Merge pull request #3008 from akohlmey/next_patch_release

Update version strings for 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 +1,33 @@
+# GitHub action to build LAMMPS on Windows with Visual C++
+name: "Native Windows Compilation"
+
+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: Building LAMMPS via CMake
+      shell: bash
+      run: |
+        cmake -C cmake/presets/windows.cmake \
+              -S cmake -B build \
+              -D BUILD_SHARED_LIBS=on \
+              -D LAMMPS_EXCEPTIONS=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

.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

cmake/CMakeLists.txt

@@ -81,22 +81,40 @@ 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
@@ -281,6 +299,11 @@ else()
   target_include_directories(mpi_stubs PUBLIC $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
   if(BUILD_SHARED_LIBS)
     target_link_libraries(lammps PRIVATE mpi_stubs)
+    if(MSVC)
+      target_link_libraries(lmp PRIVATE mpi_stubs)
+      target_include_directories(lmp INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
+      target_compile_definitions(lmp INTERFACE $<INSTALL_INTERFACE:LAMMPS_LIB_NO_MPI>)
+    endif(MSVC)
     target_include_directories(lammps INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
     target_compile_definitions(lammps INTERFACE $<INSTALL_INTERFACE:LAMMPS_LIB_NO_MPI>)
   else()
@@ -468,9 +491,12 @@ foreach(HEADER cmath)
   endif(NOT FOUND_${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
@@ -591,15 +617,12 @@ foreach(PKG_WITH_INCL CORESHELL QEQ OPENMP DPD-SMOOTH KOKKOS OPT INTEL GPU)
 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 +631,7 @@ 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()
 
 ######################################################

cmake/CMakeSettings.json

@@ -0,0 +1,55 @@
+{
+    "configurations": [
+        {
+            "name": "x64-Debug-MSVC",
+            "generator": "Ninja",
+            "configurationType": "Debug",
+            "buildRoot": "${workspaceRoot}\\build\\${name}",
+            "installRoot": "${workspaceRoot}\\install\\${name}",
+            "cmakeCommandArgs": "-S ${workspaceRoot}\\cmake -C ${workspaceRoot}\\cmake\\presets\\windows.cmake",
+            "buildCommandArgs": "",
+            "ctestCommandArgs": "",
+            "inheritEnvironments": [ "msvc_x64_x64" ],
+            "variables": [
+                {
+                    "name": "BUILD_SHARED_LIBS",
+                    "value": "True",
+                    "type": "BOOL"
+                },
+                {
+                    "name": "BUILD_TOOLS",
+                    "value": "True",
+                    "type": "BOOL"
+                },
+                {
+                    "name": "LAMMPS_EXCEPTIONS",
+                    "value": "True",
+                    "type": "BOOL"
+                }
+            ]
+        },
+        {
+            "name": "x64-Debug-Clang",
+            "generator": "Ninja",
+            "configurationType": "Debug",
+            "buildRoot": "${workspaceRoot}\\build\\${name}",
+            "installRoot": "${workspaceRoot}\\install\\${name}",
+            "cmakeCommandArgs": "-S ${workspaceRoot}\\cmake -C ${workspaceRoot}\\cmake\\presets\\windows.cmake",
+            "buildCommandArgs": "",
+            "ctestCommandArgs": "",
+            "inheritEnvironments": [ "clang_cl_x64" ],
+            "variables": [
+                {
+                    "name": "BUILD_TOOLS",
+                    "value": "True",
+                    "type": "BOOL"
+                },
+                {
+                    "name": "LAMMPS_EXCEPTIONS",
+                    "value": "True",
+                    "type": "BOOL"
+                }
+            ]
+        }
+    ]
+}

cmake/Modules/GTest.cmake

@@ -7,8 +7,8 @@ else()
 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")
+set(GTEST_URL "https://github.com/google/googletest/archive/release-1.11.0.tar.gz" CACHE STRING "URL of googletest source")
+set(GTEST_MD5 "e8a8df240b6938bb6384155d4c37d937" CACHE STRING "MD5 sum for googletest source")
 mark_as_advanced(GTEST_URL)
 mark_as_advanced(GTEST_MD5)
 ExternalProject_Add(googletest

cmake/Modules/LAMMPSUtils.cmake

@@ -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/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)
@@ -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__)

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)

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

@@ -45,12 +45,12 @@ 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 ${N2P2_MPI_INCLUDE} -DMPICH_SKIP_MPICXX=1")
+      set(N2P2_PROJECT_OPTIONS "-I${N2P2_MPI_INCLUDE}")
       set(MPI_CXX_COMPILER ${CMAKE_CXX_COMPILER})
     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 ${N2P2_MPI_INCLUDE} -DMPICH_SKIP_MPICXX=1")
+      set(N2P2_PROJECT_OPTIONS "-I${N2P2_MPI_INCLUDE}")
       set(MPI_CXX_COMPILER ${CMAKE_CXX_COMPILER})
     endif()
   endif()
@@ -69,6 +69,12 @@ if(DOWNLOAD_N2P2)
   # 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

@@ -50,7 +50,7 @@ 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

@@ -12,6 +12,13 @@ if(DOWNLOAD_MSCG)
   mark_as_advanced(MSCG_URL)
   mark_as_advanced(MSCG_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 MSCG library due to a technical limitation")
+  endif()
+
   include(ExternalProject)
   ExternalProject_Add(mscg_build
     URL     ${MSCG_URL}

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/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/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/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" "27 October 2021" "2021-10-27"
 .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/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_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 +68,35 @@ 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>`_.
+
+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_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>`

doc/src/Developer.rst

@@ -11,10 +11,12 @@ of time and requests from the LAMMPS user community.
    :maxdepth: 1
 
    Developer_org
+   Developer_parallel
    Developer_flow
    Developer_write
    Developer_notes
    Developer_plugins
    Developer_unittest
    Classes
+   Developer_platform
    Developer_utils

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 +1,152 @@
+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:: 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
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -60,6 +62,9 @@ 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.
 
+Similarly the :cpp:func:`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()``
@@ -83,6 +88,9 @@ strings for compliance without conversion.
 .. doxygenfunction:: tnumeric
    :project: progguide
 
+.. doxygenfunction:: logical
+   :project: progguide
+
 
 String processing
 ^^^^^^^^^^^^^^^^^
@@ -95,6 +103,12 @@ and parsing files or arguments.
 .. doxygenfunction:: strdup
    :project: progguide
 
+.. doxygenfunction:: lowercase
+   :project: progguide
+
+.. doxygenfunction:: uppercase
+   :project: progguide
+
 .. doxygenfunction:: trim
    :project: progguide
 
@@ -137,21 +151,6 @@ 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
 ^^^^^^^^^^^^^^^^^^^^^^^^
 

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 */
    ...

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_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 +104,45 @@ 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 this.
+
 **After changes are made**
 
 After everything is done, add the files to the branch and commit them:
@@ -287,28 +305,32 @@ 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 +351,7 @@ 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 +373,11 @@ 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 +441,7 @@ 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 +455,8 @@ 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 +464,7 @@ 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 +476,14 @@ 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_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 +21,53 @@ 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 with every stable release;
+  updates are always "fast forward" merges from *develop*
+* **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>".)
 
+.. note::
+
+   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
+   also includes commits that have added and removed some large files
+   (mostly by accident).  If you do not need access to the entire commit
+   history, you can speed up the "cloning" process and reduce local disk
+   space requirements by using the *--depth* git command line flag thus
+   create a "shallow clone" of the repository that contains 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.
+
 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 +75,9 @@ 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 +100,7 @@ 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

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. (accepted 09/2021), DOI:10.1016/j.cpc.2021.108171 <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/Manual_version.rst

@@ -7,7 +7,7 @@ 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

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/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/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/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/fix.rst

@@ -166,6 +166,7 @@ page are followed by one or more of (g,i,k,o,t) to indicate which
 accelerated styles exist.
 
 * :doc:`accelerate/cos <fix_accelerate_cos>` - apply cosine-shaped acceleration to atoms
+* :doc:`acks2/reaxff <fix_acks2_reaxff>` - apply ACKS2 charge equilibration
 * :doc:`adapt <fix_adapt>` - change a simulation parameter over time
 * :doc:`adapt/fep <fix_adapt_fep>` - enhanced version of fix adapt
 * :doc:`addforce <fix_addforce>` - add a force to each atom
@@ -246,6 +247,7 @@ accelerated styles exist.
 * :doc:`manifoldforce <fix_manifoldforce>` - restrain atoms to a manifold during minimization
 * :doc:`mdi/engine <fix_mdi_engine>` - connect LAMMPS to external programs via the MolSSI Driver Interface (MDI)
 * :doc:`meso/move <fix_meso_move>` - move mesoscopic SPH/SDPD particles in a prescribed fashion
+* :doc:`mol/swap <fix_mol_swap>` - Monte Carlo atom type swapping with a molecule
 * :doc:`momentum <fix_momentum>` - zero the linear and/or angular momentum of a group of atoms
 * :doc:`momentum/chunk <fix_momentum>` - zero the linear and/or angular momentum of a chunk of atoms
 * :doc:`move <fix_move>` - move atoms in a prescribed fashion

doc/src/fix_acks2_reaxff.rst

@@ -0,0 +1,118 @@
+.. index:: fix acks2/reaxff
+.. index:: fix acks2/reaxff/kk
+
+fix acks2/reaxff command
+========================
+
+Accelerator Variants: *acks2/reaxff/kk*
+
+Syntax
+""""""
+
+.. parsed-literal::
+
+   fix ID group-ID acks2/reaxff Nevery cutlo cuthi tolerance params args
+
+* ID, group-ID are documented in :doc:`fix <fix>` command
+* acks2/reaxff = style name of this fix command
+* Nevery = perform ACKS2 every this many steps
+* cutlo,cuthi = lo and hi cutoff for Taper radius
+* tolerance = precision to which charges will be equilibrated
+* params = reaxff or a filename
+
+Examples
+""""""""
+
+.. code-block:: LAMMPS
+
+   fix 1 all acks2/reaxff 1 0.0 10.0 1.0e-6 reaxff
+   fix 1 all acks2/reaxff 1 0.0 10.0 1.0e-6 param.acks2
+
+Description
+"""""""""""
+
+Perform the atom-condensed Kohn-Sham DFT to second order (ACKS2) charge
+equilibration method as described in :ref:`(Verstraelen) <Verstraelen>`.
+ACKS2 impedes unphysical long-range charge transfer sometimes seen with
+QEq (e.g. for dissociation of molecules), at increased computational
+cost.  It is typically used in conjunction with the ReaxFF force field
+model as implemented in the :doc:`pair_style reaxff <pair_reaxff>`
+command, but it can be used with any potential in LAMMPS, so long as it
+defines and uses charges on each atom.  For more technical details about
+the charge equilibration performed by fix acks2/reaxff, see the
+:ref:`(O'Hearn) <O'Hearn>` paper.
+
+The ACKS2 method minimizes the electrostatic energy of the system by
+adjusting the partial charge on individual atoms based on interactions
+with their neighbors. It requires some parameters for each atom type.
+If the *params* setting above is the word "reaxff", then these are
+extracted from the :doc:`pair_style reaxff <pair_reaxff>` command and
+the ReaxFF force field file it reads in.  If a file name is specified
+for *params*\ , then the parameters are taken from the specified file
+and the file must contain one line for each atom type.  The latter form
+must be used when performing QeQ with a non-ReaxFF potential.  The lines
+should be formatted as follows:
+
+.. parsed-literal::
+
+   bond_softness
+   itype chi eta gamma bcut
+
+where the first line is the global parameter *bond_softness*. The
+remaining 1 to Ntypes lines include *itype*, the atom type from 1 to
+Ntypes, *chi*, the electronegativity in eV, *eta*, the self-Coulomb
+potential in eV, *gamma*, the valence orbital exponent, and *bcut*, the
+bond cutoff distance.  Note that these 4 quantities are also in the
+ReaxFF potential file, except that eta is defined here as twice the eta
+value in the ReaxFF file. Note that unlike the rest of LAMMPS, the units
+of this fix are hard-coded to be A, eV, and electronic charge.
+
+**Restart, fix_modify, output, run start/stop, minimize info:**
+
+No information about this fix is written to :doc:`binary restart files
+<restart>`.  No global scalar or vector or per-atom quantities are
+stored by this fix for access by various :doc:`output commands
+<Howto_output>`.  No parameter of this fix can be used with the
+*start/stop* keywords of the :doc:`run <run>` command.
+
+This fix is invoked during :doc:`energy minimization <minimize>`.
+
+----------
+
+.. include:: accel_styles.rst
+
+----------
+
+Restrictions
+""""""""""""
+
+This fix is part of the REAXFF package.  It is only enabled if LAMMPS
+was built with that package.  See the :doc:`Build package
+<Build_package>` doc page for more info.
+
+This fix does not correctly handle interactions involving multiple
+periodic images of the same atom. Hence, it should not be used for
+periodic cell dimensions less than 10 angstroms.
+
+This fix may be used in combination with :doc:`fix efield <fix_efield>`
+and will apply the external electric field during charge equilibration,
+but there may be only one fix efield instance used, it may only use a
+constant electric field, and the electric field vector may only have
+components in non-periodic directions.
+
+Related commands
+""""""""""""""""
+
+:doc:`pair_style reaxff <pair_reaxff>`, :doc:`fix qeq/reaxff <fix_qeq_reaxff>`
+
+**Default:** none
+
+----------
+
+.. _O'Hearn:
+
+**(O'Hearn)** O'Hearn, Alperen, Aktulga, SIAM J. Sci. Comput., 42(1), C1-C22 (2020).
+
+.. _Verstraelen:
+
+**(Verstraelen)** Verstraelen, Ayers, Speybroeck, Waroquier, J. Chem. Phys. 138, 074108 (2013).

doc/src/fix_atom_swap.rst

@@ -73,51 +73,51 @@ is the same after the swap as it was before the swap, even though the
 atom masses have changed.
 
 The *semi-grand* keyword can be set to *yes* to switch to the
-semi-grand canonical ensemble as discussed in :ref:`(Sadigh) <Sadigh>`. This
-means that the total number of each particle type does not need to be
-conserved. The default is *no*, which means that the only kind of swap
-allowed exchanges an atom of one type with an atom of a different
-given type. In other words, the relative mole fractions of the swapped
-atoms remains constant. Whereas in the semi-grand canonical ensemble,
-the composition of the system can change. Note that when using
-*semi-grand*, atoms in the fix group whose type is not listed
-in the *types* keyword are ineligible for attempted
-conversion. An attempt is made to switch
-the selected atom (if eligible) to one of the other listed types
-with equal probability. Acceptance of each attempt depends upon the Metropolis criterion.
+semi-grand canonical ensemble as discussed in :ref:`(Sadigh)
+<Sadigh>`. This means that the total number of each particle type does
+not need to be conserved. The default is *no*, which means that the
+only kind of swap allowed exchanges an atom of one type with an atom
+of a different given type. In other words, the relative mole fractions
+of the swapped atoms remains constant. Whereas in the semi-grand
+canonical ensemble, the composition of the system can change. Note
+that when using *semi-grand*, atoms in the fix group whose type is not
+listed in the *types* keyword are ineligible for attempted
+conversion. An attempt is made to switch the selected atom (if
+eligible) to one of the other listed types with equal
+probability. Acceptance of each attempt depends upon the Metropolis
+criterion.
 
-The *mu* keyword allows users to specify chemical
-potentials. This is required and allowed only when using *semi-grand*\ .
-All chemical potentials are absolute, so there is one for
-each swap type listed following the *types* keyword.
-In semi-grand canonical ensemble simulations the chemical composition
-of the system is controlled by the difference in these values. So
-shifting all values by a constant amount will have no effect
-on the simulation.
+The *mu* keyword allows users to specify chemical potentials. This is
+required and allowed only when using *semi-grand*\ .  All chemical
+potentials are absolute, so there is one for each swap type listed
+following the *types* keyword.  In semi-grand canonical ensemble
+simulations the chemical composition of the system is controlled by
+the difference in these values. So shifting all values by a constant
+amount will have no effect on the simulation.
 
 This command may optionally use the *region* keyword to define swap
 volume.  The specified region must have been previously defined with a
-:doc:`region <region>` command.  It must be defined with side = *in*\ .
-Swap attempts occur only between atoms that are both within the
+:doc:`region <region>` command.  It must be defined with side = *in*\
+.  Swap attempts occur only between atoms that are both within the
 specified region. Swaps are not otherwise attempted.
 
 You should ensure you do not swap atoms belonging to a molecule, or
-LAMMPS will soon generate an error when it tries to find those atoms.
-LAMMPS will warn you if any of the atoms eligible for swapping have a
-non-zero molecule ID, but does not check for this at the time of
+LAMMPS will eventually generate an error when it tries to find those
+atoms.  LAMMPS will warn you if any of the atoms eligible for swapping
+have a non-zero molecule ID, but does not check for this at the time of
 swapping.
 
 If not using *semi-grand* this fix checks to ensure all atoms of the
 given types have the same atomic charge. LAMMPS does not enforce this
-in general, but it is needed for this fix to simplify the
-swapping procedure. Successful swaps will swap the atom type and charge
-of the swapped atoms. Conversely, when using *semi-grand*, it is assumed that all the atom
-types involved in switches have the same charge. Otherwise, charge
-would not be conserved. As a consequence, no checks on atomic charges are
-performed, and successful switches update the atom type but not the
-atom charge. While it is possible to use *semi-grand* with groups of
-atoms that have different charges, these charges will not be changed when the
-atom types change.
+in general, but it is needed for this fix to simplify the swapping
+procedure. Successful swaps will swap the atom type and charge of the
+swapped atoms. Conversely, when using *semi-grand*, it is assumed that
+all the atom types involved in switches have the same
+charge. Otherwise, charge would not be conserved. As a consequence, no
+checks on atomic charges are performed, and successful switches update
+the atom type but not the atom charge. While it is possible to use
+*semi-grand* with groups of atoms that have different charges, these
+charges will not be changed when the atom types change.
 
 Since this fix computes total potential energies before and after
 proposed swaps, so even complicated potential energy calculations are
@@ -133,23 +133,24 @@ OK, including the following:
 Some fixes have an associated potential energy. Examples of such fixes
 include: :doc:`efield <fix_efield>`, :doc:`gravity <fix_gravity>`,
 :doc:`addforce <fix_addforce>`, :doc:`langevin <fix_langevin>`,
-:doc:`restrain <fix_restrain>`, :doc:`temp/berendsen <fix_temp_berendsen>`,
-:doc:`temp/rescale <fix_temp_rescale>`, and :doc:`wall fixes <fix_wall>`.
-For that energy to be included in the total potential energy of the
-system (the quantity used when performing GCMC moves),
-you MUST enable the :doc:`fix_modify <fix_modify>` *energy* option for
-that fix.  The doc pages for individual :doc:`fix <fix>` commands
-specify if this should be done.
+:doc:`restrain <fix_restrain>`, :doc:`temp/berendsen
+<fix_temp_berendsen>`, :doc:`temp/rescale <fix_temp_rescale>`, and
+:doc:`wall fixes <fix_wall>`.  For that energy to be included in the
+total potential energy of the system (the quantity used when
+performing GCMC moves), you MUST enable the :doc:`fix_modify
+<fix_modify>` *energy* option for that fix.  The doc pages for
+individual :doc:`fix <fix>` commands specify if this should be done.
 
 Restart, fix_modify, output, run start/stop, minimize info
 """""""""""""""""""""""""""""""""""""""""""""""""""""""""""
 
-This fix writes the state of the fix to :doc:`binary restart files <restart>`.  This includes information about the random
-number generator seed, the next timestep for MC exchanges, the number
-of exchange attempts and successes etc.  See
-the :doc:`read_restart <read_restart>` command for info on how to
-re-specify a fix in an input script that reads a restart file, so that
-the operation of the fix continues in an uninterrupted fashion.
+This fix writes the state of the fix to :doc:`binary restart files
+<restart>`.  This includes information about the random number
+generator seed, the next timestep for MC exchanges, the number of
+exchange attempts and successes etc.  See the :doc:`read_restart
+<read_restart>` command for info on how to re-specify a fix in an
+input script that reads a restart file, so that the operation of the
+fix continues in an uninterrupted fashion.
 
 .. note::
 
@@ -165,12 +166,13 @@ by various :doc:`output commands <Howto_output>`.  The vector values are
 the following global cumulative quantities:
 
 * 1 = swap attempts
-* 2 = swap successes
+* 2 = swap accepts
 
 The vector values calculated by this fix are "extensive".
 
 No parameter of this fix can be used with the *start/stop* keywords of
-the :doc:`run <run>` command.  This fix is not invoked during :doc:`energy minimization <minimize>`.
+the :doc:`run <run>` command.  This fix is not invoked during
+:doc:`energy minimization <minimize>`.
 
 Restrictions
 """"""""""""
@@ -184,7 +186,8 @@ Related commands
 
 :doc:`fix nvt <fix_nh>`, :doc:`neighbor <neighbor>`,
 :doc:`fix deposit <fix_deposit>`, :doc:`fix evaporate <fix_evaporate>`,
-:doc:`delete_atoms <delete_atoms>`, :doc:`fix gcmc <fix_gcmc>`
+:doc:`delete_atoms <delete_atoms>`, :doc:`fix gcmc <fix_gcmc>`,
+:doc:`fix mol/swap <fix_mol_swap>`
 
 Default
 """""""

doc/src/fix_langevin.rst

@@ -138,16 +138,18 @@ temperature with optional time-dependence as well.
 
 Like other fixes that perform thermostatting, this fix can be used
 with :doc:`compute commands <compute>` that remove a "bias" from the
-atom velocities.  E.g. removing the center-of-mass velocity from a
-group of atoms or removing the x-component of velocity from the
-calculation.  This is not done by default, but only if the
-:doc:`fix_modify <fix_modify>` command is used to assign a temperature
-compute to this fix that includes such a bias term.  See the doc pages
-for individual :doc:`compute commands <compute>` to determine which ones
-include a bias.  In this case, the thermostat works in the following
-manner: bias is removed from each atom, thermostatting is performed on
-the remaining thermal degrees of freedom, and the bias is added back
-in.
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 The *damp* parameter is specified in time units and determines how
 rapidly the temperature is relaxed.  For example, a value of 100.0 means
@@ -183,7 +185,8 @@ omega (which is derived from the angular momentum in the case of
 aspherical particles).
 
 The rotational temperature of the particles can be monitored by the
-:doc:`compute temp/sphere <compute_temp_sphere>` and :doc:`compute temp/asphere <compute_temp_asphere>` commands with their rotate
+:doc:`compute temp/sphere <compute_temp_sphere>` and :doc:`compute
+temp/asphere <compute_temp_asphere>` commands with their rotate
 options.
 
 For the *omega* keyword there is also a scale factor of

doc/src/fix_langevin_drude.rst

@@ -167,17 +167,20 @@ functions, and include :doc:`thermo_style <thermo_style>` command
 keywords for the simulation box parameters and timestep and elapsed
 time.  Thus it is easy to specify a time-dependent temperature.
 
-Like other fixes that perform thermostatting, this fix can be used with
-:doc:`compute commands <compute>` that remove a "bias" from the atom
-velocities.  E.g. removing the center-of-mass velocity from a group of
-atoms.  This is not done by default, but only if the
-:doc:`fix_modify <fix_modify>` command is used to assign a temperature
-compute to this fix that includes such a bias term.  See the doc pages
-for individual :doc:`compute commands <compute>` to determine which ones
-include a bias.  In this case, the thermostat works in the following
-manner: bias is removed from each atom, thermostatting is performed on
-the remaining thermal degrees of freedom, and the bias is added back
-in.  NOTE: this feature has not been tested.
+Like other fixes that perform thermostatting, this fix can be used
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 Note: The temperature thermostatting the core-Drude particle pairs
 should be chosen low enough, so as to mimic as closely as possible the

doc/src/fix_mol_swap.rst

@@ -0,0 +1,170 @@
+.. index:: fix mol/swap
+
+fix mol/swap command
+=====================
+
+Syntax
+""""""
+
+.. parsed-literal::
+
+   fix ID group-ID mol/swap N X itype jtype seed T keyword value ...
+
+* ID, group-ID are documented in :doc:`fix <fix>` command
+* atom/swap = style name of this fix command
+* N = invoke this fix every N steps
+* X = number of swaps to attempt every N steps
+* itype,jtype = two atom types to swap with each other
+* seed = random # seed (positive integer)
+* T = scaling temperature of the MC swaps (temperature units)
+* zero or more keyword/value pairs may be appended to args
+* keyword = *ke*
+
+  .. parsed-literal::
+
+       *ke* value = *no* or *yes*
+         *no* = no conservation of kinetic energy after atom swaps
+         *yes* = kinetic energy is conserved after atom swaps
+
+Examples
+""""""""
+
+.. code-block:: LAMMPS
+
+   fix 2 all mol/swap 100 1 2 3 29494 300.0 ke no
+   fix mySwap fluid mol/swap 500 10 1 2 482798 1.0
+
+Description
+"""""""""""
+
+This fix performs Monte Carlo swaps of two specified atom types within
+a randomly selected molecule.  Two possible use cases are as follows.
+
+First, consider a mixture of some molecules with atoms of itype and
+other molecules with atoms of jtype.  The fix will select a random
+molecule and attempt to swap all the itype atoms to jtype for the
+first kind of molecule, or all the jtype atoms to itype for the second
+kind.  Because the swap will only take place if it is energetically
+favorable, the fix can be used to determine the miscibility of 2
+different kinds of molecules much more quickly than just dynamics
+would do it.
+
+Second, consider diblock co-polymers with two types of monomers itype
+and jtype.  The fix will select a random molecule and attempt to do a
+itype <--> jtype swap of all those monomers within the molecule.  Thus
+the fix can be used to find the energetically favorable fractions of
+two flavors of diblock co-polymers.
+
+Intra-molecular swaps of atom types are attempted every N timesteps.  On
+that timestep, X swaps are attempted.  For each attempt a single
+molecule ID is randomly selected.  The range of possible molecule IDs
+from loID to hiID is pre-computed before each run begins.  The
+loID/hiID is set for the molecule with the smallest/largest ID which
+has any itype or jtype atoms in it.  Note that if you define a system
+with many molecule IDs between loID and hiID which have no itype or
+jtype atoms, then the fix will be inefficient at performing swaps.
+Also note that if atoms with molecule ID = 0 exist, they are not
+considered molecules by this fix; they are assumed to be solvent atoms
+or molecules.
+
+Candidate atoms for swapping must also be in the fix group.  Atoms
+within the selected molecule which are not itype or jtype are ignored.
+
+When an atom is swapped from itype to jtype (or vice versa), if
+charges are defined, the charge values for itype versus jtype atoms
+are also swapped.  This requires that all itype atoms in the system
+have the same charge value.  Likewise all jtype atoms in the system
+must have the same charge value.  If this is not the case, LAMMPS
+issues a warning that it cannot swap charge values.
+
+If the *ke* keyword is set to yes, which is the default, and the
+masses of itype and jtype atoms are different, then when a swap
+occurs, the velocity of the swapped atom is rescaled by the sqrt of
+the mass ratio, so as to conserve the kinetic energy of the atom.
+
+----------
+
+The potential energy of the entire system is computed before and after
+each swap is performed within a single molecule.  The specified
+temperature T is used in the Metropolis criterion to accept or reject
+the attempted swap.  If the swap is rejected all swapped values are
+reversed.
+
+The potential energy calculations can include systems and models with
+the following features:
+
+* manybody pair styles, including EAM
+* hybrid pair styles
+* long-range electrostatics (kspace)
+* triclinic systems
+* potential energy contributions from other fixes
+
+For the last bullet point, fixes can have an associated potential
+energy. Examples of such fixes include: :doc:`efield <fix_efield>`,
+:doc:`gravity <fix_gravity>`, :doc:`addforce <fix_addforce>`,
+:doc:`langevin <fix_langevin>`, :doc:`restrain <fix_restrain>`,
+:doc:`temp/berendsen <fix_temp_berendsen>`, :doc:`temp/rescale
+<fix_temp_rescale>`, and :doc:`wall fixes <fix_wall>`.  For that
+energy to be included in the total potential energy of the system (the
+quantity used for the swap accept/reject decision), you MUST enable
+the :doc:`fix_modify <fix_modify>` *energy* option for that fix.  The
+doc pages for individual :doc:`fix <fix>` commands specify if this
+should be done.
+
+.. note::
+
+  One comment on computational efficiency.  If the cutoff lengths
+  defined for the pair style are different for itype versus jtype
+  atoms (for any of their interactions with any other atom type), then
+  a new neighbor list needs to be generated for every attempted swap.
+  This is potentially expensive if N is small or X is large.
+
+Restart, fix_modify, output, run start/stop, minimize info
+"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""
+
+This fix writes the state of the fix to :doc:`binary restart files
+<restart>`.  This includes information about the random number
+generator seed, the next timestep for MC exchanges, the number of
+exchange attempts and successes etc.  See the :doc:`read_restart
+<read_restart>` command for info on how to re-specify a fix in an
+input script that reads a restart file, so that the operation of the
+fix continues in an uninterrupted fashion.
+
+.. note::
+
+   For this to work correctly, the timestep must **not** be changed
+   after reading the restart with :doc:`reset_timestep <reset_timestep>`.
+   The fix will try to detect it and stop with an error.
+
+None of the :doc:`fix_modify <fix_modify>` options are relevant to this
+fix.
+
+This fix computes a global vector of length 2, which can be accessed
+by various :doc:`output commands <Howto_output>`.  The vector values are
+the following global cumulative quantities:
+
+* 1 = swap attempts
+* 2 = swap accepts
+
+The vector values calculated by this fix are "extensive".
+
+No parameter of this fix can be used with the *start/stop* keywords of
+the :doc:`run <run>` command.  This fix is not invoked during
+:doc:`energy minimization <minimize>`.
+
+Restrictions
+""""""""""""
+
+This fix is part of the MC package.  It is only enabled if LAMMPS was
+built with that package.  See the :doc:`Build package <Build_package>`
+doc page for more info.
+
+Related commands
+""""""""""""""""
+
+:doc:`fix atom/swap <fix_atom_swap>`, :doc:`fix gcmc <fix_gcmc>`
+
+Default
+"""""""
+
+The option default is ke = yes.

doc/src/fix_nh.rst

@@ -486,19 +486,20 @@ temperature or pressure during thermodynamic output via the
 compute-ID.  It also means that changing attributes of *thermo_temp*
 or *thermo_press* will have no effect on this fix.
 
-Like other fixes that perform thermostatting, fix nvt and fix npt can
-be used with :doc:`compute commands <compute>` that calculate a
-temperature after removing a "bias" from the atom velocities.
-E.g. removing the center-of-mass velocity from a group of atoms or
-only calculating temperature on the x-component of velocity or only
-calculating temperature for atoms in a geometric region.  This is not
-done by default, but only if the :doc:`fix_modify <fix_modify>` command
-is used to assign a temperature compute to this fix that includes such
-a bias term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+Like other fixes that perform thermostatting, this fix can be used
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_npt_asphere.rst

@@ -48,8 +48,9 @@ can also have a bias velocity removed from them before thermostatting
 takes place; see the description below.
 
 Additional parameters affecting the thermostat and barostat are
-specified by keywords and values documented with the :doc:`fix npt <fix_nh>` command.  See, for example, discussion of the *temp*,
-*iso*, *aniso*, and *dilate* keywords.
+specified by keywords and values documented with the :doc:`fix npt
+<fix_nh>` command.  See, for example, discussion of the *temp*, *iso*,
+*aniso*, and *dilate* keywords.
 
 The particles in the fix group are the only ones whose velocities and
 positions are updated by the velocity/position update portion of the
@@ -89,18 +90,19 @@ It also means that changing attributes of *thermo_temp* or
 *thermo_press* will have no effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_npt_body.rst

@@ -87,18 +87,19 @@ It also means that changing attributes of *thermo_temp* or
 *thermo_press* will have no effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_npt_cauchy.rst

@@ -400,19 +400,20 @@ temperature or pressure during thermodynamic output via the
 compute-ID.  It also means that changing attributes of *thermo_temp*
 or *thermo_press* will have no effect on this fix.
 
-Like other fixes that perform thermostatting, fix npt/cauchy can
-be used with :doc:`compute commands <compute>` that calculate a
-temperature after removing a "bias" from the atom velocities.
-E.g. removing the center-of-mass velocity from a group of atoms or
-only calculating temperature on the x-component of velocity or only
-calculating temperature for atoms in a geometric region.  This is not
-done by default, but only if the :doc:`fix_modify <fix_modify>` command
-is used to assign a temperature compute to this fix that includes such
-a bias term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+Like other fixes that perform thermostatting, this fix can be used
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_npt_sphere.rst

@@ -103,18 +103,19 @@ appropriate compute-ID.  It also means that changing attributes of
 *thermo_temp* or *thermo_press* will have no effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_nvt_asphere.rst

@@ -72,18 +72,19 @@ It also means that changing attributes of *thermo_temp* will have no
 effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_nvt_body.rst

@@ -69,18 +69,19 @@ It also means that changing attributes of *thermo_temp* will have no
 effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_nvt_sllod.rst

@@ -37,15 +37,16 @@ trajectory consistent with the canonical ensemble.
 
 This thermostat is used for a simulation box that is changing size
 and/or shape, for example in a non-equilibrium MD (NEMD) simulation.
-The size/shape change is induced by use of the :doc:`fix deform <fix_deform>` command, so each point in the simulation box
-can be thought of as having a "streaming" velocity.  This
-position-dependent streaming velocity is subtracted from each atom's
-actual velocity to yield a thermal velocity which is used for
-temperature computation and thermostatting.  For example, if the box
-is being sheared in x, relative to y, then points at the bottom of the
-box (low y) have a small x velocity, while points at the top of the
-box (hi y) have a large x velocity.  These velocities do not
-contribute to the thermal "temperature" of the atom.
+The size/shape change is induced by use of the :doc:`fix deform
+<fix_deform>` command, so each point in the simulation box can be
+thought of as having a "streaming" velocity.  This position-dependent
+streaming velocity is subtracted from each atom's actual velocity to
+yield a thermal velocity which is used for temperature computation and
+thermostatting.  For example, if the box is being sheared in x,
+relative to y, then points at the bottom of the box (low y) have a
+small x velocity, while points at the top of the box (hi y) have a
+large x velocity.  These velocities do not contribute to the thermal
+"temperature" of the atom.
 
 .. note::
 
@@ -60,13 +61,15 @@ contribute to the thermal "temperature" of the atom.
    consistent.
 
 The SLLOD equations of motion, originally proposed by Hoover and Ladd
-(see :ref:`(Evans and Morriss) <Evans3>`), were proven to be equivalent to
-Newton's equations of motion for shear flow by :ref:`(Evans and Morriss) <Evans3>`. They were later shown to generate the desired
-velocity gradient and the correct production of work by stresses for
-all forms of homogeneous flow by :ref:`(Daivis and Todd) <Daivis>`.  As
-implemented in LAMMPS, they are coupled to a Nose/Hoover chain
-thermostat in a velocity Verlet formulation, closely following the
-implementation used for the :doc:`fix nvt <fix_nh>` command.
+(see :ref:`(Evans and Morriss) <Evans3>`), were proven to be
+equivalent to Newton's equations of motion for shear flow by
+:ref:`(Evans and Morriss) <Evans3>`. They were later shown to generate
+the desired velocity gradient and the correct production of work by
+stresses for all forms of homogeneous flow by :ref:`(Daivis and Todd)
+<Daivis>`.  As implemented in LAMMPS, they are coupled to a
+Nose/Hoover chain thermostat in a velocity Verlet formulation, closely
+following the implementation used for the :doc:`fix nvt <fix_nh>`
+command.
 
 .. note::
 
@@ -94,27 +97,28 @@ underscore + "temp", and the group for the new compute is the same as
 the fix group.
 
 Note that this is NOT the compute used by thermodynamic output (see
-the :doc:`thermo_style <thermo_style>` command) with ID = *thermo_temp*.
-This means you can change the attributes of this fix's temperature
-(e.g. its degrees-of-freedom) via the
-:doc:`compute_modify <compute_modify>` command or print this temperature
-during thermodynamic output via the :doc:`thermo_style custom <thermo_style>` command using the appropriate compute-ID.
-It also means that changing attributes of *thermo_temp* will have no
-effect on this fix.
+the :doc:`thermo_style <thermo_style>` command) with ID =
+*thermo_temp*.  This means you can change the attributes of this fix's
+temperature (e.g. its degrees-of-freedom) via the :doc:`compute_modify
+<compute_modify>` command or print this temperature during
+thermodynamic output via the :doc:`thermo_style custom <thermo_style>`
+command using the appropriate compute-ID.  It also means that changing
+attributes of *thermo_temp* will have no effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_nvt_sphere.rst

@@ -86,18 +86,19 @@ It also means that changing attributes of *thermo_temp* will have no
 effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_qeq.rst

@@ -230,7 +230,10 @@ These fixes are part of the QEQ package.  They are only enabled if
 LAMMPS was built with that package.  See the :doc:`Build package
 <Build_package>` page for more info.
 
-The qeq fixes are not compatible with the GPU and USER-INTEL packages.
+These qeq fixes are not compatible with the GPU and USER-INTEL packages.
+
+These qeq fixes will ignore electric field contributions from
+:doc:`fix efield <fix_efield>`.
 
 Related commands
 """"""""""""""""

doc/src/fix_qeq_reaxff.rst

@@ -116,6 +116,12 @@ This fix does not correctly handle interactions involving multiple
 periodic images of the same atom.  Hence, it should not be used for
 periodic cell dimensions less than 10 angstroms.
 
+This fix may be used in combination with :doc:`fix efield <fix_efield>`
+and will apply the external electric field during charge equilibration,
+but there may be only one fix efield instance used, it may only use a
+constant electric field, and the electric field vector may only have
+components in non-periodic directions.
+
 Related commands
 """"""""""""""""
 

doc/src/fix_reaxff_species.rst

@@ -56,6 +56,17 @@ number of molecules of each species.  In this context, "species" means
 a unique molecule.  The chemical formula of each species is given in
 the first line.
 
+.. warning::
+
+   In order to compute averaged data, it is required that there are no
+   neighbor list rebuilds between the *Nfreq* steps. For that reason, fix
+   *reaxff/species* may change your neighbor list settings.  There will
+   be a warning message showing the new settings. Having an *Nfreq*
+   setting that is larger than what is required for correct computation
+   of the ReaxFF force field interactions can thus lead to incorrect
+   results.  For typical ReaxFF calculations a value of 100 is already
+   quite large.
+
 If the filename ends with ".gz", the output file is written in gzipped
 format.  A gzipped dump file will be about 3x smaller than the text version,
 but will also take longer to write.

doc/src/fix_saed_vtk.rst

@@ -28,7 +28,6 @@ Syntax
          Nstart = start averaging on this timestep
        *file* arg = filename
          filename = name of file to output time averages to
-       *overwrite* arg = none = overwrite output file with only latest output
 
 Examples
 """"""""
@@ -161,10 +160,6 @@ the *file* keyword and this string is appended with _N.vtk where N is
 an index (0,1,2...) to account for situations with multiple diffraction
 intensity outputs.
 
-The *overwrite* keyword will continuously overwrite the output file
-with the latest output, so that it only contains one timestep worth of
-output.  This option can only be used with the *ave running* setting.
-
 Restart, fix_modify, output, run start/stop, minimize info
 """""""""""""""""""""""""""""""""""""""""""""""""""""""""""
 

doc/src/fix_setforce.rst

@@ -89,26 +89,13 @@ precession vectors instead of the forces.
 
 ----------
 
-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.
+.. include:: accel_styles.rst
 
-The region keyword is also supported by Kokkos, but a Kokkos-enabled
-region must be used. See the region :doc:`region <region>` command for
-more information.
+.. note::
 
-These accelerated styles are part of the r Kokkos package.  They are
-only enabled if LAMMPS was built with that package.  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.
+  The region keyword is supported by Kokkos, but a Kokkos-enabled
+  region must be used. See the region :doc:`region <region>` command for
+  more information.
 
 ----------
 

doc/src/fix_temp_berendsen.rst

@@ -102,18 +102,19 @@ It also means that changing attributes of *thermo_temp* will have no
 effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_temp_csvr.rst

@@ -110,28 +110,29 @@ during thermodynamic output via the :doc:`thermo_style custom <thermo_style>` co
 It also means that changing attributes of *thermo_temp* will have no
 effect on this fix.
 
-Like other fixes that perform thermostatting, these fixes can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is used
-to assign a temperature compute to this fix that includes such a bias
-term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal degrees of freedom, and the bias is added back in.
+Like other fixes that perform thermostatting, this fix can be used
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 An important feature of these thermostats is that they have an
-associated effective energy that is a constant of motion.
-The effective energy is the total energy (kinetic + potential) plus
-the accumulated kinetic energy changes due to the thermostat. The
-latter quantity is the global scalar computed by these fixes. This
-feature is useful to check the integration of the equations of motion
-against discretization errors. In other words, the conservation of
-the effective energy can be used to choose an appropriate integration
+associated effective energy that is a constant of motion.  The
+effective energy is the total energy (kinetic + potential) plus the
+accumulated kinetic energy changes due to the thermostat. The latter
+quantity is the global scalar computed by these fixes. This feature is
+useful to check the integration of the equations of motion against
+discretization errors. In other words, the conservation of the
+effective energy can be used to choose an appropriate integration
 :doc:`timestep <timestep>`. This is similar to the usual paradigm of
 checking the conservation of the total energy in the microcanonical
 ensemble.

doc/src/fix_temp_rescale.rst

@@ -109,19 +109,19 @@ command using the appropriate compute-ID.  It also means that changing
 attributes of *thermo_temp* will have no effect on this fix.
 
 Like other fixes that perform thermostatting, this fix can be used
-with :doc:`compute commands <compute>` that calculate a temperature
-after removing a "bias" from the atom velocities.  E.g. removing the
-center-of-mass velocity from a group of atoms or only calculating
-temperature on the x-component of velocity or only calculating
-temperature for atoms in a geometric region.  This is not done by
-default, but only if the :doc:`fix_modify <fix_modify>` command is
-used to assign a temperature compute to this fix that includes such a
-bias term.  See the doc pages for individual :doc:`compute commands
-<compute>` to determine which ones include a bias.  In this case, the
-thermostat works in the following manner: the current temperature is
-calculated taking the bias into account, bias is removed from each
-atom, thermostatting is performed on the remaining thermal degrees of
-freedom, and the bias is added back in.
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 ----------
 

doc/src/fix_tgnh_drude.rst

@@ -187,26 +187,32 @@ barostatting.
 
 ----------
 
-Like other fixes that perform thermostatting, these fixes can
-be used with :doc:`compute commands <compute>` that calculate a
-temperature after removing a "bias" from the atom velocities.
-This is not done by default, but only if the :doc:`fix_modify <fix_modify>` command
-is used to assign a temperature compute to this fix that includes such
-a bias term.  See the doc pages for individual :doc:`compute commands <compute>` to determine which ones include a bias.  In
-this case, the thermostat works in the following manner: the current
-temperature is calculated taking the bias into account, bias is
-removed from each atom, thermostatting is performed on the remaining
-thermal DOF, and the bias is added back in.
+Like other fixes that perform thermostatting, this fix can be used
+with :doc:`compute commands <compute>` that remove a "bias" from the
+atom velocities.  E.g. to apply the thermostat only to atoms within a
+spatial :doc:`region <region>`, or to remove the center-of-mass
+velocity from a group of atoms, or to remove the x-component of
+velocity from the calculation.
+
+This is not done by default, but only if the :doc:`fix_modify
+<fix_modify>` command is used to assign a temperature compute to this
+fix that includes such a bias term.  See the doc pages for individual
+:doc:`compute temp commands <compute>` to determine which ones include
+a bias.  In this case, the thermostat works in the following manner:
+bias is removed from each atom, thermostatting is performed on the
+remaining thermal degrees of freedom, and the bias is added back in.
 
 .. note::
 
-   However, not all temperature compute commands are valid to be used with these fixes.
-   Precisely, only temperature compute that does not modify the DOF of the group can be used.
-   E.g. :doc:`compute temp/ramp <compute_temp_ramp>` and :doc:`compute viscosity/cos <compute_viscosity_cos>`
-   compute the kinetic energy after remove a velocity gradient without affecting the DOF of the group,
-   then they can be invoked in this way.
-   In contrast, :doc:`compute temp/partial <compute_temp_partial>` may remove the DOF at one or more dimensions,
-   therefore it cannot be used with these fixes.
+   However, not all temperature compute commands are valid to be used
+   with these fixes.  Precisely, only temperature compute that does
+   not modify the DOF of the group can be used.  E.g. :doc:`compute
+   temp/ramp <compute_temp_ramp>` and :doc:`compute viscosity/cos
+   <compute_viscosity_cos>` compute the kinetic energy after remove a
+   velocity gradient without affecting the DOF of the group, then they
+   can be invoked in this way.  In contrast, :doc:`compute
+   temp/partial <compute_temp_partial>` may remove the DOF at one or
+   more dimensions, therefore it cannot be used with these fixes.
 
 ----------
 

doc/src/group.rst

@@ -38,7 +38,7 @@ Syntax
        *intersect* args = two or more group IDs
        *dynamic* args = parent-ID keyword value ...
          one or more keyword/value pairs may be appended
-         keyword = *region* or *var* or *every*
+         keyword = *region* or *var* or *property* or *every*
            *region* value = region-ID
            *var* value = name of variable
            *property* value = name of custom integer or floating point vector

doc/src/improper_harmonic.rst

@@ -64,25 +64,7 @@ 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 the :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+.. include:: accel_styles.rst
 
 ----------
 

doc/src/kspace_style.rst

@@ -414,33 +414,26 @@ relative RMS error.
 
 ----------
 
-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.
+.. include:: accel_styles.rst
 
-More specifically, the *pppm/gpu* style performs charge assignment and
-force interpolation calculations on the GPU.  These processes are
-performed either in single or double precision, depending on whether
-the -DFFT_SINGLE setting was specified in your low-level Makefile, as
-discussed above.  The FFTs themselves are still calculated on the CPU.
-If *pppm/gpu* is used with a GPU-enabled pair style, part of the PPPM
-calculation can be performed concurrently on the GPU while other
-calculations for non-bonded and bonded force calculation are performed
-on the CPU.
+.. note::
 
-The *pppm/kk* style performs charge assignment and force interpolation
-calculations, along with the FFTs themselves, on the GPU or (optionally) threaded
-on the CPU when using OpenMP and FFTW3.
+  For the GPU package, the *pppm/gpu* style performs charge assignment
+  and force interpolation calculations on the GPU.  These processes
+  are performed either in single or double precision, depending on
+  whether the -DFFT_SINGLE setting was specified in your low-level
+  Makefile, as discussed above.  The FFTs themselves are still
+  calculated on the CPU.  If *pppm/gpu* is used with a GPU-enabled
+  pair style, part of the PPPM calculation can be performed
+  concurrently on the GPU while other calculations for non-bonded and
+  bonded force calculation are performed on the CPU.
 
-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.
+.. note::
 
-See the :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+  For the KOKKOS package, the *pppm/kk* style performs charge
+  assignment and force interpolation calculations, along with the FFTs
+  themselves, on the GPU or (optionally) threaded on the CPU when
+  using OpenMP and FFTW3.
 
 ----------
 

doc/src/package.rst

@@ -166,7 +166,7 @@ intel", or "package omp" command with default settings.
    set, either to default values or to specified settings.  I.e. settings
    from previous invocations do not persist across multiple invocations.
 
-See the :doc:`Speed packages <Speed_packages>` page for more details
+See the :doc:`Accelerator packages <Speed_packages>` page for more details
 about using the various accelerator packages for speeding up LAMMPS
 simulations.
 

doc/src/pair_agni.rst

@@ -67,21 +67,7 @@ and input files are provided in the examples/PACKAGES/agni directory.
 
 ----------
 
-Styles with *omp* suffix is 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 style takes
-the same arguments and should produce the same results, except for
-round-off and precision issues.
-
-The accelerated style is part of the OPENMP.  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 style 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.
+.. include:: accel_styles.rst
 
 ----------
 

doc/src/pair_hybrid.rst

@@ -383,30 +383,19 @@ coefficients to 0.0.
 
 ----------
 
-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.  Pair style *hybrid/scaled* does (currently) not support the
-*gpu*, *omp*, *kk*, or *intel* suffix.
+.. include:: accel_styles.rst
 
-Since the *hybrid*, *hybrid/overlay*, *hybrid/scaled* styles delegate
-computation to the individual sub-styles, the suffix versions of the
-*hybrid* and *hybrid/overlay* styles are used to propagate the
-corresponding suffix to all sub-styles, if those versions
-exist. Otherwise the non-accelerated version will be used.
+.. note::
 
-The individual accelerated sub-styles are part of the GPU, KOKKOS,
-INTEL, 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 the :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+  Since the *hybrid*, *hybrid/overlay*, *hybrid/scaled* styles
+  delegate computation to the individual sub-styles, the suffix
+  versions of the *hybrid* and *hybrid/overlay* styles are used to
+  propagate the corresponding suffix to all sub-styles, if those
+  versions exist. Otherwise the non-accelerated version will be used.
+  The individual accelerated sub-styles are part of the GPU, KOKKOS,
+  INTEL, 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.
 
 ----------
 

doc/src/pair_reaxff.rst

@@ -20,7 +20,7 @@ Syntax
   .. parsed-literal::
 
      keyword = *checkqeq* or *lgvdw* or *safezone* or *mincap* or *minhbonds*
-       *checkqeq* value = *yes* or *no* = whether or not to require qeq/reaxff fix
+       *checkqeq* value = *yes* or *no* = whether or not to require qeq/reaxff or acks2/reaxff fix
        *enobonds* value = *yes* or *no* = whether or not to tally energy of atoms with no bonds
        *lgvdw* value = *yes* or *no* = whether or not to use a low gradient vdW correction
        *safezone* = factor used for array allocation
@@ -119,7 +119,8 @@ The ReaxFF parameter files provided were created using a charge
 equilibration (QEq) model for handling the electrostatic interactions.
 Therefore, by default, LAMMPS requires that either the
 :doc:`fix qeq/reaxff <fix_qeq_reaxff>` or the
-:doc:`fix qeq/shielded <fix_qeq>` command be used with
+:doc:`fix qeq/shielded <fix_qeq>` or :doc:`fix acks2/reaxff <fix_acks2_reaxff>`
+command be used with
 *pair_style reaxff* when simulating a ReaxFF model, to equilibrate
 the charges each timestep.
 
@@ -128,7 +129,8 @@ for the QEq fixes, allowing a simulation to be run without charge
 equilibration. In this case, the static charges you assign to each
 atom will be used for computing the electrostatic interactions in
 the system. See the :doc:`fix qeq/reaxff <fix_qeq_reaxff>` or
-:doc:`fix qeq/shielded <fix_qeq>` command documentation for more details.
+:doc:`fix qeq/shielded <fix_qeq>` or :doc:`fix acks2/reaxff <fix_acks2_reaxff>`
+command documentation for more details.
 
 Using the optional keyword *lgvdw* with the value *yes* turns on the
 low-gradient correction of ReaxFF for long-range London Dispersion,
@@ -352,7 +354,8 @@ Related commands
 """"""""""""""""
 
 :doc:`pair_coeff <pair_coeff>`, :doc:`fix qeq/reaxff <fix_qeq_reaxff>`,
-:doc:`fix reaxff/bonds <fix_reaxff_bonds>`, :doc:`fix reaxff/species <fix_reaxff_species>`
+:doc:`fix acks2/reaxff <fix_acks2_reaxff>`, :doc:`fix reaxff/bonds <fix_reaxff_bonds>`,
+:doc:`fix reaxff/species <fix_reaxff_species>`
 
 Default
 """""""

doc/src/pair_sw.rst

@@ -159,28 +159,14 @@ taken from the ij and ik pairs (:math:`\sigma`, *a*, :math:`\gamma`)
 
 ----------
 
-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.
+.. include:: accel_styles.rst
 
-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.
+.. note::
 
-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.
-
-When using the INTEL package with this style, there is an
-additional 5 to 10 percent performance improvement when the
-Stillinger-Weber parameters p and q are set to 4 and 0 respectively.
-These parameters are common for modeling silicon and water.
-
-See the :doc:`Speed packages <Speed_packages>` page for more
-instructions on how to use the accelerated styles effectively.
+  When using the INTEL package with this style, there is an additional
+  5 to 10 percent performance improvement when the Stillinger-Weber
+  parameters p and q are set to 4 and 0 respectively.  These
+  parameters are common for modeling silicon and water.
 
 ----------
 

doc/src/plugin.rst

@@ -65,10 +65,8 @@ only enabled if LAMMPS was built with that package.
 See the :doc:`Build package <Build_package>` page for
 more info. Plugins are not available on Windows.
 
-For the loading of plugins to work the LAMMPS library must be
-:ref:`compiled as a shared library <library>`.  If plugins
-access functions or classes from a package, LAMMPS must have
-been compiled with that package included.
+If plugins access functions or classes from a package, LAMMPS must
+have been compiled with that package included.
 
 Plugins are dependent on the LAMMPS binary interface (ABI)
 and particularly the MPI library used. So they are not guaranteed

doc/src/region.rst

@@ -371,26 +371,13 @@ sub-regions can be defined with the *open* keyword.
 
 ----------
 
-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.
+.. include:: accel_styles.rst
 
-The code using the region (such as a fix or compute) must also be supported
-by Kokkos or no acceleration will occur. Currently, only *block* style
-regions are supported by Kokkos.
+.. note::
 
-These accelerated styles are part of the Kokkos package.  They are
-only enabled if LAMMPS was built with that package.  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.
+  Currently, only *block* style regions are supported by Kokkos.  The
+  code using the region (such as a fix or compute) must also be
+  supported by Kokkos or no acceleration will occur.
 
 ----------
 

doc/src/run_style.rst

@@ -125,12 +125,13 @@ screen.0 by default; see the :doc:`-plog and -pscreen command-line switches <Run
 for the second partition will not contain thermodynamic output beyond the
 first timestep of the run.
 
-See the :doc:`Speed packages <Speed_packages>` page for performance
-details of the speed-up offered by the *verlet/split* style.  One
-important performance consideration is the assignment of logical
-processors in the 2 partitions to the physical cores of a parallel
-machine.  The :doc:`processors <processors>` command has options to
-support this, and strategies are discussed in :doc:`Section 5 <Speed>` of the manual.
+See the :doc:`Accelerator packages <Speed_packages>` page for
+performance details of the speed-up offered by the *verlet/split*
+style.  One important performance consideration is the assignment of
+logical processors in the 2 partitions to the physical cores of a
+parallel machine.  The :doc:`processors <processors>` command has
+options to support this, and strategies are discussed in :doc:`Section
+5 <Speed>` of the manual.
 
 ----------
 
@@ -295,10 +296,10 @@ except for round-off and precision issues.
 
 You can specify *respa/omp* explicitly in your input script, 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.
+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.
 
 ----------
@@ -308,7 +309,8 @@ Restrictions
 
 The *verlet/split* style can only be used if LAMMPS was built with the
 REPLICA package. Correspondingly the *respa/omp* style is available
-only if the OPENMP package was included. See the :doc:`Build package <Build_package>` page for more info.
+only if the OPENMP package was included. See the :doc:`Build package
+<Build_package>` page for more info.
 
 Whenever using rRESPA, the user should experiment with trade-offs in
 speed and accuracy for their system, and verify that they are

doc/utils/check-styles.py

@@ -254,7 +254,7 @@ for command_type, entries in index.items():
 
 print("Total number of style index entries:", total_index)
 
-skip_fix = ('python', 'NEIGH_HISTORY/omp','qeq/reax','reax/c/bonds','reax/c/species')
+skip_fix = ('python', 'NEIGH_HISTORY/omp','acks2/reax','qeq/reax','reax/c/bonds','reax/c/species')
 skip_pair = ('meam/c','lj/sf','reax/c')
 
 counter = 0
@@ -282,7 +282,7 @@ if counter:
 counter = 0
 
 counter += check_style_index("compute", compute, index["compute"])
-counter += check_style_index("fix", fix, index["fix"], skip=['python','qeq/reax','reax/c/bonds','reax/c/species'])
+counter += check_style_index("fix", fix, index["fix"], skip=['python','acks2/reax','qeq/reax','reax/c/bonds','reax/c/species'])
 counter += check_style_index("angle_style", angle, index["angle_style"])
 counter += check_style_index("bond_style", bond, index["bond_style"])
 counter += check_style_index("dihedral_style", dihedral, index["dihedral_style"])

doc/utils/requirements.txt

@@ -1,4 +1,4 @@
-Sphinx==4.0.3
+Sphinx
 sphinxcontrib-spelling
 git+git://github.com/akohlmey/sphinx-fortran@parallel-read
 sphinx_tabs