Merge pull request #3135 from akohlmey/next_patch_release

Step version strings for the next patch release

.github/CODEOWNERS

@@ -83,7 +83,7 @@ src/library.*             @sjplimp
 src/main.cpp              @sjplimp
 src/min_*.*               @sjplimp
 src/memory.*              @sjplimp
-src/modify.*              @sjplimp
+src/modify.*              @sjplimp @stanmoore1
 src/molecule.*            @sjplimp
 src/my_page.h             @sjplimp
 src/my_pool_chunk.h       @sjplimp

.github/workflows/codeql-analysis.yml

@@ -3,7 +3,7 @@ name: "CodeQL Code Analysis"
 
 on:
   push:
-    branches: [master]
+    branches: [develop]
 
 jobs:
   analyze:

.github/workflows/compile-msvc.yml

@@ -0,0 +1,46 @@
+# GitHub action to build LAMMPS on Windows with Visual C++
+name: "Native Windows Compilation and Unit Tests"
+
+on:
+  push:
+    branches: [develop]
+
+jobs:
+  build:
+    name: Windows Compilation Test
+    if: ${{ github.repository == 'lammps/lammps' }}
+    runs-on: windows-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      with:
+        fetch-depth: 2
+
+    - name: Select Python version
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.10'
+
+    - name: Building LAMMPS via CMake
+      shell: bash
+      run: |
+        python3 -m pip install numpy
+        cmake -C cmake/presets/windows.cmake \
+              -D PKG_PYTHON=on \
+              -S cmake -B build \
+              -D BUILD_SHARED_LIBS=on \
+              -D LAMMPS_EXCEPTIONS=on \
+              -D ENABLE_TESTING=on
+        cmake --build build --config Release
+
+    - name: Run LAMMPS executable
+      shell: bash
+      run: |
+        ./build/Release/lmp.exe -h
+        ./build/Release/lmp.exe -in bench/in.lj
+
+    - name: Run Unit Tests
+      working-directory: build
+      shell: bash
+      run: ctest -V -C Release

.github/workflows/unittest-macos.yml

@@ -3,7 +3,7 @@ name: "Unittest for MacOS"
 
 on:
   push:
-    branches: [master]
+    branches: [develop]
 
 jobs:
   build:

.gitignore

@@ -37,8 +37,8 @@ vgcore.*
 .Trashes
 ehthumbs.db
 Thumbs.db
-.clang-format
 .lammps_history
+.vs
 
 #cmake
 /build*
@@ -49,3 +49,8 @@ Thumbs.db
 /Testing
 /cmake_install.cmake
 /lmp
+out/Debug
+out/RelWithDebInfo
+out/Release
+out/x86
+out/x64

SECURITY.md

@@ -23,6 +23,10 @@ either a user mistake or a bug in the code.  Bugs can be reported in
 the LAMMPS project
 [issue tracker on GitHub](https://github.com/lammps/lammps/issues).
 
+To mitigate issues with using homoglyphs or bidirectional reordering in
+unicode, which have been demonstrated as a vector to obfuscate and hide
+malicious changes to the source code, all LAMMPS submissions are checked
+for unicode characters and only all-ASCII source code is accepted.
 
 # Version Updates
 

cmake/CMakeLists.txt

@@ -19,6 +19,9 @@ set(SOVERSION 0)
 
 get_filename_component(LAMMPS_DIR ${CMAKE_CURRENT_SOURCE_DIR}/.. ABSOLUTE)
 get_filename_component(LAMMPS_LIB_BINARY_DIR ${CMAKE_BINARY_DIR}/lib ABSOLUTE)
+# collect all executables and shared libs in the top level build folder
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
+set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
 
 set(LAMMPS_SOURCE_DIR     ${LAMMPS_DIR}/src)
 set(LAMMPS_LIB_SOURCE_DIR ${LAMMPS_DIR}/lib)
@@ -81,22 +84,40 @@ check_for_autogen_files(${LAMMPS_SOURCE_DIR})
 include(CheckIncludeFileCXX)
 
 # set required compiler flags and compiler/CPU arch specific optimizations
-if((CMAKE_CXX_COMPILER_ID STREQUAL "Intel") OR (CMAKE_CXX_COMPILER_ID STREQUAL "IntelLLVM"))
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -restrict")
-  if(CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.3 OR CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.4)
-    set(CMAKE_TUNE_DEFAULT "-xCOMMON-AVX512")
+if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
+  if(CMAKE_SYSTEM_NAME STREQUAL "Windows")
+    if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
+      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Qrestrict")
+    endif()
+    if(CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.3 OR CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.4)
+      set(CMAKE_TUNE_DEFAULT "/QxCOMMON-AVX512")
+    else()
+      set(CMAKE_TUNE_DEFAULT "/QxHost")
+    endif()
   else()
-    set(CMAKE_TUNE_DEFAULT "-xHost")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -restrict")
+    if(CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.3 OR CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.4)
+      set(CMAKE_TUNE_DEFAULT "-xCOMMON-AVX512")
+    else()
+      set(CMAKE_TUNE_DEFAULT "-xHost")
+    endif()
   endif()
 endif()
 
-# we require C++11 without extensions
+# we require C++11 without extensions. Kokkos requires at least C++14 (currently)
 set(CMAKE_CXX_STANDARD 11)
+if(PKG_KOKKOS AND (CMAKE_CXX_STANDARD LESS 14))
+  set(CMAKE_CXX_STANDARD 14)
+endif()
 set(CMAKE_CXX_STANDARD_REQUIRED ON)
 set(CMAKE_CXX_EXTENSIONS OFF CACHE BOOL "Use compiler extensions")
-# ugly hack for MSVC which by default always reports an old C++ standard in the __cplusplus macro
+# ugly hacks for MSVC which by default always reports an old C++ standard in the __cplusplus macro
+# and prints lots of pointless warnings about "unsafe" functions
 if(MSVC)
   add_compile_options(/Zc:__cplusplus)
+  add_compile_options(/wd4244)
+  add_compile_options(/wd4267)
+  add_compile_definitions(_CRT_SECURE_NO_WARNINGS)
 endif()
 
 # export all symbols when building a .dll file on windows
@@ -115,10 +136,7 @@ endif()
 set(LAMMPS_BINARY lmp${LAMMPS_MACHINE})
 
 option(BUILD_SHARED_LIBS "Build shared library" OFF)
-if(BUILD_SHARED_LIBS) # for all pkg libs, mpi_stubs and linalg
-  set(CMAKE_POSITION_INDEPENDENT_CODE ON)
-endif()
-
+option(CMAKE_POSITION_INDEPENDENT_CODE "Create object compatible with shared libraries" ON)
 option(BUILD_TOOLS "Build and install LAMMPS tools (msi2lmp, binary2txt, chain)" OFF)
 option(BUILD_LAMMPS_SHELL "Build and install the LAMMPS shell" OFF)
 
@@ -265,28 +283,19 @@ if(BUILD_MPI)
   # We use a non-standard procedure to cross-compile with MPI on Windows
   if((CMAKE_SYSTEM_NAME STREQUAL "Windows") AND CMAKE_CROSSCOMPILING)
     include(MPI4WIN)
-    target_link_libraries(lammps PUBLIC MPI::MPI_CXX)
   else()
     find_package(MPI REQUIRED)
-    target_link_libraries(lammps PUBLIC MPI::MPI_CXX)
     option(LAMMPS_LONGLONG_TO_LONG "Workaround if your system or MPI version does not recognize 'long long' data types" OFF)
     if(LAMMPS_LONGLONG_TO_LONG)
       target_compile_definitions(lammps PRIVATE -DLAMMPS_LONGLONG_TO_LONG)
     endif()
   endif()
+  target_link_libraries(lammps PUBLIC MPI::MPI_CXX)
 else()
-  file(GLOB MPI_SOURCES ${LAMMPS_SOURCE_DIR}/STUBS/mpi.cpp)
-  add_library(mpi_stubs STATIC ${MPI_SOURCES})
-  set_target_properties(mpi_stubs PROPERTIES OUTPUT_NAME lammps_mpi_stubs${LAMMPS_MACHINE})
-  target_include_directories(mpi_stubs PUBLIC $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
-  if(BUILD_SHARED_LIBS)
-    target_link_libraries(lammps PRIVATE mpi_stubs)
-    target_include_directories(lammps INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
-    target_compile_definitions(lammps INTERFACE $<INSTALL_INTERFACE:LAMMPS_LIB_NO_MPI>)
-  else()
-    target_link_libraries(lammps PUBLIC mpi_stubs)
-  endif()
-  add_library(MPI::MPI_CXX ALIAS mpi_stubs)
+  target_sources(lammps PRIVATE ${LAMMPS_SOURCE_DIR}/STUBS/mpi.cpp)
+  add_library(mpi_stubs INTERFACE)
+  target_include_directories(mpi_stubs INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
+  target_link_libraries(lammps PUBLIC mpi_stubs)
 endif()
 
 set(LAMMPS_SIZES "smallbig" CACHE STRING "LAMMPS integer sizes (smallsmall: all 32-bit, smallbig: 64-bit #atoms #timesteps, bigbig: also 64-bit imageint, 64-bit atom ids)")
@@ -317,7 +326,6 @@ pkg_depends(ML-IAP ML-SNAP)
 pkg_depends(MPIIO MPI)
 pkg_depends(ATC MANYBODY)
 pkg_depends(LATBOLTZ MPI)
-pkg_depends(PHONON KSPACE)
 pkg_depends(SCAFACOS MPI)
 pkg_depends(DIELECTRIC KSPACE)
 pkg_depends(DIELECTRIC EXTRA-PAIR)
@@ -351,11 +359,13 @@ if(BUILD_OMP)
       ((CMAKE_CXX_COMPILER_ID STREQUAL "Intel") AND (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 19.0)))
     # GCC 9.x and later plus Clang 10.x and later implement strict OpenMP 4.0 semantics for consts.
     # Intel 18.0 was tested to support both, so we switch to OpenMP 4+ from 19.x onward to be safe.
-    target_compile_definitions(lammps PRIVATE -DLAMMPS_OMP_COMPAT=4)
+    set(LAMMPS_OMP_COMPAT_LEVEL 4)
   else()
-    target_compile_definitions(lammps PRIVATE -DLAMMPS_OMP_COMPAT=3)
+    set(LAMMPS_OMP_COMPAT_LEVEL 3)
   endif()
+  target_compile_definitions(lammps PRIVATE -DLAMMPS_OMP_COMPAT=${LAMMPS_OMP_COMPAT_LEVEL})
   target_link_libraries(lammps PRIVATE OpenMP::OpenMP_CXX)
+  target_link_libraries(lmp PRIVATE OpenMP::OpenMP_CXX)
 endif()
 
 if(PKG_MSCG OR PKG_ATC OR PKG_AWPMD OR PKG_ML-QUIP OR PKG_LATTE)
@@ -468,9 +478,12 @@ foreach(HEADER cmath)
   endif(NOT FOUND_${HEADER})
 endforeach(HEADER)
 
-set(MATH_LIBRARIES "m" CACHE STRING "math library")
-mark_as_advanced( MATH_LIBRARIES )
-target_link_libraries(lammps PRIVATE ${MATH_LIBRARIES})
+# make the standard math library overrideable and autodetected (for systems that don't have it)
+find_library(STANDARD_MATH_LIB m DOC "Standard Math library")
+mark_as_advanced(STANDARD_MATH_LIB)
+if(STANDARD_MATH_LIB)
+  target_link_libraries(lammps PRIVATE ${STANDARD_MATH_LIB})
+endif()
 
 ######################################
 # Generate Basic Style files
@@ -566,11 +579,10 @@ if(PKG_ATC)
   if(LAMMPS_SIZES STREQUAL "BIGBIG")
     message(FATAL_ERROR "The ATC Package is not compatible with -DLAMMPS_BIGBIG")
   endif()
-  target_link_libraries(atc PRIVATE ${LAPACK_LIBRARIES})
   if(BUILD_MPI)
-    target_link_libraries(atc PRIVATE MPI::MPI_CXX)
+    target_link_libraries(atc PRIVATE ${LAPACK_LIBRARIES} MPI::MPI_CXX)
   else()
-    target_link_libraries(atc PRIVATE mpi_stubs)
+    target_link_libraries(atc PRIVATE ${LAPACK_LIBRARIES} mpi_stubs)
   endif()
   target_include_directories(atc PRIVATE ${LAMMPS_SOURCE_DIR})
   target_compile_definitions(atc PRIVATE -DLAMMPS_${LAMMPS_SIZES})
@@ -584,22 +596,19 @@ endif()
 # packages which selectively include variants based on enabled styles
 # e.g. accelerator packages
 ######################################################################
-foreach(PKG_WITH_INCL CORESHELL QEQ OPENMP DPD-SMOOTH KOKKOS OPT INTEL GPU)
+foreach(PKG_WITH_INCL CORESHELL DPD-SMOOTH PHONON QEQ OPENMP KOKKOS OPT INTEL GPU)
   if(PKG_${PKG_WITH_INCL})
     include(Packages/${PKG_WITH_INCL})
   endif()
 endforeach()
 
 if(PKG_PLUGIN)
-  if(BUILD_SHARED_LIBS)
-    target_compile_definitions(lammps PRIVATE -DLMP_PLUGIN)
-  else()
-    message(WARNING "Plugin loading will not work unless BUILD_SHARED_LIBS is enabled")
-  endif()
-  # link with -ldl or equivalent for plugin loading; except on Windows
-  if(NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Windows")
-    target_link_libraries(lammps PRIVATE ${CMAKE_DL_LIBS})
-  endif()
+  target_compile_definitions(lammps PRIVATE -DLMP_PLUGIN)
+endif()
+
+# link with -ldl or equivalent for plugin loading; except on Windows
+if(NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Windows")
+   target_link_libraries(lammps PRIVATE ${CMAKE_DL_LIBS})
 endif()
 
 ######################################################################
@@ -608,7 +617,7 @@ endif()
 # and after everything else that is compiled locally
 ######################################################################
 if(CMAKE_SYSTEM_NAME STREQUAL "Windows")
-  target_link_libraries(lammps PRIVATE -lwsock32 -lpsapi)
+  target_link_libraries(lammps PRIVATE "wsock32;psapi")
 endif()
 
 ######################################################
@@ -669,6 +678,7 @@ endif()
 
 set_target_properties(lammps PROPERTIES OUTPUT_NAME lammps${LAMMPS_MACHINE})
 set_target_properties(lammps PROPERTIES SOVERSION ${SOVERSION})
+set_target_properties(lammps PROPERTIES PREFIX "lib")
 target_include_directories(lammps PUBLIC $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/lammps>)
 file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/includes/lammps)
 foreach(_HEADER ${LAMMPS_CXX_HEADERS})
@@ -688,6 +698,9 @@ foreach(_DEF ${LAMMPS_DEFINES})
 endforeach()
 if(BUILD_SHARED_LIBS)
   install(TARGETS lammps EXPORT LAMMPS_Targets LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})
+  if(NOT BUILD_MPI)
+    install(TARGETS mpi_stubs EXPORT LAMMPS_Targets LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})
+  endif()
   configure_file(pkgconfig/liblammps.pc.in ${CMAKE_CURRENT_BINARY_DIR}/liblammps${LAMMPS_MACHINE}.pc @ONLY)
   install(FILES ${CMAKE_CURRENT_BINARY_DIR}/liblammps${LAMMPS_MACHINE}.pc DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig)
   install(EXPORT LAMMPS_Targets FILE LAMMPS_Targets.cmake NAMESPACE LAMMPS:: DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/LAMMPS)
@@ -727,7 +740,7 @@ install(
 if(BUILD_SHARED_LIBS)
   if(CMAKE_VERSION VERSION_LESS 3.12)
     # adjust so we find Python 3 versions before Python 2 on old systems with old CMake
-    set(Python_ADDITIONAL_VERSIONS 3.9 3.8 3.7 3.6 3.5)
+    set(Python_ADDITIONAL_VERSIONS 3.12 3.11 3.10 3.9 3.8 3.7 3.6)
     find_package(PythonInterp) # Deprecated since version 3.12
     if(PYTHONINTERP_FOUND)
         set(Python_EXECUTABLE ${PYTHON_EXECUTABLE})
@@ -786,11 +799,17 @@ if(ClangFormat_FOUND)
 endif()
 
 get_target_property(DEFINES lammps COMPILE_DEFINITIONS)
+get_property(BUILD_IS_MULTI_CONFIG GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
+if(BUILD_IS_MULTI_CONFIG)
+  set(LAMMPS_BUILD_TYPE "Multi-Config")
+else()
+  set(LAMMPS_BUILD_TYPE ${CMAKE_BUILD_TYPE})
+endif()
 include(FeatureSummary)
 feature_summary(DESCRIPTION "The following tools and libraries have been found and configured:" WHAT PACKAGES_FOUND)
 message(STATUS "<<< Build configuration >>>
    Operating System: ${CMAKE_SYSTEM_NAME} ${CMAKE_LINUX_DISTRO} ${CMAKE_DISTRO_VERSION}
-   Build type:       ${CMAKE_BUILD_TYPE}
+   Build type:       ${LAMMPS_BUILD_TYPE}
    Install path:     ${CMAKE_INSTALL_PREFIX}
    Generator:        ${CMAKE_GENERATOR} using ${CMAKE_MAKE_PROGRAM}")
 ###############################################################################

cmake/CMakeSettings.json

@@ -0,0 +1,204 @@
+{
+  "configurations": [
+    {
+      "name": "x64-Debug-MSVC",
+      "generator": "Ninja",
+      "configurationType": "Debug",
+      "buildRoot": "${workspaceRoot}\\build\\${name}",
+      "installRoot": "${workspaceRoot}\\install\\${name}",
+      "cmakeCommandArgs": "-C ${workspaceRoot}\\cmake\\presets\\windows.cmake",
+      "buildCommandArgs": "",
+      "ctestCommandArgs": "",
+      "inheritEnvironments": [ "msvc_x64_x64" ],
+      "variables": [
+        {
+          "name": "BUILD_SHARED_LIBS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_TOOLS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "LAMMPS_EXCEPTIONS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "PKG_PYTHON",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "ENABLE_TESTING",
+          "value": "True",
+          "type": "BOOL"
+        }
+      ]
+    },
+    {
+      "name": "x64-Release-MSVC",
+      "generator": "Ninja",
+      "configurationType": "Release",
+      "buildRoot": "${workspaceRoot}\\build\\${name}",
+      "installRoot": "${workspaceRoot}\\install\\${name}",
+      "cmakeCommandArgs": "-C ${workspaceRoot}\\cmake\\presets\\windows.cmake",
+      "buildCommandArgs": "",
+      "ctestCommandArgs": "",
+      "inheritEnvironments": [ "msvc_x64_x64" ],
+      "variables": [
+        {
+          "name": "BUILD_SHARED_LIBS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_TOOLS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "LAMMPS_EXCEPTIONS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "PKG_PYTHON",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "ENABLE_TESTING",
+          "value": "True",
+          "type": "BOOL"
+        }
+      ]
+    },
+    {
+      "name": "x64-Debug-Clang",
+      "generator": "Ninja",
+      "configurationType": "Debug",
+      "buildRoot": "${workspaceRoot}\\build\\${name}",
+      "installRoot": "${workspaceRoot}\\install\\${name}",
+      "cmakeCommandArgs": "-C ${workspaceRoot}\\cmake\\presets\\windows.cmake",
+      "buildCommandArgs": "",
+      "ctestCommandArgs": "",
+      "inheritEnvironments": [ "clang_cl_x64" ],
+      "variables": [
+        {
+          "name": "BUILD_SHARED_LIBS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_TOOLS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "LAMMPS_EXCEPTIONS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "PKG_PYTHON",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "ENABLE_TESTING",
+          "value": "True",
+          "type": "BOOL"
+        }
+      ]
+    },
+    {
+      "name": "x64-Debug-OneAPI",
+      "generator": "Ninja",
+      "configurationType": "Debug",
+      "buildRoot": "${workspaceRoot}\\build\\${name}",
+      "installRoot": "${workspaceRoot}\\install\\${name}",
+      "cmakeCommandArgs": "-C ${workspaceRoot}\\cmake\\presets\\windows.cmake -DCMAKE_CXX_COMPILER=icx -DCMAKE_C_COMPILER=icx",
+      "buildCommandArgs": "",
+      "ctestCommandArgs": "",
+      "inheritEnvironments": [ "msvc_x64_x64" ],
+      "variables": [
+        {
+          "name": "BUILD_SHARED_LIBS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_TOOLS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "LAMMPS_EXCEPTIONS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "PKG_PYTHON",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "ENABLE_TESTING",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_MPI",
+          "value": "False",
+          "type": "BOOL"
+        }
+      ]
+    },
+    {
+      "name": "x64-Debug-Intel",
+      "generator": "Ninja",
+      "configurationType": "Debug",
+      "buildRoot": "${workspaceRoot}\\build\\${name}",
+      "installRoot": "${workspaceRoot}\\install\\${name}",
+      "cmakeCommandArgs": "-C ${workspaceRoot}\\cmake\\presets\\windows.cmake -DCMAKE_CXX_COMPILER=icl -DCMAKE_C_COMPILER=icl -DCMAKE_Fortran_COMPILER=ifort",
+      "buildCommandArgs": "",
+      "ctestCommandArgs": "",
+      "inheritEnvironments": [ "msvc_x64_x64" ],
+      "variables": [
+        {
+          "name": "BUILD_SHARED_LIBS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_TOOLS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "LAMMPS_EXCEPTIONS",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "PKG_PYTHON",
+          "value": "True",
+          "type": "BOOL"
+        },
+        {
+          "name": "ENABLE_TESTING",
+          "value": "False",
+          "type": "BOOL"
+        },
+        {
+          "name": "BUILD_MPI",
+          "value": "False",
+          "type": "BOOL"
+        }
+      ]
+    }
+  ]
+}

cmake/Modules/ExternalCMakeProject.cmake

@@ -0,0 +1,33 @@
+# Build a CMake based external library as subdirectory.
+# The sources will be unpacked to ${CMAKE_BINARY_DIR}/_deps/${target}-src
+# The binaries will be built in ${CMAKE_BINARY_DIR}/_deps/${target}-build
+#
+function(ExternalCMakeProject target url hash basedir cmakedir cmakefile)
+  # change settings locally
+  set(BUILD_SHARED_LIBS OFF)
+  set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+  get_filename_component(archive ${url} NAME)
+  file(MAKE_DIRECTORY ${CMAKE_BINARY_DIR}/_deps/src)
+  message(STATUS "Downloading ${url}")
+  file(DOWNLOAD ${url} ${CMAKE_BINARY_DIR}/_deps/${archive} EXPECTED_HASH MD5=${hash} SHOW_PROGRESS)
+  message(STATUS "Unpacking and configuring ${archive}")
+  execute_process(COMMAND ${CMAKE_COMMAND} -E tar xzf ${CMAKE_BINARY_DIR}/_deps/${archive}
+    WORKING_DIRECTORY ${CMAKE_BINARY_DIR}/_deps/src)
+  file(GLOB TARGET_SOURCE "${CMAKE_BINARY_DIR}/_deps/src/${basedir}*")
+  list(LENGTH TARGET_SOURCE _num)
+  if(_num GREATER 1)
+    message(FATAL_ERROR "Inconsistent ${target} library sources. "
+      "Please delete ${CMAKE_BINARY_DIR}/_deps/src and re-run cmake")
+  endif()
+  file(REMOVE_RECURSE ${CMAKE_BINARY_DIR}/_deps/${target}-src)
+  file(RENAME ${TARGET_SOURCE} ${CMAKE_BINARY_DIR}/_deps/${target}-src)
+  if(NOT (cmakefile STREQUAL ""))
+    file(COPY ${cmakefile} DESTINATION ${CMAKE_BINARY_DIR}/_deps/${target}-src/${cmakedir}/)
+    get_filename_component(_cmakefile ${cmakefile} NAME)
+    file(RENAME "${CMAKE_BINARY_DIR}/_deps/${target}-src/${cmakedir}/${_cmakefile}"
+      "${CMAKE_BINARY_DIR}/_deps/${target}-src/${cmakedir}/CMakeLists.txt")
+  endif()
+  add_subdirectory("${CMAKE_BINARY_DIR}/_deps/${target}-src/${cmakedir}"
+    "${CMAKE_BINARY_DIR}/_deps/${target}-build")
+endfunction(ExternalCMakeProject)

cmake/Modules/FindCythonize.cmake

@@ -8,18 +8,19 @@
 #=============================================================================
 
 if(CMAKE_VERSION VERSION_LESS 3.12)
+    set(Python_ADDITIONAL_VERSIONS 3.12 3.11 3.10 3.9 3.8 3.7 3.6)
     find_package(PythonInterp 3.6 QUIET) # Deprecated since version 3.12
     if(PYTHONINTERP_FOUND)
-        set(Python3_EXECUTABLE ${PYTHON_EXECUTABLE})
+        set(Python_EXECUTABLE ${PYTHON_EXECUTABLE})
     endif()
 else()
-    find_package(Python3 3.6 COMPONENTS Interpreter QUIET)
+    find_package(Python 3.6 COMPONENTS Interpreter QUIET)
 endif()
 
 # Use the Cython executable that lives next to the Python executable
 # if it is a local installation.
-if(Python3_EXECUTABLE)
-  get_filename_component(_python_path ${Python3_EXECUTABLE} PATH)
+if(Python_EXECUTABLE)
+  get_filename_component(_python_path ${Python_EXECUTABLE} PATH)
   find_program(Cythonize_EXECUTABLE
     NAMES cythonize3 cythonize cythonize.bat
     HINTS ${_python_path})

cmake/Modules/GTest.cmake

@@ -1,81 +0,0 @@
-message(STATUS "Downloading and building Google Test library")
-
-if(CMAKE_BUILD_TYPE STREQUAL "Debug")
-  set(GTEST_LIB_POSTFIX d)
-else()
-  set(GTEST_LIB_POSTFIX)
-endif()
-
-include(ExternalProject)
-set(GTEST_URL "https://github.com/google/googletest/archive/release-1.10.0.tar.gz" CACHE STRING "URL for GTest tarball")
-set(GTEST_MD5 "ecd1fa65e7de707cd5c00bdac56022cd" CACHE STRING "MD5 checksum of GTest tarball")
-mark_as_advanced(GTEST_URL)
-mark_as_advanced(GTEST_MD5)
-ExternalProject_Add(googletest
-                    URL             ${GTEST_URL}
-                    URL_MD5         ${GTEST_MD5}
-                    SOURCE_DIR      "${CMAKE_BINARY_DIR}/gtest-src"
-                    BINARY_DIR      "${CMAKE_BINARY_DIR}/gtest-build"
-                    CMAKE_ARGS      ${CMAKE_REQUEST_PIC} ${CMAKE_EXTRA_GTEST_OPTS}
-                                    -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-                                    -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR>
-                                    -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-                                    -DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}
-                                    -DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}
-                    BUILD_BYPRODUCTS <BINARY_DIR>/lib/libgtest${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
-                                     <BINARY_DIR>/lib/libgmock${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
-                                     <BINARY_DIR>/lib/libgtest_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
-                                     <BINARY_DIR>/lib/libgmock_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
-                    LOG_DOWNLOAD ON
-                    LOG_CONFIGURE ON
-                    LOG_BUILD ON
-                    INSTALL_COMMAND ""
-                    TEST_COMMAND    "")
-
-ExternalProject_Get_Property(googletest SOURCE_DIR)
-set(GTEST_INCLUDE_DIR ${SOURCE_DIR}/googletest/include)
-set(GMOCK_INCLUDE_DIR ${SOURCE_DIR}/googlemock/include)
-
-# workaround for CMake 3.10 on ubuntu 18.04
-file(MAKE_DIRECTORY ${GTEST_INCLUDE_DIR})
-file(MAKE_DIRECTORY ${GMOCK_INCLUDE_DIR})
-
-ExternalProject_Get_Property(googletest BINARY_DIR)
-set(GTEST_LIBRARY_PATH ${BINARY_DIR}/lib/libgtest${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
-set(GMOCK_LIBRARY_PATH ${BINARY_DIR}/lib/libgmock${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
-set(GTEST_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/libgtest_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
-set(GMOCK_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/libgmock_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
-
-# Prevent GoogleTest from overriding our compiler/linker options
-# when building with Visual Studio
-set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
-
-find_package(Threads QUIET)
-
-add_library(GTest::GTest UNKNOWN IMPORTED)
-set_target_properties(GTest::GTest PROPERTIES
-        IMPORTED_LOCATION ${GTEST_LIBRARY_PATH}
-        INTERFACE_INCLUDE_DIRECTORIES ${GTEST_INCLUDE_DIR}
-        INTERFACE_LINK_LIBRARIES "${CMAKE_THREAD_LIBS_INIT}")
-add_dependencies(GTest::GTest googletest)
-
-add_library(GTest::GMock UNKNOWN IMPORTED)
-set_target_properties(GTest::GMock PROPERTIES
-        IMPORTED_LOCATION ${GMOCK_LIBRARY_PATH}
-        INTERFACE_INCLUDE_DIRECTORIES ${GMOCK_INCLUDE_DIR}
-        INTERFACE_LINK_LIBRARIES "${CMAKE_THREAD_LIBS_INIT}")
-add_dependencies(GTest::GMock googletest)
-
-add_library(GTest::GTestMain UNKNOWN IMPORTED)
-set_target_properties(GTest::GTestMain PROPERTIES
-        IMPORTED_LOCATION ${GTEST_MAIN_LIBRARY_PATH}
-        INTERFACE_INCLUDE_DIRECTORIES ${GTEST_INCLUDE_DIR}
-        INTERFACE_LINK_LIBRARIES "${CMAKE_THREAD_LIBS_INIT}")
-add_dependencies(GTest::GTestMain googletest)
-
-add_library(GTest::GMockMain UNKNOWN IMPORTED)
-set_target_properties(GTest::GMockMain PROPERTIES
-        IMPORTED_LOCATION ${GMOCK_MAIN_LIBRARY_PATH}
-        INTERFACE_INCLUDE_DIRECTORIES ${GMOCK_INCLUDE_DIR}
-        INTERFACE_LINK_LIBRARIES "${CMAKE_THREAD_LIBS_INIT}")
-add_dependencies(GTest::GMockMain googletest)

cmake/Modules/LAMMPSUtils.cmake

@@ -25,7 +25,7 @@ function(validate_option name values)
 endfunction(validate_option)
 
 function(get_lammps_version version_header variable)
-    file(READ ${version_header} line)
+    file(STRINGS ${version_header} line REGEX LAMMPS_VERSION)
     set(MONTHS x Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec)
     string(REGEX REPLACE "#define LAMMPS_VERSION \"([0-9]+) ([A-Za-z]+) ([0-9]+)\"" "\\1" day "${line}")
     string(REGEX REPLACE "#define LAMMPS_VERSION \"([0-9]+) ([A-Za-z]+) ([0-9]+)\"" "\\2" month "${line}")
@@ -85,7 +85,7 @@ endfunction(GenerateBinaryHeader)
 
 # fetch missing potential files
 function(FetchPotentials pkgfolder potfolder)
-  if (EXISTS "${pkgfolder}/potentials.txt")
+  if(EXISTS "${pkgfolder}/potentials.txt")
     file(STRINGS "${pkgfolder}/potentials.txt" linelist REGEX "^[^#].")
     foreach(line ${linelist})
       string(FIND ${line} " " blank)

cmake/Modules/OpenCLLoader.cmake

@@ -1,50 +1,11 @@
 message(STATUS "Downloading and building OpenCL loader library")
-set(OPENCL_LOADER_URL "${LAMMPS_THIRDPARTY_URL}/opencl-loader-2021.09.18.tar.gz" CACHE STRING "URL for OpenCL loader tarball")
-set(OPENCL_LOADER_MD5 "3b3882627964bd02e5c3b02065daac3c" CACHE STRING "MD5 checksum of OpenCL loader tarball")
+set(OPENCL_LOADER_URL "${LAMMPS_THIRDPARTY_URL}/opencl-loader-2022.01.04.tar.gz" CACHE STRING "URL for OpenCL loader tarball")
+set(OPENCL_LOADER_MD5 "8d3a801e87a2c6653bf0e27707063914" CACHE STRING "MD5 checksum of OpenCL loader tarball")
 mark_as_advanced(OPENCL_LOADER_URL)
 mark_as_advanced(OPENCL_LOADER_MD5)
 
-include(ExternalProject)
-ExternalProject_Add(opencl_loader
-                    URL             ${OPENCL_LOADER_URL}
-                    URL_MD5         ${OPENCL_LOADER_MD5}
-                    SOURCE_DIR      "${CMAKE_BINARY_DIR}/opencl_loader-src"
-                    BINARY_DIR      "${CMAKE_BINARY_DIR}/opencl_loader-build"
-                    CMAKE_ARGS      ${CMAKE_REQUEST_PIC} ${CMAKE_EXTRA_OPENCL_LOADER_OPTS}
-                                    -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-                                    -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR>
-                                    -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-                                    -DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}
-                                    -DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}
-                    BUILD_BYPRODUCTS <BINARY_DIR>/libOpenCL${CMAKE_STATIC_LIBRARY_SUFFIX}
-                    LOG_DOWNLOAD ON
-                    LOG_CONFIGURE ON
-                    LOG_BUILD ON
-                    INSTALL_COMMAND ""
-                    TEST_COMMAND    "")
-
-ExternalProject_Get_Property(opencl_loader SOURCE_DIR)
-set(OPENCL_LOADER_INCLUDE_DIR ${SOURCE_DIR}/inc)
-
-# workaround for CMake 3.10 on ubuntu 18.04
-file(MAKE_DIRECTORY ${OPENCL_LOADER_INCLUDE_DIR})
-
-ExternalProject_Get_Property(opencl_loader BINARY_DIR)
-set(OPENCL_LOADER_LIBRARY_PATH "${BINARY_DIR}/libOpenCL${CMAKE_STATIC_LIBRARY_SUFFIX}")
-
-find_package(Threads QUIET)
-if(NOT WIN32)
-  set(OPENCL_LOADER_DEP_LIBS "Threads::Threads;${CMAKE_DL_LIBS}")
-else()
-  set(OPENCL_LOADER_DEP_LIBS "cfgmgr32;runtimeobject")
-endif()
-
-add_library(OpenCL::OpenCL UNKNOWN IMPORTED)
-add_dependencies(OpenCL::OpenCL opencl_loader)
-
-set_target_properties(OpenCL::OpenCL PROPERTIES
-  IMPORTED_LOCATION ${OPENCL_LOADER_LIBRARY_PATH}
-  INTERFACE_INCLUDE_DIRECTORIES ${OPENCL_LOADER_INCLUDE_DIR}
-  INTERFACE_LINK_LIBRARIES "${OPENCL_LOADER_DEP_LIBS}")
-
+set(INSTALL_LIBOPENCL OFF CACHE BOOL "" FORCE)
+include(ExternalCMakeProject)
+ExternalCMakeProject(opencl_loader ${OPENCL_LOADER_URL} ${OPENCL_LOADER_MD5} opencl-loader . "")
 
+add_library(OpenCL::OpenCL ALIAS OpenCL)

cmake/Modules/Packages/COMPRESS.cmake

@@ -1,10 +1,11 @@
 find_package(ZLIB REQUIRED)
 target_link_libraries(lammps PRIVATE ZLIB::ZLIB)
 
-find_package(PkgConfig REQUIRED)
-pkg_check_modules(Zstd IMPORTED_TARGET libzstd>=1.4)
-
-if(Zstd_FOUND)
+find_package(PkgConfig QUIET)
+if(PkgConfig_FOUND)
+  pkg_check_modules(Zstd IMPORTED_TARGET libzstd>=1.4)
+  if(Zstd_FOUND)
     target_compile_definitions(lammps PRIVATE -DLAMMPS_ZSTD)
     target_link_libraries(lammps PRIVATE PkgConfig::Zstd)
+  endif()
 endif()

cmake/Modules/Packages/GPU.cmake

@@ -217,13 +217,20 @@ elseif(GPU_API STREQUAL "OPENCL")
 elseif(GPU_API STREQUAL "HIP")
   if(NOT DEFINED HIP_PATH)
       if(NOT DEFINED ENV{HIP_PATH})
-          set(HIP_PATH "/opt/rocm/hip" CACHE PATH "Path to which HIP has been installed")
+          set(HIP_PATH "/opt/rocm/hip" CACHE PATH "Path to HIP installation")
       else()
-          set(HIP_PATH $ENV{HIP_PATH} CACHE PATH "Path to which HIP has been installed")
+          set(HIP_PATH $ENV{HIP_PATH} CACHE PATH "Path to HIP installation")
       endif()
   endif()
-  set(CMAKE_MODULE_PATH "${HIP_PATH}/cmake" ${CMAKE_MODULE_PATH})
-  find_package(HIP REQUIRED)
+  if(NOT DEFINED ROCM_PATH)
+      if(NOT DEFINED ENV{ROCM_PATH})
+          set(ROCM_PATH "/opt/rocm" CACHE PATH "Path to ROCm installation")
+      else()
+          set(ROCM_PATH $ENV{ROCM_PATH} CACHE PATH "Path to ROCm installation")
+      endif()
+  endif()
+  list(APPEND CMAKE_PREFIX_PATH ${HIP_PATH} ${ROCM_PATH})
+  find_package(hip REQUIRED)
   option(HIP_USE_DEVICE_SORT "Use GPU sorting" ON)
 
   if(NOT DEFINED HIP_PLATFORM)
@@ -299,12 +306,12 @@ elseif(GPU_API STREQUAL "HIP")
 
         if(HIP_COMPILER STREQUAL "clang")
           add_custom_command(OUTPUT ${CUBIN_FILE}
-            VERBATIM COMMAND ${HIP_HIPCC_EXECUTABLE} --genco --offload-arch=${HIP_ARCH} -O3 -ffast-math -DUSE_HIP -D_${GPU_PREC_SETTING} -DLAMMPS_${LAMMPS_SIZES} -I${LAMMPS_LIB_SOURCE_DIR}/gpu -o ${CUBIN_FILE} ${CU_CPP_FILE}
+            VERBATIM COMMAND ${HIP_HIPCC_EXECUTABLE} --genco --offload-arch=${HIP_ARCH} -O3 -DUSE_HIP -D_${GPU_PREC_SETTING} -DLAMMPS_${LAMMPS_SIZES} -I${LAMMPS_LIB_SOURCE_DIR}/gpu -o ${CUBIN_FILE} ${CU_CPP_FILE}
             DEPENDS ${CU_CPP_FILE}
             COMMENT "Generating ${CU_NAME}.cubin")
         else()
           add_custom_command(OUTPUT ${CUBIN_FILE}
-            VERBATIM COMMAND ${HIP_HIPCC_EXECUTABLE} --genco -t="${HIP_ARCH}" -f=\"-O3 -ffast-math -DUSE_HIP -D_${GPU_PREC_SETTING} -DLAMMPS_${LAMMPS_SIZES} -I${LAMMPS_LIB_SOURCE_DIR}/gpu\" -o ${CUBIN_FILE} ${CU_CPP_FILE}
+            VERBATIM COMMAND ${HIP_HIPCC_EXECUTABLE} --genco -t="${HIP_ARCH}" -f=\"-O3 -DUSE_HIP -D_${GPU_PREC_SETTING} -DLAMMPS_${LAMMPS_SIZES} -I${LAMMPS_LIB_SOURCE_DIR}/gpu\" -o ${CUBIN_FILE} ${CU_CPP_FILE}
             DEPENDS ${CU_CPP_FILE}
             COMMENT "Generating ${CU_NAME}.cubin")
         endif()
@@ -325,10 +332,11 @@ elseif(GPU_API STREQUAL "HIP")
 
   set_directory_properties(PROPERTIES ADDITIONAL_MAKE_CLEAN_FILES "${LAMMPS_LIB_BINARY_DIR}/gpu/*_cubin.h ${LAMMPS_LIB_BINARY_DIR}/gpu/*.cu.cpp")
 
-  hip_add_library(gpu STATIC ${GPU_LIB_SOURCES})
+  add_library(gpu STATIC ${GPU_LIB_SOURCES})
   target_include_directories(gpu PRIVATE ${LAMMPS_LIB_BINARY_DIR}/gpu)
   target_compile_definitions(gpu PRIVATE -D_${GPU_PREC_SETTING} -DMPI_GERYON -DUCL_NO_EXIT)
   target_compile_definitions(gpu PRIVATE -DUSE_HIP)
+  target_link_libraries(gpu PRIVATE hip::host)
 
   if(HIP_USE_DEVICE_SORT)
     # add hipCUB
@@ -377,8 +385,9 @@ elseif(GPU_API STREQUAL "HIP")
     endif()
   endif()
 
-  hip_add_executable(hip_get_devices ${LAMMPS_LIB_SOURCE_DIR}/gpu/geryon/ucl_get_devices.cpp)
+  add_executable(hip_get_devices ${LAMMPS_LIB_SOURCE_DIR}/gpu/geryon/ucl_get_devices.cpp)
   target_compile_definitions(hip_get_devices PRIVATE -DUCL_HIP)
+  target_link_libraries(hip_get_devices hip::host)
 
   if(HIP_PLATFORM STREQUAL "nvcc")
     target_compile_definitions(gpu PRIVATE -D__HIP_PLATFORM_NVCC__)
@@ -413,13 +422,12 @@ RegisterStylesExt(${GPU_SOURCES_DIR} gpu GPU_SOURCES)
 RegisterFixStyle(${GPU_SOURCES_DIR}/fix_gpu.h)
 
 get_property(GPU_SOURCES GLOBAL PROPERTY GPU_SOURCES)
-
-if(NOT BUILD_MPI)
-  # mpistubs is aliased to MPI::MPI_CXX, but older versions of cmake won't work forward the include path
-  target_link_libraries(gpu PRIVATE mpi_stubs)
-else()
+if(BUILD_MPI)
   target_link_libraries(gpu PRIVATE MPI::MPI_CXX)
+else()
+  target_link_libraries(gpu PRIVATE mpi_stubs)
 endif()
+
 target_compile_definitions(gpu PRIVATE -DLAMMPS_${LAMMPS_SIZES})
 set_target_properties(gpu PROPERTIES OUTPUT_NAME lammps_gpu${LAMMPS_MACHINE})
 target_sources(lammps PRIVATE ${GPU_SOURCES})

cmake/Modules/Packages/KOKKOS.cmake

@@ -1,6 +1,8 @@
 ########################################################################
 # As of version 3.3.0 Kokkos requires C++14
-set(CMAKE_CXX_STANDARD 14)
+if(CMAKE_CXX_STANDARD LESS 14)
+  message(FATAL_ERROR "The KOKKOS package requires the C++ standard to be set to at least C++14")
+endif()
 ########################################################################
 # consistency checks and Kokkos options/settings required by LAMMPS
 if(Kokkos_ENABLE_CUDA)
@@ -9,8 +11,14 @@ if(Kokkos_ENABLE_CUDA)
 endif()
 # Adding OpenMP compiler flags without the checks done for
 # BUILD_OMP can result in compile failures. Enforce consistency.
-if(Kokkos_ENABLE_OPENMP AND NOT BUILD_OMP)
-  message(FATAL_ERROR "Must enable BUILD_OMP with Kokkos_ENABLE_OPENMP")
+if(Kokkos_ENABLE_OPENMP)
+  if(NOT BUILD_OMP)
+    message(FATAL_ERROR "Must enable BUILD_OMP with Kokkos_ENABLE_OPENMP")
+  else()
+    if(LAMMPS_OMP_COMPAT_LEVEL LESS 4)
+      message(FATAL_ERROR "Compiler must support OpenMP 4.0 or later with Kokkos_ENABLE_OPENMP")
+    endif()
+  endif()
 endif()
 ########################################################################
 
@@ -25,6 +33,8 @@ if(DOWNLOAD_KOKKOS)
   endforeach()
   message(STATUS "KOKKOS download requested - we will build our own")
   list(APPEND KOKKOS_LIB_BUILD_ARGS "-DCMAKE_INSTALL_PREFIX=<INSTALL_DIR>")
+  # build KOKKOS downloaded libraries as static libraries but with PIC, if needed
+  list(APPEND KOKKOS_LIB_BUILD_ARGS "-DBUILD_SHARED_LIBS=OFF")
   if(CMAKE_REQUEST_PIC)
     list(APPEND KOKKOS_LIB_BUILD_ARGS ${CMAKE_REQUEST_PIC})
   endif()
@@ -37,35 +47,48 @@ if(DOWNLOAD_KOKKOS)
   list(APPEND KOKKOS_LIB_BUILD_ARGS "-DCMAKE_CXX_EXTENSIONS=${CMAKE_CXX_EXTENSIONS}")
   list(APPEND KOKKOS_LIB_BUILD_ARGS "-DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}")
   include(ExternalProject)
-  set(KOKKOS_URL "https://github.com/kokkos/kokkos/archive/3.4.01.tar.gz" CACHE STRING "URL for KOKKOS tarball")
-  set(KOKKOS_MD5 "4c84698917c93a18985b311bb6caf84f" CACHE STRING "MD5 checksum of KOKKOS tarball")
+  set(KOKKOS_URL "https://github.com/kokkos/kokkos/archive/3.5.00.tar.gz" CACHE STRING "URL for KOKKOS tarball")
+  set(KOKKOS_MD5 "079323d973ae0e1c38c0a54a150c674e" CACHE STRING "MD5 checksum of KOKKOS tarball")
   mark_as_advanced(KOKKOS_URL)
   mark_as_advanced(KOKKOS_MD5)
   ExternalProject_Add(kokkos_build
     URL     ${KOKKOS_URL}
     URL_MD5 ${KOKKOS_MD5}
     CMAKE_ARGS ${KOKKOS_LIB_BUILD_ARGS}
-    BUILD_BYPRODUCTS <INSTALL_DIR>/lib/libkokkoscore.a
+    BUILD_BYPRODUCTS <INSTALL_DIR>/lib/libkokkoscore.a <INSTALL_DIR>/lib/libkokkoscontainers.a
   )
   ExternalProject_get_property(kokkos_build INSTALL_DIR)
   file(MAKE_DIRECTORY ${INSTALL_DIR}/include)
-  add_library(LAMMPS::KOKKOS UNKNOWN IMPORTED)
-  set_target_properties(LAMMPS::KOKKOS PROPERTIES
+  add_library(LAMMPS::KOKKOSCORE UNKNOWN IMPORTED)
+  add_library(LAMMPS::KOKKOSCONTAINERS UNKNOWN IMPORTED)
+  set_target_properties(LAMMPS::KOKKOSCORE PROPERTIES
     IMPORTED_LOCATION "${INSTALL_DIR}/lib/libkokkoscore.a"
     INTERFACE_INCLUDE_DIRECTORIES "${INSTALL_DIR}/include"
     INTERFACE_LINK_LIBRARIES ${CMAKE_DL_LIBS})
-  target_link_libraries(lammps PRIVATE LAMMPS::KOKKOS)
-  target_link_libraries(lmp PRIVATE LAMMPS::KOKKOS)
-  add_dependencies(LAMMPS::KOKKOS kokkos_build)
+  set_target_properties(LAMMPS::KOKKOSCONTAINERS PROPERTIES
+    IMPORTED_LOCATION "${INSTALL_DIR}/lib/libkokkoscontainers.a")
+  target_link_libraries(lammps PRIVATE LAMMPS::KOKKOSCORE LAMMPS::KOKKOSCONTAINERS)
+  target_link_libraries(lmp PRIVATE LAMMPS::KOKKOSCORE LAMMPS::KOKKOSCONTAINERS)
+  add_dependencies(LAMMPS::KOKKOSCORE kokkos_build)
+  add_dependencies(LAMMPS::KOKKOSCONTAINERS kokkos_build)
 elseif(EXTERNAL_KOKKOS)
-  find_package(Kokkos 3.4.01 REQUIRED CONFIG)
+  find_package(Kokkos 3.5.00 REQUIRED CONFIG)
   target_link_libraries(lammps PRIVATE Kokkos::kokkos)
   target_link_libraries(lmp PRIVATE Kokkos::kokkos)
 else()
   set(LAMMPS_LIB_KOKKOS_SRC_DIR ${LAMMPS_LIB_SOURCE_DIR}/kokkos)
   set(LAMMPS_LIB_KOKKOS_BIN_DIR ${LAMMPS_LIB_BINARY_DIR}/kokkos)
+  # build KOKKOS internal libraries as static libraries but with PIC, if needed
+  if(BUILD_SHARED_LIBS)
+    set(BUILD_SHARED_LIBS_WAS_ON YES)
+    set(BUILD_SHARED_LIBS OFF)
+  endif()
+  if(CMAKE_REQUEST_PIC)
+    set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+  endif()
   add_subdirectory(${LAMMPS_LIB_KOKKOS_SRC_DIR} ${LAMMPS_LIB_KOKKOS_BIN_DIR})
 
+
   set(Kokkos_INCLUDE_DIRS ${LAMMPS_LIB_KOKKOS_SRC_DIR}/core/src
                           ${LAMMPS_LIB_KOKKOS_SRC_DIR}/containers/src
                           ${LAMMPS_LIB_KOKKOS_SRC_DIR}/algorithms/src
@@ -73,6 +96,9 @@ else()
   target_include_directories(lammps PRIVATE ${Kokkos_INCLUDE_DIRS})
   target_link_libraries(lammps PRIVATE kokkos)
   target_link_libraries(lmp PRIVATE kokkos)
+  if(BUILD_SHARED_LIBS_WAS_ON)
+    set(BUILD_SHARED_LIBS ON)
+  endif()
 endif()
 target_compile_definitions(lammps PUBLIC $<BUILD_INTERFACE:LMP_KOKKOS>)
 
@@ -107,6 +133,12 @@ if(PKG_KSPACE)
   endif()
 endif()
 
+
+if(PKG_PHONON)
+  list(APPEND KOKKOS_PKG_SOURCES ${KOKKOS_PKG_SOURCES_DIR}/dynamical_matrix_kokkos.cpp)
+  list(APPEND KOKKOS_PKG_SOURCES ${KOKKOS_PKG_SOURCES_DIR}/third_order_kokkos.cpp)
+endif()
+
 set_property(GLOBAL PROPERTY "KOKKOS_PKG_SOURCES" "${KOKKOS_PKG_SOURCES}")
 
 # detects styles which have KOKKOS version

cmake/Modules/Packages/LATTE.cmake

@@ -19,6 +19,14 @@ if(DOWNLOAD_LATTE)
   set(LATTE_MD5 "820e73a457ced178c08c71389a385de7" CACHE STRING "MD5 checksum of LATTE tarball")
   mark_as_advanced(LATTE_URL)
   mark_as_advanced(LATTE_MD5)
+
+  # CMake cannot pass BLAS or LAPACK library variable to external project if they are a list
+  list(LENGTH BLAS_LIBRARIES} NUM_BLAS)
+  list(LENGTH LAPACK_LIBRARIES NUM_LAPACK)
+  if((NUM_BLAS GREATER 1) OR (NUM_LAPACK GREATER 1))
+    message(FATAL_ERROR "Cannot compile downloaded LATTE library due to a technical limitation")
+  endif()
+
   include(ExternalProject)
   ExternalProject_Add(latte_build
     URL     ${LATTE_URL}

cmake/Modules/Packages/MACHDYN.cmake

@@ -7,8 +7,9 @@ endif()
 option(DOWNLOAD_EIGEN3 "Download Eigen3 instead of using an already installed one)" ${DOWNLOAD_EIGEN3_DEFAULT})
 if(DOWNLOAD_EIGEN3)
   message(STATUS "Eigen3 download requested - we will build our own")
-  set(EIGEN3_URL "https://gitlab.com/libeigen/eigen/-/archive/3.3.9/eigen-3.3.9.tar.gz" CACHE STRING "URL for Eigen3 tarball")
-  set(EIGEN3_MD5 "609286804b0f79be622ccf7f9ff2b660" CACHE STRING "MD5 checksum of Eigen3 tarball")
+
+  set(EIGEN3_URL "${LAMMPS_THIRDPARTY_URL}/eigen-3.4.0.tar.gz" CACHE STRING "URL for Eigen3 tarball")
+  set(EIGEN3_MD5 "4c527a9171d71a72a9d4186e65bea559" CACHE STRING "MD5 checksum of Eigen3 tarball")
   mark_as_advanced(EIGEN3_URL)
   mark_as_advanced(EIGEN3_MD5)
   include(ExternalProject)

cmake/Modules/Packages/ML-HDNNP.cmake

@@ -45,13 +45,11 @@ if(DOWNLOAD_N2P2)
     # get path to MPI include directory when cross-compiling to windows
     if((CMAKE_SYSTEM_NAME STREQUAL Windows) AND CMAKE_CROSSCOMPILING)
       get_target_property(N2P2_MPI_INCLUDE MPI::MPI_CXX INTERFACE_INCLUDE_DIRECTORIES)
-      set(N2P2_PROJECT_OPTIONS "-I ${N2P2_MPI_INCLUDE} -DMPICH_SKIP_MPICXX=1")
-      set(MPI_CXX_COMPILER ${CMAKE_CXX_COMPILER})
+      set(N2P2_PROJECT_OPTIONS "-I${N2P2_MPI_INCLUDE}")
     endif()
     if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
       get_target_property(N2P2_MPI_INCLUDE MPI::MPI_CXX INTERFACE_INCLUDE_DIRECTORIES)
-      set(N2P2_PROJECT_OPTIONS "-I ${N2P2_MPI_INCLUDE} -DMPICH_SKIP_MPICXX=1")
-      set(MPI_CXX_COMPILER ${CMAKE_CXX_COMPILER})
+      set(N2P2_PROJECT_OPTIONS "-I${N2P2_MPI_INCLUDE}")
     endif()
   endif()
 
@@ -64,11 +62,17 @@ if(DOWNLOAD_N2P2)
   string(TOUPPER "${CMAKE_BUILD_TYPE}" BTYPE)
   set(N2P2_BUILD_FLAGS "${CMAKE_SHARED_LIBRARY_CXX_FLAGS} ${CMAKE_CXX_FLAGS} ${CMAKE_CXX_FLAGS_${BTYPE}} ${N2P2_CXX_STD}")
   set(N2P2_BUILD_OPTIONS INTERFACES=LAMMPS COMP=${N2P2_COMP} "PROJECT_OPTIONS=${N2P2_PROJECT_OPTIONS}" "PROJECT_DEBUG="
-    "PROJECT_CC=${CMAKE_CXX_COMPILER}" "PROJECT_MPICC=${MPI_CXX_COMPILER}" "PROJECT_CFLAGS=${N2P2_BUILD_FLAGS}"
-    "PROJECT_AR=${N2P2_AR}")
+    "PROJECT_CC=${CMAKE_CXX_COMPILER}" "PROJECT_MPICC=${CMAKE_CXX_COMPILER}" "PROJECT_CFLAGS=${N2P2_BUILD_FLAGS}"
+    "PROJECT_AR=${N2P2_AR}" "APP_CORE=nnp-convert" "APP_TRAIN=nnp-train" "APP=nnp-convert")
   # echo final flag for debugging
   message(STATUS "N2P2 BUILD OPTIONS: ${N2P2_BUILD_OPTIONS}")
 
+  # must have "sed" command to compile n2p2 library (for now)
+  find_program(HAVE_SED sed)
+  if(NOT HAVE_SED)
+    message(FATAL_ERROR "Must have 'sed' program installed to compile 'n2p2' library for ML-HDNNP package")
+  endif()
+
   # download compile n2p2 library. much patch MPI calls in LAMMPS interface to accommodate MPI-2 (e.g. for cross-compiling)
   include(ExternalProject)
   ExternalProject_Add(n2p2_build

cmake/Modules/Packages/ML-PACE.cmake

@@ -1,11 +1,11 @@
+set(PACELIB_URL "https://github.com/ICAMS/lammps-user-pace/archive/refs/tags/v.2021.10.25.tar.gz" CACHE STRING "URL for PACE evaluator library sources")
 
-set(PACELIB_URL "https://github.com/ICAMS/lammps-user-pace/archive/refs/tags/v.2021.4.9.tar.gz" CACHE STRING "URL for PACE evaluator library sources")
-set(PACELIB_MD5 "4db54962fbd6adcf8c18d46e1798ceb5" CACHE STRING "MD5 checksum of PACE evaluator library tarball")
+set(PACELIB_MD5 "a2ac3315c41a1a4a5c912bcb1bc9c5cc" CACHE STRING "MD5 checksum of PACE evaluator library tarball")
 mark_as_advanced(PACELIB_URL)
 mark_as_advanced(PACELIB_MD5)
 
 # download library sources to build folder
-file(DOWNLOAD ${PACELIB_URL} ${CMAKE_BINARY_DIR}/libpace.tar.gz SHOW_PROGRESS EXPECTED_HASH MD5=${PACELIB_MD5})
+file(DOWNLOAD ${PACELIB_URL} ${CMAKE_BINARY_DIR}/libpace.tar.gz EXPECTED_HASH MD5=${PACELIB_MD5}) #SHOW_PROGRESS
 
 # uncompress downloaded sources
 execute_process(
@@ -14,12 +14,19 @@ execute_process(
   WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
 )
 
-file(GLOB PACE_EVALUATOR_INCLUDE_DIR ${CMAKE_BINARY_DIR}/lammps-user-pace-*/USER-PACE)
-file(GLOB PACE_EVALUATOR_SOURCES ${CMAKE_BINARY_DIR}/lammps-user-pace-*/USER-PACE/*.cpp)
+file(GLOB lib-pace ${CMAKE_BINARY_DIR}/lammps-user-pace-*)
+add_subdirectory(${lib-pace}/yaml-cpp build-yaml-cpp)
+set(YAML_CPP_INCLUDE_DIR ${lib-pace}/yaml-cpp/include)
+
+file(GLOB PACE_EVALUATOR_INCLUDE_DIR ${lib-pace}/ML-PACE)
+file(GLOB PACE_EVALUATOR_SOURCES ${lib-pace}/ML-PACE/*.cpp)
 list(FILTER PACE_EVALUATOR_SOURCES EXCLUDE REGEX pair_pace.cpp)
 
 add_library(pace STATIC ${PACE_EVALUATOR_SOURCES})
 set_target_properties(pace PROPERTIES CXX_EXTENSIONS ON OUTPUT_NAME lammps_pace${LAMMPS_MACHINE})
-target_include_directories(pace PUBLIC ${PACE_EVALUATOR_INCLUDE_DIR})
-target_link_libraries(lammps PRIVATE pace)
+target_include_directories(pace PUBLIC ${PACE_EVALUATOR_INCLUDE_DIR} ${YAML_CPP_INCLUDE_DIR})
 
+
+target_link_libraries(pace PRIVATE yaml-cpp-pace)
+
+target_link_libraries(lammps PRIVATE pace)

cmake/Modules/Packages/ML-QUIP.cmake

@@ -32,7 +32,8 @@ if(DOWNLOAD_QUIP)
   foreach(flag ${LAPACK_LIBRARIES})
     set(temp "${temp} ${flag}")
   endforeach()
-  set(temp "${temp}\n")
+  # Fix cmake crashing when MATH_LINKOPTS not set, required for e.g. recent Cray Programming Environment
+  set(temp "${temp} -L/_DUMMY_PATH_\n")
   set(temp "${temp}PYTHON=python\nPIP=pip\nEXTRA_LINKOPTS=\n")
   set(temp "${temp}HAVE_CP2K=0\nHAVE_VASP=0\nHAVE_TB=0\nHAVE_PRECON=1\nHAVE_LOTF=0\nHAVE_ONIOM=0\n")
   set(temp "${temp}HAVE_LOCAL_E_MIX=0\nHAVE_QC=0\nHAVE_GAP=1\nHAVE_DESCRIPTORS_NONCOMMERCIAL=1\n")
@@ -50,7 +51,7 @@ if(DOWNLOAD_QUIP)
     GIT_TAG origin/public
     GIT_SHALLOW YES
     GIT_PROGRESS YES
-    PATCH_COMMAND cp ${CMAKE_BINARY_DIR}/quip.config <SOURCE_DIR>/arch/Makefile.lammps
+    PATCH_COMMAND ${CMAKE_COMMAND} -E copy_if_different ${CMAKE_BINARY_DIR}/quip.config <SOURCE_DIR>/arch/Makefile.lammps
     CONFIGURE_COMMAND env QUIP_ARCH=lammps make config
     BUILD_COMMAND env QUIP_ARCH=lammps make libquip
     INSTALL_COMMAND ""

cmake/Modules/Packages/MSCG.cmake

@@ -12,34 +12,12 @@ if(DOWNLOAD_MSCG)
   mark_as_advanced(MSCG_URL)
   mark_as_advanced(MSCG_MD5)
 
-  include(ExternalProject)
-  ExternalProject_Add(mscg_build
-    URL     ${MSCG_URL}
-    URL_MD5 ${MSCG_MD5}
-    SOURCE_SUBDIR src/CMake
-    CMAKE_ARGS ${CMAKE_REQUEST_PIC} ${EXTRA_MSCG_OPTS}
-               -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
-               -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-               -DCMAKE_Fortran_COMPILER=${CMAKE_Fortran_COMPILER}
-               -DBLAS_LIBRARIES=${BLAS_LIBRARIES} -DLAPACK_LIBRARIES=${LAPACK_LIBRARIES}
-               -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR>
-               -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
-               -DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}
-               -DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}
-    BUILD_COMMAND ${CMAKE_COMMAND} --build . --target mscg
-    INSTALL_COMMAND ""
-    BUILD_BYPRODUCTS <BINARY_DIR>/libmscg.a
-    )
-  ExternalProject_get_property(mscg_build BINARY_DIR)
-  ExternalProject_get_property(mscg_build SOURCE_DIR)
-  file(MAKE_DIRECTORY ${SOURCE_DIR}/src)
-  add_library(LAMMPS::MSCG UNKNOWN IMPORTED)
-  set_target_properties(LAMMPS::MSCG PROPERTIES
-    IMPORTED_LOCATION "${BINARY_DIR}/libmscg.a"
-    INTERFACE_INCLUDE_DIRECTORIES "${SOURCE_DIR}/src"
-    INTERFACE_LINK_LIBRARIES "${LAPACK_LIBRARIES}")
-  target_link_libraries(lammps PRIVATE LAMMPS::MSCG)
-  add_dependencies(LAMMPS::MSCG mscg_build)
+  include(ExternalCMakeProject)
+  ExternalCMakeProject(mscg ${MSCG_URL} ${MSCG_MD5} MSCG-release src/CMake "")
+
+  # set include and link library
+  target_include_directories(lammps PRIVATE "${CMAKE_BINARY_DIR}/_deps/mscg-src/src")
+  target_link_libraries(lammps PRIVATE mscg)
 else()
   find_package(MSCG)
   if(NOT MSCG_FOUND)

cmake/Modules/Packages/PHONON.cmake

@@ -0,0 +1,9 @@
+# fix phonon may only be installed if also the FFT wrappers from KSPACE are installed
+if(NOT PKG_KSPACE)
+  get_property(LAMMPS_FIX_HEADERS GLOBAL PROPERTY FIX)
+  list(REMOVE_ITEM LAMMPS_FIX_HEADERS ${LAMMPS_SOURCE_DIR}/PHONON/fix_phonon.h)
+  set_property(GLOBAL PROPERTY FIX "${LAMMPS_FIX_HEADERS}")
+  get_target_property(LAMMPS_SOURCES lammps SOURCES)
+  list(REMOVE_ITEM LAMMPS_SOURCES ${LAMMPS_SOURCE_DIR}/PHONON/fix_phonon.cpp)
+  set_property(TARGET lammps PROPERTY SOURCES "${LAMMPS_SOURCES}")
+endif()

cmake/Modules/Packages/PLUMED.cmake

@@ -54,8 +54,8 @@ if(DOWNLOAD_PLUMED)
     set(PLUMED_BUILD_BYPRODUCTS "<INSTALL_DIR>/lib/libplumedWrapper.a")
   endif()
 
-  set(PLUMED_URL "https://github.com/plumed/plumed2/releases/download/v2.7.2/plumed-src-2.7.2.tgz" CACHE STRING "URL for PLUMED tarball")
-  set(PLUMED_MD5 "cfa0b4dd90a81c25d3302e8d97bfeaea" CACHE STRING "MD5 checksum of PLUMED tarball")
+  set(PLUMED_URL "https://github.com/plumed/plumed2/releases/download/v2.7.3/plumed-src-2.7.3.tgz" CACHE STRING "URL for PLUMED tarball")
+  set(PLUMED_MD5 "f00cc82edfefe6bb3df934911dbe32fb" CACHE STRING "MD5 checksum of PLUMED tarball")
 
   mark_as_advanced(PLUMED_URL)
   mark_as_advanced(PLUMED_MD5)

cmake/Modules/Packages/PYTHON.cmake

@@ -3,7 +3,7 @@ if(CMAKE_VERSION VERSION_LESS 3.12)
   target_include_directories(lammps PRIVATE ${PYTHON_INCLUDE_DIRS})
   target_link_libraries(lammps PRIVATE ${PYTHON_LIBRARIES})
 else()
-  find_package(Python REQUIRED COMPONENTS Development)
+  find_package(Python REQUIRED COMPONENTS Interpreter Development)
   target_link_libraries(lammps PRIVATE Python::Python)
 endif()
 target_compile_definitions(lammps PRIVATE -DLMP_PYTHON)

cmake/Modules/Packages/SCAFACOS.cmake

@@ -23,6 +23,11 @@ if(DOWNLOAD_SCAFACOS)
   file(DOWNLOAD ${LAMMPS_THIRDPARTY_URL}/scafacos-1.0.1-fix.diff ${CMAKE_CURRENT_BINARY_DIR}/scafacos-1.0.1.fix.diff
           EXPECTED_HASH MD5=4baa1333bb28fcce102d505e1992d032)
 
+  find_program(HAVE_PATCH patch)
+  if(NOT HAVE_PATCH)
+    message(FATAL_ERROR "The 'patch' program is required to build the ScaFaCoS library")
+  endif()
+
   include(ExternalProject)
   ExternalProject_Add(scafacos_build
     URL     ${SCAFACOS_URL}

cmake/Modules/Packages/VORONOI.cmake

@@ -26,6 +26,11 @@ if(DOWNLOAD_VORO)
     set(VORO_BUILD_OPTIONS CXX=${CMAKE_CXX_COMPILER} CFLAGS=${VORO_BUILD_CFLAGS})
   endif()
 
+  find_program(HAVE_PATCH patch)
+  if(NOT HAVE_PATCH)
+    message(FATAL_ERROR "The 'patch' program is required to build the voro++ library")
+  endif()
+
   ExternalProject_Add(voro_build
     URL     ${VORO_URL}
     URL_MD5 ${VORO_MD5}

cmake/Modules/Tools.cmake

@@ -25,7 +25,9 @@ if(BUILD_TOOLS)
   get_filename_component(MSI2LMP_SOURCE_DIR ${LAMMPS_TOOLS_DIR}/msi2lmp/src ABSOLUTE)
   file(GLOB MSI2LMP_SOURCES ${MSI2LMP_SOURCE_DIR}/[^.]*.c)
   add_executable(msi2lmp ${MSI2LMP_SOURCES})
-  target_link_libraries(msi2lmp PRIVATE ${MATH_LIBRARIES})
+  if(STANDARD_MATH_LIB)
+    target_link_libraries(msi2lmp PRIVATE ${STANDARD_MATH_LIB})
+  endif()
   install(TARGETS msi2lmp DESTINATION ${CMAKE_INSTALL_BINDIR})
   install(FILES ${LAMMPS_DOC_DIR}/msi2lmp.1 DESTINATION ${CMAKE_INSTALL_MANDIR}/man1)
 endif()

cmake/Modules/YAML.cmake

@@ -1,47 +0,0 @@
-message(STATUS "Downloading and building YAML library")
-
-include(ExternalProject)
-set(YAML_URL "https://pyyaml.org/download/libyaml/yaml-0.2.5.tar.gz" CACHE STRING "URL for libyaml tarball")
-set(YAML_MD5 "bb15429d8fb787e7d3f1c83ae129a999" CACHE STRING "MD5 checksum of libyaml tarball")
-mark_as_advanced(YAML_URL)
-mark_as_advanced(YAML_MD5)
-
-# support cross-compilation to windows
-if(CMAKE_CROSSCOMPILING AND (CMAKE_SYSTEM_NAME STREQUAL "Windows"))
-  if(CMAKE_SYSTEM_PROCESSOR STREQUAL "x86")
-    set(YAML_CROSS_HOST --host=i686-mingw64)
-  elseif(CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64")
-    set(YAML_CROSS_HOST --host=x86_64-mingw64)
-  else()
-    message(FATAL_ERROR "Unsupported cross-compilation "
-      " for ${CMAKE_SYSTEM_NAME}/${CMAKE_SYSTEM_PROCESSOR}"
-      " on ${CMAKE_HOST_SYSTEM}/${CMAKE_HOST_SYSTEM_PROCESSOR}")
-  endif()
-endif()
-
-ExternalProject_Add(libyaml
-                    URL               ${YAML_URL}
-                    URL_MD5           ${YAML_MD5}
-                    SOURCE_DIR        "${CMAKE_BINARY_DIR}/yaml-src"
-                    BINARY_DIR        "${CMAKE_BINARY_DIR}/yaml-build"
-                    CONFIGURE_COMMAND <SOURCE_DIR>/configure ${CONFIGURE_REQUEST_PIC}
-                                      CXX=${CMAKE_CXX_COMPILER} CC=${CMAKE_C_COMPILER}
-                                      --prefix=<INSTALL_DIR> --disable-shared ${YAML_CROSS_HOST}
-                    BUILD_BYPRODUCTS  <INSTALL_DIR>/lib/libyaml${CMAKE_STATIC_LIBRARY_SUFFIX}
-                    TEST_COMMAND      "")
-
-ExternalProject_Get_Property(libyaml INSTALL_DIR)
-set(YAML_INCLUDE_DIR ${INSTALL_DIR}/include)
-set(YAML_LIBRARY_DIR ${INSTALL_DIR}/lib)
-
-# workaround for CMake 3.10 on ubuntu 18.04
-file(MAKE_DIRECTORY ${YAML_INCLUDE_DIR})
-file(MAKE_DIRECTORY ${YAML_LIBRARY_DIR})
-
-set(YAML_LIBRARY_PATH ${INSTALL_DIR}/lib/libyaml${CMAKE_STATIC_LIBRARY_SUFFIX})
-
-add_library(Yaml::Yaml UNKNOWN IMPORTED)
-set_target_properties(Yaml::Yaml PROPERTIES
-        IMPORTED_LOCATION ${YAML_LIBRARY_PATH}
-        INTERFACE_INCLUDE_DIRECTORIES ${YAML_INCLUDE_DIR})
-add_dependencies(Yaml::Yaml libyaml)

cmake/Modules/generate_lmpgitversion.cmake

@@ -24,10 +24,10 @@ if(GIT_FOUND AND EXISTS ${LAMMPS_DIR}/.git)
     OUTPUT_STRIP_TRAILING_WHITESPACE)
 endif()
 
-set(temp "${temp}const bool LAMMPS_NS::LAMMPS::has_git_info = ${temp_git_info};\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_commit[] = \"${temp_git_commit}\";\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_branch[] = \"${temp_git_branch}\";\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_descriptor[] = \"${temp_git_describe}\";\n")
+set(temp "${temp}bool LAMMPS_NS::LAMMPS::has_git_info() { return ${temp_git_info}; }\n")
+set(temp "${temp}const char *LAMMPS_NS::LAMMPS::git_commit() { return \"${temp_git_commit}\"; }\n")
+set(temp "${temp}const char *LAMMPS_NS::LAMMPS::git_branch() { return \"${temp_git_branch}\"; }\n")
+set(temp "${temp}const char *LAMMPS_NS::LAMMPS::git_descriptor() { return \"${temp_git_describe}\"; }\n")
 set(temp "${temp}#endif\n\n")
 
 message(STATUS "Generating lmpgitversion.h...")

cmake/iwyu/iwyu-extra-map.imp

@@ -20,9 +20,14 @@
   { include: [ "@\"kspace_.*.h\"", public, "\"style_kspace.h\"", public ] },
   { include: [ "@\"nbin_.*.h\"", public, "\"style_nbin.h\"", public ] },
   { include: [ "@\"npair_.*.h\"", public, "\"style_npair.h\"", public ] },
-  { include: [ "@\"nstenci_.*.h\"", public, "\"style_nstencil.h\"", public ] },
+  { include: [ "@\"nstencil_.*.h\"", public, "\"style_nstencil.h\"", public ] },
   { include: [ "@\"ntopo_.*.h\"", public, "\"style_ntopo.h\"", public ] },
+  { include: [ "\"fmt/core.h\"", private, "\"fmt/format.h\"", public ] },
   { include: [ "<float.h>",   public, "<cfloat>", public ] },
+  { include: [ "\"float.h\"",   public, "<cfloat>", public ] },
   { include: [ "<limits.h>",  public, "<climits>", public ] },
+  { include: [ "\"limits.h\"",  public, "<climits>", public ] },
+  { include: [ "<stdio.h>",  public, "<cstdio>", public ] },
+  { include: [ "<bits/types/struct_rusage.h>", private, "<sys/types.h>", public ] },
   { include: [ "<bits/types/struct_tm.h>", private, "<ctime>", public ] },
 ]

cmake/presets/gcc.cmake

@@ -3,19 +3,19 @@
 set(CMAKE_CXX_COMPILER "g++" CACHE STRING "" FORCE)
 set(CMAKE_C_COMPILER "gcc" CACHE STRING "" FORCE)
 set(CMAKE_Fortran_COMPILER "gfortran" CACHE STRING "" FORCE)
-set(CMAKE_CXX_FLAGS_DEBUG "-Wall -g" CACHE STRING "" FORCE)
+set(CMAKE_CXX_FLAGS_DEBUG "-Wall -Og -g" CACHE STRING "" FORCE)
 set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "-g -O2 -DNDEBUG" CACHE STRING "" FORCE)
 set(CMAKE_CXX_FLAGS_RELEASE "-O3 -DNDEBUG" CACHE STRING "" FORCE)
 set(MPI_CXX "g++" CACHE STRING "" FORCE)
 set(MPI_CXX_COMPILER "mpicxx" CACHE STRING "" FORCE)
 set(MPI_C "gcc" CACHE STRING "" FORCE)
 set(MPI_C_COMPILER "mpicc" CACHE STRING "" FORCE)
-set(CMAKE_C_FLAGS_DEBUG "-Wall -g" CACHE STRING "" FORCE)
+set(CMAKE_C_FLAGS_DEBUG "-Wall -Og -g" CACHE STRING "" FORCE)
 set(CMAKE_C_FLAGS_RELWITHDEBINFO "-g -O2 -DNDEBUG" CACHE STRING "" FORCE)
 set(CMAKE_C_FLAGS_RELEASE "-O3 -DNDEBUG" CACHE STRING "" FORCE)
 set(MPI_Fortran "gfortran" CACHE STRING "" FORCE)
 set(MPI_Fortran_COMPILER "mpifort" CACHE STRING "" FORCE)
-set(CMAKE_Fortran_FLAGS_DEBUG "-Wall -g -std=f2003" CACHE STRING "" FORCE)
+set(CMAKE_Fortran_FLAGS_DEBUG "-Wall -Og -g -std=f2003" CACHE STRING "" FORCE)
 set(CMAKE_Fortran_FLAGS_RELWITHDEBINFO "-g -O2 -DNDEBUG -std=f2003" CACHE STRING "" FORCE)
 set(CMAKE_Fortran_FLAGS_RELEASE "-O3 -DNDEBUG -std=f2003" CACHE STRING "" FORCE)
 unset(HAVE_OMP_H_INCLUDE CACHE)

cmake/presets/hip_amd.cmake

@@ -0,0 +1,30 @@
+# preset that will enable hip (clang/clang++) with support for MPI and OpenMP (on Linux boxes)
+
+# prefer flang over gfortran, if available
+find_program(CLANG_FORTRAN NAMES flang gfortran f95)
+set(ENV{OMPI_FC} ${CLANG_FORTRAN})
+
+set(CMAKE_CXX_COMPILER "hipcc" CACHE STRING "" FORCE)
+set(CMAKE_C_COMPILER "hipcc" CACHE STRING "" FORCE)
+set(CMAKE_Fortran_COMPILER ${CLANG_FORTRAN} CACHE STRING "" FORCE)
+set(CMAKE_CXX_FLAGS_DEBUG "-Wall -Wextra -g" CACHE STRING "" FORCE)
+set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "-Wall -Wextra -g -O2 -DNDEBUG" CACHE STRING "" FORCE)
+set(CMAKE_CXX_FLAGS_RELEASE "-O3 -DNDEBUG" CACHE STRING "" FORCE)
+set(CMAKE_Fortran_FLAGS_DEBUG "-Wall -Wextra -g -std=f2003" CACHE STRING "" FORCE)
+set(CMAKE_Fortran_FLAGS_RELWITHDEBINFO "-Wall -Wextra -g -O2 -DNDEBUG -std=f2003" CACHE STRING "" FORCE)
+set(CMAKE_Fortran_FLAGS_RELEASE "-O3 -DNDEBUG -std=f2003" CACHE STRING "" FORCE)
+set(CMAKE_C_FLAGS_DEBUG "-Wall -Wextra -g" CACHE STRING "" FORCE)
+set(CMAKE_C_FLAGS_RELWITHDEBINFO "-Wall -Wextra -g -O2 -DNDEBUG" CACHE STRING "" FORCE)
+set(CMAKE_C_FLAGS_RELEASE "-O3 -DNDEBUG" CACHE STRING "" FORCE)
+
+set(MPI_CXX "hipcc" CACHE STRING "" FORCE)
+set(MPI_CXX_COMPILER "mpicxx" CACHE STRING "" FORCE)
+
+unset(HAVE_OMP_H_INCLUDE CACHE)
+set(OpenMP_C "hipcc" CACHE STRING "" FORCE)
+set(OpenMP_C_FLAGS "-fopenmp" CACHE STRING "" FORCE)
+set(OpenMP_C_LIB_NAMES "omp" CACHE STRING "" FORCE)
+set(OpenMP_CXX "hipcc" CACHE STRING "" FORCE)
+set(OpenMP_CXX_FLAGS "-fopenmp" CACHE STRING "" FORCE)
+set(OpenMP_CXX_LIB_NAMES "omp" CACHE STRING "" FORCE)
+set(OpenMP_omp_LIBRARY "libomp.so" CACHE PATH "" FORCE)

cmake/presets/most.cmake

@@ -48,7 +48,6 @@ set(ALL_PACKAGES
   PHONON
   PLUGIN
   POEMS
-  PYTHON
   QEQ
   REACTION
   REAXFF

cmake/presets/windows.cmake

@@ -0,0 +1,64 @@
+set(WIN_PACKAGES
+  ASPHERE
+  BOCS
+  BODY
+  BROWNIAN
+  CG-DNA
+  CG-SDK
+  CLASS2
+  COLLOID
+  COLVARS
+  CORESHELL
+  DIELECTRIC
+  DIFFRACTION
+  DIPOLE
+  DPD-BASIC
+  DPD-MESO
+  DPD-REACT
+  DPD-SMOOTH
+  DRUDE
+  EFF
+  EXTRA-COMPUTE
+  EXTRA-DUMP
+  EXTRA-FIX
+  EXTRA-MOLECULE
+  EXTRA-PAIR
+  FEP
+  GRANULAR
+  INTERLAYER
+  KSPACE
+  MANIFOLD
+  MANYBODY
+  MC
+  MEAM
+  MISC
+  ML-IAP
+  ML-SNAP
+  MOFFF
+  MOLECULE
+  MOLFILE
+  OPENMP
+  ORIENT
+  PERI
+  PHONON
+  POEMS
+  PTM
+  QEQ
+  QTB
+  REACTION
+  REAXFF
+  REPLICA
+  RIGID
+  SHOCK
+  SMTBQ
+  SPH
+  SPIN
+  SRD
+  TALLY
+  UEF
+  YAFF)
+
+foreach(PKG ${WIN_PACKAGES})
+  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
+endforeach()
+

doc/Makefile

@@ -230,7 +230,7 @@ $(VENV):
 	)
 
 $(MATHJAX):
-	@git clone -b 3.2.0 -c advice.detachedHead=0 --depth 1 git://github.com/mathjax/MathJax.git $@
+	@git clone -b 3.2.0 -c advice.detachedHead=0 --depth 1 https://github.com/mathjax/MathJax.git $@
 
 $(ANCHORCHECK): $(VENV)
 	@( \

doc/doxygen/Doxyfile.in

@@ -435,6 +435,8 @@ INPUT                  = @LAMMPS_SOURCE_DIR@/utils.cpp                 \
                          @LAMMPS_SOURCE_DIR@/my_pool_chunk.cpp         \
                          @LAMMPS_SOURCE_DIR@/my_pool_chunk.h           \
                          @LAMMPS_SOURCE_DIR@/math_eigen.h              \
+                         @LAMMPS_SOURCE_DIR@/platform.h                \
+                         @LAMMPS_SOURCE_DIR@/platform.cpp              \
 
 # The EXCLUDE_SYMLINKS tag can be used to select whether or not files or
 # directories that are symbolic links (a Unix file system feature) are excluded

doc/github-development-workflow.md

@@ -33,9 +33,9 @@ when necessary.
 ## Pull Requests
 
 ALL changes to the LAMMPS code and documentation, however trivial, MUST
-be submitted as a pull request to GitHub. All changes to the "master"
+be submitted as a pull request to GitHub. All changes to the "develop"
 branch must be made exclusively through merging pull requests. The
-"unstable" and "stable" branches, respectively are only to be updated
+"release" and "stable" branches, respectively are only to be updated
 upon patch or stable releases with fast-forward merges based on the
 associated tags. Pull requests may also be submitted to (long-running)
 feature branches created by LAMMPS developers inside the LAMMPS project,
@@ -123,16 +123,16 @@ and thus were this comment should be placed.
 
 LAMMPS uses a continuous release development model with incremental
 changes, i.e. significant effort is made - including automated pre-merge
-testing - that the code in the branch "master" does not get easily
+testing - that the code in the branch "develop" does not get easily
 broken.  These tests are run after every update to a pull request.  More
 extensive and time consuming tests (including regression testing) are
-performed after code is merged to the "master" branch. There are patch
+performed after code is merged to the "develop" branch. There are patch
 releases of LAMMPS every 3-5 weeks at a point, when the LAMMPS
 developers feel, that a sufficient amount of changes have happened, and
 the post-merge testing has been successful. These patch releases are
-marked with a `patch_<version date>` tag and the "unstable" branch
+marked with a `patch_<version date>` tag and the "release" branch
 follows only these versions (and thus is always supposed to be of
-production quality, unlike "master", which may be temporary broken, in
+production quality, unlike "develop", which may be temporary broken, in
 the case of larger change sets or unexpected incompatibilities or side
 effects.
 

doc/lammps.1

@@ -1,4 +1,4 @@
-.TH LAMMPS "20 September 2021" "2021-09-20"
+.TH LAMMPS "1" "17 February 2022" "2022-2-17"
 .SH NAME
 .B LAMMPS
 \- Molecular Dynamics Simulator.

doc/msi2lmp.1

@@ -1,4 +1,4 @@
-.TH MSI2LMP "v3.9.9" "2018-11-05"
+.TH MSI2LMP "1" "v3.9.9" "2018-11-05"
 .SH NAME
 .B MSI2LMP
 \- Converter for Materials Studio files to LAMMPS

doc/src/Bibliography.rst

@@ -1123,9 +1123,12 @@ Bibliography
 **(Sun)**
    Sun, J. Phys. Chem. B, 102, 7338-7364 (1998).
 
-**(Surblys)**
+**(Surblys2019)**
    Surblys, Matsubara, Kikugawa, Ohara, Phys Rev E, 99, 051301(R) (2019).
 
+**(Surblys2021)**
+   Surblys, Matsubara, Kikugawa, Ohara, J Appl Phys 130, 215104 (2021).
+
 **(Sutmann)**
    Sutmann, Arnold, Fahrenberger, et. al., Physical review / E 88(6), 063308 (2013)
 

doc/src/Build_cmake.rst

@@ -150,6 +150,42 @@ for IDEs like Eclipse, CodeBlocks, or Kate can be selected using the *-G*
 command line flag.  A list of available generator settings for your
 specific CMake version is given when running ``cmake --help``.
 
+.. _cmake_multiconfig:
+
+Multi-configuration build systems
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Throughout this manual it is mostly assumed that LAMMPS is being built
+on a Unix-like operating system with "make" as the underlying "builder",
+since this is the most common case.  In this case the build "configuration"
+is chose using ``-D CMAKE_BUILD_TYPE=<configuration>`` with ``<configuration>``
+being one of "Release", "Debug", "RelWithDebInfo", or "MinSizeRel".
+Some build tools, however, can also use or even require to have a so-called
+multi-configuration build system setup.  For those the built type (or
+configuration) is chosen at compile time using the same build files. E.g.
+with:
+
+.. code-block:: bash
+
+   cmake --build build-multi --config Release
+
+In that case the resulting binaries are not in the build folder directly
+but in sub-directories corresponding to the build type (i.e. Release in
+the example from above).  Similarly, for running unit tests the
+configuration is selected with the *-C* flag:
+
+.. code-block:: bash
+
+   ctest -C Debug
+
+The CMake scripts in LAMMPS have basic support for being compiled using a
+multi-config build system, but not all of it has been ported.  This is in
+particular applicable to compiling packages that require additional libraries
+that would be downloaded and compiled by CMake.  The "windows" preset file
+tries to keep track of which packages can be compiled natively with the
+MSVC compilers out-of-the box.  Not all of those external libraries are
+portable to Windows either.
+
 
 Installing CMake
 ^^^^^^^^^^^^^^^^

doc/src/Build_development.rst

@@ -185,6 +185,10 @@ The ``ctest`` command has many options, the most important ones are:
      - run subset of tests matching the regular expression <regex>
    * - -E <regex>
      - exclude subset of tests matching the regular expression <regex>
+   * - -L <regex>
+     - run subset of tests with a label matching the regular expression <regex>
+   * - -LE <regex>
+     - exclude subset of tests with a label matching the regular expression <regex>
    * - -N
      - dry-run: display list of tests without running them
    * - -T memcheck
@@ -299,6 +303,12 @@ will destroy the original file, if the generation run does not complete,
 so using *-g* is recommended unless the YAML file is fully tested
 and working.
 
+Some of the force style tests are rather slow to run and some are very
+sensitive to small differences like CPU architecture, compiler
+toolchain, compiler optimization. Those tests are flagged with a "slow"
+and/or "unstable" label, and thus those tests can be selectively
+excluded with the ``-LE`` flag or selected with the ``-L`` flag.
+
 .. admonition:: Recommendations and notes for YAML files
    :class: note
 

doc/src/Build_diskspace.rst

@@ -14,7 +14,7 @@ environments with restricted disk space capacity it may be needed to
 reduce the storage requirements. Here are some suggestions:
 
 - Create a so-called shallow repository by cloning only the last commit
-  instead of the full project history by using ``git clone git@github.com:lammps/lammps --depth=1 --branch=master``.
+  instead of the full project history by using ``git clone git@github.com:lammps/lammps --depth=1 --branch=develop``.
   This reduces the downloaded size to about half.  With ``--depth=1`` it is not possible to check out different
   versions/branches of LAMMPS, using ``--depth=1000`` will make multiple recent versions available at little
   extra storage needs (the entire git history had nearly 30,000 commits in fall 2021).

doc/src/Build_extras.rst

@@ -341,6 +341,18 @@ minutes to hours) to build.  Of course you only need to do that once.)
          $ make lib-kim args="-p /usr/local" # use an existing KIM API installation at the provided location
          $ make lib-kim args="-p /usr/local -a EAM_Dynamo_Ackland_W__MO_141627196590_002" # ditto but add one model or driver
 
+      When using the "-b " option, the KIM library is built using its native
+      cmake build system.  The ``lib/kim/Install.py`` script supports a
+      ``CMAKE`` environment variable if the cmake executable is named other
+      than ``cmake`` on your system.  Additional environment variables may be
+      provided on the command line for use by cmake.  For example, to use the
+      ``cmake3`` executable and tell it to use the gnu version 11 compilers
+      to build KIM, one could use the following command line.
+
+      .. code-block:: bash
+
+         $ CMAKE=cmake3 CXX=g++-11 CC=gcc-11 FC=gfortran-11 make lib-kim args="-b "  # (re-)install KIM API lib using cmake3 and gnu v11 compilers with only example models
+
       Settings for debugging OpenKIM web queries discussed below need to
       be applied by adding them to the ``LMP_INC`` variable through
       editing the ``Makefile.machine`` you are using.  For example:
@@ -560,11 +572,26 @@ They must be specified in uppercase.
    *  - VEGA908
       - GPU
       - AMD GPU MI100 GFX908
-   *  - INTEL_GEN
+   *  - VEGA90A
       - GPU
-      - Intel GPUs Gen9+
+      - AMD GPU
+   *  - INTEL_DG1
+      - GPU
+      - Intel Iris XeMAX GPU
+   *  - INTEL_GEN9
+      - GPU
+      - Intel GPU Gen9
+   *  - INTEL_GEN11
+      - GPU
+      - Intel GPU Gen11
+   *  - INTEL_GEN12LP
+      - GPU
+      - Intel GPU Gen12LP
+   *  - INTEL_XEHP
+      - GPU
+      - Intel GPUs Xe-HP
 
-This list was last updated for version 3.4.1 of the Kokkos library.
+This list was last updated for version 3.5.0 of the Kokkos library.
 
 .. tabs::
 

doc/src/Build_manual.rst

@@ -33,12 +33,15 @@ various tools and files.  Some of them have to be installed (see below).  For
 the rest the build process will attempt to download and install them into
 a python virtual environment and local folders.
 
-A current version of the manual (latest patch release, aka unstable
-branch) is is available online at:
-`https://docs.lammps.org/Manual.html <https://docs.lammps.org/Manual.html>`_.
-A version of the manual corresponding to the ongoing development (aka master branch)
-is available online at: `https://docs.lammps.org/latest/
-<https://docs.lammps.org/latest/>`_
+A current version of the manual (latest patch release, that is the state
+of the *release* branch) is is available online at:
+`https://docs.lammps.org/ <https://docs.lammps.org/>`_.
+A version of the manual corresponding to the ongoing development (that is
+the state of the *develop* branch) is available online at:
+`https://docs.lammps.org/latest/ <https://docs.lammps.org/latest/>`_
+A version of the manual corresponding to the latest stable LAMMPS release
+(that is the state of the *stable* branch) is available online at:
+`https://docs.lammps.org/stable/ <https://docs.lammps.org/stable/>`_
 
 Build using GNU make
 --------------------

doc/src/Build_settings.rst

@@ -71,7 +71,8 @@ LAMMPS can use them if they are available on your system.
 
          -D FFTW3_INCLUDE_DIR=path   # path to FFTW3 include files
          -D FFTW3_LIBRARY=path       # path to FFTW3 libraries
-         -D FFT_FFTW_THREADS=on      # enable using threaded FFTW3 libraries
+         -D FFTW3_OMP_LIBRARY=path   # path to FFTW3 OpenMP wrapper libraries
+         -D FFT_FFTW_THREADS=on      # enable using OpenMP threaded FFTW3 libraries
          -D MKL_INCLUDE_DIR=path     # ditto for Intel MKL library
          -D FFT_MKL_THREADS=on       # enable using threaded FFTs with MKL libraries
          -D MKL_LIBRARY=path         # path to MKL libraries
@@ -320,9 +321,7 @@ following settings:
 
       .. code-block:: make
 
-         LMP_INC = -DLAMMPS_JPEG
-         LMP_INC = -DLAMMPS_PNG
-         LMP_INC = -DLAMMPS_FFMPEG
+         LMP_INC = -DLAMMPS_JPEG -DLAMMPS_PNG -DLAMMPS_FFMPEG  <other LMP_INC settings>
 
          JPG_INC = -I/usr/local/include   # path to jpeglib.h, png.h, zlib.h header files if make cannot find them
          JPG_PATH = -L/usr/lib            # paths to libjpeg.a, libpng.a, libz.a (.so) files if make cannot find them
@@ -353,8 +352,10 @@ Read or write compressed files
 -----------------------------------------
 
 If this option is enabled, large files can be read or written with
-gzip compression by several LAMMPS commands, including
-:doc:`read_data <read_data>`, :doc:`rerun <rerun>`, and :doc:`dump <dump>`.
+compression by ``gzip`` or similar tools by several LAMMPS commands,
+including :doc:`read_data <read_data>`, :doc:`rerun <rerun>`, and
+:doc:`dump <dump>`.  Currently supported compression tools are:
+``gzip``, ``bzip2``, ``zstd``, and ``lzma``.
 
 .. tabs::
 
@@ -363,23 +364,23 @@ gzip compression by several LAMMPS commands, including
       .. code-block:: bash
 
          -D WITH_GZIP=value       # yes or no
-                                  # default is yes if CMake can find gzip, else no
-         -D GZIP_EXECUTABLE=path  # path to gzip executable if CMake cannot find it
+                                  # default is yes if CMake can find the gzip program, else no
 
    .. tab:: Traditional make
 
       .. code-block:: make
 
-         LMP_INC = -DLAMMPS_GZIP
+         LMP_INC = -DLAMMPS_GZIP   <other LMP_INC settings>
 
-This option requires that your operating system fully supports the "popen()"
-function in the standard runtime library and that a ``gzip`` executable can be
-found by LAMMPS during a run.
+This option requires that your operating system fully supports the
+"popen()" function in the standard runtime library and that a ``gzip``
+or other executable can be found by LAMMPS in the standard search path
+during a run.
 
 .. note::
 
-   On some clusters with high-speed networks, using the "fork()" library
-   call (required by "popen()") can interfere with the fast communication
+   On clusters with high-speed networks, using the "fork()" library call
+   (required by "popen()") can interfere with the fast communication
    library and lead to simulations using compressed output or input to
    hang or crash. For selected operations, compressed file I/O is also
    available using a compression library instead, which is what the
@@ -451,7 +452,7 @@ those systems:
 
       .. code-block:: make
 
-         LMP_INC = -DLAMMPS_LONGLONG_TO_LONG
+         LMP_INC = -DLAMMPS_LONGLONG_TO_LONG  <other LMP_INC settings>
 
 ----------
 
@@ -478,7 +479,7 @@ e.g. to Python. Of course, the calling code has to be set up to
 
       .. code-block:: make
 
-         LMP_INC = -DLAMMPS_EXCEPTIONS
+         LMP_INC = -DLAMMPS_EXCEPTIONS   <other LMP_INC settings>
 
 .. note::
 
@@ -519,7 +520,7 @@ executable, not the library.
 
       .. code-block:: make
 
-         LMP_INC = -DLAMMPS_TRAP_FPE
+         LMP_INC = -DLAMMPS_TRAP_FPE  <other LMP_INC settings>
 
 After compilation with this flag set, the LAMMPS executable will stop
 and produce a core dump when a division by zero, overflow, illegal math

doc/src/Build_windows.rst

@@ -4,6 +4,7 @@ Notes for building LAMMPS on Windows
 * :ref:`General remarks <generic>`
 * :ref:`Running Linux on Windows <linux>`
 * :ref:`Using GNU GCC ported to Windows <gnu>`
+* :ref:`Using Visual Studio <msvc>`
 * :ref:`Using a cross-compiler <cross>`
 
 ----------
@@ -31,13 +32,13 @@ pre-compiled Windows binary packages are sufficient for your needs.  If
 it is necessary for you to compile LAMMPS on a Windows machine
 (e.g. because it is your main desktop), please also consider using a
 virtual machine software and compile and run LAMMPS in a Linux virtual
-machine, or - if you have a sufficiently up-to-date Windows 10
-installation - consider using the Windows subsystem for Linux.  This
-optional Windows feature allows you to run the bash shell from Ubuntu
-from within Windows and from there on, you can pretty much use that
-shell like you are running on an Ubuntu Linux machine (e.g. installing
-software via apt-get and more).  For more details on that, please see
-:doc:`this tutorial <Howto_wsl>`.
+machine, or - if you have a sufficiently up-to-date Windows 10 or
+Windows 11 installation - consider using the Windows subsystem for
+Linux.  This optional Windows feature allows you to run the bash shell
+from Ubuntu from within Windows and from there on, you can pretty much
+use that shell like you are running on an Ubuntu Linux machine
+(e.g. installing software via apt-get and more).  For more details on
+that, please see :doc:`this tutorial <Howto_wsl>`.
 
 .. _gnu:
 
@@ -67,6 +68,40 @@ requiring changes to the LAMMPS source code, or figure out corrections
 yourself, please report them on the lammps-users mailing list, or file
 them as an issue or pull request on the LAMMPS GitHub project.
 
+.. _msvc:
+
+Using Microsoft Visual Studio
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Following the integration of the :doc:`platform namespace
+<Developer_platform>` into the LAMMPS code base, portability of LAMMPS
+to be compiled on Windows using Visual Studio has been significantly
+improved.  This has been tested with Visual Studio 2019 (aka version
+16).  Not all features and packages in LAMMPS are currently supported
+out of the box, but a preset ``cmake/presets/windows.cmake`` is provided
+that contains the packages that have been compiled successfully.  You
+must use the CMake based build procedure, and either use the integrated
+CMake support of Visual Studio or use an external CMake installation to
+create build files for the Visual Studio build system.  Please note that
+on launching Visual Studio it will scan the directory tree and likely
+miss the correct master ``CMakeLists.txt``.  Try to open the
+``cmake/CMakeSettings.json`` and use those CMake configurations as a
+starting point.  It is also possible to configure and compile LAMMPS
+from the command line with a CMake binary from `cmake.org <https://cmake.org>`_.
+
+Please note, that for either approach CMake will create a so-called
+:ref:`"multi-configuration" build environment <cmake_multiconfig>`, and
+the command lines for building and testing LAMMPS must be adjusted
+accordingly.
+
+To support running in parallel you can compile with OpenMP enabled using
+the OPENMP package or install Microsoft MPI (including the SDK) and compile
+LAMMPS with MPI enabled.
+
+This is work in progress and you should contact the LAMMPS developers
+via GitHub, the forum, or the mailing list, if you have questions or
+LAMMPS specific problems.
+
 .. _cross:
 
 Using a cross-compiler

doc/src/Commands_all.rst

@@ -47,7 +47,7 @@ An alphabetic list of all general LAMMPS commands.
    * :doc:`displace_atoms <displace_atoms>`
    * :doc:`dump <dump>`
    * :doc:`dump_modify <dump_modify>`
-   * :doc:`dynamical_matrix <dynamical_matrix>`
+   * :doc:`dynamical_matrix (k) <dynamical_matrix>`
    * :doc:`echo <echo>`
    * :doc:`fix <fix>`
    * :doc:`fix_modify <fix_modify>`
@@ -117,7 +117,7 @@ An alphabetic list of all general LAMMPS commands.
    * :doc:`thermo <thermo>`
    * :doc:`thermo_modify <thermo_modify>`
    * :doc:`thermo_style <thermo_style>`
-   * :doc:`third_order <third_order>`
+   * :doc:`third_order (k) <third_order>`
    * :doc:`timer <timer>`
    * :doc:`timestep <timestep>`
    * :doc:`uncompute <uncompute>`

doc/src/Commands_bond.rst

@@ -35,6 +35,7 @@ OPT.
    * :doc:`class2 (ko) <bond_class2>`
    * :doc:`fene (iko) <bond_fene>`
    * :doc:`fene/expand (o) <bond_fene_expand>`
+   * :doc:`fene/nm <bond_fene>`
    * :doc:`gaussian <bond_gaussian>`
    * :doc:`gromos (o) <bond_gromos>`
    * :doc:`harmonic (iko) <bond_harmonic>`

doc/src/Commands_compute.rst

@@ -28,6 +28,7 @@ KOKKOS, o = OPENMP, t = OPT.
    * :doc:`angle <compute_angle>`
    * :doc:`angle/local <compute_angle_local>`
    * :doc:`angmom/chunk <compute_angmom_chunk>`
+   * :doc:`ave/sphere/atom (k) <compute_ave_sphere_atom>`
    * :doc:`basal/atom <compute_basal_atom>`
    * :doc:`body/local <compute_body_local>`
    * :doc:`bond <compute_bond>`

doc/src/Commands_fix.rst

@@ -23,6 +23,7 @@ OPT.
    :columns: 5
 
    * :doc:`accelerate/cos <fix_accelerate_cos>`
+   * :doc:`acks2/reaxff (k) <fix_acks2_reaxff>`
    * :doc:`adapt <fix_adapt>`
    * :doc:`adapt/fep <fix_adapt_fep>`
    * :doc:`addforce <fix_addforce>`
@@ -103,6 +104,7 @@ OPT.
    * :doc:`manifoldforce <fix_manifoldforce>`
    * :doc:`mdi/engine <fix_mdi_engine>`
    * :doc:`meso/move <fix_meso_move>`
+   * :doc:`mol/swap <fix_mol_swap>`
    * :doc:`momentum (k) <fix_momentum>`
    * :doc:`momentum/chunk <fix_momentum>`
    * :doc:`move <fix_move>`
@@ -127,6 +129,7 @@ OPT.
    * :doc:`npt/sphere (o) <fix_npt_sphere>`
    * :doc:`npt/uef <fix_nh_uef>`
    * :doc:`numdiff <fix_numdiff>`
+   * :doc:`numdiff/virial <fix_numdiff_virial>`
    * :doc:`nve (giko) <fix_nve>`
    * :doc:`nve/asphere (gi) <fix_nve_asphere>`
    * :doc:`nve/asphere/noforce <fix_nve_asphere_noforce>`

doc/src/Commands_pair.rst

@@ -119,10 +119,12 @@ OPT.
    * :doc:`granular <pair_granular>`
    * :doc:`gw <pair_gw>`
    * :doc:`gw/zbl <pair_gw>`
+   * :doc:`harmonic/cut (o) <pair_harmonic_cut>`
    * :doc:`hbond/dreiding/lj (o) <pair_hbond_dreiding>`
    * :doc:`hbond/dreiding/morse (o) <pair_hbond_dreiding>`
    * :doc:`hdnnp <pair_hdnnp>`
    * :doc:`ilp/graphene/hbn <pair_ilp_graphene_hbn>`
+   * :doc:`ilp/tmd <pair_ilp_tmd>`
    * :doc:`kolmogorov/crespi/full <pair_kolmogorov_crespi_full>`
    * :doc:`kolmogorov/crespi/z <pair_kolmogorov_crespi_z>`
    * :doc:`lcbop <pair_lcbop>`
@@ -210,6 +212,7 @@ OPT.
    * :doc:`nm/cut (o) <pair_nm>`
    * :doc:`nm/cut/coul/cut (o) <pair_nm>`
    * :doc:`nm/cut/coul/long (o) <pair_nm>`
+   * :doc:`nm/cut/split <pair_nm>`
    * :doc:`oxdna/coaxstk <pair_oxdna>`
    * :doc:`oxdna/excv <pair_oxdna>`
    * :doc:`oxdna/hbond <pair_oxdna>`
@@ -239,6 +242,7 @@ OPT.
    * :doc:`reaxff (ko) <pair_reaxff>`
    * :doc:`rebo (io) <pair_airebo>`
    * :doc:`resquared (go) <pair_resquared>`
+   * :doc:`saip/metal <pair_saip_metal>`
    * :doc:`sdpd/taitwater/isothermal <pair_sdpd_taitwater_isothermal>`
    * :doc:`smd/hertz <pair_smd_hertz>`
    * :doc:`smd/tlsph <pair_smd_tlsph>`
@@ -262,6 +266,7 @@ OPT.
    * :doc:`spin/neel <pair_spin_neel>`
    * :doc:`srp <pair_srp>`
    * :doc:`sw (giko) <pair_sw>`
+   * :doc:`sw/mod (o) <pair_sw>`
    * :doc:`table (gko) <pair_table>`
    * :doc:`table/rx (k) <pair_table_rx>`
    * :doc:`tdpd <pair_mesodpd>`

doc/src/Developer.rst

@@ -11,10 +11,13 @@ of time and requests from the LAMMPS user community.
    :maxdepth: 1
 
    Developer_org
+   Developer_cxx_vs_c_style
+   Developer_parallel
    Developer_flow
    Developer_write
    Developer_notes
    Developer_plugins
    Developer_unittest
    Classes
+   Developer_platform
    Developer_utils

doc/src/Developer_cxx_vs_c_style.rst

@@ -0,0 +1,384 @@
+Code design
+-----------
+
+This section discusses some of the code design choices in LAMMPS and
+overall strategy in order to assist developers to write new code that
+will fit well with the remaining code.  Please see the section on
+:doc:`Requirements for contributed code <Modify_style>` for more
+specific recommendations and guidelines.  While that section is
+organized more in the form of a checklist for code contributors, the
+focus here is on overall code design strategy, choices made between
+possible alternatives, and to discuss of some relevant C++ programming
+language constructs.
+
+Historically, the basic design philosophy of the LAMMPS C++ code was
+that of a "C with classes" style.  The was motivated by the desire to
+make it easier to modify LAMMPS for people without significant training
+in C++ programming and by trying to use data structures and code constructs
+that somewhat resemble the previous implementation(s) in Fortran.
+A contributing factor for this choice also was that at the time the
+implementation of C++ compilers was not always very mature and some of
+the advanced features contained bugs or were not functioning exactly
+as the standard required; plus there was some disagreement between
+compiler vendors about how to interpret the C++ standard documents.
+
+However, C++ compilers have advanced a lot since then and with the
+transition to requiring the C++11 standard in 2020 as the minimum C++ language
+standard for LAMMPS, the decision was made to also replace some of the
+C-style constructs with equivalent C++ functionality, either from the
+C++ standard library or as custom classes or function, in order to
+improve readability of the code and to increase code reuse through
+abstraction of commonly used functionality.
+
+.. note::
+
+   Please note that as of spring 2022 there is still a sizable chunk of
+   legacy code in LAMMPS that has not yet been refactored to reflect these
+   style conventions in full.  LAMMPS has a large code base and many
+   different contributors and there also is a hierarchy of precedence
+   in which the code is adapted.  Highest priority has the code in the
+   ``src`` folder, followed by code in packages in order of their popularity
+   and complexity (simpler code is adapted sooner), followed by code
+   in the ``lib`` folder.  Source code that is downloaded during compilation
+   is not subject to the conventions discussed here.
+
+Object oriented code
+^^^^^^^^^^^^^^^^^^^^
+
+LAMMPS is designed to be an object oriented code, that is each
+simulation is represented by an instance of the LAMMPS class.  When
+running in parallel, of course, each MPI process will create such an
+instance.  This can be seen in the ``main.cpp`` file where the core
+steps of running a LAMMPS simulation are the following 3 lines of code:
+
+.. code-block:: C++
+
+    LAMMPS *lammps = new LAMMPS(argc, argv, lammps_comm);
+    lammps->input->file();
+    delete lammps;
+
+The first line creates a LAMMPS class instance and passes the command
+line arguments and the global communicator to its constructor.  The
+second line tells the LAMMPS instance to process the input (either from
+standard input or the provided input file) until the end.  And the third
+line deletes that instance again.  The remainder of the main.cpp file
+are for error handling, MPI configuration and other special features.
+
+In the constructor of the LAMMPS class instance the basic LAMMPS class hierarchy
+is created as shown in :ref:`class-topology`.  While processing the input further
+class instances are created, or deleted, or replaced and specific member functions
+of specific classes are called to trigger actions like creating atoms, computing
+forces, computing properties, propagating the system, or writing output.
+
+Compositing and Inheritance
+===========================
+
+LAMMPS makes extensive use of the object oriented programming (OOP)
+principles of *compositing* and *inheritance*. Classes like the
+``LAMMPS`` class are a **composite** containing pointers to instances of
+other classes like ``Atom``, ``Comm``, ``Force``, ``Neighbor``,
+``Modify``, and so on.  Each of these classes implement certain
+functionality by storing and manipulating data related to the simulation
+and providing member functions that trigger certain actions.  Some of
+those classes like ``Force`` are a composite again containing instances
+of classes describing the force interactions or ``Modify`` containing
+and calling fixes and computes.  In most cases (e.g. ``AtomVec``, ``Comm``,
+``Pair``, or ``Bond``) there is only one instance of those member classes
+allowed, but in a few cases (e.g. ``Region``, ``Fix``, ``Compute``, or
+``Dump``) there can be multiple instances and the parent class is
+maintaining a list of the pointers of instantiated classes instead
+of a single pointer.
+
+Changing behavior or adjusting how LAMMPS handles a simulation is
+implemented via **inheritance** where different variants of the
+functionality are realized by creating *derived* classes that can share
+common functionality in their base class and provide a consistent
+interface where the derived classes replace (dummy or pure) functions in
+the base class.  The higher level classes can then call those methods of
+the instantiated classes without having to know which specific derived
+class variant was instantiated.  In the LAMMPS documentation those
+derived classes are usually referred to a "styles", e.g.  pair styles,
+fix styles, atom styles and so on.
+
+This is the origin of the flexibility of LAMMPS and facilitates for
+example to compute forces for very different non-bonded potential
+functions by having different pair styles (implemented as different
+classes derived from the ``Pair`` class) where the evaluation of the
+potential function is confined to the implementation of the individual
+classes.  Whenever a new :doc:`pair_style` or :doc:`bond_style` or
+:doc:`comm_style` or similar command is processed in the LAMMPS input
+any existing class instance is deleted and a new instance created in
+it place.
+
+Classes derived from ``Fix`` or ``Compute`` represent a different facet
+of LAMMPS' flexibility as there can be multiple instances of them an
+their member functions will be called at different phases of the time
+integration process (as explained in `Developer_flow`).  This way
+multiple manipulations of the entire or parts of the system can be
+programmed (with fix styles) or different computations can be performed
+and accessed and further processed or output through a common interface
+(with compute styles).
+
+Further code sharing is possible by creating derived classes from the
+derived classes (for instance to implement an accelerated version of a
+pair style) where then only a subset of the methods are replaced with
+the accelerated versions.
+
+Polymorphism
+============
+
+Polymorphism and dynamic dispatch are another OOP feature that play an
+important part of how LAMMPS selects which code to execute.  In a nutshell,
+this is a mechanism where the decision of which member function to call
+from a class is determined at runtime and not when the code is compiled.
+To enable it, the function has to be declared as ``virtual`` and all
+corresponding functions in derived classes should be using the ``override``
+property. Below is a brief example.
+
+.. code-block:: c++
+
+   class Base {
+   public:
+    virtual ~Base() = default;
+    void call();
+    void normal();
+    virtual void poly();
+   };
+
+   void Base::call() {
+    normal();
+    poly();
+   }
+
+   class Derived : public Base {
+   public:
+    ~Derived() override = default;
+    void normal();
+    void poly() override;
+   };
+
+   // [....]
+
+   Base *base1 = new Base();
+   Base *base2 = new Derived();
+
+   base1->call();
+   base2->call();
+
+The difference in behavior of the ``normal()`` and the ``poly()`` member
+functions is in which of the two member functions is called when
+executing `base1->call()` and `base2->call()`.  Without polymorphism, a
+function within the base class will call only member functions within
+the same scope, that is ``Base::call()`` will always call
+``Base::normal()``.  But for the `base2->call()` the call for the
+virtual member function will be dispatched to ``Derived::poly()``
+instead.  This mechanism allows to always call functions within the
+scope of the class type that was used to create the class instance, even
+if they are assigned to a pointer using the type of a base class. This
+is the desired behavior, and thanks to dynamic dispatch, LAMMPS can even
+use styles that are loaded at runtime from a shared object file with the
+:doc:`plugin command <plugin>`.
+
+A special case of virtual functions are so-called pure functions. These
+are virtual functions that are initialized to 0 in the class declaration
+(see example below).
+
+.. code-block:: c++
+
+   class Base {
+   public:
+    virtual void pure() = 0;
+   };
+
+This has the effect that it will no longer be possible to create an
+instance of the base class and that derived classes **must** implement
+these functions.  Many of the functions listed with the various class
+styles in the section :doc:`Modify` are such pure functions.  The
+motivation for this is to define the interface or API of the functions
+but defer the implementation to the derived classes.
+
+However, there are downsides to this. For example, calls to virtual
+functions from within a constructor, will not be in the scope of the
+derived class and thus it is good practice to either avoid calling them
+or to provide an explicit scope like in ``Base::poly()``.  Furthermore,
+any destructors in classes containing virtual functions should be
+declared virtual, too, so they are processed in the expected order
+before types are removed from dynamic dispatch.
+
+.. admonition:: Important Notes
+
+   In order to be able to detect incompatibilities and to avoid unexpected
+   behavior already at compile time, it is crucial that all member functions
+   that are intended to replace a virtual or pure function use the ``override``
+   property keyword.  For the same reason it should be avoided to use overloads
+   or default arguments for virtual functions as they lead to confusion over
+   which function is supposed to override which and which arguments need to be
+   declared.
+
+Style Factories
+===============
+
+In order to create class instances of the different styles, LAMMPS often
+uses a programming pattern called `Factory`.  Those are functions that create
+an instance of a specific derived class, say ``PairLJCut`` and return a pointer
+to the type of the common base class of that style, ``Pair`` in this case.
+To associate the factory function with the style keyword, an ``std::map``
+class is used in which function pointers are indexed by their keyword
+(for example "lj/cut" for ``PairLJCut`` and "morse" ``PairMorse``).
+A couple of typedefs help to keep the code readable and a template function
+is used to implement the actual factory functions for the individual classes.
+
+I/O and output formatting
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+C-style stdio versus C++ style iostreams
+========================================
+
+LAMMPS chooses to use the "stdio" library of the standard C library for
+reading from and writing to files and console instead of C++
+"iostreams".  This is mainly motivated by the better performance, better
+control over formatting, and less effort to achieve specific formatting.
+
+Since mixing "stdio" and "iostreams" can lead to unexpected behavior using
+the latter is strongly discouraged.  Also output to the screen should not
+use the predefined ``stdout`` FILE pointer, but rather the ``screen`` and
+``logfile`` FILE pointers managed by the LAMMPS class.  Furthermore, output
+should only be done by MPI rank 0 (``comm->me == 0``) and output that is
+send to both ``screen`` and ``logfile`` should use the
+:cpp:func:`utils::logmesg() convenience function <LAMMPS_NS::utils::logmesg>`.
+
+We also discourage the use for stringstreams as the bundled {fmt} library
+and the customized tokenizer classes can provide the same functionality
+in a cleaner way with better performance. This will also help to retain
+a consistent programming style despite the many different contributors.
+
+Formatting with the {fmt} library
+===================================
+
+The LAMMPS source code includes a copy of the `{fmt} library
+<https://fmt.dev>`_ which is preferred over formatting with the
+"printf()" family of functions.  The primary reason is that it allows a
+typesafe default format for any type of supported data.  This is
+particularly useful for formatting integers of a given size (32-bit or
+64-bit) which may require different format strings depending on compile
+time settings or compilers/operating systems.  Furthermore, {fmt} gives
+better performance, has more functionality, a familiar formatting syntax
+that has similarities to ``format()`` in Python, and provides a facility
+that can be used to integrate format strings and a variable number of
+arguments into custom functions in a much simpler way that the varargs
+mechanism of the C library.  Finally, {fmt} has been included into the
+C++20 language standard, so changes to adopt it are future proof.
+
+Formatted strings are frequently created by calling the
+``fmt::format()`` function which will return a string as ``std::string``
+class instance.  In contrast to the ``%`` placeholder in ``printf()``,
+the {fmt} library uses ``{}`` to embed format descriptors.  In the
+simplest case, no additional characters are needed as {fmt} will choose
+the default format based on the data type of the argument. Alternatively
+The ``fmt::print()`` function may be used instead of ``printf()`` or
+``fprintf()``.  In addition, several LAMMPS output functions, that
+originally accepted a single string as arguments have been overloaded to
+accept a format string with optional arguments as well (e.g.
+``Error::all()``, ``Error::one()``, ``utils::logmesg()``).
+
+Summary of the {fmt} format syntax
+==================================
+
+The syntax of the format string is "{[<argument id>][:<format spec>]}",
+where either the argument id or the format spec (separated by a colon
+':') is optional.  The argument id is usually a number starting from 0
+that is the index to the arguments following the format string.  By
+default these are assigned in order (i.e. 0, 1, 2, 3, 4 etc.).  The most
+common case for using argument id would be to use the same argument in
+multiple places in the format string without having to provide it as an
+argument multiple times. In LAMMPS the argument id is rarely used.
+
+More common is the use of the format specifier, which starts with a
+colon.  This may optionally be followed by a fill character (default is
+' '). If provided, the fill character **must** be followed by an
+alignment character ('<', '^', '>' for left, centered, or right
+alignment (default)). The alignment character may be used without a fill
+character. The next important format parameter would be the minimum
+width, which may be followed by a dot '.'  and a precision for floating
+point numbers. The final character in the format string would be an
+indicator for the "presentation", i.e. 'd' for decimal presentation of
+integers, 'x' for hexadecimal, 'o' for octal, 'c' for character
+etc. This mostly follows the "printf()" scheme but without requiring an
+additional length parameter to distinguish between different integer
+widths. The {fmt} library will detect those and adapt the formatting
+accordingly.  For floating point numbers there are correspondingly, 'g'
+for generic presentation, 'e' for exponential presentation, and 'f' for
+fixed point presentation.
+
+Thus "{:8}" would represent *any* type argument using at least 8
+characters; "{:<8}" would do this as left aligned, "{:^8}" as centered,
+"{:>8}" as right aligned.  If a specific presentation is selected, the
+argument type must be compatible or else the {fmt} formatting code will
+throw an exception. Some format string examples are given below:
+
+.. code-block:: C
+
+   auto mesg = fmt::format("  CPU time: {:4d}:{:02d}:{:02d}\n", cpuh, cpum, cpus);
+   mesg = fmt::format("{:<8s}| {:<10.5g} | {:<10.5g} | {:<10.5g} |{:6.1f} |{:6.2f}\n",
+                      label, time_min, time, time_max, time_sq, tmp);
+   utils::logmesg(lmp,"{:>6} = max # of 1-2 neighbors\n",maxall);
+   utils::logmesg(lmp,"Lattice spacing in x,y,z = {:.8} {:.8} {:.8}\n",
+                  xlattice,ylattice,zlattice);
+
+which will create the following output lines:
+
+.. parsed-literal::
+
+     CPU time:    0:02:16
+     Pair    | 2.0133     | 2.0133     | 2.0133     |   0.0 | 84.21
+          4 = max # of 1-2 neighbors
+     Lattice spacing in x,y,z = 1.6795962 1.6795962 1.6795962
+
+A special feature of the {fmt} library is that format parameters like
+the width or the precision may be also provided as arguments. In that
+case a nested format is used where a pair of curly braces (with an
+optional argument id) "{}" are used instead of the value, for example
+"{:{}d}" will consume two integer arguments, the first will be the value
+shown and the second the minimum width.
+
+For more details and examples, please consult the `{fmt} syntax
+documentation <https://fmt.dev/latest/syntax.html>`_ website.
+
+
+Memory management
+^^^^^^^^^^^^^^^^^
+
+Dynamical allocation of data and objects should be done with either the
+C++ commands "new" and "delete/delete[]" or using member functions of
+the ``Memory`` class, most commonly, ``Memory::create()``,
+``Memory::grow()``, and ``Memory::destroy()``.  The use of ``malloc()``,
+``calloc()``, ``realloc()`` and ``free()`` directly is strongly
+discouraged.  To simplify adapting legacy code into the LAMMPS code base
+the member functions ``Memory::smalloc()``, ``Memory::srealloc()``, and
+``Memory::sfree()`` are available.
+
+Using those custom memory allocation functions is motivated by the
+following considerations:
+
+- memory allocation failures on *any* MPI rank during a parallel run
+  will trigger an immediate abort of the entire parallel calculation
+  instead of stalling it
+- a failing "new" will trigger an exception which is also captured by
+  LAMMPS and triggers a global abort
+- allocation of multi-dimensional arrays will be done in a C compatible
+  fashion but so that the storage of the actual data is stored in one
+  large consecutive block and thus when MPI communication is needed,
+  only this storage needs to be communicated (similar to Fortran arrays)
+- the "destroy()" and "sfree()" functions may safely be called on NULL
+  pointers
+- the "destroy()" functions will nullify the pointer variables making
+  "use after free" errors easy to detect
+- it is possible to use a larger than default memory alignment (not on
+  all operating systems, since the allocated storage pointers must be
+  compatible with ``free()`` for technical reasons)
+
+In the practical implementation of code this means that any pointer variables
+that are class members should be initialized to a ``nullptr`` value in their
+respective constructors.  That way it would be safe to call ``Memory::destroy()``
+or ``delete[]`` on them before *any* allocation outside the constructor.
+This helps to prevent memory leaks.

doc/src/Developer_notes.rst

@@ -7,6 +7,61 @@ typically document what a variable stores, what a small section of
 code does, or what a function does and its input/outputs.  The topics
 on this page are intended to document code functionality at a higher level.
 
+Reading and parsing of text and text files
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+It is frequently required for a class in LAMMPS to read in additional
+data from a file, most commonly potential parameters from a potential
+file for manybody potentials.  LAMMPS provides several custom classes
+and convenience functions to simplify the process.  This offers the
+following benefits:
+
+- better code reuse and fewer lines of code needed to implement reading
+  and parsing data from a file
+- better detection of format errors, incompatible data, and better error messages
+- exit with an error message instead of silently converting only part of the
+  text to a number or returning a 0 on unrecognized text and thus reading incorrect values
+- re-entrant code through avoiding global static variables (as used by ``strtok()``)
+- transparent support for translating unsupported UTF-8 characters to their ASCII equivalents
+  (the text to value conversion functions **only** accept ASCII characters)
+
+In most cases (e.g. potential files) the same data is needed on all MPI
+ranks.  Then it is best to do the reading and parsing only on MPI rank
+0, and communicate the data later with one or more ``MPI_Bcast()``
+calls.  For reading generic text and potential parameter files the
+custom classes :cpp:class:`TextFileReader <LAMMPS_NS::TextFileReader>`
+and :cpp:class:`PotentialFileReader <LAMMPS_NS::PotentialFileReader>`
+are available. Those classes allow to read the file as individual lines
+for which they can return a tokenizer class (see below) for parsing the
+line, or they can return blocks of numbers as a vector directly.  The
+documentation on `File reader classes <file-reader-classes>`_ contains
+an example for a typical case.
+
+When reading per-atom data, the data in the file usually needs include
+an atom ID so it can be associated with a particular atom.  In that case
+the data can be read in multi-line chunks and broadcast to all MPI ranks
+with :cpp:func:`utils::read_lines_from_file()
+<LAMMPS_NS::utils::read_lines_from_file>`.  Those chunks are then
+split into lines, parsed, and applied only to atoms the MPI rank
+"owns".
+
+For splitting a string (incrementally) into words and optionally
+converting those to numbers, the :cpp:class:`Tokenizer
+<LAMMPS_NS::Tokenizer>` and :cpp:class:`ValueTokenizer
+<LAMMPS_NS::ValueTokenizer>` can be used.  Those provide a superset of
+the functionality of ``strtok()`` from the C-library and the latter also
+includes conversion to different types.  Any errors while processing the
+string in those classes will result in an exception, which can be caught
+and the error processed as needed.  Unlike the C-library functions
+``atoi()``, ``atof()``, ``strtol()``, or ``strtod()`` the conversion
+will check if the converted text is a valid integer of floating point
+number and will not silently return an unexpected or incorrect value.
+For example, ``atoi()`` will return 12 when converting "12.5" while the
+ValueTokenizer class will throw an :cpp:class:`InvalidIntegerException
+<LAMMPS_NS::InvalidIntegerException>` if
+:cpp:func:`ValueTokenizer::next_int()
+<LAMMPS_NS::ValueTokenizer::next_int>` is called on the same string.
+
 Fix contributions to instantaneous energy, virial, and cumulative energy
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

doc/src/Developer_org.rst

@@ -225,7 +225,7 @@ follows:
   commands in an input script.
 
 - The Force class computes various forces between atoms.  The Pair
-  parent class is for non-bonded or pair-wise forces, which in LAMMPS
+  parent class is for non-bonded or pairwise forces, which in LAMMPS
   also includes many-body forces such as the Tersoff 3-body potential if
   those are computed by walking pairwise neighbor lists.  The Bond,
   Angle, Dihedral, Improper parent classes are styles for bonded

doc/src/Developer_par_comm.rst

@@ -0,0 +1,120 @@
+Communication
+^^^^^^^^^^^^^
+
+Following the partitioning scheme in use all per-atom data is
+distributed across the MPI processes, which allows LAMMPS to handle very
+large systems provided it uses a correspondingly large number of MPI
+processes.  Since The per-atom data (atom IDs, positions, velocities,
+types, etc.)  To be able to compute the short-range interactions MPI
+processes need not only access to data of atoms they "own" but also
+information about atoms from neighboring sub-domains, in LAMMPS referred
+to as "ghost" atoms.  These are copies of atoms storing required
+per-atom data for up to the communication cutoff distance. The green
+dashed-line boxes in the :ref:`domain-decomposition` figure illustrate
+the extended ghost-atom sub-domain for one processor.
+
+This approach is also used to implement periodic boundary
+conditions: atoms that lie within the cutoff distance across a periodic
+boundary are also stored as ghost atoms and taken from the periodic
+replication of the sub-domain, which may be the same sub-domain, e.g. if
+running in serial.  As a consequence of this, force computation in
+LAMMPS is not subject to minimum image conventions and thus cutoffs may
+be larger than half the simulation domain.
+
+.. _ghost-atom-comm:
+.. figure:: img/ghost-comm.png
+   :align: center
+
+   ghost atom communication
+
+   This figure shows the ghost atom communication patterns between
+   sub-domains for "brick" (left) and "tiled" communication styles for
+   2d simulations.  The numbers indicate MPI process ranks.  Here the
+   sub-domains are drawn spatially separated for clarity.  The
+   dashed-line box is the extended sub-domain of processor 0 which
+   includes its ghost atoms.  The red- and blue-shaded boxes are the
+   regions of communicated ghost atoms.
+
+Efficient communication patterns are needed to update the "ghost" atom
+data, since that needs to be done at every MD time step or minimization
+step.  The diagrams of the `ghost-atom-comm` figure illustrate how ghost
+atom communication is performed in two stages for a 2d simulation (three
+in 3d) for both a regular and irregular partitioning of the simulation
+box.  For the regular case (left) atoms are exchanged first in the
+*x*-direction, then in *y*, with four neighbors in the grid of processor
+sub-domains.
+
+In the *x* stage, processor ranks 1 and 2 send owned atoms in their
+red-shaded regions to rank 0 (and vice versa).  Then in the *y* stage,
+ranks 3 and 4 send atoms in their blue-shaded regions to rank 0, which
+includes ghost atoms they received in the *x* stage.  Rank 0 thus
+acquires all its ghost atoms; atoms in the solid blue corner regions
+are communicated twice before rank 0 receives them.
+
+For the irregular case (right) the two stages are similar, but a
+processor can have more than one neighbor in each direction.  In the
+*x* stage, MPI ranks 1,2,3 send owned atoms in their red-shaded regions to
+rank 0 (and vice versa).  These include only atoms between the lower
+and upper *y*-boundary of rank 0's sub-domain.  In the *y* stage, ranks
+4,5,6 send atoms in their blue-shaded regions to rank 0.  This may
+include ghost atoms they received in the *x* stage, but only if they
+are needed by rank 0 to fill its extended ghost atom regions in the
++/-*y* directions (blue rectangles).  Thus in this case, ranks 5 and
+6 do not include ghost atoms they received from each other (in the *x*
+stage) in the atoms they send to rank 0.  The key point is that while
+the pattern of communication is more complex in the irregular
+partitioning case, it can still proceed in two stages (three in 3d)
+via atom exchanges with only neighboring processors.
+
+When attributes of owned atoms are sent to neighboring processors to
+become attributes of their ghost atoms, LAMMPS calls this a "forward"
+communication.  On timesteps when atoms migrate to new owning processors
+and neighbor lists are rebuilt, each processor creates a list of its
+owned atoms which are ghost atoms in each of its neighbor processors.
+These lists are used to pack per-atom coordinates (for example) into
+message buffers in subsequent steps until the next reneighboring.
+
+A "reverse" communication is when computed ghost atom attributes are
+sent back to the processor who owns the atom.  This is used (for
+example) to sum partial forces on ghost atoms to the complete force on
+owned atoms.  The order of the two stages described in the
+:ref:`ghost-atom-comm` figure is inverted and the same lists of atoms
+are used to pack and unpack message buffers with per-atom forces.  When
+a received buffer is unpacked, the ghost forces are summed to owned atom
+forces.  As in forward communication, forces on atoms in the four blue
+corners of the diagrams are sent, received, and summed twice (once at
+each stage) before owning processors have the full force.
+
+These two operations are used many places within LAMMPS aside from
+exchange of coordinates and forces, for example by manybody potentials
+to share intermediate per-atom values, or by rigid-body integrators to
+enable each atom in a body to access body properties.  Here are
+additional details about how these communication operations are
+performed in LAMMPS:
+
+- When exchanging data with different processors, forward and reverse
+  communication is done using ``MPI_Send()`` and ``MPI_IRecv()`` calls.
+  If a processor is "exchanging" atoms with itself, only the pack and
+  unpack operations are performed, e.g. to create ghost atoms across
+  periodic boundaries when running on a single processor.
+
+- For forward communication of owned atom coordinates, periodic box
+  lengths are added and subtracted when the receiving processor is
+  across a periodic boundary from the sender.  There is then no need to
+  apply a minimum image convention when calculating distances between
+  atom pairs when building neighbor lists or computing forces.
+
+- The cutoff distance for exchanging ghost atoms is typically equal to
+  the neighbor cutoff.  But it can also chosen to be longer if needed,
+  e.g. half the diameter of a rigid body composed of multiple atoms or
+  over 3x the length of a stretched bond for dihedral interactions.  It
+  can also exceed the periodic box size.  For the regular communication
+  pattern (left), if the cutoff distance extends beyond a neighbor
+  processor's sub-domain, then multiple exchanges are performed in the
+  same direction.  Each exchange is with the same neighbor processor,
+  but buffers are packed/unpacked using a different list of atoms. For
+  forward communication, in the first exchange a processor sends only
+  owned atoms.  In subsequent exchanges, it sends ghost atoms received
+  in previous exchanges.  For the irregular pattern (right) overlaps of
+  a processor's extended ghost-atom sub-domain with all other processors
+  in each dimension are detected.

doc/src/Developer_par_long.rst

@@ -0,0 +1,188 @@
+Long-range interactions
+^^^^^^^^^^^^^^^^^^^^^^^
+
+For charged systems, LAMMPS can compute long-range Coulombic
+interactions via the FFT-based particle-particle/particle-mesh (PPPM)
+method implemented in :doc:`kspace style pppm and its variants
+<kspace_style>`.  For that Coulombic interactions are partitioned into
+short- and long-range components.  The short-ranged portion is computed
+in real space as a loop over pairs of charges within a cutoff distance,
+using neighbor lists.  The long-range portion is computed in reciprocal
+space using a kspace style.  For the PPPM implementation the simulation
+cell is overlaid with a regular FFT grid in 3d. It proceeds in several stages:
+
+a) each atom's point charge is interpolated to nearby FFT grid points,
+b) a forward 3d FFT is performed,
+c) a convolution operation is performed in reciprocal space,
+d) one or more inverse 3d FFTs are performed, and
+e) electric field values from grid points near each atom are interpolated to compute
+   its forces.
+
+For any of the spatial-decomposition partitioning schemes each processor
+owns the brick-shaped portion of FFT grid points contained within its
+sub-domain.  The two interpolation operations use a stencil of grid
+points surrounding each atom.  To accommodate the stencil size, each
+processor also stores a few layers of ghost grid points surrounding its
+brick.  Forward and reverse communication of grid point values is
+performed similar to the corresponding :doc:`atom data communication
+<Developer_par_comm>`.  In this case, electric field values on owned
+grid points are sent to neighboring processors to become ghost point
+values.  Likewise charge values on ghost points are sent and summed to
+values on owned points.
+
+For triclinic simulation boxes, the FFT grid planes are parallel to
+the box faces, but the mapping of charge and electric field values
+to/from grid points is done in reduced coordinates where the tilted
+box is conceptually a unit cube, so that the stencil and FFT
+operations are unchanged.  However the FFT grid size required for a
+given accuracy is larger for triclinic domains than it is for
+orthogonal boxes.
+
+.. _fft-parallel:
+.. figure:: img/fft-decomp-parallel.png
+   :align: center
+
+   parallel FFT in PPPM
+
+   Stages of a parallel FFT for a simulation domain overlaid
+   with an 8x8x8 3d FFT grid, partitioned across 64 processors.
+   Within each of the 4 diagrams, grid cells of the same color are
+   owned by a single processor; for simplicity only cells owned by 4
+   or 8 of the 64 processors are colored.  The two images on the left
+   illustrate brick-to-pencil communication.  The two images on the
+   right illustrate pencil-to-pencil communication, which in this
+   case transposes the *y* and *z* dimensions of the grid.
+
+Parallel 3d FFTs require substantial communication relative to their
+computational cost.  A 3d FFT is implemented by a series of 1d FFTs
+along the *x-*, *y-*, and *z-*\ direction of the FFT grid.  Thus the FFT
+grid cannot be decomposed like atoms into 3 dimensions for parallel
+processing of the FFTs but only in 1 (as planes) or 2 (as pencils)
+dimensions and in between the steps the grid needs to be transposed to
+have the FFT grid portion "owned" by each MPI process complete in the
+direction of the 1d FFTs it has to perform. LAMMPS uses the
+pencil-decomposition algorithm as shown in the :ref:`fft-parallel` figure.
+
+Initially (far left), each processor owns a brick of same-color grid
+cells (actually grid points) contained within in its sub-domain.  A
+brick-to-pencil communication operation converts this layout to 1d
+pencils in the *x*-dimension (center left).  Again, cells of the same
+color are owned by the same processor.  Each processor can then compute
+a 1d FFT on each pencil of data it wholly owns using a call to the
+configured FFT library.  A pencil-to-pencil communication then converts
+this layout to pencils in the *y* dimension (center right) which
+effectively transposes the *x* and *y* dimensions of the grid, followed
+by 1d FFTs in *y*.  A final transpose of pencils from *y* to *z* (far
+right) followed by 1d FFTs in *z* completes the forward FFT.  The data
+is left in a *z*-pencil layout for the convolution operation.  One or
+more inverse FFTs then perform the sequence of 1d FFTs and communication
+steps in reverse order; the final layout of resulting grid values is the
+same as the initial brick layout.
+
+Each communication operation within the FFT (brick-to-pencil or
+pencil-to-pencil or pencil-to-brick) converts one tiling of the 3d grid
+to another, where a tiling in this context means an assignment of a
+small brick-shaped subset of grid points to each processor, the union of
+which comprise the entire grid.  The parallel `fftMPI library
+<https://lammps.github.io/fftmpi/>`_ written for LAMMPS allows arbitrary
+definitions of the tiling so that an irregular partitioning of the
+simulation domain can use it directly.  Transforming data from one
+tiling to another is implemented in `fftMPI` using point-to-point
+communication, where each processor sends data to a few other
+processors, since each tile in the initial tiling overlaps with a
+handful of tiles in the final tiling.
+
+The transformations could also be done using collective communication
+across all $P$ processors with a single call to ``MPI_Alltoall()``, but
+this is typically much slower.  However, for the specialized brick and
+pencil tiling illustrated in :ref:`fft-parallel` figure, collective
+communication across the entire MPI communicator is not required.  In
+the example an :math:`8^3` grid with 512 grid cells is partitioned
+across 64 processors; each processor owns a 2x2x2 3d brick of grid
+cells.  The initial brick-to-pencil communication (upper left to upper
+right) only requires collective communication within subgroups of 4
+processors, as illustrated by the 4 colors.  More generally, a
+brick-to-pencil communication can be performed by partitioning *P*
+processors into :math:`P^{\frac{2}{3}}` subgroups of
+:math:`P^{\frac{1}{3}}` processors each.  Each subgroup performs
+collective communication only within its subgroup.  Similarly,
+pencil-to-pencil communication can be performed by partitioning *P*
+processors into :math:`P^{\frac{1}{2}}` subgroups of
+:math:`P^{\frac{1}{2}}` processors each.  This is illustrated in the
+figure for the :math:`y \Rightarrow z` communication (center).  An
+eight-processor subgroup owns the front *yz* plane of data and performs
+collective communication within the subgroup to transpose from a
+*y*-pencil to *z*-pencil layout.
+
+LAMMPS invokes point-to-point communication by default, but also
+provides the option of partitioned collective communication when using a
+:doc:`kspace_modify collective yes <kspace_modify>` command to switch to
+that mode.  In the latter case, the code detects the size of the
+disjoint subgroups and partitions the single *P*-size communicator into
+multiple smaller communicators, each of which invokes collective
+communication.  Testing on a large IBM Blue Gene/Q machine at Argonne
+National Labs showed a significant improvement in FFT performance for
+large processor counts; partitioned collective communication was faster
+than point-to-point communication or global collective communication
+involving all *P* processors.
+
+Here are some additional details about FFTs for long-range and related
+grid/particle operations that LAMMPS supports:
+
+- The fftMPI library allows each grid dimension to be a multiple of
+  small prime factors (2,3,5), and allows any number of processors to
+  perform the FFT.  The resulting brick and pencil decompositions are
+  thus not always as well-aligned but the size of subgroups of
+  processors for the two modes of communication (brick/pencil and
+  pencil/pencil) still scale as :math:`O(P^{\frac{1}{3}})` and
+  :math:`O(P^{\frac{1}{2}})`.
+
+- For efficiency in performing 1d FFTs, the grid transpose
+  operations illustrated in Figure \ref{fig:fft} also involve
+  reordering the 3d data so that a different dimension is contiguous
+  in memory.  This reordering can be done during the packing or
+  unpacking of buffers for MPI communication.
+
+- For large systems and particularly a large number of MPI processes,
+  the dominant cost for parallel FFTs is often the communication, not
+  the computation of 1d FFTs, even though the latter scales as :math:`N
+  \log(N)` in the number of grid points *N* per grid direction.  This is
+  due to the fact that only a 2d decomposition into pencils is possible
+  while atom data (and their corresponding short-range force and energy
+  computations) can be decomposed efficiently in 3d.
+
+  This can be addressed by reducing the number of MPI processes involved
+  in the MPI communication by using :doc:`hybrid MPI + OpenMP
+  parallelization <Speed_omp>`.  This will use OpenMP parallelization
+  inside the MPI domains and while that may have a lower parallel
+  efficiency, it reduces the communication overhead.
+
+  As an alternative it is also possible to start a :ref:`multi-partition
+  <partition>` calculation and then use the :doc:`verlet/split
+  integrator <run_style>` to perform the PPPM computation on a
+  dedicated, separate partition of MPI processes.  This uses an integer
+  "1:*p*" mapping of *p* sub-domains of the atom decomposition to one
+  sub-domain of the FFT grid decomposition and where pairwise non-bonded
+  and bonded forces and energies are computed on the larger partition
+  and the PPPM kspace computation concurrently on the smaller partition.
+
+- LAMMPS also implements PPPM-based solvers for other long-range
+  interactions, dipole and dispersion (Lennard-Jones), which can be used
+  in conjunction with long-range  Coulombics for point charges.
+
+- LAMMPS implements a ``GridComm`` class which overlays the simulation
+  domain with a regular grid, partitions it across processors in a
+  manner consistent with processor sub-domains, and provides methods for
+  forward and reverse communication of owned and ghost grid point
+  values.  It is used for PPPM as an FFT grid (as outlined above) and
+  also for the MSM algorithm which uses a cascade of grid sizes from
+  fine to coarse to compute long-range Coulombic forces.  The GridComm
+  class is also useful for models where continuum fields interact with
+  particles.  For example, the two-temperature model (TTM) defines heat
+  transfer between atoms (particles) and electrons (continuum gas) where
+  spatial variations in the electron temperature are computed by finite
+  differences of a discretized heat equation on a regular grid.  The
+  :doc:`fix ttm/grid <fix_ttm>` command uses the ``GridComm`` class
+  internally to perform its grid operations on a distributed grid
+  instead of the original :doc:`fix ttm <fix_ttm>` which uses a
+  replicated grid.

doc/src/Developer_par_neigh.rst

@@ -0,0 +1,159 @@
+Neighbor lists
+^^^^^^^^^^^^^^
+
+To compute forces efficiently, each processor creates a Verlet-style
+neighbor list which enumerates all pairs of atoms *i,j* (*i* = owned,
+*j* = owned or ghost) with separation less than the applicable
+neighbor list cutoff distance.  In LAMMPS the neighbor lists are stored
+in a multiple-page data structure; each page is a contiguous chunk of
+memory which stores vectors of neighbor atoms *j* for many *i* atoms.
+This allows pages to be incrementally allocated or deallocated in blocks
+as needed.  Neighbor lists typically consume the most memory of any data
+structure in LAMMPS.  The neighbor list is rebuilt (from scratch) once
+every few timesteps, then used repeatedly each step for force or other
+computations.  The neighbor cutoff distance is :math:`R_n = R_f +
+\Delta_s`, where :math:`R_f` is the (largest) force cutoff defined by
+the interatomic potential for computing short-range pairwise or manybody
+forces and :math:`\Delta_s` is a "skin" distance that allows the list to
+be used for multiple steps assuming that atoms do not move very far
+between consecutive time steps.  Typically the code triggers
+reneighboring when any atom has moved half the skin distance since the
+last reneighboring; this and other options of the neighbor list rebuild
+can be adjusted with the :doc:`neigh_modify <neigh_modify>` command.
+
+On steps when reneighboring is performed, atoms which have moved outside
+their owning processor's sub-domain are first migrated to new processors
+via communication.  Periodic boundary conditions are also (only)
+enforced on these steps to ensure each atom is re-assigned to the
+correct processor.  After migration, the atoms owned by each processor
+are stored in a contiguous vector.  Periodically each processor
+spatially sorts owned atoms within its vector to reorder it for improved
+cache efficiency in force computations and neighbor list building.  For
+that atoms are spatially binned and then reordered so that atoms in the
+same bin are adjacent in the vector.  Atom sorting can be disabled or
+its settings modified with the :doc:`atom_modify <atom_modify>` command.
+
+.. _neighbor-stencil:
+.. figure:: img/neigh-stencil.png
+   :align: center
+
+   neighbor list stencils
+
+   A 2d simulation sub-domain (thick black line) and the corresponding
+   ghost atom cutoff region (dashed blue line) for both orthogonal
+   (left) and triclinic (right) domains.  A regular grid of neighbor
+   bins (thin lines) overlays the entire simulation domain and need not
+   align with sub-domain boundaries; only the portion overlapping the
+   augmented sub-domain is shown.  In the triclinic case it overlaps the
+   bounding box of the tilted rectangle.  The blue- and red-shaded bins
+   represent a stencil of bins searched to find neighbors of a particular
+   atom (black dot).
+
+To build a local neighbor list in linear time, the simulation domain is
+overlaid (conceptually) with a regular 3d (or 2d) grid of neighbor bins,
+as shown in the :ref:`neighbor-stencil` figure for 2d models and a
+single MPI processor's sub-domain.  Each processor stores a set of
+neighbor bins which overlap its sub-domain extended by the neighbor
+cutoff distance :math:`R_n`.  As illustrated, the bins need not align
+with processor boundaries; an integer number in each dimension is fit to
+the size of the entire simulation box.
+
+Most often LAMMPS builds what it calls a "half" neighbor list where
+each *i,j* neighbor pair is stored only once, with either atom *i* or
+*j* as the central atom.  The build can be done efficiently by using a
+pre-computed "stencil" of bins around a central origin bin which
+contains the atom whose neighbors are being searched for.  A stencil
+is simply a list of integer offsets in *x,y,z* of nearby bins
+surrounding the origin bin which are close enough to contain any
+neighbor atom *j* within a distance :math:`R_n` from any atom *i* in the
+origin bin.  Note that for a half neighbor list, the stencil can be
+asymmetric since each atom only need store half its nearby neighbors.
+
+These stencils are illustrated in the figure for a half list and a bin
+size of :math:`\frac{1}{2} R_n`.  There are 13 red+blue stencil bins in
+2d (for the orthogonal case, 15 for triclinic).  In 3d there would be
+63, 13 in the plane of bins that contain the origin bin and 25 in each
+of the two planes above it in the *z* direction (75 for triclinic).  The
+reason the triclinic stencil has extra bins is because the bins tile the
+bounding box of the entire triclinic domain and thus are not periodic
+with respect to the simulation box itself.  The stencil and logic for
+determining which *i,j* pairs to include in the neighbor list are
+altered slightly to account for this.
+
+To build a neighbor list, a processor first loops over its "owned" plus
+"ghost" atoms and assigns each to a neighbor bin.  This uses an integer
+vector to create a linked list of atom indices within each bin.  It then
+performs a triply-nested loop over its owned atoms *i*, the stencil of
+bins surrounding atom *i*'s bin, and the *j* atoms in each stencil bin
+(including ghost atoms).  If the distance :math:`r_{ij} < R_n`, then
+atom *j* is added to the vector of atom *i*'s neighbors.
+
+Here are additional details about neighbor list build options LAMMPS
+supports:
+
+- The choice of bin size is an option; a size half of :math:`R_n` has
+  been found to be optimal for many typical cases.  Smaller bins incur
+  additional overhead to loop over; larger bins require more distance
+  calculations.  Note that for smaller bin sizes, the 2d stencil in the
+  figure would be more semi-circular in shape (hemispherical in 3d),
+  with bins near the corners of the square eliminated due to their
+  distance from the origin bin.
+
+- Depending on the interatomic potential(s) and other commands used in
+  an input script, multiple neighbor lists and stencils with different
+  attributes may be needed.  This includes lists with different cutoff
+  distances, e.g. for force computation versus occasional diagnostic
+  computations such as a radial distribution function, or for the
+  r-RESPA time integrator which can partition pairwise forces by
+  distance into subsets computed at different time intervals.  It
+  includes "full" lists (as opposed to half lists) where each *i,j* pair
+  appears twice, stored once with *i* and *j*, and which use a larger
+  symmetric stencil.  It also includes lists with partial enumeration of
+  ghost atom neighbors.  The full and ghost-atom lists are used by
+  various manybody interatomic potentials.  Lists may also use different
+  criteria for inclusion of a pair interaction.  Typically this simply
+  depends only on the distance between two atoms and the cutoff
+  distance.  But for finite-size coarse-grained particles with
+  individual diameters (e.g. polydisperse granular particles), it can
+  also depend on the diameters of the two particles.
+
+- When using :doc:`pair style hybrid <pair_hybrid>` multiple sub-lists
+  of the master neighbor list for the full system need to be generated,
+  one for each sub-style, which contains only the *i,j* pairs needed to
+  compute interactions between subsets of atoms for the corresponding
+  potential.  This means not all *i* or *j* atoms owned by a processor
+  are included in a particular sub-list.
+
+- Some models use different cutoff lengths for pairwise interactions
+  between different kinds of particles which are stored in a single
+  neighbor list.  One example is a solvated colloidal system with large
+  colloidal particles where colloid/colloid, colloid/solvent, and
+  solvent/solvent interaction cutoffs can be dramatically different.
+  Another is a model of polydisperse finite-size granular particles;
+  pairs of particles interact only when they are in contact with each
+  other.  Mixtures with particle size ratios as high as 10-100x may be
+  used to model realistic systems.  Efficient neighbor list building
+  algorithms for these kinds of systems are available in LAMMPS.  They
+  include a method which uses different stencils for different cutoff
+  lengths and trims the stencil to only include bins that straddle the
+  cutoff sphere surface.  More recently a method which uses both
+  multiple stencils and multiple bin sizes was developed; it builds
+  neighbor lists efficiently for systems with particles of any size
+  ratio, though other considerations (timestep size, force computations)
+  may limit the ability to model systems with huge polydispersity.
+
+- For small and sparse systems and as a fallback method, LAMMPS also
+  supports neighbor list construction without binning by using a full
+  :math:`O(N^2)` loop over all *i,j* atom pairs in a sub-domain when
+  using the :doc:`neighbor nsq <neighbor>` command.
+
+- Dependent on the "pair" setting of the :doc:`newton <newton>` command,
+  the "half" neighbor lists may contain **all** pairs of atoms where
+  atom *j* is a ghost atom (i.e. when the newton pair setting is *off*)
+  For the newton pair *on* setting the atom *j* is only added to the
+  list if its *z* coordinate is larger, or if equal the *y* coordinate
+  is larger, and that is equal, too, the *x* coordinate is larger.  For
+  homogeneously dense systems that will result in picking neighbors from
+  a same size sector in always the same direction relative to the
+  "owned" atom and thus it should lead to similar length neighbor lists
+  and thus reduce the chance of a load imbalance.

doc/src/Developer_par_openmp.rst

@@ -0,0 +1,114 @@
+OpenMP Parallelism
+^^^^^^^^^^^^^^^^^^
+
+The styles in the INTEL, KOKKOS, and OPENMP package offer to use OpenMP
+thread parallelism to predominantly distribute loops over local data
+and thus follow an orthogonal parallelization strategy to the
+decomposition into spatial domains used by the :doc:`MPI partitioning
+<Developer_par_part>`.  For clarity, this section discusses only the
+implementation in the OPENMP package as it is the simplest. The INTEL
+and KOKKOS package offer additional options and are more complex since
+they support more features and different hardware like co-processors
+or GPUs.
+
+One of the key decisions when implementing the OPENMP package was to
+keep the changes to the source code small, so that it would be easier to
+maintain the code and keep it in sync with the non-threaded standard
+implementation.  this is achieved by a) making the OPENMP version a
+derived class from the regular version (e.g. ``PairLJCutOMP`` from
+``PairLJCut``) and overriding only methods that are multi-threaded or
+need to be modified to support multi-threading (similar to what was done
+in the OPT package), b) keeping the structure in the modified code very
+similar so that side-by-side comparisons are still useful, and c)
+offloading additional functionality and multi-thread support functions
+into three separate classes ``ThrOMP``, ``ThrData``, and ``FixOMP``.
+``ThrOMP`` provides additional, multi-thread aware functionality not
+available in the corresponding base class (e.g. ``Pair`` for
+``PairLJCutOMP``) like multi-thread aware variants of the "tally"
+functions. Those functions are made available through multiple
+inheritance so those new functions have to have unique names to avoid
+ambiguities; typically ``_thr`` is appended to the name of the function.
+``ThrData`` is a classes that manages per-thread data structures.
+It is used instead of extending the corresponding storage to per-thread
+arrays to avoid slowdowns due to "false sharing" when multiple threads
+update adjacent elements in an array and thus force the CPU cache lines
+to be reset and re-fetched.  ``FixOMP`` finally manages the "multi-thread
+state" like settings and access to per-thread storage, it is activated
+by the :doc:`package omp <package>` command.
+
+Avoiding data races
+"""""""""""""""""""
+
+A key problem when implementing thread parallelism in an MD code is
+to avoid data races when updating accumulated properties like forces,
+energies, and stresses.  When interactions are computed, they always
+involve multiple atoms and thus there are race conditions when multiple
+threads want to update per-atom data of the same atoms.  Five possible
+strategies have been considered to avoid this:
+
+1) restructure the code so that there is no overlapping access possible
+   when computing in parallel, e.g. by breaking lists into multiple
+   parts and synchronizing threads in between.
+2) have each thread be "responsible" for a specific group of atoms and
+   compute these interactions multiple times, once on each thread that
+   is responsible for a given atom and then have each thread only update
+   the properties of this atom.
+3) use mutexes around functions and regions of code where the data race
+   could happen
+4) use atomic operations when updating per-atom properties
+5) use replicated per-thread data structures to accumulate data without
+   conflicts and then use a reduction to combine those results into the
+   data structures used by the regular style.
+
+Option 5 was chosen for the OPENMP package because it would retain the
+performance for the case of 1 thread and the code would be more
+maintainable.  Option 1 would require extensive code changes,
+particularly to the neighbor list code; options 2 would have incurred a
+2x or more performance penalty for the serial case; option 3 causes
+significant overhead and would enforce serialization of operations in
+inner loops and thus defeat the purpose of multi-threading; option 4
+slows down the serial case although not quite as bad as option 2.  The
+downside of option 5 is that the overhead of the reduction operations
+grows with the number of threads used, so there would be a crossover
+point where options 2 or 4 would result in faster executing.  That is
+why option 2 for example is used in the GPU package because a GPU is a
+processor with a massive number of threads.  However, since the MPI
+parallelization is generally more effective for typical MD systems, the
+expectation is that thread parallelism is only used for a smaller number
+of threads (2-8).  At the time of its implementation, that number was
+equivalent to the number of CPU cores per CPU socket on high-end
+supercomputers.
+
+Thus arrays like the force array are dimensioned to the number of atoms
+times the number of threads when enabling OpenMP support and inside the
+compute functions a pointer to a different chunk is obtained by each thread.
+Similarly, accumulators like potential energy or virial are kept in
+per-thread instances of the ``ThrData`` class and then only reduced and
+stored in their global counterparts at the end of the force computation.
+
+
+Loop scheduling
+"""""""""""""""
+
+Multi-thread parallelization is applied by distributing (outer) loops
+statically across threads.  Typically this would be the loop over local
+atoms *i* when processing *i,j* pairs of atoms from a neighbor list.
+The design of the neighbor list code results in atoms having a similar
+number of neighbors for homogeneous systems and thus load imbalances
+across threads are not common and typically happen for systems where
+also the MPI parallelization would be unbalanced, which would typically
+have a more pronounced impact on the performance.  This same loop
+scheduling scheme can also be applied to the reduction operations on
+per-atom data to try and reduce the overhead of the reduction operation.
+
+Neighbor list parallelization
+"""""""""""""""""""""""""""""
+
+In addition to the parallelization of force computations, also the
+generation of the neighbor lists is parallelized.  As explained
+previously, neighbor lists are built by looping over "owned" atoms and
+storing the neighbors in "pages".  In the OPENMP variants of the
+neighbor list code, each thread operates on a different chunk of "owned"
+atoms and allocates and fills its own set of pages with neighbor list
+data.  This is achieved by each thread keeping its own instance of the
+:cpp:class:`MyPage <LAMMPS_NS::MyPage>` page allocator class.

doc/src/Developer_par_part.rst

@@ -0,0 +1,89 @@
+Partitioning
+^^^^^^^^^^^^
+
+The underlying spatial decomposition strategy used by LAMMPS for
+distributed-memory parallelism is set with the :doc:`comm_style command
+<comm_style>` and can be either "brick" (a regular grid) or "tiled".
+
+.. _domain-decomposition:
+.. figure:: img/domain-decomp.png
+   :align: center
+
+   domain decomposition
+
+   This figure shows the different kinds of domain decomposition used
+   for MPI parallelization: "brick" on the left with an orthogonal
+   (left) and a triclinic (middle) simulation domain, and a "tiled"
+   decomposition (right).  The black lines show the division into
+   sub-domains and the contained atoms are "owned" by the corresponding
+   MPI process. The green dashed lines indicate how sub-domains are
+   extended with "ghost" atoms up to the communication cutoff distance.
+
+The LAMMPS simulation box is a 3d or 2d volume, which can be orthogonal
+or triclinic in shape, as illustrated in the :ref:`domain-decomposition`
+figure for the 2d case.  Orthogonal means the box edges are aligned with
+the *x*, *y*, *z* Cartesian axes, and the box faces are thus all
+rectangular.  Triclinic allows for a more general parallelepiped shape
+in which edges are aligned with three arbitrary vectors and the box
+faces are parallelograms.  In each dimension box faces can be periodic,
+or non-periodic with fixed or shrink-wrapped boundaries.  In the fixed
+case, atoms which move outside the face are deleted; shrink-wrapped
+means the position of the box face adjusts continuously to enclose all
+the atoms.
+
+For distributed-memory MPI parallelism, the simulation box is spatially
+decomposed (partitioned) into non-overlapping sub-domains which fill the
+box. The default partitioning, "brick", is most suitable when atom
+density is roughly uniform, as shown in the left-side images of the
+:ref:`domain-decomposition` figure.  The sub-domains comprise a regular
+grid and all sub-domains are identical in size and shape.  Both the
+orthogonal and triclinic boxes can deform continuously during a
+simulation, e.g. to compress a solid or shear a liquid, in which case
+the processor sub-domains likewise deform.
+
+
+For models with non-uniform density, the number of particles per
+processor can be load-imbalanced with the default partitioning.  This
+reduces parallel efficiency, as the overall simulation rate is limited
+by the slowest processor, i.e. the one with the largest computational
+load.  For such models, LAMMPS supports multiple strategies to reduce
+the load imbalance:
+
+- The processor grid decomposition is by default based on the simulation
+  cell volume and tries to optimize the volume to surface ratio for the sub-domains.
+  This can be changed with the :doc:`processors command <processors>`.
+- The parallel planes defining the size of the sub-domains can be shifted
+  with the :doc:`balance command <balance>`. Which can be done in addition
+  to choosing a more optimal processor grid.
+- The recursive bisectioning algorithm in combination with the "tiled"
+  communication style can produce a partitioning with equal numbers of
+  particles in each sub-domain.
+
+
+.. |decomp1| image:: img/decomp-regular.png
+   :width: 24%
+
+.. |decomp2| image:: img/decomp-processors.png
+   :width: 24%
+
+.. |decomp3| image:: img/decomp-balance.png
+   :width: 24%
+
+.. |decomp4| image:: img/decomp-rcb.png
+   :width: 24%
+
+|decomp1|  |decomp2|  |decomp3|  |decomp4|
+
+The pictures above demonstrate different decompositions for a 2d system
+with 12 MPI ranks.  The atom colors indicate the load imbalance of each
+sub-domain with green being optimal and red the least optimal.
+
+Due to the vacuum in the system, the default decomposition is unbalanced
+with several MPI ranks without atoms (left). By forcing a 1x12x1
+processor grid, every MPI rank does computations now, but number of
+atoms per sub-domain is still uneven and the thin slice shape increases
+the amount of communication between sub-domains (center left). With a
+2x6x1 processor grid and shifting the sub-domain divisions, the load
+imbalance is further reduced and the amount of communication required
+between sub-domains is less (center right).  And using the recursive
+bisectioning leads to further improved decomposition (right).

doc/src/Developer_parallel.rst

@@ -0,0 +1,28 @@
+Parallel algorithms
+-------------------
+
+LAMMPS is designed to enable running simulations in parallel using the
+MPI parallel communication standard with distributed data via domain
+decomposition.  The parallelization aims to be efficient result in good
+strong scaling (= good speedup for the same system) and good weak
+scaling (= the computational cost of enlarging the system is
+proportional to the system size).  Additional parallelization using GPUs
+or OpenMP can also be applied within the sub-domain assigned to an MPI
+process.  For clarity, most of the following illustrations show the 2d
+simulation case. The underlying algorithms in those cases, however,
+apply to both 2d and 3d cases equally well.
+
+.. note::
+
+   The text and most of the figures in this chapter were adapted
+   for the manual from the section on parallel algorithms in the
+   :ref:`new LAMMPS paper <lammps_paper>`.
+
+.. toctree::
+   :maxdepth: 1
+
+   Developer_par_part
+   Developer_par_comm
+   Developer_par_neigh
+   Developer_par_long
+   Developer_par_openmp

doc/src/Developer_platform.rst

@@ -0,0 +1,155 @@
+Platform abstraction functions
+------------------------------
+
+The ``platform`` sub-namespace inside the ``LAMMPS_NS`` namespace
+provides a collection of wrapper and convenience functions and utilities
+that perform common tasks for which platform specific code would be
+required or for which a more high-level abstraction would be convenient
+and reduce duplicated code.  This reduces redundant implementations and
+encourages consistent behavior and thus has some overlap with the
+:doc:`"utils" sub-namespace <Developer_utils>`.
+
+Time functions
+^^^^^^^^^^^^^^
+
+.. doxygenfunction:: cputime
+   :project: progguide
+
+.. doxygenfunction:: walltime
+   :project: progguide
+
+.. doxygenfunction:: usleep
+   :project: progguide
+
+Platform information functions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenfunction:: os_info
+   :project: progguide
+
+.. doxygenfunction:: compiler_info
+   :project: progguide
+
+.. doxygenfunction:: cxx_standard
+   :project: progguide
+
+.. doxygenfunction:: openmp_standard
+   :project: progguide
+
+.. doxygenfunction:: mpi_vendor
+   :project: progguide
+
+.. doxygenfunction:: mpi_info
+   :project: progguide
+
+.. doxygenfunction:: compress_info
+   :project: progguide
+
+
+File and path functions and global constants
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenvariable:: filepathsep
+   :project: progguide
+
+.. doxygenvariable:: pathvarsep
+   :project: progguide
+
+.. doxygenfunction:: guesspath
+   :project: progguide
+
+.. doxygenfunction:: path_basename
+   :project: progguide
+
+.. doxygenfunction:: path_join
+   :project: progguide
+
+.. doxygenfunction:: file_is_readable
+   :project: progguide
+
+.. doxygenfunction:: is_console
+   :project: progguide
+
+.. doxygenfunction:: path_is_directory
+   :project: progguide
+
+.. doxygenfunction:: current_directory
+   :project: progguide
+
+.. doxygenfunction:: list_directory
+   :project: progguide
+
+.. doxygenfunction:: chdir
+   :project: progguide
+
+.. doxygenfunction:: mkdir
+   :project: progguide
+
+.. doxygenfunction:: rmdir
+   :project: progguide
+
+.. doxygenfunction:: unlink
+   :project: progguide
+
+Standard I/O function wrappers
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenvariable:: END_OF_FILE
+   :project: progguide
+
+.. doxygenfunction:: ftell
+   :project: progguide
+
+.. doxygenfunction:: fseek
+   :project: progguide
+
+.. doxygenfunction:: ftruncate
+   :project: progguide
+
+.. doxygenfunction:: popen
+   :project: progguide
+
+.. doxygenfunction:: pclose
+   :project: progguide
+
+Environment variable functions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenfunction:: putenv
+   :project: progguide
+
+.. doxygenfunction:: unsetenv
+   :project: progguide
+
+.. doxygenfunction:: list_pathenv
+   :project: progguide
+
+.. doxygenfunction:: find_exe_path
+   :project: progguide
+
+Dynamically loaded object or library functions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenfunction:: dlopen
+   :project: progguide
+
+.. doxygenfunction:: dlclose
+   :project: progguide
+
+.. doxygenfunction:: dlsym
+   :project: progguide
+
+.. doxygenfunction:: dlerror
+   :project: progguide
+
+Compressed file I/O functions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+.. doxygenfunction:: has_compress_extension
+   :project: progguide
+
+.. doxygenfunction:: compressed_read
+   :project: progguide
+
+.. doxygenfunction:: compressed_write
+   :project: progguide

doc/src/Developer_utils.rst

@@ -7,7 +7,9 @@ a collection of convenience functions and utilities that perform common
 tasks that are required repeatedly throughout the LAMMPS code like
 reading or writing to files with error checking or translation of
 strings into specific types of numbers with checking for validity.  This
-reduces redundant implementations and encourages consistent behavior.
+reduces redundant implementations and encourages consistent behavior and
+thus has some overlap with the :doc:`"platform" sub-namespace
+<Developer_platform>`.
 
 I/O with status check and similar functions
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -19,18 +21,21 @@ In that case, the functions will stop with an error message, indicating
 the name of the problematic file, if possible unless the *error* argument
 is a NULL pointer.
 
-The :cpp:func:`fgets_trunc` function will work similar for ``fgets()``
-but it will read in a whole line (i.e. until the end of line or end
-of file), but store only as many characters as will fit into the buffer
-including a final newline character and the terminating NULL byte.
-If the line in the file is longer it will thus be truncated in the buffer.
-This function is used by :cpp:func:`read_lines_from_file` to read individual
-lines but make certain they follow the size constraints.
+The :cpp:func:`utils::fgets_trunc() <LAMMPS_NS::utils::fgets_trunc>`
+function will work similar for ``fgets()`` but it will read in a whole
+line (i.e. until the end of line or end of file), but store only as many
+characters as will fit into the buffer including a final newline
+character and the terminating NULL byte.  If the line in the file is
+longer it will thus be truncated in the buffer.  This function is used
+by :cpp:func:`utils::read_lines_from_file()
+<LAMMPS_NS::utils::read_lines_from_file>` to read individual lines but
+make certain they follow the size constraints.
 
-The :cpp:func:`read_lines_from_file` function will read the requested
-number of lines of a maximum length into a buffer and will return 0
-if successful or 1 if not. It also guarantees that all lines are
-terminated with a newline character and the entire buffer with a
+The :cpp:func:`utils::read_lines_from_file()
+<LAMMPS_NS::utils::read_lines_from_file>` function will read the
+requested number of lines of a maximum length into a buffer and will
+return 0 if successful or 1 if not. It also guarantees that all lines
+are terminated with a newline character and the entire buffer with a
 NULL character.
 
 ----------
@@ -54,33 +59,54 @@ String to number conversions with validity check
 
 These functions should be used to convert strings to numbers. They are
 are strongly preferred over C library calls like ``atoi()`` or
-``atof()`` since they check if the **entire** provided string is a valid
+``atof()`` since they check if the **entire** string is a valid
 (floating-point or integer) number, and will error out instead of
 silently returning the result of a partial conversion or zero in cases
-where the string is not a valid number.  This behavior allows to more
-easily detect typos or issues when processing input files.
+where the string is not a valid number.  This behavior improves
+detecting typos or issues when processing input files.
+
+Similarly the :cpp:func:`utils::logical() <LAMMPS_NS::utils::logical>` function
+will convert a string into a boolean and will only accept certain words.
 
 The *do_abort* flag should be set to ``true`` in case  this function
 is called only on a single MPI rank, as that will then trigger the
 a call to ``Error::one()`` for errors instead of ``Error::all()``
 and avoids a "hanging" calculation when run in parallel.
 
-Please also see :cpp:func:`is_integer() <LAMMPS_NS::utils::is_integer>`
-and :cpp:func:`is_double() <LAMMPS_NS::utils::is_double>` for testing
+Please also see :cpp:func:`utils::is_integer() <LAMMPS_NS::utils::is_integer>`
+and :cpp:func:`utils::is_double() <LAMMPS_NS::utils::is_double>` for testing
 strings for compliance without conversion.
 
 ----------
 
-.. doxygenfunction:: numeric
+.. doxygenfunction:: numeric(const char *file, int line, const std::string &str, bool do_abort, LAMMPS *lmp)
    :project: progguide
 
-.. doxygenfunction:: inumeric
+.. doxygenfunction:: numeric(const char *file, int line, const char *str, bool do_abort, LAMMPS *lmp)
    :project: progguide
 
-.. doxygenfunction:: bnumeric
+.. doxygenfunction:: inumeric(const char *file, int line, const std::string &str, bool do_abort, LAMMPS *lmp)
    :project: progguide
 
-.. doxygenfunction:: tnumeric
+.. doxygenfunction:: inumeric(const char *file, int line, const char *str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: bnumeric(const char *file, int line, const std::string &str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: bnumeric(const char *file, int line, const char *str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: tnumeric(const char *file, int line, const std::string &str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: tnumeric(const char *file, int line, const char *str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: logical(const char *file, int line, const std::string &str, bool do_abort, LAMMPS *lmp)
+   :project: progguide
+
+.. doxygenfunction:: logical(const char *file, int line, const char *str, bool do_abort, LAMMPS *lmp)
    :project: progguide
 
 
@@ -95,6 +121,12 @@ and parsing files or arguments.
 .. doxygenfunction:: strdup
    :project: progguide
 
+.. doxygenfunction:: lowercase
+   :project: progguide
+
+.. doxygenfunction:: uppercase
+   :project: progguide
+
 .. doxygenfunction:: trim
    :project: progguide
 
@@ -137,21 +169,6 @@ and parsing files or arguments.
 .. doxygenfunction:: is_double
    :project: progguide
 
-File and path functions
-^^^^^^^^^^^^^^^^^^^^^^^^^
-
-.. doxygenfunction:: guesspath
-   :project: progguide
-
-.. doxygenfunction:: path_basename
-   :project: progguide
-
-.. doxygenfunction:: path_join
-   :project: progguide
-
-.. doxygenfunction:: file_is_readable
-   :project: progguide
-
 Potential file functions
 ^^^^^^^^^^^^^^^^^^^^^^^^
 
@@ -191,6 +208,9 @@ Convenience functions
 .. doxygenfunction:: logmesg(LAMMPS *lmp, const std::string &mesg)
    :project: progguide
 
+.. doxygenfunction:: flush_buffers(LAMMPS *lmp)
+   :project: progguide
+
 .. doxygenfunction:: getsyserror
    :project: progguide
 
@@ -323,11 +343,11 @@ This code example should produce the following output:
 
 .. doxygenclass:: LAMMPS_NS::InvalidIntegerException
    :project: progguide
-   :members: what
+   :members:
 
 .. doxygenclass:: LAMMPS_NS::InvalidFloatException
    :project: progguide
-   :members: what
+   :members:
 
 ----------
 
@@ -376,21 +396,26 @@ A typical code segment would look like this:
 
 ----------
 
+.. file-reader-classes:
+
 File reader classes
 -------------------
 
 The purpose of the file reader classes is to simplify the recurring task
 of reading and parsing files. They can use the
-:cpp:class:`LAMMPS_NS::ValueTokenizer` class to process the read in
-text.  The :cpp:class:`LAMMPS_NS::TextFileReader` is a more general
-version while :cpp:class:`LAMMPS_NS::PotentialFileReader` is specialized
-to implement the behavior expected for looking up and reading/parsing
-files with potential parameters in LAMMPS.  The potential file reader
-class requires a LAMMPS instance, requires to be run on MPI rank 0 only,
-will use the :cpp:func:`LAMMPS_NS::utils::get_potential_file_path`
-function to look up and open the file, and will call the
-:cpp:class:`LAMMPS_NS::Error` class in case of failures to read or to
-convert numbers, so that LAMMPS will be aborted.
+:cpp:class:`ValueTokenizer <LAMMPS_NS::ValueTokenizer>` class to process
+the read in text.  The :cpp:class:`TextFileReader
+<LAMMPS_NS::TextFileReader>` is a more general version while
+:cpp:class:`PotentialFileReader <LAMMPS_NS::PotentialFileReader>` is
+specialized to implement the behavior expected for looking up and
+reading/parsing files with potential parameters in LAMMPS.  The
+potential file reader class requires a LAMMPS instance, requires to be
+run on MPI rank 0 only, will use the
+:cpp:func:`utils::get_potential_file_path
+<LAMMPS_NS::utils::get_potential_file_path>` function to look up and
+open the file, and will call the :cpp:class:`LAMMPS_NS::Error` class in
+case of failures to read or to convert numbers, so that LAMMPS will be
+aborted.
 
 .. code-block:: C++
    :caption: Use of PotentialFileReader class in pair style coul/streitz
@@ -465,10 +490,10 @@ provided, as that is used to determine whether a new page of memory
 must be used.
 
 The :cpp:class:`MyPage <LAMMPS_NS::MyPage>` class offers two ways to
-reserve a chunk: 1) with :cpp:func:`get() <LAMMPS_NS::MyPage::get>` the
-chunk size needs to be known in advance, 2) with :cpp:func:`vget()
+reserve a chunk: 1) with :cpp:func:`MyPage::get() <LAMMPS_NS::MyPage::get>` the
+chunk size needs to be known in advance, 2) with :cpp:func:`MyPage::vget()
 <LAMMPS_NS::MyPage::vget>` a pointer to the next chunk is returned, but
-its size is registered later with :cpp:func:`vgot()
+its size is registered later with :cpp:func:`MyPage::vgot()
 <LAMMPS_NS::MyPage::vgot>`.
 
 .. code-block:: C++
@@ -571,4 +596,3 @@ the communication buffers.
 
 .. doxygenunion:: LAMMPS_NS::ubuf
    :project: progguide
-

doc/src/Developer_write.rst

@@ -29,7 +29,9 @@ of code in the header before include guards:
 .. code-block:: c
 
    #ifdef FIX_CLASS
-   FixStyle(print/vel,FixPrintVel)
+   // clang-format off
+   FixStyle(print/vel,FixPrintVel);
+   // clang-format on
    #else
    /* the definition of the FixPrintVel class comes here */
    ...
@@ -53,7 +55,7 @@ of each timestep. First of all, implement a constructor:
      if (narg < 4)
        error->all(FLERR,"Illegal fix print/vel command");
 
-     nevery = force->inumeric(FLERR,arg[3]);
+     nevery = utils::inumeric(FLERR,arg[3],false,lmp);
      if (nevery <= 0)
        error->all(FLERR,"Illegal fix print/vel command");
    }

doc/src/Errors_messages.rst

@@ -1941,6 +1941,9 @@ Doc page with :doc:`WARNING messages <Errors_warnings>`
 *Compute ID for fix numdiff does not exist*
    Self-explanatory.
 
+*Compute ID for fix numdiff/virial does not exist*
+   Self-explanatory.
+
 *Compute ID for fix store/state does not exist*
    Self-explanatory.
 
@@ -3796,6 +3799,10 @@ Doc page with :doc:`WARNING messages <Errors_warnings>`
    Self-explanatory. Efficient loop over all atoms for numerical
    difference requires consecutive atom IDs.
 
+*Fix numdiff/virial must use group all*
+   Virial contributions computed by this fix are
+   computed on all atoms.
+
 *Fix nve/asphere requires extended particles*
    This fix can only be used for particles with a shape setting.
 
@@ -7772,9 +7779,6 @@ keyword to allow for additional bonds to be formed
    The system size must fit in a 32-bit integer to use this dump
    style.
 
-*Too many atoms to dump sort*
-   Cannot sort when running with more than 2\^31 atoms.
-
 *Too many elements extracted from MEAM library.*
    Increase 'maxelt' in meam.h and recompile.
 

doc/src/Errors_warnings.rst

@@ -416,7 +416,7 @@ This will most likely cause errors in kinetic fluctuations.
    not defined for the specified atom style.
 
 *Molecule has bond topology but no special bond settings*
-   This means the bonded atoms will not be excluded in pair-wise
+   This means the bonded atoms will not be excluded in pairwise
    interactions.
 
 *Molecule template for create_atoms has multiple molecules*

doc/src/Examples.rst

@@ -80,7 +80,7 @@ Lowercase directories
 +-------------+------------------------------------------------------------------+
 | friction    | frictional contact of spherical asperities between 2d surfaces   |
 +-------------+------------------------------------------------------------------+
-| gcmc        | Grand Canonical Monte Carlo (GCMC) via the fix gcmc command      |
+| mc          | Monte Carlo features via fix gcmc, widom and other commands      |
 +-------------+------------------------------------------------------------------+
 | granregion  | use of fix wall/region/gran as boundary on granular particles    |
 +-------------+------------------------------------------------------------------+
@@ -205,7 +205,7 @@ Uppercase directories
 +------------+--------------------------------------------------------------------------------------------------+
 | KAPPA      | compute thermal conductivity via several methods                                                 |
 +------------+--------------------------------------------------------------------------------------------------+
-| MC         | using LAMMPS in a Monte Carlo mode to relax the energy of a system                               |
+| MC-LOOP    | using LAMMPS in a Monte Carlo mode to relax the energy of a system in a input script loop        |
 +------------+--------------------------------------------------------------------------------------------------+
 | PACKAGES   | examples for specific packages and contributed commands                                          |
 +------------+--------------------------------------------------------------------------------------------------+

doc/src/Howto_drude2.rst

@@ -491,11 +491,6 @@ NPT ensemble using Nose-Hoover thermostat:
 **(Schroeder)**  Schroeder and Steinhauser, J Chem Phys, 133,
 154511 (2010).
 
-.. _Jiang2:
-
-**(Jiang)** Jiang, Hardy, Phillips, MacKerell, Schulten, and Roux,
- J Phys Chem Lett, 2, 87-92 (2011).
-
 .. _Thole2:
 
 **(Thole)** Chem Phys, 59, 341 (1981).

doc/src/Howto_github.rst

@@ -7,11 +7,11 @@ LAMMPS GitHub tutorial
 
 This document describes the process of how to use GitHub to integrate
 changes or additions you have made to LAMMPS into the official LAMMPS
-distribution.  It uses the process of updating this very tutorial as
-an example to describe the individual steps and options.  You need to
-be familiar with git and you may want to have a look at the
-`git book <http://git-scm.com/book/>`_ to reacquaint yourself with some
-of the more advanced git features used below.
+distribution.  It uses the process of updating this very tutorial as an
+example to describe the individual steps and options.  You need to be
+familiar with git and you may want to have a look at the `git book
+<http://git-scm.com/book/>`_ to familiarize yourself with some of the
+more advanced git features used below.
 
 As of fall 2016, submitting contributions to LAMMPS via pull requests
 on GitHub is the preferred option for integrating contributed features
@@ -37,15 +37,15 @@ username or e-mail address and password.
 **Forking the repository**
 
 To get changes into LAMMPS, you need to first fork the `lammps/lammps`
-repository on GitHub. At the time of writing, *master* is the preferred
+repository on GitHub. At the time of writing, *develop* is the preferred
 target branch. Thus go to `LAMMPS on GitHub <https://github.com/lammps/lammps>`_
-and make sure branch is set to "master", as shown in the figure below.
+and make sure branch is set to "develop", as shown in the figure below.
 
 .. image:: JPG/tutorial_branch.png
    :align: center
 
-If it is not, use the button to change it to *master*\ . Once it is, use the
-fork button to create a fork.
+If it is not, use the button to change it to *develop*. Once it is, use
+the fork button to create a fork.
 
 .. image:: JPG/tutorial_fork.png
    :align: center
@@ -64,11 +64,12 @@ LAMMPS development.
 **Adding changes to your own fork**
 
 Additions to the upstream version of LAMMPS are handled using *feature
-branches*\ .  For every new feature, a so-called feature branch is
+branches*.  For every new feature, a so-called feature branch is
 created, which contains only those modification relevant to one specific
 feature. For example, adding a single fix would consist of creating a
 branch with only the fix header and source file and nothing else.  It is
-explained in more detail here: `feature branch workflow <https://www.atlassian.com/git/tutorials/comparing-workflows/feature-branch-workflow>`_.
+explained in more detail here: `feature branch workflow
+<https://www.atlassian.com/git/tutorials/comparing-workflows/feature-branch-workflow>`_.
 
 **Feature branches**
 
@@ -94,8 +95,8 @@ The above command copies ("clones") the git repository to your local
 machine to a directory with the name you chose. If none is given, it will
 default to "lammps". Typical names are "mylammps" or something similar.
 
-You can use this local clone to make changes and
-test them without interfering with the repository on GitHub.
+You can use this local clone to make changes and test them without
+interfering with the repository on GitHub.
 
 To pull changes from upstream into this copy, you can go to the directory
 and use git pull:
@@ -103,28 +104,46 @@ and use git pull:
 .. code-block:: bash
 
      $ cd mylammps
-     $ git checkout master
-     $ git pull https://github.com/lammps/lammps
+     $ git checkout develop
+     $ git pull https://github.com/lammps/lammps develop
 
 You can also add this URL as a remote:
 
 .. code-block:: bash
 
-     $ git remote add lammps_upstream https://www.github.com/lammps/lammps
+     $ git remote add upstream https://www.github.com/lammps/lammps
 
-At this point, you typically make a feature branch from the updated master
+From then on you can update your upstream branches with:
+
+.. code-block:: bash
+
+     $ git fetch upstream
+
+and then refer to the upstream repository branches with
+`upstream/develop` or `upstream/release` and so on.
+
+At this point, you typically make a feature branch from the updated
 branch for the feature you want to work on. This tutorial contains the
 workflow that updated this tutorial, and hence we will call the branch
 "github-tutorial-update":
 
 .. code-block:: bash
 
-    $ git checkout -b github-tutorial-update master
+    $ git fetch upstream
+    $ git checkout -b github-tutorial-update upstream/develop
 
 Now that we have changed branches, we can make our changes to our local
 repository. Just remember that if you want to start working on another,
 unrelated feature, you should switch branches!
 
+.. note::
+
+   Committing changes to the *develop*, *release*, or *stable* branches
+   is strongly discouraged.  While it may be convenient initially, it
+   will create more work in the long run.  Various texts and tutorials
+   on using git effectively discuss the motivation for using feature
+   branches instead.
+
 **After changes are made**
 
 After everything is done, add the files to the branch and commit them:
@@ -287,28 +306,32 @@ After each push, the automated checks are run again.
 
 LAMMPS developers may add labels to your pull request to assign it to
 categories (mostly for bookkeeping purposes), but a few of them are
-important: needs_work, work_in_progress, test-for-regression, and
-full-regression-test. The first two indicate, that your pull request
-is not considered to be complete. With "needs_work" the burden is on
-exclusively on you; while "work_in_progress" can also mean, that a
-LAMMPS developer may want to add changes. Please watch the comments
-to the pull requests. The two "test" labels are used to trigger
-extended tests before the code is merged. This is sometimes done by
-LAMMPS developers, if they suspect that there may be some subtle
-side effects from your changes. It is not done by default, because
-those tests are very time consuming.
+important: *needs_work*, *work_in_progress*, *run_tests*,
+*test_for_regression*, and *ready_for_merge*.  The first two indicate,
+that your pull request is not considered to be complete. With
+"needs_work" the burden is on exclusively on you; while
+"work_in_progress" can also mean, that a LAMMPS developer may want to
+add changes. Please watch the comments to the pull requests. The two
+"test" labels are used to trigger extended tests before the code is
+merged. This is sometimes done by LAMMPS developers, if they suspect
+that there may be some subtle side effects from your changes. It is not
+done by default, because those tests are very time consuming.  The
+*ready_for_merge* label is usually attached when the LAMMPS developer
+assigned to the pull request considers this request complete and to
+trigger a final full test evaluation.
 
 **Reviews**
 
-As of Summer 2018, a pull request needs at least 1 approving review
-from a LAMMPS developer with write access to the repository.
-In case your changes touch code that certain developers are associated
-with, they are auto-requested by the GitHub software.  Those associations
-are set in the file
-`.github/CODEOWNERS <https://github.com/lammps/lammps/blob/master/.github/CODEOWNERS>`_
-Thus if you want to be automatically notified to review when anybody
-changes files or packages, that you have contributed to LAMMPS, you can
-add suitable patterns to that file, or a LAMMPS developer may add you.
+As of Fall 2021, a pull request needs to pass all automatic tests and at
+least 1 approving review from a LAMMPS developer with write access to
+the repository before it is eligible for merging.  In case your changes
+touch code that certain developers are associated with, they are
+auto-requested by the GitHub software.  Those associations are set in
+the file `.github/CODEOWNERS
+<https://github.com/lammps/lammps/blob/develop/.github/CODEOWNERS>`_ Thus
+if you want to be automatically notified to review when anybody changes
+files or packages, that **you** have contributed to LAMMPS, you can add
+suitable patterns to that file, or a LAMMPS developer may add you.
 
 Otherwise, you can also manually request reviews from specific developers,
 or LAMMPS developers - in their assessment of your pull request - may
@@ -329,7 +352,7 @@ LAMMPS developer (including him/herself) or c) Axel Kohlmeyer (akohlmey).
   After the review, the developer can choose to implement changes directly
   or suggest them to you.
 * Case c) means that the pull request has been assigned to the developer
-  overseeing the merging of pull requests into the master branch.
+  overseeing the merging of pull requests into the *develop* branch.
 
 In this case, Axel assigned the tutorial to Steve:
 
@@ -351,11 +374,11 @@ Sometimes, however, you might not feel comfortable having other people
 push changes into your own branch, or maybe the maintainers are not sure
 their idea was the right one.  In such a case, they can make changes,
 reassign you as the assignee, and file a "reverse pull request", i.e.
-file a pull request in your GitHub repository to include changes in the
-branch, that you have submitted as a pull request yourself.  In that
-case, you can choose to merge their changes back into your branch,
-possibly make additional changes or corrections and proceed from there.
-It looks something like this:
+file a pull request in **your** forked GitHub repository to include
+changes in the branch, that you have submitted as a pull request
+yourself.  In that case, you can choose to merge their changes back into
+your branch, possibly make additional changes or corrections and proceed
+from there.  It looks something like this:
 
 .. image:: JPG/tutorial_reverse_pull_request.png
    :align: center
@@ -419,7 +442,7 @@ This merge also shows up on the lammps GitHub page:
 
 **After a merge**
 
-When everything is fine, the feature branch is merged into the master branch:
+When everything is fine, the feature branch is merged into the *develop* branch:
 
 .. image:: JPG/tutorial_merged.png
    :align: center
@@ -433,8 +456,8 @@ branch!
 
 .. code-block:: bash
 
-   $ git checkout master
-   $ git pull master
+   $ git checkout develop
+   $ git pull https://github.com/lammps/lammps develop
    $ git branch -d github-tutorial-update
 
 If you do not pull first, it is not really a problem but git will warn
@@ -442,6 +465,7 @@ you at the next statement that you are deleting a local branch that
 was not yet fully merged into HEAD. This is because git does not yet
 know your branch just got merged into LAMMPS upstream. If you
 first delete and then pull, everything should still be fine.
+You can display all branches that are fully merged by:
 
 Finally, if you delete the branch locally, you might want to push this
 to your remote(s) as well:
@@ -453,14 +477,14 @@ to your remote(s) as well:
 **Recent changes in the workflow**
 
 Some changes to the workflow are not captured in this tutorial.  For
-example, in addition to the master branch, to which all new features
-should be submitted, there is now also an "unstable" and a "stable"
-branch; these have the same content as "master", but are only updated
-after a patch release or stable release was made.
-Furthermore, the naming of the patches now follow the pattern
-"patch_<Day><Month><Year>" to simplify comparisons between releases.
-Finally, all patches and submissions are subject to automatic testing
-and code checks to make sure they at the very least compile.
+example, in addition to the *develop* branch, to which all new features
+should be submitted, there is also a *release* and a *stable* branch;
+these have the same content as *develop*, but are only updated after a
+patch release or stable release was made.  Furthermore, the naming of
+the patches now follow the pattern "patch_<Day><Month><Year>" to
+simplify comparisons between releases.  Finally, all patches and
+submissions are subject to automatic testing and code checks to make
+sure they at the very least compile.
 
 A discussion of the LAMMPS developer GitHub workflow can be found in the file
-`doc/github-development-workflow.md <https://github.com/lammps/lammps/blob/master/doc/github-development-workflow.md>`_
+`doc/github-development-workflow.md <https://github.com/lammps/lammps/blob/develop/doc/github-development-workflow.md>`_

doc/src/Howto_pylammps.rst

@@ -545,6 +545,6 @@ Feedback and Contributing
 -------------------------
 
 If you find this Python interface useful, please feel free to provide feedback
-and ideas on how to improve it to Richard Berger (richard.berger@temple.edu). We also
+and ideas on how to improve it to Richard Berger (richard.berger@outlook.com). We also
 want to encourage people to write tutorial style IPython notebooks showcasing LAMMPS usage
 and maybe their latest research results.

doc/src/Howto_thermostat.rst

@@ -2,8 +2,8 @@ Thermostats
 ===========
 
 Thermostatting means controlling the temperature of particles in an MD
-simulation.  :doc:`Barostatting <Howto_barostat>` means controlling the
-pressure.  Since the pressure includes a kinetic component due to
+simulation.  :doc:`Barostatting <Howto_barostat>` means controlling
+the pressure.  Since the pressure includes a kinetic component due to
 particle velocities, both these operations require calculation of the
 temperature.  Typically a target temperature (T) and/or pressure (P)
 is specified by the user, and the thermostat or barostat attempts to
@@ -26,11 +26,13 @@ can be invoked via the *dpd/tstat* pair style:
 * :doc:`pair_style dpd/tstat <pair_dpd>`
 
 :doc:`Fix nvt <fix_nh>` only thermostats the translational velocity of
-particles.  :doc:`Fix nvt/sllod <fix_nvt_sllod>` also does this, except
-that it subtracts out a velocity bias due to a deforming box and
-integrates the SLLOD equations of motion.  See the :doc:`Howto nemd <Howto_nemd>` page for further details.  :doc:`Fix nvt/sphere <fix_nvt_sphere>` and :doc:`fix nvt/asphere <fix_nvt_asphere>` thermostat not only translation
-velocities but also rotational velocities for spherical and aspherical
-particles.
+particles.  :doc:`Fix nvt/sllod <fix_nvt_sllod>` also does this,
+except that it subtracts out a velocity bias due to a deforming box
+and integrates the SLLOD equations of motion.  See the :doc:`Howto
+nemd <Howto_nemd>` page for further details.  :doc:`Fix nvt/sphere
+<fix_nvt_sphere>` and :doc:`fix nvt/asphere <fix_nvt_asphere>`
+thermostat not only translation velocities but also rotational
+velocities for spherical and aspherical particles.
 
 .. note::
 
@@ -40,25 +42,31 @@ particles.
    e.g. molecular systems.  The latter can be tricky to do correctly.
 
 DPD thermostatting alters pairwise interactions in a manner analogous
-to the per-particle thermostatting of :doc:`fix langevin <fix_langevin>`.
+to the per-particle thermostatting of :doc:`fix langevin
+<fix_langevin>`.
 
-Any of the thermostatting fixes can be instructed to use custom temperature
-computes that remove bias which has two effects:  first, the current
-calculated temperature, which is compared to the requested target temperature,
-is calculated with the velocity bias removed;  second, the thermostat adjusts
-only the thermal temperature component of the particle's velocities, which are
-the velocities with the bias removed.  The removed bias is then added back
-to the adjusted velocities.  See the doc pages for the individual
-fixes and for the :doc:`fix_modify <fix_modify>` command for
-instructions on how to assign a temperature compute to a
-thermostatting fix.  For example, you can apply a thermostat to only
-the x and z components of velocity by using it in conjunction with
-:doc:`compute temp/partial <compute_temp_partial>`.  Of you could
-thermostat only the thermal temperature of a streaming flow of
-particles without affecting the streaming velocity, by using
-:doc:`compute temp/profile <compute_temp_profile>`.
+Any of the thermostatting fixes can be instructed to use custom
+temperature computes that remove bias which has two effects: first,
+the current calculated temperature, which is compared to the requested
+target temperature, is calculated with the velocity bias removed;
+second, the thermostat adjusts only the thermal temperature component
+of the particle's velocities, which are the velocities with the bias
+removed.  The removed bias is then added back to the adjusted
+velocities.  See the doc pages for the individual fixes and for the
+:doc:`fix_modify <fix_modify>` command for instructions on how to
+assign a temperature compute to a thermostatting fix.
 
-Below is a list of some custom temperature computes that can be used like that:
+For example, you can apply a thermostat only to atoms in a spatial
+region by using it in conjunction with :doc:`compute temp/region
+<compute_temp_region>`.  Or you can apply a thermostat to only the x
+and z components of velocity by using it with :doc:`compute
+temp/partial <compute_temp_partial>`.  Of you could thermostat only
+the thermal temperature of a streaming flow of particles without
+affecting the streaming velocity, by using :doc:`compute temp/profile
+<compute_temp_profile>`.
+
+Below is a list of custom temperature computes that can be used like
+that:
 
 * :doc:`compute_temp_asphere`
 * :doc:`compute_temp_body`
@@ -72,8 +80,6 @@ Below is a list of some custom temperature computes that can be used like that:
 * :doc:`compute_temp_rotate`
 * :doc:`compute_temp_sphere`
 
-
-
 .. note::
 
    Only the nvt fixes perform time integration, meaning they update
@@ -86,17 +92,17 @@ Below is a list of some custom temperature computes that can be used like that:
 * :doc:`fix nve/sphere <fix_nve_sphere>`
 * :doc:`fix nve/asphere <fix_nve_asphere>`
 
-Thermodynamic output, which can be setup via the
-:doc:`thermo_style <thermo_style>` command, often includes temperature
-values.  As explained on the page for the
-:doc:`thermo_style <thermo_style>` command, the default temperature is
-setup by the thermo command itself.  It is NOT the temperature
-associated with any thermostatting fix you have defined or with any
-compute you have defined that calculates a temperature.  The doc pages
-for the thermostatting fixes explain the ID of the temperature compute
-they create.  Thus if you want to view these temperatures, you need to
-specify them explicitly via the :doc:`thermo_style custom <thermo_style>` command.  Or you can use the
-:doc:`thermo_modify <thermo_modify>` command to re-define what
+Thermodynamic output, which can be setup via the :doc:`thermo_style
+<thermo_style>` command, often includes temperature values.  As
+explained on the page for the :doc:`thermo_style <thermo_style>`
+command, the default temperature is setup by the thermo command
+itself.  It is NOT the temperature associated with any thermostatting
+fix you have defined or with any compute you have defined that
+calculates a temperature.  The doc pages for the thermostatting fixes
+explain the ID of the temperature compute they create.  Thus if you
+want to view these temperatures, you need to specify them explicitly
+via the :doc:`thermo_style custom <thermo_style>` command.  Or you can
+use the :doc:`thermo_modify <thermo_modify>` command to re-define what
 temperature compute is used for default thermodynamic output.
 
 ----------

doc/src/Install_git.rst

@@ -9,7 +9,8 @@ has several advantages:
   command.
 * You can create your own development branches to add code to LAMMPS.
 * You can submit your new features back to GitHub for inclusion in
-  LAMMPS.
+  LAMMPS.  For that you should first create your own :doc:`fork on
+  GitHub <Howto_github>`.
 
 You must have `git <git_>`_ installed on your system to use the
 commands explained below to communicate with the git servers on
@@ -20,35 +21,56 @@ provides `limited support for subversion clients <svn_>`_.
 
    As of October 2016, the official home of public LAMMPS development is
    on GitHub.  The previously advertised LAMMPS git repositories on
-   git.lammps.org and bitbucket.org are now deprecated or offline.
+   git.lammps.org and bitbucket.org are now offline or deprecated.
 
 .. _git: https://git-scm.com
 .. _svn: https://help.github.com/en/github/importing-your-projects-to-github/working-with-subversion-on-github
 
-You can follow LAMMPS development on 3 different git branches:
+You can follow the LAMMPS development on 3 different git branches:
 
-* **stable**   :  this branch is updated with every stable release
-* **unstable** :  this branch is updated with every patch release
-* **master**   :  this branch continuously follows ongoing development
+* **stable**   :  this branch is updated from the *release* branch with
+  every stable release version and also has selected bug fixes and updates
+  back-ported from the *develop* branch
+* **release**  :  this branch is updated with every patch release;
+  updates are always "fast forward" merges from *develop*
+* **develop**  :  this branch follows the ongoing development and
+  is updated with every merge commit of a pull request
 
 To access the git repositories on your box, use the clone command to
 create a local copy of the LAMMPS repository with a command like:
 
 .. code-block:: bash
 
-   $ git clone -b unstable https://github.com/lammps/lammps.git mylammps
+   $ git clone -b release https://github.com/lammps/lammps.git mylammps
 
 where "mylammps" is the name of the directory you wish to create on
-your machine and "unstable" is one of the 3 branches listed above.
+your machine and "release" is one of the 3 branches listed above.
 (Note that you actually download all 3 branches; you can switch
 between them at any time using "git checkout <branch name>".)
 
+.. admonition:: Saving time and disk space when using ``git clone``
+
+   The complete git history of the LAMMPS project is quite large because
+   it contains the entire commit history of the project since fall 2006,
+   which includes the time when LAMMPS was managed with subversion.
+   This includes a few commits that have added and removed some large
+   files (mostly by accident).  If you do not need access to the entire
+   commit history (most people don't), you can speed up the "cloning"
+   process and reduce local disk space requirements by using the
+   *--depth* git command line flag.  That will create a "shallow clone"
+   of the repository containing only a subset of the git history.  Using
+   a depth of 1000 is usually sufficient to include the head commits of
+   the *develop* and the *release* branches.  To include the head commit
+   of the *stable* branch you may need a depth of up to 10000.  If you
+   later need more of the git history, you can always convert the
+   shallow clone into a "full clone".
+
 Once the command completes, your directory will contain the same files
 as if you unpacked a current LAMMPS tarball, with the exception, that
 the HTML documentation files are not included.  They can be fetched
 from the LAMMPS website by typing ``make fetch`` in the doc directory.
-Or they can be generated from the content provided in doc/src by
-typing ``make html`` from the doc directory.
+Or they can be generated from the content provided in ``doc/src`` by
+typing ``make html`` from the ``doc`` directory.
 
 After initial cloning, as bug fixes and new features are added to
 LAMMPS you can stay up-to-date by typing the following git commands
@@ -56,9 +78,9 @@ from within the "mylammps" directory:
 
 .. code-block:: bash
 
-   $ git checkout unstable      # not needed if you always stay in this branch
-   $ git checkout stable        # use one of these 3 checkout commands
-   $ git checkout master        # to choose the branch to follow
+   $ git checkout release      # not needed if you always stay in this branch
+   $ git checkout stable       # use one of these 3 checkout commands
+   $ git checkout develop      # to choose the branch to follow
    $ git pull
 
 Doing a "pull" will not change any files you have added to the LAMMPS
@@ -81,7 +103,7 @@ Stable versions and what tagID to use for a particular stable version
 are discussed on `this page <https://www.lammps.org/bug.html#version>`_.
 Note that this command will print some warnings, because in order to get
 back to the latest revision and to be able to update with ``git pull``
-again, you will need to do ``git checkout unstable`` (or
+again, you will need to do ``git checkout release`` (or
 check out any other desired branch) first.
 
 Once you have updated your local files with a ``git pull`` (or ``git
@@ -137,9 +159,9 @@ changed.  How to do this depends on the build system you are using.
 .. admonition:: Git protocols
    :class: note
 
-   The servers at github.com support the "git://" and "https://" access
-   protocols for anonymous, read-only access.  If you have a suitably
-   configured GitHub account, you may also use SSH protocol with the
+   The servers at github.com support the "https://" access protocol for
+   anonymous, read-only access.  If you have a suitably configured GitHub
+   account, you may also use SSH protocol with the
    URL "git@github.com:lammps/lammps.git".
 
 The LAMMPS GitHub project is currently managed by Axel Kohlmeyer

doc/src/Intro_authors.rst

@@ -8,7 +8,7 @@ University:
 * Aidan Thompson, athomps at sandia.gov
 * Stan Moore, stamoor at sandia.gov
 * Axel Kohlmeyer, akohlmey at gmail.com
-* Richard Berger, richard.berger at temple.edu
+* Richard Berger, richard.berger at outlook.com
 
 .. _sjp: http://www.cs.sandia.gov/~sjplimp
 .. _lws: https://www.lammps.org

doc/src/Intro_citing.rst

@@ -4,28 +4,41 @@ Citing LAMMPS
 Core Algorithms
 ^^^^^^^^^^^^^^^
 
-Since LAMMPS is a community project, there is not a single one
-publication or reference that describes **all** of LAMMPS.
-The canonical publication that describes the foundation, that is
-the basic spatial decomposition approach, the neighbor finding,
-and basic communications algorithms used in LAMMPS is:
+The paper mentioned below is the best overview of LAMMPS, but there are
+also publications describing particular models or algorithms implemented
+in LAMMPS or complementary software that is has interfaces to.  Please
+see below for how to cite contributions to LAMMPS.
 
- `S. Plimpton, Fast Parallel Algorithms for Short-Range Molecular Dynamics, J Comp Phys, 117, 1-19 (1995). <http://www.sandia.gov/~sjplimp/papers/jcompphys95.pdf>`_
+.. _lammps_paper:
 
-So any project using LAMMPS (or a derivative application using LAMMPS as
-a simulation engine) should cite this paper. A new publication
-describing the developments and improvements of LAMMPS in the 25 years
-since then is currently in preparation.
+The latest canonical publication that describes the basic features, the
+source code design, the program structure, the spatial decomposition
+approach, the neighbor finding, basic communications algorithms, and how
+users and developers have contributed to LAMMPS is:
+
+  `LAMMPS - A flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales, Comp. Phys. Comm. 271, 108171 (2022) <https://doi.org/10.1016/j.cpc.2021.108171>`_
+
+So a project using LAMMPS or a derivative application that uses LAMMPS
+as a simulation engine should cite this paper.  The paper is expected to
+be published in its final form under the same DOI in the first half
+of 2022.  Please also give the URL of the LAMMPS website in your paper,
+namely https://www.lammps.org.
+
+The original publication describing the parallel algorithms used in the
+initial versions of LAMMPS is:
+
+  `S. Plimpton, Fast Parallel Algorithms for Short-Range Molecular Dynamics, J Comp Phys, 117, 1-19 (1995). <http://www.sandia.gov/~sjplimp/papers/jcompphys95.pdf>`_
 
 
 DOI for the LAMMPS code
 ^^^^^^^^^^^^^^^^^^^^^^^
 
-LAMMPS developers use the `Zenodo service at CERN
-<https://zenodo.org/>`_ to create digital object identifies (DOI) for
-stable releases of the LAMMPS code. There are two types of DOIs for the
-LAMMPS source code: the canonical DOI for **all** versions of LAMMPS,
-which will always point to the **latest** stable release version is:
+LAMMPS developers use the `Zenodo service at CERN <https://zenodo.org/>`_
+to create digital object identifies (DOI) for stable releases of the
+LAMMPS source code. There are two types of DOIs for the LAMMPS source code.
+
+The canonical DOI for **all** versions of LAMMPS, which will always
+point to the **latest** stable release version is:
 
 - DOI: `10.5281/zenodo.3726416 <https://dx.doi.org/10.5281/zenodo.3726416>`_
 
@@ -45,11 +58,13 @@ about LAMMPS and its features.
 Citing contributions
 ^^^^^^^^^^^^^^^^^^^^
 
-LAMMPS has many features and that use either previously published
-methods and algorithms or novel features.  It also includes potential
-parameter filed for specific models.  Where available, a reminder about
-references for optional features used in a specific run is printed to
-the screen and log file.  Style and output location can be selected with
-the :ref:`-cite command-line switch <cite>`.  Additional references are
+LAMMPS has many features that use either previously published methods
+and algorithms or novel features.  It also includes potential parameter
+files for specific models.  Where available, a reminder about references
+for optional features used in a specific run is printed to the screen
+and log file.  Style and output location can be selected with the
+:ref:`-cite command-line switch <cite>`.  Additional references are
 given in the documentation of the :doc:`corresponding commands
-<Commands_all>` or in the :doc:`Howto tutorials <Howto>`.
+<Commands_all>` or in the :doc:`Howto tutorials <Howto>`.  So please
+make certain, that you provide the proper acknowledgments and citations
+in any published works using LAMMPS.

doc/src/Intro_opensource.rst

@@ -19,7 +19,7 @@ software and open-source distribution, see `www.gnu.org <gnuorg_>`_
 or `www.opensource.org <opensource_>`_.  The legal text of the GPL as it
 applies to LAMMPS is in the LICENSE file included in the LAMMPS distribution.
 
-.. _gpl: https://github.com/lammps/lammps/blob/master/LICENSE
+.. _gpl: https://github.com/lammps/lammps/blob/develop/LICENSE
 
 .. _lgpl: https://www.gnu.org/licenses/old-licenses/lgpl-2.1.html
 

doc/src/Library_create.rst

@@ -34,7 +34,7 @@ simple example demonstrating its use:
      int lmpargc = sizeof(lmpargv)/sizeof(const char *);
 
      /* create LAMMPS instance */
-     handle = lammps_open_no_mpi(lmpargc, lmpargv, NULL);
+     handle = lammps_open_no_mpi(lmpargc, (char **)lmpargv, NULL);
      if (handle == NULL) {
        printf("LAMMPS initialization failed");
        lammps_mpi_finalize();

doc/src/Library_utility.rst

@@ -13,6 +13,7 @@ functions.  They do not directly call the LAMMPS library.
 - :cpp:func:`lammps_fix_external_set_virial_peratom`
 - :cpp:func:`lammps_fix_external_set_vector_length`
 - :cpp:func:`lammps_fix_external_set_vector`
+- :cpp:func:`lammps_flush_buffers`
 - :cpp:func:`lammps_free`
 - :cpp:func:`lammps_is_running`
 - :cpp:func:`lammps_force_timeout`
@@ -72,6 +73,11 @@ where such memory buffers were allocated that require the use of
 
 -----------------------
 
+.. doxygenfunction:: lammps_flush_buffers
+   :project: progguide
+
+-----------------------
+
 .. doxygenfunction:: lammps_free
    :project: progguide
 

doc/src/Manual_version.rst

@@ -7,26 +7,34 @@ correctly and reliably at all times.  You can follow its development
 in a public `git repository on GitHub <https://github.com/lammps/lammps>`_.
 
 Whenever we fix a bug or update or add a feature, it will be merged into
-the `master` branch of the git repository.  When a sufficient number of
+the *develop* branch of the git repository.  When a sufficient number of
 changes have accumulated *and* the software passes a set of automated
 tests, we release it in the next *patch* release, which are made every
-few weeks.  Info on patch releases are on `this website page
+few weeks.  The *release* branch of the git repository is updated with
+every such release.  Info on patch releases are on `this website page
 <https://www.lammps.org/bug.html>`_.
 
-Once or twice a year, only bug fixes and small, non-intrusive changes are
-included for a period of time, and the code is subjected to more detailed
+Once or twice a year, we apply only bug fixes and small, non-intrusive
+changes to the *develop* branch and the code is subjected to more detailed
 and thorough testing than the default automated testing.  The latest
-patch release after such a period is then labeled as a *stable* version.
+patch release after such a period is then also labeled as a *stable* version
+and the *stable* branch is updated with it.  Between stable releases
+we occasionally release some updates to the stable release containing
+only bug fixes and updates back-ported from *develop* but no new features
+and update the *stable* branch accordingly.
 
-Each version of LAMMPS contains all the features and bug-fixes up to
-and including its version date.
+Each version of LAMMPS contains all the documented features up to and
+including its version date.
 
 The version date is printed to the screen and logfile every time you
 run LAMMPS. It is also in the file src/version.h and in the LAMMPS
 directory name created when you unpack a tarball.  And it is on the
 first page of the :doc:`manual <Manual>`.
 
-* If you browse the HTML pages on the LAMMPS WWW site, they always
-  describe the most current patch release of LAMMPS.
+* If you browse the HTML pages on the LAMMPS WWW site, they will by
+  default describe the most current patch release version of LAMMPS.
+  In the navigation bar on the bottom left, there is the option to
+  view instead the documentation for the most recent *stable* version
+  or the latest version from the current development branch.
 * If you browse the HTML pages included in your tarball, they
   describe the version you have, which may be older.

doc/src/Modify_pair.rst

@@ -12,24 +12,24 @@ includes some optional methods to enable its use with rRESPA.
 
 Here is a brief description of the class methods in pair.h:
 
-+---------------------------------+-------------------------------------------------------------------+
-| compute                         | workhorse routine that computes pairwise interactions             |
-+---------------------------------+-------------------------------------------------------------------+
-| settings                        | reads the input script line with arguments you define             |
-+---------------------------------+-------------------------------------------------------------------+
-| coeff                           | set coefficients for one i,j type pair                            |
-+---------------------------------+-------------------------------------------------------------------+
-| init_one                        | perform initialization for one i,j type pair                      |
-+---------------------------------+-------------------------------------------------------------------+
-| init_style                      | initialization specific to this pair style                        |
-+---------------------------------+-------------------------------------------------------------------+
-| write & read_restart            | write/read i,j pair coeffs to restart files                       |
-+---------------------------------+-------------------------------------------------------------------+
-| write & read_restart_settings   | write/read global settings to restart files                       |
-+---------------------------------+-------------------------------------------------------------------+
-| single                          | force and energy of a single pairwise interaction between 2 atoms |
-+---------------------------------+-------------------------------------------------------------------+
-| compute_inner/middle/outer      | versions of compute used by rRESPA                                |
-+---------------------------------+-------------------------------------------------------------------+
++---------------------------------+---------------------------------------------------------------------+
+| compute                         | workhorse routine that computes pairwise interactions               |
++---------------------------------+---------------------------------------------------------------------+
+| settings                        | reads the input script line with arguments you define               |
++---------------------------------+---------------------------------------------------------------------+
+| coeff                           | set coefficients for one i,j type pair                              |
++---------------------------------+---------------------------------------------------------------------+
+| init_one                        | perform initialization for one i,j type pair                        |
++---------------------------------+---------------------------------------------------------------------+
+| init_style                      | initialization specific to this pair style                          |
++---------------------------------+---------------------------------------------------------------------+
+| write & read_restart            | write/read i,j pair coeffs to restart files                         |
++---------------------------------+---------------------------------------------------------------------+
+| write & read_restart_settings   | write/read global settings to restart files                         |
++---------------------------------+---------------------------------------------------------------------+
+| single                          | force/r and energy of a single pairwise interaction between 2 atoms |
++---------------------------------+---------------------------------------------------------------------+
+| compute_inner/middle/outer      | versions of compute used by rRESPA                                  |
++---------------------------------+---------------------------------------------------------------------+
 
 The inner/middle/outer routines are optional.

doc/src/Modify_style.rst

@@ -305,6 +305,40 @@ you are uncertain, please ask.
   FILE pointers and only be done on MPI rank 0.  Use the :cpp:func:`utils::logmesg`
   convenience function where possible.
 
+- Usage of C++11 `virtual`, `override`, `final` keywords: Please follow the
+  `C++ Core Guideline C.128 <https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines#Rh-override>`_.
+  That means, you should only use `virtual` to declare a new virtual
+  function, `override` to indicate you are overriding an existing virtual
+  function, and `final` to prevent any further overriding.
+
+- Trivial destructors: Prefer not writing destructors when they are empty and `default`.
+
+  .. code-block:: c++
+
+     // don't write destructors for A or B like this
+     class A : protected Pointers {
+      public:
+        A();
+        ~A() override {}
+     };
+
+     class B : protected Pointers {
+      public:
+        B();
+        ~B() override = default;
+     };
+
+     // instead, let the compiler create the implicit default destructor by not writing it
+     class A : protected Pointers {
+      public:
+        A();
+     };
+
+     class B : protected Pointers {
+      public:
+        B();
+     };
+
 - Header files, especially those defining a "style", should only use
   the absolute minimum number of include files and **must not** contain
   any ``using`` statements. Typically that would be only the header for

doc/src/Packages_details.rst

@@ -1880,6 +1880,12 @@ MPIIO library.  It adds :doc:`dump styles <dump>` with a "mpiio" in
 their style name.  Restart files with an ".mpiio" suffix are also
 written and read in parallel.
 
+.. warning::
+
+   The MPIIO package is currently unmaintained and has become
+   unreliable. Use with caution.
+
+
 **Install:**
 
 The MPIIO package requires that LAMMPS is build in :ref:`MPI parallel mode <serial>`.

doc/src/Run_basics.rst

@@ -2,17 +2,25 @@ Basics of running LAMMPS
 ========================
 
 LAMMPS is run from the command line, reading commands from a file via
-the -in command line flag, or from standard input.
-Using the "-in in.file" variant is recommended:
+the -in command line flag, or from standard input.  Using the "-in
+in.file" variant is recommended (see note below).  The name of the
+LAMMPS executable is either ``lmp`` or ``lmp_<machine>`` with
+`<machine>` being the machine string used when compiling LAMMPS.  This
+is required when compiling LAMMPS with the traditional build system
+(e.g. with ``make mpi``), but optional when using CMake to configure and
+build LAMMPS:
 
 .. code-block:: bash
 
    $ lmp_serial -in in.file
    $ lmp_serial < in.file
+   $ lmp -in in.file
+   $ lmp < in.file
    $ /path/to/lammps/src/lmp_serial -i in.file
    $ mpirun -np 4 lmp_mpi -in in.file
+   $ mpiexec -np 4 lmp -in in.file
    $ mpirun -np 8 /path/to/lammps/src/lmp_mpi -in in.file
-   $ mpirun -np 6 /usr/local/bin/lmp -in in.file
+   $ mpiexec -n 6 /usr/local/bin/lmp -in in.file
 
 You normally run the LAMMPS command in the directory where your input
 script is located.  That is also where output files are produced by
@@ -23,7 +31,7 @@ executable itself can be placed elsewhere.
 .. note::
 
    The redirection operator "<" will not always work when running
-   in parallel with mpirun; for those systems the -in form is required.
+   in parallel with mpirun or mpiexec; for those systems the -in form is required.
 
 As LAMMPS runs it prints info to the screen and a logfile named
 *log.lammps*\ .  More info about output is given on the

doc/src/Run_output.rst

@@ -106,7 +106,7 @@ individual ranks. Here is an example output for this section:
 ----------
 
 The third section above lists the number of owned atoms (Nlocal),
-ghost atoms (Nghost), and pair-wise neighbors stored per processor.
+ghost atoms (Nghost), and pairwise neighbors stored per processor.
 The max and min values give the spread of these values across
 processors with a 10-bin histogram showing the distribution. The total
 number of histogram counts is equal to the number of processors.
@@ -114,7 +114,7 @@ number of histogram counts is equal to the number of processors.
 ----------
 
 The last section gives aggregate statistics (across all processors)
-for pair-wise neighbors and special neighbors that LAMMPS keeps track
+for pairwise neighbors and special neighbors that LAMMPS keeps track
 of (see the :doc:`special_bonds <special_bonds>` command).  The number
 of times neighbor lists were rebuilt is tallied, as is the number of
 potentially *dangerous* rebuilds.  If atom movement triggered neighbor

doc/src/Speed.rst

@@ -14,7 +14,7 @@ Intel Xeon Phi co-processors.
 
 The `Benchmark page <https://www.lammps.org/bench.html>`_ of the LAMMPS
 website gives performance results for the various accelerator
-packages discussed on the :doc:`Speed packages <Speed_packages>` doc
+packages discussed on the :doc:`Accelerator packages <Speed_packages>`
 page, for several of the standard LAMMPS benchmark problems, as a
 function of problem size and number of compute nodes, on different
 hardware platforms.

doc/src/Speed_kokkos.rst

@@ -214,7 +214,7 @@ threads/task as Nt. The product of these two values should be N, i.e.
    The default for the :doc:`package kokkos <package>` command when
    running on KNL is to use "half" neighbor lists and set the Newton flag
    to "on" for both pairwise and bonded interactions. This will typically
-   be best for many-body potentials. For simpler pair-wise potentials, it
+   be best for many-body potentials. For simpler pairwise potentials, it
    may be faster to use a "full" neighbor list with Newton flag to "off".
    Use the "-pk kokkos" :doc:`command-line switch <Run_options>` to change
    the default :doc:`package kokkos <package>` options. See its page for

doc/src/Tools.rst

@@ -277,17 +277,34 @@ at ens-lyon.fr, alain.dequidt at uca.fr
 eam database tool
 -----------------------------
 
-The tools/eam_database directory contains a Fortran program that will
-generate EAM alloy setfl potential files for any combination of 16
-elements: Cu, Ag, Au, Ni, Pd, Pt, Al, Pb, Fe, Mo, Ta, W, Mg, Co, Ti,
-Zr.  The files can then be used with the :doc:`pair_style eam/alloy <pair_eam>` command.
+The tools/eam_database directory contains a Fortran and a Python program
+that will generate EAM alloy setfl potential files for any combination
+of the 17 elements: Cu, Ag, Au, Ni, Pd, Pt, Al, Pb, Fe, Mo, Ta, W, Mg,
+Co, Ti, Zr, Cr.  The files can then be used with the :doc:`pair_style
+eam/alloy <pair_eam>` command.
 
-The tool is authored by Xiaowang Zhou (Sandia), xzhou at sandia.gov,
-and is based on his paper:
+The Fortran version of the tool was authored by Xiaowang Zhou (Sandia),
+xzhou at sandia.gov, with updates from Lucas Hale (NIST) lucas.hale at
+nist.gov and is based on his paper:
 
 X. W. Zhou, R. A. Johnson, and H. N. G. Wadley, Phys. Rev. B, 69,
 144113 (2004).
 
+The parameters for Cr were taken from:
+
+Lin Z B, Johnson R A and Zhigilei L V, Phys. Rev. B 77 214108 (2008).
+
+The Python version of the tool was authored  by Germain Clavier
+(TU Eindhoven) g.m.g.c.clavier at tue.nl or germain.clavier at gmail.com
+
+.. note::
+
+   The parameters in the database are only optimized for individual
+   elements. The mixed parameters for interactions between different
+   elements generated by this tool are derived from simple mixing rules
+   and are thus inferior to parameterizations that are specifically
+   optimized for specific mixtures and combinations of elements.
+
 ----------
 
 .. _eamgn:

doc/src/accel_styles.rst

@@ -1,7 +1,7 @@
 Styles with a *gpu*, *intel*, *kk*, *omp*, or *opt* suffix are
 functionally the same as the corresponding style without the suffix.
 They have been optimized to run faster, depending on your available
-hardware, as discussed on the :doc:`Speed packages <Speed_packages>` doc
+hardware, as discussed on the :doc:`Accelerator packages <Speed_packages>`
 page.  The accelerated styles take the same arguments and should
 produce the same results, except for round-off and precision issues.
 
@@ -13,5 +13,5 @@ You can specify the accelerated styles explicitly in your input script
 by including their suffix, or you can use the :doc:`-suffix command-line switch <Run_options>` when you invoke LAMMPS, or you can use the
 :doc:`suffix <suffix>` command in your input script.
 
-See the :doc:`Speed packages <Speed_packages>` page for more
+See the :doc:`Accelerator packages <Speed_packages>` page for more
 instructions on how to use the accelerated styles effectively.

doc/src/angle_charmm.rst

@@ -56,23 +56,7 @@ radian\^2.
 
 ----------
 
-Styles with a *gpu*, *intel*, *kk*, *omp*, or *opt* suffix are
-functionally the same as the corresponding style without the suffix.
-They have been optimized to run faster, depending on your available
-hardware, as discussed on the :doc:`Speed packages <Speed_packages>` doc
-page.  The accelerated styles take the same arguments and should
-produce the same results, except for round-off and precision issues.
-
-These accelerated styles are part of the GPU, INTEL, KOKKOS,
-OPENMP and OPT packages, respectively.  They are only enabled if
-LAMMPS was built with those packages.  See the :doc:`Build package <Build_package>` page for more info.
-
-You can specify the accelerated styles explicitly in your input script
-by including their suffix, or you can use the :doc:`-suffix command-line switch <Run_options>` when you invoke LAMMPS, or you can use the
-:doc:`suffix <suffix>` command in your input script.
-
-See :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+.. include:: accel_styles.rst
 
 ----------
 

doc/src/angle_class2.rst

@@ -64,34 +64,44 @@ These are the 4 coefficients for the :math:`E_a` formula:
 radians internally; hence the various :math:`K` are effectively energy
 per radian\^2 or radian\^3 or radian\^4.
 
-For the :math:`E_{bb}` formula, each line in a :doc:`angle_coeff <angle_coeff>`
-command in the input script lists 4 coefficients, the first of which
-is "bb" to indicate they are BondBond coefficients.  In a data file,
-these coefficients should be listed under a "BondBond Coeffs" heading
-and you must leave out the "bb", i.e. only list 3 coefficients after
-the angle type.
+For the :math:`E_{bb}` formula, each line in a :doc:`angle_coeff
+<angle_coeff>` command in the input script lists 4 coefficients, the
+first of which is "bb" to indicate they are BondBond coefficients.  In
+a data file, these coefficients should be listed under a "BondBond
+Coeffs" heading and you must leave out the "bb", i.e. only list 3
+coefficients after the angle type.
 
 * bb
 * :math:`M` (energy/distance\^2)
 * :math:`r_1` (distance)
 * :math:`r_2` (distance)
 
-For the :math:`E_{ba}` formula, each line in a :doc:`angle_coeff <angle_coeff>`
-command in the input script lists 5 coefficients, the first of which
-is "ba" to indicate they are BondAngle coefficients.  In a data file,
-these coefficients should be listed under a "BondAngle Coeffs" heading
-and you must leave out the "ba", i.e. only list 4 coefficients after
-the angle type.
+For the :math:`E_{ba}` formula, each line in a :doc:`angle_coeff
+<angle_coeff>` command in the input script lists 5 coefficients, the
+first of which is "ba" to indicate they are BondAngle coefficients.
+In a data file, these coefficients should be listed under a "BondAngle
+Coeffs" heading and you must leave out the "ba", i.e. only list 4
+coefficients after the angle type.
 
 * ba
-* :math:`N_1` (energy/distance\^2)
-* :math:`N_2` (energy/distance\^2)
+* :math:`N_1` (energy/distance)
+* :math:`N_2` (energy/distance)
 * :math:`r_1` (distance)
 * :math:`r_2` (distance)
 
 The :math:`\theta_0` value in the :math:`E_{ba}` formula is not specified,
 since it is the same value from the :math:`E_a` formula.
 
+.. note::
+
+   It is important that the order of the I,J,K atoms in each angle
+   listed in the Angles section of the data file read by the
+   :doc:`read_data <read_data>` command be consistent with the order
+   of the :math:`r_1` and :math:`r_2` BondBond and BondAngle
+   coefficients.  This is because the terms in the formulas for
+   :math:`E_{bb}` and :math:`E_{ba}` will use the I,J atoms to compute
+   :math:`r_{ij}` and the J,K atoms to compute :math:`r_{jk}`.
+
 ----------
 
 .. include:: accel_styles.rst

doc/src/atom_style.rst

@@ -319,28 +319,9 @@ styles; see the :doc:`Modify <Modify>` doc page.
 
 ----------
 
-Styles with a *kk* suffix are functionally the same as the
-corresponding style without the suffix.  They have been optimized to
-run faster, depending on your available hardware, as discussed in on
-the :doc:`Speed packages <Speed_packages>` doc page.  The accelerated
-styles take the same arguments and should produce the same results,
-except for round-off and precision issues.
+.. include:: accel_styles.rst
 
-Note that other acceleration packages in LAMMPS, specifically the GPU,
-INTEL, OPENMP, and OPT packages do not use accelerated atom
-styles.
-
-The accelerated styles are part of the KOKKOS package.  They are only
-enabled if LAMMPS was built with those packages.  See the :doc:`Build
-package <Build_package>` page for more info.
-
-You can specify the accelerated styles explicitly in your input script
-by including their suffix, or you can use the :doc:`-suffix command-line
-switch <Run_options>` when you invoke LAMMPS, or you can use the
-:doc:`suffix <suffix>` command in your input script.
-
-See the :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+----------
 
 Restrictions
 """"""""""""

doc/src/balance.rst

@@ -383,7 +383,7 @@ multiple groups, its weight is the product of the weight factors.
 
 This weight style is useful in combination with pair style
 :doc:`hybrid <pair_hybrid>`, e.g. when combining a more costly many-body
-potential with a fast pair-wise potential.  It is also useful when
+potential with a fast pairwise potential.  It is also useful when
 using :doc:`run_style respa <run_style>` where some portions of the
 system have many bonded interactions and others none.  It assumes that
 the computational cost for each group remains constant over time.

doc/src/bond_fene.rst

@@ -1,4 +1,5 @@
 .. index:: bond_style fene
+.. index:: bond_style fene/nm
 .. index:: bond_style fene/intel
 .. index:: bond_style fene/kk
 .. index:: bond_style fene/omp
@@ -8,12 +9,16 @@ bond_style fene command
 
 Accelerator Variants: *fene/intel*, *fene/kk*, *fene/omp*
 
+bond_style fene/nm command
+==========================
+
 Syntax
 """"""
 
 .. code-block:: LAMMPS
 
    bond_style fene
+   bond_style fene/nm
 
 Examples
 """"""""
@@ -23,6 +28,9 @@ Examples
    bond_style fene
    bond_coeff 1 30.0 1.5 1.0 1.0
 
+   bond_style fene/nm
+   bond_coeff 1 2.25344 1.5 1.0 1.12246 2 6
+
 Description
 """""""""""
 
@@ -38,16 +46,36 @@ term is attractive, the second Lennard-Jones term is repulsive.  The
 first term extends to :math:`R_0`, the maximum extent of the bond.  The second
 term is cutoff at :math:`2^\frac{1}{6} \sigma`, the minimum of the LJ potential.
 
-The following coefficients must be defined for each bond type via the
-:doc:`bond_coeff <bond_coeff>` command as in the example above, or in
-the data file or restart files read by the :doc:`read_data <read_data>`
-or :doc:`read_restart <read_restart>` commands:
+The *fene/nm* bond style substitutes the standard LJ potential with the generalized LJ potential
+in the same form as in pair style :doc:`nm/cut <pair_nm>`. The bond energy is then given by
+
+.. math::
+
+  E = -0.5 K r_0^2  \ln \left[ 1 - \left(\frac{r}{R_0}\right)^2\right] + \frac{E_0}{(n-m)} \left[ m \left(\frac{r_0}{r}\right)^n - n \left(\frac{r_0}{r}\right)^m \right]
+
+Similar to the *fene* style, the generalized Lennard-Jones is cut off at
+the potential minimum, :math:`r_0`, to be repulsive only.  The following
+coefficients must be defined for each bond type via the :doc:`bond_coeff
+<bond_coeff>` command as in the example above, or in the data file or
+restart files read by the :doc:`read_data <read_data>` or
+:doc:`read_restart <read_restart>` commands:
 
 * :math:`K` (energy/distance\^2)
 * :math:`R_0` (distance)
 * :math:`\epsilon` (energy)
 * :math:`\sigma` (distance)
 
+For the *fene/nm* style, the following coefficients are used.  Please
+note, that the standard LJ potential and thus the regular FENE potential
+is recovered for (n=12 m=6) and :math:`r_0 = 2^\frac{1}{6} \sigma`.
+
+* :math:`K` (energy/distance\^2)
+* :math:`R_0` (distance)
+* :math:`E_0` (energy)
+* :math:`r_0` (distance)
+* :math:`n` (unitless)
+* :math:`m` (unitless)
+
 ----------
 
 .. include:: accel_styles.rst
@@ -57,9 +85,10 @@ or :doc:`read_restart <read_restart>` commands:
 Restrictions
 """"""""""""
 
-This bond style can only be used if LAMMPS was built with the MOLECULE
-package.  See the :doc:`Build package <Build_package>` page for more
-info.
+The *fene* bond style can only be used if LAMMPS was built with the MOLECULE
+package; the *fene/nm* bond style can only be used if LAMMPS was built
+with the EXTRA-MOLECULE package. See the :doc:`Build package <Build_package>`
+page for more info.
 
 You typically should specify :doc:`special_bonds fene <special_bonds>`
 or :doc:`special_bonds lj/coul 0 1 1 <special_bonds>` to use this bond
@@ -68,7 +97,8 @@ style.  LAMMPS will issue a warning it that's not the case.
 Related commands
 """"""""""""""""
 
-:doc:`bond_coeff <bond_coeff>`, :doc:`delete_bonds <delete_bonds>`
+:doc:`bond_coeff <bond_coeff>`, :doc:`delete_bonds <delete_bonds>`,
+:doc:`pair style lj/cut <pair_lj>`, :doc:`pair style nm/cut <pair_nm>`.
 
 Default
 """""""

doc/src/bond_style.rst

@@ -87,6 +87,7 @@ accelerated styles exist.
 * :doc:`class2 <bond_class2>` - COMPASS (class 2) bond
 * :doc:`fene <bond_fene>` - FENE (finite-extensible non-linear elastic) bond
 * :doc:`fene/expand <bond_fene_expand>` - FENE bonds with variable size particles
+* :doc:`fene/nm <bond_fene>` - FENE bonds with a generalized Lennard-Jones potential
 * :doc:`gaussian <bond_gaussian>` - multicentered Gaussian-based bond potential
 * :doc:`gromos <bond_gromos>` - GROMOS force field bond
 * :doc:`harmonic <bond_harmonic>` - harmonic bond

doc/src/compute.rst

@@ -174,6 +174,7 @@ The individual style names on the :doc:`Commands compute <Commands_compute>` pag
 * :doc:`angle <compute_angle>` - energy of each angle sub-style
 * :doc:`angle/local <compute_angle_local>` - theta and energy of each angle
 * :doc:`angmom/chunk <compute_angmom_chunk>` - angular momentum for each chunk
+* :doc:`ave/sphere/atom <compute_ave_sphere_atom>` - compute local density and temperature around each atom
 * :doc:`basal/atom <compute_basal_atom>` - calculates the hexagonal close-packed "c" lattice vector of each atom
 * :doc:`body/local <compute_body_local>` - attributes of body sub-particles
 * :doc:`bond <compute_bond>` - energy of each bond sub-style

doc/src/compute_ave_sphere_atom.rst

@@ -0,0 +1,101 @@
+.. index:: compute ave/sphere/atom
+.. index:: compute ave/sphere/atom/kk
+
+compute ave/sphere/atom command
+================================
+
+Accelerator Variants: *ave/sphere/atom/kk*
+
+Syntax
+""""""
+
+.. parsed-literal::
+
+   compute ID group-ID ave/sphere/atom keyword values ...
+
+* ID, group-ID are documented in :doc:`compute <compute>` command
+* ave/sphere/atom = style name of this compute command
+* one or more keyword/value pairs may be appended
+
+  .. parsed-literal::
+
+     keyword = *cutoff*
+       *cutoff* value = distance cutoff
+
+Examples
+""""""""
+
+.. code-block:: LAMMPS
+
+   compute 1 all ave/sphere/atom
+
+   compute 1 all ave/sphere/atom cutoff 5.0
+   comm_modify cutoff 5.0
+
+Description
+"""""""""""
+
+Define a computation that calculates the local density and temperature
+for each atom and neighbors inside a spherical cutoff.
+
+The optional keyword *cutoff* defines the distance cutoff
+used when searching for neighbors. The default value is the cutoff
+specified by the pair style. If no pair style is defined, then a cutoff
+must be defined using this keyword. If the specified cutoff is larger than
+that of the pair_style plus neighbor skin (or no pair style is defined),
+the *comm_modify cutoff* option must also be set to match that of the
+*cutoff* keyword.
+
+The neighbor list needed to compute this quantity is constructed each
+time the calculation is performed (i.e. each time a snapshot of atoms
+is dumped).  Thus it can be inefficient to compute/dump this quantity
+too frequently.
+
+.. note::
+
+   If you have a bonded system, then the settings of
+   :doc:`special_bonds <special_bonds>` command can remove pairwise
+   interactions between atoms in the same bond, angle, or dihedral.  This
+   is the default setting for the :doc:`special_bonds <special_bonds>`
+   command, and means those pairwise interactions do not appear in the
+   neighbor list.  Because this fix uses the neighbor list, it also means
+   those pairs will not be included in the order parameter.  This
+   difficulty can be circumvented by writing a dump file, and using the
+   :doc:`rerun <rerun>` command to compute the order parameter for
+   snapshots in the dump file.  The rerun script can use a
+   :doc:`special_bonds <special_bonds>` command that includes all pairs in
+   the neighbor list.
+
+----------
+
+
+.. include:: accel_styles.rst
+
+
+----------
+
+Output info
+"""""""""""
+
+This compute calculates a per-atom array with two columns: density and temperature.
+
+These values can be accessed by any command that uses per-atom values
+from a compute as input.  See the :doc:`Howto output <Howto_output>` doc
+page for an overview of LAMMPS output options.
+
+Restrictions
+""""""""""""
+
+This compute is part of the EXTRA-COMPUTE package.  It is only enabled if
+LAMMPS was built with that package.  See the :doc:`Build package <Build_package>` page for more info.
+
+Related commands
+""""""""""""""""
+
+:doc:`comm_modify <comm_modify>`
+
+Default
+"""""""
+
+The option defaults are *cutoff* = pair style cutoff
+

doc/src/compute_bond_local.rst

@@ -13,7 +13,7 @@ Syntax
 * ID, group-ID are documented in :doc:`compute <compute>` command
 * bond/local = style name of this compute command
 * one or more values may be appended
-* value = *dist* or *engpot* or *force* or *fx* or *fy* or *fz* or *engvib* or *engrot* or *engtrans* or *omega* or *velvib* or *v_name*
+* value = *dist* or *dx* or *dy* or *dz* or *engpot* or *force* or *fx* or *fy* or *fz* or *engvib* or *engrot* or *engtrans* or *omega* or *velvib* or *v_name*
 
 .. parsed-literal::
 
@@ -21,6 +21,7 @@ Syntax
      *engpot* = bond potential energy
      *force* = bond force
 
+     *dx*,\ *dy*,\ *dz* = components of pairwise distance
      *fx*,\ *fy*,\ *fz* = components of bond force
      *engvib* = bond kinetic energy of vibration
      *engrot* = bond kinetic energy of rotation
@@ -63,6 +64,9 @@ whether the 2 atoms represent a simple diatomic molecule, or are part
 of some larger molecule.
 
 The value *dist* is the current length of the bond.
+The values *dx*, *dy*, and *dz* are the xyz components of the
+*distance* between the pair of atoms. This value is always the
+distance from the atom of lower to the one with the higher id.
 
 The value *engpot* is the potential energy for the bond,
 based on the current separation of the pair of atoms in the bond.

doc/src/compute_heat_flux.rst

@@ -89,13 +89,20 @@ included in the calculation.
 .. warning::
 
    The compute *heat/flux* has been reported to produce unphysical
-   values for angle, dihedral and improper contributions
+   values for angle, dihedral, improper and constraint force contributions
    when used with :doc:`compute stress/atom <compute_stress_atom>`,
-   as discussed in :ref:`(Surblys) <Surblys2>` and :ref:`(Boone) <Boone>`.
-   You are strongly advised to
+   as discussed in :ref:`(Surblys2019) <Surblys3>`, :ref:`(Boone) <Boone>`
+   and :ref:`(Surblys2021) <Surblys4>`. You are strongly advised to
    use :doc:`compute centroid/stress/atom <compute_stress_atom>`,
    which has been implemented specifically for such cases.
 
+.. warning::
+
+   Due to an implementation detail, the :math:`y` and :math:`z`
+   components of heat flux from :doc:`fix rigid <fix_rigid>`
+   contribution when computed via :doc:`compute stress/atom <compute_stress_atom>`
+   are highly unphysical and should not be used.
+
 The Green-Kubo formulas relate the ensemble average of the
 auto-correlation of the heat flux :math:`\mathbf{J}`
 to the thermal conductivity :math:`\kappa`:
@@ -232,10 +239,14 @@ none
 
 ----------
 
-.. _Surblys2:
+.. _Surblys3:
 
-**(Surblys)** Surblys, Matsubara, Kikugawa, Ohara, Phys Rev E, 99, 051301(R) (2019).
+**(Surblys2019)** Surblys, Matsubara, Kikugawa, Ohara, Phys Rev E, 99, 051301(R) (2019).
 
 .. _Boone:
 
 **(Boone)** Boone, Babaei, Wilmer, J Chem Theory Comput, 15, 5579--5587 (2019).
+
+.. _Surblys4:
+
+**(Surblys2021)** Surblys, Matsubara, Kikugawa, Ohara, J Appl Phys 130, 215104 (2021).