------------------------------------------------------
 *                      ALGORITHM PREAMBLE
@@ -133,11 +180,10 @@ int main(int argc, char *argv[])
   int ref_levels = 5;
   int order = 2;
   real_t alpha = 1.0;
-   real_t growth = 2;
   real_t epsilon = 0.01;
   real_t vol_fraction = 0.5;
   int max_it = 1e3;
-   real_t itol = 1e-2;
+   real_t itol = 1e-1;
   real_t ntol = 1e-4;
   real_t rho_min = 1e-6;
   real_t lambda = 1.0;
@@ -152,8 +198,6 @@ int main(int argc, char *argv[])
                  "Order (degree) of the finite elements.");
   args.AddOption(&alpha, "-alpha", "--alpha-step-length",
                  "Step length for gradient descent.");
-   args.AddOption(&growth, "-growth", "--alpha-growth-rate",
-                  "Growth rate of step length for gradient descent.");
   args.AddOption(&epsilon, "-epsilon", "--epsilon-thickness",
                  "Length scale for ρ.");
   args.AddOption(&max_it, "-mi", "--max-it",
@@ -288,7 +332,6 @@ int main(int argc, char *argv[])
   }
   FilterSolver->SetEssentialBoundary(ess_bdr_filter);
   FilterSolver->SetupFEM();
-   FilterSolver->AssembleDiffusionBilinear();

   BilinearForm mass(&control_fes);
   mass.AddDomainIntegrator(new InverseIntegrator(new MassIntegrator(one)));
@@ -342,7 +385,7 @@ int main(int argc, char *argv[])
   // 11. Iterate:
   for (int k = 1; k <= max_it; k++)
   {
-      if (k > 1) { alpha = std::pow((real_t) k,growth); }
+      if (k > 1) { alpha *= ((real_t) k) / ((real_t) k-1); }

      mfem::out << "\nStep = " << k << std::endl;

@@ -379,9 +422,7 @@ int main(int argc, char *argv[])

      // Step 5 - Update design variable ψ ← proj(ψ - αG)
      psi.Add(-alpha, grad);
-      GridFunction alpha_grad(grad);
-      alpha_grad *= alpha;
-      const real_t material_volume = proj(psi, alpha_grad, target_volume);
+      const real_t material_volume = proj(psi, target_volume);

      // Compute ||ρ - ρ_old|| in control fes.
      real_t norm_increment = zerogf.ComputeL1Error(succ_diff_rho);
@@ -137,7 +137,7 @@ public:
        exponent(exponent_), rho_min(rho_min_)
   {
      MFEM_ASSERT(rho_min_ >= 0.0, "rho_min must be >= 0");
-      MFEM_ASSERT(rho_min_ < 1.0,  "rho_min must be < 1");
+      MFEM_ASSERT(rho_min_ < 1.0,  "rho_min must be > 1");
      MFEM_ASSERT(u, "displacement field is not set");
      MFEM_ASSERT(rho_filter, "density field is not set");
   }
@@ -231,12 +231,9 @@ private:
   FiniteElementCollection * fec = nullptr;
   FiniteElementSpace * fes = nullptr;
   Array<int> ess_bdr;
-   Array<int> ess_tdof_list;
   Array<int> neumann_bdr;
   GridFunction * u = nullptr;
   LinearForm * b = nullptr;
-   BilinearForm * a = nullptr;
-   OperatorPtr A;
   bool parallel;
 #ifdef MFEM_USE_MPI
   ParMesh * pmesh = nullptr;
@@ -270,8 +267,6 @@ public:
   void ResetFEM();
   void SetupFEM();

-   void UpdateEssentialTDofs();
-   void AssembleDiffusionBilinear(bool update_ess_tdofs=true);
   void Solve();
   GridFunction * GetFEMSolution();
   LinearForm * GetLinearForm() {return b;}
@@ -376,130 +371,6 @@ public:

 };

-/**
- * @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
- *        ∫_Ω ρ dx = θ vol(Ω) as follows:
- *
- *        1. Compute the root of the R → R function
- *            f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
- *           using the Illinois method
- *        2. Set ψ ← ψ + c.
- *
- * @param psi a GridFunction to be updated
- * @param alpha_grad alpha multiplied by gradient
- * @param target_volume θ vol(Ω)
- * @param tol Illinois iteration tolerance
- * @param max_its Illinois maximum iteration number
- * @return real_t Final volume (∫_Ω sigmoid(ψ) dx)
- */
-real_t proj(GridFunction &psi, GridFunction &alpha_grad, real_t target_volume,
-            real_t tol = 1e-12, int max_its = 100)
-{
-#ifdef MFEM_USE_MPI
-   FiniteElementSpace *fes = psi.FESpace();
-   ParFiniteElementSpace *pfes = dynamic_cast<ParFiniteElementSpace*>(fes);
-#endif
-   ConstantCoefficient zero_cf(0.0);
-   real_t a = -alpha_grad.ComputeMaxError(zero_cf);
-   real_t b = -a;
-   real_t y = 0.0;
-
-   MappedGridFunctionCoefficient sigmoid_psi(
-   &psi, [&y](const real_t x) { return sigmoid(x + y); });
-   std::unique_ptr<LinearForm> int_sigmoid_psi;
-#ifdef MFEM_USE_MPI
-   ParGridFunction *par_psi = dynamic_cast<ParGridFunction *>(&psi);
-   if (par_psi)
-   {
-      int_sigmoid_psi.reset(new ParLinearForm(par_psi->ParFESpace()));
-   }
-   else
-   {
-      int_sigmoid_psi.reset(new LinearForm(psi.FESpace()));
-   }
-#else
-   int_sigmoid_psi.reset(new LinearForm(psi.FESpace()));
-#endif
-   int_sigmoid_psi->AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
-
-   y = a;
-   int_sigmoid_psi->Assemble();
-   real_t f_a = int_sigmoid_psi->Sum();  // f_a := f(a) + θ vol(Ω)
-
-   y = b;
-   int_sigmoid_psi->Assemble();
-   real_t f_b = int_sigmoid_psi->Sum();  // f_b := f(b) + θ vol(Ω)
-#ifdef MFEM_USE_MPI
-   if (pfes)
-   {
-      MPI_Allreduce(MPI_IN_PLACE, &f_a, 1, MPITypeMap<real_t>::mpi_type,
-                    MPI_SUM, MPI_COMM_WORLD);
-      MPI_Allreduce(MPI_IN_PLACE, &f_b, 1, MPITypeMap<real_t>::mpi_type,
-                    MPI_SUM, MPI_COMM_WORLD);
-   }
-#endif
-   f_a -= target_volume; // f_a := f(a)
-   f_b -= target_volume; // f_b := f(b)
-   real_t c = 0.0;
-   real_t f_c = 0.0;
-   int side = 0;
-
-   bool done = false;
-   for (int k=0; k < max_its; k++)
-   {
-      c = (f_a * b - f_b * a) / (f_a - f_b);
-
-      if (abs(b - a) < tol * abs(b + a)) { done = true; break; }
-
-      y = c;
-      int_sigmoid_psi->Assemble();
-      f_c = int_sigmoid_psi->Sum(); // f_c := f(c) + θ vol(Ω)
-#ifdef MFEM_USE_MPI
-      if (pfes)
-      {
-         MPI_Allreduce(MPI_IN_PLACE, &f_c, 1, MPITypeMap<real_t>::mpi_type,
-                       MPI_SUM, MPI_COMM_WORLD);
-      }
-#endif
-      f_c -= target_volume; // f_c := f(c)
-
-      if (f_c * f_b > 0)
-      {
-         b = c;
-         f_b = f_c;
-         if (side == -1) { f_a /= 2.0; }
-         side = -1;
-      }
-      else if (f_c * f_a > 0)
-      {
-         a = c;
-         f_a = f_c;
-         if (side == 1) { f_b /= 2.0; }
-         side = 1;
-      }
-      else
-      {
-         done = true; break;
-      }
-   }
-   if (!done)
-   {
-      mfem_warning("Projection reached maximum iteration without converging. "
-                   "Result may not be accurate.");
-   }
-   y = 0.0;
-   psi += c;
-   int_sigmoid_psi->Assemble();
-   real_t material_volume = int_sigmoid_psi->Sum();
-#ifdef MFEM_USE_MPI
-   if (pfes)
-   {
-      MPI_Allreduce(MPI_IN_PLACE, &material_volume, 1,
-                    MPITypeMap<real_t>::mpi_type, MPI_SUM, MPI_COMM_WORLD);
-   }
-#endif
-   return material_volume;
-}

 // Poisson solver

@@ -551,8 +422,12 @@ void DiffusionSolver::SetupFEM()
   }
 }

-void DiffusionSolver::UpdateEssentialTDofs()
+void DiffusionSolver::Solve()
 {
+   OperatorPtr A;
+   Vector B, X;
+   Array<int> ess_tdof_list;
+
 #ifdef MFEM_USE_MPI
   if (parallel)
   {
@@ -565,39 +440,7 @@ void DiffusionSolver::UpdateEssentialTDofs()
 #else
   fes->GetEssentialTrueDofs(ess_bdr,ess_tdof_list);
 #endif
-}
-
-void DiffusionSolver::AssembleDiffusionBilinear(bool update_ess_tdofs)
-{
-   if (update_ess_tdofs)
-   {
-      UpdateEssentialTDofs();
-   }
-#ifdef MFEM_USE_MPI
-   if (parallel)
-   {
-      a = new ParBilinearForm(pfes);
-   }
-   else
-   {
-      a = new BilinearForm(fes);
-   }
-#else
-   a = new BilinearForm(fes);
-#endif
-   a->AddDomainIntegrator(new DiffusionIntegrator(*diffcf));
-   if (masscf)
-   {
-      a->AddDomainIntegrator(new MassIntegrator(*masscf));
-   }
-   a->Assemble();
-   a->FormSystemMatrix(ess_tdof_list, A);
-}
-
-void DiffusionSolver::Solve()
-{
-   Vector B, X;
-
+   *u=0.0;
   if (b)
   {
      delete b;
@@ -632,33 +475,31 @@ void DiffusionSolver::Solve()

   b->Assemble();

-   *u=0.0;
-   if (essbdr_cf)
-   {
-      u->ProjectBdrCoefficient(*essbdr_cf,ess_bdr);
-   }
+   BilinearForm * a = nullptr;

 #ifdef MFEM_USE_MPI
   if (parallel)
   {
-      X.SetSize(pfes->TrueVSize());
-      B.SetSize(pfes->TrueVSize());
-      dynamic_cast<ParGridFunction*>(u)->ParallelAssemble(X);
-      dynamic_cast<ParLinearForm*>(b)->ParallelAssemble(B);
-      dynamic_cast<ParBilinearForm*>(a)->ParallelEliminateTDofsInRHS(
-         ess_tdof_list, X, B);
+      a = new ParBilinearForm(pfes);
   }
   else
   {
-      X.NewDataAndSize(u->GetData(), u->Size());
-      B.NewDataAndSize(b->GetData(), b->Size());
-      a->EliminateVDofsInRHS(ess_tdof_list, X, B);
+      a = new BilinearForm(fes);
   }
 #else
-   X.NewDataAndSize(u->GetData(), u->Size());
-   B.NewDataAndSize(b->GetData(), b->Size());
-   a->EliminateVDofsInRHS(ess_tdof_list, X, B);
+   a = new BilinearForm(fes);
 #endif
+   a->AddDomainIntegrator(new DiffusionIntegrator(*diffcf));
+   if (masscf)
+   {
+      a->AddDomainIntegrator(new MassIntegrator(*masscf));
+   }
+   a->Assemble();
+   if (essbdr_cf)
+   {
+      u->ProjectBdrCoefficient(*essbdr_cf,ess_bdr);
+   }
+   a->FormLinearSystem(ess_tdof_list, *u, *b, A, X, B);

   CGSolver * cg = nullptr;
   Solver * M = nullptr;
@@ -687,6 +528,7 @@ void DiffusionSolver::Solve()
   delete M;
   delete cg;
   a->RecoverFEMSolution(X, *b, *u);
+   delete a;
 }

 GridFunction * DiffusionSolver::GetFEMSolution()
@@ -718,8 +560,6 @@ DiffusionSolver::~DiffusionSolver()
 #endif
   delete fec; fec = nullptr;
   delete b;
-   A.Clear();
-   delete a;
 }


@@ -4,8 +4,8 @@
 //
 // Sample runs:
 //    mpirun -np 4 ex37p -alpha 10 -pv
-//    mpirun -np 4 ex37p -lambda 0.1 -mu 0.1 -growth 1
-//    mpirun -np 4 ex37p -o 2 -alpha 10.0 -mi 50 -vf 0.4 -ntol 1e-5 -growth 1.5
+//    mpirun -np 4 ex37p -lambda 0.1 -mu 0.1
+//    mpirun -np 4 ex37p -o 2 -alpha 5.0 -mi 50 -vf 0.4 -ntol 1e-5
 //    mpirun -np 4 ex37p -r 6 -o 2 -alpha 10.0 -epsilon 0.02 -mi 50 -ntol 1e-5
 //
 // Description: This example code demonstrates the use of MFEM to solve a
@@ -54,6 +54,61 @@
 using namespace std;
 using namespace mfem;

+/**
+ * @brief Bregman projection of ρ = sigmoid(ψ) onto the subspace
+ *        ∫_Ω ρ dx = θ vol(Ω) as follows:
+ *
+ *        1. Compute the root of the R → R function
+ *            f(c) = ∫_Ω sigmoid(ψ + c) dx - θ vol(Ω)
+ *        2. Set ψ ← ψ + c.
+ *
+ * @param psi a GridFunction to be updated
+ * @param target_volume θ vol(Ω)
+ * @param tol Newton iteration tolerance
+ * @param max_its Newton maximum iteration number
+ * @return real_t Final volume, ∫_Ω sigmoid(ψ)
+ */
+real_t proj(ParGridFunction &psi, real_t target_volume, real_t tol=1e-12,
+            int max_its=10)
+{
+   MappedGridFunctionCoefficient sigmoid_psi(&psi, sigmoid);
+   MappedGridFunctionCoefficient der_sigmoid_psi(&psi, der_sigmoid);
+
+   ParLinearForm int_sigmoid_psi(psi.ParFESpace());
+   int_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(sigmoid_psi));
+   ParLinearForm int_der_sigmoid_psi(psi.ParFESpace());
+   int_der_sigmoid_psi.AddDomainIntegrator(new DomainLFIntegrator(
+                                              der_sigmoid_psi));
+   bool done = false;
+   for (int k=0; k<max_its; k++) // Newton iteration
+   {
+      int_sigmoid_psi.Assemble(); // Recompute f(c) with updated ψ
+      real_t f = int_sigmoid_psi.Sum();
+      MPI_Allreduce(MPI_IN_PLACE, &f, 1, MPITypeMap<real_t>::mpi_type,
+                    MPI_SUM, MPI_COMM_WORLD);
+      f -= target_volume;
+
+      int_der_sigmoid_psi.Assemble(); // Recompute df(c) with updated ψ
+      real_t df = int_der_sigmoid_psi.Sum();
+      MPI_Allreduce(MPI_IN_PLACE, &df, 1, MPITypeMap<real_t>::mpi_type,
+                    MPI_SUM, MPI_COMM_WORLD);
+
+      const real_t dc = -f/df;
+      psi += dc;
+      if (abs(dc) < tol) { done = true; break; }
+   }
+   if (!done)
+   {
+      mfem_warning("Projection reached maximum iteration without converging. "
+                   "Result may not be accurate.");
+   }
+   int_sigmoid_psi.Assemble();
+   real_t material_volume = int_sigmoid_psi.Sum();
+   MPI_Allreduce(MPI_IN_PLACE, &material_volume, 1,
+                 MPITypeMap<real_t>::mpi_type, MPI_SUM, MPI_COMM_WORLD);
+   return material_volume;
+}
+
 /*
 * ---------------------------------------------------------------
 *                      ALGORITHM PREAMBLE
@@ -138,11 +193,10 @@ int main(int argc, char *argv[])
   int ref_levels = 5;
   int order = 2;
   real_t alpha = 1.0;
-   real_t growth = 2;
   real_t epsilon = 0.01;
   real_t vol_fraction = 0.5;
   int max_it = 1e3;
-   real_t itol = 1e-2;
+   real_t itol = 1e-1;
   real_t ntol = 1e-4;
   real_t rho_min = 1e-6;
   real_t lambda = 1.0;
@@ -157,8 +211,6 @@ int main(int argc, char *argv[])
                  "Order (degree) of the finite elements.");
   args.AddOption(&alpha, "-alpha", "--alpha-step-length",
                  "Step length for gradient descent.");
-   args.AddOption(&growth, "-growth", "--alpha-growth-rate",
-                  "Growth rate of step length for gradient descent.");
   args.AddOption(&epsilon, "-epsilon", "--epsilon-thickness",
                  "Length scale for ρ.");
   args.AddOption(&max_it, "-mi", "--max-it",
@@ -307,7 +359,6 @@ int main(int argc, char *argv[])
   }
   FilterSolver->SetEssentialBoundary(ess_bdr_filter);
   FilterSolver->SetupFEM();
-   FilterSolver->AssembleDiffusionBilinear();

   ParBilinearForm mass(&control_fes);
   mass.AddDomainIntegrator(new InverseIntegrator(new MassIntegrator(one)));
@@ -361,7 +412,7 @@ int main(int argc, char *argv[])
   // 11. Iterate:
   for (int k = 1; k <= max_it; k++)
   {
-      if (k > 1) { alpha = std::pow((real_t) k,growth); }
+      if (k > 1) { alpha *= ((real_t) k) / ((real_t) k-1); }

      if (myid == 0)
      {
@@ -401,9 +452,7 @@ int main(int argc, char *argv[])

      // Step 5 - Update design variable ψ ← proj(ψ - αG)
      psi.Add(-alpha, grad);
-      ParGridFunction alpha_grad(grad);
-      alpha_grad *= alpha;
-      const real_t material_volume = proj(psi, alpha_grad, target_volume);
+      const real_t material_volume = proj(psi, target_volume);

      // Compute ||ρ - ρ_old|| in control fes.
      real_t norm_increment = zerogf.ComputeL1Error(succ_diff_rho);
@@ -9,7 +9,6 @@
 //               ex4 -m ../data/beam-hex.mesh -o 2 -pa
 //               ex4 -m ../data/escher.mesh
 //               ex4 -m ../data/fichera.mesh -o 2 -hb
-//               ex4 -m ../data/fichera.mesh -o 2 -hb -ea
 //               ex4 -m ../data/fichera-q2.vtk
 //               ex4 -m ../data/fichera-q3.mesh -o 2 -sc
 //               ex4 -m ../data/square-disc-nurbs.mesh
@@ -19,7 +18,6 @@
 //               ex4 -m ../data/amr-quad.mesh
 //               ex4 -m ../data/amr-hex.mesh
 //               ex4 -m ../data/amr-hex.mesh -o 2 -hb
-//               ex4 -m ../data/amr-hex.mesh -o 2 -hb -ea
 //               ex4 -m ../data/fichera-amr.mesh -o 2 -sc
 //               ex4 -m ../data/ref-prism.mesh -o 1
 //               ex4 -m ../data/octahedron.mesh -o 1
@@ -27,8 +25,6 @@
 //
 // Device sample runs:
 //               ex4 -m ../data/star.mesh -pa -d cuda
-//               ex4 -m ../data/star.mesh -hb -ea -d cuda
-//               ex4 -m ../data/amr-quad.mesh -hb -ea -d cuda
 //               ex4 -m ../data/star.mesh -pa -d raja-cuda
 //               ex4 -m ../data/star.mesh -pa -d raja-omp
 //               ex4 -m ../data/beam-hex.mesh -pa -d cuda
@@ -197,7 +193,7 @@ int main(int argc, char *argv[])
   cout << "Size of linear system: " << A->Height() << endl;

   // 11. Solve the linear system A X = B.
-   if (!pa && (!ea || hybridization))
+   if (!pa)
   {
 #ifndef MFEM_USE_SUITESPARSE
      // Use a simple symmetric Gauss-Seidel preconditioner with PCG.
@@ -9,7 +9,6 @@
 //               mpirun -np 4 ex4p -m ../data/beam-hex.mesh -o 2 -pa
 //               mpirun -np 4 ex4p -m ../data/escher.mesh -o 2 -sc
 //               mpirun -np 4 ex4p -m ../data/fichera.mesh -o 2 -hb
-//               mpirun -np 4 ex4p -m ../data/fichera.mesh -o 2 -hb -ea
 //               mpirun -np 4 ex4p -m ../data/fichera-q2.vtk
 //               mpirun -np 4 ex4p -m ../data/fichera-q3.mesh -o 2 -sc
 //               mpirun -np 4 ex4p -m ../data/square-disc-nurbs.mesh -o 3
@@ -18,18 +17,14 @@
 //               mpirun -np 4 ex4p -m ../data/periodic-cube.mesh -no-bc
 //               mpirun -np 4 ex4p -m ../data/amr-quad.mesh
 //               mpirun -np 3 ex4p -m ../data/amr-quad.mesh -o 2 -hb
-//               mpirun -np 3 ex4p -m ../data/amr-quad.mesh -o 2 -hb -ea
 //               mpirun -np 4 ex4p -m ../data/amr-hex.mesh -o 2 -sc
 //               mpirun -np 4 ex4p -m ../data/amr-hex.mesh -o 2 -hb
-//               mpirun -np 4 ex4p -m ../data/amr-hex.mesh -o 2 -hb -ea
 //               mpirun -np 4 ex4p -m ../data/ref-prism.mesh -o 1
 //               mpirun -np 4 ex4p -m ../data/octahedron.mesh -o 1
 //               mpirun -np 4 ex4p -m ../data/star-surf.mesh -o 3 -hb
 //
 // Device sample runs:
 //               mpirun -np 4 ex4p -m ../data/star.mesh -pa -d cuda
-//               mpirun -np 4 ex4p -m ../data/star.mesh -ea -hb -d cuda
-//               mpirun -np 4 ex4p -m ../data/amr-hex.mesh -ea -hb -d cuda
 //               mpirun -np 4 ex4p -m ../data/star.mesh -pa -d raja-cuda
 //               mpirun -np 4 ex4p -m ../data/star.mesh -pa -d raja-omp
 //               mpirun -np 4 ex4p -m ../data/beam-hex.mesh -pa -d cuda
@@ -235,7 +230,7 @@ int main(int argc, char *argv[])
   pcg->SetMaxIter(2000);
   pcg->SetPrintLevel(1);
   if (hybridization) { prec = new HypreBoomerAMG(*A.As<HypreParMatrix>()); }
-   else if (pa || ea) { prec = new OperatorJacobiSmoother(*a, ess_tdof_list); }
+   else if (pa) { prec = new OperatorJacobiSmoother(*a, ess_tdof_list); }
   else
   {
      ParFiniteElementSpace *prec_fespace =
@@ -76,4 +76,4 @@ clean-build:
 	rm -rf *.dSYM *.TVD.*breakpoints

 clean-exec:
-	@rm -f refined.mesh sol.gf mesh.* sol.*
+	@rm -f refined.mesh sol.gf
@@ -71,7 +71,6 @@ endif

 SUBDIRS_ALL = $(addsuffix /all,$(SUBDIRS))
 SUBDIRS_TEST = $(addsuffix /test,$(SUBDIRS))
-SUBDIRS_TEST_NOCLEAN = $(addsuffix /test-noclean,$(SUBDIRS))
 SUBDIRS_CLEAN = $(addsuffix /clean,$(SUBDIRS))
 SUBDIRS_TPRINT = $(addsuffix /test-print,$(SUBDIRS))

@@ -88,9 +87,8 @@ SUBDIRS_TPRINT = $(addsuffix /test-print,$(SUBDIRS))

 all: $(EXAMPLES) $(SUBDIRS_ALL)

-.PHONY: $(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_TEST_NOCLEAN) \
-   $(SUBDIRS_CLEAN) $(SUBDIRS_TPRINT)
-$(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_TEST_NOCLEAN) $(SUBDIRS_CLEAN):
+.PHONY: $(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_CLEAN) $(SUBDIRS_TPRINT)
+$(SUBDIRS_ALL) $(SUBDIRS_TEST) $(SUBDIRS_CLEAN):
 	$(MAKE) -C $(@D) $(@F)
 $(SUBDIRS_TPRINT):
 	@$(MAKE) -C $(@D) $(@F)
@@ -109,7 +107,6 @@ endif
 MFEM_TESTS = EXAMPLES
 include $(MFEM_TEST_MK)
 test: $(SUBDIRS_TEST)
-test-noclean: $(SUBDIRS_TEST_NOCLEAN)
 test-print: $(SUBDIRS_TPRINT)

 # Testing: Parallel vs. serial runs
@@ -160,8 +157,6 @@ ex37-test-seq: ex37
 	@$(call mfem-test,$<,, Serial example,-mi 3)
 ex37p-test-par: ex37p
 	@$(call mfem-test,$<, $(RUN_MPI), Parallel example,-mi 3)
-ex39-test-seq: ex39
-	@$(call mfem-test,$<,, Serial example,-m ../data/compass.mesh)
 ex41-test-seq: ex41
 	@$(call mfem-test,$<,, Serial example,-tf 1.0)
 ex41p-test-par: ex41p
@@ -729,8 +729,7 @@ void BilinearForm::Assemble(int skip_zeros)
         tr = mesh -> GetBdrFaceTransformations (i);
         if (tr != NULL)
         {
-            mfem::DofTransformation doftrans;
-            fes -> GetElementVDofs (tr -> Elem1No, vdofs, doftrans);
+            fes -> GetElementVDofs (tr -> Elem1No, vdofs);
            fe1 = fes -> GetFE (tr -> Elem1No);
            // The fe2 object is really a dummy and not used on the boundaries,
            // but we can't dereference a NULL pointer, and we don't want to
@@ -744,7 +743,6 @@ void BilinearForm::Assemble(int skip_zeros)

               boundary_face_integs[k] -> AssembleFaceMatrix (*fe1, *fe2, *tr,
                                                              elemmat);
-               doftrans.TransformDual(elemmat);
               mat -> AddSubMatrix (vdofs, vdofs, elemmat, skip_zeros);
            }
         }
@@ -827,46 +825,14 @@ void BilinearForm::FormLinearSystem(const Array<int> &ess_tdof_list, Vector &x,
                                    Vector &b, OperatorHandle &A, Vector &X,
                                    Vector &B, int copy_interior)
 {
-   const SparseMatrix *P = fes->GetConformingProlongation();
-   const SparseMatrix *R = fes->GetConformingRestriction();
   if (ext)
   {
      if (hybridization)
      {
         FormSystemMatrix(ess_tdof_list, A);
-
-         std::unique_ptr<ConstrainedOperator> A_constrained([&]()
-         {
-            Operator *op;
-            Operator::FormSystemOperator(ess_tdof_list, op);
-            return dynamic_cast<ConstrainedOperator*>(op);
-         }());
-         MFEM_ASSERT(A_constrained != nullptr, "");
-
-         Vector conf_b, conf_x;
-         if (P)
-         {
-            // Nonconforming
-            conf_b.SetSize(P->Width());
-            conf_x.SetSize(P->Width());
-            P->MultTranspose(b, conf_b);
-            R->Mult(x, conf_x);
-         }
-         else
-         {
-            // Conforming
-            conf_b.MakeRef(b, 0, b.Size());
-            conf_x.MakeRef(x, 0, x.Size());
-         }
-
-         A_constrained->EliminateRHS(conf_x, conf_b);
-
-         if (P)
-         {
-            R->MultTranspose(conf_b, b); // store eliminated rhs in b
-         }
-
-         hybridization->ReduceRHS(conf_b, B);
+         ConstrainedOperator A_constrained(this, ess_tdof_list);
+         A_constrained.EliminateRHS(x, b);
+         hybridization->ReduceRHS(b, B);
         X.SetSize(B.Size());
         X = 0.0;
      }
@@ -876,6 +842,7 @@ void BilinearForm::FormLinearSystem(const Array<int> &ess_tdof_list, Vector &x,
      }
      return;
   }
+   const SparseMatrix *P = fes->GetConformingProlongation();
   FormSystemMatrix(ess_tdof_list, A);

   // Transform the system and perform the elimination in B, based on the
@@ -911,6 +878,7 @@ void BilinearForm::FormLinearSystem(const Array<int> &ess_tdof_list, Vector &x,
      if (hybridization)
      {
         // Reduction to the Lagrange multipliers system
+         const SparseMatrix *R = fes->GetConformingRestriction();
         Vector conf_b(P->Width()), conf_x(P->Width());
         P->MultTranspose(b, conf_b);
         R->Mult(x, conf_x);
@@ -923,6 +891,7 @@ void BilinearForm::FormLinearSystem(const Array<int> &ess_tdof_list, Vector &x,
      else
      {
         // Variational restriction with P
+         const SparseMatrix *R = fes->GetConformingRestriction();
         B.SetSize(P->Width());
         P->MultTranspose(b, B);
         X.SetSize(R->Height());
@@ -1725,7 +1694,6 @@ void MixedBilinearForm::Assemble(int skip_zeros)
         }
      }

-      DofTransformation dom_dof_trans, ran_dof_trans;
      for (int i = 0; i < trial_fes -> GetNBE(); i++)
      {
         const int bdr_attr = mesh->GetBdrAttribute(i);
@@ -1734,8 +1702,8 @@ void MixedBilinearForm::Assemble(int skip_zeros)
         ftr = mesh -> GetBdrFaceTransformations (i);
         if (ftr != NULL)
         {
-            trial_fes->GetElementVDofs(ftr->Elem1No, trial_vdofs, dom_dof_trans);
-            test_fes->GetElementVDofs(ftr->Elem1No, test_vdofs, ran_dof_trans);
+            trial_fes->GetElementVDofs(ftr->Elem1No, trial_vdofs);
+            test_fes->GetElementVDofs(ftr->Elem1No, test_vdofs);
            trial_fe1 = trial_fes->GetFE(ftr->Elem1No);
            test_fe1 = test_fes->GetFE(ftr->Elem1No);
            // The test_fe2 object is really a dummy and not used on the
@@ -1751,7 +1719,6 @@ void MixedBilinearForm::Assemble(int skip_zeros)
               boundary_face_integs[k]->AssembleFaceMatrix(*trial_fe1, *test_fe1, *trial_fe2,
                                                           *test_fe2,
                                                           *ftr, elemmat);
-               TransformDual(ran_dof_trans, dom_dof_trans, elemmat);
               mat->AddSubMatrix(test_vdofs, trial_vdofs, elemmat, skip_zeros);
            }
         }
@@ -2137,14 +2137,14 @@ private:
   int trial_dofs1D, test_dofs1D, quad1D;

 public:
-   GradientIntegrator() :
-      Q{NULL}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
+   GradientIntegrator(const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q{NULL}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
   { }
-   GradientIntegrator(Coefficient *q_) :
-      Q{q_}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
+   GradientIntegrator(Coefficient *q_, const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q{q_}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
   { }
-   GradientIntegrator(Coefficient &q) :
-      Q{&q}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
+   GradientIntegrator(Coefficient &q, const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q{&q}, trial_maps{NULL}, test_maps{NULL}, geom{NULL}
   { }

   void AssembleElementMatrix2(const FiniteElement &trial_fe,
@@ -2612,6 +2612,11 @@ protected:
   Vector pa_data;

 public:
+
+   VectorMassIntegrator(const IntegrationRule *ir)
+      : BilinearFormIntegrator(ir), vdim(-1), Q_order(0), Q(NULL), VQ(NULL),
+        MQ(NULL) { }
+
   /// Construct an integrator with coefficient 1.0
   VectorMassIntegrator() = default;

@@ -2710,7 +2715,7 @@ public:


 /** Integrator for $(-Q u, \nabla v)$ for Nedelec ($u$) and $H^1$ ($v$) elements.
-    This is equivalent to a weak divergence of the $H(curl)$ basis functions. */
+    This is equivalent to a weak divergence of the $H(curl$ basis functions. */
 class VectorFEWeakDivergenceIntegrator: public BilinearFormIntegrator
 {
 protected:
@@ -3038,14 +3043,15 @@ private:
   int trial_dofs1D, test_dofs1D, quad1D;

 public:
-   VectorDivergenceIntegrator() :
-      Q(NULL), trial_maps(NULL), test_maps(NULL), geom(NULL)
+   VectorDivergenceIntegrator(const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q(NULL), trial_maps(NULL), test_maps(NULL),
+      geom(NULL)
   {  }
-   VectorDivergenceIntegrator(Coefficient *q_) :
-      Q(q_), trial_maps(NULL), test_maps(NULL), geom(NULL)
+   VectorDivergenceIntegrator(Coefficient *q_, const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q(q_), trial_maps(NULL), test_maps(NULL), geom(NULL)
   { }
-   VectorDivergenceIntegrator(Coefficient &q) :
-      Q(&q), trial_maps(NULL), test_maps(NULL), geom(NULL)
+   VectorDivergenceIntegrator(Coefficient &q, const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir), Q(&q), trial_maps(NULL), test_maps(NULL), geom(NULL)
   { }

   void AssembleElementMatrix2(const FiniteElement &trial_fe,
@@ -3263,8 +3269,9 @@ private:
   void SetUpQuadratureSpaceAndCoefficients(const FiniteElementSpace &fes);

 public:
-   ElasticityIntegrator(Coefficient &l, Coefficient &m)
-   { lambda = &l; mu = &m; }
+   ElasticityIntegrator(Coefficient &l, Coefficient &m,
+                        const IntegrationRule *ir = NULL) :
+      BilinearFormIntegrator(ir) { lambda = &l; mu = &m; }
   /** With this constructor $\lambda = q_l m$ and $\mu = q_m m$
       if $dim q_l + 2 q_m = 0$ then $tr(\sigma) = 0$. */
   ElasticityIntegrator(Coefficient &m, real_t q_l, real_t q_m)
@@ -39,16 +39,11 @@ void PLBound::Setup(const int nb_i, const int ncp_i,
   b_type = b_type_i;
   cp_type = cp_type_i;
   tol = tol_i;
-   lbound.SetSize(ncp, nb);
-   ubound.SetSize(ncp, nb);
-   lbound_t.SetSize(nb, ncp);
-   ubound_t.SetSize(nb, ncp);
+   lbound.SetSize(nb, ncp);
+   ubound.SetSize(nb, ncp);
   nodes.SetSize(nb);
   weights.SetSize(nb);
   control_points.SetSize(ncp);
-   xhat.SetSize(nb);
-   what.SetSize(nb);
-   cphat.SetSize(ncp);

   auto scalenodes = [](const Vector &in, const real_t a, const real_t b) -> Vector
   {
@@ -95,10 +90,6 @@ void PLBound::Setup(const int nb_i, const int ncp_i,
      MFEM_ABORT("Unsupported interval points. Use [0,1].\n");
   }
   control_points = scalenodes(control_points, 0.0, 1.0); // rescale to [0,1]
-   for (int i = 0; i < ncp; i++)
-   {
-      cphat(i) = 2.0*control_points(i) - 1.0;
-   }

   Poly_1D::Basis &basis1d(poly1d.GetBasis(nb-1, b_type));

@@ -134,28 +125,22 @@ void PLBound::Setup(const int nb_i, const int ncp_i,
      {
         if (j == 0)
         {
-            lbound(j,i) = bv(i);
-            ubound(j,i) = bv(i);
+            lbound(i, j) = bv(i);
+            ubound(i, j) = bv(i);
         }
         else if (j == ncp-1)
         {
-            lbound(j,i) = bv(i);
-            ubound(j,i) = bv(i);
+            lbound(i, j) = bv(i);
+            ubound(i, j) = bv(i);
         }
         else
         {
            vals(0)  = bv(i);
            vals(1) =  bmv(i) +  dm*bdmv(i);
            vals(2) =  bpv(i) +  dp*bdpv(i);
-            lbound(j,i) = vals.Min()-tol; // tolerance for good measure
-            ubound(j,i) = vals.Max()+tol; // tolerance for good measure
-            if (b_type == 2)
-            {
-               lbound(j,i) = std::max(lbound(j,i),0_r);
-            }
+            lbound(i, j) = vals.Min()-tol; // tolerance for good measure
+            ubound(i, j) = vals.Max()+tol; // tolerance for good measure
         }
-         lbound_t(i,j) = lbound(j,i);
-         ubound_t(i,j) = ubound(j,i);
      }
   }

@@ -187,11 +172,6 @@ void PLBound::Setup(const int nb_i, const int ncp_i,
         nodes(i) = irule.IntPoint(i).x;
      }
   }
-   for (int i = 0; i < nb; i++)
-   {
-      xhat(i) = 2.0*nodes(i) - 1.0;
-      what(i) = 2.0*weights(i);
-   }

   if (b_type == 2)
   {
@@ -293,7 +273,8 @@ void PLBound::Get1DBounds(const Vector &coeff, Vector &intmin,
   intmax.SetSize(ncp);
   intmin = 0.0;
   intmax = 0.0;
-   Vector coeffm;
+   Vector coeffm(nb);
+   coeffm = 0.0;

   real_t a0 = 0.0;
   real_t a1 = 0.0;
@@ -321,8 +302,6 @@ void PLBound::Get1DBounds(const Vector &coeff, Vector &intmin,
   // compute L2 projection for linear bases: a0 + a1*x
   if (proj)
   {
-      coeffm.SetSize(nb);
-      coeffm = 0.0;
      for (int i = 0; i < nb; i++)
      {
         x = 2.0*nodes_int(i)-1;
@@ -363,8 +342,8 @@ void PLBound::Get1DBounds(const Vector &coeff, Vector &intmin,
      real_t c = coeffm(i);
      for (int j = 0; j < ncp; j++)
      {
-         intmin(j) += min(lbound(j,i)*c, ubound(j,i)*c);
-         intmax(j) += max(lbound(j,i)*c, ubound(j,i)*c);
+         intmin(j) += min(lbound(i,j)*c, ubound(i,j)*c);
+         intmax(j) += max(lbound(i,j)*c, ubound(i,j)*c);
      }
   }
 }
@@ -495,10 +474,10 @@ void PLBound::Get2DBounds(const Vector &coeff, Vector &intmin,
         real_t w1 = intmaxT(id2++);
         for (int k = 0; k < ncp; k++) // kth row
         {
-            vals(0) = w0*lbound(k,j);
-            vals(1) = w0*ubound(k,j);
-            vals(2) = w1*lbound(k,j);
-            vals(3) = w1*ubound(k,j);
+            vals(0) = w0*lbound(j,k);
+            vals(1) = w0*ubound(j,k);
+            vals(2) = w1*lbound(j,k);
+            vals(3) = w1*ubound(j,k);
            intmin(k*ncp+i) += vals.Min();
            intmax(k*ncp+i) += vals.Max();
         }
@@ -574,17 +553,17 @@ void PLBound::Get3DBounds(const Vector &coeff, Vector &intmin,
            for (int i = 0; i < nb; i++)
            {
               x = 2.0*nodes(i)-1; // x-coordinate
-               minNodalVals(i) -= a0V(j) + a1V(j)*x;
-               maxNodalVals(i) -= a0V(j) + a1V(j)*x;
+               minBounds(i) -= a0V(j) + a1V(j)*x;
+               maxBounds(i) -= a0V(j) + a1V(j)*x;
            }
            // Compute Bernstein coefficients
            LUFactors lu(basisMatLU.GetData(), lu_ip.GetData());
-            lu.Solve(nb, 1, minNodalVals.GetData());
-            lu.Solve(nb, 1, maxNodalVals.GetData());
+            lu.Solve(nb, 1, minBounds.GetData());
+            lu.Solve(nb, 1, maxBounds.GetData());
            for (int i = 0; i < nb; i++)
            {
-               intminT(i*ncp2+j) = minNodalVals(i);
-               intmaxT(i*ncp2+j) = maxNodalVals(i);
+               intminT(i*ncp2+j) = minBounds(i);
+               intmaxT(i*ncp2+j) = maxBounds(i);
            }
         }
      }
@@ -638,10 +617,10 @@ void PLBound::Get3DBounds(const Vector &coeff, Vector &intmin,
         real_t w1 = intmaxT(id2++);
         for (int k = 0; k < ncp; k++) // kth slice
         {
-            vals(0) = w0*lbound(k,j);
-            vals(1) = w0*ubound(k,j);
-            vals(2) = w1*lbound(k,j);
-            vals(3) = w1*ubound(k,j);
+            vals(0) = w0*lbound(j,k);
+            vals(1) = w0*ubound(j,k);
+            vals(2) = w1*lbound(j,k);
+            vals(3) = w1*ubound(j,k);
            intmin(k*ncp2+i) += vals.Min();
            intmax(k*ncp2+i) += vals.Max();
         }
@@ -674,8 +653,7 @@ void PLBound::SetupBernsteinBasisMat(DenseMatrix &basisMat,
                                     Vector &nodesBern) const
 {
   const int nbern = nodesBern.Size();
-   L2_SegmentElement el(nbern-1, 2);
-   // we use L2 to leverage lexicographic order
+   L2_SegmentElement el(nbern-1, 2); // we use L2 to leverage lexicographic order
   Array<int> ordering = el.GetLexicographicOrdering();
   basisMat.SetSize(nbern, nbern);
   Vector shape(nbern);
@@ -688,39 +666,6 @@ void PLBound::SetupBernsteinBasisMat(DenseMatrix &basisMat,
   }
 }

-DenseMatrix PLBound::GetBoundingMatrix(int dim, bool is_lower) const
-{
-   if (dim > 1)
-   {
-      const int ncpd = static_cast<int>(std::pow(ncp, dim));
-      const int nbd = static_cast<int>(std::pow(nb, dim));
-      DenseMatrix boundND(ncpd, nbd);
-      Vector phimin, phimax, col;
-      Vector coeffs(nbd);
-      coeffs = 0.0;
-      for (int j = 0; j < nbd; j++)
-      {
-         coeffs(j) = 1.0;
-         boundND.GetColumnReference(j, col);
-         GetNDBounds(dim, coeffs, phimin, phimax);
-         col = is_lower ? phimin : phimax;
-         coeffs(j) = 0.0;
-      }
-      return boundND;
-   }
-   return is_lower ? lbound : ubound;
-}
-
-DenseMatrix PLBound::GetLowerBoundMatrix(int dim) const
-{
-   return GetBoundingMatrix(dim, true);
-}
-
-DenseMatrix PLBound::GetUpperBoundMatrix(int dim) const
-{
-   return GetBoundingMatrix(dim, false);
-}
-
 constexpr int PLBound::min_ncp_gl_x[2][11];
 constexpr int PLBound::min_ncp_gll_x[2][11];
 constexpr int PLBound::min_ncp_pos_x[2][11];
@@ -13,25 +13,20 @@
 #define MFEM_BOUNDS

 #include "../config/config.hpp"
-#include "../general/forall.hpp"
 #include "fespace.hpp"

 namespace mfem
 {

 /** @name Piecewise linear bounds of bases
-    \brief Piecewise linear bounds of bases can be used to compute bounds on
-    the grid function in each element. The bounds for the bases are constructed
-    based on the following parameters:
+    \brief Piecewise linear bounds of bases can be used to compute bounds on the grid function in each element. The bounds for the bases are constructed based on the following parameters:

    (i) @b nb: number of bases/nodes in 1D (i.e. polynomial order+1),

-    (ii) @b b_type: bases type, 0 - Lagrange interpolants on Gauss-Legendre
-    nodes, 1 - Lagrange interpolants on Gauss-Lobatto-Legendre nodes, and
+    (ii) @b b_type: bases type, 0 - Lagrange interpolants on Gauss-Legendre nodes, 1 - Lagrange interpolants on Gauss-Lobatto-Legendre nodes, and
    2 - Positive/Bernstein bases on uniformly distributed nodes,

-    (iii) @b ncp: number of control points used to construct the piecewise
-    linear bounds
+    (iii) @b ncp: number of control points used to construct the piecewise linear bounds

    (iv) @b cp_type: control point distribution. 0 - GL + end-points,
                    1 - Chebyshev.
@@ -40,9 +35,7 @@ namespace mfem

    If the user does not specify @b ncp and @b cp_type, the minimum value of
    @b ncp is used that would bound the bases for the @b cp_type. We default
-    to @b cp_type = 0 as it requires fewer number of points to bound the bases.
-    Typically, @b ncp = 2 @b nb is sufficient to get fairly compact bounds, and
-    increasing @b ncp results in tighter bounds.
+    to @b cp_type = 0 as it requires fewer number of points to bound the bases. Typically, @b ncp = 2 @b nb is sufficient to get fairly compact bounds, and increasing @b ncp results in tighter bounds.

    Finally, only tensor-product elements are currently supported.

@@ -61,9 +54,7 @@ private:
   bool proj = true; // Use linear projection to compute bounds.
   real_t tol = 0.0; // offset bounds to avoid round-off errors
   Vector nodes, weights, control_points;
-   Vector xhat, what, cphat;
-   DenseMatrix lbound, ubound; // ncp x nb matrices with bounds of all bases
-   DenseMatrix lbound_t, ubound_t; // nb x ncp transposes for device kernel
+   DenseMatrix lbound, ubound; // nb x ncp matrices with bounds of all bases
   // Some auxillary storage for computing the bounds with Bernstein
   DenseMatrix basisMatNodes; // Bernstein bases at equispaced nodes
   DenseMatrix basisMatInt;   // Bernstein bases at GLL nodes
@@ -89,9 +80,6 @@ private:
      {3,5,8,9,11,12,13,13,14,15,16}
   };

-   /// Helper function to extract lower or upper bounding matrix
-   DenseMatrix GetBoundingMatrix(int dim, bool is_lower) const;
-
 public:
   // Constructor
   PLBound(const int nb_i, const int ncp_i, const int b_type_i,
@@ -104,699 +92,46 @@ public:
   PLBound(const FiniteElementSpace *fes,
           const int ncp_i = -1, const int cp_type_i = 0);

-   /// Get minimum number of control points needed to bound the given bases
+   // Get minimum number of control points needed to bound the given bases
   int GetMinimumPointsForGivenBases(int nb_i, int b_type_i,
                                     int cp_type_i) const;

-   /// Print information about the bounds
+   // Print information about the bounds
   void Print(std::ostream &outp = mfem::out) const;

-   /** @brief Enable (default) or disable linear projection before bounding.
-    *
-    *  @details This projection increases the computational cost but results in
-    *  tighter bounds.
-    */
-   void SetProjectionFlagForBounding(bool proj_)
-   {
-      proj = proj_;
-   }
+   // Enable (default) or disable linear projection before bounding.
+   // This projection increases the computational cost but results in tighter
+   // bounds.
+   void SetProjectionFlagForBounding(bool proj_) { proj = proj_; }

-   /** @brief Compute piecewise linear bounds for the lexicographically-ordered
-    *  nodal coefficients in @a coeff in 1D/2D/3D.
-    *
-    *  @param[in] rdim    The spatial dimension of the element (1, 2, or 3).
-    *  @param[in] coeff   The vector of lexicographically-ordered coefficients.
-    *                     Should be of size nb^rdim, where nb is the number of
-    *                     bases/nodes in 1D. These coefficients must correspond
-    *                     to the bases type and number of bases, used in the
-    *                     constructor of PLBound.
-    *
-    *  @param[out] intmin The vector of minimum bound for all control points.
-    *  @param[out] intmax The vector of maximum bound for all control points.
-    *                     Both intmin and intmax are of size ncp^rdim, where
-    *                     ncp is the number of control points in 1D, and are
-    *                     ordered lexicographically.
-    */
+   /// Compute piecewise linear bounds for the lexicographically-ordered
+   /// coefficients in @a coeff in 1D/2D/3D.
   void GetNDBounds(const int rdim, const Vector &coeff,
                    Vector &intmin, Vector &intmax) const;

   /// Get number of control points used to compute the bounds.
   int GetNControlPoints() const { return ncp; }
-
-   /// Get the underlying 1D basis type.
-   int GetBasisType() const { return b_type; }
-
-   /// Get 1D control point locations (lexicographic order) in [0,1].
-   const Vector &GetControlPoints() const { return control_points; }
-
-   /** @brief Compute element-wise bounds from a lexicographic E-vector.
-    *
-    *  @details The expected layout of @a e_vec is `ND x VDIM x NE`, where
-    *  `ND = nb^rdim`, `VDIM = fes_vdim`, and `NE` is the number of elements.
-    *  The output layout matches GridFunction::GetElementBounds:
-    *  `NE x active_vdim`, with the element index varying fastest.
-    */
-   void GetElementBoundsKernel(const int rdim, const int fes_vdim,
-                               const Vector &e_vec, Vector &lower,
-                               Vector &upper, const int vdim = 0) const;
-
-   /** @brief Get lower and upper bounding matrix (ncp^dim x nb^dim)
-    *
-    *  @details The matrices can be used to compute the bounds at control points
-    *           by a simple matrix-vector product with the
-    *           lexicographically-ordered nodal coefficients.
-    *           The resulting output is also lexicographically-ordered.
-    *
-    *  @note These matrices do not account for the linear projection step that
-    *        is optionally done in GetNDBounds before bounding the function.
-    */
-   ///@{
-   DenseMatrix GetLowerBoundMatrix(int dim = 1) const;
-   DenseMatrix GetUpperBoundMatrix(int dim = 1) const;
-   ///@}
-
 private:
-   /** @brief Compute piecewise linear bounds for the lexicographically-ordered
-    *  nodal coefficients in @a coeff in 1D.
-    *  See GetNDBounds for details of the input and output parameters.
-    */
+   /// Compute piecewise linear bounds for the lexicographically-ordered
+   /// coefficients in @a coeff in 1D.
   void Get1DBounds(const Vector &coeff, Vector &intmin, Vector &intmax) const;

-   /** @brief Compute piecewise linear bounds for the lexicographically-ordered
-    *  nodal coefficients in @a coeff in 2D.
-    *  See GetNDBounds for details of the input and output parameters.
-    */
+   /// Compute piecewise linear bounds for the lexicographically-ordered
+   /// coefficients in @a coeff in 2D.
   void Get2DBounds(const Vector &coeff, Vector &intmin, Vector &intmax) const;

-   /** @brief Compute piecewise linear bounds for the lexicographically-ordered
-    *  nodal coefficients in @a coeff in 3D.
-    *  See GetNDBounds for details of the input and output parameters.
-    */
+   /// Compute piecewise linear bounds for the lexicographically-ordered
+   /// coefficients in @a coeff in 3D.
   void Get3DBounds(const Vector &coeff, Vector &intmin, Vector &intmax) const;

-   /** @brief Setup matrix used to compute values at given 1D locations in [0,1]
-    *  for Bernstein bases.
-    */
+   /// Setup matrix used to compute values at given 1D locations in [0,1]
+   /// for Bernstein bases.
   void SetupBernsteinBasisMat(DenseMatrix &basisMat, Vector &nodesBern) const;

   void Setup(const int nb_i, const int ncp_i, const int b_type_i,
              const int cp_type_i, const real_t tol_i);
 };

-namespace internal
-{
-
-struct PLBoundDeviceData
-{
-   int nb;
-   int ncp;
-   const real_t *xhat;
-   const real_t *what;
-   const real_t *cphat;
-   const real_t *lbound;
-   const real_t *ubound;
-};
-
-template<int T_NB = 0, bool T_PROJ = true>
-inline void GetElementBoundsKernel1D(const PLBoundDeviceData &data,
-                                     const int fes_vdim,
-                                     const int ne,
-                                     const Vector &e_vec,
-                                     Vector &lower,
-                                     Vector &upper,
-                                     const int comp0,
-                                     const int ncomp)
-{
-   constexpr int GENERIC_MAX_ND = 32;
-   constexpr int MAX_ND = T_NB ? T_NB : GENERIC_MAX_ND;
-   constexpr int BLOCK_X = 2*MAX_ND;
-
-   const int nd = T_NB ? T_NB : data.nb;
-   MFEM_VERIFY(nd <= MAX_ND,
-               "Device element bounds kernel supports up to 32 "
-               "1D degrees of freedom.");
-
-   const auto E = Reshape(e_vec.Read(), nd, fes_vdim, ne);
-   auto L = Reshape(lower.Write(), ne, ncomp);
-   auto U = Reshape(upper.Write(), ne, ncomp);
-
-   mfem::forall_2D<BLOCK_X>(ne*ncomp, BLOCK_X, 1,
-                            [=] MFEM_HOST_DEVICE (int ec)
-   {
-      const int e = ec % ne;
-      const int c = ec / ne;
-      const int vc = comp0 + c;
-      const real_t *coeff = &E(0, vc, e);
-      const int tid = MFEM_THREAD_ID(x);
-
-      MFEM_SHARED real_t sproj[MAX_ND];
-      MFEM_SHARED real_t ssum0[MAX_ND];
-      MFEM_SHARED real_t ssum1[MAX_ND];
-      MFEM_SHARED real_t smin[BLOCK_X];
-      MFEM_SHARED real_t smax[BLOCK_X];
-      MFEM_SHARED real_t sa0;
-      MFEM_SHARED real_t sa1;
-
-      MFEM_FOREACH_THREAD(i, x, nd)
-      {
-         if constexpr (T_PROJ)
-         {
-            const real_t x = data.xhat[i];
-            const real_t w = data.what[i];
-            ssum0[i] = 0.5*coeff[i]*w;
-            ssum1[i] = 1.5*coeff[i]*w*x;
-         }
-         else
-         {
-            ssum0[i] = 0.0;
-            ssum1[i] = 0.0;
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      MFEM_FOREACH_THREAD(ii, x, 1)
-      {
-         sa0 = 0.0;
-         sa1 = 0.0;
-         for (int i = 0; i < nd; i++)
-         {
-            sa0 += ssum0[i];
-            sa1 += ssum1[i];
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      MFEM_FOREACH_THREAD(i, x, nd)
-      {
-         if constexpr (T_PROJ)
-         {
-            const real_t x = data.xhat[i];
-            sproj[i] = coeff[i] - sa0 - sa1*x;
-         }
-         else
-         {
-            sproj[i] = coeff[i];
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      real_t lower_local = HUGE_VAL;
-      real_t upper_local = -HUGE_VAL;
-      MFEM_FOREACH_THREAD(j, x, data.ncp)
-      {
-         real_t lo = 0.0;
-         real_t hi = 0.0;
-         if constexpr (T_PROJ)
-         {
-            const real_t xcp = data.cphat[j];
-            lo = sa0 + sa1*xcp;
-            hi = lo;
-         }
-
-         for (int i = 0; i < nd; i++)
-         {
-            const real_t val = sproj[i];
-            const real_t lv = data.lbound[j + i*data.ncp]*val;
-            const real_t uv = data.ubound[j + i*data.ncp]*val;
-            lo += lv < uv ? lv : uv;
-            hi += lv > uv ? lv : uv;
-         }
-         lower_local = lower_local < lo ? lower_local : lo;
-         upper_local = upper_local > hi ? upper_local : hi;
-      }
-
-      smin[tid] = lower_local;
-      smax[tid] = upper_local;
-      MFEM_SYNC_THREAD;
-
-      MFEM_FOREACH_THREAD(ii, x, 1)
-      {
-         real_t lower_ec = smin[0];
-         real_t upper_ec = smax[0];
-         const int nthreads = MFEM_THREAD_SIZE(x);
-         const int nactive = data.ncp < nthreads ? data.ncp : nthreads;
-         for (int t = 1; t < nactive; t++)
-         {
-            lower_ec = lower_ec < smin[t] ? lower_ec : smin[t];
-            upper_ec = upper_ec > smax[t] ? upper_ec : smax[t];
-         }
-         L(e, c) = lower_ec;
-         U(e, c) = upper_ec;
-      }
-   });
-}
-
-template<int T_NB = 0, int T_NCP = 0, bool T_PROJ = true>
-inline void GetElementBoundsKernel2D(const PLBoundDeviceData &data,
-                                     const int fes_vdim,
-                                     const int ne,
-                                     const Vector &e_vec,
-                                     Vector &lower,
-                                     Vector &upper,
-                                     const int comp0,
-                                     const int ncomp)
-{
-   constexpr int DEFAULT_MAX_NB = 8;
-   constexpr int DEFAULT_MAX_CP = 3*DEFAULT_MAX_NB;
-   constexpr int MAX_NB = T_NB ? T_NB : DEFAULT_MAX_NB;
-   constexpr int MAX_CP = T_NCP ? T_NCP : DEFAULT_MAX_CP;
-   constexpr int MAX_THREADS = MAX_CP*MAX_CP;
-
-   const int nb = data.nb;
-   const int ncp = data.ncp;
-   const int nd = nb*nb;
-   MFEM_VERIFY(nb <= MAX_NB,
-               "Device 2D element bounds kernel exceeds its compile-time "
-               "1D degree bound.");
-   MFEM_VERIFY(ncp <= MAX_CP,
-               "Device 2D element bounds kernel exceeds its compile-time "
-               "control-point bound.");
-   MFEM_VERIFY(ncp*ncp <= MAX_THREADS,
-               "Device 2D element bounds kernel exceeds its compile-time "
-               "thread-block bound.");
-
-   const auto E = Reshape(e_vec.Read(), nd, fes_vdim, ne);
-   auto L = Reshape(lower.Write(), ne, ncomp);
-   auto U = Reshape(upper.Write(), ne, ncomp);
-
-   mfem::forall_2D<MAX_THREADS>(ne*ncomp, ncp, ncp,
-                                [=] MFEM_HOST_DEVICE (int ec)
-   {
-      const int e = ec % ne;
-      const int c = ec / ne;
-      const int vc = comp0 + c;
-      const real_t *coeff = &E(0, vc, e);
-      const int tx = MFEM_THREAD_ID(x);
-      const int ty = MFEM_THREAD_ID(y);
-
-      MFEM_SHARED real_t sproj[MAX_NB*MAX_NB];
-      MFEM_SHARED real_t srow_min[MAX_NB*MAX_CP];
-      MFEM_SHARED real_t srow_max[MAX_NB*MAX_CP];
-      MFEM_SHARED real_t srow_a0[MAX_NB];
-      MFEM_SHARED real_t srow_a1[MAX_NB];
-      MFEM_SHARED real_t sa0[MAX_CP];
-      MFEM_SHARED real_t sa1[MAX_CP];
-      MFEM_SHARED real_t smin[MAX_THREADS];
-      MFEM_SHARED real_t smax[MAX_THREADS];
-
-      // Stage 1a: for each nodal row, form the per-node contributions to the
-      // row-wise linear fit used by the first 1D bounding solve.
-      MFEM_FOREACH_THREAD(jrow, y, nb)
-      {
-         const real_t *row_coeff = coeff + jrow*nb;
-         const int row_ncp_off = jrow*MAX_CP;
-         MFEM_FOREACH_THREAD(i, x, nb)
-         {
-            if constexpr (T_PROJ)
-            {
-               const real_t x = data.xhat[i];
-               const real_t w = data.what[i];
-               srow_min[row_ncp_off + i] = 0.5*row_coeff[i]*w;
-               srow_max[row_ncp_off + i] = 1.5*row_coeff[i]*w*x;
-            }
-            else
-            {
-               srow_min[row_ncp_off + i] = 0.0;
-               srow_max[row_ncp_off + i] = 0.0;
-            }
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 1b: reduce the row-wise projection coefficients a0/a1.
-      if constexpr (T_PROJ)
-      {
-         MFEM_FOREACH_THREAD(jrow, y, nb)
-         {
-            const int row_ncp_off = jrow*MAX_CP;
-            real_t a0 = 0.0;
-            real_t a1 = 0.0;
-            MFEM_FOREACH_THREAD(ii, x, 1)
-            {
-               for (int i = 0; i < nb; i++)
-               {
-                  a0 += srow_min[row_ncp_off + i];
-                  a1 += srow_max[row_ncp_off + i];
-               }
-               srow_a0[jrow] = a0;
-               srow_a1[jrow] = a1;
-            }
-         }
-         MFEM_SYNC_THREAD;
-      }
-
-      // Stage 1c: subtract the row-wise linear fit once and cache the
-      // projected row coefficients for reuse across all x-control points.
-      MFEM_FOREACH_THREAD(jrow, y, nb)
-      {
-         const real_t *row_coeff = coeff + jrow*nb;
-         MFEM_FOREACH_THREAD(i, x, nb)
-         {
-            if constexpr (T_PROJ)
-            {
-               const real_t x = data.xhat[i];
-               sproj[jrow*MAX_NB + i] = row_coeff[i]
-                                        - srow_a0[jrow] - srow_a1[jrow]*x;
-            }
-            else
-            {
-               sproj[jrow*MAX_NB + i] = row_coeff[i];
-            }
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 1d: solve the first 1D bounding problem along each nodal row and
-      // store bounds at every x-direction control point.
-      MFEM_FOREACH_THREAD(icp, x, ncp)
-      {
-         MFEM_FOREACH_THREAD(jrow, y, nb)
-         {
-            const int row_cp_off = jrow*ncp;
-            real_t lo = 0.0;
-            real_t hi = 0.0;
-            if constexpr (T_PROJ)
-            {
-               const real_t xcp = data.cphat[icp];
-               lo = srow_a0[jrow] + srow_a1[jrow]*xcp;
-               hi = lo;
-            }
-            for (int i = 0; i < nb; i++)
-            {
-               const real_t val = sproj[jrow*MAX_NB + i];
-               const real_t lv = data.lbound[icp + i*data.ncp]*val;
-               const real_t uv = data.ubound[icp + i*data.ncp]*val;
-               lo += lv < uv ? lv : uv;
-               hi += lv > uv ? lv : uv;
-            }
-            srow_min[row_cp_off + icp] = lo;
-            srow_max[row_cp_off + icp] = hi;
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 2a: from the row bounds, form the per-row contributions to the
-      // second 1D projection solve in the y-direction.
-      MFEM_FOREACH_THREAD(icp, x, ncp)
-      {
-         MFEM_FOREACH_THREAD(jrow, y, nb)
-         {
-            const int row_cp_off = jrow*ncp;
-            if constexpr (T_PROJ)
-            {
-               const real_t x = data.xhat[jrow];
-               const real_t w = data.what[jrow];
-               const real_t t = 0.5*(srow_min[row_cp_off + icp] +
-                                     srow_max[row_cp_off + icp]);
-               smin[row_cp_off + icp] = 0.5*t*w;
-               smax[row_cp_off + icp] = 1.5*t*w*x;
-            }
-            else
-            {
-               smin[row_cp_off + icp] = 0.0;
-               smax[row_cp_off + icp] = 0.0;
-            }
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 2b: reduce the y-direction projection coefficients for each
-      // x-control-point column.
-      MFEM_FOREACH_THREAD(jj, y, 1)
-      {
-         MFEM_FOREACH_THREAD(icp, x, ncp)
-         {
-            real_t a0 = 0.0;
-            real_t a1 = 0.0;
-            for (int jrow = 0; jrow < nb; jrow++)
-            {
-               a0 += smin[jrow*ncp + icp];
-               a1 += smax[jrow*ncp + icp];
-            }
-            sa0[icp] = a0;
-            sa1[icp] = a1;
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 2c: subtract the y-direction linear fit from the intermediate
-      // row bounds so the final tensor-product bound uses the perturbation.
-      if constexpr (T_PROJ)
-      {
-         MFEM_FOREACH_THREAD(icp, x, ncp)
-         {
-            MFEM_FOREACH_THREAD(jrow, y, nb)
-            {
-               const int row_cp_off = jrow*ncp;
-               const real_t x = data.xhat[jrow];
-               const real_t t = sa0[icp] + sa1[icp]*x;
-               srow_min[row_cp_off + icp] -= t;
-               srow_max[row_cp_off + icp] -= t;
-            }
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      // Stage 3: each thread now owns one 2D control point (icp, kcp) and
-      // accumulates its final lower/upper bound from the row-bound data.
-      MFEM_FOREACH_THREAD(icp, x, ncp)
-      {
-         MFEM_FOREACH_THREAD(kcp, y, ncp)
-         {
-            real_t lo = 0.0;
-            real_t hi = 0.0;
-            if constexpr (T_PROJ)
-            {
-               const real_t xcp = data.cphat[kcp];
-               lo = sa0[icp] + sa1[icp]*xcp;
-               hi = lo;
-            }
-            for (int jrow = 0; jrow < nb; jrow++)
-            {
-               const real_t w0 = srow_min[jrow*ncp + icp];
-               const real_t w1 = srow_max[jrow*ncp + icp];
-               const real_t lb = data.lbound[kcp + jrow*data.ncp];
-               const real_t ub = data.ubound[kcp + jrow*data.ncp];
-               const real_t v0 = lb*w0;
-               const real_t v1 = ub*w0;
-               const real_t v2 = lb*w1;
-               const real_t v3 = ub*w1;
-               real_t vlo = v0 < v1 ? v0 : v1;
-               real_t vhi = v0 > v1 ? v0 : v1;
-               vlo = vlo < v2 ? vlo : v2;
-               vlo = vlo < v3 ? vlo : v3;
-               vhi = vhi > v2 ? vhi : v2;
-               vhi = vhi > v3 ? vhi : v3;
-               lo += vlo;
-               hi += vhi;
-            }
-            const int slot = kcp*ncp + icp;
-            smin[slot] = lo;
-            smax[slot] = hi;
-         }
-      }
-      MFEM_SYNC_THREAD;
-
-      const int lane = ty*ncp + tx;
-      const int nactive = ncp*ncp;
-      const int nthreads = MFEM_THREAD_SIZE(x)*MFEM_THREAD_SIZE(y);
-
-      // Reduce all 2D control-point bounds to one lower/upper pair per
-      // (element, component).
-      if (nthreads == 1)
-      {
-         if (tx == 0 && ty == 0)
-         {
-            real_t lower_ec = smin[0];
-            real_t upper_ec = smax[0];
-            for (int t = 1; t < nactive; t++)
-            {
-               lower_ec = lower_ec < smin[t] ? lower_ec : smin[t];
-               upper_ec = upper_ec > smax[t] ? upper_ec : smax[t];
-            }
-            L(e, c) = lower_ec;
-            U(e, c) = upper_ec;
-         }
-      }
-      else
-      {
-         for (int stride = (nactive + 1)/2; stride > 0;
-              stride = (stride + 1)/2)
-         {
-            if (lane < stride && lane + stride < nactive)
-            {
-               smin[lane] = smin[lane] < smin[lane + stride] ?
-                            smin[lane] : smin[lane + stride];
-               smax[lane] = smax[lane] > smax[lane + stride] ?
-                            smax[lane] : smax[lane + stride];
-            }
-            MFEM_SYNC_THREAD;
-            if (stride == 1) { break; }
-         }
-
-         if (lane == 0)
-         {
-            L(e, c) = smin[0];
-            U(e, c) = smax[0];
-         }
-      }
-   });
-}
-
-} // namespace internal
-
-inline void PLBound::GetElementBoundsKernel(const int rdim, const int fes_vdim,
-                                            const Vector &e_vec,
-                                            Vector &lower, Vector &upper,
-                                            const int vdim) const
-{
-   MFEM_VERIFY(b_type != BasisType::Positive,
-               "Bernstein device bounds are not implemented.");
-   if (rdim == 3)
-   {
-      MFEM_ABORT("Device element bounds kernel currently only supports 1D/2D.");
-   }
-   MFEM_VERIFY(rdim == 1 || rdim == 2, "Invalid element dimension.");
-   MFEM_VERIFY(vdim >= -1 && vdim <= fes_vdim, "Invalid vector component.");
-   const int nd = static_cast<int>(std::pow(nb, rdim));
-   const int ne = e_vec.Size()/(nd*fes_vdim);
-   const int ncomp = (vdim > 0) ? 1 : fes_vdim;
-
-   lower.SetSize(ne*ncomp, e_vec);
-   upper.SetSize(ne*ncomp, e_vec);
-   lower.UseDevice(true);
-   upper.UseDevice(true);
-
-   if (!proj)
-   {
-      MFEM_ABORT("Device element bounds kernel currently requires projection "
-                 "enabled.");
-   }
-
-   const real_t *dxhat = xhat.Read();
-   const real_t *dwhat = what.Read();
-   const real_t *dcphat = cphat.Read();
-   const real_t *dlbound = lbound.Read();
-   const real_t *dubound = ubound.Read();
-
-   internal::PLBoundDeviceData data
-   {
-      nb,
-      ncp,
-      dxhat,
-      dwhat,
-      dcphat,
-      dlbound,
-      dubound
-   };
-
-   const int comp0 = (vdim > 0) ? (vdim - 1) : 0;
-
-   if (rdim == 1)
-   {
-      switch (nb)
-      {
-         case 2: return internal::GetElementBoundsKernel1D<2, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 3: return internal::GetElementBoundsKernel1D<3, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 4: return internal::GetElementBoundsKernel1D<4, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 5: return internal::GetElementBoundsKernel1D<5, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 6: return internal::GetElementBoundsKernel1D<6, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 7: return internal::GetElementBoundsKernel1D<7, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 8: return internal::GetElementBoundsKernel1D<8, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 9: return internal::GetElementBoundsKernel1D<9, true>(data, fes_vdim, ne,
-                                                                     e_vec, lower, upper,
-                                                                     comp0, ncomp);
-         case 10: return internal::GetElementBoundsKernel1D<10, true>(data, fes_vdim, ne,
-                                                                       e_vec, lower, upper,
-                                                                       comp0, ncomp);
-         default: return internal::GetElementBoundsKernel1D<0, true>(data, fes_vdim, ne,
-                                                                      e_vec, lower, upper,
-                                                                      comp0, ncomp);
-      }
-   }
-#define MFEM_PLBOUND_2D_DISPATCH(NB, NCP) \
-   return internal::GetElementBoundsKernel2D<NB, NCP, true>(data, fes_vdim, ne, \
-                                                            e_vec, lower, upper, \
-                                                            comp0, ncomp)
-   switch (nb)
-   {
-      case 2:
-         switch (ncp)
-         {
-            case 4: MFEM_PLBOUND_2D_DISPATCH(2, 4);
-            case 6: MFEM_PLBOUND_2D_DISPATCH(2, 6);
-            case 8: MFEM_PLBOUND_2D_DISPATCH(2, 8);
-         }
-         break;
-      case 3:
-         switch (ncp)
-         {
-            case 6: MFEM_PLBOUND_2D_DISPATCH(3, 6);
-            case 9: MFEM_PLBOUND_2D_DISPATCH(3, 9);
-            case 12: MFEM_PLBOUND_2D_DISPATCH(3, 12);
-         }
-         break;
-      case 4:
-         switch (ncp)
-         {
-            case 8: MFEM_PLBOUND_2D_DISPATCH(4, 8);
-            case 12: MFEM_PLBOUND_2D_DISPATCH(4, 12);
-            case 16: MFEM_PLBOUND_2D_DISPATCH(4, 16);
-         }
-         break;
-      case 5:
-         switch (ncp)
-         {
-            case 10: MFEM_PLBOUND_2D_DISPATCH(5, 10);
-            case 15: MFEM_PLBOUND_2D_DISPATCH(5, 15);
-            case 20: MFEM_PLBOUND_2D_DISPATCH(5, 20);
-         }
-         break;
-      case 6:
-         switch (ncp)
-         {
-            case 12: MFEM_PLBOUND_2D_DISPATCH(6, 12);
-            case 18: MFEM_PLBOUND_2D_DISPATCH(6, 18);
-            case 24: MFEM_PLBOUND_2D_DISPATCH(6, 24);
-         }
-         break;
-      case 7:
-         switch (ncp)
-         {
-            case 14: MFEM_PLBOUND_2D_DISPATCH(7, 14);
-            case 21: MFEM_PLBOUND_2D_DISPATCH(7, 21);
-            case 28: MFEM_PLBOUND_2D_DISPATCH(7, 28);
-         }
-         break;
-      case 8:
-         switch (ncp)
-         {
-            case 16: MFEM_PLBOUND_2D_DISPATCH(8, 16);
-            case 24: MFEM_PLBOUND_2D_DISPATCH(8, 24);
-            case 32: MFEM_PLBOUND_2D_DISPATCH(8, 32);
-         }
-         break;
-   }
-#undef MFEM_PLBOUND_2D_DISPATCH
-   return internal::GetElementBoundsKernel2D<0, 0, true>(data, fes_vdim, ne,
-                                                         e_vec, lower, upper,
-                                                         comp0, ncomp);
-}
-
 } // namespace mfem

 #endif // MFEM_BOUNDS
@@ -1302,73 +1302,6 @@ real_t TraceCoefficient::Eval(ElementTransformation &T,
   return ma.Trace();
 }

-VectorComponentCoefficient::VectorComponentCoefficient(VectorCoefficient &A,
-                                                       int c)
-   : a(&A), va(A.GetVDim())
-{
-   SetComponent(c);
-}
-
-void VectorComponentCoefficient::SetComponent(int c)
-{
-   MFEM_ASSERT(c < a->GetVDim() && c >= 0,
-               "VectorComponentCoefficient:  "
-               "Index not in range.");
-
-   component = c;
-}
-
-void VectorComponentCoefficient::SetTime(real_t t)
-{
-   if (a) { a->SetTime(t); }
-   this->Coefficient::SetTime(t);
-}
-
-real_t VectorComponentCoefficient::Eval(ElementTransformation &T,
-                                        const IntegrationPoint &ip)
-{
-   a->Eval(va, T, ip);
-   return va[component];
-}
-
-MatrixComponentCoefficient::MatrixComponentCoefficient(MatrixCoefficient &A,
-                                                       int ri, int ci)
-   : a(&A), ma(A.GetHeight(), A.GetWidth())
-{
-   SetRowIndex(ri);
-   SetColumnIndex(ci);
-}
-
-void MatrixComponentCoefficient::SetRowIndex(int ri)
-{
-   MFEM_ASSERT(ri < a->GetHeight() && ri >= 0,
-               "MatrixComponentCoefficient:  "
-               "Row index not in range.");
-
-   row_idx = ri;
-}
-
-void MatrixComponentCoefficient::SetColumnIndex(int ci)
-{
-   MFEM_ASSERT(ci < a->GetWidth() && ci >= 0,
-               "MatrixComponentCoefficient:  "
-               "Column index not in range.");
-   col_idx = ci;
-}
-
-void MatrixComponentCoefficient::SetTime(real_t t)
-{
-   if (a) { a->SetTime(t); }
-   this->Coefficient::SetTime(t);
-}
-
-real_t MatrixComponentCoefficient::Eval(ElementTransformation &T,
-                                        const IntegrationPoint &ip)
-{
-   a->Eval(ma, T, ip);
-   return ma(row_idx,col_idx);
-}
-
 VectorSumCoefficient::VectorSumCoefficient(int dim)
   : VectorCoefficient(dim),
     ACoef(NULL), BCoef(NULL),
@@ -52,9 +52,6 @@ public:
   /// Get the time for time dependent coefficients
   real_t GetTime() { return time; }

-   /// Returns dimension of the vector.
-   int GetVDim() { return 1; }
-
   /** @brief Evaluate the coefficient in the element described by @a T at the
       point @a ip. */
   /** @note When this method is called, the caller must make sure that the
@@ -117,10 +114,11 @@ public:
   /// Construct the constant coefficient using a vector of constants.
   /** @a c should be a vector defined by attributes, so for region with
       attribute @a i @a c[i-1] is the coefficient in that region */
-   PWConstCoefficient(const Vector &c) { UpdateConstants(c); }
+   PWConstCoefficient(Vector &c)
+   { constants.SetSize(c.Size()); constants=c; }

   /// Update the constants with vector @a c.
-   void UpdateConstants(const Vector &c) { constants = c; }
+   void UpdateConstants(Vector &c) { constants.SetSize(c.Size()); constants=c; }

   /// Return a reference to the i-th constant
   real_t &operator()(int i) { return constants(i-1); }
@@ -1334,8 +1332,8 @@ public:
   /// Get the coefficient located at (i,j) in the matrix.
   Coefficient* GetCoeff (int i, int j) { return Coeff[i*width+j]; }

-   /** @brief Set the coefficient located at (i,j) in the matrix.  By default
-       this will take ownership of the Coefficient passed in, but this
+   /** @brief Set the coefficient located at (i,j) in the matrix.  By default by
+       default this will take ownership of the Coefficient passed in, but this
       can be overridden with the @a own parameter. */
   void Set(int i, int j, Coefficient * c, bool own=true);

@@ -1875,85 +1873,6 @@ public:
               const IntegrationPoint &ip) override;
 };

-/// Scalar coefficient defined as component of a vector coefficient
-class VectorComponentCoefficient : public Coefficient
-{
-private:
-   VectorCoefficient *a = nullptr;
-
-   mutable Vector va;
-   int component;
-
-public:
-   /// Construct with a vector coefficient.
-   VectorComponentCoefficient(VectorCoefficient &A)
-      : a(&A), va(A.GetVDim()), component(0) {};
-
-   VectorComponentCoefficient(VectorCoefficient &A, int c);
-
-   /// Set the time for internally stored coefficients
-   void SetTime(real_t t) override;
-
-   /// Reset the vector coefficient
-   void SetACoef(VectorCoefficient &A) { a = &A; }
-
-   /// Return the vector coefficient
-   VectorCoefficient * GetACoef() const { return a; }
-
-   /// Set the component
-   void SetComponent(int c);
-
-   /// Return the component
-   int GetComponent() const { return component; }
-
-   /// Evaluate the trace coefficient at @a ip.
-   real_t Eval(ElementTransformation &T,
-               const IntegrationPoint &ip) override;
-};
-
-/// Scalar coefficient defined as component of a matrix coefficient
-class MatrixComponentCoefficient : public Coefficient
-{
-private:
-   MatrixCoefficient *a = nullptr;
-
-   mutable DenseMatrix ma;
-   int row_idx,col_idx;
-
-public:
-   MatrixComponentCoefficient(MatrixCoefficient &A)
-      : a(&A), ma(A.GetHeight(), A.GetWidth()), row_idx(0), col_idx(0) {};
-
-   /// Construct with the matrix coefficient.
-   MatrixComponentCoefficient(MatrixCoefficient &A, int ri, int ci);
-
-   /// Set the time for internally stored coefficients
-   void SetTime(real_t t) override;
-
-   /// Reset the matrix coefficient
-   void SetACoef(MatrixCoefficient &A) { a = &A; }
-
-   /// Return the matrix coefficient
-   MatrixCoefficient * GetACoef() const { return a; }
-
-   /// Reset the index
-   void SetRowIndex(int ri);
-
-   /// Return the index
-   int GetRowIndex() const { return row_idx; }
-
-   /// Reset the index
-   void SetColumnIndex(int ci);
-
-   /// Return the index
-   int GetColumnIndex() const { return col_idx; }
-
-
-   /// Evaluate the trace coefficient at @a ip.
-   real_t Eval(ElementTransformation &T,
-               const IntegrationPoint &ip) override;
-};
-
 /// Vector coefficient defined as the linear combination of two vectors
 class VectorSumCoefficient : public VectorCoefficient
 {
@@ -82,25 +82,6 @@ public:
   /// underlying #fes
   int VectorDim() const;

-   /// Copy assignment. Only the data of the base class Vector is copied.
-   /** It is assumed that this object and @a rhs use FiniteElementSpace%s that
-       have the same size.
-
-       @note Defining this method overwrites the implicitly defined copy
-       assignment operator. */
-   ComplexGridFunction &operator=(const ComplexGridFunction &rhs)
-   { return operator=((const Vector &)rhs); }
-
-   /// Copy the data from @a v.
-   /** The size of @a v must be equal to double of the size of the associated
-       FiniteElementSpace #fes. */
-   ComplexGridFunction &operator=(const Vector &v)
-   {
-      MFEM_ASSERT(fes && v.Size() == 2*fes->GetVSize(), "");
-      Vector::operator=(v);
-      return *this;
-   }
-
   /// Assign constant values to the ComplexGridFunction data.
   ComplexGridFunction &operator=(const std::complex<real_t> & value)
   { *gfr = value.real(); *gfi = value.imag(); return *this; }
@@ -492,8 +492,6 @@ void VisItDataCollection::SaveRootFile()
                           to_padded_string(cycle, pad_digits_cycle) +
                           ".mfem_root";
   std::ofstream root_file(root_name);
-   MFEM_VERIFY(root_file.is_open(),
-               "Failed to open ofstream " << root_name);
   root_file << GetVisItRootString();
   if (!root_file)
   {
@@ -979,10 +977,7 @@ void ParaViewDataCollection::Save()
   // Save the local part of the mesh and grid functions fields to the local
   // VTU file. Also save coefficient fields.
   {
-      std::string os_str = vtu_prefix + GenerateVTUFileName("proc", myid);
-      std::ofstream os(os_str);
-      MFEM_VERIFY(os.is_open(),
-                  "Failed to open ofstream " << os_str);
+      std::ofstream os(vtu_prefix + GenerateVTUFileName("proc", myid));
      os.precision(precision);
      SaveDataVTU(os, levels_of_detail);
   }
@@ -994,10 +989,7 @@ void ParaViewDataCollection::Save()
                  "QuadratureFunction output is not supported for "
                  "ParaViewDataCollection on domain boundary!");
      const std::string &field_name = qfield.first;
-      std::string os_str = vtu_prefix + GenerateVTUFileName(field_name, myid);
-      std::ofstream os(os_str);
-      MFEM_VERIFY(os.is_open(),
-                  "Failed to open ofstream " << os_str);
+      std::ofstream os(vtu_prefix + GenerateVTUFileName(field_name, myid));
      qfield.second->SaveVTU(os, pv_data_format, GetCompressionLevel(), field_name);
   }

@@ -1008,10 +1000,7 @@ void ParaViewDataCollection::Save()
   {
      // Create the main PVTU file
      {
-         std::string os_str = vtu_prefix + GeneratePVTUFileName("data");
-         std::ofstream pvtu_out(os_str);
-         MFEM_VERIFY(pvtu_out.is_open(),
-                     "Failed to open ofstream " << os_str);
+         std::ofstream pvtu_out(vtu_prefix + GeneratePVTUFileName("data"));
         WritePVTUHeader(pvtu_out);

         // Grid function fields and coefficient fields
@@ -1066,10 +1055,8 @@ void ParaViewDataCollection::Save()
         const std::string &q_field_name = q_field.first;
         std::string q_fname = GeneratePVTUPath() + "/"
                               + GeneratePVTUFileName(q_field_name);
-         std::string os_str = col_path + "/" + q_fname;
-         std::ofstream pvtu_out(os_str);
-         MFEM_VERIFY(pvtu_out.is_open(),
-                     "Failed to open ofstream " << os_str);
+
+         std::ofstream pvtu_out(col_path + "/" + q_fname);
         WritePVTUHeader(pvtu_out);
         int vec_dim = q_field.second->GetVDim();
         pvtu_out << "<PPointData>\n";
@@ -90,8 +90,8 @@ void map_quadrature_data_to_fields_impl(
   }
   else
   {
-      MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
-                        " for this field descriptor");
+      MFEM_ABORT("quadrature data mapping to field is not implemented for"
+                 " this field descriptor");
   }
 }

@@ -169,9 +169,8 @@ void map_quadrature_data_to_fields_tensor_impl_1d(
   }
   else
   {
-      MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
-                        "for this field descriptor with sum factorization on"
-                        " tensor product elements");
+      MFEM_ABORT("quadrature data mapping to field is not implemented for"
+                 " this field descriptor with sum factorization on tensor product elements");
   }
 }

@@ -307,9 +306,8 @@ void map_quadrature_data_to_fields_tensor_impl_2d(
   }
   else
   {
-      MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
-                        " for this field descriptor with sum factorization on"
-                        " tensor product elements");
+      MFEM_ABORT("quadrature data mapping to field is not implemented for"
+                 " this field descriptor with sum factorization on tensor product elements");
   }
 }

@@ -494,9 +492,8 @@ void map_quadrature_data_to_fields_tensor_impl_3d(
   }
   else
   {
-      MFEM_ABORT_KERNEL("quadrature data mapping to field is not implemented"
-                        " for this field descriptor with sum factorization on"
-                        " tensor product elements");
+      MFEM_ABORT("quadrature data mapping to field is not implemented for"
+                 " this field descriptor with sum factorization on tensor product elements");
   }
 }

@@ -652,6 +652,16 @@ void forall(func_t f,
 class FDJacobian : public Operator
 {
 public:
+   FDJacobian(const Operator &op, real_t fixed_eps = 0.0) :
+      Operator(op.Height(), op.Width()),
+      op(op),
+      x(op.Width()),
+      fixed_eps(fixed_eps)
+   {
+      f.SetSize(Height());
+      xpev.SetSize(Width());
+   }
+
   FDJacobian(const Operator &op, const Vector &x, real_t fixed_eps = 0.0) :
      Operator(op.Height(), op.Width()),
      op(op),
@@ -671,6 +681,18 @@ public:
                    MPI_COMM_WORLD);
   }

+   void Update(const Vector &x_new)
+   {
+      x = x_new;
+      f.UseDevice(x.UseDevice());
+      xpev.UseDevice(x.UseDevice());
+
+      op.Mult(x, f);
+      const real_t xnorm_local = x.Norml2();
+      MPI_Allreduce(&xnorm_local, &xnorm, 1, MPITypeMap<real_t>::mpi_type, MPI_SUM,
+                    MPI_COMM_WORLD);
+   }
+
   void Mult(const Vector &v, Vector &y) const override
   {
      // See [1] for choice of eps.
@@ -12,6 +12,7 @@
 #include "dgmassinv.hpp"
 #include "bilinearform.hpp"
 #include "dgmassinv_kernels.hpp"
+#include "../general/forall.hpp"

 namespace mfem
 {
@@ -118,6 +119,151 @@ void DGMassInverse::Update()

 DGMassInverse::~DGMassInverse() = default;

+template<int DIM, int D1D, int Q1D>
+void DGMassInverse::DGMassCGIteration(const Vector &b_, Vector &u_) const
+{
+   using namespace internal; // host/device kernel functions
+
+   const int NE = fes.GetNE();
+   const int d1d = m->dofs1D;
+   const int q1d = m->quad1D;
+
+   const int ND = static_cast<int>(pow(d1d, DIM));
+
+   const auto B = m->maps->B.Read();
+   const auto Bt = m->maps->Bt.Read();
+   const auto pa_data = m->pa_data.Read();
+   const auto dinv = diag_inv.Read();
+   auto r = r_.Write();
+   auto d = d_.Write();
+   auto z = z_.Write();
+   auto u = u_.ReadWrite();
+
+   const real_t RELTOL = rel_tol;
+   const real_t ABSTOL = abs_tol;
+   const int MAXIT = max_iter;
+   const bool IT_MODE = iterative_mode;
+   const bool CHANGE_BASIS = (d2q != nullptr);
+
+   // b is the right-hand side (if no change of basis, this just points to the
+   // incoming RHS vector, if we have to change basis, this points to the
+   // internal b2 vector where we put the transformed RHS)
+   const real_t *b;
+   // the following are non-null if we have to change basis
+   real_t *b2 = nullptr; // non-const access to b2
+   const real_t *b_orig = nullptr; // RHS vector in "original" basis
+   const real_t *d2q_B = nullptr; // matrix to transform initial guess
+   const real_t *q2d_B = nullptr; // matrix to transform solution
+   const real_t *q2d_Bt = nullptr; // matrix to transform RHS
+   if (CHANGE_BASIS)
+   {
+      d2q_B = d2q->B.Read();
+      q2d_B = B_.Read();
+      q2d_Bt = Bt_.Read();
+
+      b2 = b2_.Write();
+      b_orig = b_.Read();
+      b = b2;
+   }
+   else
+   {
+      b = b_.Read();
+   }
+
+   static constexpr int NB = Q1D ? Q1D : 1; // block size
+
+   mfem::forall_2D(NE, NB, NB, [=] MFEM_HOST_DEVICE (int e)
+   {
+      // Perform change of basis if needed
+      if (CHANGE_BASIS)
+      {
+         // Transform RHS
+         DGMassBasis<DIM,D1D>(e, NE, q2d_Bt, b_orig, b2, d1d);
+         if (IT_MODE)
+         {
+            // Transform initial guess
+            DGMassBasis<DIM,D1D>(e, NE, d2q_B, u, u, d1d);
+         }
+      }
+
+      const int tid = MFEM_THREAD_ID(x) + NB*MFEM_THREAD_ID(y);
+
+      // Compute first residual
+      if (IT_MODE)
+      {
+         DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, u, r, d1d, q1d);
+         DGMassAxpy(e, NE, ND, 1.0, b, -1.0, r, r); // r = b - r
+      }
+      else
+      {
+         // if not in iterative mode, use zero initial guess
+         const int BX = MFEM_THREAD_SIZE(x);
+         const int BY = MFEM_THREAD_SIZE(y);
+         const int bxy = BX*BY;
+         const auto B = ConstDeviceMatrix(b, ND, NE);
+         auto U = DeviceMatrix(u, ND, NE);
+         auto R = DeviceMatrix(r, ND, NE);
+         for (int i = tid; i < ND; i += bxy)
+         {
+            U(i, e) = 0.0;
+            R(i, e) = B(i, e);
+         }
+         MFEM_SYNC_THREAD;
+      }
+
+      DGMassPreconditioner(e, NE, ND, dinv, r, z);
+      DGMassAxpy(e, NE, ND, 1.0, z, 0.0, z, d); // d = z
+
+      real_t nom = DGMassDot<NB>(e, NE, ND, d, r);
+      if (nom < 0.0) { return; /* Not positive definite */ }
+      real_t r0 = fmax(nom*RELTOL*RELTOL, ABSTOL*ABSTOL);
+      if (nom <= r0) { return; /* Converged */ }
+
+      DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, d, z, d1d, q1d);
+      real_t den = DGMassDot<NB>(e, NE, ND, z, d);
+      if (den <= 0.0)
+      {
+         DGMassDot<NB>(e, NE, ND, d, d);
+         // d2 > 0 => not positive definite
+         if (den == 0.0) { return; }
+      }
+
+      // start iteration
+      int i = 1;
+      while (true)
+      {
+         const real_t alpha = nom/den;
+         DGMassAxpy(e, NE, ND, 1.0, u, alpha, d, u); // u = u + alpha*d
+         DGMassAxpy(e, NE, ND, 1.0, r, -alpha, z, r); // r = r - alpha*A*d
+
+         DGMassPreconditioner(e, NE, ND, dinv, r, z);
+
+         real_t betanom = DGMassDot<NB>(e, NE, ND, r, z);
+         if (betanom < 0.0) { return; /* Not positive definite */ }
+         if (betanom <= r0) { break; /* Converged */ }
+
+         if (++i > MAXIT) { break; }
+
+         const real_t beta = betanom/nom;
+         DGMassAxpy(e, NE, ND, 1.0, z, beta, d, d); // d = z + beta*d
+         DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, d, z, d1d, q1d); // z = A d
+         den = DGMassDot<NB>(e, NE, ND, d, z);
+         if (den <= 0.0)
+         {
+            DGMassDot<NB>(e, NE, ND, d, d);
+            // d2 > 0 => not positive definite
+            if (den == 0.0) { break; }
+         }
+         nom = betanom;
+      }
+
+      if (CHANGE_BASIS)
+      {
+         DGMassBasis<DIM,D1D>(e, NE, q2d_B, u, u, d1d);
+      }
+   });
+}
+
 void DGMassInverse::Mult(const Vector &Mu, Vector &u) const
 {
   // Dispatch to templated version based on dim, d1d, and q1d.
@@ -160,4 +306,23 @@ DGMassInvKernels::DGMassInvKernels()
   k::Specialization<3,6,7>::Add();
 }

+/// @cond Suppress_Doxygen_warnings
+
+template <int DIM, int D1D, int Q1D>
+DGMassInverse::CGKernelType DGMassInverse::CGKernels::Kernel()
+{
+   return &DGMassInverse::DGMassCGIteration<DIM,D1D,Q1D>;
+}
+
+DGMassInverse::CGKernelType DGMassInverse::CGKernels::Fallback(
+   int dim, int, int)
+{
+   if (dim == 1) { return &DGMassInverse::DGMassCGIteration<1>; }
+   else if (dim == 2) { return &DGMassInverse::DGMassCGIteration<2>; }
+   else if (dim == 3) { return &DGMassInverse::DGMassCGIteration<3>; }
+   else { MFEM_ABORT("Unsupported dimension."); }
+}
+
+/// @endcond
+
 } // namespace mfem
@@ -15,7 +15,6 @@
 #include "../linalg/kernels.hpp"
 #include "kernels.hpp"
 #include "integ/bilininteg_mass_kernels.hpp"
-#include "dgmassinv.hpp"

 namespace mfem
 {
@@ -57,7 +56,7 @@ void DGMassApply(const int e,
      }
      else if (DIM == 3)
      {
-         SmemPAMassApply3D_Element<TD1D,TQ1D,NBZ,ACCUM>(e, NE, B, pa_data, x, y);
+         SmemPAMassApply3D_Element<TD1D,TQ1D,ACCUM>(e, NE, B, pa_data, x, y);
      }
      else
      {
@@ -334,170 +333,6 @@ void DGMassBasis(const int e,

 } // namespace internal

-template<int DIM, int D1D, int Q1D>
-void DGMassInverse::DGMassCGIteration(const Vector &b_, Vector &u_) const
-{
-   using namespace internal; // host/device kernel functions
-
-   const int NE = fes.GetNE();
-   const int d1d = m->dofs1D;
-   const int q1d = m->quad1D;
-
-   const int ND = static_cast<int>(pow(d1d, DIM));
-
-   const auto B = m->maps->B.Read();
-   const auto Bt = m->maps->Bt.Read();
-   const auto pa_data = m->pa_data.Read();
-   const auto dinv = diag_inv.Read();
-   auto r = r_.Write();
-   auto d = d_.Write();
-   auto z = z_.Write();
-   auto u = u_.ReadWrite();
-
-   const real_t RELTOL = rel_tol;
-   const real_t ABSTOL = abs_tol;
-   const int MAXIT = max_iter;
-   const bool IT_MODE = iterative_mode;
-   const bool CHANGE_BASIS = (d2q != nullptr);
-
-   // b is the right-hand side (if no change of basis, this just points to the
-   // incoming RHS vector, if we have to change basis, this points to the
-   // internal b2 vector where we put the transformed RHS)
-   const real_t *b;
-   // the following are non-null if we have to change basis
-   real_t *b2 = nullptr; // non-const access to b2
-   const real_t *b_orig = nullptr; // RHS vector in "original" basis
-   const real_t *d2q_B = nullptr; // matrix to transform initial guess
-   const real_t *q2d_B = nullptr; // matrix to transform solution
-   const real_t *q2d_Bt = nullptr; // matrix to transform RHS
-   if (CHANGE_BASIS)
-   {
-      d2q_B = d2q->B.Read();
-      q2d_B = B_.Read();
-      q2d_Bt = Bt_.Read();
-
-      b2 = b2_.Write();
-      b_orig = b_.Read();
-      b = b2;
-   }
-   else
-   {
-      b = b_.Read();
-   }
-
-   static constexpr int NB = Q1D ? Q1D : 1; // block size
-
-   mfem::forall_2D<NB*NB>(NE, NB, NB, [=] MFEM_HOST_DEVICE (int e)
-   {
-      // Perform change of basis if needed
-      if (CHANGE_BASIS)
-      {
-         // Transform RHS
-         DGMassBasis<DIM,D1D>(e, NE, q2d_Bt, b_orig, b2, d1d);
-         if (IT_MODE)
-         {
-            // Transform initial guess
-            DGMassBasis<DIM,D1D>(e, NE, d2q_B, u, u, d1d);
-         }
-      }
-
-      const int tid = MFEM_THREAD_ID(x) + NB*MFEM_THREAD_ID(y);
-
-      // Compute first residual
-      if (IT_MODE)
-      {
-         DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, u, r, d1d, q1d);
-         DGMassAxpy(e, NE, ND, 1.0, b, -1.0, r, r); // r = b - r
-      }
-      else
-      {
-         // if not in iterative mode, use zero initial guess
-         const int BX = MFEM_THREAD_SIZE(x);
-         const int BY = MFEM_THREAD_SIZE(y);
-         const int bxy = BX*BY;
-         const auto B = ConstDeviceMatrix(b, ND, NE);
-         auto U = DeviceMatrix(u, ND, NE);
-         auto R = DeviceMatrix(r, ND, NE);
-         for (int i = tid; i < ND; i += bxy)
-         {
-            U(i, e) = 0.0;
-            R(i, e) = B(i, e);
-         }
-         MFEM_SYNC_THREAD;
-      }
-
-      DGMassPreconditioner(e, NE, ND, dinv, r, z);
-      DGMassAxpy(e, NE, ND, 1.0, z, 0.0, z, d); // d = z
-
-      real_t nom = DGMassDot<NB>(e, NE, ND, d, r);
-      if (nom < 0.0) { return; /* Not positive definite */ }
-      real_t r0 = fmax(nom*RELTOL*RELTOL, ABSTOL*ABSTOL);
-      if (nom <= r0) { return; /* Converged */ }
-
-      DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, d, z, d1d, q1d);
-      real_t den = DGMassDot<NB>(e, NE, ND, z, d);
-      if (den <= 0.0)
-      {
-         DGMassDot<NB>(e, NE, ND, d, d);
-         // d2 > 0 => not positive definite
-         if (den == 0.0) { return; }
-      }
-
-      // start iteration
-      int i = 1;
-      while (true)
-      {
-         const real_t alpha = nom/den;
-         DGMassAxpy(e, NE, ND, 1.0, u, alpha, d, u); // u = u + alpha*d
-         DGMassAxpy(e, NE, ND, 1.0, r, -alpha, z, r); // r = r - alpha*A*d
-
-         DGMassPreconditioner(e, NE, ND, dinv, r, z);
-
-         real_t betanom = DGMassDot<NB>(e, NE, ND, r, z);
-         if (betanom < 0.0) { return; /* Not positive definite */ }
-         if (betanom <= r0) { break; /* Converged */ }
-
-         if (++i > MAXIT) { break; }
-
-         const real_t beta = betanom/nom;
-         DGMassAxpy(e, NE, ND, 1.0, z, beta, d, d); // d = z + beta*d
-         DGMassApply<DIM,D1D,Q1D>(e, NE, B, Bt, pa_data, d, z, d1d, q1d); // z = A d
-         den = DGMassDot<NB>(e, NE, ND, d, z);
-         if (den <= 0.0)
-         {
-            DGMassDot<NB>(e, NE, ND, d, d);
-            // d2 > 0 => not positive definite
-            if (den == 0.0) { break; }
-         }
-         nom = betanom;
-      }
-
-      if (CHANGE_BASIS)
-      {
-         DGMassBasis<DIM,D1D>(e, NE, q2d_B, u, u, d1d);
-      }
-   });
-}
-
-/// @cond Suppress_Doxygen_warnings
-
-template <int DIM, int D1D, int Q1D>
-inline DGMassInverse::CGKernelType DGMassInverse::CGKernels::Kernel()
-{
-   return &DGMassInverse::DGMassCGIteration<DIM,D1D,Q1D>;
-}
-
-inline DGMassInverse::CGKernelType DGMassInverse::CGKernels::Fallback(
-   int dim, int, int)
-{
-   if (dim == 1) { return &DGMassInverse::DGMassCGIteration<1>; }
-   else if (dim == 2) { return &DGMassInverse::DGMassCGIteration<2>; }
-   else if (dim == 3) { return &DGMassInverse::DGMassCGIteration<3>; }
-   else { MFEM_ABORT("Unsupported dimension."); }
-}
-
-/// @endcond
-
 } // namespace mfem

 #endif
@@ -320,8 +320,8 @@ public:
    error estimation procedure where the flux averaging is replaced by a global
    L2 projection (requiring a mass matrix solve).

-    The required BilinearFormIntegrator must implement the method
-    ComputeElementFlux().
+    The required BilinearFormIntegrator must implement the methods
+    ComputeElementFlux() and ComputeFluxEnergy().

    Implemented for the parallel case only.
 */
@@ -357,8 +357,8 @@ protected:

 public:
   /** @brief Construct a new L2ZienkiewiczZhuEstimator object.
-       @param integ    This BilinearFormIntegrator must implement the method
-                       ComputeElementFlux().
+       @param integ    This BilinearFormIntegrator must implement the methods
+                       ComputeElementFlux() and ComputeFluxEnergy().
       @param sol      The solution field whose error is to be estimated.
       @param flux_fes The L2ZienkiewiczZhuEstimator assumes ownership of this
                       FiniteElementSpace and will call its Update() method when
@@ -382,8 +382,8 @@ public:
   { }

   /** @brief Construct a new L2ZienkiewiczZhuEstimator object.
-       @param integ    This BilinearFormIntegrator must implement the method
-                       ComputeElementFlux().
+       @param integ    This BilinearFormIntegrator must implement the methods
+                       ComputeElementFlux() and ComputeFluxEnergy().
       @param sol      The solution field whose error is to be estimated.
       @param flux_fes The L2ZienkiewiczZhuEstimator does NOT assume ownership
                       of this FiniteElementSpace; will call its Update() method
@@ -69,9 +69,9 @@ inline int ToLexOrdering2D(const int face_id, const int size1d, const int i)
 }

 /// @brief Given a face DOF index on a shared face, ordered lexicographically
-/// relative to the element (where the local face is face_id), return the
-/// corresponding face DOF index ordered lexicographically relative to the face
-/// itself.
+/// relative to element the element (where the local face is face_id), and
+/// return the corresponding face DOF index ordered lexicographically relative
+/// to the face itself.
 MFEM_HOST_DEVICE
 inline int PermuteFace2D(const int face_id, const int orientation,
                         const int size1d, const int index)
@@ -231,7 +231,7 @@ void FiniteElement::CalcPhysLaplacian(ElementTransformation &Trans,
   {
      for (int nd = 0; nd < dof; nd++)
      {
-         Laplacian[nd] = hess(nd,0) + hess(nd,3) + hess(nd,5);
+         Laplacian[nd] = hess(nd,0) + hess(nd,4) + hess(nd,5);
      }
   }
   else if (dim == 2)
@@ -268,9 +268,11 @@ void FiniteElement::CalcPhysLinLaplacian(ElementTransformation &Trans,
      scale[0] =   Gij(0,0);
      scale[1] = 2*Gij(0,1);
      scale[2] = 2*Gij(0,2);
-      scale[3] =   Gij(1,1);
-      scale[4] = 2*Gij(1,2);
-      scale[5] =   Gij(2,2);
+
+      scale[3] = 2*Gij(1,2);
+      scale[4] =   Gij(2,2);
+
+      scale[5] =   Gij(1,1);
   }
   else if (dim == 2)
   {
@@ -307,12 +309,12 @@ void  FiniteElement::CalcPhysHessian(ElementTransformation &Trans,
      map[2] = 2;

      map[3] = 1;
-      map[4] = 3;
-      map[5] = 4;
+      map[4] = 5;
+      map[5] = 3;

      map[6] = 2;
-      map[7] = 4;
-      map[8] = 5;
+      map[7] = 3;
+      map[8] = 4;
   }
   else if (dim == 2)
   {
@@ -380,7 +382,11 @@ const DofToQuad &FiniteElement::GetDofToQuad(const IntegrationRule &ir,
   #pragma omp critical (DofToQuad)
 #endif
   {
-      d2q = DofToQuad::SearchArray(dof2quad_array, ir, mode);
+      for (int i = 0; i < dof2quad_array.Size(); i++)
+      {
+         d2q = dof2quad_array[i];
+         if (d2q->IntRule != &ir || d2q->mode != mode) { d2q = nullptr; }
+      }
      if (!d2q)
      {
 #ifdef MFEM_THREAD_SAFE
@@ -655,67 +661,58 @@ void ScalarFiniteElement::ScalarLocalL2Restriction(
 void NodalFiniteElement::CreateLexicographicFullMap(const IntegrationRule &ir)
 const
 {
-   // Get the FULL version of the map. This call contains omp critical region,
-   // so it is done before the critical region below.
-   auto &d2q = GetDofToQuad(ir, DofToQuad::FULL);

 #if defined(MFEM_THREAD_SAFE) && defined(MFEM_USE_OPENMP)
   #pragma omp critical (DofToQuad)
 #endif
   {
-      // Do not run if the new Dof2Quad is already present, e.g. added in a
-      // previous call or added by another omp thread.
-      if (DofToQuad::SearchArray(dof2quad_array, ir,
-                                 DofToQuad::LEXICOGRAPHIC_FULL) == nullptr)
+      // Get the FULL version of the map.
+      auto &d2q = GetDofToQuad(ir, DofToQuad::FULL);
+      //Undo the native ordering which is what FiniteElement::GetDofToQuad returns.
+      auto *d2q_new = new DofToQuad(d2q);
+      d2q_new->mode = DofToQuad::LEXICOGRAPHIC_FULL;
+      const int nqpt = ir.GetNPoints();
+
+      const int b_dim = (range_type == VECTOR) ? dim : 1;
+
+      for (int i = 0; i < nqpt; i++)
      {
-         // Undo the native ordering which is what FiniteElement::GetDofToQuad
-         // returns.
-         auto *d2q_new = new DofToQuad(d2q);
-         d2q_new->mode = DofToQuad::LEXICOGRAPHIC_FULL;
-         const int nqpt = ir.GetNPoints();
-
-         const int b_dim = (range_type == VECTOR) ? dim : 1;
-
-         for (int i = 0; i < nqpt; i++)
+         for (int d = 0; d < b_dim; d++)
         {
-            for (int d = 0; d < b_dim; d++)
+            for (int j = 0; j < dof; j++)
            {
-               for (int j = 0; j < dof; j++)
-               {
-                  const double val = d2q.B[i + nqpt*(d+b_dim*lex_ordering[j])];
-                  d2q_new->B[i+nqpt*(d+b_dim*j)] = val;
-                  d2q_new->Bt[j+dof*(i+nqpt*d)] = val;
-               }
+               const double val = d2q.B[i + nqpt*(d+b_dim*lex_ordering[j])];
+               d2q_new->B[i+nqpt*(d+b_dim*j)] = val;
+               d2q_new->Bt[j+dof*(i+nqpt*d)] = val;
            }
         }
-
-         const int g_dim = [this]()
-         {
-            switch (deriv_type)
-            {
-               case GRAD: return dim;
-               case DIV: return 1;
-               case CURL: return cdim;
-               default: return 0;
-            }
-         }();
-
-         for (int i = 0; i < nqpt; i++)
-         {
-            for (int d = 0; d < g_dim; d++)
-            {
-               for (int j = 0; j < dof; j++)
-               {
-                  const double val = d2q.G[i + nqpt*(d+g_dim*lex_ordering[j])];
-                  d2q_new->G[i+nqpt*(d+g_dim*j)] = val;
-                  d2q_new->Gt[j+dof*(i+nqpt*d)] = val;
-               }
-            }
-         }
-
-         dof2quad_array.Append(d2q_new);
      }

+      const int g_dim = [this]()
+      {
+         switch (deriv_type)
+         {
+            case GRAD: return dim;
+            case DIV: return 1;
+            case CURL: return cdim;
+            default: return 0;
+         }
+      }();
+
+      for (int i = 0; i < nqpt; i++)
+      {
+         for (int d = 0; d < g_dim; d++)
+         {
+            for (int j = 0; j < dof; j++)
+            {
+               const double val = d2q.G[i + nqpt*(d+g_dim*lex_ordering[j])];
+               d2q_new->G[i+nqpt*(d+g_dim*j)] = val;
+               d2q_new->Gt[j+dof*(i+nqpt*d)] = val;
+            }
+         }
+      }
+
+      dof2quad_array.Append(d2q_new);
   }
 }

@@ -727,7 +724,13 @@ const DofToQuad &NodalFiniteElement::GetDofToQuad(const IntegrationRule &ir,
   #pragma omp critical (DofToQuad)
 #endif
   {
-      d2q = DofToQuad::SearchArray(dof2quad_array, ir, mode);
+      //Should make this loop a function of FiniteElement
+      for (int i = 0; i < dof2quad_array.Size(); i++)
+      {
+         d2q = dof2quad_array[i];
+         if (d2q->IntRule == &ir && d2q->mode == mode) { break; }
+         d2q = nullptr;
+      }
   }
   if (d2q) { return *d2q; }
   if (mode != DofToQuad::LEXICOGRAPHIC_FULL)
@@ -1044,50 +1047,9 @@ void VectorFiniteElement::SetDerivMembers()
   switch (map_type)
   {
      case H_DIV:
-         switch (dim)
-         {
-            case 3: // div: 3D H_DIV -> 3D INTEGRAL
-               deriv_type = DIV;
-               deriv_range_type = SCALAR;
-               deriv_map_type = INTEGRAL;
-               break;
-            case 2: // div: 2D H_DIV -> 2D INTEGRAL
-               deriv_type = DIV;
-               deriv_range_type = SCALAR;
-               deriv_map_type = INTEGRAL;
-               break;
-            default:
-               MFEM_ABORT("Invalid dimension, Dim = " << dim);
-         }
-         break;
-      case H_DIV_R2D:
-         switch (dim)
-         {
-            case 2: // div: 2D H_DIV_R2D -> 2D INTEGRAL
-               deriv_type = DIV;
-               deriv_range_type = SCALAR;
-               deriv_map_type = INTEGRAL;
-               break;
-            case 1: // div: 1D H_DIV_R2D -> 1D INTEGRAL
-               deriv_type = DIV;
-               deriv_range_type = SCALAR;
-               deriv_map_type = INTEGRAL;
-               break;
-            default:
-               MFEM_ABORT("Invalid dimension, Dim = " << dim);
-         }
-         break;
-      case H_DIV_R1D:
-         switch (dim)
-         {
-            case 1: // div: 1D H_DIV_R1D -> 1D INTEGRAL
-               deriv_type = DIV;
-               deriv_range_type = SCALAR;
-               deriv_map_type = INTEGRAL;
-               break;
-            default:
-               MFEM_ABORT("Invalid dimension, Dim = " << dim);
-         }
+         deriv_type = DIV;
+         deriv_range_type = SCALAR;
+         deriv_map_type = INTEGRAL;
         break;
      case H_CURL:
         switch (dim)
@@ -1105,49 +1067,13 @@ void VectorFiniteElement::SetDerivMembers()
               break;
            case 1:
               deriv_type = NONE;
-               deriv_range_type = UNKNOWN_RANGE_TYPE;
-               deriv_map_type = UNKNOWN_MAP_TYPE;
+               deriv_range_type = SCALAR;
+               deriv_map_type = INTEGRAL;
               break;
            default:
               MFEM_ABORT("Invalid dimension, Dim = " << dim);
         }
         break;
-      case H_CURL_R2D:
-         switch (dim)
-         {
-            case 2:
-               // curl: 2D H_CURL_R2D -> H_DIV_R2D
-               deriv_type = CURL;
-               deriv_range_type = VECTOR;
-               deriv_map_type = H_DIV_R2D;
-               break;
-            case 1:
-               // curl: 1D H_CURL_R2D -> H_DIV_R2D
-               deriv_type = CURL;
-               deriv_range_type = VECTOR;
-               deriv_map_type = H_DIV_R2D;
-               break;
-            default:
-               MFEM_ABORT("Invalid dimension, Dim = " << dim);
-         }
-         break;
-      case H_CURL_R1D:
-         switch (dim)
-         {
-            case 1:
-               // curl: 1D H_CURL_R1D -> H_DIV_R1D
-               deriv_type = CURL;
-               deriv_range_type = VECTOR;
-               deriv_map_type = H_DIV_R1D;
-               break;
-            case 0:
-               deriv_type = NONE;
-               deriv_range_type = UNKNOWN_RANGE_TYPE;
-               deriv_map_type = UNKNOWN_MAP_TYPE;
-            default:
-               MFEM_ABORT("Invalid dimension, Dim = " << dim);
-         }
-         break;
      default:
         MFEM_ABORT("Invalid MapType = " << map_type);
   }
@@ -2705,7 +2631,15 @@ const DofToQuad &TensorBasisElement::GetTensorDofToQuad(
   #pragma omp critical (DofToQuad)
 #endif
   {
-      d2q = DofToQuad::SearchArray(dof2quad_array, ir, mode);
+      for (int i = 0; i < dof2quad_array.Size(); i++)
+      {
+         auto* d2q_ = dof2quad_array[i];
+         if (d2q_->IntRule == &ir && d2q_->mode == mode)
+         {
+            d2q = d2q_;
+            break;
+         }
+      }
      if (!d2q)
      {
         d2q = new DofToQuad;
@@ -44,7 +44,7 @@ public:
      NumBasisTypes   = 9   /**< Keep track of maximum types to prevent
                                 hard-coding */
   };
-   /** @brief If the input does not represent a valid BasisType, abort with an
+   /** @brief If the input does not represents a valid BasisType, abort with an
       error; otherwise return the input. */
   static int Check(int b_type)
   {
@@ -52,7 +52,7 @@ public:
                  "unknown BasisType: " << b_type);
      return b_type;
   }
-   /** @brief If the input does not represent a valid nodal BasisType, abort
+   /** @brief If the input does not represents a valid nodal BasisType, abort
       with an error; otherwise return the input. */
   static int CheckNodal(int b_type)
   {
@@ -222,12 +222,6 @@ public:

   /// Returns absolute value of the maps
   DofToQuad Abs() const;
-
-   /// Auxiliary function for searching DofToQuad arrays.
-   static inline DofToQuad *SearchArray(
-      const Array<DofToQuad*> &dof2quad_array,
-      const IntegrationRule &ir,
-      DofToQuad::Mode mode);
 };

 /// Describes the function space on each element
@@ -295,20 +289,10 @@ public:
                          $ u(x) = (1/w) \hat u(\hat x) $ */
      H_DIV,     /**< For vector fields; preserves surface integrals of the
                          normal component $ u(x) = (J/w) \hat u(\hat x) $ */
-      H_CURL,    /**< For vector fields; preserves line integrals of the
+      H_CURL     /**< For vector fields; preserves line integrals of the
                          tangential component
                          $ u(x) = J^{-t} \hat u(\hat x) $ (square J),
                          $ u(x) = J(J^t J)^{-1} \hat u(\hat x) $ (general J) */
-      H_DIV_R2D, /**< For 3-component vector fields in 2D; equivalent to a
-                          direct sum of an H_DIV basis and an INTEGRAL basis */
-      H_CURL_R2D,/**< For 3-component vector fields in 2D; equivalent to a
-                          direct sum of an H_CURL basis and a VALUE basis */
-      H_DIV_R1D, /**< For 3-component vector fields in 1D; equivalent to a
-                          direct sum of a VALUE basis and a pair of INTEGRAL
-                          bases */
-      H_CURL_R1D /**< For 3-component vector fields in 1D; equivalent to a
-                          direct sum of an INTEGRAL basis and a pair of VALUE
-                          bases */
   };

   /** @brief Enumeration for DerivType: defines which derivative method
@@ -340,28 +324,12 @@ public:
   int GetDim() const { return dim; }

   /** @brief Returns the vector dimension for vector-valued finite elements,
-       which is also the dimension of the interpolation operation and the
-       width of the DenseMatrix argument in
-       CalcVShape(const IntegrationPoint &ip, DenseMatrix &shape). */
+       which is also the dimension of the interpolation operation. */
   int GetRangeDim() const { return vdim; }

-   /** @brief Returns the vector dimension, in physical space, for
-       vector-valued finite elements, which is also the width of the
-       DenseMatrix argument in
-       CalcPhysVShape(ElementTransformation &Trans, DenseMatrix &shape). */
-   virtual int GetPhysRangeDim(int /* space_dim */) const { return vdim; }
-
-   /** Returns the dimension of the curl for vector-valued finite elements,
-       which is also the width of the DenseMatrix argument in
-       CalcCurlShape(const IntegrationPoint &ip, DenseMatrix &curl_shape). */
+   /// Returns the dimension of the curl for vector-valued finite elements.
   int GetCurlDim() const { return cdim; }

-   /** Returns the dimension, in physical space, of the curl for vector-valued
-       finite elements, which is also the width of the DenseMatrix argument in
-       CalcPhysCurlShape(ElementTransformation &Trans, DenseMatrix &curl_shape).
-   */
-   virtual int GetPhysCurlDim(int /* space_dim */) const { return cdim; }
-
   /// Returns the Geometry::Type of the reference element.
   Geometry::Type GetGeomType() const { return geom_type; }

@@ -439,7 +407,6 @@ public:
   /** Each row of the result DenseMatrix @a Hessian contains upper triangular
       part of the Hessian of one shape function.
       The order in 2D is {u_xx, u_xy, u_yy}.
-       The order in 3D is {u_xx, u_xy, u_xz, u_yy, u_yz, u_zz}.
       The size (#dof x (#dim (#dim+1)/2) of @a Hessian must be set in advance.*/
   virtual void CalcHessian(const IntegrationPoint &ip,
                            DenseMatrix &Hessian) const;
@@ -1016,8 +983,6 @@ protected:
 public:
   VectorFiniteElement(int D, Geometry::Type G, int Do, int O, int M,
                       int F = FunctionSpace::Pk);
-
-   int GetPhysRangeDim(int space_dim) const override { return space_dim; }
 };

 /// @brief Class for computing 1D special polynomials and their associated basis
@@ -1155,7 +1120,7 @@ public:
      return GetPoints(p, btype, on_device);
   }

-   /// Get coordinates of a closed (GaussLobatto) set of points if degree @a p
+   /// Get coordinates of a closed (GaussLegendre) set of points if degree @a p
   const real_t *ClosedPoints(const int p,
                              const int btype = BasisType::GaussLobatto,
                              bool on_device = false)
@@ -1411,21 +1376,6 @@ public:
 void InvertLinearTrans(ElementTransformation &trans,
                       const IntegrationPoint &pt, Vector &x);

-
-// static inline method
-inline DofToQuad *DofToQuad::SearchArray(
-   const Array<DofToQuad*> &dof2quad_array,
-   const IntegrationRule &ir,
-   DofToQuad::Mode mode)
-{
-   for (int i = 0; i < dof2quad_array.Size(); i++)
-   {
-      DofToQuad *d2q = dof2quad_array[i];
-      if (d2q->IntRule == &ir && d2q->mode == mode) { return d2q; }
-   }
-   return nullptr;
-}
-
 } // namespace mfem

 #endif
@@ -60,12 +60,6 @@ void Linear1DFiniteElement::CalcDShape(const IntegrationPoint &ip,
   dshape(1,0) =  1.;
 }

-void Linear1DFiniteElement::CalcHessian(const IntegrationPoint &ip,
-                                        DenseMatrix &h) const
-{
-   h = 0.0;
-}
-
 Linear2DFiniteElement::Linear2DFiniteElement()
   : NodalFiniteElement(2, Geometry::TRIANGLE, 3, 1)
 {
@@ -93,11 +87,6 @@ void Linear2DFiniteElement::CalcDShape(const IntegrationPoint &ip,
   dshape(2,0) =  0.; dshape(2,1) =  1.;
 }

-void Linear2DFiniteElement::CalcHessian(const IntegrationPoint &ip,
-                                        DenseMatrix &h) const
-{
-   h = 0.0;
-}

 BiLinear2DFiniteElement::BiLinear2DFiniteElement()
   : NodalFiniteElement(2, Geometry::SQUARE, 4, 1, FunctionSpace::Qk)
@@ -1267,12 +1256,6 @@ void Linear3DFiniteElement::CalcDShape(const IntegrationPoint &ip,
   }
 }

-void Linear3DFiniteElement::CalcHessian(const IntegrationPoint &ip,
-                                        DenseMatrix &h) const
-{
-   h = 0.0;
-}
-
 void Linear3DFiniteElement::GetFaceDofs (int face, int **dofs, int *ndofs)
 const
 {
@@ -1649,37 +1632,6 @@ void TriLinear3DFiniteElement::CalcDShape(const IntegrationPoint &ip,
   dshape(7,2) =   ox *  y;
 }

-void TriLinear3DFiniteElement::CalcHessian(const IntegrationPoint &ip,
-                                           DenseMatrix &h) const
-{
-   real_t x = ip.x, y = ip.y, z = ip.z;
-   real_t ox = 1.-x, oy = 1.-y, oz = 1.-z;
-
-   h(0,0) = 0.;   h(0,1) =  oz;   h(0,2) = oy;
-   h(0,3) = 0.;   h(0,4) =  ox;   h(0,5) = 0.;
-
-   h(1,0) = 0.;   h(1,1) = -oz;   h(1,2) = -oy;
-   h(1,3) = 0.;   h(1,4) =  x;    h(1,5) = 0.;
-
-   h(2,0) = 0.;   h(2,1) =  oz;   h(2,2) = -y;
-   h(2,3) = 0.;   h(2,4) =  -x;   h(2,5) = 0.;
-
-   h(3,0) = 0.;   h(3,1) = -oz;   h(3,2) = y;
-   h(3,3) = 0.;   h(3,4) = -ox;   h(3,5) = 0.;
-
-   h(4,0) = 0.;   h(4,1) =  z;    h(4,2) = -oy;
-   h(4,3) = 0.;   h(4,4) = -ox;   h(4,5) = 0.;
-
-   h(5,0) = 0.;   h(5,1) = -z;    h(5,2) = oy;
-   h(5,3) = 0.;   h(5,4) = -x;    h(5,5) = 0.;
-
-   h(6,0) = 0.;   h(6,1) =  z;    h(6,2) = y;
-   h(6,3) = 0.;   h(6,4) =  x;    h(6,5) = 0.;
-
-   h(7,0) = 0.;   h(7,1) = -z;    h(7,2) = -y;
-   h(7,3) = 0.;   h(7,4) = ox;    h(7,5) = 0.;
-}
-

 P0SegmentFiniteElement::P0SegmentFiniteElement(int Ord)
   : NodalFiniteElement(1, Geometry::SEGMENT, 1, Ord)   // default Ord = 0
@@ -50,8 +50,6 @@ public:
       contains the derivative of one shape function */
   void CalcDShape(const IntegrationPoint &ip,
                   DenseMatrix &dshape) const override;
-   void CalcHessian(const IntegrationPoint &ip,
-                    DenseMatrix &h) const override;
 };

 /// A 2D linear element on triangle with nodes at the vertices of the triangle
@@ -72,8 +70,6 @@ public:
       so that each row contains the derivatives of one shape function */
   void CalcDShape(const IntegrationPoint &ip,
                   DenseMatrix &dshape) const override;
-   void CalcHessian(const IntegrationPoint &ip,
-                    DenseMatrix &h) const override;
   void ProjectDelta(int vertex, Vector &dofs) const override
   { dofs = 0.0; dofs(vertex) = 1.0; }
 };
@@ -408,9 +404,6 @@ public:
   void CalcDShape(const IntegrationPoint &ip,
                   DenseMatrix &dshape) const override;

-   void CalcHessian(const IntegrationPoint &ip,
-                    DenseMatrix &h) const override;
-
   void ProjectDelta(int vertex, Vector &dofs) const override
   { dofs = 0.0; dofs(vertex) = 1.0; }

@@ -452,8 +445,7 @@ public:
       so that each row contains the derivatives of one shape function */
   void CalcDShape(const IntegrationPoint &ip,
                   DenseMatrix &dshape) const override;
-   void CalcHessian(const IntegrationPoint &ip,
-                    DenseMatrix &h) const override;
+
   void ProjectDelta(int vertex, Vector &dofs) const override
   { dofs = 0.0; dofs(vertex) = 1.0; }
 };
@@ -589,7 +589,7 @@ void H1_TriangleElement::CalcHessian(const IntegrationPoint &ip,
   Vector   shape_x(p + 1),   shape_y(p + 1),   shape_l(p + 1);
   Vector  dshape_x(p + 1),  dshape_y(p + 1),  dshape_l(p + 1);
   Vector ddshape_x(p + 1), ddshape_y(p + 1), ddshape_l(p + 1);
-   DenseMatrix ddu(dof, (dim*(dim+1))/2);
+   DenseMatrix ddu(dof, dim);
 #endif

   poly1d.CalcBasis(p, ip.x, shape_x, dshape_x, ddshape_x);
@@ -2531,7 +2531,7 @@ void ND_FuentesPyramidElement::calcCurlBasis(const int p,

 ND_R1D_PointElement::ND_R1D_PointElement(int p)
   : VectorFiniteElement(1, Geometry::POINT, 2, p,
-                         H_CURL_R1D, FunctionSpace::Pk)
+                         H_CURL, FunctionSpace::Pk)
 {
   // VectorFiniteElement::SetDerivMembers doesn't support 0D H_CURL elements
   // so we mimic a 1D element and then correct the dimension here.
@@ -2562,7 +2562,7 @@ ND_R1D_SegmentElement::ND_R1D_SegmentElement(const int p,
                                             const int cb_type,
                                             const int ob_type)
   : VectorFiniteElement(1, Geometry::SEGMENT, 3 * p + 2, p,
-                         H_CURL_R1D, FunctionSpace::Pk),
+                         H_CURL, FunctionSpace::Pk),
     dof2tk(dof),
     cbasis1d(poly1d.GetBasis(p, VerifyClosed(cb_type))),
     obasis1d(poly1d.GetBasis(p - 1, VerifyOpen(ob_type)))
@@ -2839,7 +2839,7 @@ ND_R2D_SegmentElement::ND_R2D_SegmentElement(const int p,
                                             const int cb_type,
                                             const int ob_type)
   : VectorFiniteElement(1, Geometry::SEGMENT, 2 * p + 1, p,
-                         H_CURL_R2D, FunctionSpace::Pk),
+                         H_CURL, FunctionSpace::Pk),
     dof2tk(dof),
     cbasis1d(poly1d.GetBasis(p, VerifyClosed(cb_type))),
     obasis1d(poly1d.GetBasis(p - 1, VerifyOpen(ob_type)))
@@ -3023,7 +3023,7 @@ void ND_R2D_SegmentElement::Project(VectorCoefficient &vc,
 ND_R2D_FiniteElement::ND_R2D_FiniteElement(int p, Geometry::Type G, int Do,
                                           const real_t *tk_fe)
   : VectorFiniteElement(2, G, Do, p,
-                         H_CURL_R2D, FunctionSpace::Pk),
+                         H_CURL, FunctionSpace::Pk),
     tk(tk_fe),
     dof_map(dof),
     dof2tk(dof)
@@ -663,9 +663,6 @@ public:
                         const int cb_type = BasisType::GaussLobatto,
                         const int ob_type = BasisType::GaussLegendre);

-   int GetPhysRangeDim(int space_dim) const override { return 2; }
-   int GetPhysCurlDim(int space_dim) const override { return 1; }
-
   void CalcVShape(const IntegrationPoint &ip,
                   DenseMatrix &shape) const override;

@@ -708,9 +705,6 @@ private:
                           DenseMatrix &I) const;

 public:
-   int GetPhysRangeDim(int space_dim) const override { return 3; }
-   int GetPhysCurlDim(int space_dim) const override { return 3; }
-
   using FiniteElement::CalcVShape;
   using FiniteElement::CalcPhysCurlShape;

@@ -84,46 +84,6 @@ void NURBS1DFiniteElement::CalcHessian (const IntegrationPoint &ip,
   add(1.0, hess, (-d2sum + 2*dsum*dsum*sum)*sum*sum, shape_x, hess);
 }

-void NURBS1DFiniteElement::Project(Coefficient &coeff,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   IntegrationPoint ip;
-
-   for (int i = 0; i <= order; i++)
-   {
-      real_t kx = kv[0]->GetBotella(ijk[0] + i);
-      if (!kv[0]->inSpan(kx, ijk[0]+order)) { continue; }
-      ip.x = kv[0]->GetRefPoint(kx, ijk[0]+order);
-
-      Trans.SetIntPoint(&ip);
-      dofs(i) = coeff.Eval(Trans, ip);
-   }
-}
-
-void NURBS1DFiniteElement::Project(VectorCoefficient &vc,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == vc.GetVDim()*dof, "");
-   Vector x(vc.GetVDim());
-   IntegrationPoint ip;
-
-   for (int i = 0; i <= order; i++)
-   {
-      real_t kx = kv[0]->GetBotella(ijk[0] + i);
-      if (!kv[0]->inSpan(kx, ijk[0]+order)) { continue; }
-      ip.x = kv[0]->GetRefPoint(kx, ijk[0]+order);
-
-      Trans.SetIntPoint(&ip);
-      vc.Eval(x, Trans, ip);
-      for (int j = 0; j < x.Size(); j++)
-      {
-         dofs(dof*j+i) = x(j);
-      }
-   }
-}
-

 void NURBS2DFiniteElement::SetOrder() const
 {
@@ -255,63 +215,6 @@ void NURBS2DFiniteElement::CalcHessian (const IntegrationPoint &ip,
   }
 }

-void NURBS2DFiniteElement::Project(Coefficient &coeff,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   IntegrationPoint ip;
-   for (int o = 0, j = 0; j <= orders[1]; j++)
-   {
-      real_t ky = kv[1]->GetBotella(ijk[1] + j);
-      if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-      {
-         o += orders[0] + 1;
-         continue;
-      }
-      ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-      for (int i = 0; i <= orders[0]; i++, o++)
-      {
-         real_t kx = kv[0]->GetBotella(ijk[0] + i);
-         if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-         ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-         Trans.SetIntPoint(&ip);
-         dofs(o) = coeff.Eval(Trans, ip);
-      }
-   }
-}
-
-void NURBS2DFiniteElement::Project(VectorCoefficient &vc,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == vc.GetVDim()*dof, "");
-   Vector x(vc.GetVDim());
-   IntegrationPoint ip;
-   for (int o = 0, j = 0; j <= orders[1]; j++)
-   {
-      real_t ky = kv[1]->GetBotella(ijk[1] + j);
-      if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-      {
-         o += orders[0] + 1;
-         continue;
-      }
-      ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-      for (int i = 0; i <= orders[0]; i++, o++)
-      {
-         real_t kx = kv[0]->GetBotella(ijk[0] + i);
-         if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-         ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-         Trans.SetIntPoint(&ip);
-         vc.Eval(x, Trans, ip);
-         for (int v = 0; v < x.Size(); v++)
-         {
-            dofs(dof*v+o) = x(v);
-         }
-      }
-   }
-}

 void NURBS3DFiniteElement::SetOrder() const
 {
@@ -445,10 +348,11 @@ void NURBS3DFiniteElement::CalcHessian (const IntegrationPoint &ip,
            d2sum[0] += ( hessian(o,0) = d2sx*sy*sz*weights(o) );
            d2sum[1] += ( hessian(o,1) = dsx*dsy*sz*weights(o) );
            d2sum[2] += ( hessian(o,2) = dsx*sy*dsz*weights(o) );
-            d2sum[3] += ( hessian(o,3) = sx*d2sy*sz*weights(o) );
-            d2sum[4] += ( hessian(o,4) = sx*dsy*dsz*weights(o) );
-            d2sum[5] += ( hessian(o,5) = sx*sy*d2sz*weights(o) );

+            d2sum[3] += ( hessian(o,3) = sx*dsy*dsz*weights(o) );
+
+            d2sum[4] += ( hessian(o,4) = sx*sy*d2sz*weights(o) );
+            d2sum[5] += ( hessian(o,5) = sx*d2sy*sz*weights(o) );
         }
      }
   }
@@ -497,85 +401,6 @@ void NURBS3DFiniteElement::CalcHessian (const IntegrationPoint &ip,
   }
 }

-void NURBS3DFiniteElement::Project(Coefficient &coeff,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   IntegrationPoint ip;
-
-   for (int o = 0, k = 0; k <= orders[2]; k++)
-   {
-      real_t kz = kv[2]->GetBotella(ijk[2] + k);
-      if (!kv[2]->inSpan(kz, ijk[2]+orders[2]))
-      {
-         o += (orders[0] + 1)*(orders[1] + 1);
-         continue;
-      }
-      ip.z = kv[2]->GetRefPoint(kz, ijk[2]+orders[2]);
-      for (int j = 0; j <= orders[1]; j++)
-      {
-         real_t ky = kv[1]->GetBotella(ijk[1] + j);
-         if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-         {
-            o += orders[0] + 1;
-            continue;
-         }
-         ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-         for (int i = 0; i <= orders[0]; i++, o++)
-         {
-            real_t kx = kv[0]->GetBotella(ijk[0] + i);
-            if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-            ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-            Trans.SetIntPoint(&ip);
-            dofs(o) = coeff.Eval(Trans, ip);
-         }
-      }
-   }
-}
-
-void NURBS3DFiniteElement::Project(VectorCoefficient &vc,
-                                   ElementTransformation &Trans,
-                                   Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == vc.GetVDim()*dof, "");
-   Vector x(vc.GetVDim());
-   IntegrationPoint ip;
-
-   for (int o = 0, k = 0; k <= orders[2]; k++)
-   {
-      real_t kz = kv[2]->GetBotella(ijk[2] + k);
-      if (!kv[2]->inSpan(kz, ijk[2]+orders[2]))
-      {
-         o += (orders[0] + 1)*(orders[1] + 1);
-         continue;
-      }
-      ip.z = kv[2]->GetRefPoint(kz, ijk[2]+orders[2]);
-      for (int j = 0; j <= orders[1]; j++)
-      {
-         real_t ky = kv[1]->GetBotella(ijk[1] + j);
-         if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-         {
-            o += orders[0] + 1;
-            continue;
-         }
-         ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-         for (int i = 0; i <= orders[0]; i++, o++)
-         {
-            real_t kx = kv[0]->GetBotella(ijk[0] + i);
-            if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-            ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-            for (int v = 0; v < x.Size(); v++)
-            {
-               dofs(dof*v+o) = x(v);
-            }
-         }
-      }
-   }
-}

 void NURBS_HDiv2DFiniteElement::SetOrder() const
 {
@@ -692,63 +517,6 @@ void NURBS_HDiv2DFiniteElement::CalcDivShape(const IntegrationPoint &ip,
   }
 }

-void NURBS_HDiv2DFiniteElement::Project(VectorCoefficient &vc,
-                                        ElementTransformation &Trans,
-                                        Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == dof, "");
-   MFEM_ASSERT(vc.GetVDim() == 2, "");
-   Vector x(2), mx(2);
-   IntegrationPoint ip;
-   int o = 0;
-
-   for (int j = 0; j <= orders[1]; j++)
-   {
-      real_t ky = kv[1]->GetBotella(ijk[1] + j);
-      if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-      {
-         o += orders[0] + 2;
-         continue;
-      }
-      ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-      for (int i = 0; i <= orders[0]+1; i++, o++)
-      {
-         real_t kx = kv1[0]->GetBotella(ijk[0] + i);
-         if (!kv1[0]->inSpan(kx, ijk[0]+orders[0]+1)) { continue; }
-         ip.x = kv1[0]->GetRefPoint(kx, ijk[0]+orders[0]+1);
-
-         Trans.SetIntPoint(&ip);
-         vc.Eval(x, Trans, ip);
-
-         Trans.AdjugateJacobian().Mult(x,mx);
-         dofs(o) = mx(0);
-      }
-   }
-
-   for (int j = 0; j <= orders[1]+1; j++)
-   {
-      real_t ky = kv1[1]->GetBotella(ijk[1] + j);
-      if (!kv1[1]->inSpan(ky, ijk[1]+orders[1]+1))
-      {
-         o += orders[0] + 1;
-         continue;
-      }
-      ip.y = kv1[1]->GetRefPoint(ky, ijk[1]+orders[1]+1);
-      for (int i = 0; i <= orders[0]; i++, o++)
-      {
-         real_t kx = kv[0]->GetBotella(ijk[0] + i);
-         if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-         ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-         Trans.SetIntPoint(&ip);
-         vc.Eval(x, Trans, ip);
-
-         Trans.AdjugateJacobian().Mult(x,mx);
-         dofs(o) = mx(1);
-      }
-   }
-}
-
 NURBS_HDiv2DFiniteElement::~NURBS_HDiv2DFiniteElement()
 {
   if (kv1[0]) { delete kv1[0]; }
@@ -928,120 +696,6 @@ void NURBS_HDiv3DFiniteElement::CalcDivShape(const IntegrationPoint &ip,
   }
 }

-
-void NURBS_HDiv3DFiniteElement::Project(VectorCoefficient &vc,
-                                        ElementTransformation &Trans,
-                                        Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == dof, "");
-   MFEM_ASSERT(vc.GetVDim() == 3, "");
-   Vector x(2), mx(3);
-   IntegrationPoint ip;
-
-   int o = 0;
-
-   for (int k = 0; k <= orders[2]; k++)
-   {
-      real_t kz = kv[2]->GetBotella(ijk[2] + k);
-      if (!kv[2]->inSpan(kz, ijk[2]+orders[2]))
-      {
-         o += (orders[0] + 2)*(orders[1] + 1);
-         continue;
-      }
-      ip.z = kv[2]->GetRefPoint(kz, ijk[2]+orders[2]);
-      for (int j = 0; j <= orders[1]; j++)
-      {
-         real_t ky = kv[1]->GetBotella(ijk[1] + j);
-         if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-         {
-            o += orders[0] + 2;
-            continue;
-         }
-         ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-         for (int i = 0; i <= orders[0]+1; i++, o++)
-         {
-            real_t kx = kv1[0]->GetBotella(ijk[0] + i);
-            if (!kv1[0]->inSpan(kx, ijk[0]+orders[0]+1)) { continue; }
-            ip.x = kv1[0]->GetRefPoint(kx, ijk[0]+orders[0]+1);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.AdjugateJacobian().Mult(x,mx);
-            dofs(o) = mx(0);
-         }
-      }
-   }
-
-   for (int k = 0; k <= orders[2]; k++)
-   {
-      real_t kz = kv[2]->GetBotella(ijk[2] + k);
-      if (!kv[2]->inSpan(kz, ijk[2]+orders[2]))
-      {
-         o += (orders[0] + 1)*(orders[1] + 2);
-         continue;
-      }
-      ip.z = kv[2]->GetRefPoint(kz, ijk[2]+orders[2]);
-      for (int j = 0; j <= orders[1]+1; j++)
-      {
-         real_t ky = kv1[1]->GetBotella(ijk[1] + j);
-         if (!kv1[1]->inSpan(ky, ijk[1]+orders[1]+1))
-         {
-            o += orders[0] + 1;
-            continue;
-         }
-         ip.y = kv1[1]->GetRefPoint(ky, ijk[1]+orders[1]+1);
-         for (int i = 0; i <= orders[0]; i++, o++)
-         {
-            real_t kx = kv[0]->GetBotella(ijk[0] + i);
-            if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-            ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.AdjugateJacobian().Mult(x,mx);
-            dofs(o) = mx(1);
-         }
-      }
-   }
-
-   for (int k = 0; k <= orders[2]+1; k++)
-   {
-      real_t kz = kv1[2]->GetBotella(ijk[2] + k);
-      if (!kv1[2]->inSpan(kz, ijk[2]+orders[2]+1))
-      {
-         o += (orders[0] + 1)*(orders[1] + 1);
-         continue;
-      }
-      ip.z = kv1[2]->GetRefPoint(kz, ijk[2]+orders[2]+1);
-      for (int j = 0; j <= orders[1]; j++)
-      {
-         real_t ky = kv[1]->GetBotella(ijk[1] + j);
-         if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-         {
-            o += orders[0] + 1;
-            continue;
-         }
-         ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-         for (int i = 0; i <= orders[0]; i++, o++)
-         {
-            real_t kx = kv[0]->GetBotella(ijk[0] + i);
-            if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-            ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.AdjugateJacobian().Mult(x,mx);
-            dofs(o) = mx(2);
-         }
-      }
-   }
-
-}
-
-
 NURBS_HDiv3DFiniteElement::~NURBS_HDiv3DFiniteElement()
 {
   if (kv1[0]) { delete kv1[0]; }
@@ -1163,68 +817,13 @@ void NURBS_HCurl2DFiniteElement::CalcCurlShape(const IntegrationPoint &ip,
   }
 }

-void NURBS_HCurl2DFiniteElement::Project(VectorCoefficient &vc,
-                                         ElementTransformation &Trans,
-                                         Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == dof, "");
-   MFEM_ASSERT(vc.GetVDim() == 2, "");
-   Vector x(2), xm(2);
-   IntegrationPoint ip;
-   int i, j, o;
-   for (o = 0, j = 0; j <= orders[1]+1; j++)
-   {
-      real_t ky = kv1[1]->GetBotella(ijk[1] + j);
-      if (!kv1[1]->inSpan(ky, ijk[1]+orders[1]+1))
-      {
-         o += orders[0] + 1;
-         continue;
-      }
-      ip.y = kv1[1]->GetRefPoint(ky, ijk[1]+orders[1]+1);
-      for (i = 0; i <= orders[0]; i++, o++)
-      {
-         real_t kx = kv[0]->GetBotella(ijk[0] + i);
-         if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-         ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-         Trans.SetIntPoint(&ip);
-         vc.Eval(x, Trans, ip);
-
-         Trans.Jacobian().MultTranspose(x,xm);
-         dofs(o) = xm(0);
-      }
-   }
-
-   for (j = 0; j <= orders[1]; j++)
-   {
-      real_t ky = kv[1]->GetBotella(ijk[1] + j);
-      if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-      {
-         o += orders[0] + 2;
-         continue;
-      }
-      ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-      for (i = 0; i <= orders[0]+1; i++, o++)
-      {
-         real_t kx = kv1[0]->GetBotella(ijk[0] + i);
-         if (!kv1[0]->inSpan(kx, ijk[0]+orders[0]+1)) { continue; }
-         ip.x = kv1[0]->GetRefPoint(kx, ijk[0]+orders[0]+1);
-
-         Trans.SetIntPoint(&ip);
-         vc.Eval(x, Trans, ip);
-
-         Trans.Jacobian().MultTranspose(x,xm);
-         dofs(o) = xm(1);
-      }
-   }
-}
-
 NURBS_HCurl2DFiniteElement::~NURBS_HCurl2DFiniteElement()
 {
   if (kv1[0]) { delete kv1[0]; }
   if (kv1[1]) { delete kv1[1]; }
 }

+
 void NURBS_HCurl3DFiniteElement::SetOrder() const
 {
   orders[0] = kv[0]->GetOrder();
@@ -1404,124 +1003,11 @@ void NURBS_HCurl3DFiniteElement::CalcCurlShape(const IntegrationPoint &ip,
            curl_shape(o,0) = shape1_x(i)*dsy1_sz;
            curl_shape(o,1) = -dshape1_x(i)*sy1_sz;
            curl_shape(o,2) = 0.0;
-
         }
      }
   }
 }

-void NURBS_HCurl3DFiniteElement::Project(VectorCoefficient &vc,
-                                         ElementTransformation &Trans,
-                                         Vector &dofs) const
-{
-   MFEM_ASSERT(dofs.Size() == dof, "");
-   MFEM_ASSERT(vc.GetVDim() == 3, "");
-   Vector x(3), xm(3);
-   IntegrationPoint ip;
-
-   int o = 0;
-   for (int k = 0; k <= orders[2]+1; k++)
-   {
-      real_t kz = kv1[2]->GetBotella(ijk[2] + k);
-      if (!kv1[2]->inSpan(kz, ijk[2]+orders[2]+1))
-      {
-         o += (orders[0] + 1)*(orders[1] + 2);
-         continue;
-      }
-      ip.z = kv1[2]->GetRefPoint(kz, ijk[2]+orders[2]+1);
-      for (int j = 0; j <= orders[1]+1; j++)
-      {
-         real_t ky = kv1[1]->GetBotella(ijk[1] + j);
-         if (!kv1[1]->inSpan(ky, ijk[1]+orders[1]+1))
-         {
-            o += orders[0] + 1;
-            continue;
-         }
-         ip.y = kv1[1]->GetRefPoint(ky, ijk[1]+orders[1]+1);
-         for (int i = 0; i <= orders[0]; i++, o++)
-         {
-            real_t kx = kv[0]->GetBotella(ijk[0] + i);
-            if (!kv[0]->inSpan(kx, ijk[0]+orders[0])) { continue; }
-            ip.x = kv[0]->GetRefPoint(kx, ijk[0]+orders[0]);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.Jacobian().MultTranspose(x,xm);
-            dofs(o) = xm(0);
-         }
-      }
-   }
-
-   for (int k = 0; k <= orders[2]+1; k++)
-   {
-      real_t kz = kv1[2]->GetBotella(ijk[2] + k);
-      if (!kv1[2]->inSpan(kz, ijk[2]+orders[2]+1))
-      {
-         o += (orders[0] + 2)*(orders[1] + 1);
-         continue;
-      }
-      ip.z = kv1[2]->GetRefPoint(kz, ijk[2]+orders[2]+1);
-      for (int j = 0; j <= orders[1]; j++)
-      {
-         real_t ky = kv[1]->GetBotella(ijk[1] + j);
-         if (!kv[1]->inSpan(ky, ijk[1]+orders[1]))
-         {
-            o += orders[0] + 2;
-            continue;
-         }
-         ip.y = kv[1]->GetRefPoint(ky, ijk[1]+orders[1]);
-         for (int i = 0; i <= orders[0]+1; i++, o++)
-         {
-            real_t kx = kv1[0]->GetBotella(ijk[0] + i);
-            if (!kv1[0]->inSpan(kx, ijk[0]+orders[0]+1)) { continue; }
-            ip.x = kv1[0]->GetRefPoint(kx, ijk[0]+orders[0]+1);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.Jacobian().MultTranspose(x,xm);
-            dofs(o) = xm(1);
-         }
-      }
-   }
-
-   for (int k = 0; k <= orders[2]; k++)
-   {
-      real_t kz = kv[2]->GetBotella(ijk[2] + k);
-      if (!kv[2]->inSpan(kz, ijk[2]+orders[2]))
-      {
-         o += (orders[0] + 2)*(orders[1] + 2);
-         continue;
-      }
-      ip.z = kv[2]->GetRefPoint(kz, ijk[2]+orders[2]);
-      for (int j = 0; j <= orders[1]+1; j++)
-      {
-         real_t ky = kv1[1]->GetBotella(ijk[1] + j);
-         if (!kv1[1]->inSpan(ky, ijk[1]+orders[1]+1))
-         {
-            o += orders[0] + 2;
-            continue;
-         }
-         ip.y = kv1[1]->GetRefPoint(ky, ijk[1]+orders[1]+1);
-         for (int i = 0; i <= orders[0]+1; i++, o++)
-         {
-            real_t kx = kv1[0]->GetBotella(ijk[0] + i);
-            if (!kv1[0]->inSpan(kx, ijk[0]+orders[0]+1)) { continue; }
-            ip.x = kv1[0]->GetRefPoint(kx, ijk[0]+orders[0]+1);
-
-            Trans.SetIntPoint(&ip);
-            vc.Eval(x, Trans, ip);
-
-            Trans.Jacobian().MultTranspose(x,xm);
-            dofs(o) = xm(2);
-         }
-      }
-   }
-
-}
-
-
 NURBS_HCurl3DFiniteElement::~NURBS_HCurl3DFiniteElement()
 {
   if (kv1[0]) { delete kv1[0]; }
@@ -86,18 +86,6 @@ public:
                   DenseMatrix &dshape) const override;
   void CalcHessian (const IntegrationPoint &ip,
                     DenseMatrix &hessian) const override;
-
-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(Coefficient &coeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
 };

 /// An arbitrary order 2D NURBS element on a square
@@ -133,18 +121,6 @@ public:
                   DenseMatrix &dshape) const override;
   void CalcHessian (const IntegrationPoint &ip,
                     DenseMatrix &hessian) const override;
-
-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(Coefficient &coeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
 };

 /// An arbitrary order 3D NURBS element on a cube
@@ -185,18 +161,6 @@ public:
                   DenseMatrix &dshape) const override;
   void CalcHessian (const IntegrationPoint &ip,
                     DenseMatrix &hessian) const override;
-
-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(Coefficient &coeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
 };


@@ -278,13 +242,6 @@ public:
   void CalcDivShape(const IntegrationPoint &ip,
                     Vector &divshape) const override;

-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
   ~NURBS_HDiv2DFiniteElement();
 };

@@ -379,13 +336,6 @@ public:
   void CalcDivShape(const IntegrationPoint &ip,
                     Vector &divshape) const override;

-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
   ~NURBS_HDiv3DFiniteElement();
 };

@@ -465,13 +415,6 @@ public:
   void CalcCurlShape(const IntegrationPoint &ip,
                      DenseMatrix &curl_shape) const override;

-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
   ~NURBS_HCurl2DFiniteElement();
 };

@@ -563,13 +506,6 @@ public:
   void CalcCurlShape(const IntegrationPoint &ip,
                      DenseMatrix &curl_shape) const override;

-   using FiniteElement::Project;
-
-   /** Evaluate the dofs that are defined on this element.
-       Dofs that can not be evaluated will remain unmodified. */
-   void Project(VectorCoefficient &vcoeff,
-                ElementTransformation &Trans, Vector &dofs) const override;
-
   ~NURBS_HCurl3DFiniteElement();
 };

@@ -2006,7 +2006,7 @@ RT_R1D_SegmentElement::RT_R1D_SegmentElement(const int p,
                                             const int cb_type,
                                             const int ob_type)
   : VectorFiniteElement(1, Geometry::SEGMENT, 3 * p + 4, p + 1,
-                         H_DIV_R1D, FunctionSpace::Pk),
+                         H_DIV, FunctionSpace::Pk),
     dof2nk(dof),
     cbasis1d(poly1d.GetBasis(p + 1, VerifyClosed(cb_type))),
     obasis1d(poly1d.GetBasis(p, VerifyOpen(ob_type)))
@@ -2281,7 +2281,7 @@ const real_t RT_R2D_SegmentElement::nk[2] = { 0.,1.};
 RT_R2D_SegmentElement::RT_R2D_SegmentElement(const int p,
                                             const int ob_type)
   : VectorFiniteElement(1, Geometry::SEGMENT, p + 1, p + 1,
-                         H_DIV_R2D, FunctionSpace::Pk),
+                         H_DIV, FunctionSpace::Pk),
     dof2nk(dof),
     obasis1d(poly1d.GetBasis(p, VerifyOpen(ob_type)))
 {
@@ -2392,7 +2392,7 @@ void RT_R2D_SegmentElement::LocalInterpolation(const VectorFiniteElement &cfe,
 RT_R2D_FiniteElement::RT_R2D_FiniteElement(int p, Geometry::Type G, int Do,
                                           const real_t *nk_fe)
   : VectorFiniteElement(2, G, Do, p + 1,
-                         H_DIV_R2D, FunctionSpace::Pk),
+                         H_DIV, FunctionSpace::Pk),
     nk(nk_fe),
     dof_map(dof),
     dof2nk(dof)
@@ -510,9 +510,6 @@ public:
   RT_R2D_SegmentElement(const int p,
                         const int ob_type = BasisType::GaussLegendre);

-   int GetPhysRangeDim(int space_dim) const override { return 2; }
-   int GetPhysCurlDim(int space_dim) const override { return 0; }
-
   void CalcVShape(const IntegrationPoint &ip,
                   DenseMatrix &shape) const override;

@@ -550,9 +547,6 @@ private:
                           DenseMatrix &I) const;

 public:
-   int GetPhysRangeDim(int space_dim) const override { return 3; }
-   int GetPhysCurlDim(int space_dim) const override { return 0; }
-
   using FiniteElement::CalcVShape;

   void CalcVShape(ElementTransformation &Trans,
@@ -111,36 +111,36 @@ public:
   | :------: | :---: | :---: | :-------: | :-----: | :---: |
   | H1_[DIM]_[ORDER] | H1 | * | 1 | VALUE | H1 nodal elements |
   | H1@[BTYPE]_[DIM]_[ORDER] | H1 | * | * | VALUE | H1 nodal elements |
-   | H1Pos_[DIM]_[ORDER] | H1 | * | 2 | VALUE | H1 nodal elements |
+   | H1Pos_[DIM]_[ORDER] | H1 | * | 1 | VALUE | H1 nodal elements |
   | H1Pos_Trace_[DIM]_[ORDER] | H^{1/2} | * | 2 | VALUE | H^{1/2}-conforming trace elements for H1 defined on the interface between mesh elements (faces,edges,vertices) |
   | H1_Trace_[DIM]_[ORDER] | H^{1/2} | * | 1 | VALUE | H^{1/2}-conforming trace elements for H1 defined on the interface between mesh elements (faces,edges,vertices) |
-   | H1_Trace@[BTYPE]_[DIM]_[ORDER] | H^{1/2} | * | * | VALUE | H^{1/2}-conforming trace elements for H1 defined on the interface between mesh elements (faces,edges,vertices) |
+   | H1_Trace@[BTYPE]_[DIM]_[ORDER] | H^{1/2} | * | 1 | VALUE | H^{1/2}-conforming trace elements for H1 defined on the interface between mesh elements (faces,edges,vertices) |
   | ND_[DIM]_[ORDER] | H(curl) | * | 1 / 0 | H_CURL | Nedelec vector elements |
   | ND@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(curl) | * | * / * | H_CURL | Nedelec vector elements |
-   | ND_Trace_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0  | H_CURL | H^{1/2}-conforming trace elements for H(curl) defined on the interface between mesh elements (faces,edges) |
-   | ND_Trace@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H^{1/2} | * | * / * | H_CURL | H^{1/2}-conforming trace elements for H(curl) defined on the interface between mesh elements (faces,edges) |
+   | ND_Trace_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0  | H_CURL | H^{1/2}-conforming trace elements for H(curl) defined on the interface between mesh elements (faces) |
+   | ND_Trace@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0 | H_CURL | H^{1/2}-conforming trace elements for H(curl) defined on the interface between mesh elements (faces) |
   | ND_R1D_[DIM]_[ORDER] | H(curl) | * | 1 / 0 | H_CURL | 3D H(curl)-conforming Nedelec vector elements in 1D. |
   | ND_R1D@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(curl) | * | * / * | H_CURL | 3D H(curl)-conforming Nedelec vector elements in 1D. |
   | ND_R2D_[DIM]_[ORDER] | H(curl) | * | 1 / 0 | H_CURL | 3D H(curl)-conforming Nedelec vector elements in 2D. |
   | ND_R2D@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(curl) | * | * / * | H_CURL | 3D H(curl)-conforming Nedelec vector elements in 2D. |
   | RT_[DIM]_[ORDER] | H(div) | * | 1 / 0 | H_DIV | Raviart-Thomas vector elements |
   | RT@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(div) | * | * / * | H_DIV | Raviart-Thomas vector elements |
-   | RT_Trace_[DIM]_[ORDER] | H^{1/2} | * | 0 | INTEGRAL | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
-   | RT_ValTrace_[DIM]_[ORDER] | H^{1/2} | * | 0 | VALUE | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
-   | RT_Trace@[BTYPE]_[DIM]_[ORDER] | H^{1/2} | * | * | INTEGRAL | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
-   | RT_ValTrace@[BTYPE]_[DIM]_[ORDER] |  H^{1/2} | * | * | VALUE | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
+   | RT_Trace_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0 | INTEGRAL | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
+   | RT_ValTrace_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0 | VALUE | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
+   | RT_Trace@[BTYPE]_[DIM]_[ORDER] | H^{1/2} | * | 1 / 0 | INTEGRAL | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
+   | RT_ValTrace@[BTYPE]_[DIM]_[ORDER] |  H^{1/2} | * | 1 / 0 | VALUE | H^{1/2}-conforming trace elements for H(div) defined on the interface between mesh elements (faces) |
   | RT_R1D_[DIM]_[ORDER] | H(div) | * | 1 / 0 | H_DIV | 3D H(div)-conforming Raviart-Thomas vector elements in 1D. |
   | RT_R1D@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(div) | * | * / * | H_DIV | 3D H(div)-conforming Raviart-Thomas vector elements in 1D. |
   | RT_R2D_[DIM]_[ORDER] | H(div) | * | 1 / 0 | H_DIV | 3D H(div)-conforming Raviart-Thomas vector elements in 2D. |
   | RT_R2D@[CBTYPE][OBTYPE]_[DIM]_[ORDER] | H(div) | * | * / * | H_DIV | 3D H(div)-conforming Raviart-Thomas vector elements in 2D. |
   | L2_[DIM]_[ORDER] | L2 | * | 0 | VALUE | Discontinuous L2 elements |
-   | L2_T[BTYPE]_[DIM]_[ORDER] | L2 | * | * | VALUE | Discontinuous L2 elements |
+   | L2_T[BTYPE]_[DIM]_[ORDER] | L2 | * | 0 | VALUE | Discontinuous L2 elements |
   | L2Int_[DIM]_[ORDER] | L2 | * | 0 | INTEGRAL | Discontinuous L2 elements |
-   | L2Int_T[BTYPE]_[DIM]_[ORDER] | L2 | * | * | INTEGRAL | Discontinuous L2 elements |
+   | L2Int_T[BTYPE]_[DIM]_[ORDER] | L2 | * | 0 | INTEGRAL | Discontinuous L2 elements |
   | DG_Iface_[DIM]_[ORDER] | - | * | 0 | VALUE | Discontinuous elements on the interface between mesh elements (faces) |
-   | DG_Iface@[BTYPE]_[DIM]_[ORDER] | - | * | * | VALUE | Discontinuous elements on the interface between mesh elements (faces) |
+   | DG_Iface@[BTYPE]_[DIM]_[ORDER] | - | * | 0 | VALUE | Discontinuous elements on the interface between mesh elements (faces) |
   | DG_IntIface_[DIM]_[ORDER] | - | * | 0 | INTEGRAL | Discontinuous elements on the interface between mesh elements (faces) |
-   | DG_IntIface@[BTYPE]_[DIM]_[ORDER] | - | * | * | INTEGRAL | Discontinuous elements on the interface between mesh elements (faces) |
+   | DG_IntIface@[BTYPE]_[DIM]_[ORDER] | - | * | 0 | INTEGRAL | Discontinuous elements on the interface between mesh elements (faces) |
   | NURBS[ORDER] | - | * | - | VALUE | Non-Uniform Rational B-Splines (NURBS) elements |
   | LinearNonConf3D | - | 1 | 1 | VALUE | Piecewise-linear nonconforming finite elements in 3D |
   | CrouzeixRaviart | - | - | - | - | Crouzeix-Raviart nonconforming elements in 2D |
@@ -172,7 +172,7 @@ public:
   | :------: | :--------: |
   | [DIM]    | Dimension of the elements (1D, 2D, 3D) |
   | [ORDER]  | Approximation order of the elements (P0, P1, P2, ...) |
-   | [BTYPE]  | BasisType of the element (0-GaussLegendre, 1-GaussLobatto, 2-Bernstein, 3-OpenUniform, 4-CloseUniform, 5-OpenHalfUniform 6-Serendipity 7-ClosedGL 8-IntegratedGLL) |
+   | [BTYPE]  | BasisType of the element (0-GaussLegendre, 1 - GaussLobatto, 2-Bernstein, 3-OpenUniform, 4-CloseUniform, 5-OpenHalfUniform) |
   | [OBTYPE] | Open BasisType of the element for elements which have both types |
   | [CBTYPE] | Closed BasisType of the element for elements which have both types |

@@ -282,7 +282,14 @@ int FiniteElementSpace::DofToVDof(int dof, int vd, int ndofs_) const
 void FiniteElementSpace::AdjustVDofs(Array<int> &vdofs)
 {
   int n = vdofs.Size(), *vdof = vdofs;
-   for (int i = 0; i < n; i++) { vdof[i] = UnsignIndex(vdof[i]); }
+   for (int i = 0; i < n; i++)
+   {
+      int j;
+      if ((j = vdof[i]) < 0)
+      {
+         vdof[i] = -1-j;
+      }
+   }
 }

 void FiniteElementSpace::GetElementVDofs(int i, Array<int> &vdofs,
@@ -476,14 +483,13 @@ void FiniteElementSpace::ReorderElementToDofTable()
   for (int k = 0, dof_counter = 0; k < nnz; k++)
   {
      const int sdof = J[k]; // signed dof
-      const int dof = UnsignIndex(sdof);
+      const int dof = (sdof < 0) ? -1-sdof : sdof;
      int new_dof = dof_marker[dof];
      if (new_dof < 0)
      {
         dof_marker[dof] = new_dof = dof_counter++;
      }
-      // Preserve the sign of sdof
-      J[k] = (sdof < 0) ? FlipIndexSign(new_dof) : new_dof;
+      J[k] = (sdof < 0) ? -1-new_dof : new_dof; // preserve the sign of sdof
   }
 }

@@ -541,7 +547,7 @@ void MarkDofs(const Array<int> &dofs, Array<int> &mark_array)
 {
   for (auto d : dofs)
   {
-      mark_array[UnsignIndex(d)] = -1;
+      mark_array[d >= 0 ? d : -1 - d] = -1;
   }
 }

@@ -925,7 +931,7 @@ void FiniteElementSpace::AddDependencies(
            if (std::abs(coef) > 1e-12)
            {
               const int mdof = master_dofs[j];
-               if (mdof != sdof && mdof != FlipIndexSign(sdof))
+               if (mdof != sdof && mdof != (-1-sdof))
               {
                  deps.Add(sdof, mdof, coef);
               }
@@ -1018,7 +1024,7 @@ int FiniteElementSpace::GetDegenerateFaceDofs(int index, Array<int> &dofs,
   // FiniteElementSpace::AddDependencies.

   Array<int> edof;
-   int order = GetEdgeDofs(FlipIndexSign(index), edof, variant);
+   int order = GetEdgeDofs(-1 - index, edof, variant);

   int nv = fec->DofForGeometry(Geometry::POINT);
   int ne = fec->DofForGeometry(Geometry::SEGMENT);
@@ -1510,76 +1516,36 @@ const FaceRestriction *FiniteElementSpace::GetFaceRestriction(
   const bool is_dg_space = IsDGSpace();
   const L2FaceValues m = (is_dg_space && mul==L2FaceValues::DoubleValued) ?
                          L2FaceValues::DoubleValued : L2FaceValues::SingleValued;
-   auto key = std::make_tuple(is_dg_space, f_ordering, type, m);
+   key_face key = std::make_tuple(is_dg_space, f_ordering, type, m);
   auto itr = L2F.find(key);
   if (itr != L2F.end())
   {
-      return itr->second.get();
+      return itr->second;
   }
   else
   {
-      std::unique_ptr<FaceRestriction> res;
+      FaceRestriction *res;
      if (is_dg_space)
      {
         if (Conforming())
         {
-            res.reset(new L2FaceRestriction(*this, f_ordering, type, m));
+            res = new L2FaceRestriction(*this, f_ordering, type, m);
         }
         else
         {
-            res.reset(new NCL2FaceRestriction(*this, f_ordering, type, m));
+            res = new NCL2FaceRestriction(*this, f_ordering, type, m);
         }
      }
      else if (dynamic_cast<const DG_Interface_FECollection*>(fec))
      {
-         res.reset(new L2InterfaceFaceRestriction(*this, f_ordering, type));
+         res = new L2InterfaceFaceRestriction(*this, f_ordering, type);
      }
      else
      {
-         res.reset(new ConformingFaceRestriction(*this, f_ordering, type));
+         res = new ConformingFaceRestriction(*this, f_ordering, type);
      }
-      return L2F.emplace(key, std::move(res)).first->second.get();
-   }
-}
-
-const InterpolationManager &FiniteElementSpace::GetInterpolationManager(
-   ElementDofOrdering f_ordering, FaceType type) const
-{
-   const auto key = make_tuple(f_ordering, type);
-
-   auto it = interpolations.find(key);
-   if (it != interpolations.end())
-   {
-      return *it->second;
-   }
-   else
-   {
-      auto interp = make_unique<InterpolationManager>(*this, f_ordering, type);
-
-      int face_idx = 0;
-      for (int f = 0; f < mesh->GetNumFacesWithGhost(); ++f)
-      {
-         Mesh::FaceInformation face = mesh->GetFaceInformation(f);
-         if (!face.IsOfFaceType(type) || face.IsNonconformingCoarse())
-         {
-            continue;
-         }
-         if (face.IsConforming() || face.IsBoundary())
-         {
-            interp->RegisterFaceConformingInterpolation(face, face_idx);
-         }
-         else
-         {
-            interp->RegisterFaceCoarseToFineInterpolation(face, face_idx);
-         }
-         ++face_idx;
-      }
-
-      // Transform the interpolation matrix map into contiguous memory.
-      interp->LinearizeInterpolatorMapIntoVector();
-      interp->InitializeNCInterpConfig();
-
-      return *interpolations.emplace(key, std::move(interp)).first->second;
+      L2F[key] = res;
+      return res;
   }
 }

@@ -1704,8 +1670,8 @@ SparseMatrix *FiniteElementSpace::RefinementMatrix_main(

         for (int i = 0; i < fine_ldof; i++)
         {
-            const int r = DofToVDof(dofs[i], vd);
-            const int m = UnsignIndex(r);
+            int r = DofToVDof(dofs[i], vd);
+            int m = (r >= 0) ? r : (-1 - r);

            if (!mark[m])
            {
@@ -1766,7 +1732,7 @@ SparseMatrix *FiniteElementSpace::VariableOrderRefinementMatrix(
         for (int i = 0; i < fine_ldof; i++)
         {
            const int r = DofToVDof(dofs[i], vd);
-            const int m = UnsignIndex(r);
+            int m = (r >= 0) ? r : (-1 - r);

            if (!mark[m])
            {
@@ -2476,8 +2442,8 @@ SparseMatrix* FiniteElementSpace::DerefinementMatrix(int old_ndofs,
         {
            if (!std::isfinite(lR(i, 0))) { continue; }

-            const int r = DofToVDof(dofs[i], vd);
-            const int m = UnsignIndex(r);
+            int r = DofToVDof(dofs[i], vd);
+            int m = (r >= 0) ? r : (-1 - r);

            if (is_dg || !mark[m])
            {
@@ -3195,7 +3161,7 @@ void FiniteElementSpace::CalcEdgeFaceVarOrders(
            else
            {
               // degenerate face (i.e., edge-face constraint)
-               slave_orders |= edge_orders[FlipIndexSign(slave.index)];
+               slave_orders |= edge_orders[-1 - slave.index];
            }
         }

@@ -3934,16 +3900,6 @@ const FiniteElement *FiniteElementSpace::GetBE(int i) const
   return BE;
 }

-const FiniteElement *FiniteElementSpace::GetTypicalBE() const
-{
-   if (mesh->GetNBE() > 0) { return GetBE(0); }
-
-   Geometry::Type geom = mesh->GetTypicalFaceGeometry();
-   const FiniteElement *be = fec->FiniteElementForGeometry(geom);
-   MFEM_VERIFY(be != nullptr, "Could not determine a typical BE!");
-   return be;
-}
-
 const FiniteElement *FiniteElementSpace::GetFaceElement(int i) const
 {
   MFEM_VERIFY(!IsVariableOrder(), "not implemented");
@@ -3974,11 +3930,6 @@ const FiniteElement *FiniteElementSpace::GetFaceElement(int i) const
   return fe;
 }

-const FiniteElement *FiniteElementSpace::GetTypicalFaceElement() const
-{
-   return fec->FiniteElementForGeometry(mesh->GetTypicalFaceGeometry());
-}
-
 const FiniteElement *FiniteElementSpace::GetEdgeElement(int i,
                                                        int variant) const
 {
@@ -4018,8 +3969,11 @@ void FiniteElementSpace::Destroy()
      delete E2Q_array[i];
   }
   E2Q_array.SetSize(0);
+   for (auto &x : L2F)
+   {
+      delete x.second;
+   }
   L2F.clear();
-   interpolations.clear();
   for (int i = 0; i < E2IFQ_array.Size(); i++)
   {
      delete E2IFQ_array[i];
@@ -13,7 +13,6 @@
 #define MFEM_FESPACE

 #include "../config/config.hpp"
-#include "../general/hash_util.hpp"
 #include "../linalg/ordering.hpp"
 #include "../linalg/sparsemat.hpp"
 #include "../mesh/mesh.hpp"
@@ -321,11 +320,18 @@ protected:
   mutable OperatorHandle L2E_nat, L2E_lex;
   /// The face restriction operators, see GetFaceRestriction().
   using key_face = std::tuple<bool, ElementDofOrdering, FaceType, L2FaceValues>;
-   mutable std::unordered_map<key_face,std::unique_ptr<FaceRestriction>,
-           TupleHasher> L2F;
-
-   mutable std::unordered_map<std::tuple<ElementDofOrdering,FaceType>,
-           std::unique_ptr<InterpolationManager>, TupleHasher> interpolations;
+   struct key_hash
+   {
+      std::size_t operator()(const key_face& k) const
+      {
+         return std::get<0>(k)
+                + 2 * (int)std::get<1>(k)
+                + 4 * (int)std::get<2>(k)
+                + 8 * (int)std::get<3>(k);
+      }
+   };
+   using map_L2F = std::unordered_map<const key_face,FaceRestriction*,key_hash>;
+   mutable map_L2F L2F;

   mutable Array<QuadratureInterpolator*> E2Q_array;
   mutable Array<FaceQuadratureInterpolator*> E2IFQ_array;
@@ -745,9 +751,6 @@ public:
      ElementDofOrdering f_ordering, FaceType,
      L2FaceValues mul = L2FaceValues::DoubleValued) const;

-   const InterpolationManager &GetInterpolationManager(
-      ElementDofOrdering f_ordering, FaceType type) const;
-
   /** @brief Return a QuadratureInterpolator that interpolates E-vectors to
       quadrature point values and/or derivatives (Q-vectors). */
   /** An E-vector represents the element-wise discontinuous version of the FE
@@ -839,7 +842,7 @@ public:
       Note: For vector-valued elements, the results pads up the range dimension
       to the spatial dimension. E.g., consider a stack of 5 vector-valued
       elements each representing 2D vectors, living in a 3 dimensional space.
-       Then this function would give 15, not 10.
+       Then this fucntion would give 15, not 10.
       */
   int GetVectorDim() const;

@@ -1150,7 +1153,7 @@ public:

   /// Helper to return the DOF associated with a sign encoded DOF
   static inline int DecodeDof(int dof)
-   { return UnsignIndex(dof); }
+   { return (dof >= 0) ? dof : (-1 - dof); }

   /// Helper to determine the DOF and sign of a sign encoded DOF
   static inline int DecodeDof(int dof, real_t& sign)
@@ -1323,24 +1326,12 @@ public:
        associated with i'th boundary face in the mesh object. */
   const FiniteElement *GetBE(int i) const;

-   /// @brief Return a "typical" boundary element.
-   ///
-   /// This can be used in situations where the local mesh partition may be
-   /// empty.
-   const FiniteElement *GetTypicalBE() const;
-
   /** @brief Returns pointer to the FiniteElement in the FiniteElementCollection
        associated with i'th face in the mesh object.  Faces in this case refer
        to the MESHDIM-1 primitive so in 2D they are segments and in 1D they are
        points.*/
   const FiniteElement *GetFaceElement(int i) const;

-   /// @brief Return a "typical" face element.
-   ///
-   /// This can be used in situations where the local mesh partition may be
-   /// empty.
-   const FiniteElement *GetTypicalFaceElement() const;
-
   /** @brief Returns pointer to the FiniteElement in the FiniteElementCollection
        associated with i'th edge in the mesh object. */
   const FiniteElement *GetEdgeElement(int i, int variant = 0) const;
@@ -23,29 +23,10 @@
 #include <limits>
 #include <ostream>
 #include <string>
-#include <variant>

 namespace mfem
 {

-/** This enumerated type describes the three main projection types:
-    - ELEMENT, assigns the degree of freedom per element, as specified in the
-      specific element
-    - GLOBAL_L2, solves a global L2 projection
-    - ELEMENT_L2, solves a element level L2 projection. Inter element
-      connectivity is dealt with similar as in:
-      Bezier-Projection : A unified approach for local projection and
-      quadrature-free refinement and coarsening of NURBS and T-splines with
-      particular application to isogeometric design and analysis
-      [CMAME (284) 2015 pg 55-105]
-    - DEFAULT, for NURBS spaces this is ELEMENT_L2, while for all other spaces
-      this ELEMENT.
-   Note 1: ELEMENT_L2 also works for non NURBS elements
-   Note 2: For NURBS elements the ELEMENT projection gives results without
-   over and undershoots. However, the gradient near the boundary does not
-   converge.*/
-enum class ProjectType { DEFAULT, ELEMENT, GLOBAL_L2, ELEMENT_L2 };
-
 /// Class for grid function - Vector with associated FE space.
 class GridFunction : public Vector
 {
@@ -80,23 +61,10 @@ protected:
                        bool wcoef,
                        int subdomain);

-   /** @brief Project a discontinuous (vector) coefficient as a grid function on
-       a continuous finite element space. Return in dof_attr the maximal
-       attribute of the elements containing each degree of freedom. */
-   virtual void ProjectDiscCoefficient(
-      std::variant<Coefficient*, VectorCoefficient*> coeff, Array<int> &dof_attr);
-
-   /** @brief Project a discontinuous (vector) coefficient as a grid function on
-       a continuous finite element space. The values in shared dofs are
-       determined from the element with maximal attribute. */
-   virtual void ProjectDiscCoefficient(
-      std::variant<Coefficient*, VectorCoefficient*> coeff)
-   { Array<int> dof_attr; ProjectDiscCoefficient(coeff, dof_attr); };
-
-   /** Helper function for ProjectCoefficientElementL2 */
-   void ProjectCoefficientElementL2_(Coefficient &coeff, Vector &sol, Vector &Va);
-   void ProjectCoefficientElementL2_(VectorCoefficient &vcoeff, Vector &sol,
-                                     Vector &Va);
+   /** Project a discontinuous vector coefficient in a continuous space and
+       return in dof_attr the maximal attribute of the elements containing each
+       degree of freedom. */
+   void ProjectDiscCoefficient(VectorCoefficient &coeff, Array<int> &dof_attr);

   /// Loading helper.
   void LegacyNCReorder();
@@ -104,6 +72,7 @@ protected:
   void Destroy();

 public:
+
   GridFunction() { fes = NULL; fec_owned = NULL; fes_sequence = 0; UseDevice(true); }

   /// Copy constructor. The internal true-dof vector #t_vec is not copied.
@@ -115,10 +84,6 @@ public:
   GridFunction(FiniteElementSpace *f) : Vector(f->GetVSize())
   { fes = f; fec_owned = NULL; fes_sequence = f->GetSequence(); UseDevice(true); }

-   /// Same as above but specify the memory type
-   GridFunction(FiniteElementSpace *f, MemoryType mt) : Vector(f->GetVSize(), mt)
-   { fes = f; fec_owned = NULL; fes_sequence = f->GetSequence(); UseDevice(true); }
-
   /// Construct a GridFunction using previously allocated array @a data.
   /** The GridFunction does not assume ownership of @a data which is assumed to
       be of size at least `f->GetVSize()`. Similar to the Vector constructor
@@ -159,13 +124,11 @@ public:

   FiniteElementCollection *OwnFEC() { return fec_owned; }

-   /** @brief Shortcut for calling FiniteElementSpace::GetVectorDim() on the
-       underlying #fes */
-   int VectorDim() const { return fes->GetVectorDim(); }
+   /// Shortcut for calling FiniteElementSpace::GetVectorDim() on the underlying #fes
+   int VectorDim() const;

-   /** @brief Shortcut for calling FiniteElementSpace::GetCurlDim() on the
-       underlying #fes */
-   int CurlDim() const { return fes->GetCurlDim(); }
+   /// Shortcut for calling FiniteElementSpace::GetCurlDim() on the underlying #fes
+   int CurlDim() const;

   /// Read only access to the (optional) internal true-dof Vector.
   const Vector &GetTrueVector() const
@@ -457,30 +420,9 @@ public:
   /** @brief Project @a coeff Coefficient to @a this GridFunction. The
       projection computation depends on the choice of the FiniteElementSpace
       #fes. Note that this is usually interpolation at the degrees of freedom
-       in each element (not L2 projection). For elements without a projection
-       member function one could use ProjectCoefficientGlobalL2 instead.
-       NOTE: For parallel simulations with NURBS elements some dofs might
-       not be defined, if the evaluation point does not reside on this rank.
-       If that is the case it is defined on another rank, and the issue is
-       rectified with the appropriate communication, see in ParGridFunction.
-       */
-   virtual void ProjectCoefficient(Coefficient &coeff,
-                                   ProjectType type = ProjectType::DEFAULT);
-
-   /** @brief Project @a coeff Coefficient to @a this GridFunction. The
-       projection is a global L2 projection. This routine can be used a
-       fallback for elements without a projection member function.*/
-   virtual void ProjectCoefficientGlobalL2(Coefficient &coeff,
-                                           real_t rtol = 1e-12,
-                                           int iter = 1000);
-
-   /** @brief Project @a coeff Coefficient to @a this GridFunction. The
-       projection is an element local L2 projection, with an appropriate
-       weighting for Dofs that are shared between elements. Inspired on
-       Bezier-Projection [CMAME (284) 2015 pg 55-105]
-       This routine can be used a fallback for elements without a projection
-       member function.*/
-   virtual void ProjectCoefficientElementL2(Coefficient &coeff);
+       in each element (not L2 projection). For NURBS spaces these degrees of
+       freedom are not available and L2 projection is resorted to as fallback. */
+   virtual void ProjectCoefficient(Coefficient &coeff);

   /** @brief Project @a coeff Coefficient to @a this GridFunction, using one
       element for each degree of freedom in @a dofs and nodal interpolation on
@@ -490,26 +432,9 @@ public:
   /** @brief Project @a vcoeff VectorCoefficient to @a this GridFunction. The
       projection computation depends on the choice of the FiniteElementSpace
       #fes. Note that this is usually interpolation at the degrees of freedom
-       in each element (not L2 projection). For elements without a projection
-       member function one could use ProjectCoefficientGlobalL2 instead.
-       NOTE: For parallel simulations with NURBS elements some dofs might
-       not be defined, if the evaluation point does not reside on this rank.
-       If that is the case it is defined on another rank, and the issue is
-       rectified with the appropriate communication, see in ParGridFunction.*/
-   virtual void ProjectCoefficient(VectorCoefficient &vcoeff,
-                                   ProjectType type = ProjectType::DEFAULT);
-
-   /** @brief Project @a coeff Coefficient to @a this GridFunction. The
-       projection is a global L2 projection. This routine can be used a
-       fallback for elements without a projection member function.*/
-   virtual void ProjectCoefficientGlobalL2(VectorCoefficient &vcoeff,
-                                           real_t rtol = 1e-12,
-                                           int iter = 1000);
-
-   /** @brief Project @a coeff Coefficient to @a this GridFunction. The
-       projection is a global L2 projection. This routine can be used a
-       fallback for elements without a projection member function.*/
-   virtual void ProjectCoefficientElementL2(VectorCoefficient &vcoeff);
+       in each element (not L2 projection). For NURBS spaces these degrees of
+       freedom are not available and L2 projection is resorted to as fallback. */
+   void ProjectCoefficient(VectorCoefficient &vcoeff);

   /** @brief Project @a vcoeff VectorCoefficient to @a this GridFunction, using
       one element for each degree of freedom in @a dofs and nodal interpolation
@@ -524,17 +449,10 @@ public:
       but using an array of scalar coefficients for each component. */
   void ProjectCoefficient(Coefficient *coeff[]);

-   /** @brief Project a discontinuous coefficient as a grid function on
-       a continuous finite element space. The values in shared dofs are
-       determined from the element with maximal attribute. */
-   virtual void ProjectDiscCoefficient(Coefficient &coeff)
-   { ProjectDiscCoefficient(&coeff); }
-
   /** @brief Project a discontinuous vector coefficient as a grid function on
       a continuous finite element space. The values in shared dofs are
       determined from the element with maximal attribute. */
-   virtual void ProjectDiscCoefficient(VectorCoefficient &coeff)
-   { ProjectDiscCoefficient(&coeff); }
+   virtual void ProjectDiscCoefficient(VectorCoefficient &coeff);

   enum AvgType {ARITHMETIC, HARMONIC};
   /** @brief Projects a discontinuous coefficient so that the values in shared
@@ -550,9 +468,6 @@ public:
   std::unique_ptr<GridFunction> ProlongateToMaxOrder() const;

 protected:
-   void ProjectBdrCoefficientNormal(Coefficient *coeff, VectorCoefficient *vcoeff,
-                                    const Array<int> &attr);
-
   /** @brief Accumulates (depending on @a type) the values of @a coeff at all
       shared vdofs and counts in how many zones each vdof appears. */
   void AccumulateAndCountZones(Coefficient &coeff, AvgType type,
@@ -585,70 +500,6 @@ protected:
   /// P-refinement version of Update().
   void UpdatePRef();

-   /** @brief Estimate the minimum value of the GridFunction in element @a elem
-    *  if it is below a certain @a min_threshold.
-    *
-    *  @details For a given element \p elem and grid function component \p vdim
-    *  an estimate of the function minimum is the minimum of the piecewise
-    *  linear lower bound obtained using the given PLBound object. The actual
-    *  minimum is between [minimum lower bound, minimum upper bound]. We
-    *  improve the estimate of the function minimum by recursively
-    *  subdividing the interval with the lowest lower bound, and computing
-    *  bounds on the sub-intervals.
-    *  This process continues until (i) the maximum recursion depth is reached
-    *  or (ii) the difference between the minimum upper bound and minimum lower
-    *  bound is less than a certain tolerance (\p tol * [initial maximum
-    *  upper bound - initial minimum lower bound]).
-    *  The function also terminates if the lowest minima estimate is found
-    *  to be above the given threshold \p min_threshold. This is useful when
-    *  we are interested in computing the global minimum of the function
-    *  over all elements. In this case we can reject elements where the lowest
-    *  bound is above the current global minimum. In case the function
-    *  minimum on the element is below the global minimum, we update
-    *  \p min_threshold.
-    *
-    *  We return a pair of values that bracket the actual minimum, i.e.
-    *  [min_lower_bound, min_upper_bound].
-    */
-   std::pair<real_t,real_t> EstimateFunctionMinimum(const int elem,
-                                                    const PLBound &plb,
-                                                    const int vdim,
-                                                    const int max_depth,
-                                                    const real_t tol,
-                                                    real_t &min_threshold)const;
-
-   /** @brief Estimate the maximum value of the GridFunction in element @a elem
-    *  if it is below a certain @a max_threshold.
-    *
-    *  @details For a given element \p elem and grid function component \p vdim
-    *  an estimate of the function maximum is the maximum of the piecewise
-    *  linear upper bound obtained using the given PLBound object. The actual
-    *  maximum is between [maximum lower bound, maximum upper bound]. We
-    *  improve the estimate of the function maximum by recursively
-    *  subdividing the interval with the highest upper bound, and computing
-    *  bounds on the sub-intervals.
-    *  This process continues until (i) the maximum recursion depth is reached
-    *  or (ii) the difference between the maximum upper bound and maximum lower
-    *  bound is less than a certain tolerance (\p tol * [initial maximum
-    *  upper bound - initial maximum lower bound]).
-    *  The function also terminates if the highest maxima estimate is found
-    *  to be below the given threshold \p max_threshold. This is useful when
-    *  we are interested in computing the global maximum of the function
-    *  over all elements. In this case we can reject elements where the upper
-    *  bound is below the current global maximum. In case the function
-    *  maximum on the element is above the global maximum, we update
-    *  \p max_threshold.
-    *
-    *  We return a pair of values that bracket the actual maximum, i.e.
-    *  [max_lower_bound, max_upper_bound].
-    */
-   std::pair<real_t,real_t> EstimateFunctionMaximum(const int elem,
-                                                    const PLBound &plb,
-                                                    const int vdim,
-                                                    const int max_depth,
-                                                    const real_t tol,
-                                                    real_t &max_threshold)const;
-
 public:
   /** @brief For each vdof, counts how many elements contain the vdof,
       as containment is determined by FiniteElementSpace::GetElementVDofs(). */
@@ -677,26 +528,15 @@ public:
   virtual void ProjectBdrCoefficient(Coefficient *coeff[],
                                      const Array<int> &attr);

-   /** @brief Project the normal component of the given VectorCoefficient on
-       the boundary. */
-   /** Only boundary attributes that are marked in @a bdr_attr are
-       projected. Assumes RT-type vector finite element GridFunction. */
+   /** Project the normal component of the given VectorCoefficient on
+       the boundary. Only boundary attributes that are marked in
+       'bdr_attr' are projected. Assumes RT-type VectorFE GridFunction. */
   void ProjectBdrCoefficientNormal(VectorCoefficient &vcoeff,
-                                    const Array<int> &bdr_attr)
-   { ProjectBdrCoefficientNormal(NULL, &vcoeff, bdr_attr); }
-
-   /** @brief Project the given Coefficient in the normal direction on the
-       boundary. */
-   /** Only boundary attributes that are marked in @a bdr_attr are projected.
-       Assumes RT-type vector finite element GridFunction. */
-   void ProjectBdrCoefficientNormal(Coefficient &coeff,
-                                    const Array<int> &bdr_attr)
-   { ProjectBdrCoefficientNormal(&coeff, NULL, bdr_attr); }
+                                    const Array<int> &bdr_attr);

   /** @brief Project the tangential components of the given VectorCoefficient
-       on the boundary. */
-   /** Only boundary attributes that are marked in @a bdr_attr
-       are projected. Assumes ND-type vector finite element GridFunction. */
+       on the boundary. Only boundary attributes that are marked in @a bdr_attr
+       are projected. Assumes ND-type VectorFE GridFunction. */
   virtual void ProjectBdrCoefficientTangent(VectorCoefficient &vcoeff,
                                             const Array<int> &bdr_attr);

@@ -1758,21 +1598,21 @@ public:
    */
   ///@{
   /// Computes the \ref PLBound for the gridfunction with number of control
-   /// points based on \p ref_factor, and returns the overall bounds for each
-   /// vdim (across all elements) in \p lower and \p upper. We also return the
+   /// points based on @a ref_factor, and returns the overall bounds for each
+   /// vdim (across all elements) in @b lower and @b upper. We also return the
   /// PLBound object used to compute the bounds.
-   /// We compute the bounds for each vdim if \p vdim < 1.
+   /// We compute the bounds for each vdim if @a vdim < 1.
   /// Note: For most cases, this method/interface will be sufficient.
   virtual PLBound GetBounds(Vector &lower, Vector &upper,
                             const int ref_factor=1, const int vdim=-1) const;

   /// Computes the \ref PLBound for the gridfunction with number of control
-   /// points based on \p ref_factor, and returns the bounds for each element
-   /// ordered byNodes:
+   /// points based on @a ref_factor, and returns the bounds for each element
+   /// ordered byVDim:
   /// lower_{0,0}, lower_{1,0}, ..., lower_{ne-1,0},
   /// lower_{0,1}, ..., lower_{ne-1,vdim-1}. We also return the
   /// PLBound object used to compute the bounds.
-   /// We compute the bounds for each vdim if \p vdim < 1.
+   /// We compute the bounds for each vdim if @a vdim < 1.
   PLBound GetElementBounds(Vector &lower, Vector &upper,
                            const int ref_factor=1, const int vdim=-1) const;

@@ -1783,18 +1623,6 @@ public:
                                        Vector &lower, Vector &upper,
                                        const int vdim = -1) const;

-   /** @brief Gets the bounds on given reference range inside an element.
-    *
-    *  @details @a ref_range is a vector of size 2*dim that specifies the
-    *  lower and upper limits in each dimension of the reference element.
-    *  For example, in 2D, ref_range = [rmin, smin, rmax, smax].
-    */
-   void GetElementBoundsAtControlPoints(const int elem, const PLBound &plb,
-                                        const Vector &ref_range,
-                                        const int vdim,
-                                        Vector &lower, Vector &upper,
-                                        Vector &control_pos) const;
-
   /// Compute bounds on the grid function for the given element.
   /// The bounds are stored in @b lower and @b upper.
   void GetElementBounds(const int elem, const PLBound &plb,
@@ -1802,45 +1630,11 @@ public:
                         const int vdim = -1) const;

   /// Compute bounds on the grid function for all the elements. The bounds
-   /// are returned in @b lower and @b upper, ordered byNodes:
+   /// are returned in @b lower and @b upper, ordered byVDim:
   /// lower_{0,0}, lower_{1,0}, ..., lower_{ne-1,0},
   /// lower_{0,1}, ..., lower_{ne-1,vdim-1}
   void GetElementBounds(const PLBound &plb, Vector &lower, Vector &upper,
                         const int vdim=-1) const;
-
-   /** @brief Estimate the minimum value of the GridFunction in element @a elem.
-    *
-    *  @details See the protected version of EstimateFunctionMinimum for
-    *  details.
-    */
-   std::pair<real_t, real_t> EstimateFunctionMinimum(const int elem,
-                                                     const PLBound &plb,
-                                                     const int vdim,
-                                                     const int max_depth,
-                                                     const real_t tol) const;
-
-   /** @brief Estimate the minimum value of the GridFunction in element @a elem.
-    *
-    *  @details See the protected version of EstimateFunctionMaximum for
-    *  details.
-    */
-   std::pair<real_t, real_t> EstimateFunctionMaximum(const int elem,
-                                                     const PLBound &plb,
-                                                     const int vdim,
-                                                     const int max_depth,
-                                                     const real_t tol) const;
-
-   /** @brief Estimate the GridFunction minimum across all elements. */
-   virtual std::pair<real_t,real_t> EstimateFunctionMinimum(const int vdim,
-                                                            const PLBound &plb,
-                                                            const int max_depth,
-                                                            const real_t tol) const;
-
-   /** @brief Estimate the GridFunction maximum across all elements. */
-   virtual std::pair<real_t,real_t> EstimateFunctionMaximum(const int vdim,
-                                                            const PLBound &plb,
-                                                            const int max_depth,
-                                                            const real_t tol) const;
   ///@}

   /// Destroys grid function.
@@ -1946,7 +1740,7 @@ real_t ComputeElementLpDistance(real_t p, int i,
                                GridFunction& gf1, GridFunction& gf2);


-/// Class used for extruding a scalar coefficient
+/// Class used for extruding scalar GridFunctions
 class ExtrudeCoefficient : public Coefficient
 {
 private:
@@ -1954,53 +1748,13 @@ private:
   Mesh *mesh_in;
   Coefficient &sol_in;
 public:
-   /// Constructs an instance of VectorExtrudeCoefficient
-   /**
-    * @param m      1D mesh
-    * @param s      1D vector coefficient
-    * @param n_     number of transverse elements of the extruded mesh
-    */
   ExtrudeCoefficient(Mesh *m, Coefficient &s, int n_)
-      : n(n_), mesh_in(m), sol_in(s)
-   { MFEM_VERIFY(n > 0, "Number of transverse elements must be positive!"); }
-
+      : n(n_), mesh_in(m), sol_in(s) { }
   real_t Eval(ElementTransformation &T, const IntegrationPoint &ip) override;
-
   virtual ~ExtrudeCoefficient() { }
 };

-/// Class used for extruding a vector coefficient
-class VectorExtrudeCoefficient : public VectorCoefficient
-{
-private:
-   int n;
-   Mesh *mesh_in;
-   VectorCoefficient &sol_in;
-public:
-   /// Constructs an instance of VectorExtrudeCoefficient
-   /**
-    * @param m      1D mesh
-    * @param s      1D vector coefficient
-    * @param n_     number of transverse elements of the extruded mesh
-    */
-   VectorExtrudeCoefficient(Mesh *m, VectorCoefficient &s, int n_)
-      : VectorCoefficient(s.GetVDim()), n(n_), mesh_in(m), sol_in(s)
-   { MFEM_VERIFY(n > 0, "Number of transverse elements must be positive!"); }
-
-   void Eval(Vector &v, ElementTransformation &T,
-             const IntegrationPoint &ip) override;
-   using VectorCoefficient::Eval;
-
-   virtual ~VectorExtrudeCoefficient() { }
-};
-
-/// Extrude a 1D GridFunction, after extruding the mesh with Extrude1D()
-/**
- * @param mesh      1D mesh
- * @param mesh2d    extruded mesh
- * @param sol       grid function
- * @param ny        number of transverse elements of the extruded mesh
- */
+/// Extrude a scalar 1D GridFunction, after extruding the mesh with Extrude1D.
 GridFunction *Extrude1DGridFunction(Mesh *mesh, Mesh *mesh2d,
                                    GridFunction *sol, const int ny);

@@ -106,7 +106,9 @@ FindPointsGSLIB::FindPointsGSLIB()
   gsl_comm = new gslib::comm;
   cr       = new gslib::crystal;
 #ifdef MFEM_USE_MPI
-   if (!Mpi::IsInitialized()) { Mpi::Init(); }
+   int initialized = 0;
+   MPI_Initialized(&initialized);
+   if (!initialized) { MPI_Init(NULL, NULL); }
   MPI_Comm comm = MPI_COMM_WORLD;
   comm_init(gsl_comm, comm);
 #else
@@ -232,7 +234,7 @@ void FindPointsGSLIB::Setup(Mesh &m, const double bb_t, const double newt_tol,
 }

 void FindPointsGSLIB::FindPoints(const Vector &point_pos,
-                                 const int point_pos_ordering)
+                                 int point_pos_ordering)
 {
   MFEM_VERIFY(setupflag, "Use FindPointsGSLIB::Setup before finding points.");
   bool dev_mode = (point_pos.UseDevice() && Device::IsEnabled());
@@ -480,7 +482,7 @@ void FindPointsGSLIB::SetupDevice()
 }

 void FindPointsGSLIB::FindPointsOnDevice(const Vector &point_pos,
-                                         const int point_pos_ordering)
+                                         int point_pos_ordering)
 {
   if (!DEV.setup_device)
   {
@@ -488,7 +490,7 @@ void FindPointsGSLIB::FindPointsOnDevice(const Vector &point_pos,
   }
   DEV.find_device = true;

-   const unsigned int id = gsl_comm->id, np = gsl_comm->np;
+   const int id = gsl_comm->id, np = gsl_comm->np;

   gsl_mfem_ref.SetSize(points_cnt * dim);
   gsl_mfem_elem.SetSize(points_cnt);
@@ -503,13 +505,13 @@ void FindPointsGSLIB::FindPointsOnDevice(const Vector &point_pos,

   if (dim == 2)
   {
-      FindPointsLocal2(point_pos, point_pos_ordering, gsl_code, gsl_elem,
-                       gsl_ref, gsl_dist, points_cnt);
+      FindPointsLocal2(point_pos, point_pos_ordering, gsl_code, gsl_elem, gsl_ref,
+                       gsl_dist, points_cnt);
   }
   else
   {
-      FindPointsLocal3(point_pos, point_pos_ordering, gsl_code, gsl_elem,
-                       gsl_ref, gsl_dist, points_cnt);
+      FindPointsLocal3(point_pos, point_pos_ordering, gsl_code, gsl_elem, gsl_ref,
+                       gsl_dist, points_cnt);
   }

   // Sync from device to host
@@ -650,7 +652,7 @@ void FindPointsGSLIB::FindPointsOnDevice(const Vector &point_pos,
         {
            const int pp = hash_offset[i];
            /* don't send back to where it just came from */
-            if (static_cast<unsigned>(pp) == p->proc)
+            if (pp == p->proc)
            {
               continue;
            }
@@ -1066,7 +1068,7 @@ void FindPointsGSLIB::InterpolateOnDevice(const Vector &field_in_evec,
         sarray_transfer(struct evalOutPt_t, &outpt, proc, 1, cr);

         opt = (evalOutPt_t *)outpt.ptr;
-         for (size_t index = 0; index < outpt.n; index++)
+         for (int index = 0; index < outpt.n; index++)
         {
            int idx = ordering == Ordering::byNODES ?
                      opt->index + i*points_cnt :
@@ -1083,7 +1085,7 @@ void FindPointsGSLIB::InterpolateOnDevice(const Vector &field_in_evec,
 #else
 void FindPointsGSLIB::SetupDevice() {};
 void FindPointsGSLIB::FindPointsOnDevice(const Vector &point_pos,
-                                         const int point_pos_ordering) {};
+                                         int point_pos_ordering) {};
 void FindPointsGSLIB::InterpolateOnDevice(const Vector &field_in_evec,
                                          Vector &field_out,
                                          const int nel, const int ncomp,
@@ -1092,8 +1094,7 @@ void FindPointsGSLIB::InterpolateOnDevice(const Vector &field_in_evec,
 #endif

 void FindPointsGSLIB::FindPoints(Mesh &m, const Vector &point_pos,
-                                 const int point_pos_ordering,
-                                 const double bb_t,
+                                 int point_pos_ordering, const double bb_t,
                                 const double newt_tol, const int npt_max)
 {
   if (!setupflag || (mesh != &m) )
@@ -1104,28 +1105,16 @@ void FindPointsGSLIB::FindPoints(Mesh &m, const Vector &point_pos,
 }

 void FindPointsGSLIB::Interpolate(const Vector &point_pos,
-                                  const GridFunction &field_in,
-                                  Vector &field_out,
-                                  const int point_pos_ordering)
+                                  const GridFunction &field_in, Vector &field_out,
+                                  int point_pos_ordering)
 {
   FindPoints(point_pos, point_pos_ordering);
   Interpolate(field_in, field_out);
 }

-void FindPointsGSLIB::Interpolate(const Vector &point_pos,
-                                  const GridFunction &field_in,
-                                  Vector &field_out,
-                                  const int point_pos_ordering,
-                                  const int field_out_ordering)
-{
-   FindPoints(point_pos, point_pos_ordering);
-   Interpolate(field_in, field_out, field_out_ordering);
-}
-
 void FindPointsGSLIB::Interpolate(Mesh &m, const Vector &point_pos,
-                                  const GridFunction &field_in,
-                                  Vector &field_out,
-                                  const int point_pos_ordering)
+                                  const GridFunction &field_in, Vector &field_out,
+                                  int point_pos_ordering)
 {
   FindPoints(m, point_pos, point_pos_ordering);
   Interpolate(field_in, field_out);
@@ -1411,7 +1400,7 @@ void FindPointsGSLIB::SetupSplitMeshesAndIntegrationRules(const int order)
 {
   MFEM_VERIFY(mesh, "Setup FindPointsGSLIB with mesh first.");
   const int dof1D = order+1;
-   dim = mesh->Dimension();
+   const int dim = mesh->Dimension();

   SetupSplitMeshes();
   if (dim == 2)
@@ -1481,7 +1470,7 @@ void FindPointsGSLIB::SetupSplitMeshesAndIntegrationRules(const int order)
 }

 void FindPointsGSLIB::GetNodalValues(const GridFunction *gf_in,
-                                     Vector &node_vals) const
+                                     Vector &node_vals)
 {
   const GridFunction *nodes     = gf_in;
   const FiniteElementSpace *fes = nodes->FESpace();
@@ -1769,13 +1758,6 @@ void FindPointsGSLIB::MapRefPosAndElemIndices()

 void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
                                  Vector &field_out)
-{
-   Interpolate(field_in, field_out, field_in.FESpace()->GetOrdering());
-}
-
-void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
-                                  Vector &field_out,
-                                  const int field_out_ordering)
 {
   const int  gf_order   = field_in.FESpace()->GetMaxElementOrder(),
              mesh_order = mesh->GetNodalFESpace()->GetMaxElementOrder();
@@ -1818,7 +1800,7 @@ void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
      const int maxOrder = field_in.FESpace()->GetMaxElementOrder();

      InterpolateOnDevice(node_vals, field_out, NE_split_total, ncomp,
-                          maxOrder+1, field_out_ordering);
+                          maxOrder+1, field_in.FESpace()->GetOrdering());
      return;
 #endif
   }
@@ -1830,13 +1812,12 @@ void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
       field_in.FESpace()->IsVariableOrder() ==
       mesh->GetNodalFESpace()->IsVariableOrder())
   {
-      InterpolateH1(field_in, field_out, field_out_ordering);
+      InterpolateH1(field_in, field_out);
      return;
   }
   else
   {
-      InterpolateGeneral(field_in, field_out,
-                         field_out_ordering);
+      InterpolateGeneral(field_in, field_out);
      if (!fec_l2 || avgtype == AvgType::NONE) { return; }
   }

@@ -1880,11 +1861,11 @@ void FindPointsGSLIB::Interpolate(const GridFunction &field_in,

      if (gf_order_h1 == mesh_order) // basis is GaussLobatto by default
      {
-         InterpolateH1(field_in_h1, field_out_l2, field_out_ordering);
+         InterpolateH1(field_in_h1, field_out_l2);
      }
      else
      {
-         InterpolateGeneral(field_in_h1, field_out_l2, field_out_ordering);
+         InterpolateGeneral(field_in_h1, field_out_l2);
      }

      // Copy interpolated values for the points on element border
@@ -1892,7 +1873,7 @@ void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
      {
         for (int i = 0; i < indl2.Size(); i++)
         {
-            int idx = field_out_ordering == Ordering::byNODES?
+            int idx = field_in_h1.FESpace()->GetOrdering() == Ordering::byNODES?
                      indl2[i] + j*points_cnt:
                      indl2[i]*ncomp + j;
            field_out(idx) = field_out_l2(idx);
@@ -1902,8 +1883,7 @@ void FindPointsGSLIB::Interpolate(const GridFunction &field_in,
 }

 void FindPointsGSLIB::InterpolateH1(const GridFunction &field_in,
-                                    Vector &field_out,
-                                    const int field_out_ordering)
+                                    Vector &field_out)
 {
   FiniteElementSpace ind_fes(mesh, field_in.FESpace()->FEColl());
   if (field_in.FESpace()->IsVariableOrder())
@@ -1933,8 +1913,7 @@ void FindPointsGSLIB::InterpolateH1(const GridFunction &field_in,
                dataptrout = i*points_cnt;
      if (field_in.FESpace()->GetOrdering() == Ordering::byNODES)
      {
-         field_in_scalar.NewDataAndSize(field_in.GetData()+dataptrin,
-                                        points_fld);
+         field_in_scalar.NewDataAndSize(field_in.GetData()+dataptrin, points_fld);
      }
      else
      {
@@ -1966,7 +1945,7 @@ void FindPointsGSLIB::InterpolateH1(const GridFunction &field_in,
                        (gslib::findpts_data_3 *)this->fdataD);
      }
   }
-   if (field_out_ordering == Ordering::byVDIM)
+   if (field_in.FESpace()->GetOrdering() == Ordering::byVDIM)
   {
      Vector field_out_temp = field_out;
      for (int i = 0; i < ncomp; i++)
@@ -1980,8 +1959,7 @@ void FindPointsGSLIB::InterpolateH1(const GridFunction &field_in,
 }

 void FindPointsGSLIB::InterpolateGeneral(const GridFunction &field_in,
-                                         Vector &field_out,
-                                         const int field_out_ordering)
+                                         Vector &field_out)
 {
   int ncomp   = field_in.VectorDim(),
       nptorig = points_cnt,
@@ -2001,7 +1979,7 @@ void FindPointsGSLIB::InterpolateGeneral(const GridFunction &field_in,
         if (dim == 3) { ip.z = gsl_mfem_ref(index*dim + 2); }
         Vector localval(ncomp);
         field_in.GetVectorValue(gsl_mfem_elem[index], ip, localval);
-         if (field_out_ordering == Ordering::byNODES)
+         if (field_in.FESpace()->GetOrdering() == Ordering::byNODES)
         {
            for (int i = 0; i < ncomp; i++)
            {
@@ -2036,10 +2014,7 @@ void FindPointsGSLIB::InterpolateGeneral(const GridFunction &field_in,
      for (int index = 0; index < npt; index++)
      {
         if (gsl_code[index] == 2) { continue; }
-         for (int d = 0; d < dim; ++d)
-         {
-            pt->r[d]= gsl_mfem_ref(index*dim + d);
-         }
+         for (int d = 0; d < dim; ++d) { pt->r[d]= gsl_mfem_ref(index*dim + d); }
         pt->index = index;
         pt->proc  = gsl_proc[index];
         pt->el    = gsl_mfem_elem[index];
@@ -2129,7 +2104,7 @@ void FindPointsGSLIB::InterpolateGeneral(const GridFunction &field_in,
            sdpt = (struct send_pt *)sendpt->ptr;
            for (int index = 0; index < static_cast<int>(sendpt->n); index++)
            {
-               int idx = field_out_ordering == Ordering::byNODES ?
+               int idx = field_in.FESpace()->GetOrdering() == Ordering::byNODES ?
                         sdpt->index + j*nptorig :
                         sdpt->index*ncomp + j;
               field_out(idx) = sdpt->ival;
@@ -2252,8 +2227,7 @@ void FindPointsGSLIB::DistributeInterpolatedValues(const Vector &int_vals,
      sarray_transfer(struct out_pt, outpt, proc, 1, cr);

      // Store received data
-      MFEM_VERIFY(outpt->n == static_cast<size_t>(points_cnt),
-                  "Incompatible size. Number of points "
+      MFEM_VERIFY(outpt->n == points_cnt, "Incompatible size. Number of points "
                  "received does not match the number of points originally "
                  "found using FindPoints.");

@@ -2272,7 +2246,7 @@ void FindPointsGSLIB::DistributeInterpolatedValues(const Vector &int_vals,
   }
 }

-void FindPointsGSLIB::GetAxisAlignedBoundingBoxes(Vector &aabb) const
+void FindPointsGSLIB::GetAxisAlignedBoundingBoxes(Vector &aabb)
 {
   MFEM_VERIFY(setupflag, "Call FindPointsGSLIB::Setup method first");
   auto *findptsData3 = (gslib::findpts_data_3 *)this->fdataD;
@@ -2343,7 +2317,7 @@ void FindPointsGSLIB::GetAxisAlignedBoundingBoxes(Vector &aabb) const
 }

 void FindPointsGSLIB::GetOrientedBoundingBoxes(DenseTensor &obbA, Vector &obbC,
-                                               Vector &obbV) const
+                                               Vector &obbV)
 {
   MFEM_VERIFY(setupflag, "Call FindPointsGSLIB::Setup method first");
   auto *findptsData3 = (gslib::findpts_data_3 *)this->fdataD;
@@ -2528,8 +2502,8 @@ void OversetFindPointsGSLIB::Setup(Mesh &m, const int meshid,
 }

 void OversetFindPointsGSLIB::FindPoints(const Vector &point_pos,
-                                        const Array<unsigned int> &point_id,
-                                        const int point_pos_ordering)
+                                        Array<unsigned int> &point_id,
+                                        int point_pos_ordering)
 {
   MFEM_VERIFY(setupflag, "Use OversetFindPointsGSLIB::Setup before "
               "finding points.");
@@ -2608,10 +2582,10 @@ void OversetFindPointsGSLIB::FindPoints(const Vector &point_pos,
 }

 void OversetFindPointsGSLIB::Interpolate(const Vector &point_pos,
-                                         const Array<unsigned int> &point_id,
+                                         Array<unsigned int> &point_id,
                                         const GridFunction &field_in,
                                         Vector &field_out,
-                                         const int point_pos_ordering)
+                                         int point_pos_ordering)
 {
   FindPoints(point_pos, point_id, point_pos_ordering);
   Interpolate(field_in, field_out);
@@ -2622,7 +2596,9 @@ GSOPGSLIB::GSOPGSLIB(Array<long long> &ids)
   gsl_comm = new gslib::comm;
   cr       = new gslib::crystal;
 #ifdef MFEM_USE_MPI
-   if (!Mpi::IsInitialized()) { Mpi::Init(); }
+   int initialized;
+   MPI_Initialized(&initialized);
+   if (!initialized) { MPI_Init(NULL, NULL); }
   MPI_Comm comm = MPI_COMM_WORLD;
   comm_init(gsl_comm, comm);
 #else
@@ -119,13 +119,11 @@ protected:
   } DEV;

   /// Use GSLIB for communication and interpolation
-   virtual void InterpolateH1(const GridFunction &field_in, Vector &field_out,
-                              const int field_out_ordering);
+   virtual void InterpolateH1(const GridFunction &field_in, Vector &field_out);
   /// Uses GSLIB Crystal Router for communication followed by MFEM's
   /// interpolation functions
   virtual void InterpolateGeneral(const GridFunction &field_in,
-                                   Vector &field_out,
-                                   const int field_out_ordering);
+                                   Vector &field_out);

   /// Since GSLIB is designed to work with quads/hexes, we split every
   /// triangle/tet/prism/pyramid element into quads/hexes.
@@ -142,7 +140,7 @@ protected:
   virtual void SetupSplitMeshesAndIntegrationRules(const int order);

   /// Get GridFunction value at the points expected by GSLIB.
-   virtual void GetNodalValues(const GridFunction *gf_in, Vector &node_vals) const;
+   virtual void GetNodalValues(const GridFunction *gf_in, Vector &node_vals);

   /// Map {r,s,t} coordinates from [-1,1] to [0,1] for MFEM. For simplices,
   /// find the original element number (that was split into micro quads/hexes)
@@ -184,7 +182,7 @@ protected:
       These positions can be ordered byNodes: (XXX...,YYY...,ZZZ) or
       byVDim: (XYZ,XYZ,....XYZ) specified by @a point_pos_ordering. */
   void FindPointsOnDevice(const Vector &point_pos,
-                           const int point_pos_ordering = Ordering::byNODES);
+                           int point_pos_ordering = Ordering::byNODES);

   /** Interpolation of field values at prescribed reference space positions.
       @param[in] field_in_evec E-vector of grid function to be interpolated.
@@ -202,19 +200,13 @@ protected:
                            const int dof1dsol, const int ordering);

 public:
-   /// Serial constructor
   FindPointsGSLIB();
-
-   /// Serial constructor + setup with given Mesh (see \ref Setup)
   FindPointsGSLIB(Mesh &mesh_in, const double bb_t = 0.1,
                   const double newt_tol = 1.0e-12,
                   const int npt_max = 256);

 #ifdef MFEM_USE_MPI
-   /// Constructor for ParMesh
   FindPointsGSLIB(MPI_Comm comm_);
-
-   /// Constructor + setup with given ParMesh (see \ref Setup)
   FindPointsGSLIB(ParMesh &mesh_in, const double bb_t = 0.1,
                   const double newt_tol = 1.0e-12,
                   const int npt_max = 256);
@@ -261,15 +253,10 @@ public:
       #gsl_dist        Distance between the sought and the found point
                        in physical space. */
   void FindPoints(const Vector &point_pos,
-                   const int point_pos_ordering = Ordering::byNODES);
-   /// Convenience function when point positions are in a ParticleVector
-   void FindPoints(const ParticleVector &point_pos)
-   {
-      FindPoints(point_pos, point_pos.GetOrdering());
-   }
+                   int point_pos_ordering = Ordering::byNODES);
   /// Setup FindPoints and search positions
   void FindPoints(Mesh &m, const Vector &point_pos,
-                   const int point_pos_ordering = Ordering::byNODES,
+                   int point_pos_ordering = Ordering::byNODES,
                   const double bb_t = 0.1, const double newt_tol = 1.0e-12,
                   const int npt_max = 256);

@@ -279,28 +266,20 @@ public:
                              \p field_in is in H1 and in the same space as the
                              mesh that was given to Setup().
       @param[out] field_out  Interpolated values. For points that are not found
-                              the value is set to #default_interp_value.
-                              The output ordering is determined from field_in.*/
+                              the value is set to #default_interp_value. */
   virtual void Interpolate(const GridFunction &field_in, Vector &field_out);
-   /// Interpolation of field values, with output ordering specification.
-   virtual void Interpolate(const GridFunction &field_in, Vector &field_out,
-                            const int field_out_ordering);
   /** Search positions and interpolate. The ordering (byNODES or byVDIM) of
       the output values in \p field_out corresponds to the ordering used
       in the input GridFunction \p field_in. */
   void Interpolate(const Vector &point_pos, const GridFunction &field_in,
                    Vector &field_out,
-                    const int point_pos_ordering = Ordering::byNODES);
-   /// Search positions and interpolate with given point and output ordering.
-   void Interpolate(const Vector &point_pos, const GridFunction &field_in,
-                    Vector &field_out, const int point_pos_ordering,
-                    const int field_out_ordering);
+                    int point_pos_ordering = Ordering::byNODES);
   /** Setup FindPoints, search positions and interpolate. The ordering (byNODES
       or byVDIM) of the output values in \p field_out corresponds to the
       ordering used in the input GridFunction \p field_in. */
   void Interpolate(Mesh &m, const Vector &point_pos,
                    const GridFunction &field_in, Vector &field_out,
-                    const int point_pos_ordering = Ordering::byNODES);
+                    int point_pos_ordering = Ordering::byNODES);

   /// Average type to be used for L2 functions in-case a point is located at
   /// an element boundary where the function might be multi-valued.
@@ -397,7 +376,7 @@ public:
   /// The size of the returned vector is (nel x nverts x dim), where nel is the
   /// number of elements (after splitting for simplcies), nverts is number of
   /// vertices (4 in 2D, 8 in 3D), and dim is the spatial dimension.
-   void GetAxisAlignedBoundingBoxes(Vector &aabb) const;
+   void GetAxisAlignedBoundingBoxes(Vector &aabb);

   /// Return the oriented bounding boxes (OBB) computed during \ref Setup.
   /// Each OBB is represented using the inverse transformation (A^{-1}) and
@@ -407,8 +386,7 @@ public:
   /// size (dim x dim x nel), and the OBB centers are returned in \p obbC,
   /// a vector of size (nel x dim). The vertices of the OBBs are returned in
   /// \p obbV, a vector of size (nel x nverts x dim) .
-   void GetOrientedBoundingBoxes(DenseTensor &obbA, Vector &obbC,
-                                 Vector &obbV) const;
+   void GetOrientedBoundingBoxes(DenseTensor &obbA, Vector &obbC, Vector &obbV);
 };

 /** \brief OversetFindPointsGSLIB enables use of findpts for arbitrary number of
@@ -468,14 +446,13 @@ public:
                                       byNodes: (XXX...,YYY...,ZZZ) or
                                       byVDim: (XYZ,XYZ,....XYZ) */
   void FindPoints(const Vector &point_pos,
-                   const Array<unsigned int> &point_id,
-                   const int point_pos_ordering = Ordering::byNODES);
+                   Array<unsigned int> &point_id,
+                   int point_pos_ordering = Ordering::byNODES);

   /** Search positions and interpolate */
-   void Interpolate(const Vector &point_pos,
-                    const Array<unsigned int> &point_id,
+   void Interpolate(const Vector &point_pos, Array<unsigned int> &point_id,
                    const GridFunction &field_in, Vector &field_out,
-                    const int point_pos_ordering = Ordering::byNODES);
+                    int point_pos_ordering = Ordering::byNODES);
   using FindPointsGSLIB::Interpolate;
 };

@@ -254,7 +254,7 @@ get_edge(const double *elx[2], const double *wtend, int ei,
      edge.dxdn[d] = workspace + (2 + d) * pN; //dxdn and dydn at DOFs along edge
   }

-   if (static_cast<unsigned>(side_init) != (1u << ei))
+   if (side_init != (1u << ei))
   {
 #define ELX(d, j, k) elx[d][j + k * pN] // assumes lexicographic ordering
      for (int d = 0; d < 2; ++d)
@@ -294,7 +294,7 @@ get_face(const double *elx[3], const double *wtend, int fi, double *workspace,
      face.dxdn[d] = workspace+(3+d)*p_Nfr;
   }

-   if (static_cast<unsigned>(side_init) != (1u << fi))
+   if (side_init != (1u << fi))
   {
      const int e_stride[3] = {1, pN, pN*pN};
 #define ELX(d, j, k, l) elx[d][j*e_stride[d1]+k*e_stride[d2]+l*e_stride[dn]]
@@ -342,7 +342,7 @@ get_edge(const double *elx[3], const double *wtend, int ei, double *workspace,

   if (jidx >= 3*pN) { return edge; }

-   if (static_cast<unsigned>(side_init) != (64u << ei))
+   if (side_init != (64u << ei))
   {
      const int e_stride[3] = {1, pN, pN*pN};
 #define ELX(d, j, k, l) elx[d][j*e_stride[de]+k*e_stride[dn1]+l*e_stride[dn2]]
@@ -789,6 +789,7 @@ void Hybridization::ComputeH()
   }
   else
   {
+      // TODO: add ones on the diagonal of zero rows
      V->Finalize();
      Array<HYPRE_BigInt> V_J(V->NumNonZeroElems());
      MFEM_ASSERT(c_pfes, "");
@@ -822,13 +823,6 @@ void Hybridization::ComputeH()
      MFEM_VERIFY(pH.Type() != Operator::PETSC_MATIS, "To be implemented");
      pH.MakePtAP(plpH, pP);
      delete lpH;
-
-      HypreParMatrix *hH = pH.As<HypreParMatrix>();
-      MFEM_ASSERT(hH, "");
-
-      SparseMatrix H_diag;
-      hH->GetDiag(H_diag);
-      H_diag.SetDiagIdentity();
   }
 #endif
 }
@@ -14,11 +14,8 @@

 #include "../config/config.hpp"
 #include "../general/array.hpp"
-#include "../linalg/operator.hpp"
 #include "../linalg/vector.hpp"

-#include <memory>
-
 namespace mfem
 {

@@ -48,30 +45,15 @@ protected:
   Array<int> hat_dof_gather_map;
   Array<DofType> hat_dof_marker;

-   Array<int> el_to_face; ///< Element to face connectivity.
-   Array<int> el_face_offsets; ///< Per-element offsets into @a el_to_face.
-   Array<int> face_to_el; ///< Face-to-element connectivity.
-   Array<int> face_face_offsets; ///< Face-to-face offsets.
-
-   int n_el_face; ///< Total number of element-to-face connections.
-   int n_face_face; ///< Total number of face-to-face connections.
-
+   Array<int> el_to_face;
+   Array<int> face_to_el;
   Vector Ct_mat; ///< Constraint matrix (transposed) stored element-wise.

-   /// @name For parallel non-conforming meshes
-   ///@{
-   std::unique_ptr<Operator> P_pc; ///< Partially conforming prolongation.
-   std::unique_ptr<Operator> P_nbr; ///< Face-neighbor prolongation.
-   ///@}
-
   Array<int> idofs, bdofs;

   Vector Ahat, Ahat_ii, Ahat_ib, Ahat_bi, Ahat_bb;
   Array<int> Ahat_ii_piv, Ahat_bb_piv;

-   /// Return the (partially) conforming prolongation on the constraint space.
-   const Operator &GetProlongation() const;
-
 public:
   /// Construct the constraint matrix.
   void ConstructC();
@@ -1004,16 +1004,13 @@ inline void SmemPADiffusionApply3D(const int NE,
   const int max_d1d = T_D1D ? T_D1D : DeviceDofQuadLimits::Get().MAX_D1D;
   MFEM_VERIFY(D1D <= max_d1d, "");
   MFEM_VERIFY(Q1D <= max_q1d, "");
-   const auto b = Reshape(b_.Read(), Q1D, D1D);
-   const auto g = Reshape(g_.Read(), Q1D, D1D);
-   const auto d = Reshape(d_.Read(), Q1D, Q1D, Q1D, symmetric ? 6 : 9, NE);
-   const auto x = Reshape(x_.Read(), D1D, D1D, D1D, NE);
+   auto b = Reshape(b_.Read(), Q1D, D1D);
+   auto g = Reshape(g_.Read(), Q1D, D1D);
+   auto d = Reshape(d_.Read(), Q1D, Q1D, Q1D, symmetric ? 6 : 9, NE);
+   auto x = Reshape(x_.Read(), D1D, D1D, D1D, NE);
   auto y = Reshape(y_.ReadWrite(), D1D, D1D, D1D, NE);
   MFEM_VERIFY(D1D <= Q1D, "THREAD_DIRECT requires D1D <= Q1D");
-
-   mfem::forall_3D<T_Q1D*T_Q1D*T_Q1D>(NE,
-                                      Q1D, Q1D, Q1D,
-                                      [=] MFEM_HOST_DEVICE (int e)
+   mfem::forall_3D(NE, Q1D, Q1D, Q1D, [=] MFEM_HOST_DEVICE (int e)
   {
      const int D1D = T_D1D ? T_D1D : d1d;
      const int Q1D = T_Q1D ? T_Q1D : q1d;
@@ -197,21 +197,15 @@ static void EAHdivAssemble3D(const int NE,
      // Assemble (one row per thread)
      MFEM_FOREACH_THREAD(idx_i, x, NDOF)
      {
-         // NOTE: due to an llvm backend bug, usage of the modulus operator
-         // has been removed from this foreach section.
         const int ic = idx_i / NDOF_C;
-         const int idx_ii = idx_i - ic * NDOF_C; // idx_i % NDOF_C
+         const int idx_ii = idx_i % NDOF_C;

         const int nx_i = (ic == 0) ? D1D : D1D-1;
         const int ny_i = (ic == 1) ? D1D : D1D-1;

-         const int qx_i = idx_ii / nx_i;
-         const int ix = idx_ii - qx_i * nx_i; // idx_ii % nx_i
-
-         const int qy_i = qx_i / ny_i;
-         const int iy = qx_i - qy_i * ny_i; // (idx_ii / nx_i) % ny_i
-
-         const int iz = qy_i; // (idx_ii / nx_i) / ny_i
+         const int ix = idx_ii % nx_i;
+         const int iy = (idx_ii / nx_i) % ny_i;
+         const int iz = (idx_ii / nx_i) / ny_i;

         const real_t (&Bi1)[MQ1][MD1] = (ic == 0) ? r_Bc : r_Bo;
         const real_t (&Bi2)[MQ1][MD1] = (ic == 1) ? r_Bc : r_Bo;
@@ -220,18 +214,14 @@ static void EAHdivAssemble3D(const int NE,
         for (int idx_j = 0; idx_j < NDOF; ++idx_j)
         {
            const int jc = idx_j / NDOF_C;
-            const int idx_jj = idx_j - jc * NDOF_C; // idx_j % NDOF_C
+            const int idx_jj = idx_j % NDOF_C;

            const int nx_j = (jc == 0) ? D1D : D1D-1;
            const int ny_j = (jc == 1) ? D1D : D1D-1;

-            const int qx_j = idx_jj / nx_j;
-            const int jx = idx_jj - qx_j * nx_j; // idx_jj % nx_j
-
-            const int qy_j = qx_j / ny_j;
-            const int jy = qx_j - qy_j * ny_j; // (idx_jj / nx_j) % ny_j
-
-            const int jz = qy_j; // (idx_jj / nx_j) / ny_j
+            const int jx = idx_jj % nx_j;
+            const int jy = (idx_jj / nx_j) % ny_j;
+            const int jz = (idx_jj / nx_j) / ny_j;

            const real_t (&Bj1)[MQ1][MD1] = (jc == 0) ? r_Bc : r_Bo;
            const real_t (&Bj2)[MQ1][MD1] = (jc == 1) ? r_Bc : r_Bo;
@@ -181,12 +181,6 @@ constexpr int NBZ(int D1D)
 {
   return ipow(2, D(D1D) >= 0 ? D(D1D) : 0);
 }
-constexpr int NBZ3D(int MDQ)
-{
-   return MDQ > 0 ? std::min<int>(
-             (128 + MDQ * MDQ * MDQ - 1) / (MDQ * MDQ * MDQ), 64)
-          : 1;
-}
 }

 // Shared memory PA Mass Diagonal 2D kernel
@@ -810,23 +804,19 @@ void PAMassApply3D_Element(const int e,
   }
 }

-template <int T_D1D, int T_Q1D, int TBATCH, bool ACCUMULATE = true>
-MFEM_HOST_DEVICE inline void
-SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
-                          const real_t *d_, const real_t *x_, real_t *y_,
-                          int d1d = 0, int q1d = 0)
+template<int T_D1D, int T_Q1D, bool ACCUMULATE = true>
+MFEM_HOST_DEVICE inline
+void SmemPAMassApply3D_Element(const int e,
+                               const int NE,
+                               const real_t *b_,
+                               const real_t *d_,
+                               const real_t *x_,
+                               real_t *y_,
+                               const int d1d = 0,
+                               const int q1d = 0)
 {
-   static_assert(TBATCH > 0, "TBATCH must be positive");
-#if defined(__CUDA_ARCH__) || defined(__HIP_DEVICE_COMPILE__)
-   constexpr int tbatch = TBATCH;
-   const int tidz = MFEM_THREAD_ID(z);
-#else
-   // host always batch size 1
-   constexpr int tbatch = 1;
-   constexpr int tidz = 0;
-#endif
-   const int D1D = T_D1D ? T_D1D : d1d;
-   const int Q1D = T_Q1D ? T_Q1D : q1d;
+   constexpr int D1D = T_D1D ? T_D1D : d1d;
+   constexpr int Q1D = T_Q1D ? T_Q1D : q1d;
   constexpr int MQ1 = T_Q1D ? T_Q1D : DofQuadLimits::MAX_Q1D;
   constexpr int MD1 = T_D1D ? T_D1D : DofQuadLimits::MAX_D1D;
   constexpr int MDQ = (MQ1 > MD1) ? MQ1 : MD1;
@@ -839,37 +829,33 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
   MFEM_SHARED real_t sDQ[MQ1*MD1];
   real_t (*B)[MD1] = (real_t (*)[MD1]) sDQ;
   real_t (*Bt)[MQ1] = (real_t (*)[MQ1]) sDQ;
-   MFEM_SHARED real_t sm0[tbatch][MDQ*MDQ*MDQ];
-   MFEM_SHARED real_t sm1[tbatch][MDQ*MDQ*MDQ];
-   real_t (*X)[MD1][MD1]   = (real_t (*)[MD1][MD1]) (sm0+tidz);
-   real_t (*DDQ)[MD1][MQ1] = (real_t (*)[MD1][MQ1]) (sm1+tidz);
-   real_t (*DQQ)[MQ1][MQ1] = (real_t (*)[MQ1][MQ1]) (sm0+tidz);
-   real_t (*QQQ)[MQ1][MQ1] = (real_t (*)[MQ1][MQ1]) (sm1+tidz);
-   real_t (*QQD)[MQ1][MD1] = (real_t (*)[MQ1][MD1]) (sm0+tidz);
-   real_t (*QDD)[MD1][MD1] = (real_t (*)[MD1][MD1]) (sm1+tidz);
-   MFEM_FOREACH_THREAD(dy, y, D1D)
+   MFEM_SHARED real_t sm0[MDQ*MDQ*MDQ];
+   MFEM_SHARED real_t sm1[MDQ*MDQ*MDQ];
+   real_t (*X)[MD1][MD1]   = (real_t (*)[MD1][MD1]) sm0;
+   real_t (*DDQ)[MD1][MQ1] = (real_t (*)[MD1][MQ1]) sm1;
+   real_t (*DQQ)[MQ1][MQ1] = (real_t (*)[MQ1][MQ1]) sm0;
+   real_t (*QQQ)[MQ1][MQ1] = (real_t (*)[MQ1][MQ1]) sm1;
+   real_t (*QQD)[MQ1][MD1] = (real_t (*)[MQ1][MD1]) sm0;
+   real_t (*QDD)[MD1][MD1] = (real_t (*)[MD1][MD1]) sm1;
+   MFEM_FOREACH_THREAD(dy,y,D1D)
   {
-      MFEM_FOREACH_THREAD(dx, x, D1D)
+      MFEM_FOREACH_THREAD(dx,x,D1D)
      {
         MFEM_UNROLL(MD1)
         for (int dz = 0; dz < D1D; ++dz)
         {
-            X[dz][dy][dx] = x(dx, dy, dz, e);
+            X[dz][dy][dx] = x(dx,dy,dz,e);
         }
      }
-      MFEM_FOREACH_THREAD(dx, x, Q1D) { B[dx][dy] = b(dx, dy); }
-   }
-   if (tidz == 0)
-   {
-      MFEM_FOREACH_THREAD(dy, y, D1D)
+      MFEM_FOREACH_THREAD(dx,x,Q1D)
      {
-         MFEM_FOREACH_THREAD(dx, x, Q1D) { B[dx][dy] = b(dx, dy); }
+         B[dx][dy] = b(dx,dy);
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(dy, y, D1D)
+   MFEM_FOREACH_THREAD(dy,y,D1D)
   {
-      MFEM_FOREACH_THREAD(qx, x, Q1D)
+      MFEM_FOREACH_THREAD(qx,x,Q1D)
      {
         real_t u[D1D];
         MFEM_UNROLL(MD1)
@@ -894,9 +880,9 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(qy, y, Q1D)
+   MFEM_FOREACH_THREAD(qy,y,Q1D)
   {
-      MFEM_FOREACH_THREAD(qx, x, Q1D)
+      MFEM_FOREACH_THREAD(qx,x,Q1D)
      {
         real_t u[D1D];
         MFEM_UNROLL(MD1)
@@ -921,9 +907,9 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(qy, y, Q1D)
+   MFEM_FOREACH_THREAD(qy,y,Q1D)
   {
-      MFEM_FOREACH_THREAD(qx, x, Q1D)
+      MFEM_FOREACH_THREAD(qx,x,Q1D)
      {
         real_t u[Q1D];
         MFEM_UNROLL(MQ1)
@@ -943,22 +929,22 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
         MFEM_UNROLL(MQ1)
         for (int qz = 0; qz < Q1D; qz++)
         {
-            QQQ[qz][qy][qx] = u[qz] * d(qx, qy, qz, e);
+            QQQ[qz][qy][qx] = u[qz] * d(qx,qy,qz,e);
         }
      }
   }
   MFEM_SYNC_THREAD;
-   if (tidz == 0)
+   MFEM_FOREACH_THREAD(di,y,D1D)
   {
-      MFEM_FOREACH_THREAD(di, y, D1D)
+      MFEM_FOREACH_THREAD(q,x,Q1D)
      {
-         MFEM_FOREACH_THREAD(q, x, Q1D) { Bt[di][q] = b(q, di); }
+         Bt[di][q] = b(q,di);
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(qy, y, Q1D)
+   MFEM_FOREACH_THREAD(qy,y,Q1D)
   {
-      MFEM_FOREACH_THREAD(dx, x, D1D)
+      MFEM_FOREACH_THREAD(dx,x,D1D)
      {
         real_t u[Q1D];
         MFEM_UNROLL(MQ1)
@@ -983,9 +969,9 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(dy, y, D1D)
+   MFEM_FOREACH_THREAD(dy,y,D1D)
   {
-      MFEM_FOREACH_THREAD(dx, x, D1D)
+      MFEM_FOREACH_THREAD(dx,x,D1D)
      {
         real_t u[Q1D];
         MFEM_UNROLL(MQ1)
@@ -1010,9 +996,9 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
      }
   }
   MFEM_SYNC_THREAD;
-   MFEM_FOREACH_THREAD(dy, y, D1D)
+   MFEM_FOREACH_THREAD(dy,y,D1D)
   {
-      MFEM_FOREACH_THREAD(dx, x, D1D)
+      MFEM_FOREACH_THREAD(dx,x,D1D)
      {
         real_t u[D1D];
         MFEM_UNROLL(MD1)
@@ -1034,11 +1020,11 @@ SmemPAMassApply3D_Element(const int e, const int NE, const real_t *b_,
         {
            if (ACCUMULATE)
            {
-               y(dx, dy, dz, e) += u[dz];
+               y(dx,dy,dz,e) += u[dz];
            }
            else
            {
-               y(dx, dy, dz, e) = u[dz];
+               y(dx,dy,dz,e) = u[dz];
            }
         }
      }
@@ -1129,8 +1115,8 @@ inline void PAMassApply3D(const int NE,
   });
 }

-// Shared memory PA Mass Apply 3D kernel
-template<int T_D1D = 0, int T_Q1D = 0, int TBATCH=1>
+// Shared memory PA Mass Apply 2D kernel
+template<int T_D1D = 0, int T_Q1D = 0>
 inline void SmemPAMassApply3D(const int NE,
                              const Array<real_t> &b_,
                              const Array<real_t> &bt_,
@@ -1140,9 +1126,6 @@ inline void SmemPAMassApply3D(const int NE,
                              const int d1d = 0,
                              const int q1d = 0)
 {
-   static_assert(T_D1D > 0, "T_D1D must be positive");
-   static_assert(T_Q1D > 0, "T_Q1D must be positive");
-   static_assert(TBATCH > 0, "TBATCH must be positive");
   MFEM_CONTRACT_VAR(bt_);
   const int D1D = T_D1D ? T_D1D : d1d;
   const int Q1D = T_Q1D ? T_Q1D : q1d;
@@ -1150,15 +1133,13 @@ inline void SmemPAMassApply3D(const int NE,
   const int max_d1d = T_D1D ? T_D1D : DeviceDofQuadLimits::Get().MAX_D1D;
   MFEM_VERIFY(D1D <= max_d1d, "");
   MFEM_VERIFY(Q1D <= max_q1d, "");
-   const auto b = b_.Read();
-   const auto d = d_.Read();
-   const auto x = x_.Read();
+   auto b = b_.Read();
+   auto d = d_.Read();
+   auto x = x_.Read();
   auto y = y_.ReadWrite();
-   mfem::forall_2D_batch<T_Q1D * T_Q1D * TBATCH>(NE, Q1D, Q1D, TBATCH,
-                                                 [=] MFEM_HOST_DEVICE(int e)
+   mfem::forall_2D(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE (int e)
   {
-      internal::SmemPAMassApply3D_Element<T_D1D, T_Q1D, TBATCH>(e, NE, b, d, x,
-                                                                y, d1d, q1d);
+      internal::SmemPAMassApply3D_Element<T_D1D,T_Q1D>(e, NE, b, d, x, y, d1d, q1d);
   });
 }

@@ -1175,8 +1156,8 @@ inline void EAMassAssemble1D(const int NE,
   const int Q1D = T_Q1D ? T_Q1D : q1d;
   MFEM_VERIFY(D1D <= DeviceDofQuadLimits::Get().MAX_D1D, "");
   MFEM_VERIFY(Q1D <= DeviceDofQuadLimits::Get().MAX_Q1D, "");
-   const auto B = Reshape(basis.Read(), Q1D, D1D);
-   const auto D = Reshape(padata.Read(), Q1D, NE);
+   auto B = Reshape(basis.Read(), Q1D, D1D);
+   auto D = Reshape(padata.Read(), Q1D, NE);
   auto M = Reshape(add ? eadata.ReadWrite() : eadata.Write(), D1D, D1D, NE);
   mfem::forall_2D(NE, D1D, D1D, [=] MFEM_HOST_DEVICE (int e)
   {
@@ -1413,16 +1394,7 @@ ApplyKernelType MassIntegrator::ApplyPAKernels::Kernel()
 {
   if constexpr (DIM == 1) { return internal::PAMassApply1D; }
   else if constexpr (DIM == 2) { return internal::SmemPAMassApply2D<T_D1D,T_Q1D>; }
-   else if constexpr (DIM == 3)
-   {
-      constexpr int MDQ = T_D1D >= T_Q1D ? T_D1D : T_Q1D;
-      // max 64 threads in z limit in cuda and hip
-      if constexpr (MDQ > 0)
-      {
-         return internal::SmemPAMassApply3D<T_D1D, T_Q1D,
-                internal::mass::NBZ3D(MDQ)>;
-      }
-   }
+   else if constexpr (DIM == 3) { return internal::SmemPAMassApply3D<T_D1D, T_Q1D>; }
   MFEM_ABORT("");
 }

@@ -28,7 +28,7 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
   const FaceType ftype = FaceType::Interior;
   const int nf = mesh.GetNFbyType(ftype);

-   const Geometry::Type geom = mesh.GetTypicalFaceGeometry();
+   const Geometry::Type geom = mesh.GetFaceGeometry(0);
   const int trial_order = trial_fes.GetMaxElementOrder();
   const int test_order = test_fes.GetMaxElementOrder();
   const int qorder = test_order + trial_order - 1;
@@ -47,7 +47,7 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
      });
   }

-   const FiniteElement &trial_face_el = *trial_fes.GetTypicalTraceElement();
+   const FiniteElement &trial_face_el = *trial_fes.GetFaceElement(0);
   const auto maps = &trial_face_el.GetDofToQuad(ir, DofToQuad::TENSOR);
   const int ndof_face = trial_face_el.GetDof();

@@ -72,7 +72,7 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
      MFEM_ABORT("Unknown kernel.");
   }

-   const FiniteElement &test_el = *test_fes.GetTypicalFE();
+   const FiniteElement &test_el = *test_fes.GetFE(0);
   const int n_faces_per_el = 2*dim; // assuming tensor product
   // Get all the local face maps (mapping from lexicographic face index to
   // lexicographic volume index, depending on the local face index).
@@ -90,10 +90,10 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
   Array<int> face_info(nf * 4);
   {
      int fidx = 0;
-      for (int f = 0; f < mesh.GetNumFacesWithGhost(); ++f)
+      for (int f = 0; f < mesh.GetNumFaces(); ++f)
      {
         Mesh::FaceInformation finfo = mesh.GetFaceInformation(f);
-         if (!finfo.IsInterior() || finfo.IsNonconformingCoarse()) { continue; }
+         if (!finfo.IsInterior()) { continue; }
         face_info[0 + fidx*4] = finfo.element[0].local_face_id;
         face_info[1 + fidx*4] = finfo.element[0].orientation;
         face_info[2 + fidx*4] = finfo.element[1].local_face_id;
@@ -114,7 +114,7 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
   else
   {
      d_emat = emat.Write();
-      emat = 0.0; // Will execute on device, since Write() sets the device flag
+      mfem::forall(emat.Size(), [=] MFEM_HOST_DEVICE (int i) { d_emat[i] = 0.0; });
   }

   const auto face_mats = Reshape(mass_emat.Read(), ndof_face, ndof_face, nf);
@@ -133,104 +133,26 @@ void NormalTraceJumpIntegrator::AssembleEAInteriorFaces(
      }
   };

-   auto permute_face_2 = [=] MFEM_HOST_DEVICE(int local_face_1, int local_face_2,
-                                              int orient, int size1d, int index)
+   mfem::forall_3D(nf, ndof_face, ndof_face, 2, [=] MFEM_HOST_DEVICE (int f)
   {
-      if (dim == 2)
+      MFEM_FOREACH_THREAD(el_i, z, 2)
      {
-         return internal::PermuteFace2D(local_face_1, local_face_2, orient,
-                                        size1d, index);
-      }
-      else // dim == 3
-      {
-         return internal::PermuteFace3D(local_face_1, local_face_2, orient,
-                                        size1d, index);
-      }
-   };
-
-   if (mesh.Conforming())
-   {
-      mfem::forall_3D(nf, ndof_face, ndof_face, 2, [=] MFEM_HOST_DEVICE (int f)
-      {
-         MFEM_FOREACH_THREAD(el_i, z, 2)
+         const int lf_i = d_face_info(0, el_i, f);
+         const int orient = d_face_info(1, el_i, f);
+         // Loop over face indices in "native ordering"
+         MFEM_FOREACH_THREAD(i_lex, x, ndof_face)
         {
-            const int lf_i = d_face_info(0, el_i, f);
-            const int orient = d_face_info(1, el_i, f);
-            // Loop over face indices in "native ordering"
-            MFEM_FOREACH_THREAD(i_lex, x, ndof_face)
+            // Convert to lexicographic relative to the face itself
+            const int i_face = permute_face(lf_i, orient, d1d, i_lex);
+            // Convert from lexicographic face DOF to volume DOF
+            const int i = d_face_maps(i_lex, lf_i);
+            MFEM_FOREACH_THREAD(j, y, ndof_face)
            {
-               // Convert to lexicographic relative to the face itself
-               const int i_face = permute_face(lf_i, orient, d1d, i_lex);
-               // Convert from lexicographic face DOF to volume DOF
-               const int i = d_face_maps(i_lex, lf_i);
-               MFEM_FOREACH_THREAD(j, y, ndof_face)
-               {
-                  el_mats(i, j, el_i, f) += face_mats(i_face, j, f);
-               }
+               el_mats(i, j, el_i, f) += face_mats(i_face, j, f);
            }
         }
-      });
-   }
-   else
-   {
-      const InterpolationManager &interp =
-         test_fes.GetInterpolationManager(ElementDofOrdering::LEXICOGRAPHIC, ftype);
-
-      auto interp_configs = interp.GetFaceInterpConfig().Read();
-      const int nc_size = interp.GetNumInterpolators();
-      auto d_interp = Reshape(interp.GetInterpolators().Read(),
-                              ndof_face, ndof_face, nc_size);
-
-      mfem::forall(nf, [=] MFEM_HOST_DEVICE (int f)
-      {
-         const InterpConfig conf = interp_configs[f];
-         const int master_side = conf.master_side;
-         const int interp_index = conf.index;
-
-         const int lf_0 = d_face_info(0, 0, f);
-
-         for (int el_i = 0; el_i < 2; ++el_i)
-         {
-            const int lf_i = d_face_info(0, el_i, f);
-            const int orient = d_face_info(1, el_i, f);
-
-            for (int j = 0; j < ndof_face; j++)
-            {
-               for (int i_lex = 0; i_lex < ndof_face; i_lex++)
-               {
-                  real_t val = 0.0;
-                  if (conf.is_non_conforming && el_i == master_side)
-                  {
-                     // Interpolate from el_i (coarse element) to the fine face.
-                     // The mapping is given by d_interp, which uses indices
-                     // relative to element 0.
-
-                     // i0 is lexicographic relative to element 0
-                     const int i0 = permute_face_2(lf_i, lf_0, orient, d1d, i_lex);
-
-                     // k0 is lexicographic relative to element 0
-                     for (int k0 = 0; k0 < ndof_face; k0++)
-                     {
-                        // k is relative to the face itself
-                        const int k = permute_face(lf_0, orient, d1d, k0);
-                        val += d_interp(k0, i0, interp_index)
-                               * face_mats(k, j, f);
-                     }
-                  }
-                  else
-                  {
-                     // Convert to lexicographic relative to the face itself
-                     const int i_face = permute_face(lf_i, orient, d1d, i_lex);
-                     val = face_mats(i_face, j, f);
-                  }
-                  // Convert from lexicographic face DOF to volume DOF
-                  const int i = d_face_maps(i_lex, lf_i);
-                  el_mats(i, j, el_i, f) += val;
-               }
-            }
-         }
-      });
-   }
+      }
+   });
 }

 }
@@ -54,7 +54,7 @@ void SmemPAVectorDiffusionApply2D(const int NE,
   const auto XE = Reshape(x.Read(), D1D, D1D, SDIM, NE);
   auto YE = Reshape(y.ReadWrite(), D1D, D1D, SDIM, NE);

-   mfem::forall_2D<T_Q1D*T_Q1D>(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
+   mfem::forall_2D(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
   {
      constexpr int MD1 = T_D1D > 0 ? SetMaxOf(T_D1D) : DofQuadLimits::MAX_T1D;
      constexpr int MQ1 = T_Q1D > 0 ? SetMaxOf(T_Q1D) : DofQuadLimits::MAX_T1D;
@@ -120,7 +120,7 @@ void SmemPAVectorDiffusionApply3D(const int NE,
   const auto XE = Reshape(x.Read(), D1D, D1D, D1D, SDIM, NE);
   auto YE = Reshape(y.ReadWrite(), D1D, D1D, D1D, SDIM, NE);

-   mfem::forall_2D<T_Q1D*T_Q1D>(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
+   mfem::forall_2D(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
   {
      constexpr int MD1 = T_D1D > 0 ? SetMaxOf(T_D1D) : DofQuadLimits::MAX_T1D;
      constexpr int MQ1 = T_Q1D > 0 ? SetMaxOf(T_Q1D) : DofQuadLimits::MAX_T1D;
@@ -171,15 +171,15 @@ template<int DIM, int T_SDIM, int T_D1D, int T_Q1D>
 VectorDiffusionIntegrator::ApplyKernelType
 VectorDiffusionIntegrator::ApplyPAKernels::Kernel()
 {
-   if constexpr (DIM == 2)
+   if (DIM == 2)
   {
      return internal::SmemPAVectorDiffusionApply2D<T_SDIM, T_D1D, T_Q1D>;
   }
-   else if constexpr (DIM == 3)
+   else if (DIM == 3)
   {
      return internal::SmemPAVectorDiffusionApply3D<T_SDIM, T_D1D, T_Q1D>;
   }
-   MFEM_ABORT("Unsupported kernel");
+   else { MFEM_ABORT("Unsupported kernel"); }
 }

 inline VectorDiffusionIntegrator::ApplyKernelType
@@ -51,7 +51,7 @@ void SmemPAVectorMassApply2D(const int NE,
   const auto X = Reshape(x.Read(), D1D, D1D, VDIM, NE);
   auto Y = Reshape(y.ReadWrite(), D1D, D1D, VDIM, NE);

-   mfem::forall_2D<T_Q1D*T_Q1D>(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
+   mfem::forall_2D(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
   {
      constexpr int MD1 = T_D1D > 0 ? SetMaxOf(T_D1D) : DofQuadLimits::MAX_T1D;
      constexpr int MQ1 = T_Q1D > 0 ? SetMaxOf(T_Q1D) : DofQuadLimits::MAX_T1D;
@@ -119,7 +119,7 @@ void SmemPAVectorMassApply3D(const int NE,
   const auto X = Reshape(x.Read(), D1D, D1D, D1D, VDIM, NE);
   auto Y = Reshape(y.ReadWrite(), D1D, D1D, D1D, VDIM, NE);

-   mfem::forall_2D<T_Q1D*T_Q1D>(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
+   mfem::forall_2D(NE, Q1D, Q1D, [=] MFEM_HOST_DEVICE(int e)
   {
      constexpr int MD1 = T_D1D > 0 ? SetMaxOf(T_D1D) : DofQuadLimits::MAX_T1D;
      constexpr int MQ1 = T_Q1D > 0 ? SetMaxOf(T_Q1D) : DofQuadLimits::MAX_T1D;
@@ -182,15 +182,15 @@ template<int DIM, int T_D1D, int T_Q1D>
 VectorMassIntegrator::VectorMassAddMultPAType
 VectorMassIntegrator::VectorMassAddMultPA::Kernel()
 {
-   if constexpr (DIM == 2)
+   if (DIM == 2)
   {
      return internal::SmemPAVectorMassApply2D<T_D1D,T_Q1D>;
   }
-   else if constexpr (DIM == 3)
+   else if (DIM == 3)
   {
      return internal::SmemPAVectorMassApply3D<T_D1D, T_Q1D>;
   }
-   MFEM_ABORT("Unsupported kernel");
+   else { MFEM_ABORT("Unsupported kernel"); }
 }

 inline VectorMassIntegrator::VectorMassAddMultPAType
@@ -301,14 +301,18 @@ template <int DIM, int T_D1D, int T_Q1D>
 DomainLFIntegrator::AssembleKernelType
 DomainLFIntegrator::AssembleKernels::Kernel()
 {
-   if constexpr (DIM == 1) { return DLFEvalAssemble1D<T_D1D, T_Q1D>; }
-   if constexpr (DIM == 2) { return DLFEvalAssemble2D<T_D1D, T_Q1D>; }
-   if constexpr (DIM == 3) { return DLFEvalAssemble3D<T_D1D, T_Q1D>; }
+   switch (DIM)
+   {
+      case 1:
+         return DLFEvalAssemble1D<T_D1D, T_Q1D>;
+      case 2:
+         return DLFEvalAssemble2D<T_D1D, T_Q1D>;
+      case 3:
+         return DLFEvalAssemble3D<T_D1D, T_Q1D>;
+   }
   MFEM_ABORT("");
 }
-
 /// \endcond DO_NOT_DOCUMENT

 } // namespace mfem
-
-#endif // MFEM_LININTEG_DOMAIN_KERNELS_HPP
+#endif
@@ -43,52 +43,56 @@ public:
      index = i;
   }

-   void Set3w(const real_t x1, const real_t x2, const real_t x3, const real_t w)
-   { x = x1; y = x2; z = x3; weight = w; }
-   void Set2w(const real_t x1, const real_t x2, const real_t w)
-   { x = x1; y = x2; weight = w; }
-   void Set1w(const real_t x1, const real_t w)
-   { x = x1; weight = w; }
-
-   void Set3w(const real_t *p) { Set3w(p[0], p[1], p[2], p[3]); }
-   void Set2w(const real_t *p) { Set2w(p[0], p[1], p[2]); }
-   void Set1w(const real_t *p) { Set1w(p[0], p[1]); }
-
-   void Set3(const real_t x1, const real_t x2, const real_t x3)
-   { x = x1; y = x2; z = x3; }
-   void Set2(const real_t x1, const real_t x2)
-   { x = x1; y = x2; }
-   void Set1(const real_t x1)
-   { x = x1; }
-
-   void Set3(const real_t *p) { Set3(p[0], p[1], p[2]); }
-   void Set2(const real_t *p) { Set2(p[0], p[1]); }
-   void Set1(const real_t *p) { Set1(p[0]); }
-
-   void Set(const real_t x1, const real_t x2, const real_t x3, const real_t w)
-   { Set3w(x1, x2, x3, w); }
-
   void Set(const real_t *p, const int dim)
   {
      MFEM_ASSERT(1 <= dim && dim <= 3, "invalid dim: " << dim);
-      switch (dim)
+      x = p[0];
+      if (dim > 1)
      {
-         case 3: Set3(p); break;
-         case 2: Set2(p); break;
-         case 1: Set1(p); break;
+         y = p[1];
+         if (dim > 2)
+         {
+            z = p[2];
+         }
      }
   }

   void Get(real_t *p, const int dim) const
   {
      MFEM_ASSERT(1 <= dim && dim <= 3, "invalid dim: " << dim);
-      switch (dim)
+      p[0] = x;
+      if (dim > 1)
      {
-         case 3: p[2] = z;
-         case 2: p[1] = y;
-         case 1: p[0] = x;
+         p[1] = y;
+         if (dim > 2)
+         {
+            p[2] = z;
+         }
      }
   }
+
+   void Set(const real_t x1, const real_t x2, const real_t x3, const real_t w)
+   { x = x1; y = x2; z = x3; weight = w; }
+
+   void Set3w(const real_t *p) { x = p[0]; y = p[1]; z = p[2]; weight = p[3]; }
+
+   void Set3(const real_t x1, const real_t x2, const real_t x3)
+   { x = x1; y = x2; z = x3; }
+
+   void Set3(const real_t *p) { x = p[0]; y = p[1]; z = p[2]; }
+
+   void Set2w(const real_t x1, const real_t x2, const real_t w)
+   { x = x1; y = x2; weight = w; }
+
+   void Set2w(const real_t *p) { x = p[0]; y = p[1]; weight = p[2]; }
+
+   void Set2(const real_t x1, const real_t x2) { x = x1; y = x2; }
+
+   void Set2(const real_t *p) { x = p[0]; y = p[1]; }
+
+   void Set1w(const real_t x1, const real_t w) { x = x1; weight = w; }
+
+   void Set1w(const real_t *p) { x = p[0]; weight = p[1]; }
 };

 /// Class for an integration rule - an Array of IntegrationPoint.
@@ -121,6 +125,18 @@ private:
   void AddTriPoints3b(const int off, const real_t b, const real_t weight)
   { AddTriPoints3(off, (1. - b)/2., b, weight); }

+   void AddTriPoints3R(const int off, const real_t a, const real_t b,
+                       const real_t c, const real_t weight)
+   {
+      IntPoint(off + 0).Set2w(a, b, weight);
+      IntPoint(off + 1).Set2w(c, a, weight);
+      IntPoint(off + 2).Set2w(b, c, weight);
+   }
+
+   void AddTriPoints3R(const int off, const real_t a, const real_t b,
+                       const real_t weight)
+   { AddTriPoints3R(off, a, b, 1. - a - b, weight); }
+
   void AddTriPoints6(const int off, const real_t a, const real_t b,
                      const real_t c, const real_t weight)
   {
@@ -167,6 +183,14 @@ private:
      AddTetPoints3(off + 1, a, 1. - 3.*a, weight);
   }

+   // given b, add the permutations of (a,a,a,b), where 3*a + b = 1
+   void AddTetPoints4b(const int off, const real_t b, const real_t weight)
+   {
+      const real_t a = (1. - b)/3.;
+      IntPoint(off).Set(a, a, a, weight);
+      AddTetPoints3(off + 1, a, b, weight);
+   }
+
   // add the permutations of (a,a,b,b), 2*(a + b) = 1
   void AddTetPoints6(const int off, const real_t a, const real_t weight)
   {
@@ -185,37 +209,14 @@ private:
      AddTetPoints6(off + 6, a, bc, cb, weight);
   }

-   // add all 24 permutations of (a,b,c,d) where a+b+c+d = 1, all distinct
-   void AddTetPoints24(const int off, const real_t a, const real_t b,
-                       const real_t c, const real_t weight)
+   // given (b,c), add the permutations of (a,a,b,c), 2*a + b + c = 1
+   void AddTetPoints12bc(const int off, const real_t b, const real_t c,
+                         const real_t weight)
   {
-      const real_t d = 1. - a - b - c;
-      // all 24 permutations of 4 distinct barycentric coordinates
-      // permuting which coordinate goes to x, y, z (4th is 1-x-y-z)
-      IntPoint(off +  0).Set(a, b, c, weight);
-      IntPoint(off +  1).Set(a, b, d, weight);
-      IntPoint(off +  2).Set(a, c, b, weight);
-      IntPoint(off +  3).Set(a, c, d, weight);
-      IntPoint(off +  4).Set(a, d, b, weight);
-      IntPoint(off +  5).Set(a, d, c, weight);
-      IntPoint(off +  6).Set(b, a, c, weight);
-      IntPoint(off +  7).Set(b, a, d, weight);
-      IntPoint(off +  8).Set(b, c, a, weight);
-      IntPoint(off +  9).Set(b, c, d, weight);
-      IntPoint(off + 10).Set(b, d, a, weight);
-      IntPoint(off + 11).Set(b, d, c, weight);
-      IntPoint(off + 12).Set(c, a, b, weight);
-      IntPoint(off + 13).Set(c, a, d, weight);
-      IntPoint(off + 14).Set(c, b, a, weight);
-      IntPoint(off + 15).Set(c, b, d, weight);
-      IntPoint(off + 16).Set(c, d, a, weight);
-      IntPoint(off + 17).Set(c, d, b, weight);
-      IntPoint(off + 18).Set(d, a, b, weight);
-      IntPoint(off + 19).Set(d, a, c, weight);
-      IntPoint(off + 20).Set(d, b, a, weight);
-      IntPoint(off + 21).Set(d, b, c, weight);
-      IntPoint(off + 22).Set(d, c, a, weight);
-      IntPoint(off + 23).Set(d, c, b, weight);
+      const real_t a = (1. - b - c)/2.;
+      AddTetPoints3(off,     a, b, weight);
+      AddTetPoints3(off + 3, a, c, weight);
+      AddTetPoints6(off + 6, a, b, c, weight);
   }

 public:
@@ -14,7 +14,6 @@

 #include "../config/config.hpp"
 #include "kernel_reporter.hpp"
-#include "../general/hash_util.hpp"
 #include <unordered_map>
 #include <tuple>
 #include <type_traits>
@@ -87,6 +86,35 @@ namespace mfem
    }                                                                          \
  }

+/// @brief Hashes variadic packs for which each type contained in the variadic
+/// pack has a specialization of `std::hash` available.
+///
+/// For example, packs containing int, bool, enum values, etc.
+template<typename ...KernelParameters>
+struct KernelDispatchKeyHash
+{
+private:
+   template<int N>
+   size_t operator()(std::tuple<KernelParameters...> value) const { return 0; }
+
+   // The hashing formula here is taken directly from the Boost library, with
+   // the magic number 0x9e3779b9 chosen to minimize hashing collisions.
+   template<std::size_t N, typename THead, typename... TTail>
+   size_t operator()(std::tuple<KernelParameters...> value) const
+   {
+      constexpr int Index = N - sizeof...(TTail) - 1;
+      auto lhs_hash = std::hash<THead>()(std::get<Index>(value));
+      auto rhs_hash = operator()<N, TTail...>(value);
+      return lhs_hash^(rhs_hash + 0x9e3779b9 + (lhs_hash<<6) + (lhs_hash>>2));
+   }
+public:
+   /// Returns the hash of the given @a value.
+   size_t operator()(std::tuple<KernelParameters...> value) const
+   {
+      return operator()<sizeof...(KernelParameters),KernelParameters...>(value);
+   }
+};
+
 namespace internal { template<typename... Types> struct KernelTypeList { }; }

 template<typename... T> class KernelDispatchTable { };
@@ -100,8 +128,8 @@ class KernelDispatchTable<Kernels,
         internal::KernelTypeList<Params...>,
         internal::KernelTypeList<OptParams...>>
 {
-   using TableType =
-      std::unordered_map<std::tuple<Params...>, Signature, TupleHasher>;
+   using TableType = std::unordered_map<std::tuple<Params...>,
+         Signature, KernelDispatchKeyHash<Params...>>;
   TableType table;

   /// @brief Call function @a f with arguments @a args (perfect forwaring).
@@ -297,8 +297,7 @@ void LinearForm::Assemble()
         tr = mesh->GetBdrFaceTransformations(i);
         if (tr != NULL)
         {
-            mfem::DofTransformation doftrans;
-            fes -> GetElementVDofs (tr -> Elem1No, vdofs, doftrans);
+            fes -> GetElementVDofs (tr -> Elem1No, vdofs);
            for (int k = 0; k < boundary_face_integs.Size(); k++)
            {
               if (boundary_face_integs_marker[k] &&
@@ -308,7 +307,6 @@ void LinearForm::Assemble()
               boundary_face_integs[k]->
               AssembleRHSElementVect(*fes->GetFE(tr->Elem1No),
                                      *tr, elemvect);
-               doftrans.TransformDual(elemvect);
               AddElementVector (vdofs, elemvect);
            }
         }
@@ -164,8 +164,8 @@ private:

 public:
   /// Constructs the domain integrator $ (Q, \nabla v) $
-   DomainLFGradIntegrator(VectorCoefficient &QF, const IntegrationRule *ir = NULL)
-      : DeltaLFIntegrator(QF, ir), Q(QF) { }
+   DomainLFGradIntegrator(VectorCoefficient &QF)
+      : DeltaLFIntegrator(QF), Q(QF) { }

   bool SupportsDevice() const override { return true; }

@@ -158,16 +158,15 @@ void LORBase::ConstructLocalDofPermutation(Array<int> &perm_) const
               int i;
               i = dofmap_lor[off_lor + i1 + i2*2];
               int s1 = i < 0 ? -1 : 1;
-               int idof_lor = vdof_lor[UnsignIndex(i)];
+               int idof_lor = vdof_lor[absdof(i)];
               i = dofmap_ho[off_ho + i1*n1 + i2*n2];
               int s2 = i < 0 ? -1 : 1;
-               int idof_ho = vdof_ho[UnsignIndex(i)];
+               int idof_ho = vdof_ho[absdof(i)];
               int s3 = idof_lor < 0 ? -1 : 1;
               int s4 = idof_ho < 0 ? -1 : 1;
               int s = s1*s2*s3*s4;
-               i = UnsignIndex(idof_ho);
-               perm_[UnsignIndex(idof_lor)] = s < 0 ? -1-UnsignIndex(i) :
-                                              UnsignIndex(i);
+               i = absdof(idof_ho);
+               perm_[absdof(idof_lor)] = s < 0 ? -1-absdof(i) : absdof(i);
            }
         }
      };
@@ -233,7 +232,7 @@ void LORBase::ConstructDofPermutation() const
         int j = l_perm[i];
         int s = j < 0 ? -1 : 1;
         int t_i = pfes_lor->GetLocalTDofNumber(i);
-         int t_j = pfes_ho->GetLocalTDofNumber(UnsignIndex(j));
+         int t_j = pfes_ho->GetLocalTDofNumber(absdof(j));
         // Either t_i and t_j both -1, or both non-negative
         if ((t_i < 0 && t_j >=0) || (t_j < 0 && t_i >= 0))
         {
@@ -57,6 +57,8 @@ private:
   /// values (after temporarily changing them for LOR assembly).
   void ResetIntegrationRules(GetIntegratorsFn get_integrators);

+   static inline int absdof(int i) { return i < 0 ? -1-i : i; }
+
 protected:
   enum FESpaceType { H1, ND, RT, L2, INVALID };

@@ -78,7 +78,10 @@ template <int Dim>
 void BuildBoxes(const Mesh &mesh,
                std::vector<::moonolith::AABB<Dim, double>> &element_boxes)
 {
-   MFEM_ASSERT(mesh.Dimension() == Dim, "Mesh and box dimensions mismatched");
+#ifndef NDEBUG
+   const int dim = mesh.Dimension();
+   assert(dim == Dim);
+#endif
   element_boxes.resize(mesh.GetNE());

   DenseMatrix pts;
@@ -758,7 +758,7 @@ void VectorConvectionNLFIntegrator::AssembleElementVector(
   EF.UseExternalData(elfun.GetData(), nd, dim);
   ELV.UseExternalData(elvect.GetData(), nd, dim);

-   Vector vec1(dim), vec2(dim);
+   Vector vec1(dim), vec2(dim), vecvq(dim);
   const IntegrationRule *ir = GetIntegrationRule(el, T);
   ELV = 0.0;
   for (int i = 0; i < ir->GetNPoints(); i++)
@@ -772,6 +772,11 @@ void VectorConvectionNLFIntegrator::AssembleElementVector(

      MultAtB(EF, dshape, gradEF);
      EF.MultTranspose(shape, vec1);
+      if (VQ)
+      {
+         VQ->Eval(vecvq, T, ip);
+         vec1 += vecvq;
+      }
      gradEF.Mult(vec1, vec2);
      vec2 *= w;
      AddMultVWt(shape, vec2, ELV);
@@ -797,7 +802,7 @@ void VectorConvectionNLFIntegrator::AssembleElementGrad(
   EF.UseExternalData(elfun.GetData(), nd, dim);

   real_t w;
-   Vector vec1(dim), vec2(dim), vec3(nd);
+   Vector vec1(dim), vec2(dim), vec3(nd), vecvq(dim);

   const IntegrationRule *ir = GetIntegrationRule(el, trans);

@@ -822,6 +827,12 @@ void VectorConvectionNLFIntegrator::AssembleElementGrad(
      MultAtB(EF, dshapex, gradEF);
      EF.MultTranspose(shape, vec1);

+      if (VQ)
+      {
+         VQ->Eval(vecvq, trans, ip);
+         vec1 += vecvq;
+      }
+
      trans.AdjugateJacobian().Mult(vec1, vec2);

      vec2 *= w;
@@ -381,6 +381,7 @@ class VectorConvectionNLFIntegrator : public NonlinearFormIntegrator
 {
 private:
   Coefficient *Q{};
+   VectorCoefficient *VQ{};
   DenseMatrix dshape, dshapex, EF, gradEF, ELV, elmat_comp;
   Vector shape;
   // PA extension
@@ -390,7 +391,13 @@ private:
   int dim, ne, nq;

 public:
-   VectorConvectionNLFIntegrator(Coefficient &q): Q(&q) { }
+   VectorConvectionNLFIntegrator(Coefficient &q,
+                                 const IntegrationRule *ir = NULL) :
+      NonlinearFormIntegrator(ir), Q(&q) { }
+
+   VectorConvectionNLFIntegrator(Coefficient &q, VectorCoefficient &vq,
+                                 const IntegrationRule *ir = NULL) :
+      NonlinearFormIntegrator(ir), Q(&q), VQ(&vq) { }

   VectorConvectionNLFIntegrator() = default;

@@ -488,16 +488,10 @@ void ParBilinearForm::FormLinearSystem(
         R.Mult(x, true_X);

         FormSystemMatrix(ess_tdof_list, A);
-
-         std::unique_ptr<ConstrainedOperator> A_constrained([&]()
-         {
-            Operator *op;
-            Operator::FormSystemOperator(ess_tdof_list, op);
-            return dynamic_cast<ConstrainedOperator*>(op);
-         }());
-         MFEM_ASSERT(A_constrained != nullptr, "");
-
+         ConstrainedOperator *A_constrained;
+         Operator::FormConstrainedSystemOperator(ess_tdof_list, A_constrained);
         A_constrained->EliminateRHS(true_X, true_B);
+         delete A_constrained;
         R.MultTranspose(true_B, b);
         hybridization->ReduceRHS(true_B, B);
         X.SetSize(B.Size());
@@ -424,7 +424,7 @@ void ParFiniteElementSpace::GetGroupComm(
            {
               if (ind[l] < 0)
               {
-                  dofs[l] = m + FlipIndexSign(ind[l]);
+                  dofs[l] = m + (-1-ind[l]);
                  if (g_ldof_sign)
                  {
                     (*g_ldof_sign)[dofs[l]] = -1;
@@ -462,7 +462,7 @@ void ParFiniteElementSpace::GetGroupComm(
            {
               if (ind[l] < 0)
               {
-                  dofs[l] = m + FlipIndexSign(ind[l]);
+                  dofs[l] = m + (-1-ind[l]);
                  if (g_ldof_sign)
                  {
                     (*g_ldof_sign)[dofs[l]] = -1;
@@ -500,7 +500,7 @@ void ParFiniteElementSpace::GetGroupComm(
            {
               if (ind[l] < 0)
               {
-                  dofs[l] = m + FlipIndexSign(ind[l]);
+                  dofs[l] = m + (-1-ind[l]);
                  if (g_ldof_sign)
                  {
                     (*g_ldof_sign)[dofs[l]] = -1;
@@ -538,16 +538,16 @@ void ParFiniteElementSpace::ApplyLDofSigns(Array<int> &dofs) const
   {
      if (dofs[i] < 0)
      {
-         if (ldof_sign[FlipIndexSign(dofs[i])] < 0)
+         if (ldof_sign[-1-dofs[i]] < 0)
         {
-            dofs[i] = FlipIndexSign(dofs[i]);
+            dofs[i] = -1-dofs[i];
         }
      }
      else
      {
         if (ldof_sign[dofs[i]] < 0)
         {
-            dofs[i] = FlipIndexSign(dofs[i]);
+            dofs[i] = -1-dofs[i];
         }
      }
   }
@@ -646,38 +646,39 @@ const FaceRestriction *ParFiniteElementSpace::GetFaceRestriction(
   auto itr = L2F.find(key);
   if (itr != L2F.end())
   {
-      return itr->second.get();
+      return itr->second;
   }
   else
   {
-      std::unique_ptr<FaceRestriction> res;
+      FaceRestriction *res;
      if (is_dg_space)
      {
         if (Conforming())
         {
-            res.reset(new ParL2FaceRestriction(*this, f_ordering, type, m));
+            res = new ParL2FaceRestriction(*this, f_ordering, type, m);
         }
         else
         {
-            res.reset(new ParNCL2FaceRestriction(*this, f_ordering, type, m));
+            res = new ParNCL2FaceRestriction(*this, f_ordering, type, m);
         }
      }
      else if (dynamic_cast<const DG_Interface_FECollection*>(fec))
      {
-         res.reset(new L2InterfaceFaceRestriction(*this, f_ordering, type));
+         res = new L2InterfaceFaceRestriction(*this, f_ordering, type);
      }
      else
      {
         if (Conforming())
         {
-            res.reset(new ConformingFaceRestriction(*this, f_ordering, type));
+            res = new ConformingFaceRestriction(*this, f_ordering, type);
         }
         else
         {
-            res.reset(new ParNCH1FaceRestriction(*this, f_ordering, type));
+            res = new ParNCH1FaceRestriction(*this, f_ordering, type);
         }
      }
-      return L2F.emplace(key, std::move(res)).first->second.get();
+      L2F[key] = res;
+      return res;
   }
 }

@@ -699,8 +700,7 @@ void ParFiniteElementSpace::GetSharedEdgeDofs(
      for (int i = 0; i < dofs.Size(); i++)
      {
         const int di = dofs[i];
-         dofs[i] = di >= 0 ? rdofs[di] :
-                   FlipIndexSign(rdofs[FlipIndexSign(di)]);
+         dofs[i] = (di >= 0) ? rdofs[di] : -1-rdofs[-1-di];
      }
   }
 }
@@ -724,8 +724,7 @@ void ParFiniteElementSpace::GetSharedTriangleDofs(
      for (int i = 0; i < dofs.Size(); i++)
      {
         const int di = dofs[i];
-         dofs[i] = di >= 0 ? rdofs[di] :
-                   FlipIndexSign(rdofs[FlipIndexSign(di)]);
+         dofs[i] = (di >= 0) ? rdofs[di] : -1-rdofs[-1-di];
      }
   }
 }
@@ -749,8 +748,7 @@ void ParFiniteElementSpace::GetSharedQuadrilateralDofs(
      for (int i = 0; i < dofs.Size(); i++)
      {
         const int di = dofs[i];
-         dofs[i] = (di >= 0) ? rdofs[di] :
-                   FlipIndexSign(rdofs[FlipIndexSign(di)]);
+         dofs[i] = (di >= 0) ? rdofs[di] : -1-rdofs[-1-di];
      }
   }
 }
@@ -1490,7 +1488,7 @@ void ParFiniteElementSpace::ExchangeFaceNbrData()
         GetElementVDofs(my_elems[i], ldofs);
         for (int j = 0; j < ldofs.Size(); j++)
         {
-            int ldof = UnsignIndex(ldofs[j]);
+            int ldof = (ldofs[j] >= 0 ? ldofs[j] : -1-ldofs[j]);

            if (ldof_marker[ldof] != fn)
            {
@@ -1551,7 +1549,7 @@ void ParFiniteElementSpace::ExchangeFaceNbrData()
         GetElementVDofs(my_elems[i], ldofs);
         for (int j = 0; j < ldofs.Size(); j++)
         {
-            int ldof = UnsignIndex(ldofs[j]);
+            int ldof = (ldofs[j] >= 0 ? ldofs[j] : -1-ldofs[j]);

            if (ldof_marker[ldof] != fn)
            {
@@ -1576,15 +1574,14 @@ void ParFiniteElementSpace::ExchangeFaceNbrData()

      for (int i = 0; i < num_ldofs; i++)
      {
-         int ldof = UnsignIndex(ldofs_fn[i]);
+         int ldof = (ldofs_fn[i] >= 0 ? ldofs_fn[i] : -1-ldofs_fn[i]);
         ldof_marker[ldof] = i;
      }

      for ( ; j < j_end; j++)
      {
-         const int ldof = UnsignIndex(send_J[j]);
-         send_J[j] = (send_J[j] >= 0 ? ldof_marker[ldof] :
-                      FlipIndexSign(ldof_marker[ldof]));
+         int ldof = (send_J[j] >= 0 ? send_J[j] : -1-send_J[j]);
+         send_J[j] = (send_J[j] >= 0 ? ldof_marker[ldof] : -1-ldof_marker[ldof]);
      }
   }

@@ -1676,7 +1673,12 @@ void ParFiniteElementSpace::ExchangeFaceNbrData()
   {
      for (int j_end = face_nbr_ldof.GetI()[fn+1]; j < j_end; j++)
      {
-         const int ldof = UnsignIndex(face_nbr_ldof.GetJ()[j]);
+         int ldof = face_nbr_ldof.GetJ()[j];
+         if (ldof < 0)
+         {
+            ldof = -1-ldof;
+         }
+
         face_nbr_glob_dof_map[j] = dof_face_nbr_offsets[fn] + ldof;
      }
   }
@@ -1720,7 +1722,7 @@ void ParFiniteElementSpace::GetFaceNbrFaceVDofs(int i, Array<int> &vdofs) const
   MFEM_ASSERT(Nonconforming() && i >= pmesh->GetNumFaces(), "");
   int el1, el2, inf1, inf2;
   pmesh->GetFaceElements(i, &el1, &el2);
-   el2 = FlipIndexSign(el2);
+   el2 = -1 - el2;
   pmesh->GetFaceInfos(i, &inf1, &inf2);
   MFEM_ASSERT(0 <= el2 && el2 < face_nbr_element_dof.Size(), "");
   const int nd = face_nbr_element_dof.RowSize(el2);
@@ -1736,8 +1738,7 @@ void ParFiniteElementSpace::GetFaceNbrFaceVDofs(int i, Array<int> &vdofs) const
   for (int j = 0; j < vdofs.Size(); j++)
   {
      const int ldof = vdofs[j];
-      vdofs[j] = (ldof >= 0) ? vol_vdofs[ldof] :
-                 FlipIndexSign(vol_vdofs[FlipIndexSign(ldof)]);
+      vdofs[j] = (ldof >= 0) ? vol_vdofs[ldof] : -1-vol_vdofs[-1-ldof];
   }
 }

@@ -2061,8 +2062,8 @@ void ParFiniteElementSpace::GetGhostFaceDofs(const MeshId &face_id,

         for (int j = 0; j < ne; j++)
         {
-            dofs[offset++] = (ind[j] >= 0) ? (first + ind[j]) :
-                             FlipIndexSign(first + FlipIndexSign(ind[j]));
+            dofs[offset++] = (ind[j] >= 0) ? (first + ind[j])
+                             /*         */ : (-1 - (first + (-1 - ind[j])));
         }
      }
      else
@@ -2072,8 +2073,8 @@ void ParFiniteElementSpace::GetGhostFaceDofs(const MeshId &face_id,
         const int *ind = fec->DofOrderForOrientation(Geometry::SEGMENT, Eo[i]);
         for (int j = 0; j < ne; j++)
         {
-            dofs[offset++] = (ind[j] >= 0) ? (first + ind[j]) :
-                             FlipIndexSign(first + FlipIndexSign(ind[j]));
+            dofs[offset++] = (ind[j] >= 0) ? (first + ind[j])
+                             /*         */ : (-1 - (first + (-1 - ind[j])));
         }
      }
   }
@@ -2866,7 +2867,7 @@ void NeighborRowMessage::Encode(int rank)

            if (ind && (edof = ind[edof]) < 0)
            {
-               edof = FlipIndexSign(edof);
+               edof = -1 - edof;
               s = -1;
            }

@@ -3067,10 +3068,10 @@ void NeighborRowMessage::Decode(int rank)

         // If edof arrived with a negative index, flip it, and the scaling.
         real_t s = (edof < 0) ? -1.0 : 1.0;
-         edof = UnsignIndex(edof);
+         edof = (edof < 0) ? -1 - edof : edof;
         if (ind && (edof = ind[edof]) < 0)
         {
-            edof = FlipIndexSign(edof);
+            edof = -1 - edof;
            s *= -1.0;
         }

@@ -3121,10 +3122,10 @@ void NeighborRowMessage::Decode(int rank)

            // If edof arrived with a negative index, flip it, and the scaling.
            s = (edof < 0) ? -1.0 : 1.0;
-            edof = UnsignIndex(edof);
+            edof = (edof < 0) ? -1 - edof : edof;
            if (ind && (edof = ind[edof]) < 0)
            {
-               edof = FlipIndexSign(edof);
+               edof = -1 - edof;
               s *= -1.0;
            }

@@ -4405,9 +4406,12 @@ ParFiniteElementSpace::RebalanceMatrix(int old_ndofs,
         {
            for (int j = 0; j < dofs.Size(); j++)
            {
-               const int row = UnsignIndex(DofToVDof(dofs[j], vd));
-               const int col = UnsignIndex(DofToVDof(old_dofs[j], vd,
-                                                     old_ndofs));
+               int row = DofToVDof(dofs[j], vd);
+               if (row < 0) { row = -1 - row; }
+
+               int col = DofToVDof(old_dofs[j], vd, old_ndofs);
+               if (col < 0) { col = -1 - col; }
+
               i_diag[row] = col;
            }
         }
@@ -4432,7 +4436,9 @@ ParFiniteElementSpace::RebalanceMatrix(int old_ndofs,
      {
         for (int j = 0; j < dofs.Size(); j++)
         {
-            const int row = UnsignIndex(DofToVDof(dofs[j], vd));
+            int row = DofToVDof(dofs[j], vd);
+            if (row < 0) { row = -1 - row; }
+
            if (i_diag[row] == i_diag[row+1]) // diag row empty?
            {
               i_offd[row] = old_dofs[j + vd * dofs.Size()];
@@ -4541,9 +4547,9 @@ ParFiniteElementSpace::ParallelDerefinementMatrix(int old_ndofs,
   {
      const Embedding &emb = dtrans.embeddings[k];

-      const int fine_rank = old_ranks[k];
-      const int coarse_rank = (emb.parent < 0) ? FlipIndexSign(emb.parent)
-                              : old_pncmesh->ElementRank(emb.parent);
+      int fine_rank = old_ranks[k];
+      int coarse_rank = (emb.parent < 0) ? (-1 - emb.parent)
+                        : old_pncmesh->ElementRank(emb.parent);

      if (coarse_rank != MyRank && fine_rank == MyRank)
      {
@@ -4631,8 +4637,8 @@ ParFiniteElementSpace::ParallelDerefinementMatrix(int old_ndofs,
            {
               if (!std::isfinite(lR(i, 0))) { continue; }

-               const int r = DofToVDof(dofs[i], vd);
-               const int m = UnsignIndex(r);
+               int r = DofToVDof(dofs[i], vd);
+               int m = (r >= 0) ? r : (-1 - r);

               if (is_dg || !mark[m])
               {
@@ -4681,7 +4687,8 @@ ParFiniteElementSpace::ParallelDerefinementMatrix(int old_ndofs,
            {
               if (!std::isfinite(lR(i, 0))) { continue; }

-               const int m = UnsignIndex(DofToVDof(dofs[i], vd));
+               int r = DofToVDof(dofs[i], vd);
+               int m = (r >= 0) ? r : (-1 - r);

               if (is_dg || !mark[m])
               {
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Sohail Reddy	9a12ddc9c1	Updated apps to use new architecture	2026-02-25 15:19:10 -08:00
Sohail Reddy	1d57520c3c	Added field tracking by ID and generalized interface	2026-01-27 10:24:09 -07:00
Sohail Reddy	b7753cb4db	fixed cmake	2026-01-06 18:59:44 -08:00
Sohail Reddy	842fec483f	Merge branch 'master' into multiapp	2026-01-06 18:53:05 -08:00
Sohail Reddy	4b0eafd047	Fixed const correctness	2026-01-06 18:49:38 -08:00
Sohail Reddy	e793c70058	Updated fsi app for constrained inner product on ess_dof	2025-11-19 14:28:38 -08:00
Sohail Reddy	1856912d63	Fixed style	2025-11-19 14:24:23 -08:00
Sohail Reddy	3b6817e36b	Added custom inner product to fixed point relaxation methods	2025-11-19 14:24:04 -08:00
Sohail Reddy	e4dcfb684f	Merge branch 'ode-stage-solve' into multiapp	2025-11-18 23:26:55 -08:00
Sohail Reddy	7dcf77da54	Merge branch 'master' into multiapp	2025-11-18 23:25:23 -08:00
Sohail Reddy	3e823f1da7	updated morpher coupled bc	2025-11-18 23:16:06 -08:00
Sohail Reddy	9a2fee8b6f	moved FPI relaxation member functions to cpp	2025-10-19 21:44:25 -07:00
Sohail Reddy	4b38bd79e9	clean up fsi example	2025-10-16 18:05:41 -07:00
Sohail Reddy	d1378b8a7b	bug fix fpisolver; reset relaxation each call	2025-10-16 18:04:17 -07:00
Sohail Reddy	3972b24f3b	fixed ale velocity calculation	2025-10-15 22:19:59 -07:00
Sohail Reddy	48bd66640d	added command line option for relaxation factor and fixed mpi_c_bool	2025-10-15 22:19:35 -07:00
Sohail Reddy	a230b87a20	Fixed pure virtual function overide if GSLib not built	2025-10-14 18:31:08 -07:00
Sohail Reddy	5f9f782ad2	fixed style	2025-10-14 17:01:51 -07:00
Sohail Reddy	159a259f30	fixed redeclared variable in FPISolver	2025-10-14 16:56:20 -07:00
Sohail Reddy	67da324c26	Merge branch 'master' into multiapp	2025-10-14 16:28:08 -07:00
Sohail Reddy	b5cf20e76c	added cmake for multiapp miniapps	2025-10-14 16:26:00 -07:00
Sohail Reddy	1510492dfd	fixed style	2025-10-14 16:24:23 -07:00
Sohail Reddy	360e662cf8	FSI miniapp and updated elasticity and navier-stokes apps	2025-10-14 16:22:53 -07:00
Sohail Reddy	c1ec6a8c72	bug fix in navier miniapp for Step() function	2025-10-14 13:27:04 -07:00
Sohail Reddy	805499d799	bugfix for updating grid functions for transfer	2025-10-14 13:26:15 -07:00
Sohail Reddy	7b0330ffca	Removed repetitive code in cht miniapp	2025-10-14 13:23:55 -07:00
Sohail Reddy	68fd37de1d	Added completed conjugate heat transfer test case	2025-10-11 17:44:41 -07:00
Sohail Reddy	9f1d2ac249	reverted changes to navier miniapp	2025-10-11 17:43:24 -07:00
Sohail Reddy	a594ab5a3a	fixed namespace std use	2025-10-11 17:42:57 -07:00
Sohail Reddy	343a8b473e	moved fixed point solver to solvers.cpp	2025-10-11 17:13:31 -07:00
Sohail Reddy	911709c619	fixed use of MFEM_USE_MPI in multiapp	2025-10-11 16:10:17 -07:00
Sohail Reddy	c303956b9f	fixed source field ownership and cleaning	2025-10-11 01:29:50 -07:00
Sohail Reddy	c031ec4466	Fixed const correctness and added operator ownership in multiapp	2025-10-10 17:37:12 -07:00
Sohail Reddy	58c56ec9dc	added LinkedFieldsCollection to manage linked fields for each application	2025-10-10 00:01:12 -07:00
Sohail Reddy	7db740ede3	Added documentation, updated class names for coupling schemes	2025-09-28 23:36:06 -07:00
Sohail Reddy	0436adfb1c	updated fixed point solver	2025-09-28 23:31:33 -07:00
Sohail Reddy	a6f2d8981a	Merge branch 'master' into multiapp	2025-09-08 18:02:54 -07:00
Sohail Reddy	90edc198e3	update fsi app	2025-09-08 17:58:24 -07:00
Sohail Reddy	c691c7c854	Formatted multiapp files and added documentation	2025-09-08 10:21:16 -07:00
Sohail Reddy	7c9105bd0e	fixed style	2025-09-08 01:41:26 -07:00
Sohail Reddy	773bac0114	updated navier-stokes miniapp for ALE	2025-09-08 01:29:33 -07:00
Sohail Reddy	440db8189c	Added option for ALE to VectorConvectionNLFIntegrator	2025-09-08 01:28:26 -07:00
Sohail Reddy	94efb4cd81	Updated multiapp interface for type-erased operator, field transfer and coupling scheme	2025-09-08 01:27:47 -07:00
Sohail Reddy	ce3bdc0dfc	Simplified mesh-morphing/diffusion app	2025-09-08 01:24:53 -07:00
Sohail Reddy	aaf59d3a83	updated elasticity miniapp to use Schur complement	2025-09-08 01:22:39 -07:00
Sohail Reddy	3b3ffa7d7a	updated native navier miniapp to use standard ODESolve::Step signature	2025-09-05 13:53:12 -07:00
Sohail Reddy	2898ec669c	Updated native navier miniapp to own/not-own the boundary conditions	2025-09-04 17:19:45 -07:00
Sohail Reddy	f34bfbbd8d	Added field transfer based on FindPoints	2025-09-04 10:35:50 -07:00
Sohail Reddy	3cec2cba78	updated navier-stokes and elasticity examples	2025-09-03 16:34:45 -07:00
Sohail Reddy	f769e2a7d7	updated morpher to diffuse displacement or velocity	2025-09-03 16:34:08 -07:00
Sohail Reddy	493674e650	updated navier-stokes miniapp to work with scaled pressure	2025-09-03 16:31:58 -07:00
Sohail Reddy	13632cde51	updated elasticity miniapp	2025-09-03 16:31:03 -07:00
Sohail Reddy	ae63fda0fd	Updated multiapp object for multi-stage coupling	2025-08-19 11:54:02 -07:00
Sohail Reddy	48b3e428fb	clean up	2025-08-19 11:53:32 -07:00
Sohail Reddy	89dd191866	bug-fix: fixed point solver; updated relaxation schemes to clamp relaxation factors	2025-08-19 11:47:14 -07:00
Sohail Reddy	2a4f9184be	Updated Navier-Stokes miniapp for multi-stage coupling and artificial compressibility	2025-08-19 11:40:47 -07:00
Sohail Reddy	ff66dce92e	updated elasticity and morpher miniapps for multi-stage coupling	2025-08-19 11:38:25 -07:00
Sohail Reddy	01ef886faf	Added parallelized DistanceSquared for Vectors	2025-08-19 11:09:47 -07:00
Sohail Reddy	4be67907c4	Working FSI miniapp	2025-08-13 16:12:04 -07:00
Sohail Reddy	9443523dec	Updated the multiapp (CoupledApplication) framework	2025-08-13 16:10:19 -07:00
Sohail Reddy	fac6dfe283	Added mesh morphing app	2025-08-13 16:09:50 -07:00
Sohail Reddy	7776766ee7	updated FPISolver	2025-08-13 16:09:09 -07:00
Sohail Reddy	8e24224a18	updated cht example...unused atm	2025-08-13 16:08:33 -07:00
Sohail Reddy	fa4c607622	updated Navier-Stokes miniapp for partial assembly	2025-08-13 16:07:09 -07:00
Sohail Reddy	29bd541a3e	updated elasticity miniapp	2025-08-13 16:03:23 -07:00
Sohail Reddy	369f82adad	Added function to fetch TimeDependantOperator from ODESolver	2025-08-13 16:01:39 -07:00
Sohail Reddy	e2bc1aefd8	Working elasticity miniapp	2025-08-01 19:09:05 -07:00
Sohail Reddy	033814fe70	fixed code style	2025-07-31 10:14:48 -07:00
Sohail Reddy	f4d4a5c4da	Working fully implicit incompressible navier-stokes solver	2025-07-31 10:13:33 -07:00
Sohail Reddy	6b8d341478	Renamed some multiapp member functions	2025-07-31 09:56:27 -07:00
Sohail Reddy	7a02905d32	Updated constructors for some bilinear and nonlinearform integrator to now take integration rule as input	2025-07-31 09:53:16 -07:00
Sohail Reddy	a4c2ad2f3c	Updated type erasure to support non-mfem apps	2025-07-21 10:27:35 -07:00
Sohail Reddy	4a11684323	Working monolithic (linear and nonlinear) solves for multiapp	2025-07-17 18:22:41 -07:00
Sohail Reddy	7b4b2de092	Merge branch 'master' into multiapp	2025-07-15 16:37:35 -07:00
Sohail Reddy	285aa03049	conv-diff mulitapp example	2025-07-15 16:35:56 -07:00
Sohail Reddy	27af36adc5	Changed class naming and fixed point solver and relaxation schemes	2025-07-15 16:35:03 -07:00
Sohail Reddy	de781c05b8	Fixed function pointer for relaxation method in FPISolver	2025-07-10 17:04:58 -07:00
Sohail Reddy	125f5c9e48	Added relaxation methods to fixed point solvers and updated multiapp for explicit coupling	2025-07-10 16:59:03 -07:00
Sohail Reddy	0d6c8fbbf1	Updated multiapp partition implicit solve to use fixed point Solver object	2025-07-09 19:48:04 -07:00
Sohail Reddy	34ebc0f158	Changed scheme naming convention and added/separated Addtive and Alternating Schwarz coupling schemes	2025-07-08 18:16:32 -07:00
Sohail Reddy	8db7813d86	Working paritioned implicit solves	2025-07-08 11:06:27 -07:00
Sohail Reddy	d31e5c8af0	Merge branch 'master' into multiapp	2025-07-02 20:46:57 -07:00
Sohail Reddy	d7e43cfc74	added test case for two-way partitioned coupled solve	2025-07-02 20:45:51 -07:00
Sohail Reddy	82193e0404	Merge branch 'master' into multiapp	2025-06-16 15:09:01 -07:00
Sohail Reddy	5796633307	updated example for implicit time-integration	2025-06-16 15:05:22 -07:00
Sohail Reddy	3d55c021e3	updated header copyright	2025-06-12 14:47:11 -07:00
Sohail Reddy	a30303ecf9	fixed type checking with SFINAE	2025-06-12 14:31:05 -07:00
Sohail Reddy	9287488024	Merge branch 'master' into multiapp	2025-06-11 14:11:32 -07:00
Sohail Reddy	9aa2866b0d	Merge branch 'master' into multiapp	2025-05-29 14:00:03 -07:00
Sohail Reddy	ad16d2f5ae	added field transfer, multiapp abstractions and working one-way coupling	2025-05-29 13:58:58 -07:00
Sohail Reddy	c552925a54	Merge branch 'master' into multiapp	2025-03-13 15:41:44 -07:00
Sohail Reddy	c3b9b62336	updated mfem_application to perform index controlled operators	2025-02-20 11:28:02 -08:00
Sohail Reddy	c36e5facd1	initial multiapp skeleton with MFEMApplication class and type-erased multiapp	2024-10-02 17:11:14 -07:00