diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
index f6f822676e..69aff2d72d 100644
--- a/cmake/CMakeLists.txt
+++ b/cmake/CMakeLists.txt
@@ -207,7 +207,7 @@ include_directories(${LAMMPS_SOURCE_DIR})
 if(PKG_USER-ADIOS)
   # The search for ADIOS2 must come before MPI because
   # it includes its own MPI search with the latest FindMPI.cmake
-  # script that defines the MPI::MPI_C target 
+  # script that defines the MPI::MPI_C target
   enable_language(C)
   find_package(ADIOS2 REQUIRED)
   list(APPEND LAMMPS_LINK_LIBS adios2::adios2)
@@ -320,10 +320,15 @@ pkg_depends(USER-LB MPI)
 pkg_depends(USER-PHONON KSPACE)
 pkg_depends(USER-SCAFACOS MPI)
 
+include(CheckIncludeFileCXX)
 find_package(OpenMP QUIET)
 option(BUILD_OMP "Build with OpenMP support" ${OpenMP_FOUND})
-if(BUILD_OMP OR PKG_KOKKOS OR PKG_USER-INTEL)
+if(BUILD_OMP)
   find_package(OpenMP REQUIRED)
+  check_include_file_cxx(omp.h HAVE_OMP_H_INCLUDE)
+  if(NOT HAVE_OMP_H_INCLUDE)
+    message(FATAL_ERROR "Cannot find required 'omp.h' header file")
+  endif()
   set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${OpenMP_C_FLAGS}")
   set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${OpenMP_CXX_FLAGS}")
 endif()
@@ -367,7 +372,7 @@ if(PKG_KSPACE)
   endif()
 endif()
 
-if(PKG_MSCG OR PKG_USER-ATC OR PKG_USER-AWPMD OR PKG_USER-QUIP OR PKG_LATTE)
+if(PKG_MSCG OR PKG_USER-ATC OR PKG_USER-AWPMD OR PKG_USER-PLUMED OR PKG_USER-QUIP OR PKG_LATTE)
   find_package(LAPACK)
   find_package(BLAS)
   if(NOT LAPACK_FOUND OR NOT BLAS_FOUND)
@@ -381,19 +386,10 @@ if(PKG_MSCG OR PKG_USER-ATC OR PKG_USER-AWPMD OR PKG_USER-QUIP OR PKG_LATTE)
 endif()
 
 if(PKG_PYTHON)
-  find_package(PythonInterp REQUIRED)
   find_package(PythonLibs REQUIRED)
   add_definitions(-DLMP_PYTHON)
   include_directories(${PYTHON_INCLUDE_DIR})
   list(APPEND LAMMPS_LINK_LIBS ${PYTHON_LIBRARY})
-  if(BUILD_LIB AND BUILD_SHARED_LIBS)
-    if(NOT PYTHON_INSTDIR)
-      execute_process(COMMAND ${PYTHON_EXECUTABLE}
-        -c "import distutils.sysconfig as cg; print(cg.get_python_lib(1,0,prefix='${CMAKE_INSTALL_PREFIX}'))"
-        OUTPUT_VARIABLE PYTHON_INSTDIR OUTPUT_STRIP_TRAILING_WHITESPACE)
-    endif()
-    install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../python/lammps.py DESTINATION ${PYTHON_INSTDIR})
-  endif()
 endif()
 
 find_package(JPEG QUIET)
@@ -452,7 +448,13 @@ endif()
 
 
 if(PKG_VORONOI)
-  option(DOWNLOAD_VORO "Download and compile the Voro++ library instead of using an already installed one" OFF)
+  find_package(VORO)
+  if(VORO_FOUND)
+    set(DOWNLOAD_VORO_DEFAULT OFF)
+  else()
+    set(DOWNLOAD_VORO_DEFAULT ON)
+  endif()
+  option(DOWNLOAD_VORO "Download and compile the Voro++ library instead of using an already installed one" ${DOWNLOAD_VORO_DEFAULT})
   if(DOWNLOAD_VORO)
     message(STATUS "Voro++ download requested - we will build our own")
     include(ExternalProject)
@@ -485,7 +487,13 @@ if(PKG_VORONOI)
 endif()
 
 if(PKG_LATTE)
-  option(DOWNLOAD_LATTE "Download the LATTE library instead of using an already installed one" OFF)
+  find_package(LATTE)
+  if(LATTE_FOUND)
+    set(DOWNLOAD_LATTE_DEFAULT OFF)
+  else()
+    set(DOWNLOAD_LATTE_DEFAULT ON)
+  endif()
+  option(DOWNLOAD_LATTE "Download the LATTE library instead of using an already installed one" ${DOWNLOAD_LATTE_DEFAULT})
   if(DOWNLOAD_LATTE)
     if (CMAKE_VERSION VERSION_LESS "3.7") # due to SOURCE_SUBDIR
       message(FATAL_ERROR "For downlading LATTE you need at least cmake-3.7")
@@ -496,7 +504,7 @@ if(PKG_LATTE)
       URL https://github.com/lanl/LATTE/archive/v1.2.1.tar.gz
       URL_MD5 85ac414fdada2d04619c8f936344df14
       SOURCE_SUBDIR cmake
-      CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CMAKE_REQUEST_PIC}
+      CMAKE_ARGS -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR> ${CMAKE_REQUEST_PIC} -DBLAS_LIBRARIES=${BLAS_LIBRARIES} -DLAPACK_LIBRARIES=${LAPACK_LIBRARIES}
     )
     ExternalProject_get_property(latte_build INSTALL_DIR)
     set(LATTE_LIBRARIES ${INSTALL_DIR}/${CMAKE_INSTALL_LIBDIR}/liblatte.a)
@@ -512,7 +520,15 @@ endif()
 
 if(PKG_USER-SCAFACOS)
   find_package(GSL REQUIRED)
-  option(DOWNLOAD_SCAFACOS "Download ScaFaCoS library instead of using an already installed one" OFF)
+  find_package(PkgConfig QUIET)
+  set(DOWNLOAD_SCAFACOS_DEFAULT ON)
+  if(PKG_CONFIG_FOUND)
+    pkg_check_modules(SCAFACOS QUIET scafacos)
+    if(SCAFACOS_FOUND)
+      set(DOWNLOAD_SCAFACOS_DEFAULT OFF)
+    endif()
+  endif()
+  option(DOWNLOAD_SCAFACOS "Download ScaFaCoS library instead of using an already installed one" ${DOWNLOAD_SCAFACOS_DEFAULT})
   if(DOWNLOAD_SCAFACOS)
     message(STATUS "ScaFaCoS download requested - we will build our own")
     include(ExternalProject)
@@ -552,8 +568,8 @@ if(PKG_USER-SCAFACOS)
     list(APPEND LAMMPS_LINK_LIBS ${MPI_Fortran_LIBRARIES})
     list(APPEND LAMMPS_LINK_LIBS ${MPI_C_LIBRARIES})
   else()
-    FIND_PACKAGE(PkgConfig REQUIRED)
-    PKG_CHECK_MODULES(SCAFACOS scafacos REQUIRED)
+    find_package(PkgConfig REQUIRED)
+    pkg_check_modules(SCAFACOS REQUIRED scafacos)
     list(APPEND LAMMPS_LINK_LIBS ${SCAFACOS_LDFLAGS})
   endif()
   include_directories(${SCAFACOS_INCLUDE_DIRS})
@@ -567,29 +583,53 @@ if(PKG_USER-PLUMED)
   validate_option(PLUMED_MODE PLUMED_MODE_VALUES)
   string(TOUPPER ${PLUMED_MODE} PLUMED_MODE)
 
-  option(DOWNLOAD_PLUMED "Download Plumed package instead of using an already installed one" OFF)
+  find_package(PkgConfig QUIET)
+  set(DOWNLOAD_PLUMED_DEFAULT ON)
+  if(PKG_CONFIG_FOUND)
+    pkg_check_modules(PLUMED QUIET plumed)
+    if(PLUMED_FOUND)
+      set(DOWNLOAD_PLUMED_DEFAULT OFF)
+    endif()
+  endif()
+
+  option(DOWNLOAD_PLUMED "Download Plumed package instead of using an already installed one" ${DOWNLOAD_PLUMED_DEFAULT})
   if(DOWNLOAD_PLUMED)
+    if(BUILD_MPI)
+      set(PLUMED_CONFIG_MPI "--enable-mpi")
+      set(PLUMED_CONFIG_CC  ${CMAKE_MPI_C_COMPILER})
+      set(PLUMED_CONFIG_CXX  ${CMAKE_MPI_CXX_COMPILER})
+    else()
+      set(PLUMED_CONFIG_MPI "--disable-mpi")
+      set(PLUMED_CONFIG_CC  ${CMAKE_C_COMPILER})
+      set(PLUMED_CONFIG_CXX  ${CMAKE_CXX_COMPILER})
+    endif()
+    if(BUILD_OMP)
+      set(PLUMED_CONFIG_OMP "--enable-openmp")
+    else()
+      set(PLUMED_CONFIG_OMP "--disable-openmp")
+    endif()
     message(STATUS "PLUMED download requested - we will build our own")
     include(ExternalProject)
     ExternalProject_Add(plumed_build
-      URL https://github.com/plumed/plumed2/releases/download/v2.4.4/plumed-src-2.4.4.tgz
-      URL_MD5 71ed465bdc7c2059e282dbda8d564e71
+      URL https://github.com/plumed/plumed2/releases/download/v2.5.1/plumed-src-2.5.1.tgz
+      URL_MD5 c2a7b519e32197a120cdf47e0f194f81
       BUILD_IN_SOURCE 1
       CONFIGURE_COMMAND <SOURCE_DIR>/configure --prefix=<INSTALL_DIR>
                                                ${CONFIGURE_REQUEST_PIC}
-                                                --enable-modules=all
-                                               CXX=${CMAKE_MPI_CXX_COMPILER}
-                                               CC=${CMAKE_MPI_C_COMPILER}
+                                               --enable-modules=all
+                                               ${PLUMED_CONFIG_MPI}
+                                               ${PLUMED_CONFIG_OMP}
+                                               CXX=${PLUMED_CONFIG_CXX}
+                                               CC=${PLUMED_CONFIG_CC}
     )
     ExternalProject_get_property(plumed_build INSTALL_DIR)
     set(PLUMED_INSTALL_DIR ${INSTALL_DIR})
     list(APPEND LAMMPS_DEPS plumed_build)
     if(PLUMED_MODE STREQUAL "STATIC")
       add_definitions(-D__PLUMED_WRAPPER_CXX=1)
-      list(APPEND LAMMPS_LINK_LIBS ${PLUMED_INSTALL_DIR}/lib/plumed/obj/kernel.o
-        "${PLUMED_INSTALL_DIR}/lib/plumed/obj/PlumedStatic.o" ${GSL_LIBRARIES} ${CMAKE_DL_LIBS})
+      list(APPEND LAMMPS_LINK_LIBS ${PLUMED_INSTALL_DIR}/lib/libplumed.a ${GSL_LIBRARIES} ${LAPACK_LIBRARIES} ${CMAKE_DL_LIBS})
     elseif(PLUMED_MODE STREQUAL "SHARED")
-      list(APPEND LAMMPS_LINK_LIBS ${PLUMED_INSTALL_DIR}/lib/libplumed.so ${CMAKE_DL_LIBS})
+      list(APPEND LAMMPS_LINK_LIBS ${PLUMED_INSTALL_DIR}/lib/libplumed.so ${PLUMED_INSTALL_DIR}/lib/libplumedKernel.so ${CMAKE_DL_LIBS})
     elseif(PLUMED_MODE STREQUAL "RUNTIME")
       add_definitions(-D__PLUMED_HAS_DLOPEN=1 -D__PLUMED_DEFAULT_KERNEL=${PLUMED_INSTALL_DIR}/lib/libplumedKernel.so)
       list(APPEND LAMMPS_LINK_LIBS ${PLUMED_INSTALL_DIR}/lib/libplumedWrapper.a -rdynamic ${CMAKE_DL_LIBS})
@@ -597,7 +637,7 @@ if(PKG_USER-PLUMED)
     set(PLUMED_INCLUDE_DIRS "${PLUMED_INSTALL_DIR}/include")
   else()
     find_package(PkgConfig REQUIRED)
-    pkg_check_modules(PLUMED plumed REQUIRED)
+    pkg_check_modules(PLUMED REQUIRED plumed)
     if(PLUMED_MODE STREQUAL "STATIC")
       add_definitions(-D__PLUMED_WRAPPER_CXX=1)
       include(${PLUMED_LIBDIR}/plumed/src/lib/Plumed.cmake.static)
@@ -613,9 +653,13 @@ if(PKG_USER-PLUMED)
 endif()
 
 if(PKG_USER-MOLFILE)
+  set(MOLFILE_INCLUDE_DIRS "${LAMMPS_LIB_SOURCE_DIR}/molfile" CACHE STRING "Path to VMD molfile plugin headers")
   add_library(molfile INTERFACE)
-  target_include_directories(molfile INTERFACE ${LAMMPS_LIB_SOURCE_DIR}/molfile)
-  target_link_libraries(molfile INTERFACE ${CMAKE_DL_LIBS})
+  target_include_directories(molfile INTERFACE ${MOLFILE_INCLUDE_DIRS})
+  # no need to link with -ldl on windows
+  if(NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Windows")
+    target_link_libraries(molfile INTERFACE ${CMAKE_DL_LIBS})
+  endif()
   list(APPEND LAMMPS_LINK_LIBS molfile)
 endif()
 
@@ -626,9 +670,14 @@ if(PKG_USER-NETCDF)
   add_definitions(-DLMP_HAS_NETCDF -DNC_64BIT_DATA=0x0020)
 endif()
 
-
 if(PKG_USER-SMD)
-  option(DOWNLOAD_EIGEN3 "Download Eigen3 instead of using an already installed one)" OFF)
+  find_package(Eigen3 NO_MODULE)
+  if(EIGEN3_FOUND)
+    set(DOWNLOAD_EIGEN3_DEFAULT OFF)
+  else()
+    set(DOWNLOAD_EIGEN3_DEFAULT ON)
+  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")
     include(ExternalProject)
@@ -670,15 +719,27 @@ if(PKG_USER-VTK)
 endif()
 
 if(PKG_KIM)
-  option(DOWNLOAD_KIM "Download KIM-API v2 from OpenKIM instead of using an already installed one" OFF)
+  find_package(CURL)
+  if(CURL_FOUND)
+    include_directories(${CURL_INCLUDE_DIRS})
+    list(APPEND LAMMPS_LINK_LIBS ${CURL_LIBRARIES})
+    add_definitions(-DLMP_KIM_CURL)
+  endif()
+  find_package(KIM-API QUIET)
+  if(KIM-API_FOUND)
+    set(DOWNLOAD_KIM_DEFAULT OFF)
+  else()
+    set(DOWNLOAD_KIM_DEFAULT ON)
+  endif()
+  option(DOWNLOAD_KIM "Download KIM-API from OpenKIM instead of using an already installed one" ${DOWNLOAD_KIM_DEFAULT})
   if(DOWNLOAD_KIM)
-    message(STATUS "KIM-API v2 download requested - we will build our own")
+    message(STATUS "KIM-API download requested - we will build our own")
     enable_language(C)
     enable_language(Fortran)
     include(ExternalProject)
     ExternalProject_Add(kim_build
-      URL https://s3.openkim.org/kim-api/kim-api-v2-2.0.1.txz
-      URL_MD5 289c57f0c3bc2a549662283cac1c4ef1
+      URL https://s3.openkim.org/kim-api/kim-api-2.0.2.txz
+      URL_MD5 537d9c0abd30f85b875ebb584f9143fa
       BINARY_DIR build
       CMAKE_ARGS -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
                  -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
@@ -687,17 +748,14 @@ if(PKG_KIM)
                  -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
       )
     ExternalProject_get_property(kim_build INSTALL_DIR)
-    set(KIM-API-V2_INCLUDE_DIRS ${INSTALL_DIR}/include/kim-api-v2)
-    set(KIM-API-V2_LDFLAGS ${INSTALL_DIR}/${CMAKE_INSTALL_LIBDIR}/libkim-api-v2${CMAKE_SHARED_LIBRARY_SUFFIX})
+    set(KIM-API_INCLUDE_DIRS ${INSTALL_DIR}/include/kim-api)
+    set(KIM-API_LDFLAGS ${INSTALL_DIR}/${CMAKE_INSTALL_LIBDIR}/libkim-api${CMAKE_SHARED_LIBRARY_SUFFIX})
     list(APPEND LAMMPS_DEPS kim_build)
   else()
-    find_package(KIM-API-V2)
-    if(NOT KIM-API-V2_FOUND)
-      message(FATAL_ERROR "KIM-API v2 not found, help CMake to find it by setting PKG_CONFIG_PATH, or set DOWNLOAD_KIM=ON to download it")
-    endif()
+    find_package(KIM-API REQUIRED)
   endif()
-  list(APPEND LAMMPS_LINK_LIBS "${KIM-API-V2_LDFLAGS}")
-  include_directories(${KIM-API-V2_INCLUDE_DIRS})
+  list(APPEND LAMMPS_LINK_LIBS "${KIM-API_LDFLAGS}")
+  include_directories(${KIM-API_INCLUDE_DIRS})
 endif()
 
 if(PKG_MESSAGE)
@@ -712,6 +770,7 @@ if(PKG_MESSAGE)
     set_target_properties(cslib PROPERTIES OUTPUT_NAME "csmpi")
   else()
     target_compile_definitions(cslib PRIVATE -DMPI_NO)
+    target_include_directories(cslib PRIVATE ${LAMMPS_LIB_SOURCE_DIR}/message/cslib/src/STUBS_MPI)
     set_target_properties(cslib PROPERTIES OUTPUT_NAME "csnompi")
   endif()
 
@@ -731,7 +790,13 @@ endif()
 
 if(PKG_MSCG)
   find_package(GSL REQUIRED)
-  option(DOWNLOAD_MSCG "Download MSCG library instead of using an already installed one)" OFF)
+  find_package(MSCG QUIET)
+  if(MSGC_FOUND)
+    set(DOWNLOAD_MSCG_DEFAULT OFF)
+  else()
+    set(DOWNLOAD_MSCG_DEFAULT ON)
+  endif()
+  option(DOWNLOAD_MSCG "Download MSCG library instead of using an already installed one)" ${DOWNLOAD_MSCG_DEFAULT})
   if(DOWNLOAD_MSCG)
     if (CMAKE_VERSION VERSION_LESS "3.7") # due to SOURCE_SUBDIR
       message(FATAL_ERROR "For downlading MSCG you need at least cmake-3.7")
@@ -780,7 +845,6 @@ endif()
 ########################################################################
 # Basic system tests (standard libraries, headers, functions, types)   #
 ########################################################################
-include(CheckIncludeFileCXX)
 foreach(HEADER cmath)
   check_include_file_cxx(${HEADER} FOUND_${HEADER})
   if(NOT FOUND_${HEADER})
@@ -947,7 +1011,7 @@ if(PKG_USER-OMP)
 
     # detects styles which have USER-OMP version
     RegisterStylesExt(${USER-OMP_SOURCES_DIR} omp OMP_SOURCES)
-    RegisterFixStyle("${USER-OMP_SOURCES_DIR}/fix_omp.h")
+    RegisterFixStyle(${USER-OMP_SOURCES_DIR}/fix_omp.h)
 
     get_property(USER-OMP_SOURCES GLOBAL PROPERTY OMP_SOURCES)
 
@@ -1060,37 +1124,79 @@ if(PKG_OPT)
 endif()
 
 if(PKG_USER-INTEL)
-    find_package(TBB REQUIRED)
-    find_package(MKL REQUIRED)
+  if(LAMMPS_SIZES STREQUAL BIGBIG)
+    message(FATAL_ERROR "The USER-INTEL Package is not compatible with -DLAMMPS_BIGBIG")
+  endif()
+  add_definitions(-DLMP_USER_INTEL)
 
-    if(NOT CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
-      message(FATAL_ERROR "USER-INTEL is only useful together with intel compiler")
-    endif()
+  set(INTEL_ARCH "cpu" CACHE STRING "Architectures used by USER-INTEL (cpu or knl)")
+  set(INTEL_ARCH_VALUES cpu knl)
+  set_property(CACHE INTEL_ARCH PROPERTY STRINGS ${INTEL_ARCH_VALUES})
+  validate_option(INTEL_ARCH INTEL_ARCH_VALUES)
+  string(TOUPPER ${INTEL_ARCH} INTEL_ARCH)
 
-    if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16)
-        message(FATAL_ERROR "USER-INTEL needs at least a 2016 intel compiler, found ${CMAKE_CXX_COMPILER_VERSION}")
-    endif()
-
-    if(NOT BUILD_OMP)
-        message(FATAL_ERROR "USER-INTEL requires OpenMP")
-    endif()
-
-    if(NOT ${LAMMPS_MEMALIGN} STREQUAL "64")
-        message(FATAL_ERROR "USER-INTEL is only useful with LAMMPS_MEMALIGN=64")
-    endif()
-
-    set(INTEL_ARCH "cpu" CACHE STRING "Architectures used by USER-INTEL (cpu or knl)")
-    set(INTEL_ARCH_VALUES cpu knl)
-    set_property(CACHE INTEL_ARCH PROPERTY STRINGS ${INTEL_ARCH_VALUES})
-    validate_option(INTEL_ARCH INTEL_ARCH_VALUES)
-    string(TOUPPER ${INTEL_ARCH} INTEL_ARCH)
-
-    if(INTEL_ARCH STREQUAL "KNL")
-      set(CMAKE_EXE_LINKER_FLAGS  "${CMAKE_EXE_LINKER_FLAGS} -xHost -qopenmp -qoffload")
-      set(MIC_OPTIONS "-qoffload-option,mic,compiler,\"-fp-model fast=2 -mGLOB_default_function_attrs=\\\"gather_scatter_loop_unroll=4\\\"\"")
-      add_compile_options(-xMIC-AVX512 -qoffload -fno-alias -ansi-alias -restrict -qoverride-limits ${MIC_OPTIONS})
-      add_definitions(-DLMP_INTEL_OFFLOAD)
+  find_package(Threads QUIET)
+  if(Threads_FOUND)
+    set(INTEL_LRT_MODE "threads" CACHE STRING "Long-range threads mode (none, threads, or c++11)")
+  else()
+    set(INTEL_LRT_MODE "none" CACHE STRING "Long-range threads mode (none, threads, or c++11)")
+  endif()
+  set(INTEL_LRT_VALUES none threads c++11)
+  set_property(CACHE INTEL_LRT_MODE PROPERTY STRINGS ${INTEL_LRT_VALUES})
+  validate_option(INTEL_LRT_MODE INTEL_LRT_VALUES)
+  string(TOUPPER ${INTEL_LRT_MODE} INTEL_LRT_MODE)
+  if(INTEL_LRT_MODE STREQUAL "THREADS")
+    if(Threads_FOUND)
+      add_definitions(-DLMP_INTEL_USELRT)
+      list(APPEND LAMMPS_LINK_LIBS ${CMAKE_THREAD_LIBS_INIT})
     else()
+      message(FATAL_ERROR "Must have working threads library for Long-range thread support")
+    endif()
+  endif()
+  if(INTEL_LRT_MODE STREQUAL "C++11")
+    add_definitions(-DLMP_INTEL_USERLRT -DLMP_INTEL_LRT11)
+  endif()
+
+  if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
+    if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16)
+      message(FATAL_ERROR "USER-INTEL needs at least a 2016 Intel compiler, found ${CMAKE_CXX_COMPILER_VERSION}")
+    endif()
+  else()
+    message(WARNING "USER-INTEL gives best performance with Intel compilers")
+  endif()
+
+  find_package(TBB QUIET)
+  if(TBB_FOUND)
+    list(APPEND LAMMPS_LINK_LIBS ${TBB_MALLOC_LIBRARIES})
+  else()
+    add_definitions(-DLMP_INTEL_NO_TBB)
+    if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
+      message(WARNING "USER-INTEL with Intel compilers should use TBB malloc libraries")
+    endif()
+  endif()
+
+  find_package(MKL QUIET)
+  if(MKL_FOUND)
+    add_definitions(-DLMP_USE_MKL_RNG)
+    list(APPEND LAMMPS_LINK_LIBS ${MKL_LIBRARIES})
+  else()
+    message(STATUS "Pair style dpd/intel will be faster with MKL libraries")
+  endif()
+
+  if((NOT ${CMAKE_SYSTEM_NAME} STREQUAL "Windows") AND (NOT ${LAMMPS_MEMALIGN} STREQUAL "64") AND (NOT ${LAMMPS_MEMALIGN} STREQUAL "128") AND (NOT ${LAMMPS_MEMALIGN} STREQUAL "256"))
+    message(FATAL_ERROR "USER-INTEL only supports memory alignment of 64, 128 or 256 on this platform")
+  endif()
+
+  if(INTEL_ARCH STREQUAL "KNL")
+    if(NOT CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
+      message(FATAL_ERROR "Must use Intel compiler with USER-INTEL for KNL architecture")
+    endif()
+    set(CMAKE_EXE_LINKER_FLAGS  "${CMAKE_EXE_LINKER_FLAGS} -xHost -qopenmp -qoffload")
+    set(MIC_OPTIONS "-qoffload-option,mic,compiler,\"-fp-model fast=2 -mGLOB_default_function_attrs=\\\"gather_scatter_loop_unroll=4\\\"\"")
+    add_compile_options(-xMIC-AVX512 -qoffload -fno-alias -ansi-alias -restrict -qoverride-limits ${MIC_OPTIONS})
+    add_definitions(-DLMP_INTEL_OFFLOAD)
+  else()
+    if(CMAKE_CXX_COMPILER_ID STREQUAL "Intel")
       if(CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.3 OR CMAKE_CXX_COMPILER_VERSION VERSION_EQUAL 17.4)
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -xCOMMON-AVX512")
       else()
@@ -1103,33 +1209,33 @@ if(PKG_USER-INTEL)
           add_compile_options(${_FLAG})
         endif()
       endforeach()
+    else()
+      add_compile_options(-O3 -ffast-math)
     endif()
+  endif()
 
-    add_definitions(-DLMP_INTEL_USELRT -DLMP_USE_MKL_RNG)
+  # collect sources
+  set(USER-INTEL_SOURCES_DIR ${LAMMPS_SOURCE_DIR}/USER-INTEL)
+  set(USER-INTEL_SOURCES ${USER-INTEL_SOURCES_DIR}/fix_intel.cpp
+                         ${USER-INTEL_SOURCES_DIR}/fix_nh_intel.cpp
+                         ${USER-INTEL_SOURCES_DIR}/intel_buffers.cpp
+                         ${USER-INTEL_SOURCES_DIR}/nbin_intel.cpp
+                         ${USER-INTEL_SOURCES_DIR}/npair_intel.cpp
+                         ${USER-INTEL_SOURCES_DIR}/verlet_lrt_intel.cpp)
 
-    list(APPEND LAMMPS_LINK_LIBS ${TBB_MALLOC_LIBRARIES} ${MKL_LIBRARIES})
+  set_property(GLOBAL PROPERTY "USER-INTEL_SOURCES" "${USER-INTEL_SOURCES}")
 
-    set(USER-INTEL_SOURCES_DIR ${LAMMPS_SOURCE_DIR}/USER-INTEL)
-    set(USER-INTEL_SOURCES ${USER-INTEL_SOURCES_DIR}/intel_preprocess.h
-                           ${USER-INTEL_SOURCES_DIR}/intel_buffers.h
-                           ${USER-INTEL_SOURCES_DIR}/intel_buffers.cpp
-                           ${USER-INTEL_SOURCES_DIR}/math_extra_intel.h
-                           ${USER-INTEL_SOURCES_DIR}/nbin_intel.h
-                           ${USER-INTEL_SOURCES_DIR}/nbin_intel.cpp
-                           ${USER-INTEL_SOURCES_DIR}/npair_intel.h
-                           ${USER-INTEL_SOURCES_DIR}/npair_intel.cpp
-                           ${USER-INTEL_SOURCES_DIR}/intel_simd.h
-                           ${USER-INTEL_SOURCES_DIR}/intel_intrinsics.h)
+  # detect styles which have a USER-INTEL version
+  RegisterStylesExt(${USER-INTEL_SOURCES_DIR} intel USER-INTEL_SOURCES)
+  RegisterNBinStyle(${USER-INTEL_SOURCES_DIR}/nbin_intel.h)
+  RegisterNPairStyle(${USER-INTEL_SOURCES_DIR}/npair_intel.h)
+  RegisterFixStyle(${USER-INTEL_SOURCES_DIR}/fix_intel.h)
+  RegisterIntegrateStyle(${USER-INTEL_SOURCES_DIR}/verlet_lrt_intel.h)
 
-    set_property(GLOBAL PROPERTY "USER-INTEL_SOURCES" "${USER-INTEL_SOURCES}")
+  get_property(USER-INTEL_SOURCES GLOBAL PROPERTY USER-INTEL_SOURCES)
 
-    # detects styles which have USER-INTEL version
-    RegisterStylesExt(${USER-INTEL_SOURCES_DIR} opt USER-INTEL_SOURCES)
-
-    get_property(USER-INTEL_SOURCES GLOBAL PROPERTY USER-INTEL_SOURCES)
-
-    list(APPEND LIB_SOURCES ${USER-INTEL_SOURCES})
-    include_directories(${USER-INTEL_SOURCES_DIR})
+  list(APPEND LIB_SOURCES ${USER-INTEL_SOURCES})
+  include_directories(${USER-INTEL_SOURCES_DIR})
 endif()
 
 if(PKG_GPU)
@@ -1171,6 +1277,10 @@ if(PKG_GPU)
         message(FATAL_ERROR "Could not find bin2c, use -DBIN2C=/path/to/bin2c to help cmake finding it.")
       endif()
       option(CUDPP_OPT "Enable CUDPP_OPT" ON)
+      option(CUDA_MPS_SUPPORT "Enable tweaks to support CUDA Multi-process service (MPS)" OFF)
+      if(CUDA_MPS_SUPPORT)
+        set(GPU_CUDA_MPS_FLAGS "-DCUDA_PROXY")
+      endif()
 
       set(GPU_ARCH "sm_30" CACHE STRING "LAMMPS GPU CUDA SM primary architecture (e.g. sm_60)")
 
@@ -1234,7 +1344,7 @@ if(PKG_GPU)
       add_library(gpu STATIC ${GPU_LIB_SOURCES} ${GPU_LIB_CUDPP_SOURCES} ${GPU_OBJS})
       target_link_libraries(gpu ${CUDA_LIBRARIES} ${CUDA_CUDA_LIBRARY})
       target_include_directories(gpu PRIVATE ${LAMMPS_LIB_BINARY_DIR}/gpu ${CUDA_INCLUDE_DIRS})
-      target_compile_definitions(gpu PRIVATE -D_${GPU_PREC_SETTING} -DMPI_GERYON -DUCL_NO_EXIT)
+      target_compile_definitions(gpu PRIVATE -D_${GPU_PREC_SETTING} -DMPI_GERYON -DUCL_NO_EXIT ${GPU_CUDA_MPS_FLAGS})
       if(CUDPP_OPT)
         target_include_directories(gpu PRIVATE ${LAMMPS_LIB_SOURCE_DIR}/gpu/cudpp_mini)
         target_compile_definitions(gpu PRIVATE -DUSE_CUDPP)
@@ -1331,36 +1441,14 @@ execute_process(COMMAND ${CMAKE_COMMAND} -E copy_if_different "${LAMMPS_STYLE_HE
 ######################################
 # Generate lmpgitversion.h
 ######################################
-set(temp "#ifndef LMP_GIT_VERSION_H\n#define LMP_GIT_VERSION_H\n")
-set(temp_git_commit "(unknown)")
-set(temp_git_branch "(unknown)")
-set(temp_git_describe "(unknown)")
-set(temp_git_info "false")
-if(GIT_FOUND AND EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/../.git)
-  set(temp_git_info "true")
-  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/../.git rev-parse HEAD
-    OUTPUT_VARIABLE temp_git_commit
-    ERROR_QUIET
-    OUTPUT_STRIP_TRAILING_WHITESPACE)
-  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/../.git rev-parse --abbrev-ref HEAD
-    OUTPUT_VARIABLE temp_git_branch
-    ERROR_QUIET
-    OUTPUT_STRIP_TRAILING_WHITESPACE)
-  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/../.git describe --dirty=-modified
-    OUTPUT_VARIABLE temp_git_describe
-    ERROR_QUIET
-    OUTPUT_STRIP_TRAILING_WHITESPACE)
-endif()
-
-set(temp "${temp}const bool LAMMPS_NS::LAMMPS::has_git_info = ${temp_git_info};\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_commit[] = \"${temp_git_commit}\";\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_branch[] = \"${temp_git_branch}\";\n")
-set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_descriptor[] = \"${temp_git_describe}\";\n")
-set(temp "${temp}#endif\n\n")
-
-message(STATUS "Generating lmpgitversion.h...")
-file(WRITE "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h.tmp" "${temp}" )
-execute_process(COMMAND ${CMAKE_COMMAND} -E copy_if_different "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h.tmp" "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h")
+add_custom_target(gitversion COMMAND ${CMAKE_COMMAND}
+  -DCMAKE_CURRENT_SOURCE_DIR="${CMAKE_CURRENT_SOURCE_DIR}"
+  -DGIT_EXECUTABLE="${GIT_EXECUTABLE}"
+  -DGIT_FOUND="${GIT_FOUND}"
+  -DLAMMPS_STYLE_HEADERS_DIR="${LAMMPS_STYLE_HEADERS_DIR}"
+  -P ${CMAKE_CURRENT_SOURCE_DIR}/Modules/generate_lmpgitversion.cmake)
+set_property(DIRECTORY APPEND PROPERTY ADDITIONAL_MAKE_CLEAN_FILES ${LAMMPS_STYLE_HEADERS_DIR}/gitversion.h)
+list(APPEND LAMMPS_DEPS gitversion)
 
 ###########################################
 # Actually add executable and lib to build
@@ -1406,9 +1494,19 @@ if(BUILD_EXE)
   if(ENABLE_TESTING)
     add_test(ShowHelp ${LAMMPS_BINARY} -help)
   endif()
+
+  enable_language(C)
+  get_filename_component(MSI2LMP_SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/../tools/msi2lmp/src ABSOLUTE)
+  file(GLOB MSI2LMP_SOURCES ${MSI2LMP_SOURCE_DIR}/[^.]*.c)
+  add_executable(msi2lmp ${MSI2LMP_SOURCES})
+  target_link_libraries(msi2lmp m)
+  install(TARGETS msi2lmp DESTINATION ${CMAKE_INSTALL_BINDIR})
+  install(FILES ${LAMMPS_DOC_DIR}/msi2lmp.1 DESTINATION ${CMAKE_INSTALL_MANDIR}/man1)
+
 endif()
 
 
+
 ###############################################################################
 # Build documentation
 ###############################################################################
@@ -1470,11 +1568,14 @@ if(BUILD_DOC)
 endif()
 
 ###############################################################################
-# Install potential files in data directory
+# Install potential and force field files in data directory
 ###############################################################################
 set(LAMMPS_POTENTIALS_DIR ${CMAKE_INSTALL_FULL_DATADIR}/lammps/potentials)
 install(DIRECTORY ${LAMMPS_SOURCE_DIR}/../potentials/ DESTINATION ${LAMMPS_POTENTIALS_DIR})
 
+set(LAMMPS_FRC_FILES_DIR ${CMAKE_INSTALL_FULL_DATADIR}/lammps/frc_files)
+install(DIRECTORY ${LAMMPS_SOURCE_DIR}/../tools/msi2lmp/frc_files/ DESTINATION ${LAMMPS_FRC_FILES_DIR})
+
 configure_file(etc/profile.d/lammps.sh.in ${CMAKE_BINARY_DIR}/etc/profile.d/lammps.sh @ONLY)
 configure_file(etc/profile.d/lammps.csh.in ${CMAKE_BINARY_DIR}/etc/profile.d/lammps.csh @ONLY)
 install(
@@ -1483,6 +1584,49 @@ install(
   DESTINATION ${CMAKE_INSTALL_SYSCONFDIR}/profile.d
 )
 
+###############################################################################
+# Install LAMMPS lib and python module into site-packages folder with
+# "install-python" target.  Behaves exactly like "make install-python" for
+# conventional build.  Only available, if a shared library is built.
+# This is primarily for people that only want to use the Python wrapper.
+###############################################################################
+if(BUILD_LIB AND BUILD_SHARED_LIBS)
+  find_package(PythonInterp)
+  if (PYTHONINTERP_FOUND)
+    add_custom_target(
+      install-python
+      ${PYTHON_EXECUTABLE} install.py -v ${LAMMPS_SOURCE_DIR}/version.h
+      -m ${CMAKE_CURRENT_SOURCE_DIR}/../python/lammps.py
+      -l ${CMAKE_BINARY_DIR}/liblammps${CMAKE_SHARED_LIBRARY_SUFFIX}
+      WORKING_DIRECTORY  ${CMAKE_CURRENT_SOURCE_DIR}/../python
+      COMMENT "Installing LAMMPS Python module")
+  else()
+    add_custom_target(
+      install-python
+      ${CMAKE_COMMAND} -E echo "Must have Python installed to install the LAMMPS Python module")
+  endif()
+else()
+  add_custom_target(
+    install-python
+    ${CMAKE_COMMAND} -E echo "Must build LAMMPS as a shared library to use the Python module")
+endif()
+
+###############################################################################
+# Add LAMMPS python module to "install" target. This is taylored for building
+# LAMMPS for package managers and with different prefix settings.
+# This requires either a shared library or that the PYTHON package is included.
+###############################################################################
+if((BUILD_LIB AND BUILD_SHARED_LIBS) OR (PKG_PYTHON))
+  find_package(PythonInterp)
+  if (PYTHONINTERP_FOUND)
+    execute_process(COMMAND ${PYTHON_EXECUTABLE}
+      -c "import distutils.sysconfig as cg; print(cg.get_python_lib(1,0,prefix='${CMAKE_INSTALL_PREFIX}'))"
+      OUTPUT_VARIABLE PYTHON_DEFAULT_INSTDIR OUTPUT_STRIP_TRAILING_WHITESPACE)
+    set(PYTHON_INSTDIR ${PYTHON_DEFAULT_INSTDIR} CACHE PATH "Installation folder for LAMMPS Python module")
+    install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/../python/lammps.py DESTINATION ${PYTHON_INSTDIR})
+  endif()
+endif()
+
 ###############################################################################
 # Testing
 #
diff --git a/cmake/Modules/FindKIM-API-V2.cmake b/cmake/Modules/FindKIM-API.cmake
similarity index 56%
rename from cmake/Modules/FindKIM-API-V2.cmake
rename to cmake/Modules/FindKIM-API.cmake
index 6ca6e068df..5108b0f98c 100644
--- a/cmake/Modules/FindKIM-API-V2.cmake
+++ b/cmake/Modules/FindKIM-API.cmake
@@ -19,7 +19,7 @@
 #
 
 #
-# Copyright (c) 2013--2018, Regents of the University of Minnesota.
+# Copyright (c) 2013--2019, Regents of the University of Minnesota.
 # All rights reserved.
 #
 # Contributors:
@@ -28,23 +28,32 @@
 #    Ryan S. Elliott
 #
 
-# - Find KIM-API-V2
+# - Find KIM-API
 #
 # sets standard pkg_check_modules variables plus:
 #
-# KIM-API-V2-CMAKE_C_COMPILER
-# KIM-API-V2-CMAKE_CXX_COMPILER
-# KIM-API-V2-CMAKE_Fortran_COMPILER
+# KIM-API-CMAKE_C_COMPILER
+# KIM-API-CMAKE_CXX_COMPILER
+# KIM-API-CMAKE_Fortran_COMPILER
 #
-find_package(PkgConfig REQUIRED)
+
+if(KIM-API_FIND_QUIETLY)
+  set(REQ_OR_QUI "QUIET")
+else()
+  set(REQ_OR_QUI "REQUIRED")
+endif()
+
+find_package(PkgConfig ${REQ_OR_QUI})
 include(FindPackageHandleStandardArgs)
 
-pkg_check_modules(KIM-API-V2 REQUIRED libkim-api-v2>=2.0)
+pkg_check_modules(KIM-API ${REQ_OR_QUI} libkim-api>=2.0)
 
-pkg_get_variable(KIM-API-V2-CMAKE_C_COMPILER libkim-api-v2 CMAKE_C_COMPILER)
-pkg_get_variable(KIM-API-V2-CMAKE_CXX_COMPILER libkim-api-v2 CMAKE_CXX_COMPILER)
-pkg_get_variable(KIM-API-V2_CMAKE_Fortran_COMPILER libkim-api-v2 CMAKE_Fortran_COMPILER)
+if(KIM-API_FOUND)
+  pkg_get_variable(KIM-API-CMAKE_C_COMPILER libkim-api CMAKE_C_COMPILER)
+  pkg_get_variable(KIM-API-CMAKE_CXX_COMPILER libkim-api CMAKE_CXX_COMPILER)
+  pkg_get_variable(KIM-API_CMAKE_Fortran_COMPILER libkim-api CMAKE_Fortran_COMPILER)
+endif()
 
-# handle the QUIETLY and REQUIRED arguments and set KIM-API-V2_FOUND to TRUE
+# handle the QUIETLY and REQUIRED arguments and set KIM-API_FOUND to TRUE
 # if all listed variables are TRUE
-find_package_handle_standard_args(KIM-API-V2 REQUIRED_VARS KIM-API-V2_LIBRARIES)
+find_package_handle_standard_args(KIM-API REQUIRED_VARS KIM-API_LIBRARIES)
diff --git a/cmake/Modules/StyleHeaderUtils.cmake b/cmake/Modules/StyleHeaderUtils.cmake
index a7b23b4cf1..ebaa5dae8e 100644
--- a/cmake/Modules/StyleHeaderUtils.cmake
+++ b/cmake/Modules/StyleHeaderUtils.cmake
@@ -91,6 +91,10 @@ function(RegisterFixStyle path)
     AddStyleHeader(${path} FIX)
 endfunction(RegisterFixStyle)
 
+function(RegisterIntegrateStyle path)
+    AddStyleHeader(${path} INTEGRATE)
+endfunction(RegisterIntegrateStyle)
+
 function(RegisterStyles search_path)
     FindStyleHeaders(${search_path} ANGLE_CLASS     angle_     ANGLE     ) # angle     ) # force
     FindStyleHeaders(${search_path} ATOM_CLASS      atom_vec_  ATOM_VEC  ) # atom      ) # atom      atom_vec_hybrid
diff --git a/cmake/Modules/generate_lmpgitversion.cmake b/cmake/Modules/generate_lmpgitversion.cmake
new file mode 100644
index 0000000000..a4aa59b262
--- /dev/null
+++ b/cmake/Modules/generate_lmpgitversion.cmake
@@ -0,0 +1,30 @@
+set(temp "#ifndef LMP_GIT_VERSION_H\n#define LMP_GIT_VERSION_H\n")
+set(temp_git_commit "(unknown)")
+set(temp_git_branch "(unknown)")
+set(temp_git_describe "(unknown)")
+set(temp_git_info "false")
+if(GIT_FOUND AND EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/../.git)
+  set(temp_git_info "true")
+  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/.. rev-parse HEAD
+    OUTPUT_VARIABLE temp_git_commit
+    ERROR_QUIET
+    OUTPUT_STRIP_TRAILING_WHITESPACE)
+  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/.. rev-parse --abbrev-ref HEAD
+    OUTPUT_VARIABLE temp_git_branch
+    ERROR_QUIET
+    OUTPUT_STRIP_TRAILING_WHITESPACE)
+  execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR}/.. describe --dirty=-modified
+    OUTPUT_VARIABLE temp_git_describe
+    ERROR_QUIET
+    OUTPUT_STRIP_TRAILING_WHITESPACE)
+endif()
+
+set(temp "${temp}const bool LAMMPS_NS::LAMMPS::has_git_info = ${temp_git_info};\n")
+set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_commit[] = \"${temp_git_commit}\";\n")
+set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_branch[] = \"${temp_git_branch}\";\n")
+set(temp "${temp}const char LAMMPS_NS::LAMMPS::git_descriptor[] = \"${temp_git_describe}\";\n")
+set(temp "${temp}#endif\n\n")
+
+message(STATUS "Generating lmpgitversion.h...")
+file(WRITE "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h.tmp" "${temp}" )
+execute_process(COMMAND ${CMAKE_COMMAND} -E copy_if_different "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h.tmp" "${LAMMPS_STYLE_HEADERS_DIR}/lmpgitversion.h")
diff --git a/cmake/README.md b/cmake/README.md
index ce3b4502af..a635f3e06d 100644
--- a/cmake/README.md
+++ b/cmake/README.md
@@ -155,11 +155,13 @@ make
 
 The CMake build exposes a lot of different options. In the old build system
 some of the package selections were possible by using special make target like
-`make yes-std` or `make no-lib`. Achieving the same result with cmake requires
+`make yes-std` or `make no-lib`. Achieving a similar result with cmake requires
 specifying all options manually. This can quickly become a very long command
 line that is hard to handle.  While these could be stored in a simple script
 file, there is another way of defining "presets" to compile LAMMPS in a certain
-way.
+way. Since the cmake build process - contrary to the conventional build system -
+includes the compilation of the bundled libraries into the standard build process,
+the grouping of those presets is somewhat different.
 
 A preset is a regular CMake script file that can use constructs such as
 variables, lists and for-loops to manipulate configuration options and create
@@ -171,10 +173,10 @@ Such a file can then be passed to cmake via the `-C` flag. Several examples of
 presets can be found in the `cmake/presets` folder.
 
 ```bash
-# build LAMMPS with all "standard" packages which don't use libraries and enable GPU package
+# build LAMMPS with all packages enabled which don't use external libraries and enable GPU package
 mkdir build
 cd build
-cmake -C ../cmake/presets/std_nolib.cmake -D PKG_GPU=on ../cmake
+cmake -C ../cmake/presets/all_on.cmake -C ../cmake/presets/nolib.cmake -D PKG_GPU=on ../cmake
 ```
 
 # Reference
@@ -1429,6 +1431,17 @@ TODO
   </dl>
   </td>
 </tr>
+<tr>
+  <td><code>INTEL_LRT_MODE</code></td>
+  <td>How to support Long-range thread mode in Verlet integration</td>
+  <td>
+  <dl>
+    <dt><code>threads</code> (default, if pthreads available)</dt>
+    <dt><code>none</code> (default, if pthreads not available)</dt>
+    <dt><code>c++11</code></dt>
+  </dl>
+  </td>
+</tr>
 </tbody>
 </table>
 
@@ -1503,6 +1516,16 @@ target API.
   </dl>
   </td>
 </tr>
+<tr>
+  <td><code>CUDA_MPS_SUPPORT</code> (CUDA only)</td>
+  <td>Enable tweaks for running with Nvidia CUDA Multi-process services daemon</td>
+  <td>
+  <dl>
+    <dt><code>on</code></dt>
+    <dt><code>off</code> (default)</dt>
+  </dl>
+  </td>
+</tr>
 <tr>
   <td><code>BIN2C</code> (CUDA only)</td>
   <td>Path to bin2c executable, will automatically pick up the first one in your $PATH.</td>
diff --git a/cmake/etc/profile.d/lammps.csh.in b/cmake/etc/profile.d/lammps.csh.in
index def49bf75c..42f222d67c 100644
--- a/cmake/etc/profile.d/lammps.csh.in
+++ b/cmake/etc/profile.d/lammps.csh.in
@@ -1,2 +1,4 @@
-# set environment for LAMMPS executables to find potential files
+# set environment for LAMMPS and msi2lmp executables
+# to find potential and force field files
 if ( "$?LAMMPS_POTENTIALS" == 0 ) setenv LAMMPS_POTENTIALS @LAMMPS_POTENTIALS_DIR@
+if ( "$?MSI2LMP_LIBRARY" == 0 ) setenv MSI2LMP_LIBRARY @LAMMPS_FRC_FILES_DIR@
diff --git a/cmake/etc/profile.d/lammps.sh.in b/cmake/etc/profile.d/lammps.sh.in
index acd75fa0cf..c1967cb5b2 100644
--- a/cmake/etc/profile.d/lammps.sh.in
+++ b/cmake/etc/profile.d/lammps.sh.in
@@ -1,2 +1,5 @@
-# set environment for LAMMPS executables to find potential files
-export LAMMPS_POTENTIALS=${LAMMPS_POTENTIALS-@LAMMPS_POTENTIALS_DIR@}
+# set environment for LAMMPS and msi2lmp executables
+# to find potential and force field files
+LAMMPS_POTENTIALS=${LAMMPS_POTENTIALS-@LAMMPS_POTENTIALS_DIR@}
+MSI2LMP_LIBRARY=${MSI2LMP_LIBRARY-@LAMMPS_FRC_FILES_DIR@}
+export LAMMPS_POTENTIALS MSI2LMP_LIBRARY
diff --git a/cmake/presets/all_off.cmake b/cmake/presets/all_off.cmake
index b434796d7c..9d03be99ec 100644
--- a/cmake/presets/all_off.cmake
+++ b/cmake/presets/all_off.cmake
@@ -1,21 +1,17 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
+# preset that turns on all existing packages off. can be used to reset
+# an existing package selection without losing any other settings
 
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-PLUMED USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
+set(ALL_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
+        GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MISC MESSAGE MOLECULE
+        MPIIO MSCG OPT PERI POEMS PYTHON QEQ REPLICA RIGID SHOCK SNAP SPIN
+        SRD VORONOI
+        USER-ADIOS USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK
+        USER-COLVARS USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP
+        USER-H5MD USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
+        USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE USER-NETCDF USER-OMP
+        USER-PHONON USER-PLUMED USER-PTM USER-QMMM USER-QTB USER-QUIP
+        USER-REAXC USER-SCAFACOS USER-SDPD USER-SMD USER-SMTBQ USER-SPH
+        USER-TALLY USER-UEF USER-VTK USER-YAFF)
 
 foreach(PKG ${ALL_PACKAGES})
   set(PKG_${PKG} OFF CACHE BOOL "" FORCE)
diff --git a/cmake/presets/all_on.cmake b/cmake/presets/all_on.cmake
index 3a1100f337..2ff107975a 100644
--- a/cmake/presets/all_on.cmake
+++ b/cmake/presets/all_on.cmake
@@ -1,21 +1,19 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
+# preset that turns on all existing packages. using the combination
+# this preset followed by the nolib.cmake preset should configure a
+# LAMMPS binary, with as many packages included, that can be compiled
+# with just a working C++ compiler and an MPI library.
 
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-PLUMED USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
+set(ALL_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
+        GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MISC MESSAGE MOLECULE
+        MPIIO MSCG OPT PERI POEMS PYTHON QEQ REPLICA RIGID SHOCK SNAP SPIN
+        SRD VORONOI
+        USER-ADIOS USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK
+        USER-COLVARS USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP
+        USER-H5MD USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
+        USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE USER-NETCDF USER-OMP
+        USER-PHONON USER-PLUMED USER-PTM USER-QMMM USER-QTB USER-QUIP
+        USER-REAXC USER-SCAFACOS USER-SDPD USER-SMD USER-SMTBQ USER-SPH
+        USER-TALLY USER-UEF USER-VTK USER-YAFF)
 
 foreach(PKG ${ALL_PACKAGES})
   set(PKG_${PKG} ON CACHE BOOL "" FORCE)
diff --git a/cmake/presets/clang.cmake b/cmake/presets/clang.cmake
new file mode 100644
index 0000000000..828f359f54
--- /dev/null
+++ b/cmake/presets/clang.cmake
@@ -0,0 +1,17 @@
+# preset that will enable clang/clang++ with support for MPI and OpenMP (on Linux boxes)
+
+set(CMAKE_CXX_COMPILER "clang++" CACHE STRING "" FORCE)
+set(CMAKE_C_COMPILER "clang" CACHE STRING "" FORCE)
+set(CMAKE_CXX_FLAGS "-Wall -Wextra -g -O2 -DNDEBG" CACHE STRING "" FORCE)
+set(MPI_CXX "clang++" CACHE STRING "" FORCE)
+set(MPI_CXX_COMPILER "mpicxx" CACHE STRING "" FORCE)
+unset(HAVE_OMP_H_INCLUDE CACHE)
+
+set(OpenMP_C "clang" CACHE STRING "" FORCE)
+set(OpenMP_C_FLAGS "-fopenmp" CACHE STRING "" FORCE)
+set(OpenMP_C_LIB_NAMES "omp" CACHE STRING "" FORCE)
+set(OpenMP_CXX "clang++" CACHE STRING "" FORCE)
+set(OpenMP_CXX_FLAGS "-fopenmp" CACHE STRING "" FORCE)
+set(OpenMP_CXX_LIB_NAMES "omp" CACHE STRING "" FORCE)
+set(OpenMP_omp_LIBRARY "/usr/lib64/libomp.so" CACHE PATH "" FORCE)
+
diff --git a/cmake/presets/manual_selection.cmake b/cmake/presets/manual_selection.cmake
deleted file mode 100644
index 6db41b708c..0000000000
--- a/cmake/presets/manual_selection.cmake
+++ /dev/null
@@ -1,71 +0,0 @@
-set(PKG_ASPHERE OFF CACHE BOOL "" FORCE)
-set(PKG_BODY OFF CACHE BOOL "" FORCE)
-set(PKG_CLASS2 OFF CACHE BOOL "" FORCE)
-set(PKG_COLLOID OFF CACHE BOOL "" FORCE)
-set(PKG_COMPRESS OFF CACHE BOOL "" FORCE)
-set(PKG_CORESHELL OFF CACHE BOOL "" FORCE)
-set(PKG_DIPOLE OFF CACHE BOOL "" FORCE)
-set(PKG_GPU OFF CACHE BOOL "" FORCE)
-set(PKG_GRANULAR OFF CACHE BOOL "" FORCE)
-set(PKG_KIM OFF CACHE BOOL "" FORCE)
-set(PKG_KOKKOS OFF CACHE BOOL "" FORCE)
-set(PKG_KSPACE OFF CACHE BOOL "" FORCE)
-set(PKG_LATTE OFF CACHE BOOL "" FORCE)
-set(PKG_LIB OFF CACHE BOOL "" FORCE)
-set(PKG_MANYBODY OFF CACHE BOOL "" FORCE)
-set(PKG_MC OFF CACHE BOOL "" FORCE)
-set(PKG_MEAM OFF CACHE BOOL "" FORCE)
-set(PKG_MISC OFF CACHE BOOL "" FORCE)
-set(PKG_MOLECULE OFF CACHE BOOL "" FORCE)
-set(PKG_MPIIO OFF CACHE BOOL "" FORCE)
-set(PKG_MSCG OFF CACHE BOOL "" FORCE)
-set(PKG_OPT OFF CACHE BOOL "" FORCE)
-set(PKG_PERI OFF CACHE BOOL "" FORCE)
-set(PKG_POEMS OFF CACHE BOOL "" FORCE)
-set(PKG_PYTHOFF OFF CACHE BOOL "" FORCE)
-set(PKG_QEQ OFF CACHE BOOL "" FORCE)
-set(PKG_REAX OFF CACHE BOOL "" FORCE)
-set(PKG_REPLICA OFF CACHE BOOL "" FORCE)
-set(PKG_RIGID OFF CACHE BOOL "" FORCE)
-set(PKG_SHOCK OFF CACHE BOOL "" FORCE)
-set(PKG_SNAP OFF CACHE BOOL "" FORCE)
-set(PKG_SRD OFF CACHE BOOL "" FORCE)
-set(PKG_VOROFFOI OFF CACHE BOOL "" FORCE)
-
-set(PKG_USER OFF CACHE BOOL "" FORCE)
-set(PKG_USER-ATC OFF CACHE BOOL "" FORCE)
-set(PKG_USER-AWPMD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-BOCS OFF CACHE BOOL "" FORCE)
-set(PKG_USER-CGDNA OFF CACHE BOOL "" FORCE)
-set(PKG_USER-CGSDK OFF CACHE BOOL "" FORCE)
-set(PKG_USER-COLVARS OFF CACHE BOOL "" FORCE)
-set(PKG_USER-DIFFRACTIOFF OFF CACHE BOOL "" FORCE)
-set(PKG_USER-DPD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-DRUDE OFF CACHE BOOL "" FORCE)
-set(PKG_USER-EFF OFF CACHE BOOL "" FORCE)
-set(PKG_USER-FEP OFF CACHE BOOL "" FORCE)
-set(PKG_USER-H5MD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-INTEL OFF CACHE BOOL "" FORCE)
-set(PKG_USER-LB OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MANIFOLD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MEAMC OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MESO OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MGPT OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MISC OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MOFFF OFF CACHE BOOL "" FORCE)
-set(PKG_USER-MOLFILE OFF CACHE BOOL "" FORCE)
-set(PKG_USER-NETCDF OFF CACHE BOOL "" FORCE)
-set(PKG_USER-OMP OFF CACHE BOOL "" FORCE)
-set(PKG_USER-PHONON OFF CACHE BOOL "" FORCE)
-set(PKG_USER-PLUMED OFF CACHE BOOL "" FORCE)
-set(PKG_USER-QMMM OFF CACHE BOOL "" FORCE)
-set(PKG_USER-QTB OFF CACHE BOOL "" FORCE)
-set(PKG_USER-QUIP OFF CACHE BOOL "" FORCE)
-set(PKG_USER-REAXC OFF CACHE BOOL "" FORCE)
-set(PKG_USER-SDPD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-SMD OFF CACHE BOOL "" FORCE)
-set(PKG_USER-SMTBQ OFF CACHE BOOL "" FORCE)
-set(PKG_USER-SPH OFF CACHE BOOL "" FORCE)
-set(PKG_USER-TALLY OFF CACHE BOOL "" FORCE)
-set(PKG_USER-UEF OFF CACHE BOOL "" FORCE)
-set(PKG_USER-VTK OFF CACHE BOOL "" FORCE)
diff --git a/cmake/presets/mingw-cross.cmake b/cmake/presets/mingw-cross.cmake
new file mode 100644
index 0000000000..b53e5a7b93
--- /dev/null
+++ b/cmake/presets/mingw-cross.cmake
@@ -0,0 +1,17 @@
+set(WIN_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
+                 GRANULAR KSPACE MANYBODY MC MISC MOLECULE OPT PERI POEMS QEQ
+                 REPLICA RIGID SHOCK SNAP SPIN SRD VORONOI USER-ATC USER-AWPMD
+                 USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS USER-DIFFRACTION
+                 USER-DPD USER-DRUDE USER-EFF USER-FEP USER-INTEL USER-MANIFOLD
+                 USER-MEAMC USER-MESO USER-MISC USER-MOFFF USER-MOLFILE USER-OMP
+                 USER-PHONON USER-PTM USER-QTB USER-REAXC USER-SDPD USER-SMD
+                 USER-SMTBQ USER-SPH USER-TALLY USER-UEF USER-YAFF)
+
+foreach(PKG ${WIN_PACKAGES})
+  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
+endforeach()
+
+set(DOWNLOAD_VORO ON CACHE BOOL "" FORCE)
+set(DOWNLOAD_EIGEN3 ON CACHE BOOL "" FORCE)
+set(LAMMPS_MEMALIGN "0" CACHE STRING "" FORCE)
+set(INTEL_LRT_MODE "none" CACHE STRING "" FORCE)
diff --git a/cmake/presets/minimal.cmake b/cmake/presets/minimal.cmake
new file mode 100644
index 0000000000..e9ce6d6103
--- /dev/null
+++ b/cmake/presets/minimal.cmake
@@ -0,0 +1,8 @@
+# preset that turns on just a few, frequently used packages
+# this will be compiled quickly and handle a lot of common inputs.
+
+set(ALL_PACKAGES KSPACE MANYBODY MOLECULE RIGID)
+
+foreach(PKG ${ALL_PACKAGES})
+  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
+endforeach()
diff --git a/cmake/presets/most.cmake b/cmake/presets/most.cmake
new file mode 100644
index 0000000000..35ad7ba55c
--- /dev/null
+++ b/cmake/presets/most.cmake
@@ -0,0 +1,15 @@
+# preset that turns on a wide range of packages, some of which require
+# external libraries. Compared to all_on.cmake some more unusual packages
+# are removed. The resulting binary should be able to run most inputs.
+
+set(ALL_PACKAGES ASPHERE CLASS2 COLLOID CORESHELL DIPOLE
+        GRANULAR KSPACE MANYBODY MC MISC MOLECULE OPT PERI
+        PYTHON QEQ REPLICA RIGID SHOCK SRD VORONOI
+        USER-CGDNA USER-CGSDK USER-COLVARS USER-DIFFRACTION USER-DPD
+        USER-DRUDE USER-FEP USER-MEAMC USER-MESO
+        USER-MISC USER-MOFFF USER-OMP USER-PLUMED USER-PHONON USER-REAXC
+        USER-SPH USER-SMD USER-UEF USER-YAFF)
+
+foreach(PKG ${ALL_PACKAGES})
+  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
+endforeach()
diff --git a/cmake/presets/nolib.cmake b/cmake/presets/nolib.cmake
index 4c02fb6210..c0968a8d82 100644
--- a/cmake/presets/nolib.cmake
+++ b/cmake/presets/nolib.cmake
@@ -1,21 +1,10 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
+# preset that turns off all packages that require some form of external
+# library or special compiler (fortran or cuda) or equivalent.
 
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-PLUMED USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
+set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MPIIO MSCG PYTHON
+        VORONOI USER-ADIOS USER-ATC USER-AWPMD USER-H5MD USER-LB
+        USER-MOLFILE USER-NETCDF USER-PLUMED USER-QMMM USER-QUIP
+        USER-SCAFACOS USER-SMD USER-VTK)
 
 foreach(PKG ${PACKAGES_WITH_LIB})
   set(PKG_${PKG} OFF CACHE BOOL "" FORCE)
diff --git a/cmake/presets/std.cmake b/cmake/presets/std.cmake
deleted file mode 100644
index 4176aba44e..0000000000
--- a/cmake/presets/std.cmake
+++ /dev/null
@@ -1,22 +0,0 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
-
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
-
-foreach(PKG ${STANDARD_PACKAGES})
-  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
-endforeach()
diff --git a/cmake/presets/std_nolib.cmake b/cmake/presets/std_nolib.cmake
deleted file mode 100644
index aa067f2ba0..0000000000
--- a/cmake/presets/std_nolib.cmake
+++ /dev/null
@@ -1,26 +0,0 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
-
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
-
-foreach(PKG ${STANDARD_PACKAGES})
-  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
-endforeach()
-
-foreach(PKG ${PACKAGES_WITH_LIB})
-  set(PKG_${PKG} OFF CACHE BOOL "" FORCE)
-endforeach()
diff --git a/cmake/presets/user.cmake b/cmake/presets/user.cmake
deleted file mode 100644
index af606203e9..0000000000
--- a/cmake/presets/user.cmake
+++ /dev/null
@@ -1,22 +0,0 @@
-set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS CORESHELL DIPOLE GPU
-                      GRANULAR KIM KOKKOS KSPACE LATTE MANYBODY MC MEAM MISC
-                      MOLECULE MPIIO MSCG OPT PERI POEMS
-                      PYTHON QEQ REAX REPLICA RIGID SHOCK SNAP SRD VORONOI)
-
-set(USER_PACKAGES USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-CGSDK USER-COLVARS
-                  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
-                  USER-INTEL USER-LB USER-MANIFOLD USER-MEAMC USER-MESO
-                  USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-                  USER-NETCDF USER-OMP USER-PHONON USER-QMMM USER-QTB
-                  USER-QUIP USER-REAXC USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-                  USER-UEF USER-VTK)
-
-set(PACKAGES_WITH_LIB COMPRESS GPU KIM KOKKOS LATTE MEAM MPIIO MSCG POEMS PYTHON REAX VORONOI
-                      USER-ATC USER-AWPMD USER-COLVARS USER-H5MD USER-LB USER-MOLFILE
-                      USER-NETCDF USER-PLUMED USER-QMMM USER-QUIP USER-SMD USER-VTK)
-
-set(ALL_PACKAGES ${STANDARD_PACKAGES} ${USER_PACKAGES})
-
-foreach(PKG ${USER_PACKAGES})
-  set(PKG_${PKG} ON CACHE BOOL "" FORCE)
-endforeach()
diff --git a/doc/Makefile b/doc/Makefile
index 044e358bd5..fa60aa3698 100644
--- a/doc/Makefile
+++ b/doc/Makefile
@@ -116,6 +116,13 @@ mobi: epub
 	@echo "Conversion finished. The MOBI manual file is created."
 
 pdf: $(OBJECTS) $(ANCHORCHECK)
+	@(\
+		cd src/Developer; \
+		pdflatex developer; \
+		pdflatex developer; \
+		mv developer.pdf ../../Developer.pdf; \
+		cd ../../; \
+	)
 	@(\
                 . $(VENV)/bin/activate ;\
                 cp -r src/* $(RSTDIR)/ ;\
@@ -135,14 +142,7 @@ pdf: $(OBJECTS) $(ANCHORCHECK)
 	  make && \
 	  make && \
 	  mv LAMMPS.pdf ../Manual.pdf && \
-	  cd ../; 
-	@(\
-		cd src/Developer; \
-		pdflatex developer; \
-		pdflatex developer; \
-		mv developer.pdf ../../Developer.pdf; \
-		cd ../../; \
-	)
+	  cd ../;
 	@rm -rf latex/_sources
 	@rm -rf latex/PDF
 	@rm -rf latex/USER
@@ -211,7 +211,7 @@ $(VENV):
 	@( \
 		$(VIRTUALENV) -p $(PYTHON) $(VENV); \
 		. $(VENV)/bin/activate; \
-		pip install Sphinx; \
+		pip install Sphinx==1.7.6; \
 		deactivate;\
 	)
 
diff --git a/doc/lammps.1 b/doc/lammps.1
index d49650bfaa..4686198fef 100644
--- a/doc/lammps.1
+++ b/doc/lammps.1
@@ -1,40 +1,259 @@
-.TH LAMMPS "2018-08-22"
+.TH LAMMPS "11 April 2019" "2019-04-11"
 .SH NAME
 .B LAMMPS
 \- Molecular Dynamics Simulator.
 
 .SH SYNOPSIS
-.B lmp 
--in in.file
+.B lmp
+\-in <input file> [OPTIONS] ...
 
 or
 
-mpirun \-np 2 
-.B lmp 
--in in.file
+mpirun \-np 2
+.B lmp
+<input file> [OPTIONS] ...
+
+or
+
+.B lmp
+\-r2data file.restart file.data
 
 .SH DESCRIPTION
-.B LAMMPS 
-LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale 
-Atomic/Molecular Massively Parallel Simulator. LAMMPS has potentials for soft 
-materials (biomolecules, polymers) and solid-state materials (metals, 
-semiconductors) and coarse-grained or mesoscopic systems. It can be used to 
-model atoms or, more generically, as a parallel particle simulator at the 
+.B LAMMPS
+is a classical molecular dynamics code, and an acronym for \fBL\fRarge-scale
+\fBA\fRtomic/\fBM\fRolecular \fBM\fRassively \fBP\fRarallel \fBS\fRimulator.
+.B LAMMPS
+has potentials for soft
+materials (bio-molecules, polymers) and solid-state materials (metals,
+semiconductors) and coarse-grained or mesoscopic systems. It can be used to
+model atoms or, more generically, as a parallel particle simulator at the
 atomic, meso, or continuum scale.
 
-See http://lammps.sandia.gov/ for documentation.
+See https://lammps.sandia.gov/ for more information and documentation.
+
+.SH EXECUTABLE NAME
+The
+.B LAMMPS
+executable can have different names depending on how it was configured,
+compiled and installed. It will be either
+.B lmp
+or
+.B lmp_<machine name>.
+The <machine name> suffix corresponds to the (machine specific) makefile
+used to compile
+.B LAMMPS
+when using the conventional build process. When building
+.B LAMMPS
+using
+.B CMake
+this <machine name> parameter can be chosen arbitrarily at configuration
+time, but more common is to just use
+.B lmp
+without a suffix. In this manpage we will use
+.B lmp
+to represent any of those names.
 
 .SH OPTIONS
-See https://lammps.sandia.gov/doc/Run_options.html for details on
-command-line options.
 
-.SH COPYRIGHT 
-© 2003--2018 Sandia Corporation
+.TP
+\fB\-h\fR or \fB\-help\fR
+Print a brief help summary and a list of settings and options compiled
+into this executable. It also explicitly lists all LAMMPS styles
+(atom_style, fix, compute, pair_style, bond_style, etc) available in
+the specific executable. This can tell you if the command you want to
+use was included via the appropriate package at compile time.
+LAMMPS will print the info and immediately exit if this switch is used.
+.TP
+\fB\-e\fR or \fB\-echo\fR
+Set the style of command echoing. The style can be
+.B none
+or
+.B screen
+or
+.B log
+or
+.B both.
+Depending on the style, each command read from the input script will
+be echoed to the screen and/or logfile. This can be useful to figure
+out which line of your script is causing an input error.
+The default value is
+.B log.
+.TP
+\fB\-i <input file>\fR or \fB\-in <input file>\fR
+Specify a file to use as an input script. If it is not specified,
+LAMMPS reads its script from standard input. This is a required
+switch when running LAMMPS in multi-partition mode.
+.TP
+\fB\-k on/off [keyword value]\fR or \fB\-kokkos on/off [keyword value]\fR
+Enable or disable general KOKKOS support, as provided by the KOKKOS
+package.  Even if LAMMPS is built with this package, this switch must
+be set to \fBon\fR to enable running with KOKKOS-enabled styles. More
+details on this switch and its optional keyword value pairs are discussed
+at: https://lammps.sandia.gov/doc/Run_options.html
+.TP
+\fB\-l <log file>\fR or \fB\-log <log file>\fR
+Specify a log file for LAMMPS to write status information to.
+The default value is "log.lammps". If the file name "none" is used,
+\fBLAMMPS\fR will not write a log file. In multi-partition mode only
+some high-level all-partition information is written to the "<log file>"
+file, the remainder is written in a per-partition file "<log file>.N"
+with "N" being the respective partition number, unless overridden
+by the \-plog flag (see below).
+.TP
+\fB\-m <number>\fR or \fB\-mpicolor <number>\fR
+If used, this must be the first command-line argument after the
+.B LAMMPS
+executable name. It is only used when
+.B LAMMPS
+is launched by an mpirun command which also launches one or more
+other executable(s) at the same time.
+.B LAMMPS
+and the other executable(s) perform an MPI_Comm_split(), each with
+their own different colors, to split the MPI_COMM_WORLD communicator
+for each executable to the subset of processors they are supposed to
+be actually running on. Currently, this is only used in
+.B LAMMPS
+to perform client/server messaging with another application.
+.B LAMMPS
+can act as either a client or server (or both).
+.TP
+\fB\-nc\fR or \fB\-nocite\fR
+Disable writing the "log.cite" file which is normally written to
+list references for specific cite-able features used during a
+.B LAMMPS
+run.
+.TP
+\fB\-pk <style> [options]\fR or \fB\-package <style> [options]\fR
+Invoke the \fBpackage\R command with <style> and optional arguments.
+The syntax is the same as if the command appeared in an input script.
+For example "-pk gpu 2" is the same as "package gpu 2" in the input
+script. The possible styles and options are discussed in the
+.B LAMMPS
+manual for the "package" command. This switch can be used multiple
+times, e.g. to set options for the USER-INTEL and USER-OMP packages
+when used together. Along with the "-sf" or "-suffix" switch, this
+is a convenient mechanism for invoking accelerator packages and their
+options without having to edit an input script.
+.TP
+\fB\-p\fR or \fB\-partition\fR
+Invoke
+.B LAMMPS
+in multi-partition mode. Without this,
+.B LAMMPS
+uses all P processors allocated via MPI to run a single simulation.
+If this switch is used, the P processors are split into separate
+partitions and each partition runs its own simulation. The arguments
+to the switch specify the number of processors in each partition.
+Arguments of the form "MxN" mean M partitions, each with N processors.
+Arguments of the form "N" mean a single partition with N processors.
+The sum of processors in all partitions must be equal P. Thus the
+command “-partition 8x2 4 5” has 10 partitions and runs on a total
+of 25 processors.  Running with multiple partitions is required for
+multi-replica simulations, where each replica runs on on one or more
+few processors.
+.TP
+\fB\-pl <basename>\fR or \fB\-plog <basename>\fR
+Specify the base name for the per-partition log files in multi-partition
+runs, where partition N writes log information to <basename>.N.
+If basename is set to "none", then no per-partition log files are created.
+This overrides the name specified in the \-log command-line option.
+.TP
+\fB\-ps <basename>\fR or \fB\-pscreen <basename>\fR
+Specify the base name for the per-partition screen files in multi-partition
+runs, where partition N writes screen output to <basename>.N.
+If basename is set to "none", then no per-partition screen files are created.
+The default value is "screen" or whatever is set by the \-screen flag.
+.TP
+\fB\-r2data <restart file> [remap] <data file>\fR or
+\fB\-restart2data <restart file> [remap] <data file>\fR
+Convert <restart file> previously written by
+.B LAMMPS
+into a data file and immediately exit. This option has replaced the
+external restart2data executable. Following <restart file>
+argument, the optional word "remap" may be used. This has the
+same effect like adding it to a "read_restart" command.
+The syntax following the <data file> name is identical to the
+arguments of the "write_data" command. See the
+.B LAMMPS
+manual for details on either of the two commands.
+.TP
+\fB\-r2dump <restart file> [remap] <dump file>\fR or
+\fB\-restart2dump <restart file> [remap] <dump file>\fR
+Convert <restart file> previously written by
+.B LAMMPS
+into a dump file and immediately exit. Following <restart file>
+argument, the optional word "remap" may be used. This has the
+same effect like adding it to a "read_restart" command.
+The syntax following the <dump file> name is identical to the
+arguments of the "dump" command. See the
+.B LAMMPS
+manual for details on either of the two commands.
+.TP
+\fB\-sc <file name>\fR or \fB\-screen <file name>\fR
+Specify a file for
+.B LAMMPS
+to write its screen information to. By default, this will be
+the standard output. If <file name> is "none", (most) screen
+output will be suppressed.  In multi-partition mode only
+some high-level all-partition information is written to the
+screen or "<file name>" file, the remainder is written in a
+per-partition file "screen.N" or "<file name>.N" 
+with "N" being the respective partition number, and unless
+overridden by the \-pscreen flag (see above).
+.TP
+\fB\-sf <suffix>\fR or \fB\-suffix <suffix>\fR
+Use variants of various styles in the input, if they exist. This is
+achieved by transparently trying to convert a style named <my/style>
+into <my/style/suffix> if that latter style exists, but otherwise
+fall back to the former. The most useful suffixes are  "gpu",
+"intel", "kk", "omp", "opt", or "hybrid". These refer to styles from
+optional packages that LAMMPS can be built with. The hybrid suffix is
+special, as it enables, having two suffixes tried (e.g. first "intel"
+and then "omp") and thus requires two arguments. Along with the
+"-package" command-line switch, this is a convenient mechanism for
+invoking styles from accelerator packages and setting their options
+without having to edit an input script.
+
+See https://lammps.sandia.gov/doc/Run_options.html for additional
+details and discussions on command-line options.
+
+.SH LAMMPS BASICS
+LAMMPS executes by reading commands from a input script (text file),
+one line at a time.  When the input script ends, LAMMPS exits.  Each
+command causes LAMMPS to take some action.  It may set or change an
+internal, read and parse a file, or run a simulation.  Most commands
+have default settings, which means you only need to use the command
+if you wish to change the default.
+
+The ordering of commands in an input script is usually not very important
+unless a command like "run" is encountered, which starts some calculation
+using the current internal state. Also, if a "pair_style" or "bond_style"
+other similar style command is issued that has a different name from what
+was previously active, it will replace the previous style and wipe out
+all corresponding "pair_coeff" or "bond_coeff" or equivalent settings.
+Some commands are only valid when they follow other commands.  For
+example you cannot set the temperature of a group of atoms until atoms
+have been defined and a group command is used to define which atoms
+belong to the group of a given name. Sometimes command B will use values
+that can be set by command A. This means command A must precede command
+B in the input to have the desired effect. Some commands must be issued
+.B before
+the simulation box is defined and others can only be issued
+.B after.
+Many input script errors are detected by
+.B LAMMPS
+and an ERROR or WARNING message is printed.  The documentation for
+each command lists restrictions on how the command can be used, and
+the chapter on errors in the
+.B LAMMPS
+manual gives some additional information about error messages, if possible.
+
+.SH COPYRIGHT
+© 2003--2019 Sandia Corporation
 
 This package is free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2 of the License, or
-(at your option) any later version.
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
 
 This package is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of
diff --git a/doc/msi2lmp.1 b/doc/msi2lmp.1
new file mode 100644
index 0000000000..08a442e1de
--- /dev/null
+++ b/doc/msi2lmp.1
@@ -0,0 +1,111 @@
+.TH MSI2LMP "v3.9.9" "2018-11-05"
+.SH NAME
+.B MSI2LMP
+\- Converter for Materials Studio files to LAMMPS
+
+.SH SYNOPSIS
+.B msi2lmp
+<ROOTNAME> [-class <I|1|II|2|O|0>] [-frc <path to frc file>] [-print #] [-ignore] [-nocenter] [-oldstyle] [-shift <x> <y> <z>]
+
+.SH DESCRIPTION
+.PP
+.B MSI2LMP
+is a tool bundled with LAMMPS to aide in the conversion of simulation
+inputs from Biovia's Materials Studio software for use with LAMMPS.
+It is a standalone program that generates a LAMMPS data file based on
+the information in an MS .car file (atom coordinates), an .mdf file
+(molecular topology and atom types) and an .frc (forcefield parameters)
+file.  The .car and .mdf files are specific to a molecular system while
+the .frc file is specific to a forcefield (variant).  The only coherency
+needed between .frc and .car/.mdf files are the atom types.
+.PP
+
+.SH OPTIONS
+.TP
+\fB\<ROOTNAME>\fR
+This has to be the first argument and is a
+.B mandatory
+argument. It defines the root of the file names; i.e. for a
+.B <ROOTNAME>
+of benzene, you have to provide the files 'benzene.car' and 'benzene.mdf'
+in the current working directory.
+.B msi2lmp
+will then read and process those files according to its remaining settings.
+All other settins are optional and have defaults as listed.
+.TP
+\fB\-c <I,1,II,2,O,0>\fR, \fB\-class <I,1,II,2,O,0>\fR
+The \-c or \-class option selects the force field class, i.e which pair
+styles and bond styles and so on are required in the LAMMPS input file.
+Class I or class 1 uses similar combination of functional forms as Amber
+and Charmm force field and support the force fields 
+.B cvff
+and
+.B clayff.
+Class II or class 2 corresponds to the more complex force fields
+.B COMPASS
+and
+.B pcff.
+Class O or class 0 finally is an experimental and incomplete extension
+and supports generating output for
+.B OPLS-AA
+.TP
+\fB\-f <ffname>\fR, \fB\-frc <ffname>\fR
+The \-c or \-frc option allows the selection of the force field parameter
+file
+.B<ffname>.frc.
+Valid names for <ffname> with this distribution are: cvff, clayff, cvff_aug,
+pcff, compass_published, cff91, and oplsaa. If the argument is a pathname,
+i.e. it starts with a '.' or a '/', then this absolute path is used to read
+the force field, otherwise
+.B msi2lmp
+will look in the folder pointed to by the environment variable
+$MSI2LMP_LIBRARY. If the variable is not set, then it will look in the current
+directory. The extension '.frc' is appended, if missing.
+Default is to look for the cvff.frc force field file.
+.TP
+\fB\-p <loglevel>\fR, \fB\-print <loglevel>\fR,
+Selects the amount of information messages about the progress of the
+conversion printed to the screen.
+.B <loglevel>
+can be a number from 0 (silent except for errors) to 3 (very detailed).
+.TP
+\fB\-i\fR, \fB\-ignore\fR,
+Ignore errors about missing parameters and use 0.0 for the respective
+force constants making these no-ops. Is correct to be used for a few
+molecules and settings, but often an indication, that either the atom
+type assignment have errors, or the force field file is missing entries.
+.TP
+\fB\-n\fR, \fB\-nocenter\fR,
+Do not center the box around the (geometrical) center of the atoms,
+but around the origin. Default is to recenter.
+.TP
+\fB\-o\fR, \fB\-oldstyle\fR,
+Write out a data file without style hint comments to be compatible
+with old LAMMPS versions. Default is to write out those comments.
+.TP
+\fB-s <x> <y> <z>\fR, \fB-shift <x> <y> <z>\fR,
+Shift the entire system (box and coordinates) by a vector
+(default: 0.0 0.0 0.0).
+.TP
+
+.SH EXAMPLES
+
+msi2lmp benzene -c 2 -p 1 -f ../frc_files/pcff.frc
+
+msi2lmp benzene-class1 -c I
+
+msi2lmp decane -c 0 -f oplsaa
+
+
+.SH COPYRIGHT
+© 2003--2019 Sandia Corporation
+
+This package is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
+
+This package is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
diff --git a/doc/src/Build_cmake.txt b/doc/src/Build_cmake.txt
index 5c29e11280..265c16e3d4 100644
--- a/doc/src/Build_cmake.txt
+++ b/doc/src/Build_cmake.txt
@@ -28,7 +28,7 @@ Makefile(s). Example:
 
 cd lammps                        # change to the LAMMPS distribution directory
 mkdir build; cd build            # create a new directory (folder) for build
-cmake ../cmake \[options ...\]   # configuration with (command-line) cmake
+cmake \[options ...\] ../cmake     # configuration with (command-line) cmake
 make                             # compilation :pre
 
 The cmake command will detect available features, enable selected
@@ -41,7 +41,8 @@ If your machine has multiple CPU cores (most do these days), using a
 command like "make -jN" (with N being the number of available local
 CPU cores) can be much faster.  If you plan to do development on
 LAMMPS or need to re-compile LAMMPS repeatedly, installation of the
-ccache (= Compiler Cache) software may speed up compilation even more.
+ccache (= Compiler Cache) software may speed up repeated compilation
+even more.
 
 After compilation, you can optionally copy the LAMMPS executable and
 library into your system folders (by default under $HOME/.local) with:
@@ -108,7 +109,8 @@ command-line options.  Several useful ones are:
 -D CMAKE_BUILD_TYPE=type      # type = Release or Debug
 -G output                     # style of output CMake generates
 -DVARIABLE=value              # setting for a LAMMPS feature to enable
--D VARIABLE=value             # ditto, but cannot come after CMakeLists.txt dir :pre
+-D VARIABLE=value             # ditto, but cannot come after CMakeLists.txt dir
+-C path/to/preset/file        # load some CMake settings before configuring :pre
 
 All the LAMMPS-specific -D variables that a LAMMPS build supports are
 described on the pages linked to from the "Build"_Build.html doc page.
diff --git a/doc/src/Build_extras.txt b/doc/src/Build_extras.txt
index cbbd9db2f3..17d18243f2 100644
--- a/doc/src/Build_extras.txt
+++ b/doc/src/Build_extras.txt
@@ -82,17 +82,19 @@ which GPU hardware to build for.
 
 [CMake build]:
 
--D GPU_API=value      # value = opencl (default) or cuda
--D GPU_PREC=value     # precision setting
-                      # value = double or mixed (default) or single
--D OCL_TUNE=value     # hardware choice for GPU_API=opencl
-                      # generic (default) or intel (Intel CPU) or fermi, kepler, cypress (NVIDIA)
--D GPU_ARCH=value     # primary GPU hardware choice for GPU_API=cuda
-                      # value = sm_XX, see below
-                      # default is Cuda-compiler dependent, but typically sm_20
--D CUDPP_OPT=value    # optimization setting for GPU_API=cuda
-                      # enables CUDA Performance Primitives Optimizations
-                      # yes (default) or no :pre
+-D GPU_API=value          # value = opencl (default) or cuda
+-D GPU_PREC=value         # precision setting
+                          # value = double or mixed (default) or single
+-D OCL_TUNE=value         # hardware choice for GPU_API=opencl
+                          # generic (default) or intel (Intel CPU) or fermi, kepler, cypress (NVIDIA)
+-D GPU_ARCH=value         # primary GPU hardware choice for GPU_API=cuda
+                          # value = sm_XX, see below
+                          # default is Cuda-compiler dependent, but typically sm_20
+-D CUDPP_OPT=value        # optimization setting for GPU_API=cuda
+                          # enables CUDA Performance Primitives Optimizations
+                          # value = yes (default) or no
+-D CUDA_MPS_SUPPORT=value # enables some tweaks required to run with active nvidia-cuda-mps daemon
+                          # value = yes or no (default) :pre
 
 GPU_ARCH settings for different GPU hardware is as follows:
 
@@ -169,16 +171,18 @@ used to build the GPU library.
 
 KIM package :h4,link(kim)
 
-To build with this package, the KIM library must be downloaded and
-built on your system.  It must include the KIM models that you want to
-use with LAMMPS.
+To build with this package, the KIM library with API v2 must be downloaded
+and built on your system.  It must include the KIM models that you want to
+use with LAMMPS. If you want to use the "kim_query"_kim_query.html
+command, you also need to have libcurl installed with the matching
+development headers and the curl-config tool.
 
 Note that in LAMMPS lingo, a KIM model driver is a pair style
 (e.g. EAM or Tersoff).  A KIM model is a pair style for a particular
 element or alloy and set of parameters, e.g. EAM for Cu with a
-specific EAM potential file.  Also note that installing the KIM API
-library with all its models, may take around 30 min to build.  Of
-course you only need to do that once.
+specific EAM potential file.  Also note that downloading and installing
+the KIM API library with all its models, may take a long time (10s of
+minutes to hours) to build.  Of course you only need to do that once.
 
 See the list of KIM model drivers here:
 https://openkim.org/browse/model-drivers/alphabetical
@@ -193,7 +197,7 @@ https://openkim.org/browse/models/by-model-drivers
 If DOWNLOAD_KIM is set, the KIM library will be downloaded and built
 inside the CMake build directory.  If the KIM library is already on
 your system (in a location CMake cannot find it), set the PKG_CONFIG_PATH
-environment variable so that libkim-api-v2 can be found.
+environment variable so that libkim-api can be found.
 
 [Traditional make]:
 
@@ -855,23 +859,34 @@ file.
 USER-INTEL package :h4,link(user-intel)
 
 To build with this package, you must choose which hardware you want to
-build for, either Intel CPUs or Intel KNLs.  You should also typically
-"install the USER-OMP package"_#user-omp, as it can be used in tandem
-with the USER-INTEL package to good effect, as explained on the "Speed
-intel"_Speed_intel.html doc page.
+build for, either x86 CPUs or Intel KNLs in offload mode.  You should
+also typically "install the USER-OMP package"_#user-omp, as it can be
+used in tandem with the USER-INTEL package to good effect, as explained
+on the "Speed intel"_Speed_intel.html doc page.
 
 [CMake build]:
 
 -D INTEL_ARCH=value     # value = cpu (default) or knl
--D BUILD_OMP=yes        # also required to build with the USER-INTEl package :pre
+-D INTEL_LRT_MODE=value # value = threads, none, or c++11 :pre
 
-Requires an Intel compiler as well as the Intel TBB and MKL libraries.
+In Long-range thread mode (LRT) a modified verlet style is used, that
+operates the Kspace calculation in a separate thread concurrently to
+other calculations. This has to be enabled in the "package intel"_package.html
+command at runtime. With the setting "threads" it used the pthreads
+library, while c++11 will use the built-in thread support of C++11
+compilers. The option "none" skips compilation of this feature. The
+default is to use "threads" if pthreads is available and otherwise "none".
+
+Best performance is achieved with Intel hardware, Intel compilers, as well as
+the Intel TBB and MKL libraries. However, the code also compiles, links, and
+runs with other compilers and without TBB and MKL.
 
 [Traditional make]:
 
 Choose which hardware to compile for in Makefile.machine via the
 following settings.  See src/MAKE/OPTIONS/Makefile.intel_cpu* and
-Makefile.knl files for examples.
+Makefile.knl files for examples. and src/USER-INTEL/README for
+additional information.
 
 For CPUs:
 
@@ -893,7 +908,17 @@ USER-MOLFILE package :h4,link(user-molfile)
 
 [CMake build]:
 
-No additional settings are needed besides "-D PKG_USER-MOLFILE=yes".
+-D MOLFILE_INCLUDE_DIRS=path   # (optional) path where VMD molfile plugin headers are installed
+-D PKG_USER-MOLFILE=yes     :pre
+
+
+Using "-D PKG_USER-MOLFILE=yes" enables the package, and setting
+"-D MOLFILE_INCLUDE DIRS" allows to provide a custom location for
+the molfile plugin header files. These should match the ABI of the
+plugin files used, and thus one typically sets them to include
+folder of the local VMD installation in use. LAMMPS ships with a
+couple of default header files that correspond to a popular VMD
+version, usually the latest release.
 
 [Traditional make]:
 
@@ -902,7 +927,11 @@ loading library libdl.a that is typically present on all systems.  It
 is required for LAMMPS to link with this package.  If the setting is
 not valid for your system, you will need to edit the Makefile.lammps
 file.  See lib/molfile/README and lib/molfile/Makefile.lammps for
-details.
+details. It is also possible to configure a different folder with
+the VMD molfile plugin header files. LAMMPS ships with a couple of
+default headers, but these are not compatible with all VMD versions,
+so it is often best to change this setting to the location of the
+same include files of the local VMD installation in use.
 
 :line
 
diff --git a/doc/src/Build_package.txt b/doc/src/Build_package.txt
index c5eca96edb..401f53f638 100644
--- a/doc/src/Build_package.txt
+++ b/doc/src/Build_package.txt
@@ -149,26 +149,41 @@ system. Using these files you can enable/disable portions of the
 available packages in LAMMPS. If you need a custom preset you can take
 one of them as a starting point and customize it to your needs.
 
-cmake -C ../cmake/presets/all_on.cmake \[OPTIONS\] ../cmake | enable all packages
-cmake -C ../cmake/presets/all_off.cmake \[OPTIONS\] ../cmake | disable all packages
-cmake -C ../cmake/presets/std.cmake \[OPTIONS\] ../cmake | enable standard packages
-cmake -C ../cmake/presets/user.cmake \[OPTIONS\] ../cmake | enable user packages
-cmake -C ../cmake/presets/std_nolib.cmake \[OPTIONS\] ../cmake | enable standard packages that do not require extra libraries
-cmake -C ../cmake/presets/nolib.cmake \[OPTIONS\] ../cmake | disable all packages that do not require extra libraries
-cmake -C ../cmake/presets/manual_selection.cmake \[OPTIONS\] ../cmake | example of how to create a manual selection of packages :tb(s=|,a=l)
+cmake -C ../cmake/presets/all_on.cmake  \[OPTIONS\] ../cmake |
+      enable all packages |
+cmake -C ../cmake/presets/all_off.cmake \[OPTIONS\] ../cmake |
+      disable all packages |
+cmake -C ../cmake/presets/minimal.cmake \[OPTIONS\] ../cmake |
+      enable just a few core packages |
+cmake -C ../cmake/presets/most.cmake    \[OPTIONS\] ../cmake |
+      enable most common packages |
+cmake -C ../cmake/presets/nolib.cmake   \[OPTIONS\] ../cmake |
+      disable packages that do require extra libraries or tools |
+cmake -C ../cmake/presets/clang.cmake   \[OPTIONS\] ../cmake |
+      change settings to use the Clang compilers by default |
+cmake -C ../cmake/presets/mingw.cmake \[OPTIONS\] ../cmake |
+      enable all packages compatible with MinGW compilers :tb(c=2,s=|,a=l)
 
 NOTE: Running cmake this way manipulates the variable cache in your
-current build directory. You can combine presets and options with
-multiple cmake runs.
+current build directory. You can combine multiple presets and options
+in a single cmake run, or change settings incrementally by running
+cmake with new flags.
 
 [Example:]
 
-# build LAMMPS with all "standard" packages which don't
-# use libraries and enable GPU package
+# build LAMMPS with most commonly used packages, but then remove
+# those requiring additional library or tools, but still enable
+# GPU package and configure it for using CUDA. You can run.
 mkdir build
 cd build
-cmake -C ../cmake/presets/std_nolib.cmake -D PKG_GPU=on ../cmake :pre
+cmake -C ../cmake/presets/most.cmake -C ../cmake/presets/nolib.cmake -D PKG_GPU=on -D GPU_API=cuda ../cmake :pre
 
+# to add another package, say BODY to the previous configuration you can run:
+cmake -D PKG_BODY=on . :pre
+
+# to reset the package selection from above to the default of no packages
+# but leaving all other settings untouched. You can run:
+cmake -C ../cmake/presets/no_all.cmake . :pre
 :line
 
 [Make shortcuts for installing many packages]:
diff --git a/doc/src/Build_settings.txt b/doc/src/Build_settings.txt
index f1db9f0130..287cd39ff6 100644
--- a/doc/src/Build_settings.txt
+++ b/doc/src/Build_settings.txt
@@ -57,10 +57,10 @@ FFT_INC = -DFFT_SINGLE        # do not specify for double precision
 FFT_INC = -DFFT_PACK_ARRAY    # or -DFFT_PACK_POINTER or -DFFT_PACK_MEMCPY :pre
                               # default is FFT_PACK_ARRAY if not specified
 
-FFT_INC =    	-I/usr/local/include
+FFT_INC =       -I/usr/local/include
 FFT_PATH =      -L/usr/local/lib
-FFT_LIB =	-lfftw3             # FFTW3 double precision
-FFT_LIB =	-lfftw3 -lfftw3f    # FFTW3 single precision
+FFT_LIB =       -lfftw3             # FFTW3 double precision
+FFT_LIB =       -lfftw3 -lfftw3f    # FFTW3 single precision
 FFT_LIB =       -lmkl_intel_lp64 -lmkl_sequential -lmkl_core  # MKL with Intel compiler
 FFT_LIB =       -lmkl_gf_lp64 -lmkl_sequential -lmkl_core     # MKL with GNU compier :pre
 
@@ -179,8 +179,11 @@ e.g. from 511 to -512, which can cause diagnostics like the
 mean-squared displacement, as calculated by the "compute
 msd"_compute_msd.html command, to be faulty.
 
-Note that the USER-ATC package is not currently compatible with the
-"bigbig" setting.
+Note that the USER-ATC package and the USER-INTEL package are currently
+not compatible with the "bigbig" setting. Also, there are limitations
+when using the library interface. Some functions with known issues
+have been replaced by dummy calls printing a corresponding error rather
+than crashing randomly or corrupting data.
 
 Also note that the GPU package requires its lib/gpu library to be
 compiled with the same size setting, or the link will fail.  A CMake
diff --git a/doc/src/Build_windows.txt b/doc/src/Build_windows.txt
index bf1ec265a1..b3dbf775c9 100644
--- a/doc/src/Build_windows.txt
+++ b/doc/src/Build_windows.txt
@@ -51,11 +51,10 @@ provides a unix/linux interface to low-level Windows functions, so LAMMPS
 can be compiled on Windows. The necessary (minor) modifications to LAMMPS
 are included, but may not always up-to-date for recently added functionality
 and the corresponding new code. A machine makefile for using cygwin for
-the old build system is provided. The CMake build system is untested
-for this; you will have to request that makefiles are generated and
-manually set the compiler.
+the old build system is provided. Using CMake for this mode of compilation
+is untested and not likely to work.
 
-When compiling for Windows [not] set the -DLAMMPS_MEMALIGN define
+When compiling for Windows do [not] set the -DLAMMPS_MEMALIGN define
 in the LMP_INC makefile variable and add -lwsock32 -lpsapi to the linker
 flags in LIB makefile variable. Try adding -static-libgcc or -static or
 both to the linker flags when your resulting LAMMPS Windows executable
@@ -79,7 +78,13 @@ probably the currently best tested and supported way to build LAMMPS
 executables for Windows.  There are makefiles provided for the
 traditional build system, but CMake has also been successfully tested
 using the mingw32-cmake and mingw64-cmake wrappers that are bundled
-with the cross-compiler environment on Fedora machines.
+with the cross-compiler environment on Fedora machines. A CMake preset
+selecting all packages compatible with this cross-compilation build
+is provided. You likely need to disable the GPU package unless you
+download and install the contents of the pre-compiled "OpenCL ICD loader
+library"_https://download.lammps.org/thirdparty/opencl-win-devel.tar.gz
+into your MinGW64 cross-compiler environment. The cross-compilation
+currently will only produce non-MPI serial binaries.
 
 Please keep in mind, though, that this only applies to compiling LAMMPS.
 Whether the resulting binaries do work correctly is no tested by the
diff --git a/doc/src/Commands_all.txt b/doc/src/Commands_all.txt
index 155b56ace8..66c348ee30 100644
--- a/doc/src/Commands_all.txt
+++ b/doc/src/Commands_all.txt
@@ -68,6 +68,7 @@ An alphabetic list of all general LAMMPS commands.
 "improper_style"_improper_style.html,
 "include"_include.html,
 "jump"_jump.html,
+"kim_query"_kim_query.html,
 "kspace_modify"_kspace_modify.html,
 "kspace_style"_kspace_style.html,
 "label"_label.html,
@@ -78,6 +79,7 @@ An alphabetic list of all general LAMMPS commands.
 "minimize"_minimize.html,
 "min_modify"_min_modify.html,
 "min_style"_min_style.html,
+"min_style spin"_min_spin.html,
 "molecule"_molecule.html,
 "ndx2group"_group2ndx.html,
 "neb"_neb.html,
diff --git a/doc/src/Commands_fix.txt b/doc/src/Commands_fix.txt
index 678cc9ba0d..14de1d06dd 100644
--- a/doc/src/Commands_fix.txt
+++ b/doc/src/Commands_fix.txt
@@ -61,6 +61,7 @@ OPT.
 "edpd/source"_fix_dpd_source.html,
 "efield"_fix_efield.html,
 "ehex"_fix_ehex.html,
+"electron/stopping"_fix_electron_stopping.html,
 "enforce2d (k)"_fix_enforce2d.html,
 "eos/cv"_fix_eos_cv.html,
 "eos/table"_fix_eos_table.html,
@@ -224,7 +225,7 @@ OPT.
 "wall/body/polyhedron"_fix_wall_body_polyhedron.html,
 "wall/colloid"_fix_wall.html,
 "wall/ees"_fix_wall_ees.html,
-"wall/gran (o)"_fix_wall_gran.html,
+"wall/gran"_fix_wall_gran.html,
 "wall/gran/region"_fix_wall_gran_region.html,
 "wall/harmonic"_fix_wall.html,
 "wall/lj1043"_fix_wall.html,
diff --git a/doc/src/Commands_pair.txt b/doc/src/Commands_pair.txt
index b18d852c09..e887f0178a 100644
--- a/doc/src/Commands_pair.txt
+++ b/doc/src/Commands_pair.txt
@@ -98,6 +98,7 @@ OPT.
 "gran/hertz/history (o)"_pair_gran.html,
 "gran/hooke (o)"_pair_gran.html,
 "gran/hooke/history (ko)"_pair_gran.html,
+"granular"_pair_granular.html,
 "gw"_pair_gw.html,
 "gw/zbl"_pair_gw.html,
 "hbond/dreiding/lj (o)"_pair_hbond_dreiding.html,
diff --git a/doc/src/Eqs/min_spin_damping.jpg b/doc/src/Eqs/min_spin_damping.jpg
new file mode 100644
index 0000000000..0c700cc678
Binary files /dev/null and b/doc/src/Eqs/min_spin_damping.jpg differ
diff --git a/doc/src/Eqs/min_spin_damping.tex b/doc/src/Eqs/min_spin_damping.tex
new file mode 100644
index 0000000000..88b05447d3
--- /dev/null
+++ b/doc/src/Eqs/min_spin_damping.tex
@@ -0,0 +1,13 @@
+\documentclass[preview]{standalone}
+\usepackage{varwidth}
+\usepackage[utf8x]{inputenc}
+\usepackage{amsmath, amssymb, graphics, setspace}
+
+\begin{document}
+\begin{varwidth}{50in}
+  \begin{equation}
+    \frac{d \vec{s}_{i}}{dt} = \lambda\, \vec{s}_{i} \times\left( \vec{\omega}_{i} \times\vec{s}_{i} \right)
+    \nonumber
+  \end{equation}
+\end{varwidth}
+\end{document}
diff --git a/doc/src/Eqs/min_spin_timestep.jpg b/doc/src/Eqs/min_spin_timestep.jpg
new file mode 100644
index 0000000000..0d8f8d07f9
Binary files /dev/null and b/doc/src/Eqs/min_spin_timestep.jpg differ
diff --git a/doc/src/Eqs/min_spin_timestep.tex b/doc/src/Eqs/min_spin_timestep.tex
new file mode 100644
index 0000000000..b0f6e68e4d
--- /dev/null
+++ b/doc/src/Eqs/min_spin_timestep.tex
@@ -0,0 +1,14 @@
+\documentclass[preview]{standalone}
+\usepackage{varwidth}
+\usepackage[utf8x]{inputenc}
+\usepackage{amsmath, amssymb, graphics, setspace}
+
+\begin{document}
+\begin{varwidth}{50in}
+  \begin{equation}
+    {\Delta t}_{\rm max} = \frac{2\pi}{\kappa
+    \left|\vec{\omega}_{\rm max} \right|} 
+    \nonumber
+  \end{equation}
+\end{varwidth}
+\end{document}
diff --git a/doc/src/Howto.txt b/doc/src/Howto.txt
index 36f6be7194..0df417af75 100644
--- a/doc/src/Howto.txt
+++ b/doc/src/Howto.txt
@@ -148,7 +148,7 @@ END_RST -->
 
 <!-- HTML_ONLY -->
 
-"CHARMM, AMBER, and DREIDING force fields"_Howto_bioFF.html
+"CHARMM, AMBER, COMPASS, and DREIDING force fields"_Howto_bioFF.html
 "TIP3P water model"_Howto_tip3p.html
 "TIP4P water model"_Howto_tip4p.html
 "SPC water model"_Howto_spc.html :all(b)
diff --git a/doc/src/Howto_bioFF.txt b/doc/src/Howto_bioFF.txt
index deb5b31441..b6995920ae 100644
--- a/doc/src/Howto_bioFF.txt
+++ b/doc/src/Howto_bioFF.txt
@@ -7,29 +7,31 @@ Documentation"_ld - "LAMMPS Commands"_lc :c
 
 :line
 
-CHARMM, AMBER, and DREIDING force fields :h3
+CHARMM, AMBER, COMPASS, and DREIDING force fields :h3
 
 A force field has 2 parts: the formulas that define it and the
 coefficients used for a particular system.  Here we only discuss
 formulas implemented in LAMMPS that correspond to formulas commonly
-used in the CHARMM, AMBER, and DREIDING force fields.  Setting
-coefficients is done in the input data file via the
-"read_data"_read_data.html command or in the input script with
+used in the CHARMM, AMBER, COMPASS, and DREIDING force fields.  Setting
+coefficients is done either from special sections in an input data file
+via the "read_data"_read_data.html command or in the input script with
 commands like "pair_coeff"_pair_coeff.html or
-"bond_coeff"_bond_coeff.html.  See the "Tools"_Tools.html doc page for
-additional tools that can use CHARMM or AMBER to assign force field
-coefficients and convert their output into LAMMPS input.
+"bond_coeff"_bond_coeff.html and so on.  See the "Tools"_Tools.html doc
+page for additional tools that can use CHARMM, AMBER, or Materials
+Studio generated files to assign force field coefficients and convert
+their output into LAMMPS input.
 
 See "(MacKerell)"_#howto-MacKerell for a description of the CHARMM force
-field.  See "(Cornell)"_#howto-Cornell for a description of the AMBER force
-field.
+field.  See "(Cornell)"_#howto-Cornell for a description of the AMBER
+force field.  See "(Sun)"_#howto-Sun for a description of the COMPASS
+force field.
 
 :link(charmm,http://www.scripps.edu/brooks)
 :link(amber,http://amber.scripps.edu)
 
-These style choices compute force field formulas that are consistent
-with common options in CHARMM or AMBER.  See each command's
-documentation for the formula it computes.
+The interaction styles listed below compute force field formulas that
+are consistent with common options in CHARMM or AMBER.  See each
+command's documentation for the formula it computes.
 
 "bond_style"_bond_harmonic.html harmonic
 "angle_style"_angle_charmm.html charmm
@@ -44,28 +46,54 @@ documentation for the formula it computes.
 "special_bonds"_special_bonds.html charmm
 "special_bonds"_special_bonds.html amber :ul
 
-NOTE: For CHARMM, newer {charmmfsw} or {charmmfsh} styles were
-released in March 2017.  We recommend they be used instead of the
-older {charmm} styles.  See discussion of the differences on the "pair
-charmm"_pair_charmm.html and "dihedral charmm"_dihedral_charmm.html
-doc pages.
+NOTE: For CHARMM, newer {charmmfsw} or {charmmfsh} styles were released
+in March 2017.  We recommend they be used instead of the older {charmm}
+styles.  See discussion of the differences on the "pair
+charmm"_pair_charmm.html and "dihedral charmm"_dihedral_charmm.html doc
+pages.
+
+COMPASS is a general force field for atomistic simulation of common
+organic molecules, inorganic small molecules, and polymers which was
+developed using ab initio and empirical parameterization techniques.
+See the "Tools"_Tools.html doc page for the msi2lmp tool for creating
+LAMMPS template input and data files from BIOVIA’s Materials Studio
+files.  Please note that the msi2lmp tool is very old and largely
+unmaintained, so it does not support all features of Materials Studio
+provided force field files, especially additions during the last decade.
+You should watch the output carefully and compare results, where
+possible.  See "(Sun)"_#howto-Sun for a description of the COMPASS force
+field.
+
+These interaction styles listed below compute force field formulas that
+are consistent with the COMPASS force field.  See each command's
+documentation for the formula it computes.
+
+"bond_style"_bond_class2.html class2
+"angle_style"_angle_class2.html class2
+"dihedral_style"_dihedral_class2.html class2
+"improper_style"_improper_class2.html class2 :ul
+
+"pair_style"_pair_class2.html lj/class2
+"pair_style"_pair_class2.html lj/class2/coul/cut
+"pair_style"_pair_class2.html lj/class2/coul/long :ul
+
+"special_bonds"_special_bonds.html lj/coul 0 0 1 :ul
 
 DREIDING is a generic force field developed by the "Goddard
 group"_http://www.wag.caltech.edu at Caltech and is useful for
-predicting structures and dynamics of organic, biological and
-main-group inorganic molecules. The philosophy in DREIDING is to use
-general force constants and geometry parameters based on simple
-hybridization considerations, rather than individual force constants
-and geometric parameters that depend on the particular combinations of
-atoms involved in the bond, angle, or torsion terms. DREIDING has an
-"explicit hydrogen bond term"_pair_hbond_dreiding.html to describe
-interactions involving a hydrogen atom on very electronegative atoms
-(N, O, F).
+predicting structures and dynamics of organic, biological and main-group
+inorganic molecules. The philosophy in DREIDING is to use general force
+constants and geometry parameters based on simple hybridization
+considerations, rather than individual force constants and geometric
+parameters that depend on the particular combinations of atoms involved
+in the bond, angle, or torsion terms. DREIDING has an "explicit hydrogen
+bond term"_pair_hbond_dreiding.html to describe interactions involving a
+hydrogen atom on very electronegative atoms (N, O, F).
 
 See "(Mayo)"_#howto-Mayo for a description of the DREIDING force field
 
-These style choices compute force field formulas that are consistent
-with the DREIDING force field.  See each command's
+The interaction styles listed below compute force field formulas that
+are consistent with the DREIDING force field.  See each command's
 documentation for the formula it computes.
 
 "bond_style"_bond_harmonic.html harmonic
@@ -100,6 +128,9 @@ Fischer, Gao, Guo, Ha, et al, J Phys Chem, 102, 3586 (1998).
 [(Cornell)] Cornell, Cieplak, Bayly, Gould, Merz, Ferguson,
 Spellmeyer, Fox, Caldwell, Kollman, JACS 117, 5179-5197 (1995).
 
+:link(howto-Sun)
+[(Sun)] Sun, J. Phys. Chem. B, 102, 7338–7364 (1998).
+
 :link(howto-Mayo)
 [(Mayo)] Mayo, Olfason, Goddard III, J Phys Chem, 94, 8897-8909
 (1990).
diff --git a/doc/src/Howto_library.txt b/doc/src/Howto_library.txt
index 40a8bf0a70..ba009cfad9 100644
--- a/doc/src/Howto_library.txt
+++ b/doc/src/Howto_library.txt
@@ -166,9 +166,6 @@ void lammps_gather_atoms_subset(void *, char *, int, int, int, int *, void *)
 void lammps_scatter_atoms(void *, char *, int, int, void *)
 void lammps_scatter_atoms_subset(void *, char *, int, int, int, int *, void *) :pre
 
-void lammps_create_atoms(void *, int, tagint *, int *, double *, double *,
-                         imageint *, int) :pre
-
 The gather functions collect peratom info of the requested type (atom
 coords, atom types, forces, etc) from all processors, and returns the
 same vector of values to each calling processor.  The scatter
@@ -176,6 +173,11 @@ functions do the inverse.  They distribute a vector of peratom values,
 passed by all calling processors, to individual atoms, which may be
 owned by different processors.
 
+IMPORTANT NOTE: These functions are not compatible with the
+-DLAMMPS_BIGBIG setting when compiling LAMMPS.  Dummy functions
+that result in an error message and abort will be substituted
+instead of resulting in random crashes and memory corruption.
+
 The lammps_gather_atoms() function does this for all N atoms in the
 system, ordered by atom ID, from 1 to N.  The
 lammps_gather_atoms_concat() function does it for all N atoms, but
@@ -196,6 +198,9 @@ those values to each atom in the system.  The
 lammps_scatter_atoms_subset() function takes a subset of IDs as an
 argument and only scatters those values to the owning atoms.
 
+void lammps_create_atoms(void *, int, tagint *, int *, double *, double *,
+                         imageint *, int) :pre
+
 The lammps_create_atoms() function takes a list of N atoms as input
 with atom types and coords (required), an optionally atom IDs and
 velocities and image flags.  It uses the coords of each atom to assign
diff --git a/doc/src/Howto_pylammps.txt b/doc/src/Howto_pylammps.txt
index b731a8e31a..54f17d912a 100644
--- a/doc/src/Howto_pylammps.txt
+++ b/doc/src/Howto_pylammps.txt
@@ -57,6 +57,17 @@ library is then loaded by the Python interface. In this example we enable the
 MOLECULE package and compile LAMMPS with C++ exceptions, PNG, JPEG and FFMPEG
 output support enabled.
 
+Step 1a: For the CMake based build system, the steps are:
+
+mkdir $LAMMPS_DIR/build-shared
+cd  $LAMMPS_DIR/build-shared :pre
+
+# MPI, PNG, Jpeg, FFMPEG are auto-detected
+cmake ../cmake -DPKG_MOLECULE=yes -DLAMMPS_EXCEPTIONS=yes -DBUILD_LIB=yes -DBUILD_SHARED_LIBS=yes
+make :pre
+
+Step 1b: For the legacy, make based build system, the steps are:
+
 cd $LAMMPS_DIR/src :pre
 
 # add packages if necessary
@@ -68,10 +79,9 @@ make mpi mode=shlib LMP_INC="-DLAMMPS_PNG -DLAMMPS_JPEG -DLAMMPS_FFMPEG -DLAMMPS
 Step 2: Installing the LAMMPS Python package :h6
 
 PyLammps is part of the lammps Python package. To install it simply install
-that package into your current Python installation.
+that package into your current Python installation with:
 
-cd $LAMMPS_DIR/python
-python install.py :pre
+make install-python :pre
 
 NOTE: Recompiling the shared library requires re-installing the Python package
 
@@ -94,14 +104,21 @@ apt-get install python-virtualenv :pre
 
 Creating a virtualenv with lammps installed :h6
 
-# create virtualenv name 'testing' :pre
+# create virtualenv named 'testing'
+virtualenv $HOME/python/testing :pre
 
 # activate 'testing' environment
-source testing/bin/activate :pre
+source $HOME/python/testing/bin/activate :pre
+
+Now configure and compile the LAMMPS shared library as outlined above.
+When using CMake and the shared library has already been build, you
+need to re-run CMake to update the location of the python executable
+to the location in the virtual environment with:
+
+cmake . -DPYTHON_EXECUTABLE=$(which python) :pre
 
 # install LAMMPS package in virtualenv
-(testing) cd $LAMMPS_DIR/python
-(testing) python install.py :pre
+(testing) make install-python :pre
 
 # install other useful packages
 (testing) pip install matplotlib jupyter mpi4py :pre
diff --git a/doc/src/Howto_tip3p.txt b/doc/src/Howto_tip3p.txt
index 942b42aea1..a34577c5e1 100644
--- a/doc/src/Howto_tip3p.txt
+++ b/doc/src/Howto_tip3p.txt
@@ -10,7 +10,7 @@ Documentation"_ld - "LAMMPS Commands"_lc :c
 TIP3P water model :h3
 
 The TIP3P water model as implemented in CHARMM
-"(MacKerell)"_#howto-MacKerell specifies a 3-site rigid water molecule with
+"(MacKerell)"_#howto-tip3p specifies a 3-site rigid water molecule with
 charges and Lennard-Jones parameters assigned to each of the 3 atoms.
 In LAMMPS the "fix shake"_fix_shake.html command can be used to hold
 the two O-H bonds and the H-O-H angle rigid.  A bond style of
@@ -60,6 +60,10 @@ models"_http://en.wikipedia.org/wiki/Water_model.
 
 :line
 
+:link(howto-tip3p)
+[(MacKerell)] MacKerell, Bashford, Bellott, Dunbrack, Evanseck, Field,
+Fischer, Gao, Guo, Ha, et al, J Phys Chem, 102, 3586 (1998).
+
 :link(Jorgensen1)
 [(Jorgensen)] Jorgensen, Chandrasekhar, Madura, Impey, Klein, J Chem
 Phys, 79, 926 (1983).
diff --git a/doc/src/Manual.txt b/doc/src/Manual.txt
index af0a2681ab..e36e4063c9 100644
--- a/doc/src/Manual.txt
+++ b/doc/src/Manual.txt
@@ -1,7 +1,7 @@
 <!-- HTML_ONLY -->
 <HEAD>
 <TITLE>LAMMPS Users Manual</TITLE>
-<META NAME="docnumber" CONTENT="28 Feb 2019 version">
+<META NAME="docnumber" CONTENT="29 Mar 2019 version">
 <META NAME="author" CONTENT="http://lammps.sandia.gov - Sandia National Laboratories">
 <META NAME="copyright" CONTENT="Copyright (2003) Sandia Corporation. This software and manual is distributed under the GNU General Public License.">
 </HEAD>
@@ -21,7 +21,7 @@
 :line
 
 LAMMPS Documentation :c,h1
-28 Feb 2019 version :c,h2
+29 Mar 2019 version :c,h2
 
 "What is a LAMMPS version?"_Manual_version.html
 
diff --git a/doc/src/Packages_details.txt b/doc/src/Packages_details.txt
index 3a362a23d0..0ab1b5e4fd 100644
--- a/doc/src/Packages_details.txt
+++ b/doc/src/Packages_details.txt
@@ -341,6 +341,8 @@ KIM package :link(PKG-KIM),h4
 A "pair_style kim"_pair_kim.html command which is a wrapper on the
 Knowledge Base for Interatomic Models (KIM) repository of interatomic
 potentials, enabling any of them to be used in LAMMPS simulations.
+Also a "kim_query"_kim_query.html command, which allows to query
+the OpenKIM database for stored properties.
 
 To use this package you must have the KIM library available on your
 system.
diff --git a/doc/src/Python_install.txt b/doc/src/Python_install.txt
index 97f6bf3c3a..2c134974f5 100644
--- a/doc/src/Python_install.txt
+++ b/doc/src/Python_install.txt
@@ -12,16 +12,23 @@ Installing LAMMPS in Python :h3
 For Python to invoke LAMMPS, there are 2 files it needs to know about:
 
 python/lammps.py
-src/liblammps.so :ul
+liblammps.so or liblammps.dylib :ul
 
-Lammps.py is the Python wrapper on the LAMMPS library interface.
-Liblammps.so is the shared LAMMPS library that Python loads, as
-described above.
+The python source code in lammps.py is the Python wrapper on the
+LAMMPS library interface. The liblammps.so or liblammps.dylib file
+is the shared LAMMPS library that Python loads dynamically.
 
-You can insure Python can find these files in one of two ways:
+You can achieve that Python can find these files in one of two ways:
 
-set two environment variables
-run the python/install.py script :ul
+set two environment variables pointing to the location in the source tree
+run "make install-python" or run the python/install.py script explicitly :ul
+
+When calling "make install-python" LAMMPS will try to install the
+python module and the shared library into the python site-packages folders;
+either the system-wide ones, or the local users ones (in case of insufficient
+permissions for the global install). Python will then find the module
+and shared library file automatically. The exact location of these folders
+depends on your python version and your operating system.
 
 If you set the paths to these files as environment variables, you only
 have to do it once.  For the csh or tcsh shells, add something like
@@ -30,42 +37,28 @@ this to your ~/.cshrc file, one line for each of the two files:
 setenv PYTHONPATH $\{PYTHONPATH\}:/home/sjplimp/lammps/python
 setenv LD_LIBRARY_PATH $\{LD_LIBRARY_PATH\}:/home/sjplimp/lammps/src :pre
 
-If you use the python/install.py script, you need to invoke it every
-time you rebuild LAMMPS (as a shared library) or make changes to the
-python/lammps.py file.
+On MacOSX you may also need to set DYLD_LIBRARY_PATH accordingly.
+For Bourne/Korn shells accordingly into the corresponding files using
+the "export" shell builtin.
 
-You can invoke install.py from the python directory as
+If you use "make install-python" or the python/install.py script, you need
+to invoke it every time you rebuild LAMMPS (as a shared library) or
+make changes to the python/lammps.py file, so that the site-packages
+files are updated with the new version.
 
-% python install.py \[libdir\] \[pydir\] :pre
+If the default settings of "make install-python" are not what you want,
+you can invoke install.py from the python directory manually as
 
-The optional libdir is where to copy the LAMMPS shared library to; the
-default is /usr/local/lib.  The optional pydir is where to copy the
-lammps.py file to; the default is the site-packages directory of the
-version of Python that is running the install script.
+% python install.py -m \<python module\> -l <shared library> -v <version.h file> \[-d \<pydir\>\] :pre
 
-Note that libdir must be a location that is in your default
-LD_LIBRARY_PATH, like /usr/local/lib or /usr/lib.  And pydir must be a
-location that Python looks in by default for imported modules, like
-its site-packages dir.  If you want to copy these files to
-non-standard locations, such as within your own user space, you will
-need to set your PYTHONPATH and LD_LIBRARY_PATH environment variables
-accordingly, as above.
+The -m flag points to the lammps.py python module file to be installed,
+the -l flag points to the LAMMPS shared library file to be installed,
+the -v flag points to the version.h file in the LAMMPS source
+and the optional -d flag to a custom (legacy) installation folder :ul
 
-If the install.py script does not allow you to copy files into system
-directories, prefix the python command with "sudo".  If you do this,
-make sure that the Python that root runs is the same as the Python you
-run.  E.g. you may need to do something like
-
-% sudo /usr/local/bin/python install.py \[libdir\] \[pydir\] :pre
-
-You can also invoke install.py from the make command in the src
-directory as
-
-% make install-python :pre
-
-In this mode you cannot append optional arguments.  Again, you may
-need to prefix this with "sudo".  In this mode you cannot control
-which Python is invoked by root.
+If you use a legacy installation folder, you will need to set your
+PYTHONPATH and LD_LIBRARY_PATH (and/or DYLD_LIBRARY_PATH) environment
+variables accordingly, as described above.
 
 Note that if you want Python to be able to load different versions of
 the LAMMPS shared library (see "this section"_Python_shlib.html), you will
diff --git a/doc/src/Python_overview.txt b/doc/src/Python_overview.txt
index a5d6a469ff..0195ec2b20 100644
--- a/doc/src/Python_overview.txt
+++ b/doc/src/Python_overview.txt
@@ -13,11 +13,11 @@ Overview of Python and LAMMPS :h3
 LAMMPS can work together with Python in three ways.  First, Python can
 wrap LAMMPS through the its "library interface"_Howto_library.html, so
 that a Python script can create one or more instances of LAMMPS and
-launch one or more simulations.  In Python lingo, this is "extending"
-Python with LAMMPS.
+launch one or more simulations.  In Python lingo, this is called
+"extending" Python with a LAMMPS module.
 
 Second, a lower-level Python interface can be used indirectly through
-provided PyLammps and IPyLammps wrapper classes, written in Python.
+the provided PyLammps and IPyLammps wrapper classes, written in Python.
 These wrappers try to simplify the usage of LAMMPS in Python by
 providing an object-based interface to common LAMMPS functionality.
 They also reduces the amount of code necessary to parameterize LAMMPS
@@ -25,11 +25,12 @@ scripts through Python and make variables and computes directly
 accessible.
 
 Third, LAMMPS can use the Python interpreter, so that a LAMMPS
-input script can invoke Python code directly, and pass information
-back-and-forth between the input script and Python functions you
-write.  This Python code can also callback to LAMMPS to query or change
-its attributes.  In Python lingo, this is "embedding" Python in
-LAMMPS.  When used in this mode, Python can perform operations that
-the simple LAMMPS input script syntax cannot.
+input script or styles can invoke Python code directly, and pass
+information back-and-forth between the input script and Python
+functions you write.  This Python code can also callback to LAMMPS
+to query or change its attributes through the LAMMPS Python module
+mentioned above.  In Python lingo, this is "embedding" Python in
+LAMMPS.  When used in this mode, Python can perform script operations
+that the simple LAMMPS input script syntax can not.
 
 
diff --git a/doc/src/Run_options.txt b/doc/src/Run_options.txt
index 9c12b3ff24..1c3cb60c5f 100644
--- a/doc/src/Run_options.txt
+++ b/doc/src/Run_options.txt
@@ -79,7 +79,7 @@ stdin.
 Explicitly enable or disable KOKKOS support, as provided by the KOKKOS
 package.  Even if LAMMPS is built with this package, as described
 in "Speed kokkos"_Speed_kokkos.html, this switch must be set to enable
-running with the KOKKOS-enabled styles the package provides.  If the
+running with KOKKOS-enabled styles the package provides.  If the
 switch is not set (the default), LAMMPS will operate as if the KOKKOS
 package were not installed; i.e. you can run standard LAMMPS or with
 the GPU or USER-OMP packages, for testing or benchmarking purposes.
@@ -448,7 +448,7 @@ partition screen files file.N.
 [-suffix style args] :link(suffix)
 
 Use variants of various styles if they exist.  The specified style can
-be {cuda}, {gpu}, {intel}, {kk}, {omp}, {opt}, or {hybrid}.  These
+be {gpu}, {intel}, {kk}, {omp}, {opt}, or {hybrid}.  These
 refer to optional packages that LAMMPS can be built with, as described
 in "Accelerate performance"_Speed.html.  The "gpu" style corresponds to the
 GPU package, the "intel" style to the USER-INTEL package, the "kk"
diff --git a/doc/src/Speed_intel.txt b/doc/src/Speed_intel.txt
index da772f29fd..2688b43e6f 100644
--- a/doc/src/Speed_intel.txt
+++ b/doc/src/Speed_intel.txt
@@ -24,7 +24,7 @@ LAMMPS to run on the CPU cores and co-processor cores simultaneously.
 
 Angle Styles: charmm, harmonic :ulb,l
 Bond Styles: fene, fourier, harmonic :l
-Dihedral Styles: charmm, harmonic, opls :l
+Dihedral Styles: charmm, fourier, harmonic, opls :l
 Fixes: nve, npt, nvt, nvt/sllod, nve/asphere :l
 Improper Styles: cvff, harmonic :l
 Pair Styles: airebo, airebo/morse, buck/coul/cut, buck/coul/long,
@@ -34,6 +34,10 @@ rebo, sw, tersoff :l
 K-Space Styles: pppm, pppm/disp :l
 :ule
 
+IMPORTANT NOTE: None of the styles in the USER-INTEL package currently
+support computing per-atom stress.  If any compute or fix in your
+input requires it, LAMMPS will abort with an error message.
+
 [Speed-ups to expect:]
 
 The speedups will depend on your simulation, the hardware, which
diff --git a/doc/src/commands_list.txt b/doc/src/commands_list.txt
index 27e0906b5f..6f90d9c93a 100644
--- a/doc/src/commands_list.txt
+++ b/doc/src/commands_list.txt
@@ -53,6 +53,7 @@ Commands :h1
    include
    info
    jump
+   kim_query
    kspace_modify
    kspace_style
    label
@@ -61,6 +62,7 @@ Commands :h1
    mass
    message
    min_modify
+   min_spin
    min_style
    minimize
    molecule
diff --git a/doc/src/compute.txt b/doc/src/compute.txt
index 4886e73ab6..87dbee57d6 100644
--- a/doc/src/compute.txt
+++ b/doc/src/compute.txt
@@ -54,9 +54,10 @@ local quantities have the word "local" in their style,
 e.g. {bond/local}.  Styles with neither "atom" or "local" in their
 style produce global quantities.
 
-Note that a single compute produces either global or per-atom or local
-quantities, but never more than one of these (with only a few
-exceptions, as documented by individual compute commands).
+Note that a single compute can produce either global or per-atom or
+local quantities, but not both global and per-atom.  It can produce
+local quantities in tandem with global or per-atom quantities.  The
+compute doc page will explain.
 
 Global, per-atom, and local quantities each come in three kinds: a
 single scalar value, a vector of values, or a 2d array of values.  The
diff --git a/doc/src/fix.txt b/doc/src/fix.txt
index 395f2ad7a9..c424e56074 100644
--- a/doc/src/fix.txt
+++ b/doc/src/fix.txt
@@ -83,8 +83,10 @@ not in the specified fix group.  Local quantities are calculated by
 each processor based on the atoms it owns, but there may be zero or
 more per atoms.
 
-Note that a single fix may produces either global or per-atom or local
-quantities (or none at all), but never more than one of these.
+Note that a single fix can produce either global or per-atom or local
+quantities (or none at all), but not both global and per-atom.  It can
+produce local quantities in tandem with global or per-atom quantities.
+The fix doc page will explain.
 
 Global, per-atom, and local quantities each come in three kinds: a
 single scalar value, a vector of values, or a 2d array of values.  The
@@ -199,6 +201,7 @@ accelerated styles exist.
 "edpd/source"_fix_dpd_source.html -
 "efield"_fix_efield.html - impose electric field on system
 "ehex"_fix_ehex.html - enhanced heat exchange algorithm
+"electron/stopping"_fix_electron_stopping.html - electronic stopping power as a friction force
 "enforce2d"_fix_enforce2d.html - zero out z-dimension velocity and force
 "eos/cv"_fix_eos_cv.html -
 "eos/table"_fix_eos_table.html -
diff --git a/doc/src/fix_ave_histo.txt b/doc/src/fix_ave_histo.txt
index 79f4d53481..0a17813d21 100644
--- a/doc/src/fix_ave_histo.txt
+++ b/doc/src/fix_ave_histo.txt
@@ -35,6 +35,7 @@ keyword = {mode} or {file} or {ave} or {start} or {beyond} or {overwrite} or {ti
   {mode} arg = {scalar} or {vector}
     scalar = all input values are scalars
     vector = all input values are vectors
+  {kind} arg = {global} or {peratom} or {local}
   {file} arg = filename
     filename = name of file to output histogram(s) to
   {ave} args = {one} or {running} or {window}
@@ -92,7 +93,8 @@ either all global, all per-atom, or all local quantities.  Inputs of
 different kinds (e.g. global and per-atom) cannot be mixed.  Atom
 attributes are per-atom vector values.  See the doc page for
 individual "compute" and "fix" commands to see what kinds of
-quantities they generate.
+quantities they generate.  See the optional {kind} keyword below for
+how to force the fix ave/histo command to disambiguate if necessary.
 
 Note that the output of this command is a single histogram for all
 input values combined together, not one histogram per input value.
@@ -231,6 +233,14 @@ keyword is set to {vector}, then all input values must be global or
 per-atom or local vectors, or columns of global or per-atom or local
 arrays.
 
+The {kind} keyword only needs to be set if a compute or fix produces
+more than one kind of output (global, per-atom, local).  If this is
+not the case, then LAMMPS will determine what kind of input is
+provided and whether all the input arguments are consistent.  If a
+compute or fix produces more than one kind of output, the {kind}
+keyword should be used to specify which output will be used.  The
+remaining input arguments must still be consistent.
+
 The {beyond} keyword determines how input values that fall outside the
 {lo} to {hi} bounds are treated.  Values such that {lo} <= value <=
 {hi} are assigned to one bin.  Values on a bin boundary are assigned
@@ -240,7 +250,7 @@ If {beyond} is set to {end} then values < {lo} are counted in the
 first bin and values > {hi} are counted in the last bin.  If {beyond}
 is set to {extend} then two extra bins are created, so that there are
 Nbins+2 total bins.  Values < {lo} are counted in the first bin and
-values > {hi} are counted in the last bin (Nbins+1).  Values between
+values > {hi} are counted in the last bin (Nbins+2).  Values between
 {lo} and {hi} (inclusive) are counted in bins 2 through Nbins+1.  The
 "coordinate" stored and printed for these two extra bins is {lo} and
 {hi}.
@@ -354,5 +364,6 @@ ave/chunk"_fix_ave_chunk.html, "fix ave/time"_fix_ave_time.html,
 
 [Default:] none
 
-The option defaults are mode = scalar, ave = one, start = 0, no file
-output, beyond = ignore, and title 1,2,3 = strings as described above.
+The option defaults are mode = scalar, kind = figured out from input
+arguments, ave = one, start = 0, no file output, beyond = ignore, and
+title 1,2,3 = strings as described above.
diff --git a/doc/src/fix_bond_react.txt b/doc/src/fix_bond_react.txt
index 5da0f33e3a..af443ede92 100644
--- a/doc/src/fix_bond_react.txt
+++ b/doc/src/fix_bond_react.txt
@@ -385,6 +385,10 @@ No parameter of this fix can be used with the {start/stop} keywords of
 the "run"_run.html command.  This fix is not invoked during "energy
 minimization"_minimize.html.
 
+When fix bond/react is 'unfixed,' all internally-created groups are
+deleted. Therefore, fix bond/react can only be unfixed after unfixing
+all other fixes that use any group created by fix bond/react.
+
 [Restrictions:]
 
 This fix is part of the USER-MISC package.  It is only enabled if
diff --git a/doc/src/fix_electron_stopping.txt b/doc/src/fix_electron_stopping.txt
new file mode 100644
index 0000000000..096629c330
--- /dev/null
+++ b/doc/src/fix_electron_stopping.txt
@@ -0,0 +1,165 @@
+"LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
+
+:link(lws,http://lammps.sandia.gov)
+:link(ld,Manual.html)
+:link(lc,Commands_all.html)
+
+:line
+
+fix electron/stopping command :h3
+
+[Syntax:]
+
+fix ID group-ID electron/stopping Ecut file keyword value ... :pre
+
+ID, group-ID are documented in "fix"_fix.html command :ulb,l
+electron/stopping = style name of this fix command :l
+Ecut = minimum kinetic energy for electronic stopping (energy units) :l
+file = name of the file containing the electronic stopping power table :l
+zero or more keyword/value pairs may be appended to args :l
+keyword = {region} or {minneigh} :l
+  {region} value = region-ID
+    region-ID = region, whose atoms will be affected by this fix
+  {minneigh} value = minneigh
+    minneigh = minimum number of neighbors an atom to have stopping applied :pre
+:ule
+
+[Examples:]
+
+fix el all electron/stopping 10.0 elstop-table.txt
+fix el all electron/stopping 10.0 elstop-table.txt minneigh 3
+fix el mygroup electron/stopping 1.0 elstop-table.txt region bulk :pre
+
+[Description:]
+
+This fix implements inelastic energy loss for fast projectiles in solids. It
+applies a friction force to fast moving atoms to slow them down due to
+"electronic stopping"_#elstopping (energy lost via electronic collisions per
+unit of distance). This fix should be used for simulation of irradiation
+damage or ion implantation, where the ions can lose noticeable amounts of
+energy from electron excitations. If the electronic stopping power is not
+considered, the simulated range of the ions can be severely overestimated
+("Nordlund98"_#Nordlund98, "Nordlund95"_#Nordlund95).
+
+The electronic stopping is implemented by applying a friction force
+to each atom as:
+
+\begin\{equation\}
+\vec\{F\}_i = \vec\{F\}^0_i - \frac\{\vec\{v\}_i\}\{\|\vec\{v\}_i\|\} \cdot S_e
+\end\{equation\}
+
+where \(\vec\{F\}_i\) is the resulting total force on the atom.
+\(\vec\{F\}^0_i\) is the original force applied to the atom, \(\vec\{v\}_i\) is
+its velocity and \(S_e\) is the stopping power of the ion.
+
+NOTE: In addition to electronic stopping, atomic cascades and irradiation
+simulations require the use of an adaptive timestep (see
+"fix dt/reset"_fix_dt_reset.html) and the repulsive ZBL potential (see
+"ZBL"_pair_zbl.html potential) or similar. Without these settings the
+interaction between the ion and the target atoms will be faulty. It is also
+common to use in such simulations a thermostat ("fix_nvt"_fix_nh.html) in
+the borders of the simulation cell.
+
+NOTE: This fix removes energy from fast projectiles without depositing it as a
+heat to the simulation cell. Such implementation might lead to the unphysical
+results when the amount of energy deposited to the electronic system is large,
+e.g. simulations of Swift Heavy Ions (energy per nucleon of 100 keV/amu or
+higher) or multiple projectiles. You could compensate energy loss by coupling
+bulk atoms with some thermostat or control heat transfer between electronic and
+atomic subsystems with the two-temperature model ("fix_ttm"_fix_ttm.html).
+
+At low velocities the electronic stopping is negligible. The electronic
+friction is not applied to atoms whose kinetic energy is smaller than {Ecut},
+or smaller than the lowest energy value given in the table in {file}.
+Electronic stopping should be applied only when a projectile reaches bulk
+material. This fix scans neighbor list and excludes atoms with fewer than
+{minneigh} neighbors (by default one). If the pair potential cutoff is large,
+minneigh should be increased, though not above the number of nearest neighbors
+in bulk material. An alternative is to disable the check for neighbors by
+setting {minneigh} to zero and using the {region} keyword. This is necessary
+when running simulations of cluster bombardment.
+
+If the {region} keyword is used, the atom must also be in the specified
+geometric "region"_region.html in order to have electronic stopping applied to
+it. This is useful if the position of the bulk material is fixed. By default
+the electronic stopping is applied everywhere in the simulation cell.
+
+:line
+
+The energy ranges and stopping powers are read from the file {file}.
+Lines starting with {#} and empty lines are ignored. Otherwise each
+line must contain exactly [N+1] numbers, where [N] is the number of atom
+types in the simulation.
+
+The first column is the energy for which the stopping powers on that
+line apply. The energies must be sorted from the smallest to the largest.
+The other columns are the stopping powers \(S_e\) for each atom type,
+in ascending order, in force "units"_units.html. The stopping powers for
+intermediate energy values are calculated with linear interpolation between
+2 nearest points.
+
+For example:
+
+# This is a comment
+#       atom-1    atom-2
+# eV    eV/Ang    eV/Ang  # units metal
+ 10        0        0
+250       60       80
+750      100      150 :pre
+
+
+If an atom which would have electronic stopping applied to it has a
+kinetic energy higher than the largest energy given in {file}, LAMMPS
+will exit with an error message.
+
+The stopping power depends on the energy of the ion and the target
+material. The electronic stopping table can be obtained from
+scientific publications, experimental databases or by using
+"SRIM"_#SRIM software. Other programs such as "CasP"_#CasP or
+"PASS"_#PASS can calculate the energy deposited as a function
+of the impact parameter of the ion; these results can be used
+to derive the stopping power.
+
+[Restart, fix_modify, output, run start/stop, minimize info:]
+
+No information about this fix is written to "binary restart
+files"_restart.html.
+
+The "fix_modify"_fix_modify.html options are not supported.
+
+This fix computes a global scalar, which can be accessed by various
+"output commands"_Howto_output.html. The scalar is the total energy
+loss from electronic stopping applied by this fix since the start of
+the latest run. It is considered "intensive".
+
+The {start/stop} keywords of the "run"_run.html command have no effect
+on this fix.
+
+[Restrictions:]
+
+This pair style is part of the USER-MISC package. It is only enabled if
+LAMMPS was built with that package. See the "Build package"_Build_package.html
+doc page for more info.
+
+[Default:]
+
+The default is no limitation by region, and minneigh = 1.
+
+:line
+:link(elstopping)
+[(electronic stopping)] Wikipedia - Electronic Stopping Power: https://en.wikipedia.org/wiki/Stopping_power_%28particle_radiation%29
+
+:link(Nordlund98)
+[(Nordlund98)] Nordlund, Kai, et al.  Physical Review B 57.13 (1998): 7556.
+
+:link(Nordlund95)
+[(Nordlund95)] Nordlund, Kai. Computational materials science 3.4 (1995): 448-456.
+
+:link(SRIM)
+[(SRIM)] SRIM webpage: http://www.srim.org/
+
+:link(CasP)
+[(CasP)] CasP webpage: https://www.helmholtz-berlin.de/people/gregor-schiwietz/casp_en.html
+
+:link(PASS)
+[(PASS)] PASS webpage: https://www.sdu.dk/en/DPASS
diff --git a/doc/src/fix_hyper_global.txt b/doc/src/fix_hyper_global.txt
index a7a938b144..81404ac6a2 100644
--- a/doc/src/fix_hyper_global.txt
+++ b/doc/src/fix_hyper_global.txt
@@ -102,7 +102,7 @@ Bi = exp(beta * Vij(max)) :pre
 where beta = 1/kTequil, and {Tequil} is the temperature of the system
 and an argument to this fix.  Note that Bi >= 1 at every step.
 
-NOTE: To run GHD, the input script must also use the "fix
+NOTE: To run a GHD simulation, the input script must also use the "fix
 langevin"_fix_langevin.html command to thermostat the atoms at the
 same {Tequil} as specified by this fix, so that the system is running
 constant-temperature (NVT) dynamics.  LAMMPS does not check that this
@@ -166,9 +166,9 @@ correctly.  There will just be fewer events because the hyper time
 
 NOTE: If you have no physical intuition as to the smallest barrier
 height in your system, a reasonable strategy to determine the largest
-{Vmax} you can use for an LHD model, is to run a sequence of
+{Vmax} you can use for a GHD model, is to run a sequence of
 simulations with smaller and smaller {Vmax} values, until the event
-rate does not change.
+rate does not change (as a function of hyper time).
 
 The {Tequil} argument is the temperature at which the system is
 simulated; see the comment above about the "fix
@@ -177,7 +177,8 @@ beta term in the exponential factor that determines how much boost is
 achieved as a function of the bias potential.
 
 In general, the lower the value of {Tequil} and the higher the value
-of {Vmax}, the more boost will be achievable by the GHD algorithm.
+of {Vmax}, the more time boost will be achievable by the GHD
+algorithm.
 
 :line
 
@@ -190,41 +191,43 @@ The "fix_modify"_fix_modify.html {energy} option is supported by this
 fix to add the energy of the bias potential to the the system's
 potential energy as part of "thermodynamic output"_thermo_style.html.
 
-This fix computes a global scalar and global vector of length 11, which
+This fix computes a global scalar and global vector of length 12, which
 can be accessed by various "output commands"_Howto_output.html.  The
 scalar is the magnitude of the bias potential (energy units) applied on
 the current timestep.  The vector stores the following quantities:
 
 1 = boost factor on this step (unitless)
-2 = max strain Eij of any bond on this step (unitless)
+2 = max strain Eij of any bond on this step (absolute value, unitless)
 3 = ID of first atom in the max-strain bond
 4 = ID of second atom in the max-strain bond
 5 = average # of bonds/atom on this step :ul
 
-6 = fraction of timesteps with bias = 0.0 during this run
-7 = max drift distance of any atom during this run (distance units)
-8 = max bond length during this run (distance units) :ul
+6 = fraction of timesteps where the biased bond has bias = 0.0 during this run
+7 = fraction of timesteps where the biased bond has negative strain during this run
+8 = max drift distance of any atom during this run (distance units)
+9 = max bond length during this run (distance units) :ul
 
-9 = cumulative hyper time since fix was defined (time units)
-10 = cumulative count of event timesteps since fix was defined
-11 = cumulative count of atoms in events since fix was defined :ul
+10 = cumulative hyper time since fix was defined (time units)
+11 = cumulative count of event timesteps since fix was defined
+12 = cumulative count of atoms in events since fix was defined :ul
 
-The first 5 quantities are for the current timestep.  Quantities 6-8
-are for the current hyper run.  Quantities 9-11 are cumulative across
-multiple runs (since the fix was defined in the input script).
+The first 5 quantities are for the current timestep.  Quantities 6-9
+are for the current hyper run.  They are reset each time a new hyper
+run is performed.  Quantities 19-12 are cumulative across multiple
+runs (since the point in the input script the fix was defined).
 
-For value 7, drift is the distance an atom moves between timesteps
-when the bond list is reset, i.e. between events.  Atoms involved in
-an event will typically move the greatest distance since others are
-typically oscillating around their lattice site.
+For value 8, drift is the distance an atom moves between two quenched
+states when the second quench determines an event has occurred.  Atoms
+involved in an event will typically move the greatest distance since
+others typically remain near their original quenched position.
 
-For value 10, events are checked for by the "hyper"_hyper.html command
+For value 11, events are checked for by the "hyper"_hyper.html command
 once every {Nevent} timesteps.  This value is the count of those
 timesteps on which one (or more) events was detected.  It is NOT the
 number of distinct events, since more than one event may occur in the
 same {Nevent} time window.
 
-For value 11, each time the "hyper"_hyper.html command checks for an
+For value 12, each time the "hyper"_hyper.html command checks for an
 event, it invokes a compute to flag zero or more atoms as
 participating in one or more events.  E.g. atoms that have displaced
 more than some distance from the previous quench state.  Value 11 is
diff --git a/doc/src/fix_hyper_local.txt b/doc/src/fix_hyper_local.txt
index c34b9ba7da..185fa8f20b 100644
--- a/doc/src/fix_hyper_local.txt
+++ b/doc/src/fix_hyper_local.txt
@@ -22,10 +22,9 @@ Dcut = minimum distance between boosted bonds (distance units) :l
 alpha = boostostat relaxation time (time units) :l
 Btarget = desired time boost factor (unitless) :l
 zero or more keyword/value pairs may be appended :l
-keyword = {lost} or {check/bias} or {check/coeff}
-  {lostbond} value = error/warn/ignore
-  {check/bias} values = Nevery error/warn/ignore
-  {check/coeff} values = Nevery error/warn/ignore :pre
+keyword = {check/ghost} or {check/bias} :l
+  {check/ghost} values = none
+  {check/bias} values = Nevery error/warn/ignore :pre
 :ule
 
 [Examples:]
@@ -65,8 +64,8 @@ To understand this description, you should first read the description
 of the GHD algorithm on the "fix hyper/global"_fix_hyper_global.html
 doc page.  This description of LHD builds on the GHD description.
 
-The definition of bonds, Eij, and Emax are the same for GHD and LHD.
-The formulas for Vij(max) and Fij(max) are also the same except for a
+The definition of bonds and Eij are the same for GHD and LHD.  The
+formulas for Vij(max) and Fij(max) are also the same except for a
 pre-factor Cij, explained below.
 
 The bias energy Vij applied to a bond IJ with maximum strain is
@@ -117,11 +116,11 @@ where Vkl(max) is the bias energy of the maxstrain bond KL within bond
 IJ's neighborhood, beta = 1/kTequil, and {Tequil} is the temperature
 of the system and an argument to this fix.
 
-NOTE: To run LHD, the input script must also use the "fix
-langevin"_fix_langevin.html command to thermostat the atoms at the
-same {Tequil} as specified by this fix, so that the system is running
-constant-temperature (NVT) dynamics.  LAMMPS does not check that this
-is done.
+NOTE: To run an LHD simulation, the input script must also use the
+"fix langevin"_fix_langevin.html command to thermostat the atoms at
+the same {Tequil} as specified by this fix, so that the system is
+running constant-temperature (NVT) dynamics.  LAMMPS does not check
+that this is done.
 
 Note that if IJ = KL, then bond IJ is a biased bond on that timestep,
 otherwise it is not.  But regardless, the boost factor Bij can be
@@ -216,20 +215,20 @@ each pair.  E.g. something like 2x the cutoff of the interatomic
 potential.  In practice a {Dcut} value of ~10 Angstroms seems to work
 well for many solid-state systems.
 
-NOTE: You must also insure that ghost atom communication is performed
-for a distance of at least {Dcut} + {cutevent} where {cutevent} = the
-distance one or more atoms move (between quenched states) to be
-considered an "event".  It is an argument to the "compute
-event/displace" command used to detect events.  By default the ghost
-communication distance is set by the pair_style cutoff, which will
-typically be < {Dcut}.  The "comm_modify cutoff"_comm_modify.html
-command can be used to set the ghost cutoff explicitly, e.g.
+NOTE: You should insure that ghost atom communication is performed for
+a distance of at least {Dcut} + {cutevent} = the distance one or more
+atoms move (between quenched states) to be considered an "event".  It
+is an argument to the "compute event/displace" command used to detect
+events.  By default the ghost communication distance is set by the
+pair_style cutoff, which will typically be < {Dcut}.  The "comm_modify
+cutoff"_comm_modify.html command should be used to override the ghost
+cutoff explicitly, e.g.
 
 comm_modify cutoff 12.0 :pre
 
-This fix does not know the {cutevent} parameter, but uses half the
-bond length as an estimate to warn if the ghost cutoff is not long
-enough.
+Note that this fix does not know the {cutevent} parameter, but uses
+half the {cutbond} parameter as an estimate to warn if the ghost
+cutoff is not long enough.
 
 As described above the {alpha} argument is a pre-factor in the
 boostostat update equation for each bond's Cij prefactor.  {Alpha} is
@@ -269,7 +268,30 @@ NOTE: If you have no physical intuition as to the smallest barrier
 height in your system, a reasonable strategy to determine the largest
 {Btarget} you can use for an LHD model, is to run a sequence of
 simulations with smaller and smaller {Btarget} values, until the event
-rate does not change.
+rate does not change (as a function of hyper time).
+
+:line
+
+Here is additional information on the optional keywords for this fix.
+
+The {check/ghost} keyword turns on extra computation each timestep to
+compute statistics about ghost atoms used to determine which bonds to
+bias.  The output of these stats are the vector values 14 and 15,
+described below.  If this keyword is not enabled, the output
+of the stats will be zero.
+
+The {check/bias} keyword turns on extra computation and communication
+to check if any biased bonds are closer than {Dcut} to each other,
+which should not be the case if LHD is operating correctly.  Thus it
+is a debugging check.  The {Nevery} setting determines how often the
+check is made.  The {error}, {warn}, or {ignore} setting determines
+what is done if the count of too-close bonds is not zero.  Either the
+code will exit, or issue a warning, or silently tally the count.  The
+count can be output as vector value 17, as described below.  If this
+keyword is not enabled, the output of that statistic will be 0.
+
+Note that both of these computations are costly, hence they are only
+enabled by these keywords.
 
 :line
 
@@ -282,95 +304,120 @@ The "fix_modify"_fix_modify.html {energy} option is supported by this
 fix to add the energy of the bias potential to the the system's
 potential energy as part of "thermodynamic output"_thermo_style.html.
 
-This fix computes a global scalar and global vector of length 23,
-which can be accessed by various "output
-commands"_Howto_output.html.  The scalar is the magnitude of
-the bias potential (energy units) applied on the current timestep,
-summed over all biased bonds.  The vector stores the following
-quantities:
+This fix computes a global scalar and global vector of length 21,
+which can be accessed by various "output commands"_Howto_output.html.
+The scalar is the magnitude of the bias potential (energy units)
+applied on the current timestep, summed over all biased bonds.  The
+vector stores the following quantities:
 
 1 = # of biased bonds on this step
-2 = max strain Eij of any bond on this step (unitless)
-3 = average bias potential for all biased bonds on this step (energy units)
+2 = max strain Eij of any bond on this step (absolute value, unitless)
+3 = average bias coeff for all bonds on this step (unitless)
 4 = average # of bonds/atom on this step
 5 = average neighbor bonds/bond on this step within {Dcut} :ul
 
-6 = fraction of steps and bonds with no bias during this run
-7 = max drift distance of any atom during this run (distance units)
-8 = max bond length during this run (distance units)
-9 = average # of biased bonds/step during this run
-10 = average bias potential for all biased bonds during this run (energy units)
-11 = max bias potential for any biased bond during this run (energy units)
-12 = min bias potential for any biased bond during this run (energy units)
-13 = max distance from my sub-box of any ghost atom with maxstrain < qfactor during this run (distance units)
-14 = max distance outside my box of any ghost atom with any maxstrain during this run (distance units)
-15 = count of ghost neighbor atoms not found on reneighbor steps during this run
-16 = count of lost bond partners during this run
-17 = average bias coeff for lost bond partners during this run
-18 = count of bias overlaps found during this run
-19 = count of non-matching bias coefficients found during this run :ul
+6 = max bond length during this run (distance units)
+7 = average # of biased bonds/step during this run
+8 = fraction of biased bonds with no bias during this run
+9 = fraction of biased bonds with negative strain during this run
+10 = average bias coeff for all bonds during this run (unitless)
+11 = min bias coeff for any bond during this run (unitless)
+12 = max bias coeff for any bond during this run (unitless)
 
-20 = cumulative hyper time since fix created (time units)
-21 = cumulative count of event timesteps since fix created
-22 = cumulative count of atoms in events since fix created
-23 = cumulative # of new bonds since fix created :ul
+13 = max drift distance of any bond atom during this run (distance units)
+14 = max distance from proc subbox of any ghost atom with maxstrain < qfactor during this run (distance units)
+15 = max distance outside my box of any ghost atom with any maxstrain during this run (distance units)
+16 = count of ghost atoms that could not be found on reneighbor steps during this run
+17 = count of bias overlaps (< Dcut) found during this run
+
+18 = cumulative hyper time since fix created (time units)
+19 = cumulative count of event timesteps since fix created
+20 = cumulative count of atoms in events since fix created
+21 = cumulative # of new bonds formed since fix created :ul
 
 The first quantities (1-5) are for the current timestep.  Quantities
-6-19 are for the current hyper run.  They are reset each time a new
-hyper run is performed.  Quantities 20-23 are cumulative across
-multiple runs (since the fix was defined in the input script).
+6-17 are for the current hyper run.  They are reset each time a new
+hyper run is performed.  Quantities 18-21 are cumulative across
+multiple runs (since the point in the input script the fix was
+defined).
 
-For value 6, the numerator is a count of all biased bonds on every
+For value 8, the numerator is a count of all biased bonds on each
 timestep whose bias energy = 0.0 due to Eij >= {qfactor}.  The
 denominator is the count of all biased bonds on all timesteps.
 
-For value 7, drift is the distance an atom moves between timesteps
-when the bond list is reset, i.e. between events.  Atoms involved in
-an event will typically move the greatest distance since others are
-typically oscillating around their lattice site.
+For value 9, the numerator is a count of all biased bonds on each
+timestep with negative strain.  The denominator is the count of all
+biased bonds on all timesteps.
 
-For values 13 and 14, the maxstrain of a ghost atom is the maxstrain
-of any bond it is part of, and it is checked for ghost atoms within
-the bond neighbor cutoff.
+Values 13-17 are mostly useful for debugging and diagnostic purposes.
 
-Values 15-19 are mostly useful for debugging and diagnostic purposes.
+For value 13, drift is the distance an atom moves between two quenched
+states when the second quench determines an event has occurred.  Atoms
+involved in an event will typically move the greatest distance since
+others typically remain near their original quenched position.
 
-For values 15-17, it is possible that a ghost atom owned by another
-processor will move far enough (e.g. as part of an event-in-progress)
-that it will no longer be within the communication cutoff distance for
-acquiring ghost atoms.  Likewise it may be a ghost atom bond partner
-that cannot be found because it has moved too far.  These values count
-those occurrences.  Because they typically involve atoms that are part
-of events, they do not usually indicate bad dynamics.  Value 16 is the
-average bias coefficient for bonds where a partner atom was lost.
+For values 14-16, neighbor atoms in the full neighbor list with cutoff
+{Dcut} may be ghost atoms outside a processor's sub-box.  Before the
+next event occurs they may move further than {Dcut} away from the
+sub-box boundary.  Value 14 is the furthest (from the sub-box) any
+ghost atom in the neighbor list with maxstrain < {qfactor} was
+accessed during the run.  Value 15 is the same except that the ghost
+atom's maxstrain may be >= {qfactor}, which may mean it is about to
+participate in an event.  Value 16 is a count of how many ghost atoms
+could not be found on reneighbor steps, presumably because they moved
+too far away due to their participation in an event (which will likely
+be detected at the next quench).
 
-For value 18, no two bonds should be biased if they are within a
+Typical values for 14 and 15 should be slightly larger than {Dcut},
+which accounts for ghost atoms initially at a {Dcut} distance moving
+thermally before the next event takes place.
+
+Note that for values 14 and 15 to be computed, the optional keyword
+{check/ghost} must be specified.  Otherwise these values will be zero.
+This is because computing them incurs overhead, so the values are only
+computed if requested.
+
+Value 16 should be zero or small.  As explained above a small count
+likely means some ghost atoms were participating in their own events
+and moved a longer distance.  If the value is large, it likely means
+the communication cutoff for ghosts is too close to {Dcut} leading to
+many not-found ghost atoms before the next event.  This may lead to a
+reduced number of bonds being selected for biasing, since the code
+assumes those atoms are part of highly strained bonds.  As explained
+above, the "comm_modify cutoff"_comm_modify.html command can be used
+to set a longer cutoff.
+
+For value 17, no two bonds should be biased if they are within a
 {Dcut} distance of each other.  This value should be zero, indicating
-that no pair of bonds "overlap", meaning they are closer than {Dcut}
-from each other.
+that no pair of biased bonds are closer than {Dcut} from each other.
 
-For value 19, the same bias coefficient is stored by both atoms in an
-IJ bond.  This value should be zero, indicating that for all bonds,
-each atom in the bond stores the a bias coefficient with the same
-value.
+Note that for values 17 to be computed, the optional keyword
+{check/bias} must be specified and it determines how often this check
+is performed.  This is because performing the check incurs overhead,
+so if only computed as often as requested.
 
-Value 20 is simply the specified {boost} factor times the number of
-timestep times the timestep size.
+The result at the end of the run is the cumulative total from every
+timestep the check was made.  Note that the value is a count of atoms
+in bonds which found other atoms in bonds too close, so it is almost
+always an over-count of the number of too-close bonds.
 
-For value 21, events are checked for by the "hyper"_hyper.html command
+Value 18 is simply the specified {boost} factor times the number of
+timesteps times the timestep size.
+
+For value 19, events are checked for by the "hyper"_hyper.html command
 once every {Nevent} timesteps.  This value is the count of those
 timesteps on which one (or more) events was detected.  It is NOT the
 number of distinct events, since more than one event may occur in the
 same {Nevent} time window.
 
-For value 22, each time the "hyper"_hyper.html command checks for an
+For value 20, each time the "hyper"_hyper.html command checks for an
 event, it invokes a compute to flag zero or more atoms as
 participating in one or more events.  E.g. atoms that have displaced
-more than some distance from the previous quench state.  Value 22 is
+more than some distance from the previous quench state.  Value 20 is
 the cumulative count of the number of atoms participating in any of
 the events that were found.
 
-Value 23 tallies the number of new bonds created by the bond reset
+Value 21 tallies the number of new bonds created by the bond reset
 operation.  Bonds between a specific I,J pair of atoms may persist for
 the entire hyperdynamics simulation if neither I or J are involved in
 an event.
@@ -378,6 +425,16 @@ an event.
 The scalar and vector values calculated by this fix are all
 "intensive".
 
+This fix also computes a local vector of length the number of bonds
+currently in the system.  The value for each bond is its Cij prefactor
+(bias coefficient).  These values can be can be accessed by various
+"output commands"_Howto_output.html.  A particularly useful one is the
+"fix ave/histo"_fix_ave_histo.html command which can be used to
+histogram the Cij values to see if they are distributed reasonably
+close to 1.0, which indicates a good choice of {Vmax}.
+
+The local values calculated by this fix are unitless.
+
 No parameter of this fix can be used with the {start/stop} keywords of
 the "run"_run.html command.  This fix is not invoked during "energy
 minimization"_minimize.html.
@@ -392,7 +449,9 @@ doc page for more info.
 
 "hyper"_hyper.html, "fix hyper/global"_fix_hyper_global.html
 
-[Default:] None
+[Default:]
+
+The check/ghost and check/bias keywords are not enabled by default.
 
 :line
 
diff --git a/doc/src/fix_wall_gran.txt b/doc/src/fix_wall_gran.txt
index 871ee2e5d1..b517d48cca 100644
--- a/doc/src/fix_wall_gran.txt
+++ b/doc/src/fix_wall_gran.txt
@@ -7,22 +7,24 @@
 :line
 
 fix wall/gran command :h3
-fix wall/gran/omp command :h3
 
 [Syntax:]
 
-fix ID group-ID wall/gran fstyle Kn Kt gamma_n gamma_t xmu dampflag wallstyle args keyword values ... :pre
+fix ID group-ID wall/gran fstyle fstyle_params wallstyle args keyword values ... :pre
 
 ID, group-ID are documented in "fix"_fix.html command :ulb,l
 wall/gran = style name of this fix command :l
 fstyle = style of force interactions between particles and wall :l
-  possible choices: hooke, hooke/history, hertz/history :pre
-Kn = elastic constant for normal particle repulsion (force/distance units or pressure units - see discussion below) :l
-Kt = elastic constant for tangential contact (force/distance units or pressure units - see discussion below) :l
-gamma_n = damping coefficient for collisions in normal direction (1/time units or 1/time-distance units - see discussion below) :l
-gamma_t = damping coefficient for collisions in tangential direction (1/time units or 1/time-distance units - see discussion below) :l
-xmu = static yield criterion (unitless value between 0.0 and 1.0e4) :l
-dampflag = 0 or 1 if tangential damping force is excluded or included :l
+  possible choices: hooke, hooke/history, hertz/history, granular :pre
+fstyle_params = parameters associated with force interaction style :l
+  For {hooke}, {hooke/history}, and {hertz/history}, {fstyle_params} are: 
+	Kn = elastic constant for normal particle repulsion (force/distance units or pressure units - see discussion below) 
+	Kt = elastic constant for tangential contact (force/distance units or pressure units - see discussion below) 
+	gamma_n = damping coefficient for collisions in normal direction (1/time units or 1/time-distance units - see discussion below) 
+	gamma_t = damping coefficient for collisions in tangential direction (1/time units or 1/time-distance units - see discussion below)  
+	xmu = static yield criterion (unitless value between 0.0 and 1.0e4) 
+	dampflag = 0 or 1 if tangential damping force is excluded or included :pre
+  For {granular}, {fstyle_params} are set using the same syntax as for the {pair_coeff} command of "pair_style granular"_pair_granular.html :pre
 wallstyle = {xplane} or {yplane} or {zplane} or {zcylinder} :l
 args = list of arguments for a particular style :l
   {xplane} or {yplane} or {zplane} args = lo hi
@@ -44,7 +46,10 @@ keyword = {wiggle} or {shear} :l
 
 fix 1 all wall/gran hooke  200000.0 NULL 50.0 NULL 0.5 0 xplane -10.0 10.0
 fix 1 all wall/gran hooke/history 200000.0 NULL 50.0 NULL 0.5 0 zplane 0.0 NULL
-fix 2 all wall/gran hooke 100000.0 20000.0 50.0 30.0 0.5 1 zcylinder 15.0 wiggle z 3.0 2.0 :pre
+fix 2 all wall/gran hooke 100000.0 20000.0 50.0 30.0 0.5 1 zcylinder 15.0 wiggle z 3.0 2.0 
+fix 3 all wall/gran granular hooke 1000.0 50.0 tangential linear_nohistory 1.0 0.4 zplane 0.0 NULL
+fix 4 all wall/gran granular jkr 1000.0 50.0 0.3 5.0 tangential mindlin 800.0 1.0 0.5 rolling sds 500.0 200.0 0.5 twisting marshall zcylinder 15.0 wiggle z 3.0 2.0
+fix 5 all wall/gran granular dmt 1000.0 50.0 0.3 10.0 tangential mindlin 800.0 0.5 0.1 roll sds 500.0 200.0 0.1 twisting marshall zplane 0.0 NULL :pre
 
 [Description:]
 
@@ -54,31 +59,40 @@ close enough to touch it.
 
 The nature of the wall/particle interactions are determined by the
 {fstyle} setting.  It can be any of the styles defined by the
-"pair_style granular"_pair_gran.html commands.  Currently this is
-{hooke}, {hooke/history}, or {hertz/history}.  The equation for the
-force between the wall and particles touching it is the same as the
-corresponding equation on the "pair_style granular"_pair_gran.html doc
-page, in the limit of one of the two particles going to infinite
-radius and mass (flat wall).  Specifically, delta = radius - r =
-overlap of particle with wall, m_eff = mass of particle, and the
-effective radius of contact = RiRj/Ri+Rj is just the radius of the
-particle.
+"pair_style gran/*"_pair_gran.html or the more general "pair_style
+granular"_pair_granular.html" commands.  Currently the options are
+{hooke}, {hooke/history}, or {hertz/history} for the former, and
+{granular} with all the possible options of the associated
+{pair_coeff} command for the latter.  The equation for the force
+between the wall and particles touching it is the same as the
+corresponding equation on the "pair_style gran/*"_pair_gran.html and
+"pair_style_granular"_pair_granular.html doc pages, in the limit of
+one of the two particles going to infinite radius and mass (flat
+wall).  Specifically, delta = radius - r = overlap of particle with
+wall, m_eff = mass of particle, and the effective radius of contact =
+RiRj/Ri+Rj is set to the radius of the particle.
 
 The parameters {Kn}, {Kt}, {gamma_n}, {gamma_t}, {xmu} and {dampflag}
 have the same meaning and units as those specified with the
-"pair_style granular"_pair_gran.html commands.  This means a NULL can
-be used for either {Kt} or {gamma_t} as described on that page.  If a
+"pair_style gran/*"_pair_gran.html commands.  This means a NULL can be
+used for either {Kt} or {gamma_t} as described on that page.  If a
 NULL is used for {Kt}, then a default value is used where {Kt} = 2/7
 {Kn}.  If a NULL is used for {gamma_t}, then a default value is used
 where {gamma_t} = 1/2 {gamma_n}.
 
+All the model choices for cohesion, tangential friction, rolling
+friction and twisting friction supported by the "pair_style
+granular"_pair_granular.html through its {pair_coeff} command are also
+supported for walls. These are discussed in greater detail on the doc
+page for "pair_style granular"_pair_granular.html.
+
 Note that you can choose a different force styles and/or different
-values for the 6 wall/particle coefficients than for particle/particle
+values for the wall/particle coefficients than for particle/particle
 interactions.  E.g. if you wish to model the wall as a different
 material.
 
 NOTE: As discussed on the doc page for "pair_style
-granular"_pair_gran.html, versions of LAMMPS before 9Jan09 used a
+gran/*"_pair_gran.html, versions of LAMMPS before 9Jan09 used a
 different equation for Hertzian interactions.  This means Hertizian
 wall/particle interactions have also changed.  They now include a
 sqrt(radius) term which was not present before.  Also the previous
@@ -108,14 +122,14 @@ Optionally, the wall can be moving, if the {wiggle} or {shear}
 keywords are appended.  Both keywords cannot be used together.
 
 For the {wiggle} keyword, the wall oscillates sinusoidally, similar to
-the oscillations of particles which can be specified by the
-"fix move"_fix_move.html command.  This is useful in packing
-simulations of granular particles.  The arguments to the {wiggle}
-keyword specify a dimension for the motion, as well as it's
-{amplitude} and {period}.  Note that if the dimension is in the plane
-of the wall, this is effectively a shearing motion.  If the dimension
-is perpendicular to the wall, it is more of a shaking motion.  A
-{zcylinder} wall can only be wiggled in the z dimension.
+the oscillations of particles which can be specified by the "fix
+move"_fix_move.html command.  This is useful in packing simulations of
+granular particles.  The arguments to the {wiggle} keyword specify a
+dimension for the motion, as well as it's {amplitude} and {period}.
+Note that if the dimension is in the plane of the wall, this is
+effectively a shearing motion.  If the dimension is perpendicular to
+the wall, it is more of a shaking motion.  A {zcylinder} wall can only
+be wiggled in the z dimension.
 
 Each timestep, the position of a wiggled wall in the appropriate {dim}
 is set according to this equation:
@@ -137,28 +151,6 @@ the clockwise direction for {vshear} > 0 or counter-clockwise for
 {vshear} < 0.  In this case, {vshear} is the tangential velocity of
 the wall at whatever {radius} has been defined.
 
-:line
-
-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 "Speed packages"_Speed_packages.html 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, USER-INTEL, KOKKOS,
-USER-OMP and OPT packages, respectively.  They are only enabled if
-LAMMPS was built with those packages.  See the "Build
-package"_Build_package.html doc page for more info.
-
-You can specify the accelerated styles explicitly in your input script
-by including their suffix, or you can use the "-suffix command-line
-switch"_Run_options.html when you invoke LAMMPS, or you can use the
-"suffix"_suffix.html command in your input script.
-
-See the "Speed packages"_Speed_packages.html doc page for more
-instructions on how to use the accelerated styles effectively.
-
 [Restart, fix_modify, output, run start/stop, minimize info:]
 
 This fix writes the shear friction state of atoms interacting with the
@@ -188,6 +180,7 @@ Any dimension (xyz) that has a granular wall must be non-periodic.
 
 "fix move"_fix_move.html,
 "fix wall/gran/region"_fix_wall_gran_region.html,
-"pair_style granular"_pair_gran.html
+"pair_style gran/*"_pair_gran.html
+"pair_style granular"_pair_granular.html
 
 [Default:] none
diff --git a/doc/src/fix_wall_gran_region.txt b/doc/src/fix_wall_gran_region.txt
index e4145c003e..8a39d6b642 100644
--- a/doc/src/fix_wall_gran_region.txt
+++ b/doc/src/fix_wall_gran_region.txt
@@ -10,24 +10,30 @@ fix wall/gran/region command :h3
 
 [Syntax:]
 
-fix ID group-ID wall/gran/region fstyle Kn Kt gamma_n gamma_t xmu dampflag wallstyle regionID :pre
+fix ID group-ID wall/gran/region fstyle fstyle_params wallstyle regionID :pre
 
 ID, group-ID are documented in "fix"_fix.html command :ulb,l
 wall/region = style name of this fix command :l
 fstyle = style of force interactions between particles and wall :l
-  possible choices: hooke, hooke/history, hertz/history :pre
-Kn = elastic constant for normal particle repulsion (force/distance units or pressure units - see discussion below) :l
-Kt = elastic constant for tangential contact (force/distance units or pressure units - see discussion below) :l
-gamma_n = damping coefficient for collisions in normal direction (1/time units or 1/time-distance units - see discussion below) :l
-gamma_t = damping coefficient for collisions in tangential direction (1/time units or 1/time-distance units - see discussion below) :l
-xmu = static yield criterion (unitless value between 0.0 and 1.0e4) :l
-dampflag = 0 or 1 if tangential damping force is excluded or included :l
+  possible choices: hooke, hooke/history, hertz/history, granular :pre
+fstyle_params = parameters associated with force interaction style :l
+  For {hooke}, {hooke/history}, and {hertz/history}, {fstyle_params} are: 
+	Kn = elastic constant for normal particle repulsion (force/distance units or pressure units - see discussion below) 
+	Kt = elastic constant for tangential contact (force/distance units or pressure units - see discussion below) 
+	gamma_n = damping coefficient for collisions in normal direction (1/time units or 1/time-distance units - see discussion below) 
+	gamma_t = damping coefficient for collisions in tangential direction (1/time units or 1/time-distance units - see discussion below)  
+	xmu = static yield criterion (unitless value between 0.0 and 1.0e4) 
+	dampflag = 0 or 1 if tangential damping force is excluded or included :pre
+  For {granular}, {fstyle_params} are set using the same syntax as for the {pair_coeff} command of "pair_style granular"_pair_granular.html :pre
 wallstyle = region (see "fix wall/gran"_fix_wall_gran.html for options for other kinds of walls) :l
 region-ID = region whose boundary will act as wall :l,ule
 
 [Examples:]
 
-fix wall all wall/gran/region hooke/history 1000.0 200.0 200.0 100.0 0.5 1 region myCone :pre
+fix wall all wall/gran/region hooke/history 1000.0 200.0 200.0 100.0 0.5 1 region myCone 
+fix 3 all wall/gran/region granular hooke 1000.0 50.0 tangential linear_nohistory 1.0 0.4 region myBox
+fix 4 all wall/gran/region granular jkr 1000.0 50.0 tangential linear_history 800.0 1.0 0.5 rolling sds 500.0 200.0 0.5 twisting marshall region myCone
+fix 5 all wall/gran/region granular dmt 1000.0 50.0 0.3 10.0 tangential linear_history 800.0 0.5 0.1 roll sds 500.0 200.0 0.1 twisting marshall region myCone :pre
 
 [Description:]
 
@@ -42,8 +48,8 @@ Here are snapshots of example models using this command.
 Corresponding input scripts can be found in examples/granregion.
 Click on the images to see a bigger picture.  Movies of these
 simulations are "here on the Movies
-page"_http://lammps.sandia.gov/movies.html#granregion of the
-LAMMPS web site.
+page"_http://lammps.sandia.gov/movies.html#granregion of the LAMMPS
+web site.
 
 :image(JPG/gran_funnel_small.jpg,JPG/gran_funnel.png)
 :image(JPG/gran_mixer_small.jpg,JPG/gran_mixer.png)
@@ -123,12 +129,16 @@ to make the two faces differ by epsilon in their position.
 
 The nature of the wall/particle interactions are determined by the
 {fstyle} setting.  It can be any of the styles defined by the
-"pair_style granular"_pair_gran.html commands.  Currently this is
-{hooke}, {hooke/history}, or {hertz/history}.  The equation for the
-force between the wall and particles touching it is the same as the
-corresponding equation on the "pair_style granular"_pair_gran.html doc
-page, but the effective radius is calculated using the radius of the
-particle and the radius of curvature of the wall at the contact point.
+"pair_style gran/*"_pair_gran.html or the more general "pair_style
+granular"_pair_granular.html" commands.  Currently the options are
+{hooke}, {hooke/history}, or {hertz/history} for the former, and
+{granular} with all the possible options of the associated
+{pair_coeff} command for the latter.  The equation for the force
+between the wall and particles touching it is the same as the
+corresponding equation on the "pair_style gran/*"_pair_gran.html and
+"pair_style_granular"_pair_granular.html doc pages, but the effective
+radius is calculated using the radius of the particle and the radius
+of curvature of the wall at the contact point.
 
 Specifically, delta = radius - r = overlap of particle with wall,
 m_eff = mass of particle, and RiRj/Ri+Rj is the effective radius, with
@@ -141,12 +151,18 @@ particle.
 
 The parameters {Kn}, {Kt}, {gamma_n}, {gamma_t}, {xmu} and {dampflag}
 have the same meaning and units as those specified with the
-"pair_style granular"_pair_gran.html commands.  This means a NULL can
-be used for either {Kt} or {gamma_t} as described on that page.  If a
+"pair_style gran/*"_pair_gran.html commands.  This means a NULL can be
+used for either {Kt} or {gamma_t} as described on that page.  If a
 NULL is used for {Kt}, then a default value is used where {Kt} = 2/7
 {Kn}.  If a NULL is used for {gamma_t}, then a default value is used
 where {gamma_t} = 1/2 {gamma_n}.
 
+All the model choices for cohesion, tangential friction, rolling
+friction and twisting friction supported by the "pair_style
+granular"_pair_granular.html through its {pair_coeff} command are also
+supported for walls. These are discussed in greater detail on the doc
+page for "pair_style granular"_pair_granular.html.
+
 Note that you can choose a different force styles and/or different
 values for the 6 wall/particle coefficients than for particle/particle
 interactions.  E.g. if you wish to model the wall as a different
@@ -154,9 +170,9 @@ material.
 
 [Restart, fix_modify, output, run start/stop, minimize info:]
 
-Similar to "fix wall/gran"_fix_wall_gran.html command, this fix
-writes the shear friction state of atoms interacting with the wall to
-"binary restart files"_restart.html, so that a simulation can continue
+Similar to "fix wall/gran"_fix_wall_gran.html command, this fix writes
+the shear friction state of atoms interacting with the wall to "binary
+restart files"_restart.html, so that a simulation can continue
 correctly if granular potentials with shear "history" effects are
 being used.  This fix also includes info about a moving region in the
 restart file.  See the "read_restart"_read_restart.html command for
@@ -170,14 +186,14 @@ So you must re-define your region and if it is a moving region, define
 its motion attributes in a way that is consistent with the simulation
 that wrote the restart file.  In particular, if you want to change the
 region motion attributes (e.g. its velocity), then you should ensure
-the position/orientation of the region at the initial restart
-timestep is the same as it was on the timestep the restart file was
-written.  If this is not possible, you may need to ignore info in the
-restart file by defining a new fix wall/gran/region command in your
-restart script, e.g. with a different fix ID.  Or if you want to keep
-the shear history info but discard the region motion information, you
-can use the same fix ID for fix wall/gran/region, but assign it a
-region with a different region ID.
+the position/orientation of the region at the initial restart timestep
+is the same as it was on the timestep the restart file was written.
+If this is not possible, you may need to ignore info in the restart
+file by defining a new fix wall/gran/region command in your restart
+script, e.g. with a different fix ID.  Or if you want to keep the
+shear history info but discard the region motion information, you can
+use the same fix ID for fix wall/gran/region, but assign it a region
+with a different region ID.
 
 None of the "fix_modify"_fix_modify.html options are relevant to this
 fix.  No global or per-atom quantities are stored by this fix for
diff --git a/doc/src/fixes.txt b/doc/src/fixes.txt
index 3853bb77a9..d77acf946d 100644
--- a/doc/src/fixes.txt
+++ b/doc/src/fixes.txt
@@ -40,6 +40,7 @@ Fixes :h1
    fix_dt_reset
    fix_efield
    fix_ehex
+   fix_electron_stopping
    fix_enforce2d
    fix_eos_cv
    fix_eos_table
diff --git a/doc/src/kim_query.txt b/doc/src/kim_query.txt
new file mode 100644
index 0000000000..c581de0ebb
--- /dev/null
+++ b/doc/src/kim_query.txt
@@ -0,0 +1,46 @@
+"LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
+
+:link(lws,http://lammps.sandia.gov)
+:link(ld,Manual.html)
+:link(lc,Commands_all.html)
+
+:line
+
+kim_query command :h3
+
+[Syntax:]
+
+kim_query variable query_function web_query_flags :pre
+
+variable = name of a (string style) variable where the result of the query is stored
+query_function = name of the OpenKIM web API query function to be used
+web_query_flags = a series of keyword=value pairs that represent the web query; supported keywords depend on query function :ul
+
+[Examples:]
+
+kim_query latconst get_test_result test=TE_156715955670 model=MO_800509458712 &
+  prop=structure-cubic-crystal-npt species=\["Al"\] keys=\["a"\] units=\["angstrom"\] :pre
+
+[Description:]
+
+The kim_query command allows to retrieve properties from the OpenKIM
+through a web query. The result is stored in a string style
+"variable"_variable.html, the name of which must be given as the first
+argument of the kim_query command.  The second required argument is the
+name of the actual query function (e.g. {get_test_result}).  All following
+arguments are parameters handed over to the web query in the format
+{keyword=value}.  The list of supported keywords and the type of how
+the value has to be encoded depends on the query function used.  This
+mirrors the functionality available on the OpenKIM webpage at
+"https://query.openkim.org"_https://query.openkim.org/
+
+[Restrictions:]
+
+This command is part of the KIM package.  It is only enabled if
+LAMMPS was built with that package.  Furthermore, its correct
+functioning depends on compiling LAMMPS with libcurl support.
+See the "Build package"_Build_package.html doc page for more info.
+
+[Related commands:]
+
+"pair_style kim"_pair_kim.html, "variable"_variable.html
diff --git a/doc/src/lammps.book b/doc/src/lammps.book
index 198e234f0c..e97ef4b994 100644
--- a/doc/src/lammps.book
+++ b/doc/src/lammps.book
@@ -167,6 +167,7 @@ if.html
 include.html
 info.html
 jump.html
+kim_query.html
 label.html
 lattice.html
 log.html
@@ -174,6 +175,7 @@ mass.html
 message.html
 min_modify.html
 min_style.html
+min_spin.html
 minimize.html
 molecule.html
 neb.html
@@ -263,6 +265,7 @@ fix_drude_transform.html
 fix_dt_reset.html
 fix_efield.html
 fix_ehex.html
+fix_electron_stopping.html
 fix_enforce2d.html
 fix_eos_cv.html
 fix_eos_table.html
@@ -578,6 +581,7 @@ pair_extep.html
 pair_gauss.html
 pair_gayberne.html
 pair_gran.html
+pair_granular.html
 pair_gromacs.html
 pair_gw.html
 pair_ilp_graphene_hbn.html
diff --git a/doc/src/min_modify.txt b/doc/src/min_modify.txt
index 9408eea167..d342e8bf01 100644
--- a/doc/src/min_modify.txt
+++ b/doc/src/min_modify.txt
@@ -13,11 +13,15 @@ min_modify command :h3
 min_modify keyword values ... :pre
 
 one or more keyword/value pairs may be listed :ulb,l
-keyword = {dmax} or {line}
+keyword = {dmax} or {line} or {alpha_damp} or {discrete_factor}
   {dmax} value = max
     max = maximum distance for line search to move (distance units)
   {line} value = {backtrack} or {quadratic} or {forcezero}
-    backtrack,quadratic,forcezero = style of linesearch to use :pre
+    backtrack,quadratic,forcezero = style of linesearch to use 
+  {alpha_damp} value = damping
+    damping = fictitious Gilbert damping for spin minimization (adim)
+  {discrete_factor} value = factor
+    factor = discretization factor for adaptive spin timestep (adim) :pre
 :ule
 
 [Examples:]
@@ -65,6 +69,17 @@ difference of two large values (energy before and energy after) and
 that difference may be smaller than machine epsilon even if atoms
 could move in the gradient direction to reduce forces further.
 
+Keywords {alpha_damp} and {discrete_factor} only make sense when
+a "min_spin"_min_spin.html command is declared. 
+Keyword {alpha_damp} defines an analog of a magnetic Gilbert
+damping. It defines a relaxation rate toward an equilibrium for
+a given magnetic system. 
+Keyword {discrete_factor} defines a discretization factor for the
+adaptive timestep used in the {spin} minimization. 
+See "min_spin"_min_spin.html for more information about those
+quantities. 
+Default values are {alpha_damp} = 1.0 and {discrete_factor} = 10.0.
+
 [Restrictions:] none
 
 [Related commands:]
diff --git a/doc/src/min_spin.txt b/doc/src/min_spin.txt
new file mode 100644
index 0000000000..890e324aca
--- /dev/null
+++ b/doc/src/min_spin.txt
@@ -0,0 +1,65 @@
+"LAMMPS WWW Page"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
+
+:link(lws,http://lammps.sandia.gov)
+:link(ld,Manual.html)
+:link(lc,Commands_all.html)
+:line
+
+min_style spin command :h3
+
+[Syntax:]
+
+min_style spin :pre
+
+[Examples:]
+
+min_style 	spin :pre 
+
+[Description:]
+
+Apply a minimization algorithm to use when a "minimize"_minimize.html
+command is performed.
+
+Style {spin} defines a damped spin dynamics with an adaptive
+timestep, according to:
+
+:c,image(Eqs/min_spin_damping.jpg)
+
+with lambda a damping coefficient (similar to a Gilbert
+damping).
+Lambda can be defined by setting the {alpha_damp} keyword with the 
+"min_modify"_min_modify.html command. 
+
+The minimization procedure solves this equation using an
+adaptive timestep. The value of this timestep is defined 
+by the largest precession frequency that has to be solved in the 
+system:
+
+:c,image(Eqs/min_spin_timestep.jpg)
+
+with {|omega|_{max}} the norm of the largest precession frequency
+in the system (across all processes, and across all replicas if a
+spin/neb calculation is performed). 
+
+Kappa defines a discretization factor {discrete_factor} for the 
+definition of this timestep. 
+{discrete_factor} can be defined with the "min_modify"_min_modify.html
+command.
+
+NOTE: The {spin} style replaces the force tolerance by a torque
+tolerance. See "minimize"_minimize.html for more explanation. 
+
+[Restrictions:] 
+
+This minimization procedure is only applied to spin degrees of
+freedom for a frozen lattice configuration.
+
+[Related commands:]
+
+"min_style"_min_style.html, "minimize"_minimize.html, 
+"min_modify"_min_modify.html
+
+[Default:]
+
+The option defaults are {alpha_damp} = 1.0 and {discrete_factor} =
+10.0.
diff --git a/doc/src/min_style.txt b/doc/src/min_style.txt
index 4948a34864..c46c1492b4 100644
--- a/doc/src/min_style.txt
+++ b/doc/src/min_style.txt
@@ -11,11 +11,12 @@ min_style command :h3
 
 min_style style :pre
 
-style = {cg} or {hftn} or {sd} or {quickmin} or {fire} :ul
+style = {cg} or {hftn} or {sd} or {quickmin} or {fire} or {spin} :ul
 
 [Examples:]
 
 min_style cg
+min_style spin
 min_style fire :pre
 
 [Description:]
@@ -61,6 +62,10 @@ the velocity non-parallel to the current force vector.  The velocity
 of each atom is initialized to 0.0 by this style, at the beginning of
 a minimization.
 
+Style {spin} is a damped spin dynamics with an adaptive 
+timestep.
+See the "min/spin"_min_spin.html doc page for more information.
+
 Either the {quickmin} and {fire} styles are useful in the context of
 nudged elastic band (NEB) calculations via the "neb"_neb.html command.
 
diff --git a/doc/src/minimize.txt b/doc/src/minimize.txt
index 00de86c5f5..ecf1ad0fcf 100644
--- a/doc/src/minimize.txt
+++ b/doc/src/minimize.txt
@@ -103,6 +103,13 @@ the line search fails because the step distance backtracks to 0.0
 the number of outer iterations or timesteps exceeds {maxiter}
 the number of total force evaluations exceeds {maxeval} :ul
 
+NOTE: the "minimization style"_min_style.html {spin} replaces
+the force tolerance {ftol} by a torque tolerance.
+The minimization procedure stops if the 2-norm (length) of the 
+global torque vector (defined as the cross product between the 
+spins and their precession vectors omega) is less than {ftol}, 
+or if any of the other criteria are met.
+
 NOTE: You can also use the "fix halt"_fix_halt.html command to specify
 a general criterion for exiting a minimization, that is a calculation
 performed on the state of the current system, as defined by an
diff --git a/doc/src/pair_granular.txt b/doc/src/pair_granular.txt
new file mode 100644
index 0000000000..d287123246
--- /dev/null
+++ b/doc/src/pair_granular.txt
@@ -0,0 +1,765 @@
+<script type="text/javascript"
+  src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
+</script>
+<script type="text/x-mathjax-config">
+  MathJax.Hub.Config({ TeX: { equationNumbers: {autoNumber: "AMS"} } });
+</script>
+
+"LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
+
+:link(lws,http://lammps.sandia.gov)
+:link(ld,Manual.html)
+:link(lc,Commands_all.html)
+
+:line
+
+pair_style granular command :h3
+
+[Syntax:]
+
+pair_style granular cutoff :pre
+
+cutoff = global cutoff (optional).  See discussion below. :ul
+
+[Examples:]
+
+pair_style granular
+pair_coeff * * hooke 1000.0 50.0 tangential linear_nohistory 1.0 0.4 :pre
+
+pair_style granular
+pair_coeff * * hertz 1000.0 50.0 tangential mindlin NULL 1.0 0.4 :pre
+
+pair_style granular
+pair_coeff * * hertz/material 1e8 0.3 tangential mindlin_rescale NULL 1.0 0.4 damping tsuji :pre
+
+pair_style granular
+pair_coeff 1 1 jkr 1000.0 50.0 tangential mindlin 800.0 1.0 0.5 rolling sds 500.0 200.0 0.5 twisting marshall
+pair_coeff 2 2 hertz 200.0 20.0 tangential linear_history 300.0 1.0 0.1 rolling sds 200.0 100.0 0.1 twisting marshall :pre
+
+pair_style granular
+pair_coeff 1 1 hertz 1000.0 50.0 tangential mindlin 800.0 0.5 0.5 rolling sds 500.0 200.0 0.5 twisting marshall
+pair_coeff 2 2 dmt 1000.0 50.0 0.3 10.0 tangential mindlin 800.0 0.5 0.1 roll sds 500.0 200.0 0.1 twisting marshall
+pair_coeff 1 2 dmt 1000.0 50.0 0.3 10.0 tangential mindlin 800.0 0.5 0.1 roll sds 500.0 200.0 0.1 twisting marshall :pre
+
+[Description:]
+
+The {granular} styles support a variety of options for the normal,
+tangential, rolling and twisting forces resulting from contact between
+two granular particles. This expands on the options offered by the
+"pair gran/*"_pair_gran.html pair styles. The total computed forces
+and torques are the sum of various models selected for the normal,
+tangential, rolling and twisting modes of motion.
+
+All model choices and parameters are entered in the
+"pair_coeff"_pair_coeff.html command, as described below.  Unlike
+e.g. "pair gran/hooke"_pair_gran.html, coefficient values are not
+global, but can be set to different values for different combinations
+of particle types, as determined by the "pair_coeff"_pair_coeff.html
+command.  If the contact model choice is the same for two particle
+types, the mixing for the cross-coefficients can be carried out
+automatically. This is shown in the second example, where model
+choices are the same for type 1 - type 1 as for type 2 - type2
+interactions, but coefficients are different. In this case, the
+coefficients for type 2 - type interactions can be determined from
+mixing rules discussed below.  For additional flexibility,
+coefficients as well as model forms can vary between particle types,
+as shown in the third example: type 1- type 1 interactions are based
+on a Hertzian normal contact model and 2-2 interactions are based on a
+DMT cohesive model (see below).  In that example, 1-1 and 2-2
+interactions have different model forms, in which case mixing of
+coefficients cannot be determined, so 1-2 interactions must be
+explicitly defined via the {pair_coeff 1 2} command, otherwise an
+error would result.
+
+:line
+
+The first required keyword for the {pair_coeff} command is the normal
+contact model. Currently supported options for normal contact models
+and their required arguments are:
+
+{hooke} : \(k_n\), \(\eta_\{n0\}\) (or \(e\))
+{hertz} : \(k_n\), \(\eta_\{n0\}\) (or \(e\))
+{hertz/material} : E, \(\eta_\{n0\}\) (or \(e\)), \(\nu\)
+{dmt} : E, \(\eta_\{n0\}\) (or \(e\)), \(\nu\), \(\gamma\)
+{jkr} : E, \(\eta_\{n0\}\) (or \(e\)), \(\nu\), \(\gamma\) :ol
+
+Here, \(k_n\) is spring stiffness (with units that depend on model
+choice, see below); \(\eta_\{n0\}\) is a damping prefactor (or, in its
+place a coefficient of restitution \(e\), depending on the choice of
+damping mode, see below); E is Young's modulus in units of
+{force}/{length}^2, i.e. {pressure}; \(\nu\) is Poisson's ratio and
+\(\gamma\) is a surface energy density, in units of
+{energy}/{length}^2.
+
+For the {hooke} model, the normal, elastic component of force acting
+on particle {i} due to contact with particle {j} is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_\{ne, Hooke\} = k_N \delta_\{ij\} \mathbf\{n\}
+\end\{equation\}
+
+Where \(\delta = R_i + R_j - \|\mathbf\{r\}_\{ij\}\|\) is the particle
+overlap, \(R_i, R_j\) are the particle radii, \(\mathbf\{r\}_\{ij\} =
+\mathbf\{r\}_i - \mathbf\{r\}_j\) is the vector separating the two
+particle centers (note the i-j ordering so that \(F_\{ne\}\) is
+positive for repulsion), and \(\mathbf\{n\} =
+\frac\{\mathbf\{r\}_\{ij\}\}\{\|\mathbf\{r\}_\{ij\}\|\}\).  Therefore,
+for {hooke}, the units of the spring constant \(k_n\) are
+{force}/{distance}, or equivalently {mass}/{time^2}.
+
+For the {hertz} model, the normal component of force is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_\{ne, Hertz\} = k_N R_\{eff\}^\{1/2\}\delta_\{ij\}^\{3/2\} \mathbf\{n\}
+\end\{equation\}
+
+Here, \(R_\{eff\} = \frac\{R_i R_j\}\{R_i + R_j\}\) is the effective
+radius, denoted for simplicity as {R} from here on.  For {hertz}, the
+units of the spring constant \(k_n\) are {force}/{length}^2, or
+equivalently {pressure}.
+
+For the {hertz/material} model, the force is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_\{ne, Hertz/material\} = \frac\{4\}\{3\} E_\{eff\} R_\{eff\}^\{1/2\}\delta_\{ij\}^\{3/2\} \mathbf\{n\}
+\end\{equation\}
+
+Here, \(E_\{eff\} = E = \left(\frac\{1-\nu_i^2\}\{E_i\} +
+\frac\{1-\nu_j^2\}\{E_j\}\right)^\{-1\}\) is the effective Young's
+modulus, with \(\nu_i, \nu_j \) the Poisson ratios of the particles of
+types {i} and {j}. Note that if the elastic modulus and the shear
+modulus of the two particles are the same, the {hertz/material} model
+is equivalent to the {hertz} model with \(k_N = 4/3 E_\{eff\}\)
+
+The {dmt} model corresponds to the
+"(Derjaguin-Muller-Toporov)"_#DMT1975 cohesive model, where the force
+is simply Hertz with an additional attractive cohesion term:
+
+\begin\{equation\}
+\mathbf\{F\}_\{ne, dmt\} = \left(\frac\{4\}\{3\} E R^\{1/2\}\delta_\{ij\}^\{3/2\} - 4\pi\gamma R\right)\mathbf\{n\}
+\end\{equation\}
+
+The {jkr} model is the "(Johnson-Kendall-Roberts)"_#JKR1971 model,
+where the force is computed as:
+
+\begin\{equation\}
+\label\{eq:force_jkr\}
+\mathbf\{F\}_\{ne, jkr\} = \left(\frac\{4Ea^3\}\{3R\} - 2\pi a^2\sqrt\{\frac\{4\gamma E\}\{\pi a\}\}\right)\mathbf\{n\}
+\end\{equation\}
+
+Here, {a} is the radius of the contact zone, related to the overlap
+\(\delta\) according to:
+
+\begin\{equation\}
+\delta = a^2/R - 2\sqrt\{\pi \gamma a/E\}
+\end\{equation\}
+
+LAMMPS internally inverts the equation above to solve for {a} in terms
+of \(\delta\), then solves for the force in the previous
+equation. Additionally, note that the JKR model allows for a tensile
+force beyond contact (i.e. for \(\delta < 0\)), up to a maximum of
+\(3\pi\gamma R\) (also known as the 'pull-off' force).  Note that this
+is a hysteretic effect, where particles that are not contacting
+initially will not experience force until they come into contact
+\(\delta \geq 0\); as they move apart and (\(\delta < 0\)), they
+experience a tensile force up to \(3\pi\gamma R\), at which point they
+lose contact.
+
+:line
+
+In addition, the normal force is augmented by a damping term of the
+following general form:
+
+\begin\{equation\}
+\mathbf\{F\}_\{n,damp\} = -\eta_n \mathbf\{v\}_\{n,rel\}
+\end\{equation\}
+
+Here, \(\mathbf\{v\}_\{n,rel\} = (\mathbf\{v\}_j - \mathbf\{v\}_i)
+\cdot \mathbf\{n\}\) is the component of relative velocity along
+\(\mathbf\{n\}\).
+
+The optional {damping} keyword to the {pair_coeff} command followed by
+a keyword determines the model form of the damping factor \(\eta_n\),
+and the interpretation of the \(\eta_\{n0\}\) or \(e\) coefficients
+specified as part of the normal contact model settings. The {damping}
+keyword and corresponding model form selection may be appended
+anywhere in the {pair coeff} command.  Note that the choice of damping
+model affects both the normal and tangential damping (and depending on
+other settings, potentially also the twisting damping).  The options
+for the damping model currently supported are:
+
+{velocity}
+{viscoelastic}
+{tsuji} :ol
+
+If the {damping} keyword is not specified, the {viscoelastic} model is
+used by default.
+
+For {damping velocity}, the normal damping is simply equal to the
+user-specified damping coefficient in the {normal} model:
+
+\begin\{equation\}
+\eta_n = \eta_\{n0\}\
+\end\{equation\}
+
+Here, \(\gamma_n\) is the damping coefficient specified for the normal
+contact model, in units of {mass}/{time},
+
+The {damping viscoelastic} model is based on the viscoelastic
+treatment of "(Brilliantov et al)"_#Brill1996, where the normal
+damping is given by:
+
+\begin\{equation\}
+\eta_n = \eta_\{n0\}\ a m_\{eff\}
+\end\{equation\}
+
+Here, \(m_\{eff\} = m_i m_j/(m_i + m_j)\) is the effective mass, {a}
+is the contact radius, given by \(a =\sqrt\{R\delta\}\) for all models
+except {jkr}, for which it is given implicitly according to \(delta =
+a^2/R - 2\sqrt\{\pi \gamma a/E\}\).  In this case, \eta_\{n0\}\ is in
+units of 1/({time}*{distance}).
+
+The {tsuji} model is based on the work of "(Tsuji et
+al)"_#Tsuji1992. Here, the damping coefficient specified as part of
+the normal model is interpreted as a restitution coefficient
+\(e\). The damping constant \(\eta_n\) is given by:
+
+\begin\{equation\}
+\eta_n = \alpha (m_\{eff\}k_n)^\{1/2\}
+\end\{equation\}
+
+For normal contact models based on material parameters, \(k_n =
+4/3Ea\).  The parameter \(\alpha\) is related to the restitution
+coefficient {e} according to:
+
+\begin\{equation\}
+\alpha = 1.2728-4.2783e+11.087e^2-22.348e^3+27.467e^4-18.022e^5+4.8218e^6
+\end\{equation\}
+
+The dimensionless coefficient of restitution \(e\) specified as part
+of the normal contact model parameters should be between 0 and 1, but
+no error check is performed on this.
+
+The total normal force is computed as the sum of the elastic and
+damping components:
+
+\begin\{equation\}
+\mathbf\{F\}_n = \mathbf\{F\}_\{ne\} + \mathbf\{F\}_\{n,damp\}
+\end\{equation\}
+
+ :line
+
+The {pair_coeff} command also requires specification of the tangential
+contact model. The required keyword {tangential} is expected, followed
+by the model choice and associated parameters. Currently supported
+tangential model choices and their expected parameters are as follows:
+
+{linear_nohistory} : \(x_\{\gamma,t\}\), \(\mu_s\)
+{linear_history} : \(k_t\), \(x_\{\gamma,t\}\), \(\mu_s\)
+{mindlin} : \(k_t\) or NULL, \(x_\{\gamma,t\}\), \(\mu_s\)
+{mindlin_rescale} : \(k_t\) or NULL, \(x_\{\gamma,t\}\), \(\mu_s\) :ol
+
+Here, \(x_\{\gamma,t\}\) is a dimensionless multiplier for the normal
+damping \(\eta_n\) that determines the magnitude of the tangential
+damping, \(\mu_t\) is the tangential (or sliding) friction
+coefficient, and \(k_t\) is the tangential stiffness coefficient.
+
+For {tangential linear_nohistory}, a simple velocity-dependent Coulomb
+friction criterion is used, which mimics the behavior of the {pair
+gran/hooke} style. The tangential force (\mathbf\{F\}_t\) is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_t =  -min(\mu_t F_\{n0\}, \|\mathbf\{F\}_\mathrm\{t,damp\}\|) \mathbf\{t\}
+\end\{equation\}
+
+The tangential damping force \(\mathbf\{F\}_\mathrm\{t,damp\}\) is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_\mathrm\{t,damp\} = -\eta_t \mathbf\{v\}_\{t,rel\}
+\end\{equation\}
+
+The tangential damping prefactor \(\eta_t\) is calculated by scaling
+the normal damping \(\eta_n\) (see above):
+
+\begin\{equation\}
+\eta_t = -x_\{\gamma,t\} \eta_n
+\end\{equation\}
+
+The normal damping prefactor \(\eta_n\) is determined by the choice of
+the {damping} keyword, as discussed above.  Thus, the {damping}
+keyword also affects the tangential damping.  The parameter
+\(x_\{\gamma,t\}\) is a scaling coefficient. Several works in the
+literature use \(x_\{\gamma,t\} = 1\) ("Marshall"_#Marshall2009,
+"Tsuji et al"_#Tsuji1992, "Silbert et al"_#Silbert2001).  The relative
+tangential velocity at the point of contact is given by
+\(\mathbf\{v\}_\{t, rel\} = \mathbf\{v\}_\{t\} - (R_i\Omega_i +
+R_j\Omega_j) \times \mathbf\{n\}\), where \(\mathbf\{v\}_\{t\} =
+\mathbf\{v\}_r - \mathbf\{v\}_r\cdot\mathbf\{n\}\), \(\mathbf\{v\}_r =
+\mathbf\{v\}_j - \mathbf\{v\}_i\). The direction of the applied force
+is \(\mathbf\{t\} =
+\mathbf\{v_\{t,rel\}\}/\|\mathbf\{v_\{t,rel\}\}\|\).
+
+The normal force value \(F_\{n0\}\) used to compute the critical force
+depends on the form of the contact model. For non-cohesive models
+({hertz}, {hertz/material}, {hooke}), it is given by the magnitude of
+the normal force:
+
+\begin\{equation\}
+F_\{n0\} = \|\mathbf\{F\}_n\|
+\end\{equation\}
+
+For cohesive models such as {jkr} and {dmt}, the critical force is
+adjusted so that the critical tangential force approaches \(\mu_t
+F_\{pulloff\}\), see "Marshall"_#Marshall2009, equation 43, and
+"Thornton"_#Thornton1991.  For both models, \(F_\{n0\}\) takes the
+form:
+
+\begin\{equation\}
+F_\{n0\} = \|\mathbf\{F\}_ne + 2 F_\{pulloff\}\|
+\end\{equation\}
+
+Where \(F_\{pulloff\} = 3\pi \gamma R \) for {jkr}, and
+\(F_\{pulloff\} = 4\pi \gamma R \) for {dmt}.
+
+The remaining tangential options all use accumulated tangential
+displacement (i.e. contact history). This is discussed below in the
+context of the {linear_history} option, but the same treatment of the
+accumulated displacement applies to the other options as well.
+
+For {tangential linear_history}, the tangential force is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_t =  -min(\mu_t F_\{n0\}, \|-k_t\mathbf\{\xi\} + \mathbf\{F\}_\mathrm\{t,damp\}\|) \mathbf\{t\}
+\end\{equation\}
+
+Here, \(\mathbf\{\xi\}\) is the tangential displacement accumulated
+during the entire duration of the contact:
+
+\begin\{equation\}
+\mathbf\{\xi\} = \int_\{t0\}^t \mathbf\{v\}_\{t,rel\}(\tau) \mathrm\{d\}\tau
+\end\{equation\}
+
+This accumulated tangential displacement must be adjusted to account
+for changes in the frame of reference of the contacting pair of
+particles during contact. This occurs due to the overall motion of the
+contacting particles in a rigid-body-like fashion during the duration
+of the contact. There are two modes of motion that are relevant: the
+'tumbling' rotation of the contacting pair, which changes the
+orientation of the plane in which tangential displacement occurs; and
+'spinning' rotation of the contacting pair about the vector connecting
+their centers of mass (\(\mathbf\{n\}\)).  Corrections due to the
+former mode of motion are made by rotating the accumulated
+displacement into the plane that is tangential to the contact vector
+at each step, or equivalently removing any component of the tangential
+displacement that lies along \(\mathbf\{n\}\), and rescaling to
+preserve the magnitude.  This follows the discussion in
+"Luding"_#Luding2008, see equation 17 and relevant discussion in that
+work:
+
+\begin\{equation\}
+\mathbf\{\xi\} = \left(\mathbf\{\xi'\} - (\mathbf\{n\} \cdot \mathbf\{\xi'\})\mathbf\{n\}\right) \frac\{\|\mathbf\{\xi'\}\|\}\{\|\mathbf\{\xi'\}\| - \mathbf\{n\}\cdot\mathbf\{\xi'\}\}
+\label\{eq:rotate_displacements\}
+\end\{equation\}
+
+Here, \(\mathbf\{\xi'\}\) is the accumulated displacement prior to the
+current time step and \(\mathbf\{\xi\}\) is the corrected
+displacement. Corrections to the displacement due to the second mode
+of motion described above (rotations about \(\mathbf\{n\}\)) are not
+currently implemented, but are expected to be minor for most
+simulations.
+
+Furthermore, when the tangential force exceeds the critical force, the
+tangential displacement is re-scaled to match the value for the
+critical force (see "Luding"_#Luding2008, equation 20 and related
+discussion):
+
+\begin\{equation\}
+\mathbf\{\xi\} = -\frac\{1\}\{k_t\}\left(\mu_t F_\{n0\}\mathbf\{t\} + \mathbf\{F\}_\{t,damp\}\right)
+\end\{equation\}
+
+The tangential force is added to the total normal force (elastic plus
+damping) to produce the total force on the particle. The tangential
+force also acts at the contact point (defined as the center of the
+overlap region) to induce a torque on each particle according to:
+
+\begin\{equation\}
+\mathbf\{\tau\}_i = -(R_i - 0.5 \delta) \mathbf\{n\} \times \mathbf\{F\}_t
+\end\{equation\}
+
+\begin\{equation\}
+\mathbf\{\tau\}_j = -(R_j - 0.5 \delta) \mathbf\{n\} \times \mathbf\{F\}_t
+\end\{equation\}
+
+For {tangential mindlin}, the "Mindlin"_#Mindlin1949 no-slip solution is used, which differs from the {linear_history}
+option by an additional factor of {a}, the radius of the contact region. The tangential force is given by:
+
+\begin\{equation\}
+\mathbf\{F\}_t =  -min(\mu_t F_\{n0\}, \|-k_t a \mathbf\{\xi\} + \mathbf\{F\}_\mathrm\{t,damp\}\|) \mathbf\{t\}
+\end\{equation\}
+
+Here, {a} is the radius of the contact region, given by \(a = \delta
+R\) for all normal contact models, except for {jkr}, where it is given
+implicitly by \(\delta = a^2/R - 2\sqrt\{\pi \gamma a/E\}\), see
+discussion above. To match the Mindlin solution, one should set \(k_t
+= 8G\), where \(G\) is the shear modulus, related to Young's modulus
+\(E\) by \(G = E/(2(1+\nu))\), where \(\nu\) is Poisson's ratio. This
+can also be achieved by specifying {NULL} for \(k_t\), in which case a
+normal contact model that specifies material parameters \(E\) and
+\(\nu\) is required (e.g. {hertz/material}, {dmt} or {jkr}). In this
+case, mixing of the shear modulus for different particle types {i} and
+{j} is done according to:
+
+\begin\{equation\}
+1/G = 2(2-\nu_i)(1+\nu_i)/E_i + 2(2-\nu_j)(1+\nu_j)/E_j
+\end\{equation\}
+
+The {mindlin_rescale} option uses the same form as {mindlin}, but the
+magnitude of the tangential displacement is re-scaled as the contact
+unloads, i.e. if \(a < a_\{t_\{n-1\}\}\):
+
+\begin\{equation\}
+\mathbf\{\xi\} = \mathbf\{\xi_\{t_\{n-1\}\}\} \frac\{a\}\{a_\{t_\{n-1\}\}\}
+\end\{equation\}
+
+Here, \(t_\{n-1\}\) indicates the value at the previous time
+step. This rescaling accounts for the fact that a decrease in the
+contact area upon unloading leads to the contact being unable to
+support the previous tangential loading, and spurious energy is
+created without the rescaling above ("Walton"_#WaltonPC ). See also
+discussion in "Thornton et al, 2013"_#Thornton2013 , particularly
+equation 18(b) of that work and associated discussion.
+
+:line
+
+The optional {rolling} keyword enables rolling friction, which resists
+pure rolling motion of particles. The options currently supported are:
+
+{none}
+{sds} : \(k_\{roll\}\), \(\gamma_\{roll\}\), \(\mu_\{roll\}\)  :ol
+
+If the {rolling} keyword is not specified, the model defaults to {none}.
+
+For {rolling sds}, rolling friction is computed via a
+spring-dashpot-slider, using a 'pseudo-force' formulation, as detailed
+by "Luding"_#Luding2008. Unlike the formulation in
+"Marshall"_#Marshall2009, this allows for the required adjustment of
+rolling displacement due to changes in the frame of reference of the
+contacting pair.  The rolling pseudo-force is computed analogously to
+the tangential force:
+
+\begin\{equation\}
+\mathbf\{F\}_\{roll,0\} =  k_\{roll\} \mathbf\{\xi\}_\{roll\}  - \gamma_\{roll\} \mathbf\{v\}_\{roll\}
+\end\{equation\}
+
+Here, \(\mathbf\{v\}_\{roll\} = -R(\mathbf\{\Omega\}_i -
+\mathbf\{\Omega\}_j) \times \mathbf\{n\}\) is the relative rolling
+velocity, as given in "Wang et al"_#Wang2015 and
+"Luding"_#Luding2008. This differs from the expressions given by "Kuhn
+and Bagi"_#Kuhn2004 and used in "Marshall"_#Marshall2009; see "Wang et
+al"_#Wang2015 for details. The rolling displacement is given by:
+
+\begin\{equation\}
+\mathbf\{\xi\}_\{roll\} = \int_\{t_0\}^t \mathbf\{v\}_\{roll\} (\tau) \mathrm\{d\} \tau
+\end\{equation\}
+
+A Coulomb friction criterion truncates the rolling pseudo-force if it
+exceeds a critical value:
+
+\begin\{equation\}
+\mathbf\{F\}_\{roll\} =  min(\mu_\{roll\} F_\{n,0\}, \|\mathbf\{F\}_\{roll,0\}\|)\mathbf\{k\}
+\end\{equation\}
+
+Here, \(\mathbf\{k\} =
+\mathbf\{v\}_\{roll\}/\|\mathbf\{v\}_\{roll\}\|\) is the direction of
+the pseudo-force.  As with tangential displacement, the rolling
+displacement is rescaled when the critical force is exceeded, so that
+the spring length corresponds the critical force. Additionally, the
+displacement is adjusted to account for rotations of the frame of
+reference of the two contacting particles in a manner analogous to the
+tangential displacement.
+
+The rolling pseudo-force does not contribute to the total force on
+either particle (hence 'pseudo'), but acts only to induce an equal and
+opposite torque on each particle, according to:
+
+\begin\{equation\}
+\tau_\{roll,i\} =  R_\{eff\} \mathbf\{n\} \times \mathbf\{F\}_\{roll\}
+\end\{equation\}
+
+\begin\{equation\}
+\tau_\{roll,j\} =  -\tau_\{roll,i\}
+\end\{equation\}
+
+:line
+
+The optional {twisting} keyword enables twisting friction, which
+resists rotation of two contacting particles about the vector
+\(\mathbf\{n\}\) that connects their centers. The options currently
+supported are:
+
+{none}
+{sds} : \(k_\{twist\}\), \(\gamma_\{twist\}\), \(\mu_\{twist\}\)
+{marshall} :ol
+
+If the {twisting} keyword is not specified, the model defaults to {none}.
+
+For both {twisting sds} and {twisting marshall}, a history-dependent
+spring-dashpot-slider is used to compute the twisting torque. Because
+twisting displacement is a scalar, there is no need to adjust for
+changes in the frame of reference due to rotations of the particle
+pair. The formulation in "Marshall"_#Marshall2009 therefore provides
+the most straightforward treatment:
+
+\begin\{equation\}
+\tau_\{twist,0\} = -k_\{twist\}\xi_\{twist\} - \gamma_\{twist\}\Omega_\{twist\}
+\end\{equation\}
+
+Here \(\xi_\{twist\} = \int_\{t_0\}^t \Omega_\{twist\} (\tau)
+\mathrm\{d\}\tau\) is the twisting angular displacement, and
+\(\Omega_\{twist\} = (\mathbf\{\Omega\}_i - \mathbf\{\Omega\}_j) \cdot
+\mathbf\{n\}\) is the relative twisting angular velocity. The torque
+is then truncated according to:
+
+\begin\{equation\}
+\tau_\{twist\} = min(\mu_\{twist\} F_\{n,0\}, \tau_\{twist,0\})
+\end\{equation\}
+
+Similar to the sliding and rolling displacement, the angular
+displacement is rescaled so that it corresponds to the critical value
+if the twisting torque exceeds this critical value:
+
+\begin\{equation\}
+\xi_\{twist\} = \frac\{1\}\{k_\{twist\}\} (\mu_\{twist\} F_\{n,0\}sgn(\Omega_\{twist\}) - \gamma_\{twist\}\Omega_\{twist\})
+\end\{equation\}
+
+For {twisting sds}, the coefficients \(k_\{twist\}, \gamma_\{twist\}\)
+and \(\mu_\{twist\}\) are simply the user input parameters that follow
+the {twisting sds} keywords in the {pair_coeff} command.
+
+For {twisting_marshall}, the coefficients are expressed in terms of
+sliding friction coefficients, as discussed in
+"Marshall"_#Marshall2009 (see equations 32 and 33 of that work):
+
+\begin\{equation\}
+k_\{twist\} = 0.5k_ta^2
+\end\{equation\}
+
+\begin\{equation\}
+\eta_\{twist\} = 0.5\eta_ta^2
+\end\{equation\}
+
+\begin\{equation\}
+\mu_\{twist\} = \frac\{2\}\{3\}a\mu_t
+\end\{equation\}
+
+Finally, the twisting torque on each particle is given by:
+
+\begin\{equation\}
+\mathbf\{\tau\}_\{twist,i\} = \tau_\{twist\}\mathbf\{n\}
+\end\{equation\}
+
+\begin\{equation\}
+\mathbf\{\tau\}_\{twist,j\} = -\mathbf\{\tau\}_\{twist,i\}
+\end\{equation\}
+
+:line
+
+LAMMPS automatically sets pairwise cutoff values for {pair_style
+granular} based on particle radii (and in the case of {jkr} pull-off
+distances). In the vast majority of situations, this is adequate.
+However, a cutoff value can optionally be appended to the {pair_style
+granular} command to specify a global cutoff (i.e. a cutoff for all
+atom types). Additionally, the optional {cutoff} keyword can be passed
+to the {pair_coeff} command, followed by a cutoff value.  This will
+set a pairwise cutoff for the atom types in the {pair_coeff} command.
+These options may be useful in some rare cases where the automatic
+cutoff determination is not sufficient, e.g.  if particle diameters
+are being modified via the {fix adapt} command. In that case, the
+global cutoff specified as part of the {pair_style granular} command
+is applied to all atom types, unless it is overridden for a given atom
+type combination by the {cutoff} value specified in the {pair coeff}
+command.  If {cutoff} is only specified in the {pair coeff} command
+and no global cutoff is appended to the {pair_style granular} command,
+then LAMMPS will use that cutoff for the specified atom type
+combination, and automatically set pairwise cutoffs for the remaining
+atom types.
+
+:line
+
+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 "Speed packages"_Speed_packages.html 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, USER-INTEL, KOKKOS,
+USER-OMP and OPT packages, respectively.  They are only enabled if
+LAMMPS was built with those packages.  See the "Build
+package"_Build_package.html doc page for more info.
+
+You can specify the accelerated styles explicitly in your input script
+by including their suffix, or you can use the "-suffix command-line
+switch"_Run_options.html when you invoke LAMMPS, or you can use the
+"suffix"_suffix.html command in your input script.
+
+See the "Speed packages"_Speed_packages.html doc page for more
+instructions on how to use the accelerated styles effectively.
+
+:line
+
+[Mixing, shift, table, tail correction, restart, rRESPA info]:
+
+The "pair_modify"_pair_modify.html mix, shift, table, and tail options
+are not relevant for granular pair styles.
+
+Mixing of coefficients is carried out using geometric averaging for
+most quantities, e.g. if friction coefficient for type 1-type 1
+interactions is set to \(\mu_1\), and friction coefficient for type
+2-type 2 interactions is set to \(\mu_2\), the friction coefficient
+for type1-type2 interactions is computed as \(\sqrt\{\mu_1\mu_2\}\)
+(unless explicitly specified to a different value by a {pair_coeff 1 2
+...} command. The exception to this is elastic modulus, only
+applicable to {hertz/material}, {dmt} and {jkr} normal contact
+models. In that case, the effective elastic modulus is computed as:
+
+\begin\{equation\}
+E_\{eff,ij\} = \left(\frac\{1-\nu_i^2\}\{E_i\} + \frac\{1-\nu_j^2\}\{E_j\}\right)^\{-1\}
+\end\{equation\}
+
+If the {i-j} coefficients \(E_\{ij\}\) and \(\nu_\{ij\}\) are
+explicitly specified, the effective modulus is computed as:
+
+\begin\{equation\}
+E_\{eff,ij\} = \left(\frac\{1-\nu_\{ij\}^2\}\{E_\{ij\}\} + \frac\{1-\nu_\{ij\}^2\}\{E_\{ij\}\}\right)^\{-1\}
+\end\{equation\}
+
+or
+
+\begin\{equation\}
+E_\{eff,ij\} = \frac\{E_\{ij\}\}\{2(1-\nu_\{ij\})\}
+\end\{equation\}
+
+These pair styles write their information to "binary restart
+files"_restart.html, so a pair_style command does not need to be
+specified in an input script that reads a restart file.
+
+These pair styles can only be used via the {pair} keyword of the
+"run_style respa"_run_style.html command.  They do not support the
+{inner}, {middle}, {outer} keywords.
+
+The single() function of these pair styles returns 0.0 for the energy
+of a pairwise interaction, since energy is not conserved in these
+dissipative potentials.  It also returns only the normal component of
+the pairwise interaction force.  However, the single() function also
+calculates 10 extra pairwise quantities.  The first 3 are the
+components of the tangential force between particles I and J, acting
+on particle I.  The 4th is the magnitude of this tangential force.
+The next 3 (5-7) are the components of the rolling torque acting on
+particle I. The next entry (8) is the magnitude of the rolling torque.
+The next entry (9) is the magnitude of the twisting torque acting
+about the vector connecting the two particle centers.
+The last 3 (10-12) are the components of the vector connecting
+the centers of the two particles (x_I - x_J).
+
+These extra quantities can be accessed by the "compute
+pair/local"_compute_pair_local.html command, as {p1}, {p2}, ...,
+{p12}.
+
+:line
+
+[Restrictions:]
+
+All the granular pair styles are part of the GRANULAR package.  It is
+only enabled if LAMMPS was built with that package.  See the "Build
+package"_Build_package.html doc page for more info.
+
+These pair styles require that atoms store torque and angular velocity
+(omega) as defined by the "atom_style"_atom_style.html.  They also
+require a per-particle radius is stored.  The {sphere} atom style does
+all of this.
+
+This pair style requires you to use the "comm_modify vel
+yes"_comm_modify.html command so that velocities are stored by ghost
+atoms.
+
+These pair styles will not restart exactly when using the
+"read_restart"_read_restart.html command, though they should provide
+statistically similar results.  This is because the forces they
+compute depend on atom velocities.  See the
+"read_restart"_read_restart.html command for more details.
+
+[Related commands:]
+
+"pair_coeff"_pair_coeff.html
+"pair gran/*"_pair_gran.html
+
+[Default:]
+
+For the {pair_coeff} settings: {damping viscoelastic}, {rolling none},
+{twisting none}.
+
+[References:]
+
+:link(Brill1996)
+[(Brilliantov et al, 1996)] Brilliantov, N. V., Spahn, F., Hertzsch,
+J. M., & Poschel, T. (1996).  Model for collisions in granular
+gases. Physical review E, 53(5), 5382.
+
+:link(Tsuji1992) 
+[(Tsuji et al, 1992)] Tsuji, Y., Tanaka, T., & Ishida,
+T. (1992). Lagrangian numerical simulation of plug flow of
+cohesionless particles in a horizontal pipe. Powder technology, 71(3),
+239-250.
+
+:link(JKR1971)
+[(Johnson et al, 1971)] Johnson, K. L., Kendall, K., & Roberts,
+A. D. (1971).  Surface energy and the contact of elastic
+solids. Proc. R. Soc. Lond. A, 324(1558), 301-313.
+
+:link(DMT1975)
+[Derjaguin et al, 1975)] Derjaguin, B. V., Muller, V. M., & Toporov,
+Y. P. (1975). Effect of contact deformations on the adhesion of
+particles. Journal of Colloid and interface science, 53(2), 314-326.
+
+:link(Luding2008)
+[(Luding, 2008)] Luding, S. (2008). Cohesive, frictional powders:
+contact models for tension. Granular matter, 10(4), 235.
+
+:link(Marshall2009)
+[(Marshall, 2009)] Marshall, J. S. (2009). Discrete-element modeling
+of particulate aerosol flows.  Journal of Computational Physics,
+228(5), 1541-1561.
+
+:link(Silbert2001)
+[(Silbert, 2001)] Silbert, L. E., Ertas, D., Grest, G. S., Halsey,
+T. C., Levine, D., & Plimpton, S. J. (2001).  Granular flow down an
+inclined plane: Bagnold scaling and rheology. Physical Review E,
+64(5), 051302.
+
+:link(Kuhn2004)
+[(Kuhn and Bagi, 2005)] Kuhn, M. R., & Bagi, K. (2004). Contact
+rolling and deformation in granular media.  International journal of
+solids and structures, 41(21), 5793-5820.
+
+:link(Wang2015)
+[(Wang et al, 2015)] Wang, Y., Alonso-Marroquin, F., & Guo,
+W. W. (2015).  Rolling and sliding in 3-D discrete element
+models. Particuology, 23, 49-55.
+
+:link(Thornton1991)
+[(Thornton, 1991)] Thornton, C. (1991). Interparticle sliding in the
+presence of adhesion.  J. Phys. D: Appl. Phys. 24 1942
+
+:link(Mindlin1949)
+[(Mindlin, 1949)] Mindlin, R. D. (1949). Compliance of elastic bodies
+in contact.  J. Appl. Mech., ASME 16, 259-268.
+
+:link(Thornton2013)
+[(Thornton et al, 2013)] Thornton, C., Cummins, S. J., & Cleary,
+P. W. (2013).  An investigation of the comparative behaviour of
+alternative contact force models during inelastic collisions. Powder
+Technology, 233, 30-46.
+
+:link(WaltonPC)
+[(Otis R. Walton)] Walton, O.R., Personal Communication	
diff --git a/doc/src/pair_ilp_graphene_hbn.txt b/doc/src/pair_ilp_graphene_hbn.txt
index 76dda14ec6..3a5d4accd5 100644
--- a/doc/src/pair_ilp_graphene_hbn.txt
+++ b/doc/src/pair_ilp_graphene_hbn.txt
@@ -47,11 +47,16 @@ equation can be found in "(Leven1)"_#Leven1 and "(Maaravi)"_#Maaravi2.
 It is important to include all the pairs to build the neighbor list for
 calculating the normals.
 
-NOTE: This potential is intended for interactions between two different
-layers of graphene or hexagonal boron nitride. Therefore, to avoid
-interaction within the same layers, each layer should have a separate
-molecule id and is recommended to use "full" atom style in the data
-file.
+NOTE: This potential (ILP) is intended for interlayer interactions between two
+different layers of graphene, hexagonal boron nitride (h-BN) and their hetero-junction.
+To perform a realistic simulation, this potential must be used in combination with
+intra-layer potential, such as "AIREBO"_pair_airebo.html or "Tersoff"_pair_tersoff.html potential.
+To keep the intra-layer properties unaffected, the interlayer interaction
+within the same layers should be avoided. Hence, each atom has to have a layer
+identifier such that atoms residing on the same layer interact via the
+appropriate intra-layer potential and atoms residing on different layers
+interact via the ILP. Here, the molecule id is chosen as the layer identifier,
+thus a data file with the "full" atom style is required to use this potential.
 
 The parameter file (e.g. BNCH.ILP), is intended for use with {metal}
 "units"_units.html, with energies in meV. Two additional parameters,
@@ -62,6 +67,10 @@ list for calculating the normals for each atom pair.
 NOTE: The parameters presented in the parameter file (e.g. BNCH.ILP),
 are fitted with taper function by setting the cutoff equal to 16.0
 Angstrom.  Using different cutoff or taper function should be careful.
+The parameters for atoms pairs between Boron and Nitrogen are fitted with
+a screened Coulomb interaction "coul/shield"_pair_coul_shield.html. Therefore,
+to simulated the properties of h-BN correctly, this potential must be used in
+combination with the pair style "coul/shield"_pair_coul_shield.html.
 
 NOTE: Two new sets of parameters of ILP for two-dimensional hexagonal
 Materials are presented in "(Ouyang)"_#Ouyang.  These parameters provide
diff --git a/doc/src/pair_kim.txt b/doc/src/pair_kim.txt
index c5d42403e3..a415ac606b 100644
--- a/doc/src/pair_kim.txt
+++ b/doc/src/pair_kim.txt
@@ -42,12 +42,9 @@ section of the "Packages details"_Packages_details.html doc page has
 instructions on how to do this with a simple make command, when
 building LAMMPS.
 
-See the examples/kim dir for an input script that uses a KIM model (potential)
-for Lennard-Jones.  Note, for this example input script, the example models
-shipped with with kim-api package must be installed.  See the "Build
-package"_Build_package.html section and the ./lib/kim/README for details
-on how to build LAMMSPS with the kim-api and how to install the example models.
-
+See the examples/kim dir for an input script that uses a KIM model
+(potential) for Lennard-Jones.
+ 
 :line
 
 The argument {model} is the name of the KIM model for a specific
diff --git a/doc/src/pair_kolmogorov_crespi_full.txt b/doc/src/pair_kolmogorov_crespi_full.txt
index 6d76a24bdb..05effc5620 100644
--- a/doc/src/pair_kolmogorov_crespi_full.txt
+++ b/doc/src/pair_kolmogorov_crespi_full.txt
@@ -42,10 +42,16 @@ the last term in the equation for {Vij} above. This is essential only
 when the tapper function is turned off. The formula of taper function
 can be found in pair style "ilp/graphene/hbn"_pair_ilp_graphene_hbn.html.
 
-NOTE: This potential is intended for interactions between two different
-graphene layers. Therefore, to avoid interaction within the same layers,
-each layer should have a separate molecule id and is recommended to use
-"full" atom style in the data file.
+NOTE: This potential (ILP) is intended for interlayer interactions between two
+different layers of graphene. To perform a realistic simulation, this potential 
+must be used in combination with intra-layer potential, such as 
+"AIREBO"_pair_airebo.html or "Tersoff"_pair_tersoff.html potential.
+To keep the intra-layer properties unaffected, the interlayer interaction
+within the same layers should be avoided. Hence, each atom has to have a layer
+identifier such that atoms residing on the same layer interact via the
+appropriate intra-layer potential and atoms residing on different layers
+interact via the ILP. Here, the molecule id is chosen as the layer identifier,
+thus a data file with the "full" atom style is required to use this potential.
 
 The parameter file (e.g. CH.KC), is intended for use with {metal}
 "units"_units.html, with energies in meV. Two additional parameters, {S},
diff --git a/doc/src/pair_meamc.txt b/doc/src/pair_meamc.txt
index b57339b180..80f69b1a46 100644
--- a/doc/src/pair_meamc.txt
+++ b/doc/src/pair_meamc.txt
@@ -357,6 +357,13 @@ The {meam/c} style is provided in the USER-MEAMC package. It is
 only enabled if LAMMPS was built with that package.
 See the "Build package"_Build_package.html doc page for more info.
 
+The maximum number of elements, that can be read from the MEAM
+library file, is determined at compile time. The default is 5.
+If you need support for more elements, you have to change the
+define for the constant 'maxelt' at the beginning of the file
+src/USER-MEAMC/meam.h and update/recompile LAMMPS. There is no
+limit on the number of atoms types.
+
 [Related commands:]
 
 "pair_coeff"_pair_coeff.html, "pair_style eam"_pair_eam.html,
diff --git a/doc/src/pairs.txt b/doc/src/pairs.txt
index 09c310a110..30dcc8fd4b 100644
--- a/doc/src/pairs.txt
+++ b/doc/src/pairs.txt
@@ -42,6 +42,7 @@ Pair Styles :h1
    pair_gauss
    pair_gayberne
    pair_gran
+   pair_granular
    pair_gromacs
    pair_gw
    pair_hbond_dreiding
diff --git a/doc/src/velocity.txt b/doc/src/velocity.txt
index 96d3fa6dc4..decdf2a923 100644
--- a/doc/src/velocity.txt
+++ b/doc/src/velocity.txt
@@ -134,7 +134,7 @@ The {mom} and {rot} keywords are used by {create}.  If mom = yes, the
 linear momentum of the newly created ensemble of velocities is zeroed;
 if rot = yes, the angular momentum is zeroed.
 
-*line
+:line
 
 If specified, the {temp} keyword is used by {create} and {scale} to
 specify a "compute"_compute.html that calculates temperature in a
diff --git a/doc/utils/sphinx-config/false_positives.txt b/doc/utils/sphinx-config/false_positives.txt
index 5366a31d5d..a845673715 100644
--- a/doc/utils/sphinx-config/false_positives.txt
+++ b/doc/utils/sphinx-config/false_positives.txt
@@ -156,6 +156,8 @@ ba
 Babadi
 backcolor
 Baczewski
+Bagi
+Bagnold
 Bal
 balancer
 Balankura
@@ -250,6 +252,7 @@ Boresch
 Botero
 Botu
 Bouguet
+Bourne
 boxcolor
 bp
 bpls
@@ -286,6 +289,7 @@ Cao
 Capolungo
 Caro
 cartesian
+CasP
 Caswell
 Cates
 Cavium
@@ -345,7 +349,9 @@ Cii
 Cij
 cis
 civ
+Clang
 clearstore
+Cleary
 Clebsch
 clemson
 Clermont
@@ -372,6 +378,7 @@ Coeff
 CoefficientN
 coeffs
 Coeffs
+cohesionless
 Coker
 Colberg
 coleman
@@ -449,6 +456,7 @@ cuda
 Cuda
 CUDA
 CuH
+Cummins
 Curk
 customIDs
 cutbond
@@ -492,6 +500,7 @@ darkturquoise
 darkviolet
 Das
 Dasgupta
+dashpot
 dat
 datafile
 datums
@@ -529,6 +538,7 @@ Dequidt
 der
 derekt
 Derjagin
+Derjaguin
 Derlet
 Deserno
 Destree
@@ -627,6 +637,7 @@ dVx
 dW
 dx
 dy
+dylib
 dyn
 dyne
 dynes
@@ -647,6 +658,7 @@ ec
 Ec
 ecoul
 ecp
+Ecut
 edgeIDs
 edihed
 edim
@@ -1079,6 +1091,7 @@ Hyoungki
 hyperdynamics
 hyperradius
 hyperspherical
+hysteretic
 Ibanez
 ibar
 ibm
@@ -1124,6 +1137,7 @@ infty
 inhomogeneities
 inhomogeneous
 init
+initio
 initializations
 InP
 inregion
@@ -1138,6 +1152,7 @@ interconvert
 interial
 interlayer
 intermolecular
+Interparticle
 interstitials
 Intr
 intra
@@ -1156,6 +1171,7 @@ IPython
 Isele
 isenthalpic
 ish
+Ishida
 iso
 isodemic
 isoenergetic
@@ -1243,6 +1259,7 @@ Jy
 Jz
 jzimmer
 Kadiri
+Kai
 Kalia
 Kamberaj
 Kapfer
@@ -1265,6 +1282,7 @@ kcl
 Kd
 KDevelop
 ke
+kepler
 KE
 Keblinski
 keflag
@@ -1272,6 +1290,7 @@ Keir
 Kelchner
 Kelkar
 Kemper
+keV
 Keyes
 Khersonskii
 Khrapak
@@ -1298,6 +1317,7 @@ Kondor
 konglt
 Koning
 Kooser
+Korn
 Koskinen
 Koster
 Kosztin
@@ -1382,6 +1402,7 @@ libAtoms
 libawpmd
 libch
 libcolvars
+libcurl
 libdir
 libdl
 libfftw
@@ -1449,6 +1470,7 @@ logfile
 logfreq
 logicals
 Lomdahl
+Lond
 lookups
 Lookups
 LoopVar
@@ -1464,6 +1486,7 @@ lsfftw
 ltbbmalloc
 lubricateU
 lucy
+Luding
 Lussetti
 Lustig
 lwsock
@@ -1502,6 +1525,7 @@ manybody
 MANYBODY
 Maras
 Marrink
+Marroquin
 Marsaglia
 Marseille
 Martyna
@@ -1513,12 +1537,14 @@ masstotal
 Masuhiro
 Matchett
 Materias
+mathbf
 matlab
 matplotlib
 Mattox
 Mattson
 maxangle
 maxbond
+maxelt
 maxeval
 maxfiles
 Maxfoo
@@ -1601,12 +1627,14 @@ Mie
 Mikami
 Militzer
 Minary
+Mindlin
 mincap
 mingw
 minima
 minimizations
 minimizer
 minimizers
+minneigh
 minorder
 minSteps
 mintcream
@@ -1671,6 +1699,7 @@ mpiexec
 mpiio
 mpirun
 mplayer
+mps
 Mryglod
 mscg
 MSCG
@@ -1954,6 +1983,7 @@ oneway
 onn
 ons
 OO
+opencl
 openKIM
 OpenMP
 openmp
@@ -2286,6 +2316,7 @@ rg
 Rg
 Rhaphson
 rheological
+rheology
 rhodo
 Rhodo
 rhodopsin
@@ -2602,6 +2633,7 @@ Tait
 taitwater
 Tajkhorshid
 Tamaskovics
+Tanaka
 tanh
 Tartakovsky
 taskset
@@ -2689,6 +2721,7 @@ tokyo
 tol
 toolchain
 topologies
+Toporov
 Torder
 torsions
 Tosi
@@ -2733,6 +2766,7 @@ Tsrd
 Tstart
 tstat
 Tstop
+Tsuji
 Tsuzuki
 tt
 Tt
@@ -2783,6 +2817,7 @@ unimodal
 unitless
 Universite
 unix
+unmaintained
 unoptimized
 unpadded
 unphysical
@@ -2918,6 +2953,7 @@ Wi
 Wicaksono
 wih
 Wijk
+Wikipedia
 wildcard
 Wildcard
 Wirnsberger
diff --git a/examples/SPIN/spinmin/in.spinmin.bfo b/examples/SPIN/spinmin/in.spinmin.bfo
new file mode 100644
index 0000000000..5ebc9e0afe
--- /dev/null
+++ b/examples/SPIN/spinmin/in.spinmin.bfo
@@ -0,0 +1,55 @@
+# bfo in a 3d periodic box
+
+units 		metal
+dimension 	3
+boundary 	p p f
+atom_style 	spin
+
+# necessary for the serial algorithm (sametag)
+atom_modify 	map array 
+
+lattice 	sc 3.96
+region 		box block 0.0 34.0 0.0 34.0 0.0 1.0
+create_box 	1 box
+create_atoms 	1 box
+
+# setting mass, mag. moments, and interactions for bcc iron
+
+mass		1 1.0
+set 		group all spin/random 11 2.50
+
+pair_style 	hybrid/overlay spin/exchange 6.0 spin/magelec 4.5 spin/dmi 4.5
+pair_coeff 	* * spin/exchange exchange 6.0 -0.01575 0.0 1.965
+#pair_coeff 	* * spin/magelec magelec 4.5 0.000109 1.0 1.0 1.0
+pair_coeff 	* * spin/magelec magelec 4.5 0.00109 1.0 1.0 1.0
+pair_coeff 	* * spin/dmi dmi 4.5 0.00005 1.0 1.0 1.0
+
+neighbor 	0.1 bin
+neigh_modify 	every 10 check yes delay 20
+
+#fix 		1 all precession/spin zeeman 0.001 0.0 0.0 1.0 anisotropy 0.01 1.0 0.0 0.0 
+fix 		1 all precession/spin anisotropy 0.0000033 0.0 0.0 1.0
+fix_modify	1 energy yes
+
+timestep	0.0001
+
+compute 	out_mag    all spin
+compute 	out_pe     all pe
+compute 	out_ke     all ke
+compute 	out_temp   all temp
+
+variable 	magz      equal c_out_mag[3]
+variable 	magnorm   equal c_out_mag[4]
+variable 	emag      equal c_out_mag[5]
+variable 	tmag      equal c_out_mag[6]
+
+thermo          50
+thermo_style    custom step time v_magnorm v_emag v_tmag temp etotal
+thermo_modify   format float %20.15g
+
+compute 	outsp all property/atom spx spy spz sp fmx fmy fmz
+dump 		1 all custom 50 dump.lammpstrj type x y z c_outsp[1] c_outsp[2] c_outsp[3] c_outsp[4] c_outsp[5] c_outsp[6] c_outsp[7]
+
+min_style	spin
+min_modify 	alpha_damp 1.0 discrete_factor 10.0
+minimize        1.0e-10 0.0 1000 100
diff --git a/examples/SPIN/spinmin/in.spinmin.iron b/examples/SPIN/spinmin/in.spinmin.iron
new file mode 100644
index 0000000000..ebbd229b89
--- /dev/null
+++ b/examples/SPIN/spinmin/in.spinmin.iron
@@ -0,0 +1,55 @@
+# bcc iron in a 3d periodic box
+
+units 		metal
+dimension 	3
+boundary 	p p f
+atom_style 	spin
+
+# necessary for the serial algorithm (sametag)
+atom_modify 	map array 
+
+lattice 	bcc 2.8665
+region 		box block 0.0 4.0 0.0 4.0 0.0 4.0
+create_box 	1 box
+create_atoms 	1 box
+
+# setting mass, mag. moments, and interactions for bcc iron
+
+mass		1 55.845
+set 		group all spin/random 31 2.2
+#set 		group all spin 2.2 1.0 1.0 -1.0
+
+pair_style 	spin/exchange 3.5
+pair_coeff 	* * exchange 3.4 0.02726 0.2171 1.841
+
+neighbor 	0.1 bin
+neigh_modify 	every 10 check yes delay 20
+
+#fix 		1 all precession/spin zeeman 0.001 0.0 0.0 1.0 anisotropy 0.01 1.0 0.0 0.0 
+fix 		1 all precession/spin anisotropy 0.0001 0.0 0.0 1.0
+fix_modify	1 energy yes
+
+timestep	0.0001
+
+compute 	out_mag    all spin
+compute 	out_pe     all pe
+compute 	out_ke     all ke
+compute 	out_temp   all temp
+
+variable 	magx      equal c_out_mag[1]
+variable 	magy      equal c_out_mag[2]
+variable 	magz      equal c_out_mag[3]
+variable 	magnorm   equal c_out_mag[4]
+variable 	emag      equal c_out_mag[5]
+variable 	tmag      equal c_out_mag[6]
+
+thermo          100
+thermo_style    custom step time v_magx v_magz v_magnorm v_tmag etotal
+thermo_modify   format float %20.15g
+
+compute 	outsp all property/atom spx spy spz sp fmx fmy fmz
+dump 		1 all custom 100 dump.lammpstrj type x y z c_outsp[1] c_outsp[2] c_outsp[3] c_outsp[4] c_outsp[5] c_outsp[6] c_outsp[7]
+
+min_style	spin
+min_modify 	alpha_damp 1.0 discrete_factor 10.0
+minimize        1.0e-10 1.0e-10 100000 1000
diff --git a/examples/USER/misc/electron_stopping/Si.Si.elstop b/examples/USER/misc/electron_stopping/Si.Si.elstop
new file mode 100644
index 0000000000..51618149ff
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/Si.Si.elstop
@@ -0,0 +1,14 @@
+# Electronic stopping for Si in Si
+# Uses metal units
+# Kinetic energy in eV, stopping power in eV/A
+# For other atom types, add columns.
+
+# energy    Si in Si
+  3918.2      6.541
+ 15672.9     13.091
+ 35263.9     19.660
+ 62691.5     26.257
+ 97955.4     32.889
+141055.9     39.566
+191992.0     46.292
+250766.1     53.074
diff --git a/examples/USER/misc/electron_stopping/Si.sw b/examples/USER/misc/electron_stopping/Si.sw
new file mode 120000
index 0000000000..e575921334
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/Si.sw
@@ -0,0 +1 @@
+../../../../potentials/Si.sw
\ No newline at end of file
diff --git a/examples/USER/misc/electron_stopping/in.elstop b/examples/USER/misc/electron_stopping/in.elstop
new file mode 100644
index 0000000000..beaffbb821
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/in.elstop
@@ -0,0 +1,38 @@
+# Test case / example for fix electron/stopping
+# Perfect Si lattice with one primary knock-on atom.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 5.431
+
+region rbox block -10 10 -10 10 -10 10
+create_box 1 rbox
+
+mass 1 28.0855
+
+create_atoms 1 box
+
+velocity all create 300 42534 mom yes rot yes
+
+group gPKA id 1
+velocity gPKA set 1120 1620 389
+
+pair_style sw
+pair_coeff * * Si.sw Si
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop
+fix fnve all nve
+
+thermo 10
+thermo_style custom step time dt f_fel
+
+#compute ek all ke/atom
+#dump mydump all custom 200 elstop.dump id x y z vx vy vz fx fy fz c_ek
+
+run 5000
diff --git a/examples/USER/misc/electron_stopping/in.elstop.only b/examples/USER/misc/electron_stopping/in.elstop.only
new file mode 100644
index 0000000000..3e9650802c
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/in.elstop.only
@@ -0,0 +1,39 @@
+# Test case / example for fix electron/stopping
+# One fast atom, no other interactions.
+# Stopping only applied in a smaller box in the middle.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 1
+
+region rbox block -100 100 -100 100 -100 100
+region rsmallbox block -90 90 -90 90 -90 90
+
+create_box 1 rbox
+
+mass 1 28.0855
+
+create_atoms 1 single 0 0 0
+velocity all set 1120 1620 389
+
+pair_style zero 1
+pair_coeff * * 1
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop minneigh 0 region rsmallbox
+fix fnve all nve
+
+compute ek all ke/atom
+compute ektot all reduce sum c_ek
+
+thermo 100
+thermo_style custom step time dt f_fel c_ektot
+
+#dump mydump all custom 200 elstop.only.dump id x y z vx vy vz fx fy fz c_ek
+
+run 10000
diff --git a/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.1 b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.1
new file mode 100644
index 0000000000..cbe70373af
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.1
@@ -0,0 +1,597 @@
+LAMMPS (28 Feb 2019)
+OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:88)
+  using 1 OpenMP thread(s) per MPI task
+# Test case / example for fix electron/stopping
+# Perfect Si lattice with one primary knock-on atom.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 5.431
+Lattice spacing in x,y,z = 5.431 5.431 5.431
+
+region rbox block -10 10 -10 10 -10 10
+create_box 1 rbox
+Created orthogonal box = (-54.31 -54.31 -54.31) to (54.31 54.31 54.31)
+  1 by 1 by 1 MPI processor grid
+
+mass 1 28.0855
+
+create_atoms 1 box
+Created 32000 atoms
+  create_atoms CPU = 0.00282311 secs
+
+velocity all create 300 42534 mom yes rot yes
+
+group gPKA id 1
+1 atoms in group gPKA
+velocity gPKA set 1120 1620 389
+
+pair_style sw
+pair_coeff * * Si.sw Si
+Reading potential file Si.sw with DATE: 2007-06-11
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop
+fix fnve all nve
+
+thermo 10
+thermo_style custom step time dt f_fel
+
+#compute ek all ke/atom
+#dump mydump all custom 200 elstop.dump id x y z vx vy vz fx fy fz c_ek
+
+run 5000
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 5.77118
+  ghost atom cutoff = 5.77118
+  binsize = 2.88559, bins = 38 38 38
+  2 neighbor lists, perpetual/occasional/extra = 1 1 0
+  (1) pair sw, perpetual
+      attributes: full, newton on
+      pair build: full/bin/atomonly
+      stencil: full/bin/3d
+      bin: standard
+  (2) fix electron/stopping, occasional, copy from (1)
+      attributes: full, newton on
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 10.89 | 10.89 | 10.89 Mbytes
+Step Time Dt f_fel 
+       0            0  4.98128e-05            0 
+      10 0.00030141297 7.4132113e-06    143.83504 
+      20 0.00035951427 6.0316944e-06    171.53673 
+      30 0.00057458971 3.5117251e-05    274.07596 
+      40 0.00086591312 5.8243334e-06    412.87446 
+      50 0.00090045701 2.1026443e-06    429.31458 
+      60 0.00091828462 1.5368285e-06    437.79421 
+      70 0.00093305888 1.4643253e-06    444.81982 
+      80 0.00094860749 1.7487528e-06    452.21378 
+      90 0.00097032161 3.0786693e-06    462.54244 
+     100 0.0010787914 4.9354535e-05    514.16832 
+     110 0.0012080771 2.321306e-06    575.68374 
+     120 0.0012239682 1.0510328e-06    583.23471 
+     130 0.0012325497 6.8272619e-07    587.30872 
+     140 0.0012385196 5.1205819e-07    590.14077 
+     150  0.001243165 4.1524338e-07    592.34294 
+     160 0.0012470201 3.5380824e-07     594.1694 
+     170 0.0012503578 3.1203776e-07    595.74992 
+     180 0.0012533367 2.8236408e-07    597.15986 
+     190 0.0012560575 2.6071908e-07    598.44711 
+     200 0.0012585888 2.4474123e-07    599.64431 
+     210 0.0012609803 2.3298466e-07    600.77504 
+     220 0.0012632696 2.2453464e-07    601.85726 
+     230 0.0012654871 2.1880713e-07    602.90531 
+     240 0.0012676582 2.1543942e-07    603.93128 
+     250 0.0012698054 2.1422997e-07    604.94591 
+     260 0.0012719499 2.1510772e-07    605.95925 
+     270 0.0012741128 2.1812163e-07    606.98126 
+     280 0.0012763159 2.2344765e-07    608.02243 
+     290 0.0012785839 2.3141489e-07    609.09436 
+     300 0.0012809453 2.425587e-07    610.21066 
+     310 0.0012834353 2.577174e-07    611.38806 
+     320 0.0012860996 2.7820843e-07    612.64822 
+     330 0.0012890001 3.0616141e-07    614.02061 
+     340 0.0012922261 3.4518994e-07    615.54764 
+     350 0.0012959145 4.0187423e-07    617.29438 
+     360 0.0013002933 4.894618e-07    619.36917 
+     370 0.0013057872 6.3886828e-07    621.97388 
+     380 0.0013133355 9.4153332e-07    625.55502 
+     390 0.0013257779 1.8246429e-06    631.46263 
+     400 0.0013651328 1.4820738e-05    650.16503 
+     410 0.0016916358 4.5528312e-05     805.3327 
+     420 0.0020836696 2.6189823e-05    991.45963 
+     430  0.002192113 5.1312984e-06    1042.8979 
+     440 0.0022530638 1.1643276e-05    1071.7967 
+     450 0.0025312898 1.5833134e-05    1203.6961 
+     460 0.0028677695 3.9078523e-05    1363.0792 
+     470 0.0032653301 3.9299497e-05    1551.2027 
+     480 0.0036647478 4.1100578e-05    1739.9906 
+     490 0.0040772194 3.6017871e-05    1934.7262 
+     500  0.004246426 1.1620229e-05    2014.5366 
+     510 0.0045410379 2.1151987e-05    2153.4172 
+     520 0.0048951987 4.2067206e-05    2320.2216 
+     530 0.0051251181 5.9152255e-06    2428.4156 
+     540 0.0051740847 5.0188036e-06    2451.4388 
+     550 0.0053207575 4.1618335e-05    2520.4067 
+     560 0.0054412772 2.3641932e-06    2577.0541 
+     570  0.005457552 1.0847369e-06    2584.6937 
+     580 0.0054664476 7.1198746e-07    2588.8658 
+     590 0.0054726999 5.3933302e-07     2591.796 
+     600 0.0054776139 4.4178461e-07    2594.0976 
+     610 0.0054817341 3.8039473e-07    2596.0263 
+     620 0.0054853401 3.3924667e-07    2597.7135 
+     630 0.0054885957 3.1069211e-07    2599.2361 
+     640 0.0054916066 2.9064829e-07    2600.6439 
+     650 0.0054944462 2.7678405e-07    2601.9712 
+     660 0.0054971697 2.6772348e-07     2603.244 
+     670 0.0054998211 2.6266505e-07    2604.4829 
+     680 0.0055024383 2.6119265e-07    2605.7058 
+     690 0.0055050563 2.6318733e-07     2606.929 
+     700 0.0055077103 2.6880326e-07    2608.1691 
+     710 0.0055104383 2.7849814e-07    2609.4439 
+     720 0.0055132846 2.9313007e-07    2610.7742 
+     730 0.0055163044 3.141612e-07     2612.186 
+     740 0.0055195719 3.4406726e-07     2613.714 
+     750 0.0055231932 3.8719688e-07    2615.4081 
+     760 0.0055273329 4.5174267e-07    2617.3455 
+     770 0.0055322712 5.5490406e-07    2619.6579 
+     780 0.0055385515 7.3934538e-07    2622.6004 
+     790 0.0055474645 1.1452909e-06    2626.7792 
+     800 0.0055635927 2.6160295e-06    2634.3465 
+     810 0.0057044835 3.9642931e-05    2700.5132 
+     820 0.0060307501 2.9394558e-05    2853.6539 
+     830 0.0063374404 8.5188148e-06    2997.4768 
+     840 0.0063740052 1.4828325e-06    3014.6052 
+     850 0.0063848364 7.5985425e-07    3019.6727 
+     860 0.0063911095 5.0258852e-07    3022.6045 
+     870 0.0063954921 3.7335256e-07    3024.6508 
+     880 0.0063988506 2.9643864e-07    3026.2175 
+     890 0.0064015712 2.4575869e-07    3027.4855 
+     900 0.0064038584 2.1001191e-07    3028.5506 
+     910 0.0064058333 1.8353805e-07    3029.4694 
+     920  0.006407573 1.6320008e-07    3030.2782 
+     930 0.0064091297 1.4712417e-07    3031.0014 
+     940 0.0064105403 1.3412445e-07    3031.6562 
+     950 0.0064118317 1.2341509e-07    3032.2552 
+     960 0.0064130243 1.1445544e-07     3032.808 
+     970 0.0064141337 1.0686175e-07    3033.3219 
+     980 0.0064151722 1.0035437e-07    3033.8027 
+     990 0.0064161498 9.4724852e-08    3034.2549 
+    1000 0.0064170744 8.9814769e-08    3034.6824 
+    1010 0.0064179527 8.5501639e-08    3035.0882 
+    1020 0.0064187902 8.1689338e-08     3035.475 
+    1030 0.0064195915 7.8301418e-08    3035.8449 
+    1040 0.0064203606 7.5276356e-08    3036.1997 
+    1050 0.0064211009 7.2564109e-08     3036.541 
+    1060 0.0064218154 7.0123584e-08    3036.8703 
+    1070 0.0064225065 6.7920744e-08    3037.1886 
+    1080 0.0064231766 6.5927178e-08    3037.4971 
+    1090 0.0064238276 6.4119002e-08    3037.7967 
+    1100 0.0064244613 6.2476011e-08    3038.0882 
+    1110 0.0064250792 6.0981016e-08    3038.3724 
+    1120 0.0064256828 5.9619315e-08    3038.6498 
+    1130 0.0064262733 5.8378279e-08    3038.9212 
+    1140 0.0064268519 5.7247013e-08    3039.1869 
+    1150 0.0064274196 5.6216088e-08    3039.4476 
+    1160 0.0064279775 5.5277318e-08    3039.7037 
+    1170 0.0064285264 5.4423582e-08    3039.9556 
+    1180  0.006429067 5.3648672e-08    3040.2036 
+    1190 0.0064296003 5.294717e-08    3040.4482 
+    1200 0.0064301269 5.2314351e-08    3040.6897 
+    1210 0.0064306474 5.1746091e-08    3040.9283 
+    1220 0.0064311625 5.1238802e-08    3041.1644 
+    1230 0.0064316729 5.0789368e-08    3041.3983 
+    1240 0.0064321789 5.0395101e-08    3041.6301 
+    1250 0.0064326813 5.0053692e-08    3041.8603 
+    1260 0.0064331805 4.9763183e-08    3042.0889 
+    1270  0.006433677 4.9521937e-08    3042.3163 
+    1280 0.0064341713 4.9328614e-08    3042.5427 
+    1290 0.0064346639 4.9182151e-08    3042.7682 
+    1300 0.0064351552 4.9081752e-08    3042.9931 
+    1310 0.0064356458 4.9026872e-08    3043.2177 
+    1320  0.006436136 4.9017214e-08    3043.4421 
+    1330 0.0064366262 4.9052721e-08    3043.6666 
+    1340 0.0064371171 4.9133581e-08    3043.8912 
+    1350  0.006437609 4.9260223e-08    3044.1164 
+    1360 0.0064381023 4.9433327e-08    3044.3422 
+    1370 0.0064385976 4.9653831e-08     3044.569 
+    1380 0.0064390953 4.9922944e-08    3044.7968 
+    1390 0.0064395959 5.0242164e-08    3045.0261 
+    1400    0.0064401 5.0613297e-08    3045.2568 
+    1410  0.006440608 5.1038483e-08    3045.4895 
+    1420 0.0064411205 5.1520228e-08    3045.7242 
+    1430 0.0064416381 5.2061443e-08    3045.9613 
+    1440 0.0064421614 5.2665486e-08     3046.201 
+    1450  0.006442691 5.3336219e-08    3046.4437 
+    1460 0.0064432276 5.4078074e-08    3046.6896 
+    1470  0.006443772 5.4896126e-08    3046.9392 
+    1480 0.0064443249 5.5796191e-08    3047.1927 
+    1490 0.0064448873 5.6784937e-08    3047.4506 
+    1500 0.0064454599 5.7870017e-08    3047.7132 
+    1510 0.0064460439 5.9060235e-08    3047.9812 
+    1520 0.0064466403 6.0365742e-08    3048.2549 
+    1530 0.0064472503 6.1798287e-08    3048.5349 
+    1540 0.0064478752 6.337151e-08     3048.822 
+    1550 0.0064485166 6.5101323e-08    3049.1166 
+    1560  0.006449176 6.7006371e-08    3049.4197 
+    1570 0.0064498554 6.9108623e-08     3049.732 
+    1580 0.0064505567 7.1434118e-08    3050.0546 
+    1590 0.0064512824 7.4013931e-08    3050.3885 
+    1600 0.0064520352 7.6885409e-08    3050.7351 
+    1610 0.0064528182 8.0093813e-08    3051.0957 
+    1620  0.006453635 8.3694486e-08     3051.472 
+    1630 0.0064544898 8.7755778e-08    3051.8661 
+    1640 0.0064553876 9.2363047e-08    3052.2802 
+    1650 0.0064563343 9.7624226e-08    3052.7171 
+    1660 0.0064573371 1.0367771e-07    3053.1801 
+    1670 0.0064584046 1.1070379e-07    3053.6733 
+    1680 0.0064595476 1.1894157e-07    3054.2017 
+    1690 0.0064607796 1.2871484e-07    3054.7716 
+    1700 0.0064621178 1.4047265e-07     3055.391 
+    1710 0.0064635847 1.5485559e-07    3056.0705 
+    1720 0.0064652106 1.7280864e-07    3056.8241 
+    1730 0.0064670371 1.9578361e-07    3057.6713 
+    1740 0.0064691241 2.261258e-07    3058.6401 
+    1750 0.0064715615 2.6787347e-07    3059.7724 
+    1760 0.0064744931 3.2858822e-07    3061.1353 
+    1770 0.0064781697 4.2416554e-07    3062.8461 
+    1780 0.0064830857 5.9426003e-07    3065.1356 
+    1790 0.0064904338 9.7042692e-07    3068.5608 
+    1800  0.006504521 2.3570057e-06    3075.1339 
+    1810 0.0066489551 2.5350137e-05     3142.596 
+    1820 0.0067263358 2.0982567e-06    3178.7218 
+    1830 0.0067413263 1.0389873e-06    3185.7117 
+    1840 0.0067499639 7.021379e-07     3189.736 
+    1850 0.0067561793 5.4125252e-07    3192.6298 
+    1860   0.00676114 4.4920623e-07     3194.938 
+    1870 0.0067653505 3.911598e-07    3196.8961 
+    1880 0.0067690759 3.5254253e-07    3198.6279 
+    1890 0.0067724748 3.2626983e-07    3200.2074 
+    1900 0.0067756518 3.0855768e-07    3201.6834 
+    1910 0.0067786819 2.9728199e-07    3203.0908 
+    1920 0.0067816236 2.9125633e-07     3204.457 
+    1930 0.0067845263 2.8989566e-07    3205.8049 
+    1940 0.0067874357 2.9306921e-07     3207.156 
+    1950 0.0067903982 3.0106889e-07    3208.5318 
+    1960  0.006793465 3.1467844e-07    3209.9563 
+    1970 0.0067966982 3.3537556e-07    3211.4583 
+    1980 0.0068001793 3.6577201e-07    3213.0759 
+    1990 0.0068040239 4.1056728e-07     3214.863 
+    2000 0.0068084116 4.7878365e-07    3216.9034 
+    2010 0.0068136505 5.897605e-07    3219.3409 
+    2020 0.0068203489 7.9292336e-07    3222.4591 
+    2030 0.0068300039 1.259738e-06    3226.9568 
+    2040 0.0068484332 3.1869606e-06    3235.5484 
+    2050   0.00704302 3.1308435e-05    3326.3332 
+    2060 0.0073582601 1.9393034e-05    3473.3099 
+    2070 0.0076291992 6.1118973e-06    3599.5265 
+    2080 0.0076591273 1.397136e-06    3613.4525 
+    2090 0.0076695786 7.5324795e-07      3618.31 
+    2100 0.0076758692 5.1095756e-07    3621.2308 
+    2110 0.0076803593 3.8613872e-07    3623.3137 
+    2120 0.0076838539 3.1077232e-07    3624.9334 
+    2130 0.0076867208 2.6065521e-07    3626.2611 
+    2140 0.0076891581 2.2509342e-07    3627.3889 
+    2150  0.007691284 1.9865679e-07     3628.372 
+    2160 0.0076931748 1.7830513e-07    3629.2457 
+    2170 0.0076948825 1.6220815e-07    3630.0343 
+    2180 0.0076964439 1.4920028e-07    3630.7548 
+    2190 0.0076978861 1.3850522e-07      3631.42 
+    2200 0.0076992297 1.2958672e-07    3632.0393 
+    2210 0.0077004907 1.2206289e-07    3632.6203 
+    2220 0.0077016817 1.1565477e-07    3633.1687 
+    2230 0.0077028128 1.1015407e-07    3633.6892 
+    2240 0.0077038924 1.0540234e-07    3634.1859 
+    2250 0.0077049274 1.0127711e-07    3634.6618 
+    2260 0.0077059236 9.7682361e-08    3635.1197 
+    2270 0.0077068859 9.454193e-08    3635.5619 
+    2280 0.0077078187 9.1794781e-08    3635.9903 
+    2290 0.0077087255 8.9391579e-08    3636.4067 
+    2300 0.0077096098 8.7292175e-08    3636.8125 
+    2310 0.0077104742 8.5463727e-08    3637.2092 
+    2320 0.0077113216 8.3879281e-08     3637.598 
+    2330  0.007712154 8.2516693e-08    3637.9798 
+    2340 0.0077129738 8.1357804e-08    3638.3557 
+    2350 0.0077137829 8.0387796e-08    3638.7267 
+    2360 0.0077145831 7.9594705e-08    3639.0935 
+    2370 0.0077153761 7.8969036e-08     3639.457 
+    2380 0.0077161635 7.8503481e-08    3639.8178 
+    2390  0.007716947 7.8192701e-08    3640.1769 
+    2400 0.0077177281 7.8033171e-08    3640.5348 
+    2410 0.0077185083 7.8023089e-08    3640.8923 
+    2420  0.007719289 7.8162318e-08      3641.25 
+    2430 0.0077200718 7.8452384e-08    3641.6087 
+    2440 0.0077208582 7.8896522e-08    3641.9691 
+    2450 0.0077216498 7.9499759e-08    3642.3318 
+    2460 0.0077224481 8.026906e-08    3642.6977 
+    2470 0.0077232549 8.1213529e-08    3643.0675 
+    2480 0.0077240719 8.2344683e-08     3643.442 
+    2490 0.0077249012 8.3676812e-08    3643.8222 
+    2500 0.0077257448 8.5227445e-08     3644.209 
+    2510 0.0077266049 8.7017961e-08    3644.6035 
+    2520 0.0077274841 8.9074372e-08    3645.0068 
+    2530 0.0077283852 9.1428349e-08    3645.4203 
+    2540 0.0077293113 9.4118559e-08    3645.8454 
+    2550 0.0077302659 9.7192441e-08    3646.2837 
+    2560 0.0077312533 1.0070857e-07    3646.7372 
+    2570 0.0077322781 1.0473987e-07     3647.208 
+    2580 0.0077333458 1.0937801e-07    3647.6987 
+    2590  0.007734463 1.1473957e-07    3648.2124 
+    2600 0.0077356377 1.2097481e-07    3648.7528 
+    2610 0.0077368793 1.2828037e-07    3649.3242 
+    2620 0.0077381998 1.3691837e-07    3649.9322 
+    2630 0.0077396139 1.4724543e-07    3650.5836 
+    2640 0.0077411406 1.5975888e-07    3651.2873 
+    2650 0.0077428048 1.7517253e-07    3652.0548 
+    2660 0.0077446398 1.9454711e-07    3652.9016 
+    2670 0.0077466922 2.1952673e-07    3653.8493 
+    2680 0.0077490288 2.5279733e-07     3654.929 
+    2690 0.0077517515 2.9905194e-07     3656.188 
+    2700 0.0077550252 3.6725589e-07    3657.7029 
+    2710 0.0077591434 4.7681009e-07    3659.6101 
+    2720 0.0077647038 6.7839241e-07    3662.1874 
+    2730  0.007773234 1.1552111e-06    3666.1446 
+    2740 0.0077911374 3.3406902e-06     3674.458 
+    2750    0.0079702 8.4184292e-06    3757.6696 
+    2760  0.008006114 1.4496754e-06    3774.3449 
+    2770 0.0080166835 7.3926386e-07    3779.2462 
+    2780 0.0080227734 4.8640717e-07    3782.0672 
+    2790 0.0080270055 3.5945058e-07    3784.0255 
+    2800 0.0080302318 2.8394384e-07     3785.517 
+    2810  0.008032832 2.3422206e-07    3786.7179 
+    2820 0.0080350072 1.9916814e-07    3787.7215 
+    2830 0.0080368761 1.7321525e-07    3788.5831 
+    2840 0.0080385144 1.5327931e-07    3789.3377 
+    2850 0.0080399734 1.3751893e-07    3790.0091 
+    2860 0.0080412891 1.2476931e-07    3790.6141 
+    2870 0.0080424879 1.1425897e-07    3791.1649 
+    2880 0.0080435897 1.0545738e-07    3791.6707 
+    2890 0.0080446097 9.7988142e-08    3792.1386 
+    2900 0.0080455599 9.1577084e-08    3792.5741 
+    2910   0.00804645 8.6019912e-08    3792.9818 
+    2920 0.0080472879 8.1161402e-08    3793.3653 
+    2930 0.0080480798 7.6881575e-08    3793.7275 
+    2940 0.0080488311 7.3086284e-08    3794.0709 
+    2950 0.0080495465 6.9700651e-08    3794.3977 
+    2960 0.0080502295 6.666441e-08    3794.7094 
+    2970 0.0080508836 6.3928523e-08    3795.0078 
+    2980 0.0080515116 6.1452701e-08    3795.2941 
+    2990 0.0080521158 5.9203545e-08    3795.5694 
+    3000 0.0080526985 5.7153146e-08    3795.8346 
+    3010 0.0080532614 5.5278009e-08    3796.0908 
+    3020 0.0080538063 5.3558217e-08    3796.3386 
+    3030 0.0080543347 5.1976785e-08    3796.5788 
+    3040 0.0080548478 5.051914e-08    3796.8119 
+    3050 0.0080553469 4.9172716e-08    3797.0385 
+    3060 0.0080558329 4.7926619e-08    3797.2591 
+    3070 0.0080563069 4.6771366e-08    3797.4741 
+    3080 0.0080567697 4.5698662e-08    3797.6839 
+    3090 0.0080572222 4.4701228e-08    3797.8889 
+    3100 0.0080576649 4.3772647e-08    3798.0895 
+    3110 0.0080580987 4.2907247e-08    3798.2858 
+    3120 0.0080585241 4.2099999e-08    3798.4784 
+    3130 0.0080589417 4.1346425e-08    3798.6672 
+    3140 0.0080593519 4.0642535e-08    3798.8527 
+    3150 0.0080597554 3.9984758e-08    3799.0351 
+    3160 0.0080601524 3.9369895e-08    3799.2145 
+    3170 0.0080605435 3.8795073e-08    3799.3911 
+    3180  0.008060929 3.8257705e-08    3799.5651 
+    3190 0.0080613093 3.7755461e-08    3799.7368 
+    3200 0.0080616847 3.7286239e-08    3799.9062 
+    3210 0.0080620556 3.6848135e-08    3800.0734 
+    3220 0.0080624222 3.6439432e-08    3800.2387 
+    3230 0.0080627848 3.6058573e-08    3800.4022 
+    3240 0.0080631438 3.5704146e-08     3800.564 
+    3250 0.0080634994 3.5374876e-08    3800.7241 
+    3260 0.0080638517 3.5069606e-08    3800.8828 
+    3270 0.0080642011 3.4787289e-08    3801.0402 
+    3280 0.0080645478 3.4526978e-08    3801.1962 
+    3290  0.008064892 3.4287819e-08    3801.3511 
+    3300 0.0080652339 3.4069042e-08     3801.505 
+    3310 0.0080655736 3.3869955e-08    3801.6578 
+    3320 0.0080659115 3.368994e-08    3801.8098 
+    3330 0.0080662477 3.3528444e-08     3801.961 
+    3340 0.0080665823 3.3384981e-08    3802.1115 
+    3350 0.0080669156 3.3259123e-08    3802.2613 
+    3360 0.0080672476 3.3150499e-08    3802.4106 
+    3370 0.0080675787 3.305879e-08    3802.5594 
+    3380  0.008067909 3.2983732e-08    3802.7078 
+    3390 0.0080682385 3.2925108e-08    3802.8559 
+    3400 0.0080685676 3.288275e-08    3803.0038 
+    3410 0.0080688963 3.2856537e-08    3803.1515 
+    3420 0.0080692248 3.2846395e-08    3803.2991 
+    3430 0.0080695532 3.2852293e-08    3803.4466 
+    3440 0.0080698819 3.2874247e-08    3803.5943 
+    3450 0.0080702108 3.2912319e-08     3803.742 
+    3460 0.0080705401 3.2966617e-08      3803.89 
+    3470 0.0080708701 3.3037293e-08    3804.0382 
+    3480 0.0080712008 3.312455e-08    3804.1868 
+    3490 0.0080715325 3.3228638e-08    3804.3358 
+    3500 0.0080718653 3.3349858e-08    3804.4853 
+    3510 0.0080721995 3.3488567e-08    3804.6355 
+    3520  0.008072535 3.3645172e-08    3804.7862 
+    3530 0.0080728723 3.3820145e-08    3804.9378 
+    3540 0.0080732113 3.4014016e-08    3805.0901 
+    3550 0.0080735524 3.4227383e-08    3805.2434 
+    3560 0.0080738957 3.4460914e-08    3805.3977 
+    3570 0.0080742414 3.4715354e-08    3805.5532 
+    3580 0.0080745898 3.4991532e-08    3805.7098 
+    3590 0.0080749411 3.5290364e-08    3805.8677 
+    3600 0.0080752954 3.5612865e-08    3806.0271 
+    3610 0.0080756531 3.5960156e-08     3806.188 
+    3620 0.0080760143 3.6333475e-08    3806.3505 
+    3630 0.0080763794 3.6734187e-08    3806.5148 
+    3640 0.0080767487 3.7163802e-08     3806.681 
+    3650 0.0080771224 3.7623985e-08    3806.8492 
+    3660 0.0080775008 3.8116577e-08    3807.0196 
+    3670 0.0080778843 3.8643614e-08    3807.1924 
+    3680 0.0080782733 3.9207349e-08    3807.3676 
+    3690  0.008078668 3.9810283e-08    3807.5455 
+    3700  0.008079069 4.0455191e-08    3807.7262 
+    3710 0.0080794766 4.114516e-08      3807.91 
+    3720 0.0080798913 4.1883634e-08    3808.0971 
+    3730 0.0080803137 4.2674459e-08    3808.2877 
+    3740 0.0080807442 4.3521941e-08     3808.482 
+    3750 0.0080811834 4.4430917e-08    3808.6803 
+    3760 0.0080816321 4.5406834e-08     3808.883 
+    3770 0.0080820908 4.6455843e-08    3809.0902 
+    3780 0.0080825604 4.7584918e-08    3809.3025 
+    3790 0.0080830416 4.8801987e-08    3809.5201 
+    3800 0.0080835355 5.0116105e-08    3809.7436 
+    3810 0.0080840429 5.1537653e-08    3809.9733 
+    3820 0.0080845652 5.3078583e-08    3810.2097 
+    3830 0.0080851034 5.4752728e-08    3810.4535 
+    3840  0.008085659 5.6576175e-08    3810.7054 
+    3850 0.0080862335 5.8567743e-08    3810.9659 
+    3860 0.0080868289 6.0749572e-08     3811.236 
+    3870  0.008087447 6.3147889e-08    3811.5166 
+    3880 0.0080880901 6.5793981e-08    3811.8087 
+    3890  0.008088761 6.8725458e-08    3812.1136 
+    3900 0.0080894626 7.1987928e-08    3812.4327 
+    3910 0.0080901986 7.5637206e-08    3812.7675 
+    3920  0.008090973 7.9742316e-08    3813.1201 
+    3930 0.0080917909 8.4389592e-08    3813.4926 
+    3940  0.008092658 8.9688414e-08    3813.8879 
+    3950 0.0080935816 9.5779352e-08    3814.3091 
+    3960 0.0080945703 1.0284601e-07    3814.7604 
+    3970 0.0080956349 1.1113264e-07    3815.2467 
+    3980 0.0080967891 1.2097115e-07    3815.7742 
+    3990 0.0080980502 1.3282379e-07    3816.3511 
+    4000 0.0080994413 1.4735308e-07    3816.9878 
+    4010 0.0081009931 1.6554202e-07    3817.6987 
+    4020 0.0081027486 1.8891116e-07    3818.5035 
+    4030 0.0081047696 2.1993774e-07    3819.4308 
+    4040 0.0081071501 2.6293325e-07     3820.524 
+    4050 0.0081100418 3.2608623e-07    3821.8531 
+    4060 0.0081137136 4.2695471e-07    3823.5422 
+    4070 0.0081187073 6.1068659e-07    3825.8415 
+    4080 0.0081263808 1.0353843e-06    3829.3781 
+    4090 0.0081421033 2.8175459e-06    3836.6316 
+    4100 0.0083319479 3.0660994e-05     3924.296 
+    4110 0.0086521081 2.4031675e-05    4072.0381 
+    4120 0.0089367803 5.8263834e-06    4203.2922 
+    4130 0.0089679114 1.6262217e-06    4217.6293 
+    4140 0.0089805825 9.6546502e-07    4223.4594 
+    4150 0.0089889356 7.1159925e-07    4227.3001 
+    4160 0.0089954101 5.8311893e-07    4230.2754 
+    4170 0.0090008803 5.1000973e-07    4232.7881 
+    4180 0.0090057682 4.6713078e-07    4235.0326 
+    4190 0.0090103206 4.4370361e-07    4237.1225 
+    4200 0.0090147071 4.3491502e-07    4239.1361 
+    4210 0.0090190645 4.3912951e-07    4241.1362 
+    4220 0.0090235243 4.570826e-07    4243.1834 
+    4230 0.0090282367 4.9222468e-07    4245.3469 
+    4240 0.0090334045 5.5254852e-07      4247.72 
+    4250 0.0090393478 6.5600428e-07    4250.4502 
+    4260 0.0090466656 8.4827393e-07    4253.8133 
+    4270 0.0090567641 1.2818738e-06     4258.457 
+    4280 0.0090746835 2.9033891e-06    4266.7027 
+    4290 0.0092346752 2.9451638e-05    4340.3839 
+    4300 0.0093466586 4.9023913e-06    4391.9319 
+    4310 0.0093992941 7.8400922e-06     4416.149 
+    4320 0.0097053159 4.3362296e-05    4556.9393 
+    4330  0.010037349 4.9648086e-05    4709.5604 
+    4340  0.010297354 8.8232096e-06    4828.9697 
+    4350  0.010503113 4.4016316e-05    4923.4016 
+    4360  0.010926633 4.2142313e-05     5117.622 
+    4370  0.011318805 4.0285407e-05    5297.2575 
+    4380  0.011746199 4.3755472e-05    5492.8047 
+    4390  0.012044606 2.1150168e-05    5629.1924 
+    4400   0.01231664 7.0784321e-06    5753.4243 
+    4410   0.01236554 3.954763e-06    5775.7358 
+    4420     0.012415 8.8450437e-06    5798.2999 
+    4430  0.012723996 3.6113036e-05    5939.2622 
+    4440  0.013109261 4.5827638e-05    6114.8493 
+    4450  0.013251276 2.6649019e-06    6179.5172 
+    4460  0.013269544 1.2200106e-06    6187.8251 
+    4470  0.013279619 8.155501e-07    6192.4028 
+    4480  0.013286853 6.3300974e-07    6195.6879 
+    4490   0.01329269 5.3347649e-07    6198.3373 
+    4500  0.013297735 4.7451627e-07    6200.6261 
+    4510  0.013302306 4.392029e-07    6202.6992 
+    4520  0.013306599 4.1982963e-07    6204.6461 
+    4530  0.013310757 4.1285331e-07    6206.5311 
+    4540  0.013314895 4.1710029e-07    6208.4074 
+    4550  0.013319128 4.3324769e-07    6210.3267 
+    4560  0.013323586 4.6410935e-07     6212.348 
+    4570  0.013328439 5.1597347e-07    6214.5493 
+    4580   0.01333395 6.0235495e-07    6217.0498 
+    4590  0.013340584 7.5537668e-07    6220.0613 
+    4600  0.013349342 1.0699582e-06    6224.0388 
+    4610  0.013363183  1.98365e-06    6230.3293 
+    4620  0.013404081 1.4367775e-05    6248.9319 
+    4630  0.013593325 3.787203e-06    6335.0239 
+    4640   0.01361833 1.6441528e-06    6346.3866 
+    4650  0.013632159 1.1592769e-06    6352.6667 
+    4660  0.013642828 9.8623051e-07    6357.5101 
+    4670  0.013652418 9.4451692e-07    6361.8626 
+    4680  0.013662041 1.0034733e-06    6366.2295 
+    4690  0.013672824 1.2061779e-06    6371.1243 
+    4700  0.013686941 1.780995e-06    6377.5343 
+    4710  0.013713088 4.7634009e-06    6389.4131 
+    4720  0.013968014 3.9765415e-05    6505.2802 
+    4730  0.014228787 6.2632217e-06    6623.7185 
+    4740  0.014278333 4.7934169e-06    6646.2018 
+    4750  0.014382212 5.1069055e-05    6693.3424 
+    4760  0.014525205 2.0381123e-06    6758.2178 
+    4770  0.014538504 8.2250651e-07    6764.2412 
+    4780  0.014544984 4.9114353e-07    6767.1723 
+    4790  0.014549144 3.4212232e-07    6769.0518 
+    4800  0.014552156 2.589287e-07    6770.4109 
+    4810  0.014554491 2.0641662e-07    6771.4633 
+    4820  0.014556384 1.7052382e-07     6772.315 
+    4830  0.014557966 1.4457875e-07    6773.0262 
+    4840  0.014559319 1.250293e-07    6773.6339 
+    4850  0.014560498  1.09819e-07    6774.1626 
+    4860  0.014561539 9.7678962e-08     6774.629 
+    4870   0.01456247 8.7785899e-08    6775.0453 
+    4880   0.01456331 7.9583482e-08    6775.4205 
+    4890  0.014564074 7.2682934e-08    6775.7613 
+    4900  0.014564773 6.6804784e-08    6776.0732 
+    4910  0.014565418 6.1743238e-08    6776.3601 
+    4920  0.014566015 5.7343571e-08    6776.6256 
+    4930  0.014566571 5.3487327e-08    6776.8723 
+    4940   0.01456709 5.0082359e-08    6777.1026 
+    4950  0.014567577 4.7055963e-08    6777.3183 
+    4960  0.014568035 4.4350048e-08     6777.521 
+    4970  0.014568467 4.1917669e-08     6777.712 
+    4980  0.014568876 3.9720495e-08    6777.8926 
+    4990  0.014569265 3.7726941e-08    6778.0636 
+    5000  0.014569634 3.5910753e-08    6778.2261 
+Loop time of 24.155 on 1 procs for 5000 steps with 32000 atoms
+
+Performance: 0.001 ns/day, 37368.951 hours/ns, 206.996 timesteps/s
+99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 15.795     | 15.795     | 15.795     |   0.0 | 65.39
+Neigh   | 1.5182     | 1.5182     | 1.5182     |   0.0 |  6.29
+Comm    | 0.58555    | 0.58555    | 0.58555    |   0.0 |  2.42
+Output  | 0.0064323  | 0.0064323  | 0.0064323  |   0.0 |  0.03
+Modify  | 5.619      | 5.619      | 5.619      |   0.0 | 23.26
+Other   |            | 0.6313     |            |       |  2.61
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    13556 ave 13556 max 13556 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    0 ave 0 max 0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+FullNghs:  576016 ave 576016 max 576016 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 576016
+Ave neighs/atom = 18.0005
+Neighbor list builds = 68
+Dangerous builds = 42
+Total wall time: 0:00:24
diff --git a/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.4 b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.4
new file mode 100644
index 0000000000..e0f45ef460
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.g++.4
@@ -0,0 +1,597 @@
+LAMMPS (28 Feb 2019)
+OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:88)
+  using 1 OpenMP thread(s) per MPI task
+# Test case / example for fix electron/stopping
+# Perfect Si lattice with one primary knock-on atom.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 5.431
+Lattice spacing in x,y,z = 5.431 5.431 5.431
+
+region rbox block -10 10 -10 10 -10 10
+create_box 1 rbox
+Created orthogonal box = (-54.31 -54.31 -54.31) to (54.31 54.31 54.31)
+  1 by 2 by 2 MPI processor grid
+
+mass 1 28.0855
+
+create_atoms 1 box
+Created 32000 atoms
+  create_atoms CPU = 0.000856161 secs
+
+velocity all create 300 42534 mom yes rot yes
+
+group gPKA id 1
+1 atoms in group gPKA
+velocity gPKA set 1120 1620 389
+
+pair_style sw
+pair_coeff * * Si.sw Si
+Reading potential file Si.sw with DATE: 2007-06-11
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop
+fix fnve all nve
+
+thermo 10
+thermo_style custom step time dt f_fel
+
+#compute ek all ke/atom
+#dump mydump all custom 200 elstop.dump id x y z vx vy vz fx fy fz c_ek
+
+run 5000
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 5.77118
+  ghost atom cutoff = 5.77118
+  binsize = 2.88559, bins = 38 38 38
+  2 neighbor lists, perpetual/occasional/extra = 1 1 0
+  (1) pair sw, perpetual
+      attributes: full, newton on
+      pair build: full/bin/atomonly
+      stencil: full/bin/3d
+      bin: standard
+  (2) fix electron/stopping, occasional, copy from (1)
+      attributes: full, newton on
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 3.825 | 3.825 | 3.825 Mbytes
+Step Time Dt f_fel 
+       0            0  4.98128e-05            0 
+      10 0.00030141235 7.4131221e-06    143.83474 
+      20 0.00035951242 6.0314282e-06    171.53584 
+      30 0.00057457861 3.511731e-05    274.07067 
+      40 0.00086591115 5.8248574e-06    412.87352 
+      50 0.00090045749 2.102773e-06    429.31482 
+      60 0.00091828633 1.5369556e-06    437.79502 
+      70 0.00093306208 1.4645168e-06    444.82135 
+      80 0.00094861336 1.7491631e-06    452.21657 
+      90 0.00097033523 3.0804023e-06    462.54893 
+     100 0.0010792154 4.9075683e-05    514.37014 
+     110 0.0012080866 2.3201427e-06    575.68827 
+     120 0.0012239719 1.0507964e-06    583.23648 
+     130 0.0012325518 6.8263389e-07    587.30975 
+     140 0.0012385211 5.1201217e-07    590.14147 
+     150 0.0012431661 4.1521773e-07    592.34347 
+     160  0.001247021 3.5379338e-07    594.16984 
+     170 0.0012503586 3.1202939e-07    595.75031 
+     180 0.0012533374 2.8236002e-07    597.16021 
+     190 0.0012560582 2.6071816e-07    598.44745 
+     200 0.0012585895 2.4474279e-07    599.64465 
+     210  0.001260981 2.3298831e-07     600.7754 
+     220 0.0012632704 2.2454021e-07    601.85763 
+     230  0.001265488 2.1881458e-07    602.90571 
+     240 0.0012676591 2.154488e-07    603.93173 
+     250 0.0012698064 2.1424147e-07    604.94641 
+     260 0.0012719511 2.1512161e-07     605.9598 
+     270 0.0012741141 2.1813836e-07    606.98189 
+     280 0.0012763174 2.2346783e-07    608.02314 
+     290 0.0012785856 2.3143942e-07    609.09518 
+     300 0.0012809473 2.4258888e-07     610.2116 
+     310 0.0012834376 2.5775518e-07    611.38916 
+     320 0.0012861023 2.7825685e-07    612.64953 
+     330 0.0012890034 3.062254e-07    614.02218 
+     340 0.0012922301 3.4527805e-07    615.54956 
+     350 0.0012959196 4.0200263e-07    617.29679 
+     360    0.0013003 4.8966484e-07    619.37233 
+     370 0.0013057965 6.3923294e-07     621.9783 
+     380   0.00131335 9.423535e-07    625.56194 
+     390 0.0013258073 1.8277087e-06    631.47661 
+     400 0.0013653313 1.4985239e-05    650.25939 
+     410 0.0016927117 4.5643592e-05    805.84388 
+     420  0.002085671 2.5698185e-05    992.40957 
+     430 0.0021935861 5.3102217e-06     1043.597 
+     440 0.0022614637 1.5788858e-05    1075.7807 
+     450 0.0025463923 1.6989456e-05    1210.8535 
+     460 0.0029095455 3.9205279e-05    1382.8591 
+     470  0.003309122 3.8882183e-05    1571.9128 
+     480 0.0037129772 4.0573389e-05    1762.7749 
+     490  0.004120209 2.7525742e-05    1955.0148 
+     500 0.0042711049 1.9373612e-05    2026.1805 
+     510 0.0045860203 2.4773305e-05    2174.6208 
+     520  0.004995259 3.8017877e-05    2367.3335 
+     530 0.0051457762 5.4205615e-06    2438.1475 
+     540  0.005203221 8.8625579e-06    2465.1577 
+     550 0.0054221421 5.7304442e-06    2568.0888 
+     560 0.0054524345 1.5599386e-06    2582.3169 
+     570 0.0054645073 9.1093243e-07    2587.9819 
+     580 0.0054723338 6.6033575e-07    2591.6518 
+     590 0.0054782965 5.3155858e-07     2594.446 
+     600  0.005483241 4.5581839e-07    2596.7619 
+     610 0.0054875675 4.0821885e-07    2598.7875 
+     620 0.0054915013 3.7775507e-07    2600.6287 
+     630 0.0054951861 3.5898561e-07    2602.3529 
+     640 0.0054987249 3.4911444e-07    2604.0086 
+     650 0.0055021998 3.4682698e-07    2605.6342 
+     660 0.0055056844 3.5182676e-07    2607.2643 
+     670 0.0055092538 3.6473743e-07    2608.9342 
+     680 0.0055129936 3.8730595e-07    2610.6841 
+     690 0.0055170145 4.2303997e-07     2612.566 
+     700 0.0055214749 4.7876507e-07    2614.6542 
+     710 0.0055266296 5.6863699e-07    2617.0684 
+     720 0.0055329452 7.2626141e-07    2620.0278 
+     730 0.0055414528 1.0527596e-06    2624.0166 
+     740 0.0055553208 2.0371511e-06     2630.523 
+     750 0.0056023478 2.2133456e-05    2652.6057 
+     760 0.0059007346 3.8610962e-05    2792.7168 
+     770 0.0062508505 3.9428337e-05    2956.9697 
+     780 0.0063682296 2.1223153e-06    3011.9927 
+     790 0.0063824196 9.0656948e-07    3018.6346 
+     800 0.0063896741 5.6137676e-07    3022.0266 
+     810 0.0063944906 4.0276465e-07    3024.2763 
+     820 0.0063980771 3.1284015e-07    3025.9499 
+     830 0.0064009279 2.5537602e-07    3027.2789 
+     840  0.006403292 2.1569057e-07    3028.3801 
+     850 0.0064053117 1.8674792e-07      3029.32 
+     860 0.0064070756 1.6477015e-07    3030.1402 
+     870 0.0064086425 1.4755386e-07    3030.8682 
+     880 0.0064100535 1.3373048e-07    3031.5232 
+     890 0.0064113381 1.2240666e-07    3032.1191 
+     900 0.0064125183 1.1297538e-07    3032.6662 
+     910 0.0064136112 1.0501022e-07    3033.1724 
+     920 0.0064146298 9.8203162e-08    3033.6439 
+     930 0.0064155847 9.2326368e-08    3034.0856 
+     940 0.0064164843 8.7207794e-08    3034.5015 
+     950 0.0064173357 8.2715188e-08    3034.8948 
+     960 0.0064181446 7.8745279e-08    3035.2682 
+     970 0.0064189159 7.5216291e-08    3035.6241 
+     980 0.0064196535 7.2062662e-08    3035.9642 
+     990 0.0064203612 6.9231241e-08    3036.2903 
+    1000 0.0064210418 6.6678502e-08    3036.6038 
+    1010  0.006421698 6.4368478e-08    3036.9059 
+    1020 0.0064223321 6.2271202e-08    3037.1976 
+    1030 0.0064229461 6.0361517e-08    3037.4799 
+    1040 0.0064235417 5.8618162e-08    3037.7537 
+    1050 0.0064241206 5.702305e-08    3038.0197 
+    1060 0.0064246841 5.556071e-08    3038.2784 
+    1070 0.0064252336 5.4217838e-08    3038.5306 
+    1080 0.0064257701 5.2982939e-08    3038.7768 
+    1090 0.0064262948 5.1846034e-08    3039.0174 
+    1100 0.0064268085 5.079843e-08    3039.2529 
+    1110  0.006427312 4.9832523e-08    3039.4837 
+    1120 0.0064278063 4.8941643e-08    3039.7101 
+    1130 0.0064282919 4.811992e-08    3039.9325 
+    1140 0.0064287697 4.7362175e-08    3040.1512 
+    1150 0.0064292401 4.6663831e-08    3040.3665 
+    1160 0.0064297038 4.6020833e-08    3040.5786 
+    1170 0.0064301613 4.5429586e-08    3040.7878 
+    1180 0.0064306131 4.4886899e-08    3040.9944 
+    1190 0.0064310597 4.4389937e-08    3041.1986 
+    1200 0.0064315016 4.3936183e-08    3041.4005 
+    1210  0.006431939 4.3523406e-08    3041.6003 
+    1220 0.0064323725 4.3149628e-08    3041.7984 
+    1230 0.0064328025 4.2813101e-08    3041.9947 
+    1240 0.0064332292 4.2512286e-08    3042.1896 
+    1250 0.0064336531 4.2245836e-08    3042.3831 
+    1260 0.0064340745 4.201258e-08    3042.5755 
+    1270 0.0064344937 4.1811507e-08    3042.7668 
+    1280  0.006434911 4.1641759e-08    3042.9572 
+    1290 0.0064353268 4.1502622e-08    3043.1469 
+    1300 0.0064357413 4.1393513e-08     3043.336 
+    1310 0.0064361549 4.1313982e-08    3043.5247 
+    1320 0.0064365678 4.1263699e-08     3043.713 
+    1330 0.0064369803 4.1242458e-08    3043.9012 
+    1340 0.0064373927 4.125017e-08    3044.0893 
+    1350 0.0064378054 4.1286866e-08    3044.2775 
+    1360 0.0064382185 4.1352691e-08     3044.466 
+    1370 0.0064386324 4.1447915e-08    3044.6548 
+    1380 0.0064390475 4.1572925e-08    3044.8441 
+    1390 0.0064394639 4.1728238e-08     3045.034 
+    1400 0.0064398819 4.1914501e-08    3045.2247 
+    1410  0.006440302 4.2132499e-08    3045.4163 
+    1420 0.0064407245 4.2383163e-08    3045.6091 
+    1430 0.0064411496 4.2667584e-08     3045.803 
+    1440 0.0064415776 4.2987016e-08    3045.9983 
+    1450 0.0064420091  4.33429e-08    3046.1952 
+    1460 0.0064424443 4.3736874e-08    3046.3938 
+    1470 0.0064428835 4.4170794e-08    3046.5944 
+    1480 0.0064433274 4.4646761e-08     3046.797 
+    1490 0.0064437761 4.5167139e-08    3047.0019 
+    1500 0.0064442303 4.5734596e-08    3047.2093 
+    1510 0.0064446904 4.6352132e-08    3047.4195 
+    1520 0.0064451569 4.7023127e-08    3047.6327 
+    1530 0.0064456303 4.7751389e-08     3047.849 
+    1540 0.0064461114 4.8541214e-08    3048.0689 
+    1550 0.0064466006 4.9397455e-08    3048.2926 
+    1560 0.0064470987 5.0325606e-08    3048.5204 
+    1570 0.0064476064 5.1331902e-08    3048.7527 
+    1580 0.0064481245 5.2423434e-08    3048.9899 
+    1590  0.006448654 5.3608296e-08    3049.2323 
+    1600 0.0064491958 5.4895757e-08    3049.4804 
+    1610  0.006449751 5.6296469e-08    3049.7347 
+    1620 0.0064503207 5.7822727e-08    3049.9959 
+    1630 0.0064509063 5.9488788e-08    3050.2644 
+    1640 0.0064515092 6.1311263e-08    3050.5409 
+    1650 0.0064521312 6.3309616e-08    3050.8263 
+    1660  0.006452774 6.5506785e-08    3051.1214 
+    1670 0.0064534398 6.7929981e-08    3051.4272 
+    1680 0.0064541309 7.0611714e-08    3051.7448 
+    1690 0.0064548502 7.3591127e-08    3052.0755 
+    1700 0.0064556007 7.6915753e-08    3052.4207 
+    1710 0.0064563863 8.064386e-08    3052.7823 
+    1720 0.0064572113 8.4847627e-08    3053.1621 
+    1730 0.0064580807 8.9617502e-08    3053.5627 
+    1740 0.0064590008 9.5068304e-08    3053.9869 
+    1750  0.006459979 1.0134793e-07    3054.4381 
+    1760 0.0064610244 1.0865003e-07    3054.9206 
+    1770 0.0064621483 1.1723301e-07    3055.4397 
+    1780 0.0064633651 1.2744917e-07    3056.0021 
+    1790 0.0064646931 1.3979108e-07    3056.6163 
+    1800 0.0064661566 1.5496815e-07    3057.2937 
+    1810 0.0064677883 1.7403894e-07    3058.0494 
+    1820  0.006469634 1.9865267e-07    3058.9049 
+    1830 0.0064717601 2.3152064e-07    3059.8912 
+    1840 0.0064742682 2.7741818e-07    3061.0556 
+    1850 0.0064773249 3.4556351e-07    3062.4759 
+    1860 0.0064812294 4.5619653e-07    3064.2917 
+    1870 0.0064866019 6.6337441e-07    3066.7924 
+    1880 0.0064950748 1.1706786e-06    3070.7399 
+    1890 0.0065140322 3.7878566e-06    3079.5809 
+    1900 0.0066957122 6.7105464e-06    3164.3691 
+    1910 0.0067279909 1.493224e-06    3179.4195 
+    1920 0.0067392058 8.1410321e-07    3184.6428 
+    1930 0.0067460435 5.5996376e-07    3187.8246 
+    1940 0.0067509948 4.2936252e-07    3190.1267 
+    1950 0.0067549055 3.5072462e-07    3191.9436 
+    1960 0.0067581623 2.9865016e-07    3193.4556 
+    1970 0.0067609737 2.6192794e-07    3194.7601 
+    1980 0.0067634648 2.3486813e-07    3195.9153 
+    1990 0.0067657165 2.1428715e-07    3196.9589 
+    2000 0.0067677841 1.9827071e-07    3197.9167 
+    2010 0.0067697074 1.8560268e-07    3198.8073 
+    2020  0.006771516 1.7547663e-07    3199.6445 
+    2030 0.0067732327 1.6733961e-07    3200.4388 
+    2040 0.0067748755 1.6080268e-07    3201.1987 
+    2050 0.0067764591 1.5558723e-07     3201.931 
+    2060 0.0067779957 1.5149159e-07    3202.6414 
+    2070 0.0067794958 1.4836976e-07    3203.3348 
+    2080 0.0067809687 1.4611749e-07    3204.0155 
+    2090 0.0067824227 1.4466322e-07    3204.6874 
+    2100 0.0067838655 1.4396229e-07    3205.3542 
+    2110 0.0067853047 1.4399348e-07    3206.0191 
+    2120 0.0067867474 1.4475745e-07    3206.6858 
+    2130 0.0067882012 1.4627671e-07    3207.3576 
+    2140 0.0067896737 1.4859736e-07    3208.0381 
+    2150 0.0067911733 1.5179256e-07    3208.7311 
+    2160 0.0067927092 1.5596849e-07    3209.4411 
+    2170 0.0067942917 1.6127347e-07    3210.1728 
+    2180 0.0067959331 1.6791214e-07    3210.9319 
+    2190 0.0067976479 1.7616698e-07    3211.7251 
+    2200 0.0067994539 1.8643208e-07    3212.5608 
+    2210 0.0068013736 1.9926751e-07    3213.4494 
+    2220 0.0068034361 2.154897e-07    3214.4044 
+    2230 0.0068056803 2.3632937e-07    3215.4441 
+    2240 0.0068081604 2.6372257e-07    3216.5937 
+    2250 0.0068109549 3.0088625e-07    3217.8897 
+    2260 0.0068141846 3.5356212e-07    3219.3884 
+    2270 0.0068180485 4.330391e-07    3221.1825 
+    2280 0.0068229109 5.6479966e-07    3223.4417 
+    2290 0.0068295488 8.2016289e-07    3226.5284 
+    2300 0.0068401389 1.4950446e-06    3231.4568 
+    2310 0.0068668194 6.4794351e-06    3243.8847 
+    2320 0.0071339944 2.3817631e-05    3368.3827 
+    2330 0.0074221156 3.4144405e-05    3502.5364 
+    2340  0.007650075 3.3142879e-06    3608.5998 
+    2350 0.0076703526 1.1927138e-06    3618.0215 
+    2360 0.0076797526 7.185434e-07    3622.3847 
+    2370 0.0076859146 5.1648342e-07    3625.2424 
+    2380 0.0076905359 4.0623045e-07    3627.3839 
+    2390 0.0076942651 3.3753265e-07    3629.1108 
+    2400 0.0076974175 2.910504e-07    3630.5697 
+    2410 0.0077001699 2.5780894e-07    3631.8426 
+    2420  0.007702631 2.3309498e-07    3632.9803 
+    2430  0.007704873 2.1420535e-07    3634.0161 
+    2440 0.0077069459 1.9948463e-07    3634.9733 
+    2450 0.0077088862 1.8786685e-07     3635.869 
+    2460 0.0077107216 1.7863849e-07     3636.716 
+    2470 0.0077124736 1.713078e-07    3637.5242 
+    2480 0.0077141595 1.6552875e-07    3638.3017 
+    2490 0.0077157937 1.6105508e-07    3639.0552 
+    2500 0.0077173883 1.5771154e-07    3639.7903 
+    2510 0.0077189541 1.553756e-07    3640.5121 
+    2520 0.0077205008 1.539658e-07    3641.2249 
+    2530 0.0077220373 1.534345e-07     3641.933 
+    2540 0.0077235724 1.5376384e-07    3642.6405 
+    2550 0.0077251148 1.5496427e-07    3643.3513 
+    2560 0.0077266731 1.5707538e-07    3644.0695 
+    2570  0.007728257 1.6016917e-07    3644.7995 
+    2580 0.0077298765 1.6435633e-07    3645.5461 
+    2590 0.0077315435 1.6979645e-07    3646.3147 
+    2600 0.0077332712 1.7671412e-07    3647.1115 
+    2610 0.0077350759 1.8542415e-07     3647.944 
+    2620 0.0077369773 1.9637153e-07    3648.8214 
+    2630 0.0077390006 2.1019669e-07    3649.7553 
+    2640 0.0077411783 2.2784614e-07    3650.7609 
+    2650 0.0077435548 2.5076917e-07    3651.8588 
+    2660 0.0077461922 2.8128932e-07    3653.0779 
+    2670 0.0077491826 3.233607e-07    3654.4608 
+    2680 0.0077526703 3.8426634e-07    3656.0746 
+    2690 0.0077569014 4.7896536e-07    3658.0337 
+    2700 0.0077623476 6.435095e-07    3660.5572 
+    2710 0.0077700972 9.9066415e-07    3664.1508 
+    2720 0.0077837321 2.1192489e-06    3670.4787 
+    2730 0.0078537309 5.0478452e-05    3702.9978 
+    2740 0.0080019842 2.234588e-06    3771.8639 
+    2750 0.0080167983 9.3912008e-07    3778.7349 
+    2760 0.0080243022 5.7998894e-07    3782.2116 
+    2770 0.0080292782 4.1619434e-07    3784.5147 
+    2780 0.0080329859 3.2365852e-07    3786.2291 
+    2790 0.0080359374 2.6464667e-07    3787.5927 
+    2800 0.0080383893 2.2394834e-07    3788.7244 
+    2810 0.0080404882 1.9429813e-07    3789.6924 
+    2820 0.0080423251 1.7180333e-07    3790.5389 
+    2830 0.0080439606 1.5419708e-07     3791.292 
+    2840 0.0080454366 1.4007294e-07    3791.9711 
+    2850 0.0080467835 1.2851365e-07    3792.5904 
+    2860 0.0080480239 1.1889632e-07    3793.1603 
+    2870 0.0080491753 1.1078364e-07     3793.689 
+    2880 0.0080502511 1.0385986e-07    3794.1826 
+    2890 0.0080512621 9.7891518e-08    3794.6462 
+    2900 0.0080522171 9.2702379e-08    3795.0838 
+    2910 0.0080531232 8.815703e-08    3795.4988 
+    2920 0.0080539863 8.4149767e-08    3795.8939 
+    2930 0.0080548115 8.0596927e-08    3796.2714 
+    2940 0.0080556029 7.7431468e-08    3796.6332 
+    2950 0.0080563642 7.4599072e-08    3796.9811 
+    2960 0.0080570985 7.2055292e-08    3797.3166 
+    2970 0.0080578086 6.9763432e-08    3797.6407 
+    2980 0.0080584967 6.7692955e-08    3797.9548 
+    2990 0.0080591651 6.5818259e-08    3798.2596 
+    3000 0.0080598155 6.4117744e-08    3798.5562 
+    3010 0.0080604496 6.2573076e-08    3798.8452 
+    3020 0.0080610689 6.1168613e-08    3799.1273 
+    3030 0.0080616747 5.9890948e-08    3799.4033 
+    3040 0.0080622683 5.8728542e-08    3799.6735 
+    3050 0.0080628507 5.7671429e-08    3799.9386 
+    3060 0.0080634231 5.6710976e-08     3800.199 
+    3070 0.0080639862 5.5839691e-08    3800.4551 
+    3080  0.008064541 5.5051058e-08    3800.7074 
+    3090 0.0080650882 5.4339406e-08    3800.9562 
+    3100 0.0080656287 5.3699803e-08    3801.2018 
+    3110  0.008066163 5.3127961e-08    3801.4446 
+    3120  0.008066692 5.2620159e-08    3801.6849 
+    3130 0.0080672161 5.2173187e-08     3801.923 
+    3140 0.0080677361 5.1784286e-08    3802.1591 
+    3150 0.0080682524 5.1451107e-08    3802.3936 
+    3160 0.0080687656 5.1171678e-08    3802.6266 
+    3170 0.0080692762 5.0944369e-08    3802.8584 
+    3180 0.0080697848 5.0767875e-08    3803.0892 
+    3190 0.0080702919 5.064119e-08    3803.3194 
+    3200 0.0080707979 5.0563598e-08     3803.549 
+    3210 0.0080713034 5.0534662e-08    3803.7784 
+    3220 0.0080718088 5.0554215e-08    3804.0077 
+    3230 0.0080723146 5.0622362e-08    3804.2373 
+    3240 0.0080728213 5.073948e-08    3804.4672 
+    3250 0.0080733294 5.090622e-08    3804.6978 
+    3260 0.0080738394 5.1123521e-08    3804.9292 
+    3270 0.0080743518 5.139262e-08    3805.1618 
+    3280 0.0080748671 5.171507e-08    3805.3957 
+    3290 0.0080753859 5.2092761e-08    3805.6311 
+    3300 0.0080759088 5.2527952e-08    3805.8685 
+    3310 0.0080764362 5.3023303e-08    3806.1079 
+    3320 0.0080769689 5.3581914e-08    3806.3498 
+    3330 0.0080775075 5.4207378e-08    3806.5944 
+    3340 0.0080780526 5.4903844e-08     3806.842 
+    3350 0.0080786051 5.567608e-08     3807.093 
+    3360 0.0080791656 5.652957e-08    3807.3477 
+    3370 0.0080797351 5.7470611e-08    3807.6065 
+    3380 0.0080803144 5.8506444e-08    3807.8698 
+    3390 0.0080809045 5.9645402e-08    3808.1381 
+    3400 0.0080815065 6.0897097e-08     3808.412 
+    3410 0.0080821215 6.2272649e-08    3808.6918 
+    3420 0.0080827509 6.3784959e-08    3808.9782 
+    3430 0.0080833961 6.5449061e-08     3809.272 
+    3440 0.0080840587 6.7282544e-08    3809.5737 
+    3450 0.0080847405 6.9306098e-08    3809.8843 
+    3460 0.0080854434 7.1544197e-08    3810.2047 
+    3470 0.0080861698 7.402597e-08    3810.5359 
+    3480 0.0080869223 7.6786336e-08    3810.8791 
+    3490 0.0080877037 7.9867475e-08    3811.2357 
+    3500 0.0080885176 8.3320783e-08    3811.6073 
+    3510 0.0080893679 8.7209484e-08    3811.9957 
+    3520 0.0080902594 9.1612182e-08    3812.4031 
+    3530 0.0080911975 9.662777e-08    3812.8321 
+    3540  0.008092189 1.0238234e-07    3813.2857 
+    3550  0.008093242 1.0903907e-07    3813.7677 
+    3560 0.0080943663 1.1681285e-07    3814.2827 
+    3570 0.0080955744 1.2599212e-07    3814.8364 
+    3580 0.0080968821 1.3697303e-07    3815.4361 
+    3590 0.0080983096 1.5031413e-07    3816.0912 
+    3600  0.008099884 1.6682798e-07    3816.8142 
+    3610 0.0081016421 1.877419e-07    3817.6222 
+    3620 0.0081036359 2.1499717e-07    3818.5391 
+    3630 0.0081059419 2.5184713e-07    3819.6004 
+    3640 0.0081086795 3.041685e-07    3820.8614 
+    3650 0.0081120491 3.8370792e-07    3822.4147 
+    3660 0.0081164246 5.1761443e-07    3824.4335 
+    3670 0.0081226282 7.8476649e-07    3827.2984 
+    3680 0.0081330874 1.5377267e-06     3832.133 
+    3690 0.0081640997 9.4754571e-06    3846.4828 
+    3700 0.0084647088 3.6520628e-05    3985.6105 
+    3710 0.0087788105 5.0607918e-05    4130.8576 
+    3720 0.0089496823 2.7369422e-06    4209.8144 
+    3730 0.0089676915 1.1442905e-06    4218.1247 
+    3740 0.0089769276 7.2591487e-07    4222.3827 
+    3750 0.0089832427 5.3867242e-07    4225.2918 
+    3760 0.0089881163 4.3436406e-07    4227.5353 
+    3770 0.0089921427 3.689283e-07    4229.3876 
+    3780 0.0089956201 3.2480899e-07    4230.9866 
+    3790 0.0089987196 2.9368682e-07    4232.4111 
+    3800 0.0090015492 2.7114137e-07     4233.711 
+    3810 0.0090041821 2.5463023e-07    4234.9202 
+    3820 0.0090066711 2.4261002e-07    4236.0629 
+    3830 0.0090090563 2.3411372e-07    4237.1578 
+    3840 0.0090113701 2.2853263e-07    4238.2196 
+    3850 0.0090136398 2.2549889e-07    4239.2611 
+    3860 0.0090158898 2.2482231e-07    4240.2936 
+    3870 0.0090181435 2.264602e-07    4241.3277 
+    3880 0.0090204243 2.3051066e-07    4242.3742 
+    3890 0.0090227572 2.3722751e-07    4243.4449 
+    3900 0.0090251709 2.4706119e-07    4244.5528 
+    3910 0.0090276995 2.6073849e-07    4245.7136 
+    3920 0.0090303862 2.7940938e-07    4246.9474 
+    3930 0.0090332884 3.0492215e-07    4248.2805 
+    3940 0.0090364872 3.4036714e-07    4249.7505 
+    3950 0.0090401038 3.9124064e-07    4251.4133 
+    3960 0.0090443343 4.6822852e-07    4253.3593 
+    3970 0.0090495296 5.9498137e-07    4255.7504 
+    3980 0.0090564177 8.3552398e-07    4258.9229 
+    3990 0.0090669429 1.4384739e-06     4263.774 
+    4000 0.0090904831 4.9111984e-06    4274.6331 
+    4010 0.0092929124 8.3135371e-06    4368.0633 
+    4020 0.0093414419 3.1334206e-06    4390.4447 
+    4030 0.0093714047 3.1966251e-06    4404.2581 
+    4040 0.0094176451 9.8265197e-06    4425.5788 
+    4050 0.0097772862 4.2787238e-05    4591.3956 
+    4060  0.010043914 5.0703357e-05    4714.2148 
+    4070  0.010275503 5.9586189e-06    4820.8179 
+    4080  0.010329372 6.4730027e-06    4845.5948 
+    4090  0.010580719 3.2675549e-05    4961.1991 
+    4100   0.01097933 4.1824022e-05    5144.3777 
+    4110  0.011375225 4.4528389e-05    5326.1041 
+    4120  0.011791986 4.4629128e-05    5517.1914 
+    4130  0.012199057 3.8467532e-05    5703.6209 
+    4140  0.012388718 1.6598211e-05    5790.3997 
+    4150  0.012719145 2.6617697e-05    5941.4863 
+    4160  0.013138874 3.9714695e-05    6133.2127 
+    4170  0.013296898 5.7028372e-06    6205.3279 
+    4180  0.013359491 1.0623338e-05    6233.8756 
+    4190  0.013580279 4.9259166e-06    6334.5676 
+    4200  0.013608204 1.5476759e-06    6347.2885 
+    4210  0.013620408 9.4152281e-07    6352.8431 
+    4220  0.013628594 7.0110358e-07    6356.5664 
+    4230   0.01363499 5.7777895e-07     6359.474 
+    4240  0.013640419 5.071712e-07     6361.941 
+    4250  0.013645286 4.6571283e-07    6364.1515 
+    4260  0.013649829 4.4320314e-07    6366.2145 
+    4270  0.013654213 4.3508698e-07    6368.2055 
+    4280  0.013658575 4.3986766e-07     6370.186 
+    4290  0.013663045 4.5837677e-07    6372.2157 
+    4300  0.013667773 4.9416073e-07     6374.363 
+    4310  0.013672963 5.5535604e-07    6376.7211 
+    4320   0.01367894 6.6021298e-07    6379.4372 
+    4330  0.013686311 8.5526524e-07    6382.7882 
+    4340  0.013696507 1.296644e-06    6387.4262 
+    4350  0.013714701 2.9652221e-06    6395.7088 
+    4360  0.013881439 3.5899661e-05    6471.6738 
+    4370  0.014196617 3.1253608e-05    6615.1811 
+    4380  0.014504048 7.0683429e-06    6755.0394 
+    4390  0.014536871 1.4515319e-06    6769.9538 
+    4400  0.014547629 7.6742092e-07    6774.8365 
+    4410   0.01455401 5.1561918e-07    6777.7294 
+    4420  0.014558528 3.8717171e-07    6779.7758 
+    4430  0.014562024 3.1004583e-07    6781.3579 
+    4440  0.014564879 2.5893679e-07    6782.6486 
+    4450  0.014567296 2.2275131e-07    6783.7406 
+    4460  0.014569397 1.9588676e-07    6784.6888 
+    4470  0.014571258 1.7521879e-07    6785.5285 
+    4480  0.014572934 1.5887218e-07    6786.2838 
+    4490  0.014574461 1.4565562e-07    6786.9717 
+    4500  0.014575867 1.3477717e-07    6787.6046 
+    4510  0.014577173 1.2569059e-07    6788.1919 
+    4520  0.014578394 1.1800737e-07     6788.741 
+    4530  0.014579544 1.1144387e-07    6789.2576 
+    4540  0.014580632 1.0578845e-07    6789.7464 
+    4550  0.014581667 1.0088007e-07    6790.2111 
+    4560  0.014582656 9.6594222e-08    6790.6548 
+    4570  0.014583605 9.283317e-08    6791.0802 
+    4580  0.014584518 8.9519251e-08    6791.4895 
+    4590    0.0145854 8.6590045e-08    6791.8845 
+    4600  0.014586254 8.3994895e-08     6792.267 
+    4610  0.014587083 8.1692339e-08    6792.6383 
+    4620  0.014587891 7.9648193e-08    6792.9997 
+    4630  0.014588679 7.7834097e-08    6793.3523 
+    4640   0.01458945 7.6226411e-08    6793.6971 
+    4650  0.014590205 7.4805352e-08     6794.035 
+    4660  0.014590948 7.3554327e-08    6794.3668 
+    4670  0.014591678 7.2459408e-08    6794.6932 
+    4680  0.014592398 7.1508917e-08     6795.015 
+    4690   0.01459311 7.0693097e-08    6795.3328 
+    4700  0.014593813 7.0003852e-08    6795.6471 
+    4710  0.014594511 6.9434537e-08    6795.9585 
+    4720  0.014595203 6.8979799e-08    6796.2676 
+    4730  0.014595891 6.8635445e-08    6796.5748 
+    4740  0.014596576 6.839835e-08    6796.8807 
+    4750   0.01459726 6.8266383e-08    6797.1857 
+    4760  0.014597942 6.823836e-08    6797.4903 
+    4770  0.014598625 6.8314021e-08     6797.795 
+    4780  0.014599309 6.849402e-08    6798.1003 
+    4790  0.014599995 6.8779943e-08    6798.4065 
+    4800  0.014600684 6.9174339e-08    6798.7143 
+    4810  0.014601378 6.9680779e-08    6799.0241 
+    4820  0.014602078 7.0303936e-08    6799.3364 
+    4830  0.014602784 7.1049693e-08    6799.6517 
+    4840  0.014603498 7.1925284e-08    6799.9707 
+    4850  0.014604222 7.2939475e-08     6800.294 
+    4860  0.014604956 7.4102791e-08    6800.6221 
+    4870  0.014605703 7.5427802e-08    6800.9557 
+    4880  0.014606464 7.6929481e-08    6801.2958 
+    4890  0.014607241 7.8625665e-08     6801.643 
+    4900  0.014608036 8.0537626e-08    6801.9983 
+    4910   0.01460885 8.2690811e-08    6802.3627 
+    4920  0.014609688 8.5115787e-08    6802.7374 
+    4930  0.014610551 8.7849474e-08    6803.1237 
+    4940  0.014611443 9.0936752e-08    6803.5231 
+    4950  0.014612368 9.4432608e-08    6803.9372 
+    4960   0.01461333 9.8405013e-08    6804.3681 
+    4970  0.014614334 1.0293885e-07    6804.8181 
+    4980  0.014615386 1.0814135e-07    6805.2899 
+    4990  0.014616494 1.1414984e-07    6805.7869 
+    5000  0.014617666 1.2114278e-07     6806.313 
+Loop time of 9.26846 on 4 procs for 5000 steps with 32000 atoms
+
+Performance: 0.006 ns/day, 4250.474 hours/ns, 539.464 timesteps/s
+96.0% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 4.6281     | 4.7789     | 5.1937     |  11.0 | 51.56
+Neigh   | 0.40488    | 0.41576    | 0.43895    |   2.1 |  4.49
+Comm    | 0.8478     | 1.2799     | 1.4349     |  22.1 | 13.81
+Output  | 0.0048099  | 0.016429   | 0.050251   |  15.2 |  0.18
+Modify  | 2.1042     | 2.1347     | 2.1706     |   1.6 | 23.03
+Other   |            | 0.6427     |            |       |  6.93
+
+Nlocal:    8000 ave 8033 max 7977 min
+Histogram: 1 0 1 1 0 0 0 0 0 1
+Nghost:    6061.25 ave 6085 max 6028 min
+Histogram: 1 0 0 0 0 1 0 1 0 1
+Neighs:    0 ave 0 max 0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+FullNghs:  144002 ave 144601 max 143596 min
+Histogram: 1 0 1 1 0 0 0 0 0 1
+
+Total # of neighbors = 576008
+Ave neighs/atom = 18.0003
+Neighbor list builds = 67
+Dangerous builds = 38
+Total wall time: 0:00:09
diff --git a/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.1 b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.1
new file mode 100644
index 0000000000..a3370204b7
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.1
@@ -0,0 +1,196 @@
+LAMMPS (28 Feb 2019)
+OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:88)
+  using 1 OpenMP thread(s) per MPI task
+# Test case / example for fix electron/stopping
+# One fast atom, no other interactions.
+# Stopping only applied in a smaller box in the middle.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 1
+Lattice spacing in x,y,z = 1 1 1
+
+region rbox block -100 100 -100 100 -100 100
+region rsmallbox block -90 90 -90 90 -90 90
+
+create_box 1 rbox
+Created orthogonal box = (-100 -100 -100) to (100 100 100)
+  1 by 1 by 1 MPI processor grid
+
+mass 1 28.0855
+
+create_atoms 1 single 0 0 0
+Created 1 atoms
+  create_atoms CPU = 4.05312e-06 secs
+velocity all set 1120 1620 389
+
+pair_style zero 1
+pair_coeff * * 1
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop minneigh 0 region rsmallbox
+fix fnve all nve
+
+compute ek all ke/atom
+compute ektot all reduce sum c_ek
+
+thermo 100
+thermo_style custom step time dt f_fel c_ektot
+
+#dump mydump all custom 200 elstop.only.dump id x y z vx vy vz fx fy fz c_ek
+
+run 10000
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 3
+  ghost atom cutoff = 3
+  binsize = 1.5, bins = 134 134 134
+  2 neighbor lists, perpetual/occasional/extra = 1 1 0
+  (1) pair zero, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+  (2) fix electron/stopping, occasional
+      attributes: full, newton on
+      pair build: full/bin/atomonly
+      stencil: full/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 13.31 | 13.31 | 13.31 Mbytes
+Step Time Dt f_fel c_ektot 
+       0            0  4.98128e-05            0    5865.5525 
+     100 0.0049972222 5.0137252e-05    76.048699     5789.883 
+     200  0.010027278 5.0467945e-05    151.67477    5714.2548 
+     300  0.015090636 5.0803375e-05     226.8806    5639.0469 
+     400  0.020187777 5.1143663e-05     301.6685    5564.2569 
+     500  0.025319192 5.1488933e-05    376.04082    5489.8825 
+     600  0.030485386 5.1839314e-05    449.99984    5415.9215 
+     700  0.035686876 5.2194938e-05    523.54788    5342.3714 
+     800  0.040924195 5.2555944e-05    596.68721      5269.23 
+     900  0.046197886 5.2922477e-05    669.42011    5196.4951 
+    1000   0.05150851 5.3294685e-05    741.74883    5124.1643 
+    1100  0.056856642 5.3672723e-05    813.67563    5052.2355 
+    1200  0.062229338 5.3731851e-05    824.43012    5041.1224 
+    1300  0.067602524 5.3731851e-05    824.43012    5041.1224 
+    1400  0.072978188 5.387166e-05    850.91948    5014.9907 
+    1500   0.07838447 5.425887e-05    922.23961    4943.6685 
+    1600   0.08382978 5.4652329e-05    993.16341    4872.7428 
+    1700  0.089299984 5.4705935e-05    1002.3545     4863.198 
+    1800  0.094770578 5.4705935e-05    1002.3545     4863.198 
+    1900   0.10024117 5.4705935e-05    1002.3545     4863.198 
+    2000   0.10571333 5.4819488e-05    1022.8338    4843.0716 
+    2100   0.11121515 5.5222127e-05    1093.1986    4772.7048 
+    2200   0.11675757 5.5631458e-05    1163.1724    4702.7291 
+    2300   0.12234126 5.6047675e-05    1232.7573    4633.1422 
+    2400   0.12796692 5.6470985e-05    1301.9555     4563.942 
+    2500   0.13363527 5.6901598e-05    1370.7692    4495.1264 
+    2600   0.13934706 5.7339739e-05    1439.2006    4426.6932 
+    2700   0.14510304 5.7785637e-05    1507.2516    4358.6403 
+    2800     0.150904 5.8239536e-05    1574.9245    4290.9655 
+    2900   0.15675076 5.8701688e-05    1642.2213    4223.6668 
+    3000   0.16264416 5.9172358e-05    1709.1441    4156.7422 
+    3100   0.16858505 5.9651822e-05     1775.695    4090.1894 
+    3200   0.17457434 6.0140369e-05    1841.8761    4024.0064 
+    3300   0.18061294 6.0638302e-05    1907.6894    3958.1913 
+    3400   0.18669814 6.0949329e-05    1947.6558    3917.8967 
+    3500   0.19279307 6.0949329e-05    1947.6558    3917.8967 
+    3600     0.198888 6.0949329e-05    1947.6558    3917.8967 
+    3700   0.20498294 6.0949329e-05    1947.6558    3917.8967 
+    3800   0.21107787 6.0949329e-05    1947.6558    3917.8967 
+    3900    0.2171728 6.0949329e-05    1947.6558    3917.8967 
+    4000   0.22326773 6.0949329e-05    1947.6558    3917.8967 
+    4100   0.22936267 6.0949329e-05    1947.6558    3917.8967 
+    4200    0.2354576 6.0949329e-05    1947.6558    3917.8967 
+    4300   0.24155253 6.0949329e-05    1947.6558    3917.8967 
+    4400   0.24764747 6.0949329e-05    1947.6558    3917.8967 
+    4500    0.2537424 6.0949329e-05    1947.6558    3917.8967 
+    4600   0.25983733 6.0949329e-05    1947.6558    3917.8967 
+    4700   0.26593227 6.0949329e-05    1947.6558    3917.8967 
+    4800    0.2720272 6.0949329e-05    1947.6558    3917.8967 
+    4900   0.27812213 6.0949329e-05    1947.6558    3917.8967 
+    5000   0.28421706 6.0949329e-05    1947.6558    3917.8967 
+    5100     0.290312 6.0949329e-05    1947.6558    3917.8967 
+    5200   0.29640693 6.0949329e-05    1947.6558    3917.8967 
+    5300   0.30250186 6.0949329e-05    1947.6558    3917.8967 
+    5400    0.3085968 6.0949329e-05    1947.6558    3917.8967 
+    5500   0.31469173 6.0949329e-05    1947.6558    3917.8967 
+    5600   0.32078666 6.0949329e-05    1947.6558    3917.8967 
+    5700   0.32688159 6.0949329e-05    1947.6558    3917.8967 
+    5800   0.33297653 6.0949329e-05    1947.6558    3917.8967 
+    5900   0.33907146 6.0949329e-05    1947.6558    3917.8967 
+    6000   0.34516639 6.0949329e-05    1947.6558    3917.8967 
+    6100   0.35126133 6.0949329e-05    1947.6558    3917.8967 
+    6200   0.35735626 6.0949329e-05    1947.6558    3917.8967 
+    6300   0.36345119 6.0949329e-05    1947.6558    3917.8967 
+    6400   0.36954612 6.0949329e-05    1947.6558    3917.8967 
+    6500   0.37564106 6.0949329e-05    1947.6558    3917.8967 
+    6600   0.38173599 6.0949329e-05    1947.6558    3917.8967 
+    6700   0.38783092 6.0949329e-05    1947.6558    3917.8967 
+    6800   0.39392586 6.0949329e-05    1947.6558    3917.8967 
+    6900   0.40002079 6.0949329e-05    1947.6558    3917.8967 
+    7000   0.40611572 6.0949329e-05    1947.6558    3917.8967 
+    7100   0.41221066 6.0949329e-05    1947.6558    3917.8967 
+    7200   0.41830559 6.0949329e-05    1947.6558    3917.8967 
+    7300   0.42440052 6.0949329e-05    1947.6558    3917.8967 
+    7400   0.43049545 6.0949329e-05    1947.6558    3917.8967 
+    7500   0.43659039 6.0949329e-05    1947.6558    3917.8967 
+    7600   0.44268532 6.0949329e-05    1947.6558    3917.8967 
+    7700   0.44878025 6.0949329e-05    1947.6558    3917.8967 
+    7800   0.45487519 6.0949329e-05    1947.6558    3917.8967 
+    7900   0.46097012 6.0949329e-05    1947.6558    3917.8967 
+    8000   0.46706505 6.0949329e-05    1947.6558    3917.8967 
+    8100   0.47315998 6.0949329e-05    1947.6558    3917.8967 
+    8200   0.47925492 6.0949329e-05    1947.6558    3917.8967 
+    8300   0.48534985 6.0949329e-05    1947.6558    3917.8967 
+    8400   0.49144478 6.0949329e-05    1947.6558    3917.8967 
+    8500   0.49753972 6.0949329e-05    1947.6558    3917.8967 
+    8600   0.50363465 6.0949329e-05    1947.6558    3917.8967 
+    8700   0.50972958 6.0949329e-05    1947.6558    3917.8967 
+    8800   0.51582452 6.0949329e-05    1947.6558    3917.8967 
+    8900   0.52191945 6.0949329e-05    1947.6558    3917.8967 
+    9000   0.52801438 6.0949329e-05    1947.6558    3917.8967 
+    9100   0.53410931 6.0949329e-05    1947.6558    3917.8967 
+    9200   0.54020425 6.0949329e-05    1947.6558    3917.8967 
+    9300   0.54629918 6.0949329e-05    1947.6558    3917.8967 
+    9400   0.55239411 6.0949329e-05    1947.6558    3917.8967 
+    9500   0.55848905 6.0949329e-05    1947.6558    3917.8967 
+    9600   0.56458398 6.0949329e-05    1947.6558    3917.8967 
+    9700   0.57067891 6.0949329e-05    1947.6558    3917.8967 
+    9800   0.57677384 6.0949329e-05    1947.6558    3917.8967 
+    9900   0.58286878 6.0949329e-05    1947.6558    3917.8967 
+   10000   0.58896371 6.0949329e-05    1947.6558    3917.8967 
+Loop time of 1.25184 on 1 procs for 10000 steps with 1 atoms
+
+Performance: 42.066 ns/day, 0.571 hours/ns, 7988.216 timesteps/s
+99.7% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.0005827  | 0.0005827  | 0.0005827  |   0.0 |  0.05
+Neigh   | 1.2134     | 1.2134     | 1.2134     |   0.0 | 96.93
+Comm    | 0.02822    | 0.02822    | 0.02822    |   0.0 |  2.25
+Output  | 0.0017159  | 0.0017159  | 0.0017159  |   0.0 |  0.14
+Modify  | 0.0052147  | 0.0052147  | 0.0052147  |   0.0 |  0.42
+Other   |            | 0.002664   |            |       |  0.21
+
+Nlocal:    1 ave 1 max 1 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    0 ave 0 max 0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    0 ave 0 max 0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+FullNghs:  0 ave 0 max 0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 0
+Ave neighs/atom = 0
+Neighbor list builds = 960
+Dangerous builds = 568
+Total wall time: 0:00:01
diff --git a/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.4 b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.4
new file mode 100644
index 0000000000..e8bd45b20f
--- /dev/null
+++ b/examples/USER/misc/electron_stopping/log.20Mar19.elstop.only.g++.4
@@ -0,0 +1,196 @@
+LAMMPS (28 Feb 2019)
+OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:88)
+  using 1 OpenMP thread(s) per MPI task
+# Test case / example for fix electron/stopping
+# One fast atom, no other interactions.
+# Stopping only applied in a smaller box in the middle.
+#
+# Also uses fix dt/reset, as one should when energies are high
+# enough to require electronic stopping.
+
+units metal
+boundary p p p
+timestep 0.0001
+
+lattice fcc 1
+Lattice spacing in x,y,z = 1 1 1
+
+region rbox block -100 100 -100 100 -100 100
+region rsmallbox block -90 90 -90 90 -90 90
+
+create_box 1 rbox
+Created orthogonal box = (-100 -100 -100) to (100 100 100)
+  1 by 2 by 2 MPI processor grid
+
+mass 1 28.0855
+
+create_atoms 1 single 0 0 0
+Created 1 atoms
+  create_atoms CPU = 1.19209e-05 secs
+velocity all set 1120 1620 389
+
+pair_style zero 1
+pair_coeff * * 1
+
+fix fdt all dt/reset 1 NULL 0.001 0.1 emax 20.0
+fix fel all electron/stopping 1.0 Si.Si.elstop minneigh 0 region rsmallbox
+fix fnve all nve
+
+compute ek all ke/atom
+compute ektot all reduce sum c_ek
+
+thermo 100
+thermo_style custom step time dt f_fel c_ektot
+
+#dump mydump all custom 200 elstop.only.dump id x y z vx vy vz fx fy fz c_ek
+
+run 10000
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 3
+  ghost atom cutoff = 3
+  binsize = 1.5, bins = 134 134 134
+  2 neighbor lists, perpetual/occasional/extra = 1 1 0
+  (1) pair zero, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+  (2) fix electron/stopping, occasional
+      attributes: full, newton on
+      pair build: full/bin/atomonly
+      stencil: full/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.637 | 4.2 | 5.887 Mbytes
+Step Time Dt f_fel c_ektot 
+       0            0  4.98128e-05            0    5865.5525 
+     100 0.0049972222 5.0137252e-05    76.048699     5789.883 
+     200  0.010027278 5.0467945e-05    151.67477    5714.2548 
+     300  0.015090636 5.0803375e-05     226.8806    5639.0469 
+     400  0.020187777 5.1143663e-05     301.6685    5564.2569 
+     500  0.025319192 5.1488933e-05    376.04082    5489.8825 
+     600  0.030485386 5.1839314e-05    449.99984    5415.9215 
+     700  0.035686876 5.2194938e-05    523.54788    5342.3714 
+     800  0.040924195 5.2555944e-05    596.68721      5269.23 
+     900  0.046197886 5.2922477e-05    669.42011    5196.4951 
+    1000   0.05150851 5.3294685e-05    741.74883    5124.1643 
+    1100  0.056856642 5.3672723e-05    813.67563    5052.2355 
+    1200  0.062229338 5.3731851e-05    824.43012    5041.1224 
+    1300  0.067602524 5.3731851e-05    824.43012    5041.1224 
+    1400  0.072978188 5.387166e-05    850.91948    5014.9907 
+    1500   0.07838447 5.425887e-05    922.23961    4943.6685 
+    1600   0.08382978 5.4652329e-05    993.16341    4872.7428 
+    1700  0.089299984 5.4705935e-05    1002.3545     4863.198 
+    1800  0.094770578 5.4705935e-05    1002.3545     4863.198 
+    1900   0.10024117 5.4705935e-05    1002.3545     4863.198 
+    2000   0.10571333 5.4819488e-05    1022.8338    4843.0716 
+    2100   0.11121515 5.5222127e-05    1093.1986    4772.7048 
+    2200   0.11675757 5.5631458e-05    1163.1724    4702.7291 
+    2300   0.12234126 5.6047675e-05    1232.7573    4633.1422 
+    2400   0.12796692 5.6470985e-05    1301.9555     4563.942 
+    2500   0.13363527 5.6901598e-05    1370.7692    4495.1264 
+    2600   0.13934706 5.7339739e-05    1439.2006    4426.6932 
+    2700   0.14510304 5.7785637e-05    1507.2516    4358.6403 
+    2800     0.150904 5.8239536e-05    1574.9245    4290.9655 
+    2900   0.15675076 5.8701688e-05    1642.2213    4223.6668 
+    3000   0.16264416 5.9172358e-05    1709.1441    4156.7422 
+    3100   0.16858505 5.9651822e-05     1775.695    4090.1894 
+    3200   0.17457434 6.0140369e-05    1841.8761    4024.0064 
+    3300   0.18061294 6.0638302e-05    1907.6894    3958.1913 
+    3400   0.18669814 6.0949329e-05    1947.6558    3917.8967 
+    3500   0.19279307 6.0949329e-05    1947.6558    3917.8967 
+    3600     0.198888 6.0949329e-05    1947.6558    3917.8967 
+    3700   0.20498294 6.0949329e-05    1947.6558    3917.8967 
+    3800   0.21107787 6.0949329e-05    1947.6558    3917.8967 
+    3900    0.2171728 6.0949329e-05    1947.6558    3917.8967 
+    4000   0.22326773 6.0949329e-05    1947.6558    3917.8967 
+    4100   0.22936267 6.0949329e-05    1947.6558    3917.8967 
+    4200    0.2354576 6.0949329e-05    1947.6558    3917.8967 
+    4300   0.24155253 6.0949329e-05    1947.6558    3917.8967 
+    4400   0.24764747 6.0949329e-05    1947.6558    3917.8967 
+    4500    0.2537424 6.0949329e-05    1947.6558    3917.8967 
+    4600   0.25983733 6.0949329e-05    1947.6558    3917.8967 
+    4700   0.26593227 6.0949329e-05    1947.6558    3917.8967 
+    4800    0.2720272 6.0949329e-05    1947.6558    3917.8967 
+    4900   0.27812213 6.0949329e-05    1947.6558    3917.8967 
+    5000   0.28421706 6.0949329e-05    1947.6558    3917.8967 
+    5100     0.290312 6.0949329e-05    1947.6558    3917.8967 
+    5200   0.29640693 6.0949329e-05    1947.6558    3917.8967 
+    5300   0.30250186 6.0949329e-05    1947.6558    3917.8967 
+    5400    0.3085968 6.0949329e-05    1947.6558    3917.8967 
+    5500   0.31469173 6.0949329e-05    1947.6558    3917.8967 
+    5600   0.32078666 6.0949329e-05    1947.6558    3917.8967 
+    5700   0.32688159 6.0949329e-05    1947.6558    3917.8967 
+    5800   0.33297653 6.0949329e-05    1947.6558    3917.8967 
+    5900   0.33907146 6.0949329e-05    1947.6558    3917.8967 
+    6000   0.34516639 6.0949329e-05    1947.6558    3917.8967 
+    6100   0.35126133 6.0949329e-05    1947.6558    3917.8967 
+    6200   0.35735626 6.0949329e-05    1947.6558    3917.8967 
+    6300   0.36345119 6.0949329e-05    1947.6558    3917.8967 
+    6400   0.36954612 6.0949329e-05    1947.6558    3917.8967 
+    6500   0.37564106 6.0949329e-05    1947.6558    3917.8967 
+    6600   0.38173599 6.0949329e-05    1947.6558    3917.8967 
+    6700   0.38783092 6.0949329e-05    1947.6558    3917.8967 
+    6800   0.39392586 6.0949329e-05    1947.6558    3917.8967 
+    6900   0.40002079 6.0949329e-05    1947.6558    3917.8967 
+    7000   0.40611572 6.0949329e-05    1947.6558    3917.8967 
+    7100   0.41221066 6.0949329e-05    1947.6558    3917.8967 
+    7200   0.41830559 6.0949329e-05    1947.6558    3917.8967 
+    7300   0.42440052 6.0949329e-05    1947.6558    3917.8967 
+    7400   0.43049545 6.0949329e-05    1947.6558    3917.8967 
+    7500   0.43659039 6.0949329e-05    1947.6558    3917.8967 
+    7600   0.44268532 6.0949329e-05    1947.6558    3917.8967 
+    7700   0.44878025 6.0949329e-05    1947.6558    3917.8967 
+    7800   0.45487519 6.0949329e-05    1947.6558    3917.8967 
+    7900   0.46097012 6.0949329e-05    1947.6558    3917.8967 
+    8000   0.46706505 6.0949329e-05    1947.6558    3917.8967 
+    8100   0.47315998 6.0949329e-05    1947.6558    3917.8967 
+    8200   0.47925492 6.0949329e-05    1947.6558    3917.8967 
+    8300   0.48534985 6.0949329e-05    1947.6558    3917.8967 
+    8400   0.49144478 6.0949329e-05    1947.6558    3917.8967 
+    8500   0.49753972 6.0949329e-05    1947.6558    3917.8967 
+    8600   0.50363465 6.0949329e-05    1947.6558    3917.8967 
+    8700   0.50972958 6.0949329e-05    1947.6558    3917.8967 
+    8800   0.51582452 6.0949329e-05    1947.6558    3917.8967 
+    8900   0.52191945 6.0949329e-05    1947.6558    3917.8967 
+    9000   0.52801438 6.0949329e-05    1947.6558    3917.8967 
+    9100   0.53410931 6.0949329e-05    1947.6558    3917.8967 
+    9200   0.54020425 6.0949329e-05    1947.6558    3917.8967 
+    9300   0.54629918 6.0949329e-05    1947.6558    3917.8967 
+    9400   0.55239411 6.0949329e-05    1947.6558    3917.8967 
+    9500   0.55848905 6.0949329e-05    1947.6558    3917.8967 
+    9600   0.56458398 6.0949329e-05    1947.6558    3917.8967 
+    9700   0.57067891 6.0949329e-05    1947.6558    3917.8967 
+    9800   0.57677384 6.0949329e-05    1947.6558    3917.8967 
+    9900   0.58286878 6.0949329e-05    1947.6558    3917.8967 
+   10000   0.58896371 6.0949329e-05    1947.6558    3917.8967 
+Loop time of 1.38891 on 4 procs for 10000 steps with 1 atoms
+
+Performance: 37.915 ns/day, 0.633 hours/ns, 7199.876 timesteps/s
+94.0% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.0004971  | 0.00060463 | 0.00069618 |   0.0 |  0.04
+Neigh   | 1.1005     | 1.1507     | 1.2839     |   7.2 | 82.85
+Comm    | 0.025918   | 0.026382   | 0.027041   |   0.3 |  1.90
+Output  | 0.0016336  | 0.005001   | 0.01507    |   8.2 |  0.36
+Modify  | 0.059378   | 0.20196    | 0.25453    |  18.3 | 14.54
+Other   |            | 0.00422    |            |       |  0.30
+
+Nlocal:    0.25 ave 1 max 0 min
+Histogram: 3 0 0 0 0 0 0 0 0 1
+Nghost:    0 ave 0 max 0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs:    0 ave 0 max 0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+FullNghs:  0 ave 0 max 0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 0
+Ave neighs/atom = 0
+Neighbor list builds = 960
+Dangerous builds = 568
+Total wall time: 0:00:01
diff --git a/examples/hyper/global.000000.jpg b/examples/hyper/global.000000.jpg
new file mode 100644
index 0000000000..3064ece7f1
Binary files /dev/null and b/examples/hyper/global.000000.jpg differ
diff --git a/examples/hyper/global.041000.jpg b/examples/hyper/global.041000.jpg
new file mode 100644
index 0000000000..1f5253865e
Binary files /dev/null and b/examples/hyper/global.041000.jpg differ
diff --git a/examples/hyper/global.045000.jpg b/examples/hyper/global.045000.jpg
new file mode 100644
index 0000000000..fb545052cb
Binary files /dev/null and b/examples/hyper/global.045000.jpg differ
diff --git a/examples/hyper/global.048000.jpg b/examples/hyper/global.048000.jpg
new file mode 100644
index 0000000000..506ea4a4bb
Binary files /dev/null and b/examples/hyper/global.048000.jpg differ
diff --git a/examples/hyper/global.089000.jpg b/examples/hyper/global.089000.jpg
new file mode 100644
index 0000000000..094e8b5328
Binary files /dev/null and b/examples/hyper/global.089000.jpg differ
diff --git a/examples/hyper/global.10Oct18.000000.jpg b/examples/hyper/global.10Oct18.000000.jpg
deleted file mode 100644
index b462983f6a..0000000000
Binary files a/examples/hyper/global.10Oct18.000000.jpg and /dev/null differ
diff --git a/examples/hyper/global.10Oct18.003000.jpg b/examples/hyper/global.10Oct18.003000.jpg
deleted file mode 100644
index ef28d78d78..0000000000
Binary files a/examples/hyper/global.10Oct18.003000.jpg and /dev/null differ
diff --git a/examples/hyper/global.10Oct18.038000.jpg b/examples/hyper/global.10Oct18.038000.jpg
deleted file mode 100644
index 444531312b..0000000000
Binary files a/examples/hyper/global.10Oct18.038000.jpg and /dev/null differ
diff --git a/examples/hyper/global.10Oct18.059000.jpg b/examples/hyper/global.10Oct18.059000.jpg
deleted file mode 100644
index b77a9e3454..0000000000
Binary files a/examples/hyper/global.10Oct18.059000.jpg and /dev/null differ
diff --git a/examples/hyper/in.hyper.global b/examples/hyper/in.hyper.global
index 22b3b4251b..eba5c7bf89 100644
--- a/examples/hyper/in.hyper.global
+++ b/examples/hyper/in.hyper.global
@@ -12,6 +12,8 @@ variable        cutevent index 1.1
 variable        steps index 100000
 variable        nevent index 1000
 variable        zoom index 1.8
+variable        seed index 826626413
+variable        tol index 1.0e-15
 
 units           metal
 atom_style	atomic
@@ -45,7 +47,7 @@ neighbor	0.5 bin
 neigh_modify    every 1 delay 5 check yes
 
 fix		1 mobile nve
-fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 858872873 zero yes
+fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 ${seed} zero yes
 
 timestep	0.005
 
@@ -92,4 +94,4 @@ dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
 
 # run
 
-hyper           ${steps} ${nevent} HG event min 1.0e-6 1.0e-6 100 100 dump 1
+hyper           ${steps} ${nevent} HG event min ${tol} ${tol} 1000 1000 dump 1
diff --git a/examples/hyper/in.hyper.local b/examples/hyper/in.hyper.local
index ef8ed4d042..cdf478ac38 100644
--- a/examples/hyper/in.hyper.local
+++ b/examples/hyper/in.hyper.local
@@ -107,6 +107,12 @@ dump		1 all image 10000000 local.*.jpg v_acolor type size 1024 1024 &
 		zoom ${zoom} adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
 dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
 
+# test of histogramming and dump output of bias coeffs
+
+#fix            histo all ave/histo 10 100 1000 0.9 1.1 100 f_HL &
+#               mode vector kind local file tmp.histo
+#dump           2 all local 1000 tmp.local f_HL
+
 # run
 
 hyper           ${steps} ${nevent} HL event min ${tol} ${tol} 1000 1000 dump 1
diff --git a/examples/hyper/local.10Oct18.000000.jpg b/examples/hyper/local.000000.jpg
similarity index 100%
rename from examples/hyper/local.10Oct18.000000.jpg
rename to examples/hyper/local.000000.jpg
diff --git a/examples/hyper/local.001200.jpg b/examples/hyper/local.001200.jpg
new file mode 100644
index 0000000000..36bc9cd7bc
Binary files /dev/null and b/examples/hyper/local.001200.jpg differ
diff --git a/examples/hyper/local.10Oct18.000700.jpg b/examples/hyper/local.10Oct18.000700.jpg
deleted file mode 100644
index e1e61dd6aa..0000000000
Binary files a/examples/hyper/local.10Oct18.000700.jpg and /dev/null differ
diff --git a/examples/hyper/local.10Oct18.000800.jpg b/examples/hyper/local.10Oct18.000800.jpg
deleted file mode 100644
index a1e2fbc66a..0000000000
Binary files a/examples/hyper/local.10Oct18.000800.jpg and /dev/null differ
diff --git a/examples/hyper/local.10Oct18.001100.jpg b/examples/hyper/local.10Oct18.001100.jpg
deleted file mode 100644
index dea7fd4eaf..0000000000
Binary files a/examples/hyper/local.10Oct18.001100.jpg and /dev/null differ
diff --git a/examples/hyper/log.10Oct18.hyper.global.g++.4 b/examples/hyper/log.10Oct18.hyper.global.g++.4
deleted file mode 100644
index de08541583..0000000000
--- a/examples/hyper/log.10Oct18.hyper.global.g++.4
+++ /dev/null
@@ -1,1243 +0,0 @@
-LAMMPS (10 Oct 2018)
-# 3d EAM surface for global HD
-
-# nearest neighbor distance = a * sqrt(2)/2 = 2.77 Angs for Pt with a = 3.92
-# hop event on (100) surface is same distance
-# exchange event is 2 atoms moving same distance
-
-variable        Tequil index 500.0
-variable        Vmax index 0.5
-variable        qfactor index 0.3
-variable        cutbond index 3.2
-variable        cutevent index 1.1
-variable        steps index 100000
-variable        nevent index 1000
-variable        zoom index 1.8
-
-units           metal
-atom_style	atomic
-atom_modify     map array
-boundary        p p p
-
-lattice		fcc 3.92
-Lattice spacing in x,y,z = 3.92 3.92 3.92
-region		box block 0 6 0 6 0 4
-create_box	3 box
-Created orthogonal box = (0 0 0) to (23.52 23.52 15.68)
-  2 by 2 by 1 MPI processor grid
-create_atoms	1 box
-Created 576 atoms
-  Time spent = 0.000782013 secs
-
-mass            * 1.0
-
-change_box      all z final -0.1 5.0 boundary p p f
-  orthogonal box = (0 0 -0.392) to (23.52 23.52 19.6)
-create_atoms    2 single 3.5 3.5 4
-Created 1 atoms
-  Time spent = 4.69685e-05 secs
-
-# define frozen substrate and mobile atoms
-
-group           adatom type 2
-1 atoms in group adatom
-region          base block INF INF INF INF 0 1.8
-set             region base type 3
-  288 settings made for type
-group           base type 3
-288 atoms in group base
-group           mobile type 1 2
-289 atoms in group mobile
-
-# pair style
-
-pair_style	eam/alloy
-pair_coeff	* * ptvoterlammps.eam Pt Pt Pt
-
-neighbor	0.5 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 mobile nve
-fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 858872873 zero yes
-fix		2 mobile langevin 500.0 ${Tequil} 1.0 858872873 zero yes
-fix		2 mobile langevin 500.0 500.0 1.0 858872873 zero yes
-
-timestep	0.005
-
-compute         tmobile mobile temp
-
-thermo		100
-thermo_modify   temp tmobile
-WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:488)
-
-# thermal equilibration
-
-run             1000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.07583
-  ghost atom cutoff = 6.07583
-  binsize = 3.03792, bins = 8 8 7
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair eam/alloy, perpetual
-      attributes: half, newton on
-      pair build: half/bin/atomonly/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.327 | 3.327 | 3.327 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0            0   -3213.9136            0   -3213.9136   -51843.125 
-     100    211.06271   -3209.3285            0   -3201.4713   -27323.825 
-     200    320.80707   -3205.3715            0   -3193.4289   -39370.402 
-     300    393.66139    -3202.607            0   -3187.9522   -32163.403 
-     400    401.11987   -3200.2795            0    -3185.347   -35961.543 
-     500    472.27798   -3200.7267            0   -3183.1452   -33044.974 
-     600    485.16253    -3199.818            0   -3181.7569   -34242.615 
-     700    464.85129    -3199.865            0     -3182.56   -35327.179 
-     800    518.91236   -3199.4098            0   -3180.0923     -32088.2 
-     900    502.76061   -3199.3972            0    -3180.681   -36944.263 
-    1000    522.64479   -3200.0627            0   -3180.6063   -32801.856 
-Loop time of 0.333434 on 4 procs for 1000 steps with 577 atoms
-
-Performance: 1295.607 ns/day, 0.019 hours/ns, 2999.091 timesteps/s
-99.5% CPU use with 4 MPI tasks x no OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 0.25639    | 0.2636     | 0.2708     |   1.0 | 79.06
-Neigh   | 0.017381   | 0.017991   | 0.018988   |   0.4 |  5.40
-Comm    | 0.026086   | 0.034315   | 0.042505   |   3.2 | 10.29
-Output  | 0.00022078 | 0.00023323 | 0.00026107 |   0.0 |  0.07
-Modify  | 0.013295   | 0.013709   | 0.014107   |   0.2 |  4.11
-Other   |            | 0.003584   |            |       |  1.07
-
-Nlocal:    144.25 ave 149 max 139 min
-Histogram: 1 0 0 1 0 0 0 0 1 1
-Nghost:    530.5 ave 536 max 526 min
-Histogram: 1 1 0 0 0 0 0 1 0 1
-Neighs:    3471.75 ave 3626 max 3292 min
-Histogram: 1 0 0 0 1 0 1 0 0 1
-
-Total # of neighbors = 13887
-Ave neighs/atom = 24.0676
-Neighbor list builds = 88
-Dangerous builds = 0
-reset_timestep  0
-
-# pin base so will not move during quenches
-
-fix             freeze base setforce 0.0 0.0 0.0
-
-# event detection
-
-compute         event all event/displace ${cutevent}
-compute         event all event/displace 1.1
-
-# hyper/global
-
-fix             HG mobile hyper/global ${cutbond} ${qfactor} ${Vmax} ${Tequil}
-fix             HG mobile hyper/global 3.2 ${qfactor} ${Vmax} ${Tequil}
-fix             HG mobile hyper/global 3.2 0.3 ${Vmax} ${Tequil}
-fix             HG mobile hyper/global 3.2 0.3 0.5 ${Tequil}
-fix             HG mobile hyper/global 3.2 0.3 0.5 500.0
-
-# thermo output
-
-thermo_style    custom step temp pe f_HG f_HG[*]
-WARNING: New thermo_style command, previous thermo_modify settings will be lost (../output.cpp:705)
-
-thermo_modify   lost ignore
-thermo_modify   temp tmobile
-WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:488)
-
-thermo          ${nevent}
-thermo          1000
-
-# dump output options
-
-region          substrate block INF INF INF INF 1.8 3.8
-region          adatoms block INF INF INF INF 3.8 INF
-variable        acolor atom rmask(base)+2*rmask(substrate)+3*rmask(adatoms)
-
-dump		1 all image 1000000 global.*.jpg v_acolor type 		zoom ${zoom} adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
-dump		1 all image 1000000 global.*.jpg v_acolor type 		zoom 1.8 adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
-dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
-
-# run
-
-hyper           ${steps} ${nevent} HG event min 1.0e-6 1.0e-6 100 100 dump 1
-hyper           100000 ${nevent} HG event min 1.0e-6 1.0e-6 100 100 dump 1
-hyper           100000 1000 HG event min 1.0e-6 1.0e-6 100 100 dump 1
-WARNING: Resetting reneighboring criteria during hyper (../hyper.cpp:133)
-Neighbor list info ...
-  update every 1 steps, delay 0 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.07583
-  ghost atom cutoff = 6.07583
-  binsize = 3.03792, bins = 8 8 7
-  2 neighbor lists, perpetual/occasional/extra = 1 1 0
-  (1) pair eam/alloy, perpetual
-      attributes: half, newton on
-      pair build: half/bin/atomonly/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-  (2) fix hyper/global, occasional, copy from (1)
-      attributes: half, newton on
-      pair build: copy
-      stencil: none
-      bin: none
-Per MPI rank memory allocation (min/avg/max) = 6.015 | 6.015 | 6.015 Mbytes
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-       0    522.64479   -3200.0627            0            0            0            0            0            0            0            0            0            0            0            0 
-      13    522.64479   -3217.9151            0            0            0            0            0            0            0            0            0            0            0            0 
-Loop time of 0.0106812 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-       0    522.64479   -3200.0627   0.39402008    9365.7631   0.13811729          429          426    6.0069324            0   0.36151295    3.1652084            0            0            0 
-    1000    512.35059   -3198.5556   0.32845525    2044.9347   0.17572153          257          259    6.0069324        0.137   0.77425934    3.8913771    5302.7599            0            0 
-Loop time of 0.314234 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    1000    512.35059   -3198.5556   0.32845525    2044.9347   0.17572153          257          259    6.0069324        0.137   0.77425934    3.8913771    5302.7599            0            0 
-    1014    512.35059   -3217.9161   0.32845525    2044.9347   0.17572153          257          259    6.0069324   0.13510848   0.77425934    3.8913771    5302.7599            0            0 
-Loop time of 0.0071606 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    1000    512.35059   -3198.5556   0.32845525    2044.9347   0.17572153          257          259    6.0069324        0.137   0.77425934    3.8913771    5302.7599            0            0 
-    2000    502.60215   -3197.7892   0.01351505    1.3684394   0.29591771          116          127    6.0069324        0.103   0.77425934    3.8913771    11603.458            0            0 
-Loop time of 0.33185 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    2000    502.60215   -3197.7892   0.01351505    1.3684394   0.29591771          116          127    6.0069324        0.103   0.77425934    3.8913771    11603.458            0            0 
-    2015    502.60215   -3217.9155   0.01351505    1.3684394   0.29591771          116          127    6.0069324   0.10223325   0.77425934    3.8913771    11603.458            0            0 
-Loop time of 0.00889879 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    2000    502.60215   -3197.7892   0.01351505    1.3684394   0.29591771          116          127    6.0069324        0.103   0.77425934    3.8913771    11603.458            0            0 
-    3000    481.01481   -3199.1324            0            1    1.0289113          542          544    6.0069324        0.212    2.8308749    5.5814852    12488.613            0            0 
-Loop time of 0.334598 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    3000    481.01481   -3199.1324            0            1    1.0289113          542          544    6.0069324        0.212    2.8308749    5.5814852    12488.613            0            0 
-    3014    481.01481    -3217.916            0            1    1.0289113          542          544    6.0069324   0.21101526    2.8308749    5.5814852    12488.613            0            0 
-Loop time of 0.0103227 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    3000    481.01481   -3199.1324   0.25134819    341.56656   0.21155927          277          539    6.0069324        0.212    2.8308749    5.5814852    12488.613            1            2 
-    4000    474.51721   -3197.9082   0.26384891    456.53799   0.20617274          361           83    6.0069324      0.18325    2.8308749    5.5814852     22776.39            1            2 
-Loop time of 0.302547 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    4000    474.51721   -3197.9082   0.26384891    456.53799   0.20617274          361           83    6.0069324      0.18325    2.8308749    5.5814852     22776.39            1            2 
-    4014    474.51721   -3217.9172   0.26384891    456.53799   0.20617274          361           83    6.0069324   0.18261086    2.8308749    5.5814852     22776.39            1            2 
-Loop time of 0.00868511 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    4000    474.51721   -3197.9082   0.26384891    456.53799   0.20617274          361           83    6.0069324      0.18325    2.8308749    5.5814852     22776.39            1            2 
-    5000    478.08772   -3199.6792  0.043886568    2.7692147    0.2865317          275          577    6.0069324       0.1586    2.8308749    5.5814852    35085.309            1            2 
-Loop time of 0.300419 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    5000    478.08772   -3199.6792  0.043886568    2.7692147    0.2865317          275          577    6.0069324       0.1586    2.8308749    5.5814852    35085.309            1            2 
-    5015    478.08772   -3217.9131  0.043886568    2.7692147    0.2865317          275          577    6.0069324   0.15812562    2.8308749    5.5814852    35085.309            1            2 
-Loop time of 0.00705171 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    5000    478.08772   -3199.6792  0.043886568    2.7692147    0.2865317          275          577    6.0069324       0.1586    2.8308749    5.5814852    35085.309            1            2 
-    6000    458.77612   -3197.8588   0.27710376    620.98321   0.20030308          511          546    6.0069324        0.171    2.8308749    5.5814852    38747.284            1            2 
-Loop time of 0.287999 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    6000    458.77612   -3197.8588   0.27710376    620.98321   0.20030308          511          546    6.0069324        0.171    2.8308749    5.5814852    38747.284            1            2 
-    6015    458.77612   -3217.9165   0.27710376    620.98321   0.20030308          511          546    6.0069324   0.17057357    2.8308749    5.5814852    38747.284            1            2 
-Loop time of 0.00888014 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    6000    458.77612   -3197.8588   0.27710376    620.98321   0.20030308          511          546    6.0069324        0.171    2.8308749    5.5814852    38747.284            1            2 
-    7000    476.88452   -3198.3269    0.0828164    6.8352063   0.27403111          264          275    6.0069324   0.17714286    2.8308749    5.5814852    45612.389            1            2 
-Loop time of 0.29168 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    7000    476.88452   -3198.3269    0.0828164    6.8352063   0.27403111          264          275    6.0069324   0.17714286    2.8308749    5.5814852    45612.389            1            2 
-    7015    476.88452   -3217.9146    0.0828164    6.8352063   0.27403111          264          275    6.0069324   0.17676408    2.8308749    5.5814852    45612.389            1            2 
-Loop time of 0.00871038 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    7000    476.88452   -3198.3269    0.0828164    6.8352063   0.27403111          264          275    6.0069324   0.17714286    2.8308749    5.5814852    45612.389            1            2 
-    8000    521.60584   -3199.0138   0.22715857    194.82964   0.22161105          419          124    6.0069324     0.191875    2.8308749    5.5814852    46748.053            1            2 
-Loop time of 0.284021 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    8000    521.60584   -3199.0138   0.22715857    194.82964   0.22161105          419          124    6.0069324     0.191875    2.8308749    5.5814852    46748.053            1            2 
-    8015    521.60584   -3217.9163   0.22715857    194.82964   0.22161105          419          124    6.0069324   0.19151591    2.8308749    5.5814852    46748.053            1            2 
-Loop time of 0.00697637 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    8000    521.60584   -3199.0138   0.22715857    194.82964   0.22161105          419          124    6.0069324     0.191875    2.8308749    5.5814852    46748.053            1            2 
-    9000    496.87475   -3198.4928   0.13677449    23.912479   0.25569629          264          275    6.0069324   0.18388889    2.8308749    5.5814852    49596.596            1            2 
-Loop time of 0.238759 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    9000    496.87475   -3198.4928   0.13677449    23.912479   0.25569629          264          275    6.0069324   0.18388889    2.8308749    5.5814852    49596.596            1            2 
-    9014    496.87475   -3217.9149   0.13677449    23.912479   0.25569629          264          275    6.0069324   0.18360328    2.8308749    5.5814852    49596.596            1            2 
-Loop time of 0.00677681 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-    9000    496.87475   -3198.4928   0.13677449    23.912479   0.25569629          264          275    6.0069324   0.18388889    2.8308749    5.5814852    49596.596            1            2 
-   10000     478.6826   -3199.6673   0.37406677    5894.1727    0.1505589          127          132    6.0069324       0.1982    2.8308749    5.5814852    54170.476            1            2 
-Loop time of 0.23881 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   10000     478.6826   -3199.6673   0.37406677    5894.1727    0.1505589          127          132    6.0069324       0.1982    2.8308749    5.5814852    54170.476            1            2 
-   10013     478.6826   -3217.9144   0.37406677    5894.1727    0.1505589          127          132    6.0069324   0.19794267    2.8308749    5.5814852    54170.476            1            2 
-Loop time of 0.00627023 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   10000     478.6826   -3199.6673   0.37406677    5894.1727    0.1505589          127          132    6.0069324       0.1982    2.8308749    5.5814852    54170.476            1            2 
-   11000    518.40222   -3199.3332   0.34753231    3183.9595   0.16566286          383          418    6.0069324   0.18809091    2.8308749    5.5814852    58304.709            1            2 
-Loop time of 0.238288 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   11000    518.40222   -3199.3332   0.34753231    3183.9595   0.16566286          383          418    6.0069324   0.18809091    2.8308749    5.5814852    58304.709            1            2 
-   11013    518.40222    -3217.915   0.34753231    3183.9595   0.16566286          383          418    6.0069324   0.18786888    2.8308749    5.5814852    58304.709            1            2 
-Loop time of 0.00599569 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   11000    518.40222   -3199.3332   0.34753231    3183.9595   0.16566286          383          418    6.0069324   0.18809091    2.8308749    5.5814852    58304.709            1            2 
-   12000    552.07348   -3197.6675 0.0063435549    1.1586177   0.29809086          144          143    6.0069324   0.18016667    2.8308749    5.5814852    66990.451            1            2 
-Loop time of 0.23842 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   12000    552.07348   -3197.6675 0.0063435549    1.1586177   0.29809086          144          143    6.0069324   0.18016667    2.8308749    5.5814852    66990.451            1            2 
-   12013    552.07348   -3217.9165 0.0063435549    1.1586177   0.29809086          144          143    6.0069324    0.1799717    2.8308749    5.5814852    66990.451            1            2 
-Loop time of 0.00602174 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   12000    552.07348   -3197.6675 0.0063435549    1.1586177   0.29809086          144          143    6.0069324   0.18016667    2.8308749    5.5814852    66990.451            1            2 
-   13000    471.13412   -3198.1314   0.30918747    1307.5821   0.18532743          116          123    6.0069324   0.17338462    2.8308749    5.5814852    74345.114            1            2 
-Loop time of 0.237671 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   13000    471.13412   -3198.1314   0.30918747    1307.5821   0.18532743          116          123    6.0069324   0.17338462    2.8308749    5.5814852    74345.114            1            2 
-   13014    471.13412   -3217.9158   0.30918747    1307.5821   0.18532743          116          123    6.0069324   0.17319809    2.8308749    5.5814852    74345.114            1            2 
-Loop time of 0.00647223 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   13000    471.13412   -3198.1314   0.30918747    1307.5821   0.18532743          116          123    6.0069324   0.17338462    2.8308749    5.5814852    74345.114            1            2 
-   14000    470.81692   -3198.8871   0.10763953    12.160669   0.26575343          275          577    6.0069324   0.18235714    2.8308749    5.5814852    76252.748            1            2 
-Loop time of 0.238789 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   14000    470.81692   -3198.8871   0.10763953    12.160669   0.26575343          275          577    6.0069324   0.18235714    2.8308749    5.5814852    76252.748            1            2 
-   14015    470.81692   -3217.9147   0.10763953    12.160669   0.26575343          275          577    6.0069324   0.18216197    2.8308749    5.5814852    76252.748            1            2 
-Loop time of 0.00651169 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   14000    470.81692   -3198.8871   0.10763953    12.160669   0.26575343          275          577    6.0069324   0.18235714    2.8308749    5.5814852    76252.748            1            2 
-   15000     473.2435   -3199.0907   0.20712247    122.37713   0.22960391          569          570    6.0069324   0.18553333    2.8308749    5.5814852    81659.641            1            2 
-Loop time of 0.23755 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   15000     473.2435   -3199.0907   0.20712247    122.37713   0.22960391          569          570    6.0069324   0.18553333    2.8308749    5.5814852    81659.641            1            2 
-   15014     473.2435   -3217.9161   0.20712247    122.37713   0.22960391          569          570    6.0069324   0.18536033    2.8308749    5.5814852    81659.641            1            2 
-Loop time of 0.00644851 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   15000     473.2435   -3199.0907   0.20712247    122.37713   0.22960391          569          570    6.0069324   0.18553333    2.8308749    5.5814852    81659.641            1            2 
-   16000    504.33627   -3199.1713  0.036898146    2.3545967   0.28871843          264          275    6.0069324     0.199875    2.8308749    5.5814852    82224.366            1            2 
-Loop time of 0.240195 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   16000    504.33627   -3199.1713  0.036898146    2.3545967   0.28871843          264          275    6.0069324     0.199875    2.8308749    5.5814852    82224.366            1            2 
-   16015    504.33627   -3217.9137  0.036898146    2.3545967   0.28871843          264          275    6.0069324   0.19968779    2.8308749    5.5814852    82224.366            1            2 
-Loop time of 0.00684911 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   16000    504.33627   -3199.1713  0.036898146    2.3545967   0.28871843          264          275    6.0069324     0.199875    2.8308749    5.5814852    82224.366            1            2 
-   17000    497.60607    -3198.212 0.0067178767    1.1687272   0.29797782          264          275    6.0069324        0.217    2.8308749    5.5814852     82242.51            1            2 
-Loop time of 0.240567 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   17000    497.60607    -3198.212 0.0067178767    1.1687272   0.29797782          264          275    6.0069324        0.217    2.8308749    5.5814852     82242.51            1            2 
-   17016    497.60607   -3217.9161 0.0067178767    1.1687272   0.29797782          264          275    6.0069324   0.21679596    2.8308749    5.5814852     82242.51            1            2 
-Loop time of 0.00708336 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   17000    497.60607    -3198.212 0.0067178767    1.1687272   0.29797782          264          275    6.0069324        0.217    2.8308749    5.5814852     82242.51            1            2 
-   18000    523.92168    -3199.831   0.21046671    132.25396   0.22828927          264          275    6.0069324   0.22444444    2.8308749    5.5814852    82304.143            1            2 
-Loop time of 0.240636 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   18000    523.92168    -3199.831   0.21046671    132.25396   0.22828927          264          275    6.0069324   0.22444444    2.8308749    5.5814852    82304.143            1            2 
-   18014    523.92168   -3217.9153   0.21046671    132.25396   0.22828927          264          275    6.0069324   0.22427001    2.8308749    5.5814852    82304.143            1            2 
-Loop time of 0.00646216 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   18000    523.92168    -3199.831   0.21046671    132.25396   0.22828927          264          275    6.0069324   0.22444444    2.8308749    5.5814852    82304.143            1            2 
-   19000    538.76557   -3198.7203  0.036295998    2.3219194   0.28890608          397          400    6.0069324        0.228    2.8308749    5.5814852    83487.232            1            2 
-Loop time of 0.239259 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   19000    538.76557   -3198.7203  0.036295998    2.3219194   0.28890608          397          400    6.0069324        0.228    2.8308749    5.5814852    83487.232            1            2 
-   19014    538.76557   -3217.9141  0.036295998    2.3219194   0.28890608          397          400    6.0069324   0.22783212    2.8308749    5.5814852    83487.232            1            2 
-Loop time of 0.0061307 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   19000    538.76557   -3198.7203  0.036295998    2.3219194   0.28890608          397          400    6.0069324        0.228    2.8308749    5.5814852    83487.232            1            2 
-   20000     483.9598   -3198.1166   0.13750177    24.319538   0.25544017          400          131    6.0069324       0.2187    2.8308749    5.5814852    91177.618            1            2 
-Loop time of 0.241751 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   20000     483.9598   -3198.1166   0.13750177    24.319538   0.25544017          400          131    6.0069324       0.2187    2.8308749    5.5814852    91177.618            1            2 
-   20014     483.9598   -3217.9137   0.13750177    24.319538   0.25544017          400          131    6.0069324   0.21854702    2.8308749    5.5814852    91177.618            1            2 
-Loop time of 0.00646776 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   20000     483.9598   -3198.1166   0.13750177    24.319538   0.25544017          400          131    6.0069324       0.2187    2.8308749    5.5814852    91177.618            1            2 
-   21000    518.44073   -3199.7932   0.30241436    1117.3756   0.18858795          553          577    6.0069324   0.21271429    2.8308749    5.5814852     99740.17            1            2 
-Loop time of 0.239403 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   21000    518.44073   -3199.7932   0.30241436    1117.3756   0.18858795          553          577    6.0069324   0.21271429    2.8308749    5.5814852     99740.17            1            2 
-   21014    518.44073   -3217.9126   0.30241436    1117.3756   0.18858795          553          577    6.0069324   0.21257257    2.8308749    5.5814852     99740.17            1            2 
-Loop time of 0.00643963 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   21000    518.44073   -3199.7932   0.30241436    1117.3756   0.18858795          553          577    6.0069324   0.21271429    2.8308749    5.5814852     99740.17            1            2 
-   22000    518.95823   -3198.6693            0            1    0.4887755          262          263    6.0069324   0.22327273    2.8308749    5.5814852    103304.87            1            2 
-Loop time of 0.241227 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   22000    518.95823   -3198.6693            0            1    0.4887755          262          263    6.0069324   0.22327273    2.8308749    5.5814852    103304.87            1            2 
-   22033    518.95823    -3217.916            0            1    0.4887755          262          263    6.0069324   0.22293832    2.8308749    5.5814852    103304.87            1            2 
-Loop time of 0.015579 on 4 procs for 33 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   22000    518.95823   -3198.6693            0            1    0.4887755          262          263    6.0069324   0.22327273    2.8308749    5.5814852    103304.87            1            2 
-   23000    534.01428   -3197.6551   0.10264812    10.830446   0.26743848          136          431    6.0069324   0.22469565    2.8308749    5.5814852    108159.84            1            2 
-Loop time of 0.240257 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   23000    534.01428   -3197.6551   0.10264812    10.830446   0.26743848          136          431    6.0069324   0.22469565    2.8308749    5.5814852    108159.84            1            2 
-   23015    534.01428   -3217.9147   0.10264812    10.830446   0.26743848          136          431    6.0069324   0.22454921    2.8308749    5.5814852    108159.84            1            2 
-Loop time of 0.0067718 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   23000    534.01428   -3197.6551   0.10264812    10.830446   0.26743848          136          431    6.0069324   0.22469565    2.8308749    5.5814852    108159.84            1            2 
-   24000    502.61915   -3198.9796   0.22019457    165.75289   0.22442143          132          143    6.0069324   0.21883333    2.8308749    5.5814852    115124.63            1            2 
-Loop time of 0.241014 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   24000    502.61915   -3198.9796   0.22019457    165.75289   0.22442143          132          143    6.0069324   0.21883333    2.8308749    5.5814852    115124.63            1            2 
-   24014    502.61915   -3217.9149   0.22019457    165.75289   0.22442143          132          143    6.0069324   0.21870575    2.8308749    5.5814852    115124.63            1            2 
-Loop time of 0.006706 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   24000    502.61915   -3198.9796   0.22019457    165.75289   0.22442143          132          143    6.0069324   0.21883333    2.8308749    5.5814852    115124.63            1            2 
-   25000    510.27664   -3200.7431   0.34609419    3079.4414   0.16644232          120          119    6.0069324      0.21512    2.8308749    5.5814852    118042.99            1            2 
-Loop time of 0.239452 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   25000    510.27664   -3200.7431   0.34609419    3079.4414   0.16644232          120          119    6.0069324      0.21512    2.8308749    5.5814852    118042.99            1            2 
-   25013    510.27664   -3217.9127   0.34609419    3079.4414   0.16644232          120          119    6.0069324    0.2150082    2.8308749    5.5814852    118042.99            1            2 
-Loop time of 0.00622821 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   25000    510.27664   -3200.7431   0.34609419    3079.4414   0.16644232          120          119    6.0069324      0.21512    2.8308749    5.5814852    118042.99            1            2 
-   26000    511.79717   -3198.2999   0.19492582    92.206933   0.23433598          263          577    6.0069324   0.21273077    2.8308749    5.5814852    124902.88            1            2 
-Loop time of 0.271219 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   26000    511.79717   -3198.2999   0.19492582    92.206933   0.23433598          263          577    6.0069324   0.21273077    2.8308749    5.5814852    124902.88            1            2 
-   26015    511.79717   -3217.9147   0.19492582    92.206933   0.23433598          263          577    6.0069324   0.21260811    2.8308749    5.5814852    124902.88            1            2 
-Loop time of 0.0105773 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   26000    511.79717   -3198.2999   0.19492582    92.206933   0.23433598          263          577    6.0069324   0.21273077    2.8308749    5.5814852    124902.88            1            2 
-   27000    487.73368   -3197.4904   0.19560731     93.67693    0.2340741          401          572    6.0069324   0.20814815    2.8308749    5.5814852    130713.79            1            2 
-Loop time of 0.293879 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   27000    487.73368   -3197.4904   0.19560731     93.67693    0.2340741          401          572    6.0069324   0.20814815    2.8308749    5.5814852    130713.79            1            2 
-   27015    487.73368   -3217.9161   0.19560731     93.67693    0.2340741          401          572    6.0069324   0.20803257    2.8308749    5.5814852    130713.79            1            2 
-Loop time of 0.00895333 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   27000    487.73368   -3197.4904   0.19560731     93.67693    0.2340741          401          572    6.0069324   0.20814815    2.8308749    5.5814852    130713.79            1            2 
-   28000    468.95408   -3198.4177    0.3457758    3056.7694    0.1666144          549          515    6.0069324        0.204    2.8308749    5.5814852     135376.2            1            2 
-Loop time of 0.286141 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   28000    468.95408   -3198.4177    0.3457758    3056.7694    0.1666144          549          515    6.0069324        0.204    2.8308749    5.5814852     135376.2            1            2 
-   28014    468.95408   -3217.9167    0.3457758    3056.7694    0.1666144          549          515    6.0069324   0.20389805    2.8308749    5.5814852     135376.2            1            2 
-Loop time of 0.00648469 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   28000    468.95408   -3198.4177    0.3457758    3056.7694    0.1666144          549          515    6.0069324        0.204    2.8308749    5.5814852     135376.2            1            2 
-   29000    518.03534   -3198.1622  0.029706116    1.9926184   0.29095171          267          260    6.0069324   0.20031034    2.8308749    5.5814852    143604.35            1            2 
-Loop time of 0.24066 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   29000    518.03534   -3198.1622  0.029706116    1.9926184   0.29095171          267          260    6.0069324   0.20031034    2.8308749    5.5814852    143604.35            1            2 
-   29014    518.03534   -3217.9137  0.029706116    1.9926184   0.29095171          267          260    6.0069324   0.20021369    2.8308749    5.5814852    143604.35            1            2 
-Loop time of 0.0063417 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   29000    518.03534   -3198.1622  0.029706116    1.9926184   0.29095171          267          260    6.0069324   0.20031034    2.8308749    5.5814852    143604.35            1            2 
-   30000    535.78782   -3198.3125   0.33831746    2570.9054   0.17059559          122          124    6.0069324   0.19596667    2.8308749    5.5814852    150106.09            1            2 
-Loop time of 0.259515 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   30000    535.78782   -3198.3125   0.33831746    2570.9054   0.17059559          122          124    6.0069324   0.19596667    2.8308749    5.5814852    150106.09            1            2 
-   30014    535.78782   -3217.9119   0.33831746    2570.9054   0.17059559          122          124    6.0069324   0.19587526    2.8308749    5.5814852    150106.09            1            2 
-Loop time of 0.0123347 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   30000    535.78782   -3198.3125   0.33831746    2570.9054   0.17059559          122          124    6.0069324   0.19596667    2.8308749    5.5814852    150106.09            1            2 
-   31000    547.06872   -3198.3217   0.21707776    154.18603   0.22566791          275          577    6.0069324   0.19987097    2.8308749    5.5814852    151076.53            1            2 
-Loop time of 0.321976 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   31000    547.06872   -3198.3217   0.21707776    154.18603   0.22566791          275          577    6.0069324   0.19987097    2.8308749    5.5814852    151076.53            1            2 
-   31014    547.06872   -3217.9165   0.21707776    154.18603   0.22566791          275          577    6.0069324   0.19978074    2.8308749    5.5814852    151076.53            1            2 
-Loop time of 0.00811768 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   31000    547.06872   -3198.3217   0.21707776    154.18603   0.22566791          275          577    6.0069324   0.19987097    2.8308749    5.5814852    151076.53            1            2 
-   32000    469.53603    -3199.325   0.35776457    4037.4217   0.16000743          563          268    6.0069324   0.20171875    2.8308749    5.5814852    152526.06            1            2 
-Loop time of 0.290834 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   32000    469.53603    -3199.325   0.35776457    4037.4217   0.16000743          563          268    6.0069324   0.20171875    2.8308749    5.5814852    152526.06            1            2 
-   32013    469.53603   -3217.9147   0.35776457    4037.4217   0.16000743          563          268    6.0069324   0.20163684    2.8308749    5.5814852    152526.06            1            2 
-Loop time of 0.00746775 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   32000    469.53603    -3199.325   0.35776457    4037.4217   0.16000743          563          268    6.0069324   0.20171875    2.8308749    5.5814852    152526.06            1            2 
-   33000    491.33889   -3199.1986   0.32620326    1940.7983   0.17687118          258          228    6.0069324   0.19833333    2.8308749    5.5814852    156385.66            1            2 
-Loop time of 0.243351 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   33000    491.33889   -3199.1986   0.32620326    1940.7983   0.17687118          258          228    6.0069324   0.19833333    2.8308749    5.5814852    156385.66            1            2 
-   33014    491.33889   -3217.9155   0.32620326    1940.7983   0.17687118          258          228    6.0069324   0.19824923    2.8308749    5.5814852    156385.66            1            2 
-Loop time of 0.00658584 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   33000    491.33889   -3199.1986   0.32620326    1940.7983   0.17687118          258          228    6.0069324   0.19833333    2.8308749    5.5814852    156385.66            1            2 
-   34000    503.19322   -3198.8767  0.050333006    3.2161315   0.28449966          275          577    6.0069324   0.19794118    2.8308749    5.5814852    161964.99            1            2 
-Loop time of 0.238415 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   34000    503.19322   -3198.8767  0.050333006    3.2161315   0.28449966          275          577    6.0069324   0.19794118    2.8308749    5.5814852    161964.99            1            2 
-   34016    503.19322   -3217.9158  0.050333006    3.2161315   0.28449966          275          577    6.0069324   0.19784807    2.8308749    5.5814852    161964.99            1            2 
-Loop time of 0.00771642 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   34000    503.19322   -3198.8767  0.050333006    3.2161315   0.28449966          275          577    6.0069324   0.19794118    2.8308749    5.5814852    161964.99            1            2 
-   35000    513.68037   -3197.8169   0.26004762    417.98593   0.20782548          264          275    6.0069324        0.199    2.8308749    5.5814852    164995.25            1            2 
-Loop time of 0.240164 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   35000    513.68037   -3197.8169   0.26004762    417.98593   0.20782548          264          275    6.0069324        0.199    2.8308749    5.5814852    164995.25            1            2 
-   35015    513.68037   -3217.9147   0.26004762    417.98593   0.20782548          264          275    6.0069324   0.19891475    2.8308749    5.5814852    164995.25            1            2 
-Loop time of 0.00711012 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   35000    513.68037   -3197.8169   0.26004762    417.98593   0.20782548          264          275    6.0069324        0.199    2.8308749    5.5814852    164995.25            1            2 
-   36000    508.23462   -3199.0337  0.009260286    1.2397653   0.29720893          563          564    6.0069324   0.20069444    2.8308749    5.5814852    167465.14            1            2 
-Loop time of 0.240289 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   36000    508.23462   -3199.0337  0.009260286    1.2397653   0.29720893          563          564    6.0069324   0.20069444    2.8308749    5.5814852    167465.14            1            2 
-   36014    508.23462   -3217.9163  0.009260286    1.2397653   0.29720893          563          564    6.0069324   0.20061643    2.8308749    5.5814852    167465.14            1            2 
-Loop time of 0.00642586 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   36000    508.23462   -3199.0337  0.009260286    1.2397653   0.29720893          563          564    6.0069324   0.20069444    2.8308749    5.5814852    167465.14            1            2 
-   37000    500.95069   -3199.7129  0.024475083     1.764809   0.29256535          275          577    6.0069324   0.19783784    2.8308749    5.5814852    169290.01            1            2 
-Loop time of 0.239462 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   37000    500.95069   -3199.7129  0.024475083     1.764809   0.29256535          275          577    6.0069324   0.19783784    2.8308749    5.5814852    169290.01            1            2 
-   37015    500.95069    -3217.916  0.024475083     1.764809   0.29256535          275          577    6.0069324   0.19775767    2.8308749    5.5814852    169290.01            1            2 
-Loop time of 0.00713468 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   37000    500.95069   -3199.7129  0.024475083     1.764809   0.29256535          275          577    6.0069324   0.19783784    2.8308749    5.5814852    169290.01            1            2 
-   38000    495.41803   -3199.6385            0            1    1.0152866          262          275    6.0069324   0.21794737    2.8308749    5.5814852     169297.9            1            2 
-Loop time of 0.239667 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   38000    495.41803   -3199.6385            0            1    1.0152866          262          275    6.0069324   0.21794737    2.8308749    5.5814852     169297.9            1            2 
-   38013    495.41803   -3217.9157            0            1    1.0152866          262          275    6.0069324   0.21787283    2.8308749    5.5814852     169297.9            1            2 
-Loop time of 0.00627661 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   38000    495.41803   -3199.6385   0.39298625    9143.7129   0.13878932          430          431    6.0069324   0.21794737    2.8308749    5.5814852     169297.9            2            4 
-   39000    469.05202   -3196.0515   0.10638057    11.810485   0.26617945          408          415    6.0069324   0.21410256    2.8308749    5.5814852    175842.05            2            4 
-Loop time of 0.238329 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   39000    469.05202   -3196.0515   0.10638057    11.810485   0.26617945          408          415    6.0069324   0.21410256    2.8308749    5.5814852    175842.05            2            4 
-   39015    469.05202    -3217.917   0.10638057    11.810485   0.26617945          408          415    6.0069324   0.21402025    2.8308749    5.5814852    175842.05            2            4 
-Loop time of 0.00683451 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   39000    469.05202   -3196.0515   0.10638057    11.810485   0.26617945          408          415    6.0069324   0.21410256    2.8308749    5.5814852    175842.05            2            4 
-   40000    542.78328   -3198.4918   0.18612218    75.166934    0.2376931          567          560    6.0069324     0.214275    2.8308749    5.5814852    179412.45            2            4 
-Loop time of 0.23954 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   40000    542.78328   -3198.4918   0.18612218    75.166934    0.2376931          567          560    6.0069324     0.214275    2.8308749    5.5814852    179412.45            2            4 
-   40014    542.78328   -3217.9148   0.18612218    75.166934    0.2376931          567          560    6.0069324   0.21420003    2.8308749    5.5814852    179412.45            2            4 
-Loop time of 0.00652599 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   40000    542.78328   -3198.4918   0.18612218    75.166934    0.2376931          567          560    6.0069324     0.214275    2.8308749    5.5814852    179412.45            2            4 
-   41000    548.99015   -3197.5893   0.30318345    1137.4995   0.18822056          124          135    6.0069324   0.21114634    2.8308749    5.5814852    184564.49            2            4 
-Loop time of 0.239863 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   41000    548.99015   -3197.5893   0.30318345    1137.4995   0.18822056          124          135    6.0069324   0.21114634    2.8308749    5.5814852    184564.49            2            4 
-   41014    548.99015   -3217.9174   0.30318345    1137.4995   0.18822056          124          135    6.0069324   0.21107427    2.8308749    5.5814852    184564.49            2            4 
-Loop time of 0.00668764 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   41000    548.99015   -3197.5893   0.30318345    1137.4995   0.18822056          124          135    6.0069324   0.21114634    2.8308749    5.5814852    184564.49            2            4 
-   42000     492.4929   -3198.0535   0.31406773    1464.4003   0.18294209          262          264    6.0069324   0.20954762    2.8308749    5.5814852    187620.86            2            4 
-Loop time of 0.238458 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   42000     492.4929   -3198.0535   0.31406773    1464.4003   0.18294209          262          264    6.0069324   0.20954762    2.8308749    5.5814852    187620.86            2            4 
-   42014     492.4929   -3217.9154   0.31406773    1464.4003   0.18294209          262          264    6.0069324   0.20947779    2.8308749    5.5814852    187620.86            2            4 
-Loop time of 0.00658375 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   42000     492.4929   -3198.0535   0.31406773    1464.4003   0.18294209          262          264    6.0069324   0.20954762    2.8308749    5.5814852    187620.86            2            4 
-   43000    524.32334   -3199.9723     0.171134    53.082676   0.24330204          287          276    6.0069324   0.20893023    2.8308749    5.5814852    189618.98            2            4 
-Loop time of 0.240476 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   43000    524.32334   -3199.9723     0.171134    53.082676   0.24330204          287          276    6.0069324   0.20893023    2.8308749    5.5814852    189618.98            2            4 
-   43015    524.32334   -3217.9151     0.171134    53.082676   0.24330204          287          276    6.0069324   0.20885738    2.8308749    5.5814852    189618.98            2            4 
-Loop time of 0.00655174 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   43000    524.32334   -3199.9723     0.171134    53.082676   0.24330204          287          276    6.0069324   0.20893023    2.8308749    5.5814852    189618.98            2            4 
-   44000    490.60365   -3198.9839   0.12604882    18.642955   0.25944404          544          276    6.0069324   0.21018182    2.8308749    5.5814852    193452.76            2            4 
-Loop time of 0.240179 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   44000    490.60365   -3198.9839   0.12604882    18.642955   0.25944404          544          276    6.0069324   0.21018182    2.8308749    5.5814852    193452.76            2            4 
-   44015    490.60365   -3217.9148   0.12604882    18.642955   0.25944404          544          276    6.0069324   0.21011019    2.8308749    5.5814852    193452.76            2            4 
-Loop time of 0.00717342 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   44000    490.60365   -3198.9839   0.12604882    18.642955   0.25944404          544          276    6.0069324   0.21018182    2.8308749    5.5814852    193452.76            2            4 
-   45000    516.91704    -3198.746   0.30358614    1148.1804   0.18802791          114          120    6.0069324       0.2092    2.8308749    5.5814852    194591.87            2            4 
-Loop time of 0.24121 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   45000    516.91704    -3198.746   0.30358614    1148.1804   0.18802791          114          120    6.0069324       0.2092    2.8308749    5.5814852    194591.87            2            4 
-   45013    516.91704   -3217.9155   0.30358614    1148.1804   0.18802791          114          120    6.0069324   0.20913958    2.8308749    5.5814852    194591.87            2            4 
-Loop time of 0.00649601 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   45000    516.91704    -3198.746   0.30358614    1148.1804   0.18802791          114          120    6.0069324       0.2092    2.8308749    5.5814852    194591.87            2            4 
-   46000     511.1774   -3196.9369   0.25070338    336.49294   0.21183341          138          259    6.0069324   0.20769565    2.8308749    5.5814852    199937.52            2            4 
-Loop time of 0.239441 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   46000     511.1774   -3196.9369   0.25070338    336.49294   0.21183341          138          259    6.0069324   0.20769565    2.8308749    5.5814852    199937.52            2            4 
-   46015     511.1774   -3217.9159   0.25070338    336.49294   0.21183341          138          259    6.0069324   0.20762795    2.8308749    5.5814852    199937.52            2            4 
-Loop time of 0.00681973 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   46000     511.1774   -3196.9369   0.25070338    336.49294   0.21183341          138          259    6.0069324   0.20769565    2.8308749    5.5814852    199937.52            2            4 
-   47000     480.5069   -3198.8501  0.071646863    5.2743358   0.27767529          544          556    6.0069324   0.20602128    2.8308749    5.5814852    202107.88            2            4 
-Loop time of 0.24022 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   47000     480.5069   -3198.8501  0.071646863    5.2743358   0.27767529          544          556    6.0069324   0.20602128    2.8308749    5.5814852    202107.88            2            4 
-   47016     480.5069   -3217.9167  0.071646863    5.2743358   0.27767529          544          556    6.0069324   0.20595117    2.8308749    5.5814852    202107.88            2            4 
-Loop time of 0.007438 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   47000     480.5069   -3198.8501  0.071646863    5.2743358   0.27767529          544          556    6.0069324   0.20602128    2.8308749    5.5814852    202107.88            2            4 
-   48000    540.51895   -3198.5792   0.04754734    3.0147795   0.28537953          544          556    6.0069324       0.2085    2.8308749    5.5814852    202899.91            2            4 
-Loop time of 0.241529 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   48000    540.51895   -3198.5792   0.04754734    3.0147795   0.28537953          544          556    6.0069324       0.2085    2.8308749    5.5814852    202899.91            2            4 
-   48015    540.51895   -3217.9148   0.04754734    3.0147795   0.28537953          544          556    6.0069324   0.20843486    2.8308749    5.5814852    202899.91            2            4 
-Loop time of 0.00695753 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   48000    540.51895   -3198.5792   0.04754734    3.0147795   0.28537953          544          556    6.0069324       0.2085    2.8308749    5.5814852    202899.91            2            4 
-   49000    527.63013   -3199.0384   0.28400417    728.84104   0.19717822          544          577    6.0069324   0.20961224    2.8308749    5.5814852    210926.93            2            4 
-Loop time of 0.241009 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   49000    527.63013   -3199.0384   0.28400417    728.84104   0.19717822          544          577    6.0069324   0.20961224    2.8308749    5.5814852    210926.93            2            4 
-   49013    527.63013   -3217.9157   0.28400417    728.84104   0.19717822          544          577    6.0069324   0.20955665    2.8308749    5.5814852    210926.93            2            4 
-Loop time of 0.00608408 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   49000    527.63013   -3199.0384   0.28400417    728.84104   0.19717822          544          577    6.0069324   0.20961224    2.8308749    5.5814852    210926.93            2            4 
-   50000    516.69962   -3198.3346   0.35295929    3611.3455   0.16268782          266          243    6.0069324      0.20898    2.8308749    5.5814852    215664.98            2            4 
-Loop time of 0.239941 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   50000    516.69962   -3198.3346   0.35295929    3611.3455   0.16268782          266          243    6.0069324      0.20898    2.8308749    5.5814852    215664.98            2            4 
-   50013    516.69962   -3217.9156   0.35295929    3611.3455   0.16268782          266          243    6.0069324   0.20892568    2.8308749    5.5814852    215664.98            2            4 
-Loop time of 0.00602353 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   50000    516.69962   -3198.3346   0.35295929    3611.3455   0.16268782          266          243    6.0069324      0.20898    2.8308749    5.5814852    215664.98            2            4 
-   51000    533.05598   -3198.0432   0.17474232    57.719563    0.2419636          123          128    6.0069324    0.2065098    2.8308749    5.5814852     221609.1            2            4 
-Loop time of 0.240274 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   51000    533.05598   -3198.0432   0.17474232    57.719563    0.2419636          123          128    6.0069324    0.2065098    2.8308749    5.5814852     221609.1            2            4 
-   51015    533.05598   -3217.9143   0.17474232    57.719563    0.2419636          123          128    6.0069324   0.20644908    2.8308749    5.5814852     221609.1            2            4 
-Loop time of 0.00743866 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   51000    533.05598   -3198.0432   0.17474232    57.719563    0.2419636          123          128    6.0069324    0.2065098    2.8308749    5.5814852     221609.1            2            4 
-   52000    545.98999   -3198.2633            0            1   0.30964409          287          276    6.0069324   0.20332692    2.8308749    5.5814852    230246.21            2            4 
-Loop time of 0.239709 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   52000    545.98999   -3198.2633            0            1   0.30964409          287          276    6.0069324   0.20332692    2.8308749    5.5814852    230246.21            2            4 
-   52017    545.98999   -3217.9153            0            1   0.30964409          287          276    6.0069324   0.20326047    2.8308749    5.5814852    230246.21            2            4 
-Loop time of 0.00786757 on 4 procs for 17 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   52000    545.98999   -3198.2633            0            1   0.30964409          287          276    6.0069324   0.20332692    2.8308749    5.5814852    230246.21            2            4 
-   53000    453.58658   -3199.3577   0.23959479     260.0198   0.21650159          278          279    6.0069324   0.20366038    2.8308749    5.5814852    233492.88            2            4 
-Loop time of 0.240351 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   53000    453.58658   -3199.3577   0.23959479     260.0198   0.21650159          278          279    6.0069324   0.20366038    2.8308749    5.5814852    233492.88            2            4 
-   53014    453.58658   -3217.9131   0.23959479     260.0198   0.21650159          278          279    6.0069324   0.20360659    2.8308749    5.5814852    233492.88            2            4 
-Loop time of 0.0067966 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   53000    453.58658   -3199.3577   0.23959479     260.0198   0.21650159          278          279    6.0069324   0.20366038    2.8308749    5.5814852    233492.88            2            4 
-   54000    502.12681   -3199.1712   0.28827435     804.7747   0.19521941          550          563    6.0069324   0.20264815    2.8308749    5.5814852    239627.25            2            4 
-Loop time of 0.238634 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   54000    502.12681   -3199.1712   0.28827435     804.7747   0.19521941          550          563    6.0069324   0.20264815    2.8308749    5.5814852    239627.25            2            4 
-   54014    502.12681   -3217.9165   0.28827435     804.7747   0.19521941          550          563    6.0069324   0.20259562    2.8308749    5.5814852    239627.25            2            4 
-Loop time of 0.00671387 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   54000    502.12681   -3199.1712   0.28827435     804.7747   0.19521941          550          563    6.0069324   0.20264815    2.8308749    5.5814852    239627.25            2            4 
-   55000     470.7967   -3197.4136   0.31075641    1356.0734   0.18456394          285          283    6.0069324   0.20041818    2.8308749    5.5814852    246248.56            2            4 
-Loop time of 0.240888 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   55000     470.7967   -3197.4136   0.31075641    1356.0734   0.18456394          285          283    6.0069324   0.20041818    2.8308749    5.5814852    246248.56            2            4 
-   55013     470.7967   -3217.9136   0.31075641    1356.0734   0.18456394          285          283    6.0069324   0.20037082    2.8308749    5.5814852    246248.56            2            4 
-Loop time of 0.00596166 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   55000     470.7967   -3197.4136   0.31075641    1356.0734   0.18456394          285          283    6.0069324   0.20041818    2.8308749    5.5814852    246248.56            2            4 
-   56000    533.34641   -3198.1323   0.16761369    48.918113   0.24460077          287          276    6.0069324   0.19926786    2.8308749    5.5814852    252499.61            2            4 
-Loop time of 0.239487 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   56000    533.34641   -3198.1323   0.16761369    48.918113   0.24460077          287          276    6.0069324   0.19926786    2.8308749    5.5814852    252499.61            2            4 
-   56014    533.34641   -3217.9162   0.16761369    48.918113   0.24460077          287          276    6.0069324   0.19921805    2.8308749    5.5814852    252499.61            2            4 
-Loop time of 0.00619745 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   56000    533.34641   -3198.1323   0.16761369    48.918113   0.24460077          287          276    6.0069324   0.19926786    2.8308749    5.5814852    252499.61            2            4 
-   57000    516.06876   -3197.7671            0            1   0.33139119          287          276    6.0069324   0.19807018    2.8308749    5.5814852    255923.67            2            4 
-Loop time of 0.241093 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   57000    516.06876   -3197.7671            0            1   0.33139119          287          276    6.0069324   0.19807018    2.8308749    5.5814852    255923.67            2            4 
-   57016    516.06876   -3217.9146            0            1   0.33139119          287          276    6.0069324   0.19801459    2.8308749    5.5814852    255923.67            2            4 
-Loop time of 0.00772929 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   57000    516.06876   -3197.7671            0            1   0.33139119          287          276    6.0069324   0.19807018    2.8308749    5.5814852    255923.67            2            4 
-   58000    489.18902   -3198.6347   0.20937806    128.95422   0.22871806          544          276    6.0069324   0.20094828    2.8308749    5.5814852    256132.07            2            4 
-Loop time of 0.239761 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   58000    489.18902   -3198.6347   0.20937806    128.95422   0.22871806          544          276    6.0069324   0.20094828    2.8308749    5.5814852    256132.07            2            4 
-   58014    489.18902   -3217.9165   0.20937806    128.95422   0.22871806          544          276    6.0069324   0.20089978    2.8308749    5.5814852    256132.07            2            4 
-Loop time of 0.00660753 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   58000    489.18902   -3198.6347   0.20937806    128.95422   0.22871806          544          276    6.0069324   0.20094828    2.8308749    5.5814852    256132.07            2            4 
-   59000    522.75445   -3197.4454            0            1   0.91317104          274          556    6.0069324   0.20305085    2.8308749    5.5814852    259828.37            2            4 
-Loop time of 0.241627 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   59000    522.75445   -3197.4454            0            1   0.91317104          274          556    6.0069324   0.20305085    2.8308749    5.5814852    259828.37            2            4 
-   59013    522.75445   -3217.9138            0            1   0.91317104          274          556    6.0069324   0.20300612    2.8308749    5.5814852    259828.37            2            4 
-Loop time of 0.00618345 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   59000    522.75445   -3197.4454   0.40114631    11050.253    0.1333929          547          548    6.0069324   0.20305085    2.8308749    5.5814852    259828.37            3            6 
-   60000    552.18712   -3197.1906   0.21473769    146.03543   0.22659924          559          564    6.0069324   0.20126667    2.8308749    5.5814852    263208.58            3            6 
-Loop time of 0.239681 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   60000    552.18712   -3197.1906   0.21473769    146.03543   0.22659924          559          564    6.0069324   0.20126667    2.8308749    5.5814852    263208.58            3            6 
-   60015    552.18712   -3217.9157   0.21473769    146.03543   0.22659924          559          564    6.0069324   0.20121636    2.8308749    5.5814852    263208.58            3            6 
-Loop time of 0.00685382 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   60000    552.18712   -3197.1906   0.21473769    146.03543   0.22659924          559          564    6.0069324   0.20126667    2.8308749    5.5814852    263208.58            3            6 
-   61000    450.24979    -3197.259   0.20870055    126.94235    0.2289845          412          411    6.0069324   0.20103279    2.8308749    5.5814852    267126.63            3            6 
-Loop time of 0.239598 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   61000    450.24979    -3197.259   0.20870055    126.94235    0.2289845          412          411    6.0069324   0.20103279    2.8308749    5.5814852    267126.63            3            6 
-   61014    450.24979   -3217.9146   0.20870055    126.94235    0.2289845          412          411    6.0069324   0.20098666    2.8308749    5.5814852    267126.63            3            6 
-Loop time of 0.00683248 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   61000    450.24979    -3197.259   0.20870055    126.94235    0.2289845          412          411    6.0069324   0.20103279    2.8308749    5.5814852    267126.63            3            6 
-   62000    506.89399   -3197.4659   0.20762728    123.81933   0.22940595          256          267    6.0069324   0.20074194    2.8308749    5.5814852    270687.24            3            6 
-Loop time of 0.238224 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   62000    506.89399   -3197.4659   0.20762728    123.81933   0.22940595          256          267    6.0069324   0.20074194    2.8308749    5.5814852    270687.24            3            6 
-   62014    506.89399   -3217.9156   0.20762728    123.81933   0.22940595          256          267    6.0069324   0.20069662    2.8308749    5.5814852    270687.24            3            6 
-Loop time of 0.00685287 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   62000    506.89399   -3197.4659   0.20762728    123.81933   0.22940595          256          267    6.0069324   0.20074194    2.8308749    5.5814852    270687.24            3            6 
-   63000    510.04068   -3196.8255  0.063053561     4.320671   0.28044671          112          123    6.0069324   0.19930159    2.8308749    5.5814852     274694.1            3            6 
-Loop time of 0.238676 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   63000    510.04068   -3196.8255  0.063053561     4.320671   0.28044671          112          123    6.0069324   0.19930159    2.8308749    5.5814852     274694.1            3            6 
-   63014    510.04068   -3217.9141  0.063053561     4.320671   0.28044671          112          123    6.0069324   0.19925731    2.8308749    5.5814852     274694.1            3            6 
-Loop time of 0.00670481 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   63000    510.04068   -3196.8255  0.063053561     4.320671   0.28044671          112          123    6.0069324   0.19930159    2.8308749    5.5814852     274694.1            3            6 
-   64000    501.25574   -3197.7101  0.083024533    6.8683042   0.27396274          286          119    6.0069324          0.2    2.8308749    5.5814852    276114.67            3            6 
-Loop time of 0.238342 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   64000    501.25574   -3197.7101  0.083024533    6.8683042   0.27396274          286          119    6.0069324          0.2    2.8308749    5.5814852    276114.67            3            6 
-   64014    501.25574   -3217.9141  0.083024533    6.8683042   0.27396274          286          119    6.0069324   0.19995626    2.8308749    5.5814852    276114.67            3            6 
-Loop time of 0.00604939 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   64000    501.25574   -3197.7101  0.083024533    6.8683042   0.27396274          286          119    6.0069324          0.2    2.8308749    5.5814852    276114.67            3            6 
-   65000    476.31749   -3199.3383   0.15323867     35.04097   0.24983402          267          260    6.0069324   0.19838462    2.8308749    5.5814852    282281.34            3            6 
-Loop time of 0.239458 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   65000    476.31749   -3199.3383   0.15323867     35.04097   0.24983402          267          260    6.0069324   0.19838462    2.8308749    5.5814852    282281.34            3            6 
-   65014    476.31749    -3217.913   0.15323867     35.04097   0.24983402          267          260    6.0069324    0.1983419    2.8308749    5.5814852    282281.34            3            6 
-Loop time of 0.00661784 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   65000    476.31749   -3199.3383   0.15323867     35.04097   0.24983402          267          260    6.0069324   0.19838462    2.8308749    5.5814852    282281.34            3            6 
-   66000    515.81365   -3198.7056   0.21680106    153.19903   0.22577823          416          415    6.0069324   0.19919697    2.8308749    5.5814852    284618.61            3            6 
-Loop time of 0.239712 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   66000    515.81365   -3198.7056   0.21680106    153.19903   0.22577823          416          415    6.0069324   0.19919697    2.8308749    5.5814852    284618.61            3            6 
-   66014    515.81365   -3217.9165   0.21680106    153.19903   0.22577823          416          415    6.0069324   0.19915472    2.8308749    5.5814852    284618.61            3            6 
-Loop time of 0.00680089 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   66000    515.81365   -3198.7056   0.21680106    153.19903   0.22577823          416          415    6.0069324   0.19919697    2.8308749    5.5814852    284618.61            3            6 
-   67000    484.31519   -3197.7852   0.13298902    21.901246   0.25702524          275          567    6.0069324   0.19846269    2.8308749    5.5814852    289586.09            3            6 
-Loop time of 0.239938 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   67000    484.31519   -3197.7852   0.13298902    21.901246   0.25702524          275          567    6.0069324   0.19846269    2.8308749    5.5814852    289586.09            3            6 
-   67014    484.31519   -3217.9146   0.13298902    21.901246   0.25702524          275          567    6.0069324   0.19842123    2.8308749    5.5814852    289586.09            3            6 
-Loop time of 0.00659657 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   67000    484.31519   -3197.7852   0.13298902    21.901246   0.25702524          275          567    6.0069324   0.19846269    2.8308749    5.5814852    289586.09            3            6 
-   68000    484.02912    -3199.084   0.23443259    230.66083   0.21863699          412          423    6.0069324   0.19722059    2.8308749    5.5814852    298036.66            3            6 
-Loop time of 0.240483 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   68000    484.02912    -3199.084   0.23443259    230.66083   0.21863699          412          423    6.0069324   0.19722059    2.8308749    5.5814852    298036.66            3            6 
-   68014    484.02912   -3217.9156   0.23443259    230.66083   0.21863699          412          423    6.0069324   0.19717999    2.8308749    5.5814852    298036.66            3            6 
-Loop time of 0.00666052 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   68000    484.02912    -3199.084   0.23443259    230.66083   0.21863699          412          423    6.0069324   0.19722059    2.8308749    5.5814852    298036.66            3            6 
-   69000    516.84151   -3198.3447   0.20394137    113.66746   0.23084747          119          400    6.0069324   0.19605797    2.8308749    5.5814852    302894.58            3            6 
-Loop time of 0.23984 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   69000    516.84151   -3198.3447   0.20394137    113.66746   0.23084747          119          400    6.0069324   0.19605797    2.8308749    5.5814852    302894.58            3            6 
-   69015    516.84151   -3217.9163   0.20394137    113.66746   0.23084747          119          400    6.0069324   0.19601536    2.8308749    5.5814852    302894.58            3            6 
-Loop time of 0.0070501 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   69000    516.84151   -3198.3447   0.20394137    113.66746   0.23084747          119          400    6.0069324   0.19605797    2.8308749    5.5814852    302894.58            3            6 
-   70000    521.52008   -3198.1925   0.26533657    472.57625    0.2055223          128          139    6.0069324   0.19471429    2.8308749    5.5814852    308489.53            3            6 
-Loop time of 0.240016 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   70000    521.52008   -3198.1925   0.26533657    472.57625    0.2055223          128          139    6.0069324   0.19471429    2.8308749    5.5814852    308489.53            3            6 
-   70014    521.52008   -3217.9145   0.26533657    472.57625    0.2055223          128          139    6.0069324   0.19467535    2.8308749    5.5814852    308489.53            3            6 
-Loop time of 0.00656152 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   70000    521.52008   -3198.1925   0.26533657    472.57625    0.2055223          128          139    6.0069324   0.19471429    2.8308749    5.5814852    308489.53            3            6 
-   71000    456.91639   -3199.2364  0.030609593    2.0348424   0.29067211          555          275    6.0069324   0.19753521    2.8308749    5.5814852    308872.53            3            6 
-Loop time of 0.238921 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   71000    456.91639   -3199.2364  0.030609593    2.0348424   0.29067211          555          275    6.0069324   0.19753521    2.8308749    5.5814852    308872.53            3            6 
-   71016    456.91639   -3217.9154  0.030609593    2.0348424   0.29067211          555          275    6.0069324   0.19749071    2.8308749    5.5814852    308872.53            3            6 
-Loop time of 0.00665921 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   71000    456.91639   -3199.2364  0.030609593    2.0348424   0.29067211          555          275    6.0069324   0.19753521    2.8308749    5.5814852    308872.53            3            6 
-   72000    505.77427   -3198.8053  0.011213996    1.2972748   0.29661672          275          567    6.0069324   0.20022222    2.8308749    5.5814852    308922.44            3            6 
-Loop time of 0.238494 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   72000    505.77427   -3198.8053  0.011213996    1.2972748   0.29661672          275          567    6.0069324   0.20022222    2.8308749    5.5814852    308922.44            3            6 
-   72014    505.77427   -3217.9154  0.011213996    1.2972748   0.29661672          275          567    6.0069324    0.2001833    2.8308749    5.5814852    308922.44            3            6 
-Loop time of 0.00666285 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   72000    505.77427   -3198.8053  0.011213996    1.2972748   0.29661672          275          567    6.0069324   0.20022222    2.8308749    5.5814852    308922.44            3            6 
-   73000    505.42011   -3198.5745     0.241922    274.45031   0.21553199          262          544    6.0069324   0.19989041    2.8308749    5.5814852    312318.94            3            6 
-Loop time of 0.240884 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   73000    505.42011   -3198.5745     0.241922    274.45031   0.21553199          262          544    6.0069324   0.19989041    2.8308749    5.5814852    312318.94            3            6 
-   73014    505.42011   -3217.9145     0.241922    274.45031   0.21553199          262          544    6.0069324   0.19985208    2.8308749    5.5814852    312318.94            3            6 
-Loop time of 0.00641418 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   73000    505.42011   -3198.5745     0.241922    274.45031   0.21553199          262          544    6.0069324   0.19989041    2.8308749    5.5814852    312318.94            3            6 
-   74000    525.14325   -3197.1366  0.091100202    8.2841621   0.27129682          403          404    6.0069324   0.19893243    2.8308749    5.5814852    316054.12            3            6 
-Loop time of 0.239838 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   74000    525.14325   -3197.1366  0.091100202    8.2841621   0.27129682          403          404    6.0069324   0.19893243    2.8308749    5.5814852    316054.12            3            6 
-   74014    525.14325   -3217.9164  0.091100202    8.2841621   0.27129682          403          404    6.0069324    0.1988948    2.8308749    5.5814852    316054.12            3            6 
-Loop time of 0.00640178 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   74000    525.14325   -3197.1366  0.091100202    8.2841621   0.27129682          403          404    6.0069324   0.19893243    2.8308749    5.5814852    316054.12            3            6 
-   75000    529.75357   -3196.8628   0.27468673      587.107   0.20138617          262          553    6.0069324       0.1974    2.8308749    5.5814852    320757.39            3            6 
-Loop time of 0.241485 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   75000    529.75357   -3196.8628   0.27468673      587.107   0.20138617          262          553    6.0069324       0.1974    2.8308749    5.5814852    320757.39            3            6 
-   75015    529.75357   -3217.9131   0.27468673      587.107   0.20138617          262          553    6.0069324   0.19736053    2.8308749    5.5814852    320757.39            3            6 
-Loop time of 0.00727272 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   75000    529.75357   -3196.8628   0.27468673      587.107   0.20138617          262          553    6.0069324       0.1974    2.8308749    5.5814852    320757.39            3            6 
-   76000    494.67435    -3197.324  0.026840032    1.8643837   0.29183693          555          275    6.0069324   0.19744737    2.8308749    5.5814852    321584.51            3            6 
-Loop time of 0.246189 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   76000    494.67435    -3197.324  0.026840032    1.8643837   0.29183693          555          275    6.0069324   0.19744737    2.8308749    5.5814852    321584.51            3            6 
-   76015    494.67435   -3217.9124  0.026840032    1.8643837   0.29183693          555          275    6.0069324   0.19740841    2.8308749    5.5814852    321584.51            3            6 
-Loop time of 0.00856209 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   76000    494.67435    -3197.324  0.026840032    1.8643837   0.29183693          555          275    6.0069324   0.19744737    2.8308749    5.5814852    321584.51            3            6 
-   77000     478.4265   -3198.3778  0.099536255    10.075814   0.26848366          283          272    6.0069324   0.19802597    2.8308749    5.5814852    323214.67            3            6 
-Loop time of 0.244489 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   77000     478.4265   -3198.3778  0.099536255    10.075814   0.26848366          283          272    6.0069324   0.19802597    2.8308749    5.5814852    323214.67            3            6 
-   77014     478.4265   -3217.9158  0.099536255    10.075814   0.26848366          283          272    6.0069324   0.19798998    2.8308749    5.5814852    323214.67            3            6 
-Loop time of 0.00662231 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   77000     478.4265   -3198.3778  0.099536255    10.075814   0.26848366          283          272    6.0069324   0.19802597    2.8308749    5.5814852    323214.67            3            6 
-   78000    501.53059   -3199.1386  0.013408722    1.3650665   0.29595005          420          431    6.0069324   0.19646154    2.8308749    5.5814852    328321.34            3            6 
-Loop time of 0.238902 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   78000    501.53059   -3199.1386  0.013408722    1.3650665   0.29595005          420          431    6.0069324   0.19646154    2.8308749    5.5814852    328321.34            3            6 
-   78014    501.53059   -3217.9148  0.013408722    1.3650665   0.29595005          420          431    6.0069324   0.19642628    2.8308749    5.5814852    328321.34            3            6 
-Loop time of 0.00632596 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   78000    501.53059   -3199.1386  0.013408722    1.3650665   0.29595005          420          431    6.0069324   0.19646154    2.8308749    5.5814852    328321.34            3            6 
-   79000    500.93975   -3198.0923     0.116093    14.796691   0.26287499          428          543    6.0069324   0.19506329    2.8308749    5.5814852    333018.93            3            6 
-Loop time of 0.238987 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   79000    500.93975   -3198.0923     0.116093    14.796691   0.26287499          428          543    6.0069324   0.19506329    2.8308749    5.5814852    333018.93            3            6 
-   79014    500.93975   -3217.9148     0.116093    14.796691   0.26287499          428          543    6.0069324   0.19502873    2.8308749    5.5814852    333018.93            3            6 
-Loop time of 0.00644779 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   79000    500.93975   -3198.0923     0.116093    14.796691   0.26287499          428          543    6.0069324   0.19506329    2.8308749    5.5814852    333018.93            3            6 
-   80000    521.43512   -3199.0487   0.15540998    36.852069    0.2490506          253          136    6.0069324     0.193625    2.8308749    5.5814852    337716.24            3            6 
-Loop time of 0.238806 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   80000    521.43512   -3199.0487   0.15540998    36.852069    0.2490506          253          136    6.0069324     0.193625    2.8308749    5.5814852    337716.24            3            6 
-   80014    521.43512   -3217.9164   0.15540998    36.852069    0.2490506          253          136    6.0069324   0.19359112    2.8308749    5.5814852    337716.24            3            6 
-Loop time of 0.00644064 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   80000    521.43512   -3199.0487   0.15540998    36.852069    0.2490506          253          136    6.0069324     0.193625    2.8308749    5.5814852    337716.24            3            6 
-   81000    533.69561   -3197.1168   0.24520241     296.1616   0.21415781          575          280    6.0069324   0.19222222    2.8308749    5.5814852    343062.81            3            6 
-Loop time of 0.240714 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   81000    533.69561   -3197.1168   0.24520241     296.1616   0.21415781          575          280    6.0069324   0.19222222    2.8308749    5.5814852    343062.81            3            6 
-   81015    533.69561   -3217.9142   0.24520241     296.1616   0.21415781          575          280    6.0069324   0.19218663    2.8308749    5.5814852    343062.81            3            6 
-Loop time of 0.00675607 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   81000    533.69561   -3197.1168   0.24520241     296.1616   0.21415781          575          280    6.0069324   0.19222222    2.8308749    5.5814852    343062.81            3            6 
-   82000    522.58314   -3197.6951   0.34607713    3078.2225   0.16645154          569          570    6.0069324   0.19130488    2.8308749    5.5814852    347897.31            3            6 
-Loop time of 0.239094 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   82000    522.58314   -3197.6951   0.34607713    3078.2225   0.16645154          569          570    6.0069324   0.19130488    2.8308749    5.5814852    347897.31            3            6 
-   82014    522.58314    -3217.917   0.34607713    3078.2225   0.16645154          569          570    6.0069324   0.19127222    2.8308749    5.5814852    347897.31            3            6 
-Loop time of 0.00662041 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   82000    522.58314   -3197.6951   0.34607713    3078.2225   0.16645154          569          570    6.0069324   0.19130488    2.8308749    5.5814852    347897.31            3            6 
-   83000    518.24081   -3196.6457   0.27556929    599.25687   0.20099136          512          523    6.0069324   0.18978313    2.8308749    5.5814852    355870.51            3            6 
-Loop time of 0.240335 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   83000    518.24081   -3196.6457   0.27556929    599.25687   0.20099136          512          523    6.0069324   0.18978313    2.8308749    5.5814852    355870.51            3            6 
-   83015    518.24081   -3217.9151   0.27556929    599.25687   0.20099136          512          523    6.0069324   0.18974884    2.8308749    5.5814852    355870.51            3            6 
-Loop time of 0.00710487 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   83000    518.24081   -3196.6457   0.27556929    599.25687   0.20099136          512          523    6.0069324   0.18978313    2.8308749    5.5814852    355870.51            3            6 
-   84000    524.77376   -3198.1195   0.32714869    1983.8549   0.17638944          275          567    6.0069324        0.189    2.8308749    5.5814852    358623.76            3            6 
-Loop time of 0.239069 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   84000    524.77376   -3198.1195   0.32714869    1983.8549   0.17638944          275          567    6.0069324        0.189    2.8308749    5.5814852    358623.76            3            6 
-   84014    524.77376   -3217.9145   0.32714869    1983.8549   0.17638944          275          567    6.0069324   0.18896851    2.8308749    5.5814852    358623.76            3            6 
-Loop time of 0.00662088 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   84000    524.77376   -3198.1195   0.32714869    1983.8549   0.17638944          275          567    6.0069324        0.189    2.8308749    5.5814852    358623.76            3            6 
-   85000    485.77334   -3199.2545 0.0027767134    1.0665667   0.29916583          275          567    6.0069324   0.19102353    2.8308749    5.5814852    362933.93            3            6 
-Loop time of 0.240117 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   85000    485.77334   -3199.2545 0.0027767134    1.0665667   0.29916583          275          567    6.0069324   0.19102353    2.8308749    5.5814852    362933.93            3            6 
-   85014    485.77334   -3217.9148 0.0027767134    1.0665667   0.29916583          275          567    6.0069324   0.19099207    2.8308749    5.5814852    362933.93            3            6 
-Loop time of 0.00642967 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   85000    485.77334   -3199.2545 0.0027767134    1.0665667   0.29916583          275          567    6.0069324   0.19102353    2.8308749    5.5814852    362933.93            3            6 
-   86000    520.32504   -3197.8586   0.34074416     2719.857   0.16931052          572          403    6.0069324   0.19181395    2.8308749    5.5814852    366756.98            3            6 
-Loop time of 0.23899 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   86000    520.32504   -3197.8586   0.34074416     2719.857   0.16931052          572          403    6.0069324   0.19181395    2.8308749    5.5814852    366756.98            3            6 
-   86014    520.32504   -3217.9156   0.34074416     2719.857   0.16931052          572          403    6.0069324   0.19178273    2.8308749    5.5814852    366756.98            3            6 
-Loop time of 0.00667548 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   86000    520.32504   -3197.8586   0.34074416     2719.857   0.16931052          572          403    6.0069324   0.19181395    2.8308749    5.5814852    366756.98            3            6 
-   87000    492.06505   -3198.9245   0.35508545    3794.0215   0.16150733          282          284    6.0069324   0.19096552    2.8308749    5.5814852    370757.69            3            6 
-Loop time of 0.241176 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   87000    492.06505   -3198.9245   0.35508545    3794.0215   0.16150733          282          284    6.0069324   0.19096552    2.8308749    5.5814852    370757.69            3            6 
-   87014    492.06505   -3217.9141   0.35508545    3794.0215   0.16150733          282          284    6.0069324   0.19093479    2.8308749    5.5814852    370757.69            3            6 
-Loop time of 0.00634283 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   87000    492.06505   -3198.9245   0.35508545    3794.0215   0.16150733          282          284    6.0069324   0.19096552    2.8308749    5.5814852    370757.69            3            6 
-   88000     519.1972   -3199.3527   0.27684477    617.26171   0.20041941          411          416    6.0069324      0.19025    2.8308749    5.5814852    375119.46            3            6 
-Loop time of 0.239888 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   88000     519.1972   -3199.3527   0.27684477    617.26171   0.20041941          411          416    6.0069324      0.19025    2.8308749    5.5814852    375119.46            3            6 
-   88014     519.1972   -3217.9152   0.27684477    617.26171   0.20041941          411          416    6.0069324   0.19021974    2.8308749    5.5814852    375119.46            3            6 
-Loop time of 0.00669366 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   88000     519.1972   -3199.3527   0.27684477    617.26171   0.20041941          411          416    6.0069324      0.19025    2.8308749    5.5814852    375119.46            3            6 
-   89000    524.26014   -3198.5355    0.3001416    1059.9631   0.18966948          432          431    6.0069324   0.19220225    2.8308749    5.5814852    375708.76            3            6 
-Loop time of 0.241238 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   89000    524.26014   -3198.5355    0.3001416    1059.9631   0.18966948          432          431    6.0069324   0.19220225    2.8308749    5.5814852    375708.76            3            6 
-   89014    524.26014   -3217.9158    0.3001416    1059.9631   0.18966948          432          431    6.0069324   0.19217202    2.8308749    5.5814852    375708.76            3            6 
-Loop time of 0.00632095 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   89000    524.26014   -3198.5355    0.3001416    1059.9631   0.18966948          432          431    6.0069324   0.19220225    2.8308749    5.5814852    375708.76            3            6 
-   90000    498.11952   -3200.0434    0.2737435    574.39407   0.20180726           96          141    6.0069324   0.19212222    2.8308749    5.5814852    380021.68            3            6 
-Loop time of 0.240092 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   90000    498.11952   -3200.0434    0.2737435    574.39407   0.20180726           96          141    6.0069324   0.19212222    2.8308749    5.5814852    380021.68            3            6 
-   90013    498.11952   -3217.9105    0.2737435    574.39407   0.20180726           96          141    6.0069324   0.19209448    2.8308749    5.5814852    380021.68            3            6 
-Loop time of 0.00614023 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   90000    498.11952   -3200.0434    0.2737435    574.39407   0.20180726           96          141    6.0069324   0.19212222    2.8308749    5.5814852    380021.68            3            6 
-   91000      518.719   -3198.4974            0            1   0.38452588          128          139    6.0069324   0.19137363    2.8308749    5.5814852    386325.64            3            6 
-Loop time of 0.240887 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   91000      518.719   -3198.4974            0            1   0.38452588          128          139    6.0069324   0.19137363    2.8308749    5.5814852    386325.64            3            6 
-   91015      518.719   -3217.9166            0            1   0.38452588          128          139    6.0069324   0.19134209    2.8308749    5.5814852    386325.64            3            6 
-Loop time of 0.00709724 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   91000      518.719   -3198.4974            0            1   0.38452588          128          139    6.0069324   0.19137363    2.8308749    5.5814852    386325.64            3            6 
-   92000    489.88256   -3197.3306   0.22381505    180.28261   0.22296478          554          556    6.0069324   0.19186957    2.8308749    5.5814852    387621.28            3            6 
-Loop time of 0.241415 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   92000    489.88256   -3197.3306   0.22381505    180.28261   0.22296478          554          556    6.0069324   0.19186957    2.8308749    5.5814852    387621.28            3            6 
-   92014    489.88256   -3217.9165   0.22381505    180.28261   0.22296478          554          556    6.0069324   0.19184037    2.8308749    5.5814852    387621.28            3            6 
-Loop time of 0.00761282 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   92000    489.88256   -3197.3306   0.22381505    180.28261   0.22296478          554          556    6.0069324   0.19186957    2.8308749    5.5814852    387621.28            3            6 
-   93000    470.86218   -3199.1842            0            1   0.35506745          275          567    6.0069324   0.19339785    2.8308749    5.5814852     388253.6            3            6 
-Loop time of 0.242326 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   93000    470.86218   -3199.1842            0            1   0.35506745          275          567    6.0069324   0.19339785    2.8308749    5.5814852     388253.6            3            6 
-   93015    470.86218   -3217.9141            0            1   0.35506745          275          567    6.0069324   0.19336666    2.8308749    5.5814852     388253.6            3            6 
-Loop time of 0.006814 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   93000    470.86218   -3199.1842            0            1   0.35506745          275          567    6.0069324   0.19339785    2.8308749    5.5814852     388253.6            3            6 
-   94000    500.15102   -3200.7696   0.21997392    164.90621    0.2245099          547          552    6.0069324   0.19425532    2.8308749    5.5814852    390879.44            3            6 
-Loop time of 0.239427 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   94000    500.15102   -3200.7696   0.21997392    164.90621    0.2245099          547          552    6.0069324   0.19425532    2.8308749    5.5814852    390879.44            3            6 
-   94014    500.15102   -3217.9143   0.21997392    164.90621    0.2245099          547          552    6.0069324   0.19422639    2.8308749    5.5814852    390879.44            3            6 
-Loop time of 0.00671053 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   94000    500.15102   -3200.7696   0.21997392    164.90621    0.2245099          547          552    6.0069324   0.19425532    2.8308749    5.5814852    390879.44            3            6 
-   95000    490.13908   -3196.2455   0.24009629    263.06397   0.21629301          404          411    6.0069324   0.19329474    2.8308749    5.5814852    393723.55            3            6 
-Loop time of 0.240334 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   95000    490.13908   -3196.2455   0.24009629    263.06397   0.21629301          404          411    6.0069324   0.19329474    2.8308749    5.5814852    393723.55            3            6 
-   95014    490.13908   -3217.9156   0.24009629    263.06397   0.21629301          404          411    6.0069324   0.19326626    2.8308749    5.5814852    393723.55            3            6 
-Loop time of 0.00659347 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   95000    490.13908   -3196.2455   0.24009629    263.06397   0.21629301          404          411    6.0069324   0.19329474    2.8308749    5.5814852    393723.55            3            6 
-   96000    487.33226   -3198.9357            0            1   0.37635306          275          567    6.0069324   0.19283333    2.8308749    5.5814852    397503.57            3            6 
-Loop time of 0.239501 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   96000    487.33226   -3198.9357            0            1   0.37635306          275          567    6.0069324   0.19283333    2.8308749    5.5814852    397503.57            3            6 
-   96016    487.33226   -3217.9155            0            1   0.37635306          275          567    6.0069324    0.1928012    2.8308749    5.5814852    397503.57            3            6 
-Loop time of 0.00752759 on 4 procs for 16 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   96000    487.33226   -3198.9357            0            1   0.37635306          275          567    6.0069324   0.19283333    2.8308749    5.5814852    397503.57            3            6 
-   97000    474.12539   -3199.8196   0.35035926    3399.8667   0.16411988          543          577    6.0069324   0.19291753    2.8308749    5.5814852    402607.83            3            6 
-Loop time of 0.241445 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   97000    474.12539   -3199.8196   0.35035926    3399.8667   0.16411988          543          577    6.0069324   0.19291753    2.8308749    5.5814852    402607.83            3            6 
-   97014    474.12539   -3217.9109   0.35035926    3399.8667   0.16411988          543          577    6.0069324   0.19288969    2.8308749    5.5814852    402607.83            3            6 
-Loop time of 0.00657606 on 4 procs for 14 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   97000    474.12539   -3199.8196   0.35035926    3399.8667   0.16411988          543          577    6.0069324   0.19291753    2.8308749    5.5814852    402607.83            3            6 
-   98000    529.81368   -3198.9595   0.31966379    1667.4989   0.18016803          219          257    6.0069324   0.19226531    2.8308749    5.5814852    408103.05            3            6 
-Loop time of 0.239002 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   98000    529.81368   -3198.9595   0.31966379    1667.4989   0.18016803          219          257    6.0069324   0.19226531    2.8308749    5.5814852    408103.05            3            6 
-   98013    529.81368   -3217.9152   0.31966379    1667.4989   0.18016803          219          257    6.0069324    0.1922398    2.8308749    5.5814852    408103.05            3            6 
-Loop time of 0.00612688 on 4 procs for 13 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   98000    529.81368   -3198.9595   0.31966379    1667.4989   0.18016803          219          257    6.0069324   0.19226531    2.8308749    5.5814852    408103.05            3            6 
-   99000    521.70465   -3199.4429  0.069318452    4.9968747   0.27842895          404          399    6.0069324   0.19121212    2.8308749    5.5814852    410506.47            3            6 
-Loop time of 0.239787 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   99000    521.70465   -3199.4429  0.069318452    4.9968747   0.27842895          404          399    6.0069324   0.19121212    2.8308749    5.5814852    410506.47            3            6 
-   99015    521.70465   -3217.9162  0.069318452    4.9968747   0.27842895          404          399    6.0069324   0.19118315    2.8308749    5.5814852    410506.47            3            6 
-Loop time of 0.00708294 on 4 procs for 15 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-   99000    521.70465   -3199.4429  0.069318452    4.9968747   0.27842895          404          399    6.0069324   0.19121212    2.8308749    5.5814852    410506.47            3            6 
-  100000    513.67972   -3199.6382   0.37912459    6628.3181   0.14750449          554          556    6.0069324      0.19018    2.8308749    5.5814852    415873.98            3            6 
-Loop time of 0.239291 on 4 procs for 1000 steps with 577 atoms
-
-Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] 
-  100000    513.67972   -3199.6382   0.37912459    6628.3181   0.14750449          554          556    6.0069324      0.19018    2.8308749    5.5814852    415873.98            3            6 
-  100015    513.67972   -3217.9139   0.37912459    6628.3181   0.14750449          554          556    6.0069324   0.19015148    2.8308749    5.5814852    415873.98            3            6 
-Loop time of 0.00685054 on 4 procs for 15 steps with 577 atoms
-
-Final hyper stats ...
-
-Cummulative quantities for fix hyper:
-  hyper time = 415874
-  event timesteps = 3
-  # of atoms in events = 6
-Quantities for this hyper run:
-  event timesteps = 3
-  # of atoms in events = 6
-  max length of any bond = 5.58149
-  max drift distance of any atom = 2.83087
-  fraction of steps & bonds with zero bias = 0.19018
-Current quantities:
-  ave bonds/atom = 6.00693
-
-Loop time of 25.9832 on 4 procs for 100000 steps with 577 atoms
-
-Performance: 1662.613 ns/day, 0.014 hours/ns, 3848.641 timesteps/s
-100.4% CPU use with 4 MPI tasks x no OpenMP threads
-
-Hyper stats:
-  Dynamics time (%) = 24.8121 (95.4928)
-  Quench   time (%) = 0.715868 (2.75512)
-  Other    time (%) = 0.879782 (3.38596)
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 17.954     | 18.433     | 18.794     |   8.4 | 70.94
-Neigh   | 1.4147     | 1.4662     | 1.5092     |   2.9 |  5.64
-Comm    | 2.0975     | 2.2026     | 2.3076     |   5.6 |  8.48
-Output  | 0.0030999  | 0.0031937  | 0.003444   |   0.3 |  0.01
-Modify  | 2.6366     | 2.9984     | 3.4835     |  19.3 | 11.54
-Other   |            | 0.8798     |            |       |  3.39
-
-Nlocal:    144.25 ave 150 max 139 min
-Histogram: 1 0 1 0 0 0 1 0 0 1
-Nghost:    533.25 ave 538 max 527 min
-Histogram: 1 0 0 0 1 0 0 0 1 1
-Neighs:    3359.25 ave 3495 max 3245 min
-Histogram: 1 0 1 0 0 1 0 0 0 1
-
-Total # of neighbors = 13437
-Ave neighs/atom = 23.2877
-Neighbor list builds = 10069
-Dangerous builds = 0
-Total wall time: 0:00:26
diff --git a/examples/hyper/log.10Oct18.hyper.local.g++.16 b/examples/hyper/log.10Oct18.hyper.local.g++.16
deleted file mode 100644
index 480fcf0248..0000000000
--- a/examples/hyper/log.10Oct18.hyper.local.g++.16
+++ /dev/null
@@ -1,993 +0,0 @@
-LAMMPS (10 Oct 2018)
-# 3d EAM surface for local HD
-
-# nearest neighbor distance = a * sqrt(2)/2 = 2.77 Angs for Pt with a = 3.92
-# hop event on (100) surface is same distance
-# exchange event is 2 atoms moving same distance
-
-variable        Tequil index 400.0
-variable        Vmax index 0.4
-variable        qfactor index 0.3
-variable        cutbond index 3.2
-variable        Dcut index 10.0
-variable        cutevent index 1.1
-variable        alpha index 200.0
-variable        boost index 4000.0
-variable        ghostcut index 12.0
-variable        steps index 1500
-variable        nevent index 100
-variable        nx index 8
-variable        ny index 8
-variable        zoom index 1.8
-variable        seed index 826626413
-variable        tol index 1.0e-15
-variable        add index 37K
-
-units           metal
-atom_style	atomic
-atom_modify     map array
-boundary        p p p
-comm_modify     cutoff ${ghostcut}
-comm_modify     cutoff 12.0
-
-lattice		fcc 3.92
-Lattice spacing in x,y,z = 3.92 3.92 3.92
-region		box block 0 6 0 6 0 4
-create_box	2 box
-Created orthogonal box = (0 0 0) to (23.52 23.52 15.68)
-  2 by 4 by 2 MPI processor grid
-create_atoms	1 box
-Created 576 atoms
-  Time spent = 0.00108504 secs
-
-mass            * 1.0
-
-change_box      all z final -0.1 5.0 boundary p p f
-  orthogonal box = (0 0 -0.392) to (23.52 23.52 19.6)
-
-# replicate in xy
-
-replicate       ${nx} ${ny} 1
-replicate       8 ${ny} 1
-replicate       8 8 1
-  orthogonal box = (0 0 -0.392) to (188.16 188.16 19.6)
-  4 by 4 by 1 MPI processor grid
-  36864 atoms
-  Time spent = 0.0028758 secs
-
-# add adatoms
-
-include         adatoms.list.${add}
-include         adatoms.list.37K
-create_atoms 1 single 27.5 9.5 4
-Created 1 atoms
-  Time spent = 0.000183105 secs
-create_atoms 1 single 16 9 4
-Created 1 atoms
-  Time spent = 0.000178099 secs
-create_atoms 1 single 10 12 4
-Created 1 atoms
-  Time spent = 0.000179768 secs
-create_atoms 1 single 31 44 4
-Created 1 atoms
-  Time spent = 0.000184059 secs
-create_atoms 1 single 13 17 4
-Created 1 atoms
-  Time spent = 0.000173807 secs
-create_atoms 1 single 8.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000167847 secs
-create_atoms 1 single 23 26 4
-Created 1 atoms
-  Time spent = 0.000179052 secs
-create_atoms 1 single 38 27 4
-Created 1 atoms
-  Time spent = 0.000169992 secs
-create_atoms 1 single 37.5 4.5 4
-Created 1 atoms
-  Time spent = 0.000166178 secs
-create_atoms 1 single 41.5 47.5 4
-Created 1 atoms
-  Time spent = 0.000172138 secs
-create_atoms 1 single 20.5 37.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 5 8 4
-Created 1 atoms
-  Time spent = 0.00018096 secs
-create_atoms 1 single 2.5 16.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 38.5 45.5 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 9 0 4
-Created 1 atoms
-  Time spent = 0.000168085 secs
-create_atoms 1 single 39 32 4
-Created 1 atoms
-  Time spent = 0.000170946 secs
-create_atoms 1 single 45.5 11.5 4
-Created 1 atoms
-  Time spent = 0.00018096 secs
-create_atoms 1 single 40 0 4
-Created 1 atoms
-  Time spent = 0.000168085 secs
-create_atoms 1 single 44.5 2.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 4.5 44.5 4
-Created 1 atoms
-  Time spent = 0.000168085 secs
-create_atoms 1 single 24.5 13.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 47.5 23.5 4
-Created 1 atoms
-  Time spent = 0.00018096 secs
-create_atoms 1 single 1 20 4
-Created 1 atoms
-  Time spent = 0.000166893 secs
-create_atoms 1 single 38.5 31.5 4
-Created 1 atoms
-  Time spent = 0.000168085 secs
-create_atoms 1 single 12.5 12.5 4
-Created 1 atoms
-  Time spent = 0.000169992 secs
-create_atoms 1 single 2 27 4
-Created 1 atoms
-  Time spent = 0.000188828 secs
-create_atoms 1 single 21 5 4
-Created 1 atoms
-  Time spent = 0.000174999 secs
-create_atoms 1 single 47 12 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 32.5 46.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 9.5 40.5 4
-Created 1 atoms
-  Time spent = 0.000166893 secs
-create_atoms 1 single 8.5 2.5 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 41.5 22.5 4
-Created 1 atoms
-  Time spent = 0.000174046 secs
-create_atoms 1 single 29 11 4
-Created 1 atoms
-  Time spent = 0.000166893 secs
-create_atoms 1 single 3.5 3.5 4
-Created 1 atoms
-  Time spent = 0.000165224 secs
-create_atoms 1 single 5 21 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 46.5 31.5 4
-Created 1 atoms
-  Time spent = 0.000166178 secs
-create_atoms 1 single 35 46 4
-Created 1 atoms
-  Time spent = 0.000183105 secs
-create_atoms 1 single 40.5 41.5 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 10 22 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 43.5 14.5 4
-Created 1 atoms
-  Time spent = 0.000169992 secs
-create_atoms 1 single 42 42 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 4 26 4
-Created 1 atoms
-  Time spent = 0.000174999 secs
-create_atoms 1 single 19 34 4
-Created 1 atoms
-  Time spent = 0.000163078 secs
-create_atoms 1 single 33 9 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 0.5 45.5 4
-Created 1 atoms
-  Time spent = 0.000163078 secs
-create_atoms 1 single 30.5 32.5 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 25.5 5.5 4
-Created 1 atoms
-  Time spent = 0.000178099 secs
-create_atoms 1 single 47.5 39.5 4
-Created 1 atoms
-  Time spent = 0.000165939 secs
-create_atoms 1 single 15 13 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 21 21 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 14 28 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 9 34 4
-Created 1 atoms
-  Time spent = 0.000174999 secs
-create_atoms 1 single 7 38 4
-Created 1 atoms
-  Time spent = 0.000175953 secs
-create_atoms 1 single 11 35 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 20.5 45.5 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 30.5 31.5 4
-Created 1 atoms
-  Time spent = 0.000159979 secs
-create_atoms 1 single 32.5 2.5 4
-Created 1 atoms
-  Time spent = 0.000166178 secs
-create_atoms 1 single 21.5 3.5 4
-Created 1 atoms
-  Time spent = 0.000157833 secs
-create_atoms 1 single 23 12 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 4.5 33.5 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 46 43 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 42.5 45.5 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 4.5 10.5 4
-Created 1 atoms
-  Time spent = 0.000158072 secs
-create_atoms 1 single 33.5 15.5 4
-Created 1 atoms
-  Time spent = 0.000157833 secs
-create_atoms 1 single 24 5 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 13 16 4
-Created 1 atoms
-  Time spent = 0.000158072 secs
-create_atoms 1 single 16.5 23.5 4
-Created 1 atoms
-  Time spent = 0.000156164 secs
-create_atoms 1 single 45.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000247002 secs
-create_atoms 1 single 44.5 5.5 4
-Created 1 atoms
-  Time spent = 0.000156164 secs
-create_atoms 1 single 27.5 46.5 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 44.5 12.5 4
-Created 1 atoms
-  Time spent = 0.000157833 secs
-create_atoms 1 single 12 41 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 6 4 4
-Created 1 atoms
-  Time spent = 0.0001688 secs
-create_atoms 1 single 31.5 10.5 4
-Created 1 atoms
-  Time spent = 0.00015521 secs
-create_atoms 1 single 1 44 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 31 4 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 21 33 4
-Created 1 atoms
-  Time spent = 0.000156879 secs
-create_atoms 1 single 3 33 4
-Created 1 atoms
-  Time spent = 0.000164032 secs
-create_atoms 1 single 15 10 4
-Created 1 atoms
-  Time spent = 0.0001719 secs
-create_atoms 1 single 28.5 22.5 4
-Created 1 atoms
-  Time spent = 0.000153065 secs
-create_atoms 1 single 43 1 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 3.5 0.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 41 37 4
-Created 1 atoms
-  Time spent = 0.000153065 secs
-create_atoms 1 single 18.5 43.5 4
-Created 1 atoms
-  Time spent = 0.000213146 secs
-create_atoms 1 single 17 27 4
-Created 1 atoms
-  Time spent = 0.000159979 secs
-create_atoms 1 single 3 5 4
-Created 1 atoms
-  Time spent = 0.000153065 secs
-create_atoms 1 single 18.5 23.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 31.5 14.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 41 31 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 22 3 4
-Created 1 atoms
-  Time spent = 0.00015521 secs
-create_atoms 1 single 14.5 40.5 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 9 38 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 36 42 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 33 22 4
-Created 1 atoms
-  Time spent = 0.000163078 secs
-create_atoms 1 single 15.5 47.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 3 0 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 25.5 27.5 4
-Created 1 atoms
-  Time spent = 0.000176907 secs
-create_atoms 1 single 2.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 29.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000162125 secs
-create_atoms 1 single 44.5 18.5 4
-Created 1 atoms
-  Time spent = 0.000152826 secs
-create_atoms 1 single 26 40 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 41 27 4
-Created 1 atoms
-  Time spent = 0.000158072 secs
-create_atoms 1 single 39.5 5.5 4
-Created 1 atoms
-  Time spent = 0.000155926 secs
-create_atoms 1 single 3 38 4
-Created 1 atoms
-  Time spent = 0.000152826 secs
-create_atoms 1 single 35 29 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 11 19 4
-Created 1 atoms
-  Time spent = 0.000164986 secs
-create_atoms 1 single 18 1 4
-Created 1 atoms
-  Time spent = 0.000146866 secs
-create_atoms 1 single 39.5 40.5 4
-Created 1 atoms
-  Time spent = 0.000146866 secs
-create_atoms 1 single 46 17 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 1.5 23.5 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 28.5 23.5 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 10 28 4
-Created 1 atoms
-  Time spent = 0.000159979 secs
-create_atoms 1 single 19 47 4
-Created 1 atoms
-  Time spent = 0.000148058 secs
-create_atoms 1 single 10.5 16.5 4
-Created 1 atoms
-  Time spent = 0.000147104 secs
-create_atoms 1 single 38 45 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 42.5 41.5 4
-Created 1 atoms
-  Time spent = 0.000161886 secs
-create_atoms 1 single 47.5 42.5 4
-Created 1 atoms
-  Time spent = 0.000147104 secs
-create_atoms 1 single 38 7 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 10 44 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 29.5 27.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 45 30 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 3 9 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 8.5 35.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 24 44 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 47 4 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 7.5 8.5 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 32.5 41.5 4
-Created 1 atoms
-  Time spent = 0.000157833 secs
-create_atoms 1 single 0.5 34.5 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 11 8 4
-Created 1 atoms
-  Time spent = 0.000147104 secs
-create_atoms 1 single 2 40 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 25 24 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 47.5 6.5 4
-Created 1 atoms
-  Time spent = 0.000147104 secs
-create_atoms 1 single 39.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 17 21 4
-Created 1 atoms
-  Time spent = 0.000164032 secs
-create_atoms 1 single 32 43 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 16.5 29.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 34 34 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 11.5 3.5 4
-Created 1 atoms
-  Time spent = 0.000154018 secs
-create_atoms 1 single 39 22 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 24.5 36.5 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 33 31 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 35.5 35.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 14.5 34.5 4
-Created 1 atoms
-  Time spent = 0.000146866 secs
-create_atoms 1 single 34 28 4
-Created 1 atoms
-  Time spent = 0.000153065 secs
-create_atoms 1 single 37 41 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 33 46 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 27.5 28.5 4
-Created 1 atoms
-  Time spent = 0.000145197 secs
-create_atoms 1 single 40.5 22.5 4
-Created 1 atoms
-  Time spent = 0.000150919 secs
-create_atoms 1 single 27.5 1.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 12 2 4
-Created 1 atoms
-  Time spent = 0.000151873 secs
-create_atoms 1 single 36 43 4
-Created 1 atoms
-  Time spent = 0.000144005 secs
-create_atoms 1 single 28.5 9.5 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 20.5 25.5 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 3 3 4
-Created 1 atoms
-  Time spent = 0.000144005 secs
-create_atoms 1 single 38 33 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 3 20 4
-Created 1 atoms
-  Time spent = 0.000154972 secs
-create_atoms 1 single 35 11 4
-Created 1 atoms
-  Time spent = 0.000145912 secs
-create_atoms 1 single 5 25 4
-Created 1 atoms
-  Time spent = 0.000144005 secs
-create_atoms 1 single 36.5 6.5 4
-Created 1 atoms
-  Time spent = 0.000144005 secs
-create_atoms 1 single 19.5 24.5 4
-Created 1 atoms
-  Time spent = 0.000236988 secs
-create_atoms 1 single 27 41 4
-Created 1 atoms
-  Time spent = 0.000169992 secs
-create_atoms 1 single 39.5 11.5 4
-Created 1 atoms
-  Time spent = 0.000138998 secs
-create_atoms 1 single 21.5 2.5 4
-Created 1 atoms
-  Time spent = 0.000136852 secs
-create_atoms 1 single 46.5 15.5 4
-Created 1 atoms
-  Time spent = 0.000138998 secs
-create_atoms 1 single 13 24 4
-Created 1 atoms
-  Time spent = 0.000137091 secs
-create_atoms 1 single 11 37 4
-Created 1 atoms
-  Time spent = 0.000144005 secs
-create_atoms 1 single 11.5 31.5 4
-Created 1 atoms
-  Time spent = 0.000144958 secs
-create_atoms 1 single 47 0 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 25.5 17.5 4
-Created 1 atoms
-  Time spent = 0.00014019 secs
-create_atoms 1 single 32 11 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 8 17 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 27.5 12.5 4
-Created 1 atoms
-  Time spent = 0.000137806 secs
-create_atoms 1 single 25 7 4
-Created 1 atoms
-  Time spent = 0.000146151 secs
-create_atoms 1 single 25.5 37.5 4
-Created 1 atoms
-  Time spent = 0.000139952 secs
-create_atoms 1 single 12 15 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 1 7 4
-Created 1 atoms
-  Time spent = 0.000138998 secs
-create_atoms 1 single 18.5 47.5 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 5 38 4
-Created 1 atoms
-  Time spent = 0.000136852 secs
-create_atoms 1 single 42 19 4
-Created 1 atoms
-  Time spent = 0.000149012 secs
-create_atoms 1 single 30.5 7.5 4
-Created 1 atoms
-  Time spent = 0.000138044 secs
-create_atoms 1 single 42.5 7.5 4
-Created 1 atoms
-  Time spent = 0.000138998 secs
-create_atoms 1 single 26.5 18.5 4
-Created 1 atoms
-  Time spent = 0.000153065 secs
-create_atoms 1 single 18.5 1.5 4
-Created 1 atoms
-  Time spent = 0.000137091 secs
-create_atoms 1 single 41.5 10.5 4
-Created 1 atoms
-  Time spent = 0.000140905 secs
-
-# define frozen substrate and mobile atoms
-
-region          base block INF INF INF INF 0 1.8
-set             region base type 2
-  18432 settings made for type
-group           base type 2
-18432 atoms in group base
-group           mobile type 1
-18616 atoms in group mobile
-
-# pair style
-
-pair_style	eam/alloy
-pair_coeff	* * ptvoterlammps.eam Pt Pt
-
-neighbor	0.5 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 mobile nve
-fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 ${seed} zero yes
-fix		2 mobile langevin 400.0 ${Tequil} 1.0 ${seed} zero yes
-fix		2 mobile langevin 400.0 400.0 1.0 ${seed} zero yes
-fix		2 mobile langevin 400.0 400.0 1.0 826626413 zero yes
-
-timestep	0.005
-
-compute         tmobile mobile temp
-
-thermo		100
-thermo_modify   temp tmobile
-WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:488)
-
-# thermal equilibration
-
-run             1000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.07583
-  ghost atom cutoff = 12
-  binsize = 3.03792, bins = 62 62 7
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair eam/alloy, perpetual
-      attributes: half, newton on
-      pair build: half/bin/atomonly/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.359 | 3.359 | 3.36 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0            0   -206220.22            0   -206220.22   -52155.664 
-     100    188.18127   -206044.43            0   -205591.63    -25068.83 
-     200    274.34464   -205860.78            0   -205200.66   -40191.797 
-     300    325.66286   -205750.01            0    -204966.4   -31510.222 
-     400    352.48242   -205675.42            0   -204827.28   -35058.064 
-     500    370.88571   -205619.66            0   -204727.25   -32735.022 
-     600    388.62129   -205592.87            0   -204657.78   -33904.556 
-     700    389.54874   -205579.73            0    -204642.4   -32769.852 
-     800    395.56074   -205576.82            0   -204625.03   -33755.948 
-     900    398.03458   -205564.48            0   -204606.74   -32777.103 
-    1000    401.24089   -205562.85            0    -204597.4   -33785.341 
-Loop time of 4.3687 on 16 procs for 1000 steps with 37048 atoms
-
-Performance: 98.885 ns/day, 0.243 hours/ns, 228.901 timesteps/s
-98.4% CPU use with 16 MPI tasks x no OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 3.2988     | 3.3828     | 3.4667     |   2.3 | 77.43
-Neigh   | 0.20856    | 0.23127    | 0.24382    |   1.9 |  5.29
-Comm    | 0.33313    | 0.45075    | 0.55485    |   9.2 | 10.32
-Output  | 0.00042987 | 0.00044042 | 0.00049591 |   0.0 |  0.01
-Modify  | 0.18811    | 0.28363    | 0.36798    |   9.7 |  6.49
-Other   |            | 0.01983    |            |       |  0.45
-
-Nlocal:    2315.5 ave 2332 max 2297 min
-Histogram: 2 0 0 3 4 0 2 1 2 2
-Nghost:    3186.31 ave 3205 max 3170 min
-Histogram: 2 1 3 0 2 3 2 1 0 2
-Neighs:    55590.9 ave 56174 max 55103 min
-Histogram: 2 2 1 1 4 1 3 0 0 2
-
-Total # of neighbors = 889454
-Ave neighs/atom = 24.0082
-Neighbor list builds = 105
-Dangerous builds = 0
-reset_timestep  0
-
-# pin base so will not move during quenches
-
-fix             freeze base setforce 0.0 0.0 0.0
-
-# event detection
-
-compute         event all event/displace ${cutevent}
-compute         event all event/displace 1.1
-
-# hyper/local
-
-fix             HL mobile hyper/local ${cutbond} ${qfactor} ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 ${qfactor} ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 0.3 ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 0.3 0.4 ${Tequil}                 ${Dcut} ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 ${Dcut} ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 ${alpha} ${boost}
-fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 200.0 ${boost}
-fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 200.0 4000.0
-
-# thermo output
-
-thermo_style    custom step temp pe f_HL f_HL[*]
-WARNING: New thermo_style command, previous thermo_modify settings will be lost (../output.cpp:705)
-
-thermo_modify   lost ignore
-thermo_modify   temp tmobile
-WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:488)
-
-thermo          ${nevent}
-thermo          100
-
-# dump
-
-region          substrate block INF INF INF INF 1.8 3.8
-region          adatoms block INF INF INF INF 3.8 INF
-variable        acolor atom rmask(base)+2*rmask(substrate)+3*rmask(adatoms)
-
-dump		1 all image 10000000 local.*.jpg v_acolor type size 1024 1024 		zoom ${zoom} adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
-dump		1 all image 10000000 local.*.jpg v_acolor type size 1024 1024 		zoom 1.8 adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
-dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
-
-# run
-
-hyper           ${steps} ${nevent} HL event min ${tol} ${tol} 1000 1000 dump 1
-hyper           1500 ${nevent} HL event min ${tol} ${tol} 1000 1000 dump 1
-hyper           1500 100 HL event min ${tol} ${tol} 1000 1000 dump 1
-hyper           1500 100 HL event min 1.0e-15 ${tol} 1000 1000 dump 1
-hyper           1500 100 HL event min 1.0e-15 1.0e-15 1000 1000 dump 1
-WARNING: Resetting reneighboring criteria during hyper (../hyper.cpp:133)
-Neighbor list info ...
-  update every 1 steps, delay 0 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.07583
-  ghost atom cutoff = 12
-  binsize = 3.03792, bins = 62 62 7
-  2 neighbor lists, perpetual/occasional/extra = 1 1 0
-  (1) pair eam/alloy, perpetual
-      attributes: half, newton on
-      pair build: half/bin/atomonly/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-  (2) fix hyper/local, occasional
-      attributes: full, newton on, cut 10
-      pair build: full/bin/atomonly
-      stencil: full/bin/3d
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 7.566 | 7.567 | 7.567 Mbytes
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-       0    401.24089   -205562.85            0            0            0            1            0            0            0            0            0            0            0            0        4e+19            0            0            0            0            0            0            0            0            0            0            0 
-      77    401.24089   -206534.96            0            0            0            1            0            0            0            0            0            0            0            0        4e+19            0            0            0            0            0            0            0         1540            0            0            0 
-Loop time of 0.540347 on 16 procs for 77 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-       0    401.24089   -205562.85    23.271302           74   0.18753621            1    6.0138739    703.62325            0   0.55802338    3.5350432            0            0            0        4e+19    10.115141    10.115141            0            0            0            0            0            0            0            0            0 
-     100    399.15639   -205546.21    22.904368           90   0.32935524   0.39929142    6.0138739    703.62325  0.026229865   0.91517139    3.9968927        91.88    0.3995539    0.4009724   0.39695676    10.262823    10.262823            0            0            0            0            0         2000            0            0            0 
-Loop time of 0.579085 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     100    399.15639   -205546.21    22.904368           90   0.32935524   0.39929142    6.0138739    703.62325  0.026229865   0.91517139    3.9968927        91.88    0.3995539    0.4009724   0.39695676    10.262823    10.262823            0            0            0            0            0         2000            0            0            0 
-     184    399.15639   -206534.96    22.904368           90   0.32935524   0.39929142    6.0138739    703.62325  0.026229865   0.91517139    3.9968927    49.934783   0.21714886    0.4009724   0.39695676    10.262823    10.262823            0            0            0            0            0         3680            0            0            0 
-Loop time of 0.556056 on 16 procs for 84 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     100    399.15639   -205546.21    22.903938           90   0.32935524   0.39929142    6.0138739    703.62325  0.026229865   0.91517139    3.9968927        91.88    0.3995539    0.4009724   0.39695676    10.262823    10.262823            0            0            0            0            0         2000            0            0            0 
-     200    403.01717   -205543.17    20.844359           90    0.3291605   0.39888693    6.0138739    703.62325  0.039527213   0.94418421    4.0368484        90.95   0.39930574    0.4019706   0.39554353    10.262823    10.262823            0            0            0            0            0         4000            0            0            0 
-Loop time of 0.581214 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     200    403.01717   -205543.17    20.844359           90    0.3291605   0.39888693    6.0138739    703.62325  0.039527213   0.94418421    4.0368484        90.95   0.39930574    0.4019706   0.39554353    10.262823    10.262823            0            0            0            0            0         4000            0            0            0 
-     275    403.01717   -206534.96    20.844359           90    0.3291605   0.39888693    6.0138739    703.62325  0.039527213   0.94418421    4.0368484    66.145455   0.29040418    0.4019706   0.39554353    10.262823    10.262823            0            0            0            0            0         5500            0            0            0 
-Loop time of 0.481812 on 16 procs for 75 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     200    403.01717   -205543.17    21.115577           91    0.3291605   0.39888693    6.0138739    703.62325  0.039527213   0.94418421    4.0368484        90.95   0.39930574    0.4019706   0.39554353    10.262823    10.262823            0            0            0            0            0         4000            0            0            0 
-     300    399.01963   -205541.46    19.137336           85   0.32442182   0.39862755    6.0138739    703.62325  0.046873868   0.94776891    4.0368484        92.02   0.39912484   0.40296919   0.39497622    10.288936    10.288936            0            0            0            0            0         6000            0            0            0 
-Loop time of 0.5757 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     300    399.01963   -205541.46    19.137336           85   0.32442182   0.39862755    6.0138739    703.62325  0.046873868   0.94776891    4.0368484        92.02   0.39912484   0.40296919   0.39497622    10.288936    10.288936            0            0            0            0            0         6000            0            0            0 
-     377    399.01963   -206534.96    19.137336           85   0.32442182   0.39862755    6.0138739    703.62325  0.046873868   0.94776891    4.0368484    73.225464   0.31760598   0.40296919   0.39497622    10.288936    10.288936            0            0            0            0            0         7540            0            0            0 
-Loop time of 0.514907 on 16 procs for 77 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     300    399.01963   -205541.46    19.137003           85   0.32442182   0.39862755    6.0138739    703.62325  0.046873868   0.94776891    4.0368484        92.02   0.39912484   0.40296919   0.39497622    10.288936    10.288936            0            0            0            0            0         6000            0            0            0 
-     400    398.15351   -205544.87    20.470844           93   0.34589451   0.39828754    6.0138739    703.62325  0.049952465   0.94776891    4.0779385      92.0375   0.39894967   0.40395328    0.3932824    10.307052    10.307052            0            0            0            0            0         8000            0            0            0 
-Loop time of 0.577371 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     400    398.15351   -205544.87    20.470844           93   0.34589451   0.39828754    6.0138739    703.62325  0.049952465   0.94776891    4.0779385      92.0375   0.39894967   0.40395328    0.3932824    10.307052    10.307052            0            0            0            0            0         8000            0            0            0 
-     471    398.15351   -206534.96    20.470844           93   0.34589451   0.39828754    6.0138739    703.62325  0.049952465   0.94776891    4.0779385    78.163482   0.33881076   0.40395328    0.3932824    10.307052    10.307052            0            0            0            0            0         9420            0            0            0 
-Loop time of 0.465473 on 16 procs for 71 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     400    398.15351   -205544.87    20.470689           93   0.34589451   0.39828754    6.0138739    703.62325  0.049952465   0.94776891    4.0779385      92.0375   0.39894967   0.40395328    0.3932824    10.307052    10.307052            0            0            0            0            0         8000            0            0            0 
-     500    400.29399   -205544.98    17.051242           83   0.42140172   0.39805251    6.0138739    703.62325  0.056986933    1.0907861    4.0779385       91.986   0.39879563   0.40493836   0.39165573    10.307052    10.307052            0            0            0            0            0        10000            0            0            0 
-Loop time of 0.579188 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     500    400.29399   -205544.98    17.051242           83   0.42140172   0.39805251    6.0138739    703.62325  0.056986933    1.0907861    4.0779385       91.986   0.39879563   0.40493836   0.39165573    10.307052    10.307052            0            0            0            0            0        10000            0            0            0 
-     577    400.29399   -206534.96    17.051242           83   0.42140172   0.39805251    6.0138739    703.62325  0.056986933    1.0910651    4.0779385    79.710572    0.3455768   0.40493836   0.39165573    10.307052    10.307052            0            0            0            0            0        11540            0            0            0 
-Loop time of 0.502193 on 16 procs for 77 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     500    400.29399   -205544.98    17.051107           83   0.42140172   0.39805251    6.0138739    703.62325  0.056986933    1.0910651    4.0779385       91.986   0.39879563   0.40493836   0.39165573    10.307052    10.307052            0            0            0            0            0        10000            0            0            0 
-     600    400.96099   -205544.56    20.904479           91   0.41219484   0.39780769    6.0138739    703.62325  0.061331691    1.1358732    4.0779385    92.013333   0.39864794   0.40593806   0.39067432    10.307052    10.307052            0            0            0            0            0        12000            0            0            0 
-Loop time of 0.694955 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     600    400.96099   -205544.56    20.904479           91   0.41219484   0.39780769    6.0138739    703.62325  0.061331691    1.1358732    4.0779385    92.013333   0.39864794   0.40593806   0.39067432    10.307052    10.307052            0            0            0            0            0        12000            0            0            0 
-     680    400.96099   -206534.96    20.904479           91   0.41219484   0.39780769    6.0138739    703.62325  0.061331691    1.1358732    4.0779385    81.188235   0.35174818   0.40593806   0.39067432    10.307052    10.307052            0            0            0            0            0        13600            0            0            0 
-Loop time of 0.529041 on 16 procs for 80 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     600    400.96099   -205544.56    20.904088           91   0.41219484   0.39780769    6.0138739    703.62325  0.061331691    1.1358732    4.0779385    92.013333   0.39864794   0.40593806   0.39067432    10.307052    10.307052            0            0            0            0            0        12000            0            0            0 
-     700    397.78618   -205534.96    20.361513           95   0.54466603   0.39757442    6.0138739    703.62325  0.061146951    1.1853748    4.1995704        92.12   0.39850836   0.40693553   0.38981834    10.307052    10.307052            0            0            0            0            0        14000            0            0            0 
-Loop time of 0.590093 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     700    397.78618   -205534.96    20.361513           95   0.54466603   0.39757442    6.0138739    703.62325  0.061146951    1.2139704    4.1995704        92.12   0.39850836   0.40693553   0.38981834    10.307052    10.307052            0            0            0            0            0        14000            0            0            0 
-     790    397.78618   -206534.96    20.361513           95   0.54466603   0.39757442    6.0138739    703.62325  0.061146951    2.2107138    4.1995704    81.625316   0.35310868   0.40693553   0.38981834    10.307052    10.307052            0            0            0            0            0        15800            0            0            0 
-Loop time of 0.594281 on 16 procs for 90 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     700    397.78618   -205534.96    20.236364           94   0.51088027   0.39757442    6.0138739    703.62325  0.061146951    2.2107138     4.205089        92.12   0.39850836   0.40693553   0.38981834    10.307052    10.307052            0            0            0            0            0        14000            1            2            6 
-     800    399.66919   -205547.44    21.285461           94   0.56079766   0.39739855    6.0138739    703.62325   0.06556778    2.2107138    4.3041291     92.36625    0.3983806   0.40793368      0.38875    10.307052    10.385797            0            0            0            0            0        16000            1            2            6 
-Loop time of 0.583824 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     800    399.66919   -205547.44    21.285461           94   0.56079766   0.39739855    6.0138739    703.62325   0.06556778    2.2107138    4.3041291     92.36625    0.3983806   0.40793368      0.38875    10.307052    10.385797            0            0            0            0            0        16000            1            2            6 
-     872    399.66919   -206535.54    21.285461           94   0.56079766   0.39739855    6.0138739    703.62325   0.06556778    2.3177682    4.3041291    84.739679   0.36548679   0.40793368      0.38875    10.307052    10.385797            0            0            0            0            0        17440            1            2            6 
-Loop time of 0.46886 on 16 procs for 72 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     800    399.66919   -205547.44      21.2852           94   0.44964213   0.39739855    6.0138739    703.62325   0.06556778    2.3177682    4.3041291     92.36625    0.3983806   0.40793368      0.38875    10.307052    10.385797            0            0            0            0            0        16000            2            4           13 
-     900     401.5853   -205544.22    19.308189           94   0.47610389   0.39719191    6.0138739    703.62325  0.066991886    2.3177682    4.3041291    92.017778   0.39825974   0.40893337    0.3878576    10.307052    10.385797            0            0            0            0            0        18000            2            4           13 
-Loop time of 0.585137 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     900     401.5853   -205544.22    19.308189           94   0.47610389   0.39719191    6.0138739    703.62325  0.066991886    2.3177682    4.3041291    92.017778   0.39825974   0.40893337    0.3878576    10.307052    10.385797            0            0            0            0            0        18000            2            4           13 
-     975     401.5853   -206535.54    19.308189           94   0.47610389   0.39719191    6.0138739    703.62325  0.066991886    2.3177682    4.3041291    84.939487   0.36762438   0.40893337    0.3878576    10.307052    10.385797            0            0            0            0            0        19500            2            4           13 
-Loop time of 0.502012 on 16 procs for 75 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-     900     401.5853   -205544.22    19.307938           94   0.47610389   0.39719191    6.0138739    703.62325  0.066991886    2.3177682    4.3041291    92.017778   0.39825974   0.40893337    0.3878576    10.307052    10.385797            0            0            0            0            0        18000            2            4           13 
-    1000    395.06218   -205526.35    17.514295           91   0.42044925   0.39716259    6.0138739    703.62325  0.067937867    2.3177682    4.3041291       92.511   0.39814962   0.40993184    0.3867545    10.307052    10.385797            0            0            0            0            0        20000            2            4           13 
-Loop time of 0.588597 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1000    395.06218   -205526.35    17.514295           91   0.42044925   0.39716259    6.0138739    703.62325  0.067937867    2.3177682    4.3041291       92.511   0.39814962   0.40993184    0.3867545    10.307052    10.385797            0            0            0            0            0        20000            2            4           13 
-    1083    395.06218   -206535.54    17.514295           91   0.42044925   0.39716259    6.0138739    703.62325  0.067937867    2.3177682    4.3041291    85.421053   0.36763584   0.40993184    0.3867545    10.307052    10.385797            0            0            0            0            0        21660            2            4           13 
-Loop time of 0.543222 on 16 procs for 83 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1000    395.06218   -205526.35    17.514191           91   0.42044925   0.39716259    6.0138739    703.62325  0.067937867    2.3177682    4.3041291       92.511   0.39814962   0.40993184    0.3867545    10.307052    10.385797            0            0            0            0            0        20000            2            4           13 
-    1100    400.04484   -205545.92     19.52012           89   0.58919981   0.39704631    6.0138739    703.62325  0.069136967    2.3177682    4.4265979    92.517273   0.39805636   0.41093134   0.38574293    10.307052    10.385797            0            0            0            0            0        22000            2            4           13 
-Loop time of 0.590075 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1100    400.04484   -205545.92     19.52012           89   0.58919981   0.39704631    6.0138739    703.62325  0.069136967    2.3177682    4.4265979    92.517273   0.39805636   0.41093134   0.38574293    10.307052    10.385797            0            0            0            0            0        22000            2            4           13 
-    1177    400.04484   -206535.53     19.52012           89   0.58919981   0.39704631    6.0138739    703.62325  0.069136967    2.3177682    4.4265979    86.464741   0.37201529   0.41093134   0.38574293    10.307052    10.385797            0            0            0            0            0        23540            2            4           13 
-Loop time of 0.500839 on 16 procs for 77 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1100    400.04484   -205545.92    19.518413           89     0.429675   0.39705701    6.0137119     703.6043  0.069136967    2.3177682    4.4265979    92.517273   0.39805636   0.41093134   0.38574293    10.307052    10.385797            0            0            0            0            0        22000            3            6           19 
-    1200     400.7462    -205543.2    21.169548           91   0.32511134   0.39679665    6.0137119     703.6043   0.06750442    2.3177682    4.4265979    92.376667   0.39796198   0.41191655    0.3846039    10.307052    10.385797            0            0            0            0            0        24000            3            6           19 
-Loop time of 0.583971 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1200     400.7462    -205543.2    21.169548           91   0.32511134   0.39679665    6.0137119     703.6043   0.06750442    2.3177682    4.4265979    92.376667   0.39796198   0.41191655    0.3846039    10.307052    10.385797            0            0            0            0            0        24000            3            6           19 
-    1277     400.7462   -206535.53    21.169548           91   0.32511134   0.39679665    6.0137119     703.6043   0.06750442    2.3177682    4.4265979    86.806578   0.37396584   0.41191655    0.3846039    10.307052    10.385797            0            0            0            0            0        25540            3            6           19 
-Loop time of 0.509118 on 16 procs for 77 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1200     400.7462    -205543.2    21.169281           91   0.32511134   0.39679665    6.0137119     703.6043   0.06750442    2.3177682    4.4265979    92.376667   0.39796198   0.41191655    0.3846039    10.307052    10.385797            0            0            0            0            0        24000            3            6           19 
-    1300    398.53702   -205539.33     21.35815           94   0.38773898   0.39659935    6.0137119     703.6043  0.067808168    2.3177682    4.4265979    92.500769   0.39786514   0.41289519    0.3846039    10.307052    10.385797            0            0            0            0            0        26000            3            6           19 
-Loop time of 0.587306 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1300    398.53702   -205539.33     21.35815           94   0.38773898   0.39659935    6.0137119     703.6043  0.067808168    2.3177682    4.4265979    92.500769   0.39786514   0.41289519    0.3846039    10.307052    10.385797            0            0            0            0            0        26000            3            6           19 
-    1375    398.53702   -206535.53     21.35815           94   0.38773898   0.39659935    6.0137119     703.6043  0.067808168    2.3177682    4.4265979    87.455273   0.37616341   0.41289519    0.3846039    10.307052    10.385797            0            0            0            0            0        27500            3            6           19 
-Loop time of 0.483781 on 16 procs for 75 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1300    398.53702   -205539.33     21.35787           94   0.38773898   0.39659935    6.0137119     703.6043  0.067808168    2.3177682    4.4265979    92.500769   0.39786514   0.41289519    0.3846039    10.307052    10.385797            0            0            0            0            0        26000            3            6           19 
-    1400    402.80537    -205549.3    19.481887           95   0.32554201   0.39648737    6.0137119     703.6043  0.069550538    2.3177682    4.4265979    92.666429   0.39776836   0.41389491   0.38420043    10.307052    10.385797            0            0            0            0            0        28000            3            6           19 
-Loop time of 0.586411 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1400    402.80537    -205549.3    19.481887           95   0.32554201   0.39648737    6.0137119     703.6043  0.069550538    2.3177682    4.4265979    92.666429   0.39776836   0.41389491   0.38420043    10.307052    10.385797            0            0            0            0            0        28000            3            6           19 
-    1471    402.80537   -206535.53    19.481887           95   0.32554201   0.39648737    6.0137119     703.6043  0.069550538    2.3177682    4.4265979    88.193746   0.37856948   0.41389491   0.38420043    10.307052    10.385797            0            0            0            0            0        29420            3            6           19 
-Loop time of 0.473799 on 16 procs for 71 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1400    402.80537    -205549.3    19.481632           95   0.32554201   0.39648737    6.0137119     703.6043  0.069550538    2.3177682    4.4265979    92.666429   0.39776836   0.41389491   0.38420043    10.307052    10.385797            0            0            0            0            0        28000            3            6           19 
-    1500     402.0803    -205537.7    20.903964           99    0.3340498   0.39635609    6.0137119     703.6043  0.070409086    2.3177682    4.4265979    92.857333   0.39767858   0.41489448   0.38372784    10.333041    10.385797            0            0            0            0            0        30000            3            6           19 
-Loop time of 0.587342 on 16 procs for 100 steps with 37048 atoms
-
-Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] f_HL[22] f_HL[23] 
-    1500     402.0803    -205537.7    20.903964           99    0.3340498   0.39635609    6.0137119     703.6043  0.070409086    2.3177682    4.4265979    92.857333   0.39767858   0.41489448   0.38372784    10.333041    10.385797            0            0            0            0            0        30000            3            6           19 
-    1574     402.0803   -206535.53    20.903964           99    0.3340498   0.39635609    6.0137119     703.6043  0.070409086    2.3177682    4.4265979    88.491741   0.37898213   0.41489448   0.38372784    10.333041    10.385797            0            0            0            0            0        31480            3            6           19 
-Loop time of 0.493982 on 16 procs for 74 steps with 37048 atoms
-
-Final hyper stats ...
-
-Cummulative quantities for fix hyper:
-  hyper time = 30000
-  event timesteps = 3
-  # of atoms in events = 6
-Quantities for this hyper run:
-  event timesteps = 3
-  # of atoms in events = 6
-  max length of any bond = 4.4266
-  max drift distance of any atom = 2.31777
-  fraction of steps & bonds with zero bias = 0.0704091
-Current quantities:
-  ave bonds/atom = 6.01371
-Cummulative quantities specific tofix hyper/local:
-  # of new bonds formed = 19
-  max bonds/atom = 13
-Quantities for this hyper run specific to fix hyper/local:
-  ave boosted bonds/step = 92.8573
-  ave boost coeff of all bonds = 0.397679
-  max boost coeff of any bond = 0.414894
-  min boost coeff of any bond = 0.383728
-  max dist from my box of any non-maxstrain bond ghost atom = 10.333
-  max dist from my box of any bond ghost atom = 10.3858
-  count of ghost bond neighbors not found on reneighbor steps = 0
-  lost bond partners = 0
-  ave bias coeff for lost bond partners = 0
-  bias overlaps = 0
-  non-matching bias coeffs = 0
-  CPU time for bond builds = 0.044807
-Current quantities specific to fix hyper/local:
-  neighbor bonds/bond = 703.604
-  ave boost coeff for all bonds = 0.396356
-
-Loop time of 17.9972 on 16 procs for 1500 steps with 37048 atoms
-
-Performance: 36.006 ns/day, 0.667 hours/ns, 83.346 timesteps/s
-120.7% CPU use with 16 MPI tasks x no OpenMP threads
-
-Hyper stats:
-  Dynamics time (%) = 8.87027 (49.2869)
-  Quench   time (%) = 8.15972 (45.3388)
-  Other    time (%) = 1.2212 (6.78552)
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 11.6       | 11.848     | 12.043     |   3.9 | 65.83
-Neigh   | 0.50025    | 0.52638    | 0.55163    |   2.1 |  2.92
-Comm    | 0.34528    | 0.49905    | 0.66742    |  13.3 |  2.77
-Output  | 0.0021305  | 0.0021461  | 0.0022686  |   0.1 |  0.01
-Modify  | 3.7498     | 3.9009     | 3.9786     |   2.8 | 21.67
-Other   |            | 1.221      |            |       |  6.79
-
-Nlocal:    2315.5 ave 2361 max 2267 min
-Histogram: 1 1 0 4 2 1 3 3 0 1
-Nghost:    3187.88 ave 3236 max 3141 min
-Histogram: 1 0 3 2 2 1 4 1 1 1
-Neighs:    53950.6 ave 54989 max 53049 min
-Histogram: 2 0 3 2 1 2 4 1 0 1
-FullNghs:  542951 ave 554654 max 533224 min
-Histogram: 1 2 3 1 2 2 2 2 0 1
-
-Total # of neighbors = 8687214
-Ave neighs/atom = 234.485
-Neighbor list builds = 165
-Dangerous builds = 0
-Total wall time: 0:00:22
diff --git a/examples/hyper/log.25Mar19.hyper.global.g++.4 b/examples/hyper/log.25Mar19.hyper.global.g++.4
new file mode 100644
index 0000000000..6a066d0d66
--- /dev/null
+++ b/examples/hyper/log.25Mar19.hyper.global.g++.4
@@ -0,0 +1,1250 @@
+LAMMPS (28 Feb 2019)
+# 3d EAM surface for global HD
+
+# nearest neighbor distance = a * sqrt(2)/2 = 2.77 Angs for Pt with a = 3.92
+# hop event on (100) surface is same distance
+# exchange event is 2 atoms moving same distance
+
+variable        Tequil index 500.0
+variable        Vmax index 0.5
+variable        qfactor index 0.3
+variable        cutbond index 3.2
+variable        cutevent index 1.1
+variable        steps index 100000
+variable        nevent index 1000
+variable        zoom index 1.8
+variable        seed index 826626413
+variable        tol index 1.0e-15
+
+units           metal
+atom_style	atomic
+atom_modify     map array
+boundary        p p p
+
+lattice		fcc 3.92
+Lattice spacing in x,y,z = 3.92 3.92 3.92
+region		box block 0 6 0 6 0 4
+create_box	3 box
+Created orthogonal box = (0 0 0) to (23.52 23.52 15.68)
+  2 by 2 by 1 MPI processor grid
+create_atoms	1 box
+Created 576 atoms
+  Time spent = 0.000785828 secs
+
+mass            * 1.0
+
+change_box      all z final -0.1 5.0 boundary p p f
+  orthogonal box = (0 0 -0.392) to (23.52 23.52 19.6)
+create_atoms    2 single 3.5 3.5 4
+Created 1 atoms
+  Time spent = 5.79357e-05 secs
+
+# define frozen substrate and mobile atoms
+
+group           adatom type 2
+1 atoms in group adatom
+region          base block INF INF INF INF 0 1.8
+set             region base type 3
+  288 settings made for type
+group           base type 3
+288 atoms in group base
+group           mobile type 1 2
+289 atoms in group mobile
+
+# pair style
+
+pair_style	eam/alloy
+pair_coeff	* * ptvoterlammps.eam Pt Pt Pt
+
+neighbor	0.5 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 mobile nve
+fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 ${seed} zero yes
+fix		2 mobile langevin 500.0 ${Tequil} 1.0 ${seed} zero yes
+fix		2 mobile langevin 500.0 500.0 1.0 ${seed} zero yes
+fix		2 mobile langevin 500.0 500.0 1.0 826626413 zero yes
+
+timestep	0.005
+
+compute         tmobile mobile temp
+
+thermo		100
+thermo_modify   temp tmobile
+WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:487)
+
+# thermal equilibration
+
+run             1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.07583
+  ghost atom cutoff = 6.07583
+  binsize = 3.03792, bins = 8 8 7
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair eam/alloy, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.327 | 3.327 | 3.327 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0            0   -3213.9136            0   -3213.9136   -51843.125 
+     100    223.70164   -3209.0653            0   -3200.7375    -26575.84 
+     200    345.18355   -3206.1371            0   -3193.2869   -42327.268 
+     300    411.05681   -3203.8465            0   -3188.5442   -32455.226 
+     400    446.05938   -3202.2976            0   -3185.6922   -35377.683 
+     500    435.52439   -3200.2131            0   -3183.9999   -31477.028 
+     600    474.70282   -3199.4049            0   -3181.7332   -34761.287 
+     700    492.00191   -3201.1592            0   -3182.8435   -33036.989 
+     800    440.88631     -3198.37            0   -3181.9572   -34669.762 
+     900    475.14414   -3198.5845            0   -3180.8964   -31191.883 
+    1000    476.87852   -3197.3442            0   -3179.5914   -33731.074 
+Loop time of 0.339602 on 4 procs for 1000 steps with 577 atoms
+
+Performance: 1272.077 ns/day, 0.019 hours/ns, 2944.623 timesteps/s
+98.7% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.25294    | 0.26196    | 0.27409    |   1.5 | 77.14
+Neigh   | 0.017554   | 0.018856   | 0.020498   |   0.8 |  5.55
+Comm    | 0.027196   | 0.040838   | 0.050409   |   4.2 | 12.03
+Output  | 0.00025296 | 0.0002721  | 0.00030828 |   0.0 |  0.08
+Modify  | 0.013425   | 0.014212   | 0.014999   |   0.5 |  4.18
+Other   |            | 0.00346    |            |       |  1.02
+
+Nlocal:    144.25 ave 147 max 141 min
+Histogram: 1 0 0 1 0 0 0 0 1 1
+Nghost:    527.5 ave 533 max 523 min
+Histogram: 1 0 0 0 2 0 0 0 0 1
+Neighs:    3477.25 ave 3585 max 3399 min
+Histogram: 1 0 1 0 1 0 0 0 0 1
+
+Total # of neighbors = 13909
+Ave neighs/atom = 24.1057
+Neighbor list builds = 91
+Dangerous builds = 0
+reset_timestep  0
+
+# pin base so will not move during quenches
+
+fix             freeze base setforce 0.0 0.0 0.0
+
+# event detection
+
+compute         event all event/displace ${cutevent}
+compute         event all event/displace 1.1
+
+# hyper/global
+
+fix             HG mobile hyper/global ${cutbond} ${qfactor} ${Vmax} ${Tequil}
+fix             HG mobile hyper/global 3.2 ${qfactor} ${Vmax} ${Tequil}
+fix             HG mobile hyper/global 3.2 0.3 ${Vmax} ${Tequil}
+fix             HG mobile hyper/global 3.2 0.3 0.5 ${Tequil}
+fix             HG mobile hyper/global 3.2 0.3 0.5 500.0
+
+# thermo output
+
+thermo_style    custom step temp pe f_HG f_HG[*]
+WARNING: New thermo_style command, previous thermo_modify settings will be lost (../output.cpp:705)
+
+thermo_modify   lost ignore
+thermo_modify   temp tmobile
+WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:487)
+
+thermo          ${nevent}
+thermo          1000
+
+# dump output options
+
+region          substrate block INF INF INF INF 1.8 3.8
+region          adatoms block INF INF INF INF 3.8 INF
+variable        acolor atom rmask(base)+2*rmask(substrate)+3*rmask(adatoms)
+
+dump		1 all image 1000000 global.*.jpg v_acolor type 		zoom ${zoom} adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
+dump		1 all image 1000000 global.*.jpg v_acolor type 		zoom 1.8 adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
+dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
+
+# run
+
+hyper           ${steps} ${nevent} HG event min ${tol} ${tol} 1000 1000 dump 1
+hyper           100000 ${nevent} HG event min ${tol} ${tol} 1000 1000 dump 1
+hyper           100000 1000 HG event min ${tol} ${tol} 1000 1000 dump 1
+hyper           100000 1000 HG event min 1.0e-15 ${tol} 1000 1000 dump 1
+hyper           100000 1000 HG event min 1.0e-15 1.0e-15 1000 1000 dump 1
+WARNING: Resetting reneighboring criteria during hyper (../hyper.cpp:133)
+Neighbor list info ...
+  update every 1 steps, delay 0 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.07583
+  ghost atom cutoff = 6.07583
+  binsize = 3.03792, bins = 8 8 7
+  2 neighbor lists, perpetual/occasional/extra = 1 1 0
+  (1) pair eam/alloy, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+  (2) fix hyper/global, occasional, copy from (1)
+      attributes: half, newton on
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 6.015 | 6.015 | 6.015 Mbytes
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+       0    476.87852   -3197.3442            0            0            0            0            0            0            0            0            0            0            0            0            0 
+      53    476.87852   -3217.9192            0            0            0            0            0            0            0            0            0            0            0            0            0 
+Loop time of 0.0358047 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+       0    476.87852   -3197.3442   0.33187212    2213.7063   0.17396269          129          131    6.0069324            0            0            0    3.3552688            0            0            0 
+    1000    487.34979   -3198.3697   0.19401776    90.283981   0.23468448          543          548    6.0069324        0.165            0            0    3.9974111    6134.6092            0            0 
+Loop time of 0.342707 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    1000    487.34979   -3198.3697   0.19401776    90.283981   0.23468448          543          548    6.0069324        0.165            0            0    3.9974111    6134.6092            0            0 
+    1059    487.34979   -3217.9192   0.19401776    90.283981   0.23468448          543          548    6.0069324   0.15580737            0            0    3.9974111    6134.6092            0            0 
+Loop time of 0.0359111 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    1000    487.34979   -3198.3697   0.19401776    90.283981   0.23468448          543          548    6.0069324        0.165            0            0    3.9974111    6134.6092            0            0 
+    2000    522.93873   -3197.4748    0.1540961    35.745265   0.24952495          120          131    6.0069324       0.1645            0            0    4.0370436    10213.644            0            0 
+Loop time of 0.305975 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    2000    522.93873   -3197.4748    0.1540961    35.745265   0.24952495          120          131    6.0069324       0.1645            0            0    4.0370436    10213.644            0            0 
+    2057    522.93873   -3217.9192    0.1540961    35.745265   0.24952495          120          131    6.0069324   0.15994166            0            0    4.0370436    10213.644            0            0 
+Loop time of 0.0335248 on 4 procs for 57 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    2000    522.93873   -3197.4748    0.1540961    35.745265   0.24952495          120          131    6.0069324       0.1645            0            0    4.0370436    10213.644            0            0 
+    3000     485.3853   -3198.0446  0.081070047     6.563707   0.27460406          120          131    6.0069324        0.145            0            0    4.0370436    13331.739            0            0 
+Loop time of 0.269706 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    3000     485.3853   -3198.0446  0.081070047     6.563707   0.27460406          120          131    6.0069324        0.145            0            0    4.0370436    13331.739            0            0 
+    3059     485.3853   -3217.9192  0.081070047     6.563707   0.27460406          120          131    6.0069324   0.14220333            0            0    4.0370436    13331.739            0            0 
+Loop time of 0.0265908 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    3000     485.3853   -3198.0446  0.081070047     6.563707   0.27460406          120          131    6.0069324        0.145            0            0    4.0370436    13331.739            0            0 
+    4000    522.88476   -3199.0496  0.020170911    1.5970319   0.29388643          548          555    6.0069324      0.17575            0            0    4.0370436    14355.723            0            0 
+Loop time of 0.229504 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    4000    522.88476   -3199.0496  0.020170911    1.5970319   0.29388643          548          555    6.0069324      0.17575            0            0    4.0370436    14355.723            0            0 
+    4060    522.88476   -3217.9192  0.020170911    1.5970319   0.29388643          548          555    6.0069324   0.17315271            0            0    4.0370436    14355.723            0            0 
+Loop time of 0.0280094 on 4 procs for 60 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    4000    522.88476   -3199.0496  0.020170911    1.5970319   0.29388643          548          555    6.0069324      0.17575            0            0    4.0370436    14355.723            0            0 
+    5000    462.24647   -3197.3076   0.11575138    14.679837   0.26299192          130          132    6.0069324       0.1664            0            0    4.0370436    19342.466            0            0 
+Loop time of 0.234847 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    5000    462.24647   -3197.3076   0.11575138    14.679837   0.26299192          130          132    6.0069324       0.1664            0            0    4.0370436    19342.466            0            0 
+    5054    462.24647   -3217.9192   0.11575138    14.679837   0.26299192          130          132    6.0069324   0.16462208            0            0    4.0370436    19342.466            0            0 
+Loop time of 0.026547 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    5000    462.24647   -3197.3076   0.11575138    14.679837   0.26299192          130          132    6.0069324       0.1664            0            0    4.0370436    19342.466            0            0 
+    6000    463.33022   -3196.1897   0.37378421    5855.6457   0.15072771          122          123    6.0069324   0.15583333            0            0    4.0370436    22854.021            0            0 
+Loop time of 0.244725 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    6000    463.33022   -3196.1897   0.37378421    5855.6457   0.15072771          122          123    6.0069324   0.15583333            0            0    4.0370436    22854.021            0            0 
+    6054    463.33022   -3217.9192   0.37378421    5855.6457   0.15072771          122          123    6.0069324   0.15444334            0            0    4.0370436    22854.021            0            0 
+Loop time of 0.0267512 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    6000    463.33022   -3196.1897   0.37378421    5855.6457   0.15072771          122          123    6.0069324   0.15583333            0            0    4.0370436    22854.021            0            0 
+    7000    496.34089   -3198.1795   0.29031005    843.70994   0.19427864          547          552    6.0069324   0.14885714            0            0    4.1079381    27854.511            0            0 
+Loop time of 0.229727 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    7000    496.34089   -3198.1795   0.29031005    843.70994   0.19427864          547          552    6.0069324   0.14885714            0            0    4.1079381    27854.511            0            0 
+    7055    496.34089   -3217.9192   0.29031005    843.70994   0.19427864          547          552    6.0069324   0.14769667            0            0    4.1079381    27854.511            0            0 
+Loop time of 0.0260235 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    7000    496.34089   -3198.1795   0.29031005    843.70994   0.19427864          547          552    6.0069324   0.14885714            0            0    4.1079381    27854.511            0            0 
+    8000    468.63017   -3197.6685            0            1   0.31412476          275          556    6.0069324      0.14075      0.00175            0    4.1079381    31930.231            0            0 
+Loop time of 0.230083 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    8000    468.63017   -3197.6685            0            1   0.31412476          275          556    6.0069324      0.14075      0.00175            0    4.1079381    31930.231            0            0 
+    8056    468.63017   -3217.9192            0            1   0.31412476          275          556    6.0069324    0.1397716 0.0017378352            0    4.1079381    31930.231            0            0 
+Loop time of 0.0261552 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    8000    468.63017   -3197.6685            0            1   0.31412476          275          556    6.0069324      0.14075      0.00175            0    4.1079381    31930.231            0            0 
+    9000    467.53307   -3198.3982            0            1    0.3075376          543          544    6.0069324   0.14888889 0.0015555556            0    4.1079381    35292.432            0            0 
+Loop time of 0.22948 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    9000    467.53307   -3198.3982            0            1    0.3075376          543          544    6.0069324   0.14888889 0.0015555556            0    4.1079381    35292.432            0            0 
+    9051    467.53307   -3217.9192            0            1    0.3075376          543          544    6.0069324   0.14804994 0.0015467904            0    4.1079381    35292.432            0            0 
+Loop time of 0.0240657 on 4 procs for 51 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+    9000    467.53307   -3198.3982            0            1    0.3075376          543          544    6.0069324   0.14888889 0.0015555556            0    4.1079381    35292.432            0            0 
+   10000    496.73768   -3197.9106   0.11921512    15.908682   0.26180389          543          548    6.0069324       0.1531       0.0014            0    4.1079381    40303.236            0            0 
+Loop time of 0.237951 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   10000    496.73768   -3197.9106   0.11921512    15.908682   0.26180389          543          548    6.0069324       0.1531       0.0014            0    4.1079381    40303.236            0            0 
+   10061    496.73768   -3217.9192   0.11921512    15.908682   0.26180389          543          548    6.0069324   0.15217175 0.0013915118            0    4.1079381    40303.236            0            0 
+Loop time of 0.0275102 on 4 procs for 61 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   10000    496.73768   -3197.9106   0.11921512    15.908682   0.26180389          543          548    6.0069324       0.1531       0.0014            0    4.1079381    40303.236            0            0 
+   11000    526.76049   -3199.3263   0.24399827    287.99939   0.21466325          408          419    6.0069324   0.15945455 0.0012727273            0    4.1079381    42710.668            0            0 
+Loop time of 0.226262 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   11000    526.76049   -3199.3263   0.24399827    287.99939   0.21466325          408          419    6.0069324   0.15945455 0.0012727273            0    4.1079381    42710.668            0            0 
+   11058    526.76049   -3217.9192   0.24399827    287.99939   0.21466325          408          419    6.0069324   0.15861819 0.0012660517            0    4.1079381    42710.668            0            0 
+Loop time of 0.0257103 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   11000    526.76049   -3199.3263   0.24399827    287.99939   0.21466325          408          419    6.0069324   0.15945455 0.0012727273            0    4.1079381    42710.668            0            0 
+   12000    488.24107   -3198.2441   0.34073209    2719.0951   0.16931693          409          400    6.0069324   0.15558333 0.0011666667            0    4.1079381    47154.117            0            0 
+Loop time of 0.226415 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   12000    488.24107   -3198.2441   0.34073209    2719.0951   0.16931693          409          400    6.0069324   0.15558333 0.0011666667            0    4.1079381    47154.117            0            0 
+   12053    488.24107   -3217.9192   0.34073209    2719.0951   0.16931693          409          400    6.0069324    0.1548992 0.0011615365            0    4.1079381    47154.117            0            0 
+Loop time of 0.0232868 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   12000    488.24107   -3198.2441   0.34073209    2719.0951   0.16931693          409          400    6.0069324   0.15558333 0.0011666667            0    4.1079381    47154.117            0            0 
+   13000    467.87203   -3197.0681            0            1   0.32542353          275          556    6.0069324   0.14869231 0.0015384615            0    4.1079381    54700.864            0            0 
+Loop time of 0.234386 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   13000    467.87203   -3197.0681            0            1   0.32542353          275          556    6.0069324   0.14869231 0.0015384615            0    4.1079381    54700.864            0            0 
+   13055    467.87203   -3217.9192            0            1   0.32542353          275          556    6.0069324   0.14806588 0.0015319801            0    4.1079381    54700.864            0            0 
+Loop time of 0.0268174 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   13000    467.87203   -3197.0681            0            1   0.32542353          275          556    6.0069324   0.14869231 0.0015384615            0    4.1079381    54700.864            0            0 
+   14000    494.97859   -3197.9767  0.061678009    4.1849114    0.2808878          544          555    6.0069324   0.16885714 0.0014285714            0    4.1079381    55284.212            0            0 
+Loop time of 0.236772 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   14000    494.97859   -3197.9767  0.061678009    4.1849114    0.2808878          544          555    6.0069324   0.16885714 0.0014285714            0    4.1079381    55284.212            0            0 
+   14059    494.97859   -3217.9192  0.061678009    4.1849114    0.2808878          544          555    6.0069324   0.16814852 0.0014225763            0    4.1079381    55284.212            0            0 
+Loop time of 0.0262685 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   14000    494.97859   -3197.9767  0.061678009    4.1849114    0.2808878          544          555    6.0069324   0.16885714 0.0014285714            0    4.1079381    55284.212            0            0 
+   15000    487.47593   -3196.3193            0            1   0.30681413          124          135    6.0069324   0.16526667 0.0013333333            0    4.1079381    58845.637            0            0 
+Loop time of 0.228132 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   15000    487.47593   -3196.3193            0            1   0.30681413          124          135    6.0069324   0.16526667 0.0013333333            0    4.1079381    58845.637            0            0 
+   15056    487.47593   -3217.9192            0            1   0.30681413          124          135    6.0069324   0.16465197 0.0013283741            0    4.1079381    58845.637            0            0 
+Loop time of 0.0253892 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   15000    487.47593   -3196.3193            0            1   0.30681413          124          135    6.0069324   0.16526667 0.0013333333            0    4.1079381    58845.637            0            0 
+   16000    514.29619   -3198.6976   0.15192442    33.988268   0.25030702          287          568    6.0069324     0.160375      0.00125            0    4.1079381    65959.225            0            0 
+Loop time of 0.226636 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   16000    514.29619   -3198.6976   0.15192442    33.988268   0.25030702          287          568    6.0069324     0.160375      0.00125            0    4.1079381    65959.225            0            0 
+   16057    514.29619   -3217.9192   0.15192442    33.988268   0.25030702          287          568    6.0069324   0.15980569 0.0012455627            0    4.1079381    65959.225            0            0 
+Loop time of 0.0258105 on 4 procs for 57 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   16000    514.29619   -3198.6976   0.15192442    33.988268   0.25030702          287          568    6.0069324     0.160375      0.00125            0    4.1079381    65959.225            0            0 
+   17000    518.58789   -3197.5021    0.1333678    22.094631   0.25689258          116          123    6.0069324   0.16088235 0.0011764706            0    4.1079381    70525.413            0            0 
+Loop time of 0.233751 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   17000    518.58789   -3197.5021    0.1333678    22.094631   0.25689258          116          123    6.0069324   0.16088235 0.0011764706            0    4.1079381    70525.413            0            0 
+   17052    518.58789   -3217.9192    0.1333678    22.094631   0.25689258          116          123    6.0069324   0.16039174 0.0011728829            0    4.1079381    70525.413            0            0 
+Loop time of 0.0248473 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   17000    518.58789   -3197.5021    0.1333678    22.094631   0.25689258          116          123    6.0069324   0.16088235 0.0011764706            0    4.1079381    70525.413            0            0 
+   18000    505.83228   -3198.9838   0.08205079    6.7148239   0.27428244          552          563    6.0069324   0.15644444 0.0011111111            0    4.1079381    73252.823            0            0 
+Loop time of 0.240134 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   18000    505.83228   -3198.9838   0.08205079    6.7148239   0.27428244          552          563    6.0069324   0.15644444 0.0011111111            0    4.1079381    73252.823            0            0 
+   18056    505.83228   -3217.9192   0.08205079    6.7148239   0.27428244          552          563    6.0069324   0.15595924  0.001107665            0    4.1079381    73252.823            0            0 
+Loop time of 0.0243995 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   18000    505.83228   -3198.9838   0.08205079    6.7148239   0.27428244          552          563    6.0069324   0.15644444 0.0011111111            0    4.1079381    73252.823            0            0 
+   19000    527.41862   -3198.5008  0.040305357    2.5483534   0.28765437          424          263    6.0069324   0.15589474 0.0010526316            0    4.1079381     75984.28            0            0 
+Loop time of 0.22821 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   19000    527.41862   -3198.5008  0.040305357    2.5483534   0.28765437          424          263    6.0069324   0.15589474 0.0010526316            0    4.1079381     75984.28            0            0 
+   19052    527.41862   -3217.9192  0.040305357    2.5483534   0.28765437          424          263    6.0069324   0.15546924 0.0010497586            0    4.1079381     75984.28            0            0 
+Loop time of 0.0237539 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   19000    527.41862   -3198.5008  0.040305357    2.5483534   0.28765437          424          263    6.0069324   0.15589474 0.0010526316            0    4.1079381     75984.28            0            0 
+   20000    451.64207   -3198.7796  0.047092391    2.9831142   0.28552298          570          403    6.0069324      0.15125        0.001            0    4.1079381    81688.471            0            0 
+Loop time of 0.226179 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   20000    451.64207   -3198.7796  0.047092391    2.9831142   0.28552298          570          403    6.0069324      0.15125        0.001            0    4.1079381    81688.471            0            0 
+   20053    451.64207   -3217.9192  0.047092391    2.9831142   0.28552298          570          403    6.0069324   0.15085025  0.000997357            0    4.1079381    81688.471            0            0 
+Loop time of 0.0244102 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   20000    451.64207   -3198.7796  0.047092391    2.9831142   0.28552298          570          403    6.0069324      0.15125        0.001            0    4.1079381    81688.471            0            0 
+   21000    469.69339   -3200.6427            0            1    0.3308786          267          268    6.0069324   0.14852381 0.00095238095            0    4.1079381    87660.496            0            0 
+Loop time of 0.234504 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   21000    469.69339   -3200.6427            0            1    0.3308786          267          268    6.0069324   0.14852381 0.00095238095            0    4.1079381    87660.496            0            0 
+   21050    469.69339   -3217.9192            0            1    0.3308786          267          268    6.0069324   0.14817102 0.00095011876            0    4.1079381    87660.496            0            0 
+Loop time of 0.0231035 on 4 procs for 50 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   21000    469.69339   -3200.6427            0            1    0.3308786          267          268    6.0069324   0.14852381 0.00095238095            0    4.1079381    87660.496            0            0 
+   22000    473.26326   -3199.3284            0            1   0.31249141          544          555    6.0069324   0.14786364 0.00090909091            0    4.1079381    91920.285            0            0 
+Loop time of 0.235723 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   22000    473.26326   -3199.3284            0            1   0.31249141          544          555    6.0069324   0.14786364 0.00090909091            0    4.1079381    91920.285            0            0 
+   22054    473.26326   -3217.9192            0            1   0.31249141          544          555    6.0069324   0.14750159 0.00090686497            0    4.1079381    91920.285            0            0 
+Loop time of 0.024776 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   22000    473.26326   -3199.3284            0            1   0.31249141          544          555    6.0069324   0.14786364 0.00090909091            0    4.1079381    91920.285            0            0 
+   23000    496.07543   -3198.2605   0.30577111    1207.9075   0.18697914          572          403    6.0069324   0.15665217 0.0011304348            0    4.1079381    92558.536            0            0 
+Loop time of 0.229916 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   23000    496.07543   -3198.2605   0.30577111    1207.9075   0.18697914          572          403    6.0069324   0.15665217 0.0011304348            0    4.1079381    92558.536            0            0 
+   23056    496.07543   -3217.9192   0.30577111    1207.9075   0.18697914          572          403    6.0069324   0.15627169 0.0011276891            0    4.1079381    92558.536            0            0 
+Loop time of 0.0252325 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   23000    496.07543   -3198.2605   0.30577111    1207.9075   0.18697914          572          403    6.0069324   0.15665217 0.0011304348            0    4.1079381    92558.536            0            0 
+   24000    465.43821    -3199.468            0            1   0.31415739          543          544    6.0069324   0.15466667 0.0010833333            0    4.1079381    97530.178            0            0 
+Loop time of 0.231022 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   24000    465.43821    -3199.468            0            1   0.31415739          543          544    6.0069324   0.15466667 0.0010833333            0    4.1079381    97530.178            0            0 
+   24054    465.43821   -3217.9192            0            1   0.31415739          543          544    6.0069324   0.15431945 0.0010809013            0    4.1079381    97530.178            0            0 
+Loop time of 0.0246248 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   24000    465.43821    -3199.468            0            1   0.31415739          543          544    6.0069324   0.15466667 0.0010833333            0    4.1079381    97530.178            0            0 
+   25000    489.80528    -3200.439   0.25812453    399.74019   0.20865662          543          544    6.0069324      0.15368      0.00104            0    4.1079381    103216.01            0            0 
+Loop time of 0.239562 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   25000    489.80528    -3200.439   0.25812453    399.74019   0.20865662          543          544    6.0069324      0.15368      0.00104            0    4.1079381    103216.01            0            0 
+   25060    489.80528   -3217.9192   0.25812453    399.74019   0.20865662          543          544    6.0069324   0.15331205   0.00103751            0    4.1079381    103216.01            0            0 
+Loop time of 0.0290521 on 4 procs for 60 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   25000    489.80528    -3200.439   0.25812453    399.74019   0.20865662          543          544    6.0069324      0.15368      0.00104            0    4.1079381    103216.01            0            0 
+   26000    454.33199   -3197.9264   0.15449017    36.073692   0.24938278          283          272    6.0069324   0.15788462        0.001            0    4.1079381    106857.47            0            0 
+Loop time of 0.231679 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   26000    454.33199   -3197.9264   0.15449017    36.073692   0.24938278          283          272    6.0069324   0.15788462        0.001            0    4.1079381    106857.47            0            0 
+   26053    454.33199   -3217.9192   0.15449017    36.073692   0.24938278          283          272    6.0069324   0.15756343 0.00099796569            0    4.1079381    106857.47            0            0 
+Loop time of 0.0229361 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   26000    454.33199   -3197.9264   0.15449017    36.073692   0.24938278          283          272    6.0069324   0.15788462        0.001            0    4.1079381    106857.47            0            0 
+   27000    493.26662   -3198.8515   0.17523126    58.378293   0.24178166          260          271    6.0069324   0.15388889 0.00096296296            0    4.1079381     114287.4            0            0 
+Loop time of 0.228356 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   27000    493.26662   -3198.8515   0.17523126    58.378293   0.24178166          260          271    6.0069324   0.15388889 0.00096296296            0    4.1079381     114287.4            0            0 
+   27056    493.26662   -3217.9192   0.17523126    58.378293   0.24178166          260          271    6.0069324   0.15357037 0.00096096984            0    4.1079381     114287.4            0            0 
+Loop time of 0.0249045 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   27000    493.26662   -3198.8515   0.17523126    58.378293   0.24178166          260          271    6.0069324   0.15388889 0.00096296296            0    4.1079381     114287.4            0            0 
+   28000    516.59709   -3198.7939  0.017083929     1.486614   0.29483028          543          548    6.0069324   0.15278571 0.00092857143            0    4.1079381    117735.24            0            0 
+Loop time of 0.226666 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   28000    516.59709   -3198.7939  0.017083929     1.486614   0.29483028          543          548    6.0069324   0.15278571 0.00092857143            0    4.1079381    117735.24            0            0 
+   28054    516.59709   -3217.9192  0.017083929     1.486614   0.29483028          543          548    6.0069324   0.15249162 0.00092678406            0    4.1079381    117735.24            0            0 
+Loop time of 0.0245788 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   28000    516.59709   -3198.7939  0.017083929     1.486614   0.29483028          543          548    6.0069324   0.15278571 0.00092857143            0    4.1079381    117735.24            0            0 
+   29000    498.78313   -3197.7551            0            1   0.43523955          543          544    6.0069324   0.15648276 0.00089655172            0    4.3557073    122569.32            0            0 
+Loop time of 0.239195 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   29000    498.78313   -3197.7551            0            1   0.43523955          543          544    6.0069324   0.15648276 0.00089655172            0    4.3557073    122569.32            0            0 
+   29059    498.78313   -3217.9192            0            1   0.43523955          543          544    6.0069324   0.15616504 0.00089473141            0    4.3557073    122569.32            0            0 
+Loop time of 0.0290976 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   29000    498.78313   -3197.7551            0            1   0.43523955          543          544    6.0069324   0.15648276 0.00089655172            0    4.3557073    122569.32            0            0 
+   30000    466.86137   -3199.5233   0.23621441    240.39961   0.21790229          126          127    6.0069324   0.15756667 0.00086666667            0    4.3557073    127229.34            0            0 
+Loop time of 0.232616 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   30000    466.86137   -3199.5233   0.23621441    240.39961   0.21790229          126          127    6.0069324   0.15756667 0.00086666667            0    4.3557073    127229.34            0            0 
+   30059    466.86137   -3217.9192   0.23621441    240.39961   0.21790229          126          127    6.0069324   0.15725739 0.00086496557            0    4.3557073    127229.34            0            0 
+Loop time of 0.0269623 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   30000    466.86137   -3199.5233   0.23621441    240.39961   0.21790229          126          127    6.0069324   0.15756667 0.00086666667            0    4.3557073    127229.34            0            0 
+   31000    471.12992   -3199.7598            0            1   0.30984418          567          572    6.0069324   0.15541935 0.00087096774            0    4.3557073     131258.9            0            0 
+Loop time of 0.229214 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   31000    471.12992   -3199.7598            0            1   0.30984418          567          572    6.0069324   0.15541935 0.00087096774            0    4.3557073     131258.9            0            0 
+   31053    471.12992   -3217.9192            0            1   0.30984418          567          572    6.0069324   0.15515409 0.00086948121            0    4.3557073     131258.9            0            0 
+Loop time of 0.0240388 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   31000    471.12992   -3199.7598            0            1   0.30984418          567          572    6.0069324   0.15541935 0.00087096774            0    4.3557073     131258.9            0            0 
+   32000     510.4372   -3198.4263   0.38770138    8088.2308   0.14217507          511          546    6.0069324   0.15328125   0.00084375            0    4.3557073    136077.46            0            0 
+Loop time of 0.230157 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   32000     510.4372   -3198.4263   0.38770138    8088.2308   0.14217507          511          546    6.0069324   0.15328125   0.00084375            0    4.3557073    136077.46            0            0 
+   32057     510.4372   -3217.9192   0.38770138    8088.2308   0.14217507          511          546    6.0069324    0.1530087 0.00084224974            0    4.3557073    136077.46            0            0 
+Loop time of 0.0259738 on 4 procs for 57 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   32000     510.4372   -3198.4263   0.38770138    8088.2308   0.14217507          511          546    6.0069324   0.15328125   0.00084375            0    4.3557073    136077.46            0            0 
+   33000     517.9664   -3198.8477  0.065094278    4.5302347   0.27979105          136          255    6.0069324   0.15212121 0.00081818182            0    4.3557073    140653.16            0            0 
+Loop time of 0.240719 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   33000     517.9664   -3198.8477  0.065094278    4.5302347   0.27979105          136          255    6.0069324   0.15212121 0.00081818182            0    4.3557073    140653.16            0            0 
+   33055     517.9664   -3217.9192  0.065094278    4.5302347   0.27979105          136          255    6.0069324    0.1518681 0.00081682045            0    4.3557073    140653.16            0            0 
+Loop time of 0.0254009 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   33000     517.9664   -3198.8477  0.065094278    4.5302347   0.27979105          136          255    6.0069324   0.15212121 0.00081818182            0    4.3557073    140653.16            0            0 
+   34000    539.21923   -3197.9619   0.10137745    10.515709   0.26786575          119          400    6.0069324   0.15088235 0.00079411765            0    4.3557073    146106.36            0            0 
+Loop time of 0.228472 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   34000    539.21923   -3197.9619   0.10137745    10.515709   0.26786575          119          400    6.0069324   0.15088235 0.00079411765            0    4.3557073    146106.36            0            0 
+   34053    539.21923   -3217.9192   0.10137745    10.515709   0.26786575          119          400    6.0069324   0.15064752 0.00079288168            0    4.3557073    146106.36            0            0 
+Loop time of 0.0239374 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   34000    539.21923   -3197.9619   0.10137745    10.515709   0.26786575          119          400    6.0069324   0.15088235 0.00079411765            0    4.3557073    146106.36            0            0 
+   35000    495.28481   -3198.2101   0.03728079    2.3756005   0.28859913          543          544    6.0069324   0.14882857 0.00077142857            0    4.3557073    152132.21            0            0 
+Loop time of 0.227014 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   35000    495.28481   -3198.2101   0.03728079    2.3756005   0.28859913          543          544    6.0069324   0.14882857 0.00077142857            0    4.3557073    152132.21            0            0 
+   35061    495.28481   -3217.9192   0.03728079    2.3756005   0.28859913          543          544    6.0069324   0.14856964 0.00077008642            0    4.3557073    152132.21            0            0 
+Loop time of 0.0271087 on 4 procs for 61 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   35000    495.28481   -3198.2101   0.03728079    2.3756005   0.28859913          543          544    6.0069324   0.14882857 0.00077142857            0    4.3557073    152132.21            0            0 
+   36000    522.02047   -3197.5464  0.023049198    1.7073613   0.29300366          132          139    6.0069324      0.14975      0.00075            0    4.3557073    155779.35            0            0 
+Loop time of 0.230395 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   36000    522.02047   -3197.5464  0.023049198    1.7073613   0.29300366          132          139    6.0069324      0.14975      0.00075            0    4.3557073    155779.35            0            0 
+   36058    522.02047   -3217.9192  0.023049198    1.7073613   0.29300366          132          139    6.0069324   0.14950912 0.00074879361            0    4.3557073    155779.35            0            0 
+Loop time of 0.0274341 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   36000    522.02047   -3197.5464  0.023049198    1.7073613   0.29300366          132          139    6.0069324      0.14975      0.00075            0    4.3557073    155779.35            0            0 
+   37000    493.66881   -3198.2972   0.29065621    850.51576   0.19411822          110          121    6.0069324   0.14783784 0.00072972973            0    4.3557073     159446.9            0            0 
+Loop time of 0.239665 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   37000    493.66881   -3198.2972   0.29065621    850.51576   0.19411822          110          121    6.0069324   0.14783784 0.00072972973            0    4.3557073     159446.9            0            0 
+   37055    493.66881   -3217.9192   0.29065621    850.51576   0.19411822          110          121    6.0069324   0.14761841 0.00072864661            0    4.3557073     159446.9            0            0 
+Loop time of 0.0258739 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   37000    493.66881   -3198.2972   0.29065621    850.51576   0.19411822          110          121    6.0069324   0.14783784 0.00072972973            0    4.3557073     159446.9            0            0 
+   38000    471.56021   -3200.0689   0.21390468    143.23918   0.22692985          546          559    6.0069324       0.1505 0.00071052632            0    4.3557073    161793.64            0            0 
+Loop time of 0.231827 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   38000    471.56021   -3200.0689   0.21390468    143.23918   0.22692985          546          559    6.0069324       0.1505 0.00071052632            0    4.3557073    161793.64            0            0 
+   38050    471.56021   -3217.9192   0.21390468    143.23918   0.22692985          546          559    6.0069324   0.15030223 0.00070959264            0    4.3557073    161793.64            0            0 
+Loop time of 0.0234141 on 4 procs for 50 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   38000    471.56021   -3200.0689   0.21390468    143.23918   0.22692985          546          559    6.0069324       0.1505 0.00071052632            0    4.3557073    161793.64            0            0 
+   39000    488.60708   -3198.2279   0.29546108    950.85261   0.19187758          410          412    6.0069324   0.14884615 0.00069230769            0    4.3557073    167145.63            0            0 
+Loop time of 0.227483 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   39000    488.60708   -3198.2279   0.29546108    950.85261   0.19187758          410          412    6.0069324   0.14884615 0.00069230769            0    4.3557073    167145.63            0            0 
+   39062    488.60708   -3217.9192   0.29546108    950.85261   0.19187758          410          412    6.0069324    0.1486099 0.00069120885            0    4.3557073    167145.63            0            0 
+Loop time of 0.028059 on 4 procs for 62 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   39000    488.60708   -3198.2279   0.29546108    950.85261   0.19187758          410          412    6.0069324   0.14884615 0.00069230769            0    4.3557073    167145.63            0            0 
+   40000    507.73002   -3196.8491  0.012490865    1.3362947   0.29622904          543          544    6.0069324      0.15095     0.000675            0    4.3557073    171194.28            0            0 
+Loop time of 0.231293 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   40000    507.73002   -3196.8491  0.012490865    1.3362947   0.29622904          543          544    6.0069324      0.15095     0.000675            0    4.3557073    171194.28            0            0 
+   40064    507.73002   -3217.9192  0.012490865    1.3362947   0.29622904          543          544    6.0069324   0.15070887 0.00067392173            0    4.3557073    171194.28            0            0 
+Loop time of 0.0308156 on 4 procs for 64 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   40000    507.73002   -3196.8491  0.012490865    1.3362947   0.29622904          543          544    6.0069324      0.15095     0.000675            0    4.3557073    171194.28            0            0 
+   41000    479.11448    -3200.241            0            1   0.94094448          542          544    6.0069324   0.16480488 0.00065853659            0    5.4178316    171224.32            0            0 
+Loop time of 0.239781 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   41000    479.11448    -3200.241            0            1   0.94094448          542          544    6.0069324   0.16480488 0.00065853659            0    5.4178316    171224.32            0            0 
+   41055    479.11448   -3217.9192            0            1   0.94094448          542          544    6.0069324   0.16458409 0.00065765437            0    5.4178316    171224.32            0            0 
+Loop time of 0.0248787 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   41000    479.11448    -3200.241   0.31626598    1541.0515   0.18185743          398          404    6.0069324   0.16480488 0.00065853659    2.3326665    5.4178316    171224.32            1            2 
+   42000    495.84675   -3198.6432    0.1729929    55.422961   0.24261343          275          264    6.0069324    0.1692381 0.0011190476    2.3326665    5.4178316    174484.67            1            2 
+Loop time of 0.226913 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   42000    495.84675   -3198.6432    0.1729929    55.422961   0.24261343          275          264    6.0069324    0.1692381 0.0011190476    2.3326665    5.4178316    174484.67            1            2 
+   42056    495.84675   -3217.9192    0.1729929    55.422961   0.24261343          275          264    6.0069324   0.16901274 0.0011175575    2.3326665    5.4178316    174484.67            1            2 
+Loop time of 0.0239749 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   42000    495.84675   -3198.6432    0.1729929    55.422961   0.24261343          275          264    6.0069324    0.1692381 0.0011190476    2.3326665    5.4178316    174484.67            1            2 
+   43000    533.30453   -3198.6415            0            1   0.34377427          263          577    6.0069324   0.17646512 0.0010930233    2.3326665    5.4178316    175038.14            1            2 
+Loop time of 0.224798 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   43000    533.30453   -3198.6415            0            1   0.34377427          263          577    6.0069324   0.17646512 0.0010930233    2.3326665    5.4178316    175038.14            1            2 
+   43054    533.30453   -3217.9192            0            1   0.34377427          263          577    6.0069324   0.17624379 0.0010916523    2.3326665    5.4178316    175038.14            1            2 
+Loop time of 0.0243425 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   43000    533.30453   -3198.6415            0            1   0.34377427          263          577    6.0069324   0.17646512 0.0010930233    2.3326665    5.4178316    175038.14            1            2 
+   44000    497.19886   -3199.3252            0            1   0.32411085          262          264    6.0069324   0.17947727 0.0010681818    2.3326665    5.4178316    175732.69            1            2 
+Loop time of 0.23413 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   44000    497.19886   -3199.3252            0            1   0.32411085          262          264    6.0069324   0.17947727 0.0010681818    2.3326665    5.4178316    175732.69            1            2 
+   44056    497.19886   -3217.9192            0            1   0.32411085          262          264    6.0069324   0.17924914  0.001066824    2.3326665    5.4178316    175732.69            1            2 
+Loop time of 0.0264681 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   44000    497.19886   -3199.3252            0            1   0.32411085          262          264    6.0069324   0.17947727 0.0010681818    2.3326665    5.4178316    175732.69            1            2 
+   45000    501.66497   -3198.3133            0            1   0.89133337          262          264    6.0069324   0.18806667 0.0010444444    2.3326665    5.4178316    175885.32            1            2 
+Loop time of 0.233324 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   45000    501.66497   -3198.3133            0            1   0.89133337          262          264    6.0069324   0.18806667 0.0010444444    2.3326665    5.4178316    175885.32            1            2 
+   45053    501.66497   -3217.9192            0            1   0.89133337          262          264    6.0069324   0.18784543 0.0010432158    2.3326665    5.4178316    175885.32            1            2 
+Loop time of 0.0239007 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   45000    501.66497   -3198.3133   0.31380779    1455.5922   0.18306993          549          547    6.0069324   0.18806667 0.0010444444     2.332667    5.4178316    175885.32            2            4 
+   46000    512.99827   -3198.7869   0.30973921    1324.4339   0.18505929          547          552    6.0069324   0.18545652 0.0010217391     2.332667    5.4178316    180703.66            2            4 
+Loop time of 0.227399 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   46000    512.99827   -3198.7869   0.30973921    1324.4339   0.18505929          547          552    6.0069324   0.18545652 0.0010217391     2.332667    5.4178316    180703.66            2            4 
+   46058    512.99827   -3217.9192   0.30973921    1324.4339   0.18505929          547          552    6.0069324   0.18522298 0.0010204525     2.332667    5.4178316    180703.66            2            4 
+Loop time of 0.025696 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   46000    512.99827   -3198.7869   0.30973921    1324.4339   0.18505929          547          552    6.0069324   0.18545652 0.0010217391     2.332667    5.4178316    180703.66            2            4 
+   47000    508.06284   -3198.0819   0.17828926     62.67216   0.24064067          271          544    6.0069324   0.18404255        0.001     2.332667    5.4178316    186245.92            2            4 
+Loop time of 0.232521 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   47000    508.06284   -3198.0819   0.17828926     62.67216   0.24064067          271          544    6.0069324   0.18404255        0.001     2.332667    5.4178316    186245.92            2            4 
+   47062    508.06284   -3217.9192   0.17828926     62.67216   0.24064067          271          544    6.0069324   0.18380009 0.00099868259     2.332667    5.4178316    186245.92            2            4 
+Loop time of 0.0288792 on 4 procs for 62 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   47000    508.06284   -3198.0819   0.17828926     62.67216   0.24064067          271          544    6.0069324   0.18404255        0.001     2.332667    5.4178316    186245.92            2            4 
+   48000    512.83356   -3200.0643            0            1   0.96810224          258          544    6.0069324    0.1921875 0.00097916667     2.332667    5.5485401    188226.87            2            4 
+Loop time of 0.241704 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   48000    512.83356   -3200.0643            0            1   0.96810224          258          544    6.0069324    0.1921875 0.00097916667     2.332667    5.5485401    188226.87            2            4 
+   48051    512.83356   -3217.9192            0            1   0.96810224          258          544    6.0069324   0.19198352 0.00097812741     2.332667    5.5485401    188226.87            2            4 
+Loop time of 0.0259903 on 4 procs for 51 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   48000    512.83356   -3200.0643   0.36239559    4495.5483   0.15738105          280          407    6.0069324    0.1921875 0.00097916667     2.332667    5.5485401    188226.87            3            6 
+   49000     490.9639   -3198.6936   0.21113624    134.32512   0.22802517          114          115    6.0069324   0.18993878 0.00095918367     2.332667    5.5485401     191519.1            3            6 
+Loop time of 0.22826 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   49000     490.9639   -3198.6936   0.21113624    134.32512   0.22802517          114          115    6.0069324   0.18993878 0.00095918367     2.332667    5.5485401     191519.1            3            6 
+   49054     490.9639   -3217.9192   0.21113624    134.32512   0.22802517          114          115    6.0069324   0.18972969 0.00095812778     2.332667    5.5485401     191519.1            3            6 
+Loop time of 0.024157 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   49000     490.9639   -3198.6936   0.21113624    134.32512   0.22802517          114          115    6.0069324   0.18993878 0.00095918367     2.332667    5.5485401     191519.1            3            6 
+   50000    502.62206   -3199.7905   0.22799901    198.66723   0.22126947          119          400    6.0069324       0.1885      0.00094     2.332667    5.5485401    195910.67            3            6 
+Loop time of 0.226578 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   50000    502.62206   -3199.7905   0.22799901    198.66723   0.22126947          119          400    6.0069324       0.1885      0.00094     2.332667    5.5485401    195910.67            3            6 
+   50059    502.62206   -3217.9192   0.22799901    198.66723   0.22126947          119          400    6.0069324   0.18827783 0.00093889211     2.332667    5.5485401    195910.67            3            6 
+Loop time of 0.0268276 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   50000    502.62206   -3199.7905   0.22799901    198.66723   0.22126947          119          400    6.0069324       0.1885      0.00094     2.332667    5.5485401    195910.67            3            6 
+   51000    508.29336   -3198.9059   0.14109933    26.437299   0.25416947          264          275    6.0069324   0.18907843 0.00092156863     2.332667    5.5485401    199067.94            3            6 
+Loop time of 0.23022 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   51000    508.29336   -3198.9059   0.14109933    26.437299   0.25416947          264          275    6.0069324   0.18907843 0.00092156863     2.332667    5.5485401    199067.94            3            6 
+   51055    508.29336   -3217.9192   0.14109933    26.437299   0.25416947          264          275    6.0069324   0.18887474 0.00092057585     2.332667    5.5485401    199067.94            3            6 
+Loop time of 0.0267057 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   51000    508.29336   -3198.9059   0.14109933    26.437299   0.25416947          264          275    6.0069324   0.18907843 0.00092156863     2.332667    5.5485401    199067.94            3            6 
+   52000    506.84322   -3198.7391            0            1   0.35895473          264          275    6.0069324   0.19369231 0.00090384615     2.332667    5.5485401    199119.85            3            6 
+Loop time of 0.248939 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   52000    506.84322   -3198.7391            0            1   0.35895473          264          275    6.0069324   0.19369231 0.00090384615     2.332667    5.5485401    199119.85            3            6 
+   52061    506.84322   -3217.9192            0            1   0.35895473          264          275    6.0069324   0.19346536 0.00090278712     2.332667    5.5485401    199119.85            3            6 
+Loop time of 0.0283017 on 4 procs for 61 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   52000    506.84322   -3198.7391            0            1   0.35895473          264          275    6.0069324   0.19369231 0.00090384615     2.332667    5.5485401    199119.85            3            6 
+   53000    477.74415   -3199.3706            0            1   0.31797782          264          275    6.0069324    0.1960566 0.00088679245     2.332667    5.5485401    200597.61            3            6 
+Loop time of 0.226147 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   53000    477.74415   -3199.3706            0            1   0.31797782          264          275    6.0069324    0.1960566 0.00088679245     2.332667    5.5485401    200597.61            3            6 
+   53056    477.74415   -3217.9192            0            1   0.31797782          264          275    6.0069324   0.19584967 0.00088585645     2.332667    5.5485401    200597.61            3            6 
+Loop time of 0.0249364 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   53000    477.74415   -3199.3706            0            1   0.31797782          264          275    6.0069324    0.1960566 0.00088679245     2.332667    5.5485401    200597.61            3            6 
+   54000    467.64603   -3198.6476   0.12868765    19.820426   0.25852702          575          280    6.0069324   0.19614815 0.00087037037     2.332667    5.5485401     203111.2            3            6 
+Loop time of 0.242983 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   54000    467.64603   -3198.6476   0.12868765    19.820426   0.25852702          575          280    6.0069324   0.19614815 0.00087037037     2.332667    5.5485401     203111.2            3            6 
+   54051    467.64603   -3217.9192   0.12868765    19.820426   0.25852702          575          280    6.0069324   0.19596307 0.00086954913     2.332667    5.5485401     203111.2            3            6 
+Loop time of 0.0256515 on 4 procs for 51 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   54000    467.64603   -3198.6476   0.12868765    19.820426   0.25852702          575          280    6.0069324   0.19614815 0.00087037037     2.332667    5.5485401     203111.2            3            6 
+   55000    504.56378   -3198.2318   0.01979034     1.582988   0.29400296          556          567    6.0069324       0.1934 0.00085454545     2.332667    5.5485401    209967.08            3            6 
+Loop time of 0.243744 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   55000    504.56378   -3198.2318   0.01979034     1.582988   0.29400296          556          567    6.0069324       0.1934 0.00085454545     2.332667    5.5485401    209967.08            3            6 
+   55057    504.56378   -3217.9192   0.01979034     1.582988   0.29400296          556          567    6.0069324   0.19319977 0.00085366075     2.332667    5.5485401    209967.08            3            6 
+Loop time of 0.0273646 on 4 procs for 57 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   55000    504.56378   -3198.2318   0.01979034     1.582988   0.29400296          556          567    6.0069324       0.1934 0.00085454545     2.332667    5.5485401    209967.08            3            6 
+   56000    564.45428   -3198.7813   0.20223936    109.26492   0.23151007           78           91    6.0069324   0.19246429 0.00083928571     2.332667    5.5485401    215831.27            3            6 
+Loop time of 0.238614 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   56000    564.45428   -3198.7813   0.20223936    109.26492   0.23151007           78           91    6.0069324   0.19246429 0.00083928571     2.332667    5.5485401    215831.27            3            6 
+   56052    564.45428   -3217.9192   0.20223936    109.26492   0.23151007           78           91    6.0069324   0.19228573 0.0008385071     2.332667    5.5485401    215831.27            3            6 
+Loop time of 0.0241504 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   56000    564.45428   -3198.7813   0.20223936    109.26492   0.23151007           78           91    6.0069324   0.19246429 0.00083928571     2.332667    5.5485401    215831.27            3            6 
+   57000    515.72168   -3198.6584   0.31159686    1382.7848   0.18415364          544          577    6.0069324   0.19210526 0.0008245614     2.332667    5.5485401    222695.11            3            6 
+Loop time of 0.30046 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   57000    515.72168   -3198.6584   0.31159686    1382.7848   0.18415364          544          577    6.0069324   0.19210526 0.0008245614     2.332667    5.5485401    222695.11            3            6 
+   57059    515.72168   -3217.9192   0.31159686    1382.7848   0.18415364          544          577    6.0069324   0.19190662 0.00082370879     2.332667    5.5485401    222695.11            3            6 
+Loop time of 0.0361512 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   57000    515.72168   -3198.6584   0.31159686    1382.7848   0.18415364          544          577    6.0069324   0.19210526 0.0008245614     2.332667    5.5485401    222695.11            3            6 
+   58000    493.40021   -3198.8621            0            1   0.30931038          275          577    6.0069324   0.18989655 0.00081034483     2.332667    5.5485401    225894.02            3            6 
+Loop time of 0.304723 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   58000    493.40021   -3198.8621            0            1   0.30931038          275          577    6.0069324   0.18989655 0.00081034483     2.332667    5.5485401    225894.02            3            6 
+   58055    493.40021   -3217.9192            0            1   0.30931038          275          577    6.0069324   0.18971665 0.00080957713     2.332667    5.5485401    225894.02            3            6 
+Loop time of 0.034838 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   58000    493.40021   -3198.8621            0            1   0.30931038          275          577    6.0069324   0.18989655 0.00081034483     2.332667    5.5485401    225894.02            3            6 
+   59000    459.13337    -3198.423   0.32299123    1801.3772   0.17849812          117          288    6.0069324        0.189 0.00079661017     2.332667    5.5485401    232785.62            3            6 
+Loop time of 0.267864 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   59000    459.13337    -3198.423   0.32299123    1801.3772   0.17849812          117          288    6.0069324        0.189 0.00079661017     2.332667    5.5485401    232785.62            3            6 
+   59052    459.13337   -3217.9192   0.32299123    1801.3772   0.17849812          117          288    6.0069324   0.18883357 0.00079590869     2.332667    5.5485401    232785.62            3            6 
+Loop time of 0.0229472 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   59000    459.13337    -3198.423   0.32299123    1801.3772   0.17849812          117          288    6.0069324        0.189 0.00079661017     2.332667    5.5485401    232785.62            3            6 
+   60000    491.26878   -3198.9291   0.28012983    666.16416   0.19893876          560          567    6.0069324   0.18678333 0.00078333333     2.332667    5.5485401    236949.88            3            6 
+Loop time of 0.224423 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   60000    491.26878   -3198.9291   0.28012983    666.16416   0.19893876          560          567    6.0069324   0.18678333 0.00078333333     2.332667    5.5485401    236949.88            3            6 
+   60051    491.26878   -3217.9192   0.28012983    666.16416   0.19893876          560          567    6.0069324    0.1866247 0.00078266807     2.332667    5.5485401    236949.88            3            6 
+Loop time of 0.0231369 on 4 procs for 51 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   60000    491.26878   -3198.9291   0.28012983    666.16416   0.19893876          560          567    6.0069324   0.18678333 0.00078333333     2.332667    5.5485401    236949.88            3            6 
+   61000    469.65564   -3198.3735  0.086199081    7.3934564   0.27291787          562          564    6.0069324   0.18445902 0.0007704918     2.332667    5.5485401    245720.88            3            6 
+Loop time of 0.228656 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   61000    469.65564   -3198.3735  0.086199081    7.3934564   0.27291787          562          564    6.0069324   0.18445902 0.0007704918     2.332667    5.5485401    245720.88            3            6 
+   61053    469.65564   -3217.9192  0.086199081    7.3934564   0.27291787          562          564    6.0069324   0.18429889 0.00076982294     2.332667    5.5485401    245720.88            3            6 
+Loop time of 0.0245876 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   61000    469.65564   -3198.3735  0.086199081    7.3934564   0.27291787          562          564    6.0069324   0.18445902 0.0007704918     2.332667    5.5485401    245720.88            3            6 
+   62000    520.14843   -3198.5458   0.35275062    3593.8982   0.16280322          116          123    6.0069324   0.18312903 0.00075806452     2.332667    5.5485401    250136.37            3            6 
+Loop time of 0.232165 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   62000    520.14843   -3198.5458   0.35275062    3593.8982   0.16280322          116          123    6.0069324   0.18312903 0.00075806452     2.332667    5.5485401    250136.37            3            6 
+   62056    520.14843   -3217.9192   0.35275062    3593.8982   0.16280322          116          123    6.0069324   0.18296377 0.00075738043     2.332667    5.5485401    250136.37            3            6 
+Loop time of 0.0275648 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   62000    520.14843   -3198.5458   0.35275062    3593.8982   0.16280322          116          123    6.0069324   0.18312903 0.00075806452     2.332667    5.5485401    250136.37            3            6 
+   63000    506.90141   -3196.9575  0.019630501    1.5771264   0.29405188          577          555    6.0069324   0.18190476 0.00074603175     2.332667    5.5485401    257004.48            3            6 
+Loop time of 0.236446 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   63000    506.90141   -3196.9575  0.019630501    1.5771264   0.29405188          577          555    6.0069324   0.18190476 0.00074603175     2.332667    5.5485401    257004.48            3            6 
+   63059    506.90141   -3217.9192  0.019630501    1.5771264   0.29405188          577          555    6.0069324   0.18173457 0.00074533374     2.332667    5.5485401    257004.48            3            6 
+Loop time of 0.0258729 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   63000    506.90141   -3196.9575  0.019630501    1.5771264   0.29405188          577          555    6.0069324   0.18190476 0.00074603175     2.332667    5.5485401    257004.48            3            6 
+   64000    435.29185   -3197.3025   0.08981574    8.0408468   0.27172259          266          267    6.0069324   0.18060937  0.000734375     2.332667    5.5485401    261196.79            3            6 
+Loop time of 0.224694 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   64000    435.29185   -3197.3025   0.08981574    8.0408468   0.27172259          266          267    6.0069324   0.18060937  0.000734375     2.332667    5.5485401    261196.79            3            6 
+   64053    435.29185   -3217.9192   0.08981574    8.0408468   0.27172259          266          267    6.0069324   0.18045993 0.00073376735     2.332667    5.5485401    261196.79            3            6 
+Loop time of 0.023932 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   64000    435.29185   -3197.3025   0.08981574    8.0408468   0.27172259          266          267    6.0069324   0.18060937  0.000734375     2.332667    5.5485401    261196.79            3            6 
+   65000    484.45338   -3198.1013   0.27900382    648.98038   0.19944752           85           87    6.0069324   0.17955385 0.00072307692     2.332667    5.5485401    267611.45            3            6 
+Loop time of 0.225038 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   65000    484.45338   -3198.1013   0.27900382    648.98038   0.19944752           85           87    6.0069324   0.17955385 0.00072307692     2.332667    5.5485401    267611.45            3            6 
+   65053    484.45338   -3217.9192   0.27900382    648.98038   0.19944752           85           87    6.0069324   0.17940756 0.00072248782     2.332667    5.5485401    267611.45            3            6 
+Loop time of 0.0248089 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   65000    484.45338   -3198.1013   0.27900382    648.98038   0.19944752           85           87    6.0069324   0.17955385 0.00072307692     2.332667    5.5485401    267611.45            3            6 
+   66000    497.23553    -3199.036   0.25525209    373.95984   0.20989193          412          411    6.0069324   0.17804545 0.00071212121     2.332667    5.5485401    274383.49            3            6 
+Loop time of 0.233376 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   66000    497.23553    -3199.036   0.25525209    373.95984   0.20989193          412          411    6.0069324   0.17804545 0.00071212121     2.332667    5.5485401    274383.49            3            6 
+   66058    497.23553   -3217.9192   0.25525209    373.95984   0.20989193          412          411    6.0069324   0.17788913 0.00071149596     2.332667    5.5485401    274383.49            3            6 
+Loop time of 0.0279601 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   66000    497.23553    -3199.036   0.25525209    373.95984   0.20989193          412          411    6.0069324   0.17804545 0.00071212121     2.332667    5.5485401    274383.49            3            6 
+   67000    488.34684   -3198.7152   0.27967841     659.2212   0.19914288          264          275    6.0069324   0.17935821 0.00070149254     2.332667    5.5485401    274635.62            3            6 
+Loop time of 0.237521 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   67000    488.34684   -3198.7152   0.27967841     659.2212   0.19914288          264          275    6.0069324   0.17935821 0.00070149254     2.332667    5.5485401    274635.62            3            6 
+   67055    488.34684   -3217.9192   0.27967841     659.2212   0.19914288          264          275    6.0069324    0.1792111 0.00070091716     2.332667    5.5485401    274635.62            3            6 
+Loop time of 0.0262208 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   67000    488.34684   -3198.7152   0.27967841     659.2212   0.19914288          264          275    6.0069324   0.17935821 0.00070149254     2.332667    5.5485401    274635.62            3            6 
+   68000    547.06201   -3198.7151   0.11427629    14.185774   0.26349624          261          263    6.0069324   0.17882353 0.00069117647     2.332667    5.5485401    277575.99            3            6 
+Loop time of 0.224043 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   68000    547.06201   -3198.7151   0.11427629    14.185774   0.26349624          261          263    6.0069324   0.17882353 0.00069117647     2.332667    5.5485401    277575.99            3            6 
+   68060    547.06201   -3217.9192   0.11427629    14.185774   0.26349624          261          263    6.0069324   0.17866588 0.00069056715     2.332667    5.5485401    277575.99            3            6 
+Loop time of 0.0288572 on 4 procs for 60 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   68000    547.06201   -3198.7151   0.11427629    14.185774   0.26349624          261          263    6.0069324   0.17882353 0.00069117647     2.332667    5.5485401    277575.99            3            6 
+   69000    508.94771   -3198.9475   0.10069537    10.350552   0.26809482          264          275    6.0069324   0.18095652 0.00068115942     2.332667    5.5485401    279847.52            3            6 
+Loop time of 0.227692 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   69000    508.94771   -3198.9475   0.10069537    10.350552   0.26809482          264          275    6.0069324   0.18095652 0.00068115942     2.332667    5.5485401    279847.52            3            6 
+   69056    508.94771   -3217.9192   0.10069537    10.350552   0.26809482          264          275    6.0069324   0.18080978 0.00068060704     2.332667    5.5485401    279847.52            3            6 
+Loop time of 0.0247979 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   69000    508.94771   -3198.9475   0.10069537    10.350552   0.26809482          264          275    6.0069324   0.18095652 0.00068115942     2.332667    5.5485401    279847.52            3            6 
+   70000    499.92534   -3198.5636    0.3528879    3605.3669   0.16272731          283          288    6.0069324   0.18142857 0.00072857143     2.332667    5.5485401    281504.52            3            6 
+Loop time of 0.232204 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   70000    499.92534   -3198.5636    0.3528879    3605.3669   0.16272731          283          288    6.0069324   0.18142857 0.00072857143     2.332667    5.5485401    281504.52            3            6 
+   70054    499.92534   -3217.9192    0.3528879    3605.3669   0.16272731          283          288    6.0069324   0.18128872 0.00072800982     2.332667    5.5485401    281504.52            3            6 
+Loop time of 0.0249009 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   70000    499.92534   -3198.5636    0.3528879    3605.3669   0.16272731          283          288    6.0069324   0.18142857 0.00072857143     2.332667    5.5485401    281504.52            3            6 
+   71000    506.70688    -3197.313  0.082678879     6.813425   0.27407627          541          543    6.0069324   0.18050704 0.00071830986     2.332667    5.5485401    286003.61            3            6 
+Loop time of 0.229025 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   71000    506.70688    -3197.313  0.082678879     6.813425   0.27407627          541          543    6.0069324   0.18050704 0.00071830986     2.332667    5.5485401    286003.61            3            6 
+   71059    506.70688   -3217.9192  0.082678879     6.813425   0.27407627          541          543    6.0069324   0.18035717 0.00071771345     2.332667    5.5485401    286003.61            3            6 
+Loop time of 0.0265949 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   71000    506.70688    -3197.313  0.082678879     6.813425   0.27407627          541          543    6.0069324   0.18050704 0.00071830986     2.332667    5.5485401    286003.61            3            6 
+   72000    464.23294   -3197.7357            0            1   0.31542276          275          577    6.0069324   0.18266667 0.00070833333     2.332667    5.5485401    286734.83            3            6 
+Loop time of 0.228346 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   72000    464.23294   -3197.7357            0            1   0.31542276          275          577    6.0069324   0.18266667 0.00070833333     2.332667    5.5485401    286734.83            3            6 
+   72053    464.23294   -3217.9192            0            1   0.31542276          275          577    6.0069324    0.1825323 0.0007078123     2.332667    5.5485401    286734.83            3            6 
+Loop time of 0.026114 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   72000    464.23294   -3197.7357            0            1   0.31542276          275          577    6.0069324   0.18266667 0.00070833333     2.332667    5.5485401    286734.83            3            6 
+   73000    529.30216   -3198.1231    0.1005148    10.307265   0.26815543          411          416    6.0069324   0.18394521 0.00069863014     2.332667    5.5485401    287872.93            3            6 
+Loop time of 0.229123 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   73000    529.30216   -3198.1231    0.1005148    10.307265   0.26815543          411          416    6.0069324   0.18394521 0.00069863014     2.332667    5.5485401    287872.93            3            6 
+   73054    529.30216   -3217.9192    0.1005148    10.307265   0.26815543          411          416    6.0069324   0.18380924 0.00069811372     2.332667    5.5485401    287872.93            3            6 
+Loop time of 0.0243089 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   73000    529.30216   -3198.1231    0.1005148    10.307265   0.26815543          411          416    6.0069324   0.18394521 0.00069863014     2.332667    5.5485401    287872.93            3            6 
+   74000    490.65557   -3199.6766   0.14904687    31.792497   0.25133954          111          116    6.0069324   0.18322973 0.00068918919     2.332667    5.5485401    294766.16            3            6 
+Loop time of 0.236133 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   74000    490.65557   -3199.6766   0.14904687    31.792497   0.25133954          111          116    6.0069324   0.18322973 0.00068918919     2.332667    5.5485401    294766.16            3            6 
+   74055    490.65557   -3217.9192   0.14904687    31.792497   0.25133954          111          116    6.0069324   0.18309365 0.00068867733     2.332667    5.5485401    294766.16            3            6 
+Loop time of 0.0264881 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   74000    490.65557   -3199.6766   0.14904687    31.792497   0.25133954          111          116    6.0069324   0.18322973 0.00068918919     2.332667    5.5485401    294766.16            3            6 
+   75000    475.22638   -3198.1558   0.37341486    5805.6632   0.15094809          563          564    6.0069324      0.18212 0.00073333333     2.332667    5.5485401    302150.54            3            6 
+Loop time of 0.228974 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   75000    475.22638   -3198.1558   0.37341486    5805.6632   0.15094809          563          564    6.0069324      0.18212 0.00073333333     2.332667    5.5485401    302150.54            3            6 
+   75053    475.22638   -3217.9192   0.37341486    5805.6632   0.15094809          563          564    6.0069324   0.18199139 0.00073281548     2.332667    5.5485401    302150.54            3            6 
+Loop time of 0.0246332 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   75000    475.22638   -3198.1558   0.37341486    5805.6632   0.15094809          563          564    6.0069324      0.18212 0.00073333333     2.332667    5.5485401    302150.54            3            6 
+   76000    523.91803   -3198.8966  0.038679316    2.4539737   0.28816267          263          264    6.0069324   0.18286842 0.00072368421     2.332667    5.5485401     304160.3            3            6 
+Loop time of 0.223991 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   76000    523.91803   -3198.8966  0.038679316    2.4539737   0.28816267          263          264    6.0069324   0.18286842 0.00072368421     2.332667    5.5485401     304160.3            3            6 
+   76058    523.91803   -3217.9192  0.038679316    2.4539737   0.28816267          263          264    6.0069324   0.18272897 0.00072313235     2.332667    5.5485401     304160.3            3            6 
+Loop time of 0.0268497 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   76000    523.91803   -3198.8966  0.038679316    2.4539737   0.28816267          263          264    6.0069324   0.18286842 0.00072368421     2.332667    5.5485401     304160.3            3            6 
+   77000    511.16512   -3199.1926            0            1   0.31251901          264          275    6.0069324   0.18790909 0.00071428571     2.332667    5.5485401    304174.43            3            6 
+Loop time of 0.226324 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   77000    511.16512   -3199.1926            0            1   0.31251901          264          275    6.0069324   0.18790909 0.00071428571     2.332667    5.5485401    304174.43            3            6 
+   77059    511.16512   -3217.9192            0            1   0.31251901          264          275    6.0069324   0.18776522 0.00071373882     2.332667    5.5485401    304174.43            3            6 
+Loop time of 0.026314 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   77000    511.16512   -3199.1926            0            1   0.31251901          264          275    6.0069324   0.18790909 0.00071428571     2.332667    5.5485401    304174.43            3            6 
+   78000    554.58169   -3199.0107  0.022175428    1.6730858   0.29327193          263          264    6.0069324   0.19037179 0.00094871795     2.332667    5.5485401    304438.98            3            6 
+Loop time of 0.234504 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   78000    554.58169   -3199.0107  0.022175428    1.6730858   0.29327193          263          264    6.0069324   0.19037179 0.00094871795     2.332667    5.5485401    304438.98            3            6 
+   78062    554.58169   -3217.9192  0.022175428    1.6730858   0.29327193          263          264    6.0069324   0.19022059 0.00094796444     2.332667    5.5485401    304438.98            3            6 
+Loop time of 0.0297351 on 4 procs for 62 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   78000    554.58169   -3199.0107  0.022175428    1.6730858   0.29327193          263          264    6.0069324   0.19037179 0.00094871795     2.332667    5.5485401    304438.98            3            6 
+   79000    523.97176   -3198.2366    0.1672356    48.490735   0.24473985          556          567    6.0069324   0.19017722 0.00093670886     2.332667    5.5485401    306076.23            3            6 
+Loop time of 0.228044 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   79000    523.97176   -3198.2366    0.1672356    48.490735   0.24473985          556          567    6.0069324   0.19017722 0.00093670886     2.332667    5.5485401    306076.23            3            6 
+   79057    523.97176   -3217.9192    0.1672356    48.490735   0.24473985          556          567    6.0069324    0.1900401 0.00093603349     2.332667    5.5485401    306076.23            3            6 
+Loop time of 0.026444 on 4 procs for 57 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   79000    523.97176   -3198.2366    0.1672356    48.490735   0.24473985          556          567    6.0069324   0.19017722 0.00093670886     2.332667    5.5485401    306076.23            3            6 
+   80000    479.09781   -3197.6134            0            1   0.30854872          263          577    6.0069324    0.1902125     0.000925     2.332667    5.5485401    308522.09            3            6 
+Loop time of 0.224854 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   80000    479.09781   -3197.6134            0            1   0.30854872          263          577    6.0069324    0.1902125     0.000925     2.332667    5.5485401    308522.09            3            6 
+   80059    479.09781   -3217.9192            0            1   0.30854872          263          577    6.0069324   0.19007232 0.00092431832     2.332667    5.5485401    308522.09            3            6 
+Loop time of 0.0272751 on 4 procs for 59 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   80000    479.09781   -3197.6134            0            1   0.30854872          263          577    6.0069324    0.1902125     0.000925     2.332667    5.5485401    308522.09            3            6 
+   81000    517.52613   -3198.2236   0.29863857    1023.6251   0.19038135          254          256    6.0069324   0.18996296 0.00091358025     2.332667    5.5485401    311171.12            3            6 
+Loop time of 0.226269 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   81000    517.52613   -3198.2236   0.29863857    1023.6251   0.19038135          254          256    6.0069324   0.18996296 0.00091358025     2.332667    5.5485401    311171.12            3            6 
+   81056    517.52613   -3217.9192   0.29863857    1023.6251   0.19038135          254          256    6.0069324   0.18983172 0.00091294907     2.332667    5.5485401    311171.12            3            6 
+Loop time of 0.0258186 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   81000    517.52613   -3198.2236   0.29863857    1023.6251   0.19038135          254          256    6.0069324   0.18996296 0.00091358025     2.332667    5.5485401    311171.12            3            6 
+   82000    503.95678   -3197.7481  0.091495497    8.3605139   0.27116565          263          264    6.0069324   0.18862195 0.0010365854     2.332667    5.5485401    315319.38            3            6 
+Loop time of 0.235559 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   82000    503.95678   -3197.7481  0.091495497    8.3605139   0.27116565          263          264    6.0069324   0.18862195 0.0010365854     2.332667    5.5485401    315319.38            3            6 
+   82055    503.95678   -3217.9192  0.091495497    8.3605139   0.27116565          263          264    6.0069324   0.18849552 0.0010358906     2.332667    5.5485401    315319.38            3            6 
+Loop time of 0.0261242 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   82000    503.95678   -3197.7481  0.091495497    8.3605139   0.27116565          263          264    6.0069324   0.18862195 0.0010365854     2.332667    5.5485401    315319.38            3            6 
+   83000    537.67639   -3197.6886            0            1   0.32414276          263          264    6.0069324    0.1896988 0.0010240964     2.332667    5.5485401    316613.84            3            6 
+Loop time of 0.227873 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   83000    537.67639   -3197.6886            0            1   0.32414276          263          264    6.0069324    0.1896988 0.0010240964     2.332667    5.5485401    316613.84            3            6 
+   83064    537.67639   -3217.9192            0            1   0.32414276          263          264    6.0069324   0.18955263 0.0010233073     2.332667    5.5485401    316613.84            3            6 
+Loop time of 0.0301323 on 4 procs for 64 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   83000    537.67639   -3197.6886            0            1   0.32414276          263          264    6.0069324    0.1896988 0.0010240964     2.332667    5.5485401    316613.84            3            6 
+   84000    510.26841   -3199.5428   0.23554832    236.71181   0.21817723          142          424    6.0069324         0.19 0.0010119048     2.332667    5.5485401    318598.08            3            6 
+Loop time of 0.228573 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   84000    510.26841   -3199.5428   0.23554832    236.71181   0.21817723          142          424    6.0069324         0.19 0.0010119048     2.332667    5.5485401    318598.08            3            6 
+   84052    510.26841   -3217.9192   0.23554832    236.71181   0.21817723          142          424    6.0069324   0.18988245 0.0010112787     2.332667    5.5485401    318598.08            3            6 
+Loop time of 0.0254717 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   84000    510.26841   -3199.5428   0.23554832    236.71181   0.21817723          142          424    6.0069324         0.19 0.0010119048     2.332667    5.5485401    318598.08            3            6 
+   85000    472.16876   -3197.5248            0            1   0.34247044          264          275    6.0069324   0.18970588        0.001     2.332667    5.5485401    323882.61            3            6 
+Loop time of 0.231174 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   85000    472.16876   -3197.5248            0            1   0.34247044          264          275    6.0069324   0.18970588        0.001     2.332667    5.5485401    323882.61            3            6 
+   85055    472.16876   -3217.9192            0            1   0.34247044          264          275    6.0069324   0.18958321 0.00099935336     2.332667    5.5485401    323882.61            3            6 
+Loop time of 0.0253472 on 4 procs for 55 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   85000    472.16876   -3197.5248            0            1   0.34247044          264          275    6.0069324   0.18970588        0.001     2.332667    5.5485401    323882.61            3            6 
+   86000    509.30024   -3198.3226   0.20619306    119.76563   0.22996793          275          276    6.0069324   0.19110465 0.00098837209     2.332667    5.5485401    325788.44            3            6 
+Loop time of 0.241364 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   86000    509.30024   -3198.3226   0.20619306    119.76563   0.22996793          275          276    6.0069324   0.19110465 0.00098837209     2.332667    5.5485401    325788.44            3            6 
+   86053    509.30024   -3217.9192   0.20619306    119.76563   0.22996793          275          276    6.0069324   0.19098695 0.00098776336     2.332667    5.5485401    325788.44            3            6 
+Loop time of 0.0262635 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   86000    509.30024   -3198.3226   0.20619306    119.76563   0.22996793          275          276    6.0069324   0.19110465 0.00098837209     2.332667    5.5485401    325788.44            3            6 
+   87000    478.57944   -3199.3497   0.19192384    86.001287   0.23548611          260          271    6.0069324    0.1897931 0.00097701149     2.332667    5.5485401    330047.59            3            6 
+Loop time of 0.230381 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   87000    478.57944   -3199.3497   0.19192384    86.001287   0.23548611          260          271    6.0069324    0.1897931 0.00097701149     2.332667    5.5485401    330047.59            3            6 
+   87058    478.57944   -3217.9192   0.19192384    86.001287   0.23548611          260          271    6.0069324   0.18966666 0.00097636059     2.332667    5.5485401    330047.59            3            6 
+Loop time of 0.0275965 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   87000    478.57944   -3199.3497   0.19192384    86.001287   0.23548611          260          271    6.0069324    0.1897931 0.00097701149     2.332667    5.5485401    330047.59            3            6 
+   88000    515.63138   -3198.9629   0.35491784    3779.2911   0.16160071          543          577    6.0069324   0.18827273 0.00096590909     2.332667    5.5485401    337304.34            3            6 
+Loop time of 0.229339 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   88000    515.63138   -3198.9629   0.35491784    3779.2911   0.16160071          543          577    6.0069324   0.18827273 0.00096590909     2.332667    5.5485401    337304.34            3            6 
+   88050    515.63138   -3217.9192   0.35491784    3779.2911   0.16160071          543          577    6.0069324   0.18816581 0.00096536059     2.332667    5.5485401    337304.34            3            6 
+Loop time of 0.0253522 on 4 procs for 50 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   88000    515.63138   -3198.9629   0.35491784    3779.2911   0.16160071          543          577    6.0069324   0.18827273 0.00096590909     2.332667    5.5485401    337304.34            3            6 
+   89000    520.37063   -3197.8234            0            1   0.92013924          262          275    6.0069324   0.19148315 0.0011123596     2.332667    5.5485401    339909.57            3            6 
+Loop time of 0.234048 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   89000    520.37063   -3197.8234            0            1   0.92013924          262          275    6.0069324   0.19148315 0.0011123596     2.332667    5.5485401    339909.57            3            6 
+   89052    520.37063   -3217.9192            0            1   0.92013924          262          275    6.0069324   0.19137133   0.00111171     2.332667    5.5485401    339909.57            3            6 
+Loop time of 0.0242915 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   89000    520.37063   -3197.8234   0.34652166    3110.1454   0.16621101          111          112    6.0069324   0.19148315 0.0011123596     2.332667    5.5485401    339909.57            4            8 
+   90000    455.69218   -3197.8262   0.30521336    1192.3721   0.18724742          416          415    6.0069324       0.1905       0.0011     2.332667    5.5485401    345606.41            4            8 
+Loop time of 0.239736 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   90000    455.69218   -3197.8262   0.30521336    1192.3721   0.18724742          416          415    6.0069324       0.1905       0.0011     2.332667    5.5485401    345606.41            4            8 
+   90058    455.69218   -3217.9192   0.30521336    1192.3721   0.18724742          416          415    6.0069324   0.19037731 0.0010992916     2.332667    5.5485401    345606.41            4            8 
+Loop time of 0.027481 on 4 procs for 58 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   90000    455.69218   -3197.8262   0.30521336    1192.3721   0.18724742          416          415    6.0069324       0.1905       0.0011     2.332667    5.5485401    345606.41            4            8 
+   91000    506.17768   -3197.1344  0.035696451    2.2898339   0.28909279          547          548    6.0069324   0.18983516 0.0010879121     2.332667    5.5485401    350825.27            4            8 
+Loop time of 0.23396 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   91000    506.17768   -3197.1344  0.035696451    2.2898339   0.28909279          547          548    6.0069324   0.18983516 0.0010879121     2.332667    5.5485401    350825.27            4            8 
+   91051    506.17768   -3217.9192  0.035696451    2.2898339   0.28909279          547          548    6.0069324   0.18972883 0.0010873027     2.332667    5.5485401    350825.27            4            8 
+Loop time of 0.0249534 on 4 procs for 51 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   91000    506.17768   -3197.1344  0.035696451    2.2898339   0.28909279          547          548    6.0069324   0.18983516 0.0010879121     2.332667    5.5485401    350825.27            4            8 
+   92000     478.3025   -3197.9483            0            1   0.30393958          544          556    6.0069324   0.19196739  0.001076087     2.332667    5.5485401    352816.62            4            8 
+Loop time of 0.233376 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   92000     478.3025   -3197.9483            0            1   0.30393958          544          556    6.0069324   0.19196739  0.001076087     2.332667    5.5485401    352816.62            4            8 
+   92060     478.3025   -3217.9192            0            1   0.30393958          544          556    6.0069324   0.19184228 0.0010753856     2.332667    5.5485401    352816.62            4            8 
+Loop time of 0.0286014 on 4 procs for 60 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   92000     478.3025   -3197.9483            0            1   0.30393958          544          556    6.0069324   0.19196739  0.001076087     2.332667    5.5485401    352816.62            4            8 
+   93000    485.23153   -3199.9299   0.16699022    48.215364   0.24483006          544          556    6.0069324    0.1942043 0.0010645161     2.332667    5.5485401    354391.05            4            8 
+Loop time of 0.234626 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   93000    485.23153   -3199.9299   0.16699022    48.215364   0.24483006          544          556    6.0069324    0.1942043 0.0010645161     2.332667    5.5485401    354391.05            4            8 
+   93056    485.23153   -3217.9192   0.16699022    48.215364   0.24483006          544          556    6.0069324   0.19408743 0.0010638755     2.332667    5.5485401    354391.05            4            8 
+Loop time of 0.0261769 on 4 procs for 56 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   93000    485.23153   -3199.9299   0.16699022    48.215364   0.24483006          544          556    6.0069324    0.1942043 0.0010645161     2.332667    5.5485401    354391.05            4            8 
+   94000    499.72991   -3199.3195            0            1   0.30394408          544          556    6.0069324   0.19443617 0.0010531915     2.332667    5.5485401    360147.54            4            8 
+Loop time of 0.229448 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   94000    499.72991   -3199.3195            0            1   0.30394408          544          556    6.0069324   0.19443617 0.0010531915     2.332667    5.5485401    360147.54            4            8 
+   94061    499.72991   -3217.9192            0            1   0.30394408          544          556    6.0069324   0.19431008 0.0010525085     2.332667    5.5485401    360147.54            4            8 
+Loop time of 0.0281783 on 4 procs for 61 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   94000    499.72991   -3199.3195            0            1   0.30394408          544          556    6.0069324   0.19443617 0.0010531915     2.332667    5.5485401    360147.54            4            8 
+   95000    509.83941   -3199.0903  0.078854869     6.234781   0.27532912          555          556    6.0069324   0.19681053 0.0010421053     2.332667    5.5485401    360599.28            4            8 
+Loop time of 0.224206 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   95000    509.83941   -3199.0903  0.078854869     6.234781   0.27532912          555          556    6.0069324   0.19681053 0.0010421053     2.332667    5.5485401    360599.28            4            8 
+   95060    509.83941   -3217.9192  0.078854869     6.234781   0.27532912          555          556    6.0069324    0.1966863 0.0010414475     2.332667    5.5485401    360599.28            4            8 
+Loop time of 0.027992 on 4 procs for 60 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   95000    509.83941   -3199.0903  0.078854869     6.234781   0.27532912          555          556    6.0069324   0.19681053 0.0010421053     2.332667    5.5485401    360599.28            4            8 
+   96000    486.83779   -3197.2106   0.31070799    1354.5503   0.18458755          136          431    6.0069324   0.19620833   0.00103125     2.332667    5.5485401    365489.89            4            8 
+Loop time of 0.228167 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   96000    486.83779   -3197.2106   0.31070799    1354.5503   0.18458755          136          431    6.0069324   0.19620833   0.00103125     2.332667    5.5485401    365489.89            4            8 
+   96053    486.83779   -3217.9192   0.31070799    1354.5503   0.18458755          136          431    6.0069324   0.19610007  0.001030681     2.332667    5.5485401    365489.89            4            8 
+Loop time of 0.024569 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   96000    486.83779   -3197.2106   0.31070799    1354.5503   0.18458755          136          431    6.0069324   0.19620833   0.00103125     2.332667    5.5485401    365489.89            4            8 
+   97000    499.91835   -3199.2446    0.2280334    198.82589   0.22125548          280          111    6.0069324   0.19491753 0.0010206186     2.332667    5.5485401    372336.45            4            8 
+Loop time of 0.23889 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   97000    499.91835   -3199.2446    0.2280334    198.82589   0.22125548          280          111    6.0069324   0.19491753 0.0010206186     2.332667    5.5485401    372336.45            4            8 
+   97052    499.91835   -3217.9192    0.2280334    198.82589   0.22125548          280          111    6.0069324   0.19481309 0.0010200717     2.332667    5.5485401    372336.45            4            8 
+Loop time of 0.0262206 on 4 procs for 52 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   97000    499.91835   -3199.2446    0.2280334    198.82589   0.22125548          280          111    6.0069324   0.19491753 0.0010206186     2.332667    5.5485401    372336.45            4            8 
+   98000    547.56456   -3197.2191   0.27848637    641.23302   0.19968088          430          136    6.0069324    0.1957449 0.0010102041     2.332667    5.5485401    377711.41            4            8 
+Loop time of 0.239305 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   98000    547.56456   -3197.2191   0.27848637    641.23302   0.19968088          430          136    6.0069324    0.1957449 0.0010102041     2.332667    5.5485401    377711.41            4            8 
+   98054    547.56456   -3217.9192   0.27848637    641.23302   0.19968088          430          136    6.0069324    0.1956371 0.0010096477     2.332667    5.5485401    377711.41            4            8 
+Loop time of 0.0272166 on 4 procs for 54 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   98000    547.56456   -3197.2191   0.27848637    641.23302   0.19968088          430          136    6.0069324    0.1957449 0.0010102041     2.332667    5.5485401    377711.41            4            8 
+   99000    504.19627   -3196.6567            0            1   0.33814873          287          276    6.0069324   0.19517172        0.001     2.332667    5.5485401    381676.19            4            8 
+Loop time of 0.235176 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   99000    504.19627   -3196.6567            0            1   0.33814873          287          276    6.0069324   0.19517172        0.001     2.332667    5.5485401    381676.19            4            8 
+   99053    504.19627   -3217.9192            0            1   0.33814873          287          276    6.0069324   0.19506729 0.00099946493     2.332667    5.5485401    381676.19            4            8 
+Loop time of 0.0249114 on 4 procs for 53 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+   99000    504.19627   -3196.6567            0            1   0.33814873          287          276    6.0069324   0.19517172        0.001     2.332667    5.5485401    381676.19            4            8 
+  100000    542.04702   -3198.2211   0.37630331    6208.2061   0.14921597          563          564    6.0069324      0.19442      0.00099     2.332667    5.5485401     385211.4            4            8 
+Loop time of 0.226452 on 4 procs for 1000 steps with 577 atoms
+
+Step Temp PotEng f_HG f_HG[1] f_HG[2] f_HG[3] f_HG[4] f_HG[5] f_HG[6] f_HG[7] f_HG[8] f_HG[9] f_HG[10] f_HG[11] f_HG[12] 
+  100000    542.04702   -3198.2211   0.37630331    6208.2061   0.14921597          563          564    6.0069324      0.19442      0.00099     2.332667    5.5485401     385211.4            4            8 
+  100060    542.04702   -3217.9192   0.37630331    6208.2061   0.14921597          563          564    6.0069324   0.19430342 0.00098940636     2.332667    5.5485401     385211.4            4            8 
+Loop time of 0.0303354 on 4 procs for 60 steps with 577 atoms
+
+Final hyper stats ...
+
+Cummulative quantities for fix hyper:
+  hyper time = 385211
+  time boost factor = 770.423
+  event timesteps = 4
+  # of atoms in events = 8
+Quantities for this hyper run:
+  event timesteps = 4
+  # of atoms in events = 8
+  max length of any bond = 5.54854
+  max drift distance of any atom = 2.33267
+  fraction of biased bonds with zero bias = 0.19442
+  fraction of biased bonds with negative strain = 0.00099
+Current quantities:
+  ave bonds/atom = 6.00693
+
+Loop time of 26.6054 on 4 procs for 100000 steps with 577 atoms
+
+Performance: 1623.732 ns/day, 0.015 hours/ns, 3758.639 timesteps/s
+100.6% CPU use with 4 MPI tasks x no OpenMP threads
+
+Hyper stats:
+  Dynamics time (%) = 23.5897 (88.665)
+  Quench   time (%) = 2.6357 (9.90664)
+  Other    time (%) = 0.875172 (3.28945)
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 18.942     | 19.435     | 20.026     |  10.1 | 73.05
+Neigh   | 1.3021     | 1.3833     | 1.4611     |   6.2 |  5.20
+Comm    | 2.1376     | 2.1725     | 2.2239     |   2.2 |  8.17
+Output  | 0.0033467  | 0.0034443  | 0.0037186  |   0.3 |  0.01
+Modify  | 2.0693     | 2.7356     | 3.2627     |  30.2 | 10.28
+Other   |            | 0.8752     |            |       |  3.29
+
+Nlocal:    144.25 ave 152 max 139 min
+Histogram: 1 1 0 0 1 0 0 0 0 1
+Nghost:    533.25 ave 538 max 526 min
+Histogram: 1 0 0 0 0 1 0 0 0 2
+Neighs:    3368.25 ave 3528 max 3240 min
+Histogram: 1 1 0 0 0 0 1 0 0 1
+
+Total # of neighbors = 13473
+Ave neighs/atom = 23.3501
+Neighbor list builds = 10072
+Dangerous builds = 0
+Total wall time: 0:00:27
diff --git a/examples/hyper/log.25Mar19.hyper.local.g++.16 b/examples/hyper/log.25Mar19.hyper.local.g++.16
new file mode 100644
index 0000000000..b56406f963
--- /dev/null
+++ b/examples/hyper/log.25Mar19.hyper.local.g++.16
@@ -0,0 +1,1002 @@
+LAMMPS (28 Feb 2019)
+# 3d EAM surface for local HD
+
+# nearest neighbor distance = a * sqrt(2)/2 = 2.77 Angs for Pt with a = 3.92
+# hop event on (100) surface is same distance
+# exchange event is 2 atoms moving same distance
+
+variable        Tequil index 400.0
+variable        Vmax index 0.4
+variable        qfactor index 0.3
+variable        cutbond index 3.2
+variable        Dcut index 10.0
+variable        cutevent index 1.1
+variable        alpha index 200.0
+variable        boost index 4000.0
+variable        ghostcut index 12.0
+variable        steps index 1500
+variable        nevent index 100
+variable        nx index 8
+variable        ny index 8
+variable        zoom index 1.8
+variable        seed index 826626413
+variable        tol index 1.0e-15
+variable        add index 37K
+
+units           metal
+atom_style	atomic
+atom_modify     map array
+boundary        p p p
+comm_modify     cutoff ${ghostcut}
+comm_modify     cutoff 12.0
+
+lattice		fcc 3.92
+Lattice spacing in x,y,z = 3.92 3.92 3.92
+region		box block 0 6 0 6 0 4
+create_box	2 box
+Created orthogonal box = (0 0 0) to (23.52 23.52 15.68)
+  2 by 4 by 2 MPI processor grid
+create_atoms	1 box
+Created 576 atoms
+  Time spent = 0.00110102 secs
+
+mass            * 1.0
+
+change_box      all z final -0.1 5.0 boundary p p f
+  orthogonal box = (0 0 -0.392) to (23.52 23.52 19.6)
+
+# replicate in xy
+
+replicate       ${nx} ${ny} 1
+replicate       8 ${ny} 1
+replicate       8 8 1
+  orthogonal box = (0 0 -0.392) to (188.16 188.16 19.6)
+  4 by 4 by 1 MPI processor grid
+  36864 atoms
+  Time spent = 0.00289989 secs
+
+# add adatoms
+
+include         adatoms.list.${add}
+include         adatoms.list.37K
+create_atoms 1 single 27.5 9.5 4
+Created 1 atoms
+  Time spent = 0.000200033 secs
+create_atoms 1 single 16 9 4
+Created 1 atoms
+  Time spent = 0.000183105 secs
+create_atoms 1 single 10 12 4
+Created 1 atoms
+  Time spent = 0.000180006 secs
+create_atoms 1 single 31 44 4
+Created 1 atoms
+  Time spent = 0.000190973 secs
+create_atoms 1 single 13 17 4
+Created 1 atoms
+  Time spent = 0.000185013 secs
+create_atoms 1 single 8.5 28.5 4
+Created 1 atoms
+  Time spent = 0.00018692 secs
+create_atoms 1 single 23 26 4
+Created 1 atoms
+  Time spent = 0.000179052 secs
+create_atoms 1 single 38 27 4
+Created 1 atoms
+  Time spent = 0.000191927 secs
+create_atoms 1 single 37.5 4.5 4
+Created 1 atoms
+  Time spent = 0.000238895 secs
+create_atoms 1 single 41.5 47.5 4
+Created 1 atoms
+  Time spent = 0.000191927 secs
+create_atoms 1 single 20.5 37.5 4
+Created 1 atoms
+  Time spent = 0.000185966 secs
+create_atoms 1 single 5 8 4
+Created 1 atoms
+  Time spent = 0.000170946 secs
+create_atoms 1 single 2.5 16.5 4
+Created 1 atoms
+  Time spent = 0.000174046 secs
+create_atoms 1 single 38.5 45.5 4
+Created 1 atoms
+  Time spent = 0.000172853 secs
+create_atoms 1 single 9 0 4
+Created 1 atoms
+  Time spent = 0.000187159 secs
+create_atoms 1 single 39 32 4
+Created 1 atoms
+  Time spent = 0.000180006 secs
+create_atoms 1 single 45.5 11.5 4
+Created 1 atoms
+  Time spent = 0.000189066 secs
+create_atoms 1 single 40 0 4
+Created 1 atoms
+  Time spent = 0.000170946 secs
+create_atoms 1 single 44.5 2.5 4
+Created 1 atoms
+  Time spent = 0.000191927 secs
+create_atoms 1 single 4.5 44.5 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 24.5 13.5 4
+Created 1 atoms
+  Time spent = 0.000166893 secs
+create_atoms 1 single 47.5 23.5 4
+Created 1 atoms
+  Time spent = 0.000181913 secs
+create_atoms 1 single 1 20 4
+Created 1 atoms
+  Time spent = 0.000167131 secs
+create_atoms 1 single 38.5 31.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 12.5 12.5 4
+Created 1 atoms
+  Time spent = 0.000165939 secs
+create_atoms 1 single 2 27 4
+Created 1 atoms
+  Time spent = 0.000170231 secs
+create_atoms 1 single 21 5 4
+Created 1 atoms
+  Time spent = 0.00018096 secs
+create_atoms 1 single 47 12 4
+Created 1 atoms
+  Time spent = 0.000166178 secs
+create_atoms 1 single 32.5 46.5 4
+Created 1 atoms
+  Time spent = 0.000166893 secs
+create_atoms 1 single 9.5 40.5 4
+Created 1 atoms
+  Time spent = 0.000165939 secs
+create_atoms 1 single 8.5 2.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 41.5 22.5 4
+Created 1 atoms
+  Time spent = 0.000175953 secs
+create_atoms 1 single 29 11 4
+Created 1 atoms
+  Time spent = 0.000165939 secs
+create_atoms 1 single 3.5 3.5 4
+Created 1 atoms
+  Time spent = 0.000174999 secs
+create_atoms 1 single 5 21 4
+Created 1 atoms
+  Time spent = 0.0001719 secs
+create_atoms 1 single 46.5 31.5 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 35 46 4
+Created 1 atoms
+  Time spent = 0.000178099 secs
+create_atoms 1 single 40.5 41.5 4
+Created 1 atoms
+  Time spent = 0.000168085 secs
+create_atoms 1 single 10 22 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 43.5 14.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 42 42 4
+Created 1 atoms
+  Time spent = 0.000184059 secs
+create_atoms 1 single 4 26 4
+Created 1 atoms
+  Time spent = 0.000178814 secs
+create_atoms 1 single 19 34 4
+Created 1 atoms
+  Time spent = 0.0001688 secs
+create_atoms 1 single 33 9 4
+Created 1 atoms
+  Time spent = 0.000168085 secs
+create_atoms 1 single 0.5 45.5 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 30.5 32.5 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 25.5 5.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 47.5 39.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 15 13 4
+Created 1 atoms
+  Time spent = 0.000174046 secs
+create_atoms 1 single 21 21 4
+Created 1 atoms
+  Time spent = 0.000166893 secs
+create_atoms 1 single 14 28 4
+Created 1 atoms
+  Time spent = 0.000170946 secs
+create_atoms 1 single 9 34 4
+Created 1 atoms
+  Time spent = 0.000174999 secs
+create_atoms 1 single 7 38 4
+Created 1 atoms
+  Time spent = 0.000167847 secs
+create_atoms 1 single 11 35 4
+Created 1 atoms
+  Time spent = 0.000168085 secs
+create_atoms 1 single 20.5 45.5 4
+Created 1 atoms
+  Time spent = 0.000177145 secs
+create_atoms 1 single 30.5 31.5 4
+Created 1 atoms
+  Time spent = 0.000167131 secs
+create_atoms 1 single 32.5 2.5 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 21.5 3.5 4
+Created 1 atoms
+  Time spent = 0.000166893 secs
+create_atoms 1 single 23 12 4
+Created 1 atoms
+  Time spent = 0.000169039 secs
+create_atoms 1 single 4.5 33.5 4
+Created 1 atoms
+  Time spent = 0.000178099 secs
+create_atoms 1 single 46 43 4
+Created 1 atoms
+  Time spent = 0.000175953 secs
+create_atoms 1 single 42.5 45.5 4
+Created 1 atoms
+  Time spent = 0.000169992 secs
+create_atoms 1 single 4.5 10.5 4
+Created 1 atoms
+  Time spent = 0.000175953 secs
+create_atoms 1 single 33.5 15.5 4
+Created 1 atoms
+  Time spent = 0.000158787 secs
+create_atoms 1 single 24 5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 13 16 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 16.5 23.5 4
+Created 1 atoms
+  Time spent = 0.000160933 secs
+create_atoms 1 single 45.5 28.5 4
+Created 1 atoms
+  Time spent = 0.000159025 secs
+create_atoms 1 single 44.5 5.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 27.5 46.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 44.5 12.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 12 41 4
+Created 1 atoms
+  Time spent = 0.000166893 secs
+create_atoms 1 single 6 4 4
+Created 1 atoms
+  Time spent = 0.0001688 secs
+create_atoms 1 single 31.5 10.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 1 44 4
+Created 1 atoms
+  Time spent = 0.000157833 secs
+create_atoms 1 single 31 4 4
+Created 1 atoms
+  Time spent = 0.000156879 secs
+create_atoms 1 single 21 33 4
+Created 1 atoms
+  Time spent = 0.000172138 secs
+create_atoms 1 single 3 33 4
+Created 1 atoms
+  Time spent = 0.000156879 secs
+create_atoms 1 single 15 10 4
+Created 1 atoms
+  Time spent = 0.000156879 secs
+create_atoms 1 single 28.5 22.5 4
+Created 1 atoms
+  Time spent = 0.000161886 secs
+create_atoms 1 single 43 1 4
+Created 1 atoms
+  Time spent = 0.000166178 secs
+create_atoms 1 single 3.5 0.5 4
+Created 1 atoms
+  Time spent = 0.000164986 secs
+create_atoms 1 single 41 37 4
+Created 1 atoms
+  Time spent = 0.000160933 secs
+create_atoms 1 single 18.5 43.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 17 27 4
+Created 1 atoms
+  Time spent = 0.000159025 secs
+create_atoms 1 single 3 5 4
+Created 1 atoms
+  Time spent = 0.000161171 secs
+create_atoms 1 single 18.5 23.5 4
+Created 1 atoms
+  Time spent = 0.000164986 secs
+create_atoms 1 single 31.5 14.5 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 41 31 4
+Created 1 atoms
+  Time spent = 0.000159979 secs
+create_atoms 1 single 22 3 4
+Created 1 atoms
+  Time spent = 0.000158787 secs
+create_atoms 1 single 14.5 40.5 4
+Created 1 atoms
+  Time spent = 0.000156879 secs
+create_atoms 1 single 9 38 4
+Created 1 atoms
+  Time spent = 0.000155926 secs
+create_atoms 1 single 36 42 4
+Created 1 atoms
+  Time spent = 0.000170231 secs
+create_atoms 1 single 33 22 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 15.5 47.5 4
+Created 1 atoms
+  Time spent = 0.000162125 secs
+create_atoms 1 single 3 0 4
+Created 1 atoms
+  Time spent = 0.000157118 secs
+create_atoms 1 single 25.5 27.5 4
+Created 1 atoms
+  Time spent = 0.000159025 secs
+create_atoms 1 single 2.5 28.5 4
+Created 1 atoms
+  Time spent = 0.000166178 secs
+create_atoms 1 single 29.5 28.5 4
+Created 1 atoms
+  Time spent = 0.000160933 secs
+create_atoms 1 single 44.5 18.5 4
+Created 1 atoms
+  Time spent = 0.000155926 secs
+create_atoms 1 single 26 40 4
+Created 1 atoms
+  Time spent = 0.000157833 secs
+create_atoms 1 single 41 27 4
+Created 1 atoms
+  Time spent = 0.000156879 secs
+create_atoms 1 single 39.5 5.5 4
+Created 1 atoms
+  Time spent = 0.000167847 secs
+create_atoms 1 single 3 38 4
+Created 1 atoms
+  Time spent = 0.000156164 secs
+create_atoms 1 single 35 29 4
+Created 1 atoms
+  Time spent = 0.000154018 secs
+create_atoms 1 single 11 19 4
+Created 1 atoms
+  Time spent = 0.000164032 secs
+create_atoms 1 single 18 1 4
+Created 1 atoms
+  Time spent = 0.000154972 secs
+create_atoms 1 single 39.5 40.5 4
+Created 1 atoms
+  Time spent = 0.000157118 secs
+create_atoms 1 single 46 17 4
+Created 1 atoms
+  Time spent = 0.000164986 secs
+create_atoms 1 single 1.5 23.5 4
+Created 1 atoms
+  Time spent = 0.00015521 secs
+create_atoms 1 single 28.5 23.5 4
+Created 1 atoms
+  Time spent = 0.000153065 secs
+create_atoms 1 single 10 28 4
+Created 1 atoms
+  Time spent = 0.000154018 secs
+create_atoms 1 single 19 47 4
+Created 1 atoms
+  Time spent = 0.000159979 secs
+create_atoms 1 single 10.5 16.5 4
+Created 1 atoms
+  Time spent = 0.000163078 secs
+create_atoms 1 single 38 45 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 42.5 41.5 4
+Created 1 atoms
+  Time spent = 0.000159025 secs
+create_atoms 1 single 47.5 42.5 4
+Created 1 atoms
+  Time spent = 0.000155926 secs
+create_atoms 1 single 38 7 4
+Created 1 atoms
+  Time spent = 0.000154018 secs
+create_atoms 1 single 10 44 4
+Created 1 atoms
+  Time spent = 0.000158072 secs
+create_atoms 1 single 29.5 27.5 4
+Created 1 atoms
+  Time spent = 0.000159025 secs
+create_atoms 1 single 45 30 4
+Created 1 atoms
+  Time spent = 0.000172138 secs
+create_atoms 1 single 3 9 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 8.5 35.5 4
+Created 1 atoms
+  Time spent = 0.000148058 secs
+create_atoms 1 single 24 44 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 47 4 4
+Created 1 atoms
+  Time spent = 0.000155926 secs
+create_atoms 1 single 7.5 8.5 4
+Created 1 atoms
+  Time spent = 0.000146866 secs
+create_atoms 1 single 32.5 41.5 4
+Created 1 atoms
+  Time spent = 0.000146151 secs
+create_atoms 1 single 0.5 34.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 11 8 4
+Created 1 atoms
+  Time spent = 0.000146866 secs
+create_atoms 1 single 2 40 4
+Created 1 atoms
+  Time spent = 0.000148058 secs
+create_atoms 1 single 25 24 4
+Created 1 atoms
+  Time spent = 0.000154018 secs
+create_atoms 1 single 47.5 6.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 39.5 28.5 4
+Created 1 atoms
+  Time spent = 0.000147104 secs
+create_atoms 1 single 17 21 4
+Created 1 atoms
+  Time spent = 0.000150919 secs
+create_atoms 1 single 32 43 4
+Created 1 atoms
+  Time spent = 0.000149012 secs
+create_atoms 1 single 16.5 29.5 4
+Created 1 atoms
+  Time spent = 0.000154972 secs
+create_atoms 1 single 34 34 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 11.5 3.5 4
+Created 1 atoms
+  Time spent = 0.000148058 secs
+create_atoms 1 single 39 22 4
+Created 1 atoms
+  Time spent = 0.000148058 secs
+create_atoms 1 single 24.5 36.5 4
+Created 1 atoms
+  Time spent = 0.000146151 secs
+create_atoms 1 single 33 31 4
+Created 1 atoms
+  Time spent = 0.000149965 secs
+create_atoms 1 single 35.5 35.5 4
+Created 1 atoms
+  Time spent = 0.000185966 secs
+create_atoms 1 single 14.5 34.5 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 34 28 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 37 41 4
+Created 1 atoms
+  Time spent = 0.000146866 secs
+create_atoms 1 single 33 46 4
+Created 1 atoms
+  Time spent = 0.000149965 secs
+create_atoms 1 single 27.5 28.5 4
+Created 1 atoms
+  Time spent = 0.000149965 secs
+create_atoms 1 single 40.5 22.5 4
+Created 1 atoms
+  Time spent = 0.000148773 secs
+create_atoms 1 single 27.5 1.5 4
+Created 1 atoms
+  Time spent = 0.00014782 secs
+create_atoms 1 single 12 2 4
+Created 1 atoms
+  Time spent = 0.000146151 secs
+create_atoms 1 single 36 43 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 28.5 9.5 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 20.5 25.5 4
+Created 1 atoms
+  Time spent = 0.000154972 secs
+create_atoms 1 single 3 3 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 38 33 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 3 20 4
+Created 1 atoms
+  Time spent = 0.000149012 secs
+create_atoms 1 single 35 11 4
+Created 1 atoms
+  Time spent = 0.000154018 secs
+create_atoms 1 single 5 25 4
+Created 1 atoms
+  Time spent = 0.00014782 secs
+create_atoms 1 single 36.5 6.5 4
+Created 1 atoms
+  Time spent = 0.000152111 secs
+create_atoms 1 single 19.5 24.5 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 27 41 4
+Created 1 atoms
+  Time spent = 0.000147104 secs
+create_atoms 1 single 39.5 11.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 21.5 2.5 4
+Created 1 atoms
+  Time spent = 0.000152111 secs
+create_atoms 1 single 46.5 15.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 13 24 4
+Created 1 atoms
+  Time spent = 0.000153065 secs
+create_atoms 1 single 11 37 4
+Created 1 atoms
+  Time spent = 0.000146866 secs
+create_atoms 1 single 11.5 31.5 4
+Created 1 atoms
+  Time spent = 0.000158787 secs
+create_atoms 1 single 47 0 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 25.5 17.5 4
+Created 1 atoms
+  Time spent = 0.000144005 secs
+create_atoms 1 single 32 11 4
+Created 1 atoms
+  Time spent = 0.000149012 secs
+create_atoms 1 single 8 17 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 27.5 12.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 25 7 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 25.5 37.5 4
+Created 1 atoms
+  Time spent = 0.000161886 secs
+create_atoms 1 single 12 15 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 1 7 4
+Created 1 atoms
+  Time spent = 0.000154972 secs
+create_atoms 1 single 18.5 47.5 4
+Created 1 atoms
+  Time spent = 0.000162125 secs
+create_atoms 1 single 5 38 4
+Created 1 atoms
+  Time spent = 0.000145197 secs
+create_atoms 1 single 42 19 4
+Created 1 atoms
+  Time spent = 0.000147104 secs
+create_atoms 1 single 30.5 7.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 42.5 7.5 4
+Created 1 atoms
+  Time spent = 0.000145912 secs
+create_atoms 1 single 26.5 18.5 4
+Created 1 atoms
+  Time spent = 0.000150919 secs
+create_atoms 1 single 18.5 1.5 4
+Created 1 atoms
+  Time spent = 0.000144958 secs
+create_atoms 1 single 41.5 10.5 4
+Created 1 atoms
+  Time spent = 0.000151873 secs
+
+# define frozen substrate and mobile atoms
+
+region          base block INF INF INF INF 0 1.8
+set             region base type 2
+  18432 settings made for type
+group           base type 2
+18432 atoms in group base
+group           mobile type 1
+18616 atoms in group mobile
+
+# pair style
+
+pair_style	eam/alloy
+pair_coeff	* * ptvoterlammps.eam Pt Pt
+
+neighbor	0.5 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 mobile nve
+fix		2 mobile langevin ${Tequil} ${Tequil} 1.0 ${seed} zero yes
+fix		2 mobile langevin 400.0 ${Tequil} 1.0 ${seed} zero yes
+fix		2 mobile langevin 400.0 400.0 1.0 ${seed} zero yes
+fix		2 mobile langevin 400.0 400.0 1.0 826626413 zero yes
+
+timestep	0.005
+
+compute         tmobile mobile temp
+
+thermo		100
+thermo_modify   temp tmobile
+WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:487)
+
+# thermal equilibration
+
+run             1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.07583
+  ghost atom cutoff = 12
+  binsize = 3.03792, bins = 62 62 7
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair eam/alloy, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.359 | 3.359 | 3.36 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0            0   -206220.22            0   -206220.22   -52155.664 
+     100    188.18127   -206044.43            0   -205591.63    -25068.83 
+     200    274.34464   -205860.78            0   -205200.66   -40191.797 
+     300    325.66286   -205750.01            0    -204966.4   -31510.222 
+     400    352.48242   -205675.42            0   -204827.28   -35058.064 
+     500    370.88571   -205619.66            0   -204727.25   -32735.022 
+     600    388.62129   -205592.87            0   -204657.78   -33904.556 
+     700    389.54874   -205579.73            0    -204642.4   -32769.852 
+     800    395.56074   -205576.82            0   -204625.03   -33755.948 
+     900    398.03458   -205564.48            0   -204606.74   -32777.103 
+    1000    401.24089   -205562.85            0    -204597.4   -33785.341 
+Loop time of 4.22555 on 16 procs for 1000 steps with 37048 atoms
+
+Performance: 102.235 ns/day, 0.235 hours/ns, 236.655 timesteps/s
+98.5% CPU use with 16 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 3.2988     | 3.3283     | 3.3788     |   1.5 | 78.77
+Neigh   | 0.22391    | 0.23756    | 0.28119    |   2.7 |  5.62
+Comm    | 0.31341    | 0.3888     | 0.49372    |   8.0 |  9.20
+Output  | 0.00041842 | 0.00042947 | 0.00048399 |   0.0 |  0.01
+Modify  | 0.17166    | 0.2512     | 0.35242    |   9.5 |  5.94
+Other   |            | 0.0193     |            |       |  0.46
+
+Nlocal:    2315.5 ave 2332 max 2297 min
+Histogram: 2 0 0 3 4 0 2 1 2 2
+Nghost:    3186.31 ave 3205 max 3170 min
+Histogram: 2 1 3 0 2 3 2 1 0 2
+Neighs:    55590.9 ave 56174 max 55103 min
+Histogram: 2 2 1 1 4 1 3 0 0 2
+
+Total # of neighbors = 889454
+Ave neighs/atom = 24.0082
+Neighbor list builds = 105
+Dangerous builds = 0
+reset_timestep  0
+
+# pin base so will not move during quenches
+
+fix             freeze base setforce 0.0 0.0 0.0
+
+# event detection
+
+compute         event all event/displace ${cutevent}
+compute         event all event/displace 1.1
+
+# hyper/local
+
+fix             HL mobile hyper/local ${cutbond} ${qfactor} ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 ${qfactor} ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 0.3 ${Vmax} ${Tequil}                 ${Dcut} ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 0.3 0.4 ${Tequil}                 ${Dcut} ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 ${Dcut} ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 ${alpha} ${boost}
+fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 200.0 ${boost}
+fix             HL mobile hyper/local 3.2 0.3 0.4 400.0                 10.0 200.0 4000.0
+
+# thermo output
+
+thermo_style    custom step temp pe f_HL f_HL[*]
+WARNING: New thermo_style command, previous thermo_modify settings will be lost (../output.cpp:705)
+
+thermo_modify   lost ignore
+thermo_modify   temp tmobile
+WARNING: Temperature for thermo pressure is not for group all (../thermo.cpp:487)
+
+thermo          ${nevent}
+thermo          100
+
+# dump
+
+region          substrate block INF INF INF INF 1.8 3.8
+region          adatoms block INF INF INF INF 3.8 INF
+variable        acolor atom rmask(base)+2*rmask(substrate)+3*rmask(adatoms)
+
+dump		1 all image 10000000 local.*.jpg v_acolor type size 1024 1024 		zoom ${zoom} adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
+dump		1 all image 10000000 local.*.jpg v_acolor type size 1024 1024 		zoom 1.8 adiam 2.5 view 0.0 0.0 up 0 1 0 axes yes 0.9 0.01
+dump_modify	1 pad 6 amap 1 3 sa 1 3 blue red green
+
+# test of histogramming and dump output of bias coeffs
+
+#fix            histo all ave/histo 10 100 1000 0.9 1.1 100 f_HL #               mode vector kind local file tmp.histo
+#dump           2 all local 1000 tmp.local f_HL
+
+# run
+
+hyper           ${steps} ${nevent} HL event min ${tol} ${tol} 1000 1000 dump 1
+hyper           1500 ${nevent} HL event min ${tol} ${tol} 1000 1000 dump 1
+hyper           1500 100 HL event min ${tol} ${tol} 1000 1000 dump 1
+hyper           1500 100 HL event min 1.0e-15 ${tol} 1000 1000 dump 1
+hyper           1500 100 HL event min 1.0e-15 1.0e-15 1000 1000 dump 1
+WARNING: Resetting reneighboring criteria during hyper (../hyper.cpp:133)
+Neighbor list info ...
+  update every 1 steps, delay 0 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.07583
+  ghost atom cutoff = 12
+  binsize = 3.03792, bins = 62 62 7
+  3 neighbor lists, perpetual/occasional/extra = 1 2 0
+  (1) pair eam/alloy, perpetual
+      attributes: half, newton on
+      pair build: half/bin/atomonly/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+  (2) fix hyper/local, occasional
+      attributes: full, newton on, cut 10
+      pair build: full/bin/atomonly
+      stencil: full/bin/3d
+      bin: standard
+  (3) fix hyper/local, occasional, copy from (1)
+      attributes: half, newton on
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 6.941 | 6.942 | 6.942 Mbytes
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+       0    401.24089   -205562.85            0            0            0            1            0            0            0            0            0            0            0        1e+20            0            0            0            0            0            0            0            0            0            0 
+      77    401.24089   -206534.96            0            0            0            1            0            0            0            0            0            0            0        1e+20            0            0            0            0            0            0         1540            0            0            0 
+Loop time of 0.51152 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+       0    401.24089   -205562.85    24.755808           79   0.18753621            0    6.0138739    705.15041    3.5350432            0            0            0            0        1e+20            0            0            0            0            0            0            0            0            0            0 
+     100     400.6027   -205547.79    21.854739           92   0.43709939   0.99825259    6.0138739    705.15041     4.230764        92.74   0.03245633 0.0067931852   0.99890138   0.98969319    1.0024404            0            0            0            0            0         2000            0            0            0 
+Loop time of 0.453073 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     100     400.6027   -205547.79    21.854739           92   0.43709939   0.99825259    6.0138739    705.15041     4.230764        92.74   0.03245633 0.0067931852   0.99890138   0.98969319    1.0024404            0            0            0            0            0         2000            0            0            0 
+     177     400.6027   -206534.96    21.854739           92   0.43709939   0.99825259    6.0138739    705.15041     4.230764     52.39548   0.03245633 0.0067931852   0.56435106   0.98969319    1.0024404            0            0            0            0            0         3540            0            0            0 
+Loop time of 0.494676 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     100     400.6027   -205547.79    21.854339           92   0.43709939   0.99825259    6.0138739    705.15041     4.230764        92.74   0.03245633 0.0067931852   0.99890138   0.98969319    1.0024404            0            0            0            0            0         2000            0            0            0 
+     200    400.46944    -205544.7    23.349576           97   0.33740983   0.99723256    6.0138739    705.15041     4.230764       92.525  0.040097271 0.0058362605   0.99830632   0.98259113    1.0048777            0            0            0            0            0         4000            0            0            0 
+Loop time of 0.450918 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     200    400.46944    -205544.7    23.349576           97   0.33740983   0.99723256    6.0138739    705.15041     4.230764       92.525  0.040097271 0.0058362605   0.99830632   0.98259113    1.0048777            0            0            0            0            0         4000            0            0            0 
+     273    400.46944   -206534.96    23.349576           97   0.33740983   0.99723256    6.0138739    705.15041     4.230764    67.783883  0.040097271 0.0058362605   0.73135994   0.98259113    1.0048777            0            0            0            0            0         5460            0            0            0 
+Loop time of 0.488918 on 16 procs for 73 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     200    400.46944    -205544.7    23.349184           97   0.33740983   0.99723256    6.0138739    705.15041     4.230764       92.525  0.040097271 0.0058362605   0.99830632   0.98259113    1.0048777            0            0            0            0            0         4000            0            0            0 
+     300    396.89568   -205540.38    19.394419           94   0.35022551   0.99673595    6.0138739    705.15041     4.230764    93.376667  0.047799236 0.0063898904   0.99785232   0.97756247    1.0073497            0            0            0            0            0         6000            0            0            0 
+Loop time of 0.45579 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     300    396.89568   -205540.38    19.394419           94   0.35022551   0.99673595    6.0138739    705.15041     4.230764    93.376667  0.047799236 0.0063898904   0.99785232   0.97756247    1.0073497            0            0            0            0            0         6000            0            0            0 
+     373    396.89568   -206534.96    19.394419           94   0.35022551   0.99673595    6.0138739    705.15041     4.230764    75.101877  0.047799236 0.0063898904   0.80256219   0.97756247    1.0073497            0            0            0            0            0         7460            0            0            0 
+Loop time of 0.49254 on 16 procs for 73 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     300    396.89568   -205540.38    19.394206           94   0.35022551   0.99673595    6.0138739    705.15041     4.230764    93.376667  0.047799236 0.0063898904   0.99785232   0.97756247    1.0073497            0            0            0            0            0         6000            0            0            0 
+     400     399.1218   -205541.68    18.990804           94    0.3505205   0.99638391    6.0138739    705.15041     4.230764      93.3775  0.055982437 0.0068271264   0.99752641   0.97044214    1.0098482            0            0            0            0            0         8000            0            0            0 
+Loop time of 0.452751 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     400     399.1218   -205541.68    18.990804           94    0.3505205   0.99638391    6.0138739    705.15041     4.230764      93.3775  0.055982437 0.0068271264   0.99752641   0.97044214    1.0098482            0            0            0            0            0         8000            0            0            0 
+     475     399.1218   -206534.96    18.990804           94    0.3505205   0.99638391    6.0138739    705.15041     4.230764    78.633684  0.055982437 0.0068271264   0.84002224   0.97044214    1.0098482            0            0            0            0            0         9500            0            0            0 
+Loop time of 0.4963 on 16 procs for 75 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     400     399.1218   -205541.68    18.990689           94    0.3505205   0.99638391    6.0138739    705.15041     4.230764      93.3775  0.055982437 0.0068271264   0.99752641   0.97044214    1.0098482            0            0            0            0            0         8000            0            0            0 
+     500    399.61667   -205539.79    19.794362           99   0.33740217   0.99633812    6.0138739    705.15041     4.230764       93.222  0.063096694 0.0076591363   0.99729174   0.96745199    1.0123163            0            0            0            0            0        10000            0            0            0 
+Loop time of 0.45226 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     500    399.61667   -205539.79    19.794362           99   0.33740217   0.99633812    6.0138739    705.15041     4.230764       93.222  0.063096694 0.0076591363   0.99729174   0.96745199    1.0123163            0            0            0            0            0        10000            0            0            0 
+     577    399.61667   -206534.96    19.794362           99   0.33740217   0.99633812    6.0138739    705.15041     4.230764    80.781629  0.063096694 0.0076591363   0.86420428   0.96745199    1.0123163            0            0            0            0            0        11540            0            0            0 
+Loop time of 0.518479 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     500    399.61667   -205539.79     19.79402           99   0.33740217   0.99633812    6.0138739    705.15041     4.230764       93.222  0.063096694 0.0076591363   0.99729174   0.96745199    1.0123163            0            0            0            0            0        10000            0            0            0 
+     600    397.41676   -205529.51    20.336863           99   0.35185916   0.99625666    6.0138739    705.15041     4.230764    93.621667  0.066686842 0.0091859078   0.99712746   0.96713729    1.0148143            0            0            0            0            0        12000            0            0            0 
+Loop time of 0.452059 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     600    397.41676   -205529.51    20.336863           99   0.35185916   0.99625666    6.0138739    705.15041     4.230764    93.621667  0.066686842 0.0091859078   0.99712746   0.96713729    1.0148143            0            0            0            0            0        12000            0            0            0 
+     677    397.41676   -206534.96    20.336863           99   0.35185916   0.99625666    6.0138739    705.15041     4.230764    82.973412  0.066686842 0.0091859078    0.8837171   0.96713729    1.0148143            0            0            0            0            0        13540            0            0            0 
+Loop time of 0.5171 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     600    397.41676   -205529.51    20.336526           99   0.35185916   0.99625666    6.0138739    705.15041     4.230764    93.621667  0.066686842 0.0091859078   0.99712746   0.96713729    1.0148143            0            0            0            0            0        12000            0            0            0 
+     700    403.33442   -205550.89    18.955866           93   0.42542334   0.99592297    6.0138739    705.15041     4.230764    94.135714  0.068078003 0.0094089081   0.99698101    0.9641519    1.0173022            0            0            0            0            0        14000            0            0            0 
+Loop time of 0.450117 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     700    403.33442   -205550.89    18.955866           93   0.42542334   0.99592297    6.0138739    705.15041     4.230764    94.135714  0.068078003 0.0094089081   0.99698101    0.9641519    1.0173022            0            0            0            0            0        14000            0            0            0 
+     783    403.33442   -206534.96    18.955866           93   0.42542334   0.99592297    6.0138739    705.15041     4.230764    84.157088  0.068078003 0.0094089081   0.89129847    0.9641519    1.0173022            0            0            0            0            0        15660            0            0            0 
+Loop time of 0.541959 on 16 procs for 83 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     700    403.33442   -205550.89    18.955589           93   0.42542334   0.99592297    6.0138739    705.15041     4.230764    94.135714  0.068078003 0.0094089081   0.99698101    0.9641519    1.0173022            0            0            0            0            0        14000            0            0            0 
+     800     397.5897   -205530.58    19.298375           97   0.42432974   0.99573055    6.0138739    705.15041    4.2562861     94.69125  0.070492258 0.0098477948   0.99683461   0.96199283    1.0198015            0            0            0            0            0        16000            0            0            0 
+Loop time of 0.454322 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     800     397.5897   -205530.58    19.298375           97   0.42432974   0.99573055    6.0138739    705.15041    4.2562861     94.69125  0.070492258 0.0098477948   0.99683461   0.96199283    1.0198015            0            0            0            0            0        16000            0            0            0 
+     877     397.5897   -206534.96    19.298375           97   0.42432974   0.99573055    6.0138739    705.15041    4.2562861    86.377423  0.070492258 0.0098477948   0.90931322   0.96199283    1.0198015            0            0            0            0            0        17540            0            0            0 
+Loop time of 0.502899 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     800     397.5897   -205530.58     19.29822           97   0.42432974   0.99573055    6.0138739    705.15041    4.2562861     94.69125  0.070492258 0.0098477948   0.99683461   0.96199283    1.0198015            0            0            0            0            0        16000            0            0            0 
+     900    402.04231   -205545.55    18.434766           91   0.34927854   0.99563819    6.0138739    705.15041    4.2562861    94.956667  0.072594517 0.0091737752   0.99670822   0.95723843    1.0223007            0            0            0            0            0        18000            0            0            0 
+Loop time of 0.451618 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     900    402.04231   -205545.55    18.434766           91   0.34927854   0.99563819    6.0138739    705.15041    4.2562861    94.956667  0.072594517 0.0091737752   0.99670822   0.95723843    1.0223007            0            0            0            0            0        18000            0            0            0 
+     976    402.04231   -206534.96    18.434766           91   0.34927854   0.99563819    6.0138739    705.15041    4.2562861      87.5625  0.072594517 0.0091737752   0.91909569   0.95723843    1.0223007            0            0            0            0            0        19520            0            0            0 
+Loop time of 0.493429 on 16 procs for 76 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+     900    402.04231   -205545.55    18.434576           91   0.34927854   0.99563819    6.0138739    705.15041    4.2562861    94.956667  0.072594517 0.0091737752   0.99670822   0.95723843    1.0223007            0            0            0            0            0        18000            0            0            0 
+    1000    403.13682   -205538.62    20.371378          100   0.36854432   0.99555559    6.0138739    705.15041    4.2562861       94.973  0.075589904 0.0088025018   0.99659567   0.95567008    1.0247999            0            0            0            0            0        20000            0            0            0 
+Loop time of 0.452482 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1000    403.13682   -205538.62    20.371378          100   0.36854432   0.99555559    6.0138739    705.15041    4.2562861       94.973  0.075589904 0.0088025018   0.99659567   0.95567008    1.0247999            0            0            0            0            0        20000            0            0            0 
+    1081    403.13682   -206534.96    20.371378          100   0.36854432   0.99555559    6.0138739    705.15041    4.2562861    87.856614  0.075589904 0.0088025018   0.92192014   0.95567008    1.0247999            0            0            0            0            0        21620            0            0            0 
+Loop time of 0.521678 on 16 procs for 81 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1000    403.13682   -205538.62    20.371013          100   0.36854432   0.99555559    6.0138739    705.15041    4.2562861       94.973  0.075589904 0.0088025018   0.99659567   0.95567008    1.0247999            0            0            0            0            0        20000            0            0            0 
+    1100    401.64961   -205531.15    16.838899           93   0.37998317   0.99541314    6.0138739    705.15041    4.2562861    95.323636  0.077697032 0.0088979171   0.99649521   0.95206312    1.0272987            0            0            0            0            0        22000            0            0            0 
+Loop time of 0.452415 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1100    401.64961   -205531.15    16.838899           93   0.37998317   0.99541314    6.0138739    705.15041    4.2562861    95.323636  0.077697032 0.0088979171   0.99649521   0.95206312    1.0272987            0            0            0            0            0        22000            0            0            0 
+    1179    401.64961   -206534.96    16.838899           93   0.37998317   0.99541314    6.0138739    705.15041    4.2562861    88.936387  0.077697032 0.0088979171   0.92972412   0.95206312    1.0272987            0            0            0            0            0        23580            0            0            0 
+Loop time of 0.50337 on 16 procs for 79 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1100    401.64961   -205531.15    16.838708           93   0.37998317   0.99541314    6.0138739    705.15041    4.2562861    95.323636  0.077697032 0.0088979171   0.99649521   0.95206312    1.0272987            0            0            0            0            0        22000            0            0            0 
+    1200    400.40964   -205539.37    19.135216           99   0.67128843   0.99558682    6.0138739    705.15041    4.6317552       95.505  0.080458266 0.0085684868   0.99641317   0.95050066     1.029798            0            0            0            0            0        24000            0            0            0 
+Loop time of 0.44891 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1200    400.40964   -205539.37    19.135216           99   0.67128843   0.99558682    6.0138739    705.15041    4.6317552       95.505  0.080458266 0.0085684868   0.99641317   0.95050066     1.029798            0            0            0            0            0        24000            0            0            0 
+    1276    400.40964   -206534.97    19.135216           99   0.67128843   0.99558682    6.0138739    705.15041    4.6317552    89.816614  0.080458266 0.0085684868   0.93706567   0.95050066     1.029798            0            0            0            0            0        25520            0            0            0 
+Loop time of 0.508519 on 16 procs for 76 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1200    400.40964   -205539.37    19.448471          100   0.41040038   0.99558682    6.0138739      705.141    4.6317552       95.505  0.080458266 0.0085684868   0.99641317   0.95050066     1.029798    2.2953088            0            0            0            0        24000            1            2            6 
+    1300    401.71843      -205549     19.86411           94   0.31328255   0.99531422    6.0138739      705.141    4.6317552    95.636923  0.080786307 0.0080834567   0.99634504   0.95016182    1.0314365    2.2953088            0            0            0            0        26000            1            2            6 
+Loop time of 0.453256 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1300    401.71843      -205549     19.86411           94   0.31328255   0.99531422    6.0138739      705.141    4.6317552    95.636923  0.080786307 0.0080834567   0.99634504   0.95016182    1.0314365    2.2953088            0            0            0            0        26000            1            2            6 
+    1376    401.71843   -206534.97     19.86411           94   0.31328255   0.99531422    6.0138739      705.141    4.6317552    90.354651  0.080786307 0.0080834567   0.94131435   0.95016182    1.0314365    2.2953088            0            0            0            0        27520            1            2            6 
+Loop time of 0.502886 on 16 procs for 76 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1300    401.71843      -205549    19.863856           94   0.31328255   0.99531422    6.0138739      705.141    4.6317552    95.636923  0.080786307 0.0080834567   0.99634504   0.95016182    1.0314365    2.2953088            0            0            0            0        26000            1            2            6 
+    1400    397.79762   -205534.95    19.064761           90   0.33635396   0.99488167    6.0138739      705.141    4.6317552        95.55  0.080145025 0.0081557898   0.99625782   0.94925079    1.0339117    2.2953088            0            0            0            0        28000            1            2            6 
+Loop time of 0.453094 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1400    397.79762   -205534.95    19.064761           90   0.33635396   0.99488167    6.0138739      705.141    4.6317552        95.55  0.080145025 0.0081557898   0.99625782   0.94925079    1.0339117    2.2953088            0            0            0            0        28000            1            2            6 
+    1477    397.79762   -206534.97    19.064761           90   0.33635396   0.99488167    6.0138739      705.141    4.6317552     90.56872  0.080145025 0.0081557898   0.94432021   0.94925079    1.0339117    2.2953088            0            0            0            0        29540            1            2            6 
+Loop time of 0.515217 on 16 procs for 77 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1400    397.79762   -205534.95    19.064345           90   0.33635396   0.99488167    6.0138739      705.141    4.6317552        95.55  0.080145025 0.0081557898   0.99625782   0.94925079    1.0339117    2.2953088            0            0            0            0        28000            1            2            6 
+    1500    400.56079   -205539.86    18.860257           93   0.35488977   0.99467946    6.0138739      705.141    4.6317552    95.578667  0.080575861 0.0083561185   0.99615829   0.94636637    1.0355154    2.2953088            0            0            0            0        30000            1            2            6 
+Loop time of 0.450111 on 16 procs for 100 steps with 37048 atoms
+
+Step Temp PotEng f_HL f_HL[1] f_HL[2] f_HL[3] f_HL[4] f_HL[5] f_HL[6] f_HL[7] f_HL[8] f_HL[9] f_HL[10] f_HL[11] f_HL[12] f_HL[13] f_HL[14] f_HL[15] f_HL[16] f_HL[17] f_HL[18] f_HL[19] f_HL[20] f_HL[21] 
+    1500    400.56079   -205539.86    18.860257           93   0.35488977   0.99467946    6.0138739      705.141    4.6317552    95.578667  0.080575861 0.0083561185   0.99615829   0.94636637    1.0355154    2.2953088            0            0            0            0        30000            1            2            6 
+    1584    400.56079   -206534.97    18.860257           93   0.35488977   0.99467946    6.0138739      705.141    4.6317552    90.510101  0.080575861 0.0083561185   0.94333171   0.94636637    1.0355154    2.2953088            0            0            0            0        31680            1            2            6 
+Loop time of 0.566455 on 16 procs for 84 steps with 37048 atoms
+
+Final hyper stats ...
+
+Cummulative quantities for fix hyper:
+  hyper time = 30000
+  time boost factor = 4000
+  event timesteps = 1
+  # of atoms in events = 2
+Quantities for this hyper run:
+  event timesteps = 1
+  # of atoms in events = 2
+  max length of any bond = 4.63176
+  max drift distance of any atom = 2.29531
+  fraction of biased bonds with zero bias = 0.0805759
+  fraction of biased bonds with negative strain = 0.00835612
+Current quantities:
+  ave bonds/atom = 6.01387
+Cummulative quantities specific to fix hyper/local:
+  # of new bonds formed = 6
+  max bonds/atom = 13
+Quantities for this hyper run specific to fix hyper/local:
+  ave biased bonds/step = 95.5787
+  ave bias coeff of all bonds = 0.996158
+  min bias coeff of any bond = 0.946366
+  max bias coeff of any bond = 1.03552
+  max dist from my subbox of any non-maxstrain bond ghost atom = 0
+  max dist from my box of any bond ghost atom = 0
+  count of bond ghost neighbors not found on reneighbor steps = 0
+  bias overlaps = 0
+  CPU time for bond builds = 0.0147002
+Current quantities specific to fix hyper/local:
+  neighbor bonds/bond = 705.141
+  ave boost coeff for all bonds = 0.994679
+
+Loop time of 14.9193 on 16 procs for 1500 steps with 37048 atoms
+
+Performance: 43.434 ns/day, 0.553 hours/ns, 100.541 timesteps/s
+128.3% CPU use with 16 MPI tasks x no OpenMP threads
+
+Hyper stats:
+  Dynamics time (%) = 6.78318 (45.4657)
+  Quench   time (%) = 7.66443 (51.3725)
+  Other    time (%) = 0.189889 (1.27277)
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 11.726     | 11.881     | 12.051     |   2.6 | 79.64
+Neigh   | 0.49995    | 0.52243    | 0.54427    |   1.9 |  3.50
+Comm    | 0.34477    | 0.51495    | 0.62326    |  10.4 |  3.45
+Output  | 0.0017493  | 0.0017652  | 0.0018535  |   0.1 |  0.01
+Modify  | 1.7669     | 1.8088     | 1.8523     |   1.7 | 12.12
+Other   |            | 0.1899     |            |       |  1.27
+
+Nlocal:    2315.5 ave 2353 max 2275 min
+Histogram: 1 1 1 3 0 2 5 2 0 1
+Nghost:    3187.62 ave 3228 max 3148 min
+Histogram: 1 0 2 4 2 2 1 3 0 1
+Neighs:    54002.8 ave 54567 max 53263 min
+Histogram: 1 0 2 1 3 2 2 1 1 3
+FullNghs:  542996 ave 554820 max 527895 min
+Histogram: 1 0 0 4 1 3 3 2 0 2
+
+Total # of neighbors = 8687932
+Ave neighs/atom = 234.505
+Neighbor list builds = 166
+Dangerous builds = 0
+Total wall time: 0:00:19
diff --git a/examples/kim/in.query b/examples/kim/in.query
new file mode 100644
index 0000000000..33272dc298
--- /dev/null
+++ b/examples/kim/in.query
@@ -0,0 +1,11 @@
+
+# example for performing a query to the OpenKIM test database to retrieve
+# a parameter to be used in the input. here it requests the aluminium
+# lattice constant for a specific test used for a specific model and then
+# assigns it to the variable 'latconst'
+
+units metal
+info variables out log
+kim_query latconst get_test_result test=TE_156715955670 species=["Al"] model=MO_800509458712 prop=structure-cubic-crystal-npt keys=["a"] units=["angstrom"]
+info variables out log
+lattice fcc ${latconst}
diff --git a/examples/kim/log.22Mar2019.query.g++.1 b/examples/kim/log.22Mar2019.query.g++.1
new file mode 100644
index 0000000000..034bb13bba
--- /dev/null
+++ b/examples/kim/log.22Mar2019.query.g++.1
@@ -0,0 +1,34 @@
+LAMMPS (28 Feb 2019)
+
+# example for performing a query to the OpenKIM test database to retrieve
+# a parameter to be used in the input. here it requests the aluminium
+# lattice constant for a specific test used for a specific model and then
+# assigns it to the variable 'latconst'
+
+units metal
+info variables out log
+
+Info-Info-Info-Info-Info-Info-Info-Info-Info-Info-Info
+Printed on Fri Mar 22 20:00:56 2019
+
+
+Variable information:
+
+Info-Info-Info-Info-Info-Info-Info-Info-Info-Info-Info
+
+kim_query latconst get_test_result test=TE_156715955670 species=["Al"] model=MO_800509458712 prop=structure-cubic-crystal-npt keys=["a"] units=["angstrom"]
+info variables out log
+
+Info-Info-Info-Info-Info-Info-Info-Info-Info-Info-Info
+Printed on Fri Mar 22 20:00:57 2019
+
+
+Variable information:
+Variable[  0]: latconst  ,  style = string    ,  def = 4.03208274841
+
+Info-Info-Info-Info-Info-Info-Info-Info-Info-Info-Info
+
+lattice fcc ${latconst}
+lattice fcc 4.03208274841
+Lattice spacing in x,y,z = 4.03208 4.03208 4.03208
+Total wall time: 0:00:00
diff --git a/examples/micelle/data.micelle b/examples/micelle/data.micelle
index e4805bceee..5ff6196bc6 100644
--- a/examples/micelle/data.micelle
+++ b/examples/micelle/data.micelle
@@ -49,7 +49,7 @@
      22      0      1  25.100   0.000   0.000
      23      0      1  26.295   0.000   0.000
      24    110      2  27.490   0.000   0.000
-     25    128      2  28.685   0.000   0.000
+     25    128      2  28.685  35.85686 0.000
      26      0      1  29.881   0.000   0.000
      27      0      1  31.076   0.000   0.000
      28      0      1  32.271   0.000   0.000
@@ -175,7 +175,7 @@
     148      0      1  32.271   4.781   0.000
     149      0      1  33.466   4.781   0.000
     150      0      1  34.662   4.781   0.000
-    151     53      2   0.000   5.976   0.000
+    151     53      2 35.85686  5.976   0.000
     152      0      1   1.195   5.976   0.000
     153      0      1   2.390   5.976   0.000
     154      0      1   3.586   5.976   0.000
@@ -655,7 +655,7 @@
     628      0      1  32.271  23.905   0.000
     629      0      1  33.466  23.905   0.000
     630      0      1  34.662  23.905   0.000
-    631    148      2   0.000  25.100   0.000
+    631    148      2 35.85686 25.100   0.000
     632      0      1   1.195  25.100   0.000
     633      0      1   2.390  25.100   0.000
     634      0      1   3.586  25.100   0.000
@@ -976,7 +976,7 @@
     949     25      3   0.677  33.143   0.000
     950     25      4   1.353  32.819   0.000
     951     26      3  35.071  18.557   0.000
-    952     26      4  35.480  19.186   0.000
+    952     26      4 35.48000 19.186   0.000
     953     27      3  29.131  15.504   0.000
     954     27      4  28.382  15.470   0.000
     955     28      3  23.456  33.395   0.000
@@ -1096,7 +1096,7 @@
    1069     85      3  33.021  33.461   0.000
    1070     85      4  33.771  33.455   0.000
    1071     86      3   0.552  18.315   0.000
-   1072     86      4  35.766  18.701   0.000
+   1072     86      4 -0.09086 18.701   0.000
    1073     87      3  28.026  32.796   0.000
    1074     87      4  28.562  33.321   0.000
    1075     88      3  24.351  29.925   0.000
@@ -1112,7 +1112,7 @@
    1085     93      3  26.170  16.278   0.000
    1086     93      4  26.046  17.017   0.000
    1087     94      3  10.380   0.547   0.000
-   1088     94      4  10.003  35.755   0.000
+   1088     94      4  10.003 -0.10186  0.000
    1089     95      3   0.419  29.308   0.000
    1090     95      4   0.837  29.930   0.000
    1091     96      3  13.712  28.191   0.000
diff --git a/examples/micelle/in.micelle b/examples/micelle/in.micelle
index 2abdd18734..34bc9ad359 100644
--- a/examples/micelle/in.micelle
+++ b/examples/micelle/in.micelle
@@ -58,7 +58,7 @@ pair_coeff	1 4 1.0 1.0 1.12246
 pair_coeff	2 3 1.0 0.88 1.12246
 pair_coeff	2 4 1.0 0.75 1.12246
 
-thermo		1000
+thermo		50
 
 #dump		1 all atom 2000 dump.micelle
 
@@ -69,4 +69,4 @@ thermo		1000
 #dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
 
 reset_timestep	0
-run		60000
+run		1000
diff --git a/examples/micelle/in.micelle-rigid b/examples/micelle/in.micelle-rigid
new file mode 100644
index 0000000000..93cb2655f8
--- /dev/null
+++ b/examples/micelle/in.micelle-rigid
@@ -0,0 +1,87 @@
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+special_bonds	fene
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		500
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		50
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+group solvent   molecule 0
+group solute    subtract all solvent
+unfix 1
+unfix 2
+unfix 4
+fix		1 solvent nve
+fix		2 solvent temp/rescale 100 0.45 0.45 0.02 1.0
+fix		5 solute rigid molecule langevin 0.45 0.45 0.5 112211
+fix		4 all enforce2d
+run		500
+unfix 2
+unfix 4
+unfix 5
+fix		5 solute rigid/small molecule
+fix		4 all enforce2d
+run		500
diff --git a/examples/micelle/in.micelle.rigid b/examples/micelle/in.micelle.rigid
new file mode 100644
index 0000000000..47d2f74950
--- /dev/null
+++ b/examples/micelle/in.micelle.rigid
@@ -0,0 +1,86 @@
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+special_bonds	fene
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		1000
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		1000
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+group solvent   molecule 0
+group solute    subtract all solvent
+unfix 1
+unfix 2
+unfix 4
+fix		1 solvent nve
+fix		2 solvent temp/rescale 100 0.45 0.45 0.02 1.0
+fix		5 solute rigid molecule langevin 0.45 0.45 0.5 112211
+fix		4 all enforce2d
+run		20000
+unfix 5
+unfix 4
+fix		5 solute rigid/small molecule langevin 0.45 0.45 0.5 112211
+fix		4 all enforce2d
+run		20000
diff --git a/examples/micelle/log.27Nov18.micelle.g++.1 b/examples/micelle/log.27Nov18.micelle.g++.1
deleted file mode 100644
index 30a965e041..0000000000
--- a/examples/micelle/log.27Nov18.micelle.g++.1
+++ /dev/null
@@ -1,255 +0,0 @@
-LAMMPS (27 Nov 2018)
-  using 1 OpenMP thread(s) per MPI task
-# 2d micelle simulation
-
-dimension	2
-
-neighbor	0.3 bin
-neigh_modify	delay 5
-
-atom_style	bond
-
-# Soft potential push-off
-
-read_data	data.micelle
-  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  1200 atoms
-  scanning bonds ...
-  1 = max bonds/atom
-  reading bonds ...
-  300 bonds
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-special_bonds	fene
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-pair_style	soft 1.12246
-pair_coeff	* * 0.0 1.12246
-
-bond_style 	harmonic
-bond_coeff	1 50.0 0.75
-
-velocity	all create 0.45 2349852
-
-variable	prefactor equal ramp(1.0,20.0)
-
-fix		1 all nve
-fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
-fix		3 all adapt 1 pair soft a * * v_prefactor
-fix		4 all enforce2d
-
-thermo		50
-run		1000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 1.42246
-  ghost atom cutoff = 1.42246
-  binsize = 0.71123, bins = 51 51 1
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair soft, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/2d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.799 | 3.799 | 3.799 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
-      50   0.47411013   0.67721272  0.057404514    1.2083323    1.3375852 
-     100         0.45   0.73046745  0.054836584     1.234929    2.3196516 
-     150   0.67521742   0.72402001  0.043490075    1.4421648    2.8744416 
-     200         0.45   0.78481891  0.076931503    1.3113754    3.0412388 
-     250   0.66479018   0.69790602  0.081075564    1.4432178    3.6917024 
-     300         0.45   0.76820218  0.066727591    1.2845548    3.7861054 
-     350   0.67619136     0.625715  0.072722727    1.3740656    4.2861621 
-     400         0.45   0.68527759  0.090724527    1.2256271    4.4725214 
-     450   0.56702844   0.64402767  0.080555563    1.2911391    4.7402211 
-     500         0.45   0.64883009  0.078376672    1.1768318    4.7919294 
-     550     0.564664   0.58260368  0.080779475    1.2275766    4.9855705 
-     600         0.45   0.58193041  0.088386617     1.119942     5.131481 
-     650   0.52110993    0.5415273  0.097683746    1.1598867    5.2500294 
-     700         0.45   0.50856787  0.088471208    1.0466641    5.2550165 
-     750   0.51510855   0.47441291  0.089429375    1.0785216     5.375763 
-     800         0.45   0.49926696  0.085958476    1.0348504    5.4665914 
-     850   0.50688494   0.46614429  0.088962292    1.0615691     5.556932 
-     900         0.45   0.47785593   0.10150857    1.0289895    5.7765975 
-     950   0.49590559   0.46050477  0.096404887     1.052402    5.8649245 
-    1000         0.45   0.47691182   0.08808163    1.0146185    6.0177568 
-Loop time of 0.167265 on 1 procs for 1000 steps with 1200 atoms
-
-Performance: 2582728.958 tau/day, 5978.539 timesteps/s
-99.1% CPU use with 1 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 0.096171   | 0.096171   | 0.096171   |   0.0 | 57.50
-Bond    | 0.006212   | 0.006212   | 0.006212   |   0.0 |  3.71
-Neigh   | 0.024826   | 0.024826   | 0.024826   |   0.0 | 14.84
-Comm    | 0.0047672  | 0.0047672  | 0.0047672  |   0.0 |  2.85
-Output  | 0.00029063 | 0.00029063 | 0.00029063 |   0.0 |  0.17
-Modify  | 0.028771   | 0.028771   | 0.028771   |   0.0 | 17.20
-Other   |            | 0.006227   |            |       |  3.72
-
-Nlocal:    1200 ave 1200 max 1200 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    195 ave 195 max 195 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    3136 ave 3136 max 3136 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 3136
-Ave neighs/atom = 2.61333
-Ave special neighs/atom = 0.5
-Neighbor list builds = 92
-Dangerous builds = 0
-
-unfix		3
-
-# Main run
-
-pair_style	lj/cut 2.5
-
-# solvent/head - full-size and long-range
-
-pair_coeff	1 1 1.0 1.0 2.5
-pair_coeff	2 2 1.0 1.0 2.5
-pair_coeff	1 2 1.0 1.0 2.5
-
-# tail/tail - size-averaged and long-range
-
-pair_coeff	3 3 1.0 0.75 2.5
-pair_coeff	4 4 1.0 0.50 2.5
-pair_coeff	3 4 1.0 0.67 2.5
-
-# solvent/tail - full-size and repulsive
-
-pair_coeff	1 3 1.0 1.0 1.12246
-pair_coeff	1 4 1.0 1.0 1.12246
-
-# head/tail - size-averaged and repulsive
-
-pair_coeff	2 3 1.0 0.88 1.12246
-pair_coeff	2 4 1.0 0.75 1.12246
-
-thermo		1000
-
-#dump		1 all atom 2000 dump.micelle
-
-#dump		2 all image 2000 image.*.jpg type type zoom 1.6
-#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
-
-#dump		3 all movie 2000 movie.mpg type type zoom 1.6
-#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
-
-reset_timestep	0
-run		60000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 2.8
-  ghost atom cutoff = 2.8
-  binsize = 1.4, bins = 26 26 1
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair lj/cut, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/2d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 4.024 | 4.024 | 4.024 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         0.45   -1.7056163   0.08808163   -1.1679097    3.9431686 
-    1000         0.45   -1.9727655  0.058608715   -1.4645318    1.9982298 
-    2000   0.46465361   -1.9897467  0.067008449   -1.4584719    1.5873463 
-    3000   0.46175071   -2.0129279  0.057865385   -1.4936966      1.41269 
-    4000   0.44386154   -2.0280304  0.067167835   -1.5173709    1.4022093 
-    5000   0.46127582   -2.0556041  0.068318674    -1.526394    1.1416711 
-    6000   0.45354052   -2.0463246   0.05461954   -1.5385425    1.1650258 
-    7000   0.44082313    -2.040263  0.060218047   -1.5395891    1.3258681 
-    8000   0.44353466   -2.0423792  0.061769402   -1.5374447    1.2696989 
-    9000   0.46192977   -2.0761348  0.064999109   -1.5495908    0.9205826 
-   10000   0.45278646   -2.0589872  0.059623919   -1.5469542     1.075581 
-   11000   0.45583355   -2.0661957  0.058197558   -1.5525445     1.127643 
-   12000   0.45881198   -2.0921508  0.066937896   -1.5667833   0.98383574 
-   13000   0.45339481    -2.079088   0.06292782   -1.5631432    1.0188637 
-   14000   0.43601312   -2.0624084  0.057999616    -1.568759    1.1452177 
-   15000   0.45941503   -2.0746606  0.062523373    -1.553105   0.86928343 
-   16000         0.45   -2.0743162   0.05517924    -1.569512   0.86849848 
-   17000   0.45603004   -2.0657683  0.058711872   -1.5514064   0.95544551 
-   18000   0.45320383   -2.1009711  0.060716634   -1.5874283    0.8343521 
-   19000   0.44072983   -2.0846408  0.062893297    -1.581385   0.90776246 
-   20000   0.44452441   -2.0921415  0.060341571    -1.587646   0.98180005 
-   21000   0.45964557   -2.0837047  0.054459432   -1.5699827    1.0213779 
-   22000   0.46351849   -2.1053613  0.058392027   -1.5838371   0.81579487 
-   23000   0.45576065   -2.1001888  0.057646538   -1.5871614   0.76090085 
-   24000   0.44671746   -2.0848717  0.058192801   -1.5803337   0.77003809 
-   25000   0.44371239   -2.0870872  0.054804981   -1.5889396   0.92295746 
-   26000   0.45381188    -2.097021  0.057195346    -1.586392    0.7743058 
-   27000   0.46158533   -2.1071056  0.061289644   -1.5846153   0.78981802 
-   28000   0.46534671   -2.1056151  0.054934755   -1.5857214   0.80778664 
-   29000    0.4505804   -2.0949318  0.065503451   -1.5792234   0.78274755 
-   30000   0.45730883   -2.1029161  0.063461968   -1.5825264   0.82507857 
-   31000    0.4620071   -2.1124989  0.059980378   -1.5908964   0.78583986 
-   32000   0.46934619   -2.1107818  0.056442616   -1.5853842   0.70535653 
-   33000   0.45800203   -2.1062502  0.054317859    -1.594312     0.726293 
-   34000   0.44634295    -2.110401  0.057764968    -1.606665   0.85401059 
-   35000    0.4431929   -2.1274759  0.062048133   -1.6226042   0.64243758 
-   36000   0.46049645   -2.1300979  0.068463634   -1.6015216   0.57252544 
-   37000   0.45366344   -2.0977407  0.053788554   -1.5906668   0.78046879 
-   38000   0.44155077   -2.1166674  0.056888683   -1.6185959   0.53429042 
-   39000   0.45631012    -2.096949   0.04860872   -1.5924104   0.86494908 
-   40000   0.44684402   -2.1229137  0.067190397   -1.6092516   0.65110818 
-   41000    0.4479377   -2.1105264  0.059375259   -1.6035867   0.79092862 
-   42000   0.46143191   -2.1174539  0.057418393   -1.5989882   0.69762908 
-   43000    0.4356786    -2.085826  0.056534028   -1.5939764   0.89541946 
-   44000   0.45806826    -2.126423  0.060905733   -1.6078307   0.66389027 
-   45000   0.44343688   -2.1116384  0.065870114    -1.602701   0.83947585 
-   46000   0.43844672   -2.1096265  0.064158652   -1.6073865   0.77278902 
-   47000   0.45794928   -2.1142786  0.058919562   -1.5977914   0.62611933 
-   48000   0.45412335   -2.1106058  0.059153304   -1.5977076   0.66190677 
-   49000   0.45927883   -2.1197656  0.068354598   -1.5925149   0.56008845 
-   50000   0.44117285   -2.1020783  0.064763249   -1.5965099   0.85935147 
-   51000   0.45325398   -2.1125154  0.062295387   -1.5973438   0.80951782 
-   52000   0.43896579   -2.1039004  0.057475908   -1.6078245   0.84753768 
-   53000   0.45180671   -2.1092446  0.063528598   -1.5942857   0.67065038 
-   54000    0.4554341   -2.1185135  0.059603337   -1.6038556   0.76399618 
-   55000   0.43861159   -2.0986406  0.057733879   -1.6026606   0.77334084 
-   56000   0.45522991   -2.1207166  0.063287543   -1.6025785   0.78669598 
-   57000   0.46125513   -2.1150202   0.06026261   -1.5938868   0.78148646 
-   58000   0.45236938   -2.1088894  0.062678374   -1.5942186   0.75643518 
-   59000   0.43927269   -2.1274165  0.055355076   -1.6331548   0.63495311 
-   60000   0.45331102   -2.1336193  0.051244399   -1.6294416   0.56706921 
-Loop time of 13.9361 on 1 procs for 60000 steps with 1200 atoms
-
-Performance: 1859917.639 tau/day, 4305.365 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 9.2211     | 9.2211     | 9.2211     |   0.0 | 66.17
-Bond    | 0.33763    | 0.33763    | 0.33763    |   0.0 |  2.42
-Neigh   | 2.3772     | 2.3772     | 2.3772     |   0.0 | 17.06
-Comm    | 0.37693    | 0.37693    | 0.37693    |   0.0 |  2.70
-Output  | 0.0011795  | 0.0011795  | 0.0011795  |   0.0 |  0.01
-Modify  | 1.2727     | 1.2727     | 1.2727     |   0.0 |  9.13
-Other   |            | 0.3493     |            |       |  2.51
-
-Nlocal:    1200 ave 1200 max 1200 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    405 ave 405 max 405 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    9565 ave 9565 max 9565 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 9565
-Ave neighs/atom = 7.97083
-Ave special neighs/atom = 0.5
-Neighbor list builds = 4876
-Dangerous builds = 0
-Total wall time: 0:00:14
diff --git a/examples/micelle/log.27Nov18.micelle.g++.4 b/examples/micelle/log.27Nov18.micelle.g++.4
deleted file mode 100644
index c9509df4b2..0000000000
--- a/examples/micelle/log.27Nov18.micelle.g++.4
+++ /dev/null
@@ -1,255 +0,0 @@
-LAMMPS (27 Nov 2018)
-  using 1 OpenMP thread(s) per MPI task
-# 2d micelle simulation
-
-dimension	2
-
-neighbor	0.3 bin
-neigh_modify	delay 5
-
-atom_style	bond
-
-# Soft potential push-off
-
-read_data	data.micelle
-  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
-  2 by 2 by 1 MPI processor grid
-  reading atoms ...
-  1200 atoms
-  scanning bonds ...
-  1 = max bonds/atom
-  reading bonds ...
-  300 bonds
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-special_bonds	fene
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-pair_style	soft 1.12246
-pair_coeff	* * 0.0 1.12246
-
-bond_style 	harmonic
-bond_coeff	1 50.0 0.75
-
-velocity	all create 0.45 2349852
-
-variable	prefactor equal ramp(1.0,20.0)
-
-fix		1 all nve
-fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
-fix		3 all adapt 1 pair soft a * * v_prefactor
-fix		4 all enforce2d
-
-thermo		50
-run		1000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 1.42246
-  ghost atom cutoff = 1.42246
-  binsize = 0.71123, bins = 51 51 1
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair soft, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/2d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.758 | 3.85 | 4.126 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
-      50   0.47411013   0.67721272  0.057404514    1.2083323    1.3375852 
-     100         0.45   0.73046745  0.054836584     1.234929    2.3196516 
-     150   0.67521742   0.72402001  0.043490075    1.4421648    2.8744416 
-     200         0.45   0.78481891  0.076931503    1.3113754    3.0412388 
-     250   0.66479018   0.69790602  0.081075564    1.4432178    3.6917024 
-     300         0.45   0.76820218  0.066727591    1.2845548    3.7861054 
-     350   0.67619136     0.625715  0.072722727    1.3740656    4.2861621 
-     400         0.45   0.68527759  0.090724527    1.2256271    4.4725214 
-     450   0.56702844   0.64402767  0.080555563    1.2911391    4.7402211 
-     500         0.45   0.64883009  0.078376672    1.1768318    4.7919294 
-     550     0.564664   0.58260368  0.080779475    1.2275766    4.9855705 
-     600         0.45   0.58193041  0.088386617     1.119942     5.131481 
-     650   0.52110993    0.5415273  0.097683746    1.1598867    5.2500294 
-     700         0.45   0.50856787  0.088471208    1.0466641    5.2550165 
-     750   0.51510855   0.47441291  0.089429375    1.0785216     5.375763 
-     800         0.45   0.49926696  0.085958476    1.0348504    5.4665914 
-     850   0.50688494   0.46614429  0.088962292    1.0615691     5.556932 
-     900         0.45   0.47785593   0.10150857    1.0289895    5.7765975 
-     950   0.49590559   0.46050477  0.096404887     1.052402    5.8649245 
-    1000         0.45   0.47691182   0.08808163    1.0146185    6.0177568 
-Loop time of 0.0641922 on 4 procs for 1000 steps with 1200 atoms
-
-Performance: 6729792.131 tau/day, 15578.223 timesteps/s
-90.9% CPU use with 4 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 0.020663   | 0.021445   | 0.022477   |   0.5 | 33.41
-Bond    | 0.0014422  | 0.0015128  | 0.001569   |   0.1 |  2.36
-Neigh   | 0.0067129  | 0.0067645  | 0.0068202  |   0.1 | 10.54
-Comm    | 0.018454   | 0.019275   | 0.020386   |   0.5 | 30.03
-Output  | 0.00038171 | 0.00040019 | 0.00044632 |   0.0 |  0.62
-Modify  | 0.010561   | 0.010904   | 0.011309   |   0.3 | 16.99
-Other   |            | 0.003891   |            |       |  6.06
-
-Nlocal:    300 ave 305 max 292 min
-Histogram: 1 0 0 0 0 0 1 0 1 1
-Nghost:    100.25 ave 108 max 93 min
-Histogram: 1 0 1 0 0 0 1 0 0 1
-Neighs:    784 ave 815 max 739 min
-Histogram: 1 0 0 0 0 0 1 1 0 1
-
-Total # of neighbors = 3136
-Ave neighs/atom = 2.61333
-Ave special neighs/atom = 0.5
-Neighbor list builds = 92
-Dangerous builds = 0
-
-unfix		3
-
-# Main run
-
-pair_style	lj/cut 2.5
-
-# solvent/head - full-size and long-range
-
-pair_coeff	1 1 1.0 1.0 2.5
-pair_coeff	2 2 1.0 1.0 2.5
-pair_coeff	1 2 1.0 1.0 2.5
-
-# tail/tail - size-averaged and long-range
-
-pair_coeff	3 3 1.0 0.75 2.5
-pair_coeff	4 4 1.0 0.50 2.5
-pair_coeff	3 4 1.0 0.67 2.5
-
-# solvent/tail - full-size and repulsive
-
-pair_coeff	1 3 1.0 1.0 1.12246
-pair_coeff	1 4 1.0 1.0 1.12246
-
-# head/tail - size-averaged and repulsive
-
-pair_coeff	2 3 1.0 0.88 1.12246
-pair_coeff	2 4 1.0 0.75 1.12246
-
-thermo		1000
-
-#dump		1 all atom 2000 dump.micelle
-
-#dump		2 all image 2000 image.*.jpg type type zoom 1.6
-#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
-
-#dump		3 all movie 2000 movie.mpg type type zoom 1.6
-#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
-
-reset_timestep	0
-run		60000
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 2.8
-  ghost atom cutoff = 2.8
-  binsize = 1.4, bins = 26 26 1
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair lj/cut, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/2d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 4.001 | 4.032 | 4.124 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         0.45   -1.7056163   0.08808163   -1.1679097    3.9431686 
-    1000         0.45   -1.9727661   0.05860859   -1.4645325    1.9982402 
-    2000   0.45146247   -1.9766043  0.059408886   -1.4661092    1.7398826 
-    3000   0.43338517   -2.0028125  0.059884381   -1.5099041    1.4716488 
-    4000   0.46674519   -2.0200954  0.066548679   -1.4871905    1.2506693 
-    5000         0.45   -2.0207125  0.055926205   -1.5151613    1.3047457 
-    6000   0.45447759   -2.0585234  0.068004883   -1.5364197    1.1859762 
-    7000   0.43183018   -2.0170545  0.060800296   -1.5247839    1.3074223 
-    8000   0.46657547    -2.053224  0.063224367    -1.523813    1.1785643 
-    9000         0.45   -2.0691221  0.054959029    -1.564538    1.1833657 
-   10000    0.4428252   -2.0473987  0.054306905   -1.5506356     1.181794 
-   11000   0.45407036   -2.0746151  0.065849667   -1.5550734    1.1008545 
-   12000   0.46061944   -2.0580809  0.063129643   -1.5347156    1.0206491 
-   13000   0.45159068   -2.0640832  0.060059758   -1.5528091    1.0813494 
-   14000   0.44141594   -2.0467255  0.062785088   -1.5428923    1.1465772 
-   15000     0.454361   -2.0908595  0.057471037   -1.5794061   0.84297781 
-   16000   0.44061091   -2.0521452  0.064644196   -1.5472573    1.1478647 
-   17000   0.45118383    -2.081348  0.058660999   -1.5718791    1.0101404 
-   18000   0.44664866   -2.0845745  0.060435731   -1.5778623   0.96142277 
-   19000   0.45515339   -2.0914006  0.062174016   -1.5744525   0.87623323 
-   20000   0.45624408   -2.0837697  0.059263054   -1.5686428   0.92810644 
-   21000   0.46791657   -2.1062007  0.067355929   -1.5713181   0.88318793 
-   22000   0.43907391   -2.1005271  0.065885144   -1.5959339   0.77211644 
-   23000   0.43967354   -2.0723459  0.057613471   -1.5754253    1.0371548 
-   24000   0.45716384   -2.0987126  0.055157377   -1.5867723   0.89670061 
-   25000   0.45828285   -2.1041616  0.057736138   -1.5885245   0.79952286 
-   26000         0.45   -2.0743463  0.072455519   -1.5522658   0.88260204 
-   27000   0.46581599   -2.0804974  0.058113258   -1.5569564   0.93053891 
-   28000   0.46904194   -2.0920124  0.059748792   -1.5636125   0.79359618 
-   29000   0.46093196    -2.118556  0.063942334   -1.5940659   0.67707604 
-   30000   0.45733724   -2.1197827  0.066939064   -1.5958875   0.66886075 
-   31000   0.44580762   -2.0977175  0.056969121   -1.5953123   0.81042562 
-   32000   0.44403029   -2.1032264  0.063465127    -1.596101   0.71796412 
-   33000   0.45834072   -2.0934132  0.066035391    -1.569419   0.77873998 
-   34000   0.44981563   -2.0910902   0.07138738   -1.5702621   0.75679805 
-   35000   0.45383392   -2.0926654  0.067553478   -1.5716562    0.9064517 
-   36000   0.44447198   -2.1107114  0.062718917   -1.6038909    0.8538349 
-   37000   0.45838527   -2.1166464  0.062442606   -1.5962005    0.7300635 
-   38000   0.45014075   -2.1096258  0.059293718   -1.6005665   0.73988246 
-   39000   0.44377026    -2.080309  0.063545781   -1.5733628   0.99775641 
-   40000   0.44577324   -2.1134607  0.065271179   -1.6027878   0.64113168 
-   41000         0.45   -2.0937983  0.060881377   -1.5832919   0.78849829 
-   42000   0.46866695   -2.1142283  0.056417605   -1.5895343   0.73788436 
-   43000   0.43211727   -2.0819893  0.061463358   -1.5887688   0.95853724 
-   44000   0.44138397   -2.0921314  0.059643895   -1.5914713   0.89486208 
-   45000         0.45    -2.117209  0.054804331   -1.6127797   0.78564885 
-   46000   0.44285245   -2.1090975  0.057629006   -1.6089851   0.64549424 
-   47000   0.45537009   -2.1164296  0.068582324   -1.5928567   0.73629413 
-   48000   0.45046732   -2.1006362  0.057249591   -1.5932947   0.74317593 
-   49000   0.45425966   -2.1191703  0.064247719   -1.6010414   0.70962368 
-   50000   0.45506149   -2.1184671  0.064911797   -1.5988731   0.69958156 
-   51000   0.46047417   -2.1019719  0.058468259   -1.5834132   0.87219271 
-   52000   0.43808317    -2.092294  0.057280941    -1.597295   0.84156893 
-   53000   0.45012337   -2.1175234  0.064002667   -1.6037725   0.64562439 
-   54000   0.43854679   -2.1236444  0.061316257   -1.6241468   0.72478117 
-   55000   0.46382438   -2.1016563  0.060724666   -1.5774938   0.83311209 
-   56000   0.44951533   -2.0946157  0.055075217   -1.5903998   0.90066109 
-   57000   0.45937401   -2.0983442  0.061558996    -1.577794   0.58606161 
-   58000     0.446669   -2.1146838  0.062385166   -1.6060019   0.73443388 
-   59000   0.43847747   -2.1197461  0.060460257   -1.6211738    0.7230937 
-   60000   0.45294215   -2.1258513  0.061895006   -1.6113915   0.70722168 
-Loop time of 4.56226 on 4 procs for 60000 steps with 1200 atoms
-
-Performance: 5681397.232 tau/day, 13151.382 timesteps/s
-97.1% CPU use with 4 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 2.2114     | 2.2527     | 2.3592     |   4.1 | 49.38
-Bond    | 0.083713   | 0.09234    | 0.10244    |   2.3 |  2.02
-Neigh   | 0.72491    | 0.7277     | 0.72957    |   0.2 | 15.95
-Comm    | 0.79464    | 0.90036    | 0.94957    |   6.5 | 19.74
-Output  | 0.0014119  | 0.0024976  | 0.0057502  |   3.8 |  0.05
-Modify  | 0.33757    | 0.35202    | 0.36946    |   2.1 |  7.72
-Other   |            | 0.2346     |            |       |  5.14
-
-Nlocal:    300 ave 306 max 289 min
-Histogram: 1 0 0 0 0 0 0 1 1 1
-Nghost:    227.25 ave 250 max 216 min
-Histogram: 2 0 1 0 0 0 0 0 0 1
-Neighs:    2373.25 ave 2489 max 2283 min
-Histogram: 1 1 0 0 0 1 0 0 0 1
-
-Total # of neighbors = 9493
-Ave neighs/atom = 7.91083
-Ave special neighs/atom = 0.5
-Neighbor list builds = 4888
-Dangerous builds = 0
-Total wall time: 0:00:04
diff --git a/examples/micelle/log.29Mar2019.micelle-rigid.g++.1 b/examples/micelle/log.29Mar2019.micelle-rigid.g++.1
new file mode 100644
index 0000000000..f1001e6cea
--- /dev/null
+++ b/examples/micelle/log.29Mar2019.micelle-rigid.g++.1
@@ -0,0 +1,260 @@
+LAMMPS (29 Mar 2019)
+  using 1 OpenMP thread(s) per MPI task
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  1200 atoms
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  300 bonds
+  2 = max # of 1-2 neighbors
+  1 = max # of 1-3 neighbors
+  1 = max # of 1-4 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000473022 secs
+  read_data CPU = 0.0024147 secs
+special_bonds	fene
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.00022316 secs
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		500
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.42246
+  ghost atom cutoff = 1.42246
+  binsize = 0.71123, bins = 51 51 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair soft, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.799 | 3.799 | 3.799 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
+      50   0.54981866   0.93548899  0.068440043    1.5532895    1.9232786 
+     100         0.45   0.99659327  0.079228519    1.5254468    3.2135679 
+     150   0.86965411   0.90456016   0.07493355    1.8484231    4.3821925 
+     200         0.45      1.01454   0.10663502       1.5708    4.7598476 
+     250   0.79636561   0.82567712   0.12105337    1.7424325    5.4983899 
+     300         0.45   0.86475538   0.11819875    1.4325791    5.8554758 
+     350   0.72135464   0.70693069   0.10912636    1.5368106    6.0388247 
+     400         0.45   0.75067331   0.14165013    1.3419484    6.3840708 
+     450   0.64839221   0.62402486   0.14173679    1.4136135    6.4791009 
+     500         0.45   0.66669513   0.13695201    1.2532721     6.807146 
+Loop time of 0.103162 on 1 procs for 500 steps with 1200 atoms
+
+Performance: 2093802.885 tau/day, 4846.766 timesteps/s
+99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.068308   | 0.068308   | 0.068308   |   0.0 | 66.21
+Bond    | 0.004235   | 0.004235   | 0.004235   |   0.0 |  4.11
+Neigh   | 0.014069   | 0.014069   | 0.014069   |   0.0 | 13.64
+Comm    | 0.0019219  | 0.0019219  | 0.0019219  |   0.0 |  1.86
+Output  | 0.00017262 | 0.00017262 | 0.00017262 |   0.0 |  0.17
+Modify  | 0.011728   | 0.011728   | 0.011728   |   0.0 | 11.37
+Other   |            | 0.002726   |            |       |  2.64
+
+Nlocal:    1200 ave 1200 max 1200 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    197 ave 197 max 197 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    3094 ave 3094 max 3094 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 3094
+Ave neighs/atom = 2.57833
+Ave special neighs/atom = 0.5
+Neighbor list builds = 52
+Dangerous builds = 0
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		50
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+group solvent   molecule 0
+750 atoms in group solvent
+group solute    subtract all solvent
+450 atoms in group solute
+unfix 1
+unfix 2
+unfix 4
+fix		1 solvent nve
+fix		2 solvent temp/rescale 100 0.45 0.45 0.02 1.0
+fix		5 solute rigid molecule langevin 0.45 0.45 0.5 112211
+150 rigid bodies with 450 atoms
+fix		4 all enforce2d
+run		500
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4, bins = 26 26 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 5.274 | 5.274 | 5.274 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0   0.45318168   -1.3753652   0.13695201   -0.8705807     1.975423 
+      50   0.77871641   -1.6955252   0.13695201  -0.92651507   0.64222539 
+     100    0.5336062   -1.7124572   0.13695201   -1.1423948  -0.11959696 
+     150   0.58789067   -1.7926109   0.13695201   -1.1784877    1.2592743 
+     200   0.47864796   -1.8040298   0.13695201   -1.2785752    3.6739793 
+     250   0.51124651   -1.8614797   0.13695201    -1.309566    2.5817722 
+     300   0.45695639   -1.8708384   0.13695201   -1.3629901    3.0833794 
+     350     0.477504   -1.8924359   0.13695201   -1.3679098   -5.1605926 
+     400   0.45328205     -1.87754   0.13695201    -1.372674   -4.0355858 
+     450   0.47465031   -1.9071924   0.13695201   -1.3849826    3.1949617 
+     500   0.45533691   -1.9072316   0.13695201   -1.4006978   0.48079061 
+Loop time of 0.178806 on 1 procs for 500 steps with 1200 atoms
+
+Performance: 1208012.705 tau/day, 2796.326 timesteps/s
+99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.086131   | 0.086131   | 0.086131   |   0.0 | 48.17
+Bond    | 0.0042472  | 0.0042472  | 0.0042472  |   0.0 |  2.38
+Neigh   | 0.021317   | 0.021317   | 0.021317   |   0.0 | 11.92
+Comm    | 0.0025985  | 0.0025985  | 0.0025985  |   0.0 |  1.45
+Output  | 0.000175   | 0.000175   | 0.000175   |   0.0 |  0.10
+Modify  | 0.061408   | 0.061408   | 0.061408   |   0.0 | 34.34
+Other   |            | 0.00293    |            |       |  1.64
+
+Nlocal:    1200 ave 1200 max 1200 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    416 ave 416 max 416 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    8769 ave 8769 max 8769 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 8769
+Ave neighs/atom = 7.3075
+Ave special neighs/atom = 0.5
+Neighbor list builds = 47
+Dangerous builds = 2
+unfix 2
+unfix 4
+unfix 5
+fix		5 solute rigid/small molecule
+  create bodies CPU = 0.00015378 secs
+150 rigid bodies with 450 atoms
+  1.30435 = max distance from body owner to body atom
+fix		4 all enforce2d
+run		500
+Per MPI rank memory allocation (min/avg/max) = 8.64 | 8.64 | 8.64 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+     500   0.45533691   -1.9072316   0.13695201   -1.4006978    2.4545793 
+     550   0.45627282    -1.912409   0.13695201   -1.4051155    2.1845065 
+     600   0.44734553   -1.8890695   0.13695201    -1.389022    2.3458965 
+     650   0.46444648   -1.9042462   0.13695201   -1.3903185    2.1609319 
+     700   0.47113236   -1.8977576   0.13695201   -1.3784032    2.2420351 
+     750   0.48554548   -1.9253545   0.13695201   -1.3943015     2.143907 
+     800   0.46350091   -1.8865749   0.13695201   -1.3734146     2.294431 
+     850    0.4766104   -1.9094039   0.13695201   -1.3856031    2.2077157 
+     900   0.48988467   -1.9051538   0.13695201   -1.3705787    2.0107056 
+     950   0.48351943   -1.9162485   0.13695201   -1.3868399    2.1891332 
+    1000   0.49033701   -1.9115165   0.13695201   -1.3765742    2.1508141 
+Loop time of 0.166502 on 1 procs for 500 steps with 1200 atoms
+
+Performance: 1297278.008 tau/day, 3002.958 timesteps/s
+99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.085767   | 0.085767   | 0.085767   |   0.0 | 51.51
+Bond    | 0.0042562  | 0.0042562  | 0.0042562  |   0.0 |  2.56
+Neigh   | 0.018039   | 0.018039   | 0.018039   |   0.0 | 10.83
+Comm    | 0.0024002  | 0.0024002  | 0.0024002  |   0.0 |  1.44
+Output  | 0.00018239 | 0.00018239 | 0.00018239 |   0.0 |  0.11
+Modify  | 0.052717   | 0.052717   | 0.052717   |   0.0 | 31.66
+Other   |            | 0.003141   |            |       |  1.89
+
+Nlocal:    1200 ave 1200 max 1200 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    415 ave 415 max 415 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    8743 ave 8743 max 8743 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 8743
+Ave neighs/atom = 7.28583
+Ave special neighs/atom = 0.5
+Neighbor list builds = 40
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/examples/micelle/log.29Mar2019.micelle-rigid.g++.4 b/examples/micelle/log.29Mar2019.micelle-rigid.g++.4
new file mode 100644
index 0000000000..e65f67a527
--- /dev/null
+++ b/examples/micelle/log.29Mar2019.micelle-rigid.g++.4
@@ -0,0 +1,260 @@
+LAMMPS (29 Mar 2019)
+  using 1 OpenMP thread(s) per MPI task
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
+  2 by 2 by 1 MPI processor grid
+  reading atoms ...
+  1200 atoms
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  300 bonds
+  2 = max # of 1-2 neighbors
+  1 = max # of 1-3 neighbors
+  1 = max # of 1-4 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000422001 secs
+  read_data CPU = 0.00473404 secs
+special_bonds	fene
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000183344 secs
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		500
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.42246
+  ghost atom cutoff = 1.42246
+  binsize = 0.71123, bins = 51 51 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair soft, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.758 | 3.85 | 4.126 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
+      50   0.54981866   0.93548899  0.068440043    1.5532895    1.9232786 
+     100         0.45   0.99659327  0.079228519    1.5254468    3.2135679 
+     150   0.86965411   0.90456016   0.07493355    1.8484231    4.3821925 
+     200         0.45      1.01454   0.10663502       1.5708    4.7598476 
+     250   0.79636561   0.82567712   0.12105337    1.7424325    5.4983899 
+     300         0.45   0.86475538   0.11819875    1.4325791    5.8554758 
+     350   0.72135464   0.70693069   0.10912636    1.5368106    6.0388247 
+     400         0.45   0.75067331   0.14165013    1.3419484    6.3840708 
+     450   0.64839221   0.62402486   0.14173679    1.4136135    6.4791009 
+     500         0.45   0.66669513   0.13695201    1.2532721     6.807146 
+Loop time of 0.0426326 on 4 procs for 500 steps with 1200 atoms
+
+Performance: 5066547.720 tau/day, 11728.120 timesteps/s
+98.7% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.016784   | 0.019254   | 0.022154   |   1.5 | 45.16
+Bond    | 0.0010612  | 0.0012558  | 0.0014153  |   0.4 |  2.95
+Neigh   | 0.0046048  | 0.0046697  | 0.0047245  |   0.1 | 10.95
+Comm    | 0.0064592  | 0.0097114  | 0.012527   |   2.4 | 22.78
+Output  | 0.00022507 | 0.00026393 | 0.00033951 |   0.0 |  0.62
+Modify  | 0.0041659  | 0.0048084  | 0.0053945  |   0.8 | 11.28
+Other   |            | 0.002669   |            |       |  6.26
+
+Nlocal:    300 ave 304 max 292 min
+Histogram: 1 0 0 0 0 0 0 0 2 1
+Nghost:    103.5 ave 108 max 98 min
+Histogram: 1 0 0 1 0 0 0 0 0 2
+Neighs:    773.5 ave 792 max 735 min
+Histogram: 1 0 0 0 0 0 0 0 2 1
+
+Total # of neighbors = 3094
+Ave neighs/atom = 2.57833
+Ave special neighs/atom = 0.5
+Neighbor list builds = 52
+Dangerous builds = 0
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		50
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+group solvent   molecule 0
+750 atoms in group solvent
+group solute    subtract all solvent
+450 atoms in group solute
+unfix 1
+unfix 2
+unfix 4
+fix		1 solvent nve
+fix		2 solvent temp/rescale 100 0.45 0.45 0.02 1.0
+fix		5 solute rigid molecule langevin 0.45 0.45 0.5 112211
+150 rigid bodies with 450 atoms
+fix		4 all enforce2d
+run		500
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4, bins = 26 26 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 5.251 | 5.282 | 5.374 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0   0.45318168   -1.3753652   0.13695201   -0.8705807     1.975423 
+      50   0.77871641   -1.6955252   0.13695201  -0.92651507   0.64222539 
+     100    0.5336062   -1.7124572   0.13695201   -1.1423948  -0.11959696 
+     150   0.58789067   -1.7926109   0.13695201   -1.1784877    1.2592743 
+     200   0.47864796   -1.8040298   0.13695201   -1.2785752    3.6739793 
+     250   0.51124651   -1.8614797   0.13695201    -1.309566    2.5817722 
+     300   0.45695639   -1.8708384   0.13695201   -1.3629901    3.0833794 
+     350     0.477504   -1.8924359   0.13695201   -1.3679098   -5.1605926 
+     400   0.45328205     -1.87754   0.13695201    -1.372674   -4.0355858 
+     450   0.47465031   -1.9071924   0.13695201   -1.3849826    3.1949617 
+     500   0.45533691   -1.9072316   0.13695201   -1.4006978   0.48079061 
+Loop time of 0.0887392 on 4 procs for 500 steps with 1200 atoms
+
+Performance: 2434100.210 tau/day, 5634.491 timesteps/s
+98.9% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.022611   | 0.022839   | 0.023082   |   0.1 | 25.74
+Bond    | 0.0010793  | 0.0011569  | 0.0012515  |   0.2 |  1.30
+Neigh   | 0.0064609  | 0.0064996  | 0.0065265  |   0.0 |  7.32
+Comm    | 0.0071712  | 0.0073687  | 0.0077734  |   0.3 |  8.30
+Output  | 0.00023389 | 0.00025356 | 0.00030327 |   0.0 |  0.29
+Modify  | 0.047258   | 0.047683   | 0.048503   |   0.2 | 53.73
+Other   |            | 0.002938   |            |       |  3.31
+
+Nlocal:    300 ave 309 max 291 min
+Histogram: 1 0 0 1 0 0 1 0 0 1
+Nghost:    218.75 ave 223 max 216 min
+Histogram: 1 0 2 0 0 0 0 0 0 1
+Neighs:    2192.25 ave 2251 max 2113 min
+Histogram: 1 0 0 1 0 0 0 0 0 2
+
+Total # of neighbors = 8769
+Ave neighs/atom = 7.3075
+Ave special neighs/atom = 0.5
+Neighbor list builds = 47
+Dangerous builds = 2
+unfix 2
+unfix 4
+unfix 5
+fix		5 solute rigid/small molecule
+  create bodies CPU = 7.70092e-05 secs
+150 rigid bodies with 450 atoms
+  1.30435 = max distance from body owner to body atom
+fix		4 all enforce2d
+run		500
+Per MPI rank memory allocation (min/avg/max) = 8.565 | 8.597 | 8.69 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+     500   0.45533691   -1.9072316   0.13695201   -1.4006978    2.4545793 
+     550   0.45627282    -1.912409   0.13695201   -1.4051155    2.1845065 
+     600   0.44734553   -1.8890695   0.13695201    -1.389022    2.3458965 
+     650   0.46444648   -1.9042462   0.13695201   -1.3903185    2.1609319 
+     700   0.47113236   -1.8977576   0.13695201   -1.3784032    2.2420351 
+     750   0.48554548   -1.9253545   0.13695201   -1.3943015     2.143907 
+     800   0.46350091   -1.8865749   0.13695201   -1.3734146     2.294431 
+     850    0.4766104   -1.9094039   0.13695201   -1.3856031    2.2077157 
+     900   0.48988467   -1.9051538   0.13695201   -1.3705787    2.0107056 
+     950   0.48351942   -1.9162485   0.13695201   -1.3868399    2.1891332 
+    1000     0.490337   -1.9115164   0.13695201   -1.3765742    2.1508141 
+Loop time of 0.0588261 on 4 procs for 500 steps with 1200 atoms
+
+Performance: 3671840.233 tau/day, 8499.630 timesteps/s
+98.3% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.022407   | 0.022631   | 0.0229     |   0.1 | 38.47
+Bond    | 0.0010669  | 0.0011355  | 0.0012124  |   0.2 |  1.93
+Neigh   | 0.0052333  | 0.00528    | 0.0053182  |   0.0 |  8.98
+Comm    | 0.0063677  | 0.0066406  | 0.0068488  |   0.2 | 11.29
+Output  | 0.00023055 | 0.00024778 | 0.00028086 |   0.0 |  0.42
+Modify  | 0.020577   | 0.020651   | 0.020834   |   0.1 | 35.11
+Other   |            | 0.00224    |            |       |  3.81
+
+Nlocal:    300 ave 303 max 295 min
+Histogram: 1 0 0 0 0 0 1 0 1 1
+Nghost:    219 ave 224 max 215 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+Neighs:    2185.75 ave 2244 max 2143 min
+Histogram: 1 1 0 0 0 1 0 0 0 1
+
+Total # of neighbors = 8743
+Ave neighs/atom = 7.28583
+Ave special neighs/atom = 0.5
+Neighbor list builds = 40
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/examples/micelle/log.29Mar2019.micelle.g++.1 b/examples/micelle/log.29Mar2019.micelle.g++.1
new file mode 100644
index 0000000000..d482d6c890
--- /dev/null
+++ b/examples/micelle/log.29Mar2019.micelle.g++.1
@@ -0,0 +1,218 @@
+LAMMPS (29 Mar 2019)
+  using 1 OpenMP thread(s) per MPI task
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  1200 atoms
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  300 bonds
+  2 = max # of 1-2 neighbors
+  1 = max # of 1-3 neighbors
+  1 = max # of 1-4 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.00037837 secs
+  read_data CPU = 0.00206876 secs
+special_bonds	fene
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000177383 secs
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.42246
+  ghost atom cutoff = 1.42246
+  binsize = 0.71123, bins = 51 51 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair soft, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.799 | 3.799 | 3.799 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
+      50   0.47411013   0.67721272  0.057404514    1.2083323    1.3375852 
+     100         0.45   0.73046745  0.054836584     1.234929    2.3196516 
+     150   0.67521742   0.72402001  0.043490075    1.4421648    2.8744416 
+     200         0.45   0.78481891  0.076931503    1.3113754    3.0412388 
+     250   0.66479018   0.69790602  0.081075564    1.4432178    3.6917024 
+     300         0.45   0.76820218  0.066727591    1.2845548    3.7861054 
+     350   0.67619136     0.625715  0.072722727    1.3740656    4.2861621 
+     400         0.45   0.68527759  0.090724527    1.2256271    4.4725214 
+     450   0.56702844   0.64402767  0.080555563    1.2911391    4.7402211 
+     500         0.45   0.64883009  0.078376672    1.1768318    4.7919294 
+     550     0.564664   0.58260368  0.080779475    1.2275766    4.9855705 
+     600         0.45   0.58193041  0.088386617     1.119942     5.131481 
+     650   0.52110993    0.5415273  0.097683746    1.1598867    5.2500294 
+     700         0.45   0.50856787  0.088471208    1.0466641    5.2550165 
+     750   0.51510855   0.47441291  0.089429375    1.0785216     5.375763 
+     800         0.45   0.49926696  0.085958476    1.0348504    5.4665914 
+     850   0.50688494   0.46614429  0.088962292    1.0615691     5.556932 
+     900         0.45   0.47785593   0.10150857    1.0289895    5.7765975 
+     950   0.49590559   0.46050477  0.096404887     1.052402    5.8649245 
+    1000         0.45   0.47691182   0.08808163    1.0146185    6.0177568 
+Loop time of 0.208895 on 1 procs for 1000 steps with 1200 atoms
+
+Performance: 2068027.282 tau/day, 4787.100 timesteps/s
+99.4% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.14142    | 0.14142    | 0.14142    |   0.0 | 67.70
+Bond    | 0.008441   | 0.008441   | 0.008441   |   0.0 |  4.04
+Neigh   | 0.025716   | 0.025716   | 0.025716   |   0.0 | 12.31
+Comm    | 0.0036864  | 0.0036864  | 0.0036864  |   0.0 |  1.76
+Output  | 0.0003562  | 0.0003562  | 0.0003562  |   0.0 |  0.17
+Modify  | 0.023699   | 0.023699   | 0.023699   |   0.0 | 11.35
+Other   |            | 0.00558    |            |       |  2.67
+
+Nlocal:    1200 ave 1200 max 1200 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    195 ave 195 max 195 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    3136 ave 3136 max 3136 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 3136
+Ave neighs/atom = 2.61333
+Ave special neighs/atom = 0.5
+Neighbor list builds = 92
+Dangerous builds = 0
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		50
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+run		1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4, bins = 26 26 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 4.024 | 4.024 | 4.024 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   -1.7056163   0.08808163   -1.1679097    3.9431686 
+      50   0.59734982   -1.8103783  0.076066922   -1.1374593    3.2770557 
+     100         0.45   -1.8347112  0.093132329   -1.2919539     3.024661 
+     150   0.51924311   -1.8943977  0.076004124   -1.2995832    2.5570373 
+     200         0.45   -1.8918672  0.082422107   -1.3598201    2.5629655 
+     250   0.50281134    -1.920406  0.074011331   -1.3440023    2.3518682 
+     300         0.45   -1.9351047  0.075337265   -1.4101424    2.3249947 
+     350   0.47650026   -1.9313687  0.072115117   -1.3831504    2.1987532 
+     400         0.45   -1.9554318  0.081603939   -1.4242028    2.0787066 
+     450   0.47220236   -1.9468502  0.065625624   -1.4094157    2.0984288 
+     500    0.4684673   -1.9444333  0.076696283   -1.3996601    2.0528682 
+     550   0.47683128    -1.958676  0.070589719   -1.4116523    2.0856022 
+     600   0.46851243   -1.9338267   0.07060548   -1.3950992      2.26405 
+     650   0.46874142   -1.9462493  0.069134685   -1.4087638    2.1070263 
+     700   0.46437384   -1.9309953  0.071977522   -1.3950309    2.2256923 
+     750   0.47326225   -1.9484255  0.075435845   -1.4001218    2.0880254 
+     800         0.45   -1.9646005  0.064159585   -1.4508159    2.0612696 
+     850   0.46748307    -1.970559  0.060384874   -1.4430806    1.9472879 
+     900   0.46909484    -1.953723  0.062470295   -1.4225488    2.0222909 
+     950   0.45631531   -1.9387753  0.067536568   -1.4153037    2.0638421 
+    1000         0.45   -1.9727646  0.058607721   -1.4645318    1.9982315 
+Loop time of 0.252254 on 1 procs for 1000 steps with 1200 atoms
+
+Performance: 1712557.882 tau/day, 3964.254 timesteps/s
+99.0% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.17177    | 0.17177    | 0.17177    |   0.0 | 68.09
+Bond    | 0.0084555  | 0.0084555  | 0.0084555  |   0.0 |  3.35
+Neigh   | 0.03991    | 0.03991    | 0.03991    |   0.0 | 15.82
+Comm    | 0.0049119  | 0.0049119  | 0.0049119  |   0.0 |  1.95
+Output  | 0.00039077 | 0.00039077 | 0.00039077 |   0.0 |  0.15
+Modify  | 0.021131   | 0.021131   | 0.021131   |   0.0 |  8.38
+Other   |            | 0.005685   |            |       |  2.25
+
+Nlocal:    1200 ave 1200 max 1200 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    415 ave 415 max 415 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    8586 ave 8586 max 8586 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 8586
+Ave neighs/atom = 7.155
+Ave special neighs/atom = 0.5
+Neighbor list builds = 86
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/examples/micelle/log.29Mar2019.micelle.g++.4 b/examples/micelle/log.29Mar2019.micelle.g++.4
new file mode 100644
index 0000000000..f3a54970cf
--- /dev/null
+++ b/examples/micelle/log.29Mar2019.micelle.g++.4
@@ -0,0 +1,218 @@
+LAMMPS (29 Mar 2019)
+  using 1 OpenMP thread(s) per MPI task
+# 2d micelle simulation
+
+dimension	2
+
+neighbor	0.3 bin
+neigh_modify	delay 5
+
+atom_style	bond
+
+# Soft potential push-off
+
+read_data	data.micelle
+  orthogonal box = (0 0 -0.1) to (35.8569 35.8569 0.1)
+  2 by 2 by 1 MPI processor grid
+  reading atoms ...
+  1200 atoms
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  300 bonds
+  2 = max # of 1-2 neighbors
+  1 = max # of 1-3 neighbors
+  1 = max # of 1-4 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000413656 secs
+  read_data CPU = 0.00487924 secs
+special_bonds	fene
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+  special bonds CPU = 0.000178576 secs
+
+pair_style	soft 1.12246
+pair_coeff	* * 0.0 1.12246
+
+bond_style 	harmonic
+bond_coeff	1 50.0 0.75
+
+velocity	all create 0.45 2349852
+
+variable	prefactor equal ramp(1.0,20.0)
+
+fix		1 all nve
+fix		2 all temp/rescale 100 0.45 0.45 0.02 1.0
+fix		3 all adapt 1 pair soft a * * v_prefactor
+fix		4 all enforce2d
+
+thermo		50
+run		1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.42246
+  ghost atom cutoff = 1.42246
+  binsize = 0.71123, bins = 51 51 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair soft, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 3.758 | 3.85 | 4.126 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   0.40003481 2.2200223e-06   0.84966203   0.78952518 
+      50   0.47411013   0.67721272  0.057404514    1.2083323    1.3375852 
+     100         0.45   0.73046745  0.054836584     1.234929    2.3196516 
+     150   0.67521742   0.72402001  0.043490075    1.4421648    2.8744416 
+     200         0.45   0.78481891  0.076931503    1.3113754    3.0412388 
+     250   0.66479018   0.69790602  0.081075564    1.4432178    3.6917024 
+     300         0.45   0.76820218  0.066727591    1.2845548    3.7861054 
+     350   0.67619136     0.625715  0.072722727    1.3740656    4.2861621 
+     400         0.45   0.68527759  0.090724527    1.2256271    4.4725214 
+     450   0.56702844   0.64402767  0.080555563    1.2911391    4.7402211 
+     500         0.45   0.64883009  0.078376672    1.1768318    4.7919294 
+     550     0.564664   0.58260368  0.080779475    1.2275766    4.9855705 
+     600         0.45   0.58193041  0.088386617     1.119942     5.131481 
+     650   0.52110993    0.5415273  0.097683746    1.1598867    5.2500294 
+     700         0.45   0.50856787  0.088471208    1.0466641    5.2550165 
+     750   0.51510855   0.47441291  0.089429375    1.0785216     5.375763 
+     800         0.45   0.49926696  0.085958476    1.0348504    5.4665914 
+     850   0.50688494   0.46614429  0.088962292    1.0615691     5.556932 
+     900         0.45   0.47785593   0.10150857    1.0289895    5.7765975 
+     950   0.49590559   0.46050477  0.096404887     1.052402    5.8649245 
+    1000         0.45   0.47691182   0.08808163    1.0146185    6.0177568 
+Loop time of 0.0906248 on 4 procs for 1000 steps with 1200 atoms
+
+Performance: 4766906.584 tau/day, 11034.506 timesteps/s
+98.9% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.036572   | 0.039266   | 0.041216   |   1.0 | 43.33
+Bond    | 0.0023205  | 0.0024512  | 0.0025697  |   0.2 |  2.70
+Neigh   | 0.0088909  | 0.0089301  | 0.0089679  |   0.0 |  9.85
+Comm    | 0.022308   | 0.024047   | 0.027175   |   1.3 | 26.53
+Output  | 0.00057411 | 0.00061274 | 0.00071025 |   0.0 |  0.68
+Modify  | 0.0083182  | 0.0092374  | 0.0098341  |   0.6 | 10.19
+Other   |            | 0.006081   |            |       |  6.71
+
+Nlocal:    300 ave 305 max 292 min
+Histogram: 1 0 0 0 0 0 1 0 1 1
+Nghost:    100.25 ave 108 max 93 min
+Histogram: 1 0 1 0 0 0 1 0 0 1
+Neighs:    784 ave 815 max 739 min
+Histogram: 1 0 0 0 0 0 1 1 0 1
+
+Total # of neighbors = 3136
+Ave neighs/atom = 2.61333
+Ave special neighs/atom = 0.5
+Neighbor list builds = 92
+Dangerous builds = 0
+
+unfix		3
+
+# Main run
+
+pair_style	lj/cut 2.5
+
+# solvent/head - full-size and long-range
+
+pair_coeff	1 1 1.0 1.0 2.5
+pair_coeff	2 2 1.0 1.0 2.5
+pair_coeff	1 2 1.0 1.0 2.5
+
+# tail/tail - size-averaged and long-range
+
+pair_coeff	3 3 1.0 0.75 2.5
+pair_coeff	4 4 1.0 0.50 2.5
+pair_coeff	3 4 1.0 0.67 2.5
+
+# solvent/tail - full-size and repulsive
+
+pair_coeff	1 3 1.0 1.0 1.12246
+pair_coeff	1 4 1.0 1.0 1.12246
+
+# head/tail - size-averaged and repulsive
+
+pair_coeff	2 3 1.0 0.88 1.12246
+pair_coeff	2 4 1.0 0.75 1.12246
+
+thermo		50
+
+#dump		1 all atom 2000 dump.micelle
+
+#dump		2 all image 2000 image.*.jpg type type zoom 1.6
+#dump_modify	2 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+#dump		3 all movie 2000 movie.mpg type type zoom 1.6
+#dump_modify	3 pad 5 adiam 1 0.5 adiam 2 1.5 adiam 3 1.0 adiam 4 0.75
+
+reset_timestep	0
+run		1000
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4, bins = 26 26 1
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/2d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 4.001 | 4.032 | 4.124 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         0.45   -1.7056163   0.08808163   -1.1679097    3.9431686 
+      50   0.59734982   -1.8103783  0.076066922   -1.1374593    3.2770557 
+     100         0.45   -1.8347112  0.093132329   -1.2919539     3.024661 
+     150   0.51924311   -1.8943977  0.076004124   -1.2995832    2.5570373 
+     200         0.45   -1.8918672  0.082422107   -1.3598201    2.5629655 
+     250   0.50281134    -1.920406  0.074011331   -1.3440023    2.3518682 
+     300         0.45   -1.9351047  0.075337265   -1.4101424    2.3249947 
+     350   0.47650026   -1.9313687  0.072115117   -1.3831504    2.1987532 
+     400         0.45   -1.9554318  0.081603939   -1.4242028    2.0787066 
+     450   0.47220236   -1.9468502  0.065625625   -1.4094157    2.0984288 
+     500    0.4684673   -1.9444333  0.076696285   -1.3996601    2.0528682 
+     550   0.47683128    -1.958676  0.070589721   -1.4116523    2.0856023 
+     600   0.46851245   -1.9338267  0.070605469   -1.3950992      2.26405 
+     650   0.46874143   -1.9462493  0.069134686   -1.4087638    2.1070262 
+     700    0.4643739   -1.9309953  0.071977511   -1.3950309     2.225692 
+     750   0.47326259   -1.9484258  0.075435808   -1.4001218    2.0880235 
+     800         0.45   -1.9646003   0.06415956   -1.4508158    2.0612703 
+     850   0.46748278   -1.9705588   0.06038513   -1.4430804    1.9472884 
+     900   0.46909438   -1.9537221  0.062470305   -1.4225483    2.0223008 
+     950   0.45631508   -1.9387742  0.067536066   -1.4153033     2.063854 
+    1000         0.45   -1.9727651  0.058608085    -1.464532    1.9982447 
+Loop time of 0.0878521 on 4 procs for 1000 steps with 1200 atoms
+
+Performance: 4917357.613 tau/day, 11382.772 timesteps/s
+99.0% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.043517   | 0.044455   | 0.046903   |   0.7 | 50.60
+Bond    | 0.0020199  | 0.0022303  | 0.0024347  |   0.4 |  2.54
+Neigh   | 0.012207   | 0.012335   | 0.012512   |   0.1 | 14.04
+Comm    | 0.014938   | 0.018265   | 0.020068   |   1.5 | 20.79
+Output  | 0.00061369 | 0.00064814 | 0.00073504 |   0.0 |  0.74
+Modify  | 0.0052264  | 0.0053691  | 0.0055039  |   0.2 |  6.11
+Other   |            | 0.00455    |            |       |  5.18
+
+Nlocal:    300 ave 305 max 296 min
+Histogram: 1 1 0 0 0 0 1 0 0 1
+Nghost:    219.5 ave 228 max 214 min
+Histogram: 1 0 1 1 0 0 0 0 0 1
+Neighs:    2146.5 ave 2201 max 2114 min
+Histogram: 1 1 0 1 0 0 0 0 0 1
+
+Total # of neighbors = 8586
+Ave neighs/atom = 7.155
+Ave special neighs/atom = 0.5
+Neighbor list builds = 86
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/lib/gpu/lal_device.cpp b/lib/gpu/lal_device.cpp
index 6b4d0ab2a5..9397f3c6c5 100644
--- a/lib/gpu/lal_device.cpp
+++ b/lib/gpu/lal_device.cpp
@@ -237,7 +237,7 @@ int DeviceT::set_ocl_params(char *ocl_vendor) {
                         " -DBLOCK_CELL_ID="+params[11]+
                         " -DMAX_BIO_SHARED_TYPES="+params[12];
   }
-  _ocl_compile_string="-cl-fast-relaxed-math -cl-mad-enable "+std::string(OCL_INT_TYPE)+" "+
+  _ocl_compile_string="-cl-std=CL1.2 -cl-fast-relaxed-math -cl-mad-enable "+std::string(OCL_INT_TYPE)+" "+
                       std::string(OCL_PRECISION_COMPILE)+" "+_ocl_vendor_string;
   #endif
   return 0;
diff --git a/lib/kim/Install.py b/lib/kim/Install.py
index dfb6bc53dc..c3588241c4 100644
--- a/lib/kim/Install.py
+++ b/lib/kim/Install.py
@@ -18,7 +18,7 @@ parser = ArgumentParser(prog='Install.py',
 # settings
 
 thisdir = fullpath('.')
-version = "kim-api-v2-2.0.1"
+version = "kim-api-2.0.2"
 
 # help message
 
@@ -154,7 +154,7 @@ if buildflag:
   # add all OpenKIM models, if desired
   if everythingflag:
     print("Adding all OpenKIM models, this will take a while ...")
-    cmd = '%s/bin/kim-api-v2-collections-management install system OpenKIM' % (kimdir)
+    cmd = '%s/bin/kim-api-collections-management install system OpenKIM' % (kimdir)
     txt = subprocess.check_output(cmd, stderr=subprocess.STDOUT, shell=True)
     if verboseflag:
       print(txt.decode("UTF-8"))
@@ -171,7 +171,7 @@ if addflag:
     sys.exit("\nkim-api is not installed")
 
   # download single model
-  cmd = '%s/bin/kim-api-v2-collections-management install system %s' % (kimdir.decode("UTF-8"), addmodelname)
+  cmd = '%s/bin/kim-api-collections-management install system %s' % (kimdir.decode("UTF-8"), addmodelname)
   txt = subprocess.check_output(cmd, stderr=subprocess.STDOUT, shell=True)
   if verboseflag:
     print(txt.decode("UTF-8"))
diff --git a/lib/kim/Makefile.lammps b/lib/kim/Makefile.lammps
index 7c9fc7c5f7..d4e10b0fb4 100644
--- a/lib/kim/Makefile.lammps
+++ b/lib/kim/Makefile.lammps
@@ -17,13 +17,18 @@
 ifeq ($(strip $(shell pkg-config --version)),)
   $(error 'pkg-config' not found, but is required to configure the KIM API)
 endif
-
 kim_PREFIX  := $(shell cat ../../lib/kim/kim-prefix.txt 2> /dev/null)
 kim_PREFIX  := $(if $(kim_PREFIX),$(kim_PREFIX)/lib/pkgconfig,)
 kim_PREFIX  := $(if $(shell printf -- "$${PKG_CONFIG_PATH}"),$(kim_PREFIX):$(shell printf -- "$${PKG_CONFIG_PATH}"),$(kim_PREFIX))
 
-kim_SYSINC  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --cflags libkim-api-v2 2> /dev/null)
-kim_SYSLIB  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --libs   libkim-api-v2 2> /dev/null)
+# there is no usable libcurl installation
+ifeq ($(shell curl-config --version 2> /dev/null),)
+kim_SYSINC  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --cflags libkim-api 2> /dev/null)
+kim_SYSLIB  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --libs   libkim-api 2> /dev/null)
+else
+kim_SYSINC  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --cflags libkim-api 2> /dev/null) $(shell curl-config --cflags) -DLMP_KIM_CURL
+kim_SYSLIB  := $(shell export PKG_CONFIG_PATH="$(kim_PREFIX)"; pkg-config --libs   libkim-api 2> /dev/null) $(shell curl-config --libs)
+endif
 
 ifeq ($(strip $(kim_SYSINC)),)
   $(error 'pkg-config' could not find an installed KIM API library.)
diff --git a/lib/kim/README b/lib/kim/README
index 0e51a30870..d3327537b6 100644
--- a/lib/kim/README
+++ b/lib/kim/README
@@ -13,6 +13,12 @@ do the same thing by typing "python Install.py" from within this
 directory, or you can do it manually by following the instructions
 below.
 
+As of KIM API version 2, the KIM package also provides a LAMMPS command
+to perform queries through the OpenKIM web API. This feature requires
+that the CURL library (libcurl) development package and its configuration
+query tool, curl-config, are installed. The provided Makefile.lammps
+is set up to automatically detect this.
+
 -----------------
 
 Instructions:
@@ -20,17 +26,17 @@ Instructions:
 1. Configure lammps for use with the kim-api library installed in this directory
 
 # replace X.Y.Z as appropriate here and below
-$ printf "${PWD}/installed-kim-api-vX-X.Y.Z" > ./kim-prefix.txt
+$ printf "${PWD}/installed-kim-api-X-X.Y.Z" > ./kim-prefix.txt
 
 2. Download and unpack the kim-api
 
-$ wget http://s3.openkim.org/kim-api/kim-api-vX-X.Y.Z.txz
-$ tar zxvf kim-api-vX-X.Y.Z.txz
+$ wget http://s3.openkim.org/kim-api/kim-api-X.Y.Z.txz
+$ tar zxvf kim-api-X.Y.Z.txz
 
 # configure the kim-api
-$ cd kim-api-vX-X.Y.Z
+$ cd kim-api-X.Y.Z
 $ mkdir build && cd build
-$ cmake ..  -DCMAKE_INSTALL_PREFIX=${PWD}/../../installed-kim-api-vX-X.Y.Z
+$ cmake ..  -DCMAKE_INSTALL_PREFIX=${PWD}/../../installed-kim-api-X.Y.Z
 
 3. Build and install the kim-api and model
 
@@ -40,14 +46,14 @@ $ make install
 4. Remove source and build files
 
 $ cd ../../
-$ rm -rf kim-api-vX-X.Y.Z
-$ rm -rf kim-api-vX-X.Y.Z.txz
+$ rm -rf kim-api-X.Y.Z
+$ rm -rf kim-api-X.Y.Z.txz
 
 5. To add items do the following (replace the kim item name with your
    desired value)
 
-$ source ${PWD}/kim-api-vX-X.Y.Z/bin/kim-api-vX-activate
-$ kim-api-vX-collections-management install system Pair_Johnson_Fe__MO_857282754307_002
+$ source ${PWD}/kim-api-X.Y.Z/bin/kim-api-activate
+$ kim-api-collections-management install system Pair_Johnson_Fe__MO_857282754307_002
 
 
 -----------------
diff --git a/lib/message/cslib/src/STUBS_MPI/mpi.h b/lib/message/cslib/src/STUBS_MPI/mpi_dummy.h
similarity index 100%
rename from lib/message/cslib/src/STUBS_MPI/mpi.h
rename to lib/message/cslib/src/STUBS_MPI/mpi_dummy.h
diff --git a/lib/message/cslib/src/cslib.cpp b/lib/message/cslib/src/cslib.cpp
index 874333607e..336ba87588 100644
--- a/lib/message/cslib/src/cslib.cpp
+++ b/lib/message/cslib/src/cslib.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <stdio.h>
 #include <string.h>
 #include <stdlib.h>
diff --git a/lib/message/cslib/src/cslib_wrap.cpp b/lib/message/cslib/src/cslib_wrap.cpp
index c2d69eaf0d..64b4d53b25 100644
--- a/lib/message/cslib/src/cslib_wrap.cpp
+++ b/lib/message/cslib/src/cslib_wrap.cpp
@@ -14,7 +14,11 @@
 
 // C style library interface to CSlib class
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <string.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/lib/message/cslib/src/msg.cpp b/lib/message/cslib/src/msg.cpp
index da22c81850..ff654ecbcf 100644
--- a/lib/message/cslib/src/msg.cpp
+++ b/lib/message/cslib/src/msg.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <cstdio>
 #include <cstring>
 #include <cstdlib>
diff --git a/lib/message/cslib/src/msg.h b/lib/message/cslib/src/msg.h
index f75942b027..81c2d21cb9 100644
--- a/lib/message/cslib/src/msg.h
+++ b/lib/message/cslib/src/msg.h
@@ -15,7 +15,11 @@
 #ifndef MSG_H
 #define MSG_H
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 
 namespace CSLIB_NS {
 
@@ -37,7 +41,7 @@ class Msg {
   int nfield;
   int *fieldID,*fieldtype,*fieldlen;
   int lengths[2];
-  
+
   void init(int);
   void allocate(int, int &, int *&, int, int &, char *&);
   void *smalloc(int);
diff --git a/lib/message/cslib/src/msg_file.cpp b/lib/message/cslib/src/msg_file.cpp
index d97e249fad..31cdfef544 100644
--- a/lib/message/cslib/src/msg_file.cpp
+++ b/lib/message/cslib/src/msg_file.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <stdio.h>
 #include <string.h>
 #include <stdlib.h>
diff --git a/lib/message/cslib/src/msg_mpi_one.cpp b/lib/message/cslib/src/msg_mpi_one.cpp
index db11735b27..c6fbd8732f 100644
--- a/lib/message/cslib/src/msg_mpi_one.cpp
+++ b/lib/message/cslib/src/msg_mpi_one.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <string.h>
 #include <stdlib.h>
 #include <stdint.h>
diff --git a/lib/message/cslib/src/msg_mpi_two.cpp b/lib/message/cslib/src/msg_mpi_two.cpp
index e9a9e87eeb..2a4fa65ff7 100644
--- a/lib/message/cslib/src/msg_mpi_two.cpp
+++ b/lib/message/cslib/src/msg_mpi_two.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <string.h>
 #include <stdlib.h>
 #include <stdint.h>
diff --git a/lib/message/cslib/src/msg_zmq.cpp b/lib/message/cslib/src/msg_zmq.cpp
index c2d408f3a5..8bee3aebde 100644
--- a/lib/message/cslib/src/msg_zmq.cpp
+++ b/lib/message/cslib/src/msg_zmq.cpp
@@ -12,7 +12,11 @@
    See the README file in the top-level CSlib directory.
 ------------------------------------------------------------------------- */
 
+#ifdef MPI_YES
 #include <mpi.h>
+#else
+#include <mpi_dummy.h>
+#endif
 #include <zmq.h>
 #include <string.h>
 #include <stdlib.h>
diff --git a/lib/plumed/Install.py b/lib/plumed/Install.py
index 70296b35d3..3623a8cff0 100644
--- a/lib/plumed/Install.py
+++ b/lib/plumed/Install.py
@@ -17,7 +17,7 @@ parser = ArgumentParser(prog='Install.py',
 
 # settings
 
-version = "2.4.4"
+version = "2.5.1"
 mode = "static"
 
 # help message
@@ -43,6 +43,7 @@ checksums = { \
         '2.4.3' : 'b1be7c48971627febc11c61b70767fc5', \
         '2.4.4' : '71ed465bdc7c2059e282dbda8d564e71', \
         '2.5.0' : '6224cd089493661e19ceacccd35cf911', \
+        '2.5.1' : 'c2a7b519e32197a120cdf47e0f194f81', \
         }
 
 # parse and process arguments
@@ -67,6 +68,7 @@ if not args.build and not args.path:
 buildflag = args.build
 pathflag = args.path is not None
 plumedpath = args.path
+mode = args.mode
 
 homepath = fullpath('.')
 homedir = "%s/plumed2" % (homepath)
@@ -75,6 +77,8 @@ if pathflag:
     if not os.path.isdir(plumedpath):
       sys.exit("Plumed2 path %s does not exist" % plumedpath)
     homedir = fullpath(plumedpath)
+    if not os.path.isdir(os.path.join(homedir, 'include', 'plumed', 'core')):
+      sys.exit("No Plumed2 installation found at %s" % plumedpath)
 
 # download and unpack plumed2 tarball
 
@@ -127,7 +131,7 @@ if os.path.isfile("Makefile.lammps.%s" % mode):
   lines1 = open(plumedinc, 'r').readlines()
   lines2 = open("Makefile.lammps.%s" % mode, 'r').readlines()
   fp = open("Makefile.lammps", 'w')
-  fp.write(os.path.join("PLUMED_LIBDIR=", homedir, "lib\n"))
+  fp.write("PLUMED_LIBDIR=" + os.path.join(homedir, "lib\n"))
   for line in lines1:
     fp.write(line)
   for line in lines2:
diff --git a/python/README b/python/README
index 6b13959f4d..204ca2c28d 100644
--- a/python/README
+++ b/python/README
@@ -9,12 +9,12 @@ doc/Section_python.html and in doc/Section_start.html#start_5.
 Basically you need to follow these steps in the src directory:
 
 % make g++ mode=shlib           # build for whatever machine target you wish
-% make install-python           # may need to do this via sudo
+% make install-python           # install into site-packages folder
 
 You can replace the last step by a one-time setting of environment
 variables in your shell script.  Or you can run the python/install.py
 script directly to give you more control over where the two relevant
-files are installed.  See doc/Section_python.html for details.
+files are installed.  See doc/Python_install.html for details.
 
 You should then be able to launch Python and instantiate an instance
 of LAMMPS:
diff --git a/python/install.py b/python/install.py
index 9308506fd2..7f7062103a 100644
--- a/python/install.py
+++ b/python/install.py
@@ -1,56 +1,96 @@
 #!/usr/bin/env python
 
-# copy LAMMPS src/liblammps.so and lammps.py to system dirs
-
-from __future__ import print_function
-
-instructions = """
-Syntax: python install.py [-h] [pydir]
-        pydir = target dir for lammps.py and liblammps.so
-                default = Python site-packages dir
+"""
+Installer script to install the LAMMPS python module and the corresponding
+shared library into either the system-wide site-packages tree, or - failing
+that - into the corresponding user tree. Called from the 'install-python'
+build target in the conventional and CMake based build systems
 """
 
+# copy LAMMPS shared library and lammps.py to system dirs
+
+from __future__ import print_function
 import sys,os,shutil
+from argparse import ArgumentParser
 
-if (len(sys.argv) > 1 and sys.argv[1] == "-h") or len(sys.argv) > 2:
-  print(instructions)
-  sys.exit()
+parser = ArgumentParser(prog='install.py',
+                        description='LAMMPS python module installer script')
 
-if len(sys.argv) == 2: pydir = sys.argv[1]
-else: pydir = ""
+parser.add_argument("-m", "--module", required=True,
+                    help="path to the source of the LAMMPS Python module")
+parser.add_argument("-l", "--lib", required=True,
+                    help="path to the compiled LAMMPS shared library")
+parser.add_argument("-v", "--version", required=True,
+                    help="path to the LAMMPS version.h header file")
 
-# copy lammps.py to pydir if it exists
-# if pydir not specified, install in site-packages via distutils setup()
+parser.add_argument("-d","--dir",
+                    help="Legacy custom installation folder selection for module and library")
 
-if pydir:
-  if not os.path.isdir(pydir):
-    print( "ERROR: pydir %s does not exist" % pydir)
-    sys.exit()
-  str = "cp ../python/lammps.py %s" % pydir
-  print(str)
+args = parser.parse_args()
+
+# validate arguments and make paths absolute
+
+if args.module:
+  if not os.path.exists(args.module):
+    print( "ERROR: LAMMPS module file %s does not exist" % args.module)
+    parser.print_help()
+    sys.exit(1)
+  else:
+    args.module = os.path.abspath(args.module)
+
+if args.lib:
+  if not os.path.exists(args.lib):
+    print( "ERROR: LAMMPS shared library %s does not exist" % args.lib)
+    parser.print_help()
+    sys.exit(1)
+  else:
+    args.lib = os.path.abspath(args.lib)
+
+if args.version:
+  if not os.path.exists(args.version):
+    print( "ERROR: LAMMPS version header file %s does not exist" % args.version)
+    parser.print_help()
+    sys.exit(1)
+  else:
+    args.version = os.path.abspath(args.version)
+
+if args.dir:
+  if not os.path.isdir(args.dir):
+    print( "ERROR: Installation folder %s does not exist" % args.dir)
+    parser.print_help()
+    sys.exit(1)
+  else:
+    args.dir = os.path.abspath(args.dir)
+
+# if a custom directory is given, we copy the files directly
+# without any special processing or additional steps to that folder
+
+if args.dir:
+  print("Copying LAMMPS Python module to custom folder %s" % args.dir)
   try:
-    shutil.copyfile("../python/lammps.py", os.path.join(pydir,'lammps.py') )
+    shutil.copyfile(args.module, os.path.join(args.dir,'lammps.py'))
   except shutil.Error:
-    pass # source and destination are identical
+    pass # fail silently
 
-  str = "cp ../src/liblammps.so %s" % pydir
-  print(str)
+  print("Copying LAMMPS shared library to custom folder %s" % args.dir)
   try:
-     shutil.copyfile("../src/liblammps.so", os.path.join(pydir,"liblammps.so") )
+    shutil.copyfile(args.lib, os.path.join(args.dir,os.path.basename(args.lib)))
   except shutil.Error:
-    pass # source and destination are identical
-  sys.exit()
-  
-print("installing lammps.py in Python site-packages dir")
+    pass # fail silently
 
-os.chdir('../python')                # in case invoked via make in src dir
+  sys.exit()
 
 # extract version string from header
-fp = open('../src/version.h','r')
+fp = open(args.version,'r')
 txt=fp.read().split('"')[1].split()
 verstr=txt[0]+txt[1]+txt[2]
 fp.close()
 
+print("Installing LAMMPS Python module version %s into site-packages folder" % verstr)
+
+# we need to switch to the folder of the python module
+os.chdir(os.path.dirname(args.module))
+
 from distutils.core import setup
 from distutils.sysconfig import get_python_lib
 import site
@@ -62,28 +102,26 @@ try:
         version = verstr,
         author = "Steve Plimpton",
         author_email = "sjplimp@sandia.gov",
-        url = "http://lammps.sandia.gov",
-        description = "LAMMPS molecular dynamics library",
+        url = "https://lammps.sandia.gov",
+        description = "LAMMPS Molecular Dynamics Python module",
+        license = "GPL",
         py_modules = ["lammps"],
-        data_files = [(get_python_lib(), ["../src/liblammps.so"])])
+        data_files = [(get_python_lib(), [args.lib])])
 except:
   tryuser=True
-  print ("Installation into global site-packages dir failed.\nTrying user site dir %s now." % site.USER_SITE)
-
+  print ("Installation into global site-packages folder failed.\nTrying user folder %s now." % site.USER_SITE)
 
 if tryuser:
   try:
     sys.argv = ["setup.py","install","--user"]    # as if had run "python setup.py install --user"
     setup(name = "lammps",
-    version = verstr,
-    author = "Steve Plimpton",
-    author_email = "sjplimp@sandia.gov",
-    url = "http://lammps.sandia.gov",
-    description = "LAMMPS molecular dynamics library",
-    py_modules = ["lammps"],
-    data_files = [(site.USER_SITE, ["../src/liblammps.so"])])
-  except: 
-    print("Installation into user site package dir failed.\nGo to ../python and install manually.")
-
-
-
+          version = verstr,
+          author = "Steve Plimpton",
+          author_email = "sjplimp@sandia.gov",
+          url = "https://lammps.sandia.gov",
+          description = "LAMMPS Molecular Dynamics Python module",
+          license = "GPL",
+          py_modules = ["lammps"],
+          data_files = [(site.USER_SITE, [args.lib])])
+  except:
+    print("Installation into user site package folder failed.")
diff --git a/src/.gitignore b/src/.gitignore
index d405cb209e..27f4f8a64c 100644
--- a/src/.gitignore
+++ b/src/.gitignore
@@ -26,6 +26,11 @@
 /*_ssa.h
 /*_ssa.cpp
 
+/kim_query.cpp
+/kim_query.h
+/pair_kim.cpp
+/pair_kim.h
+
 /kokkos.cpp
 /kokkos.h
 /kokkos_type.h
@@ -818,8 +823,6 @@
 /pair_hbond_dreiding_morse.h
 /pair_ilp_graphene_hbn.cpp
 /pair_ilp_graphene_hbn.h
-/pair_kim.cpp
-/pair_kim.h
 /pair_kolmogorov_crespi_full.cpp
 /pair_kolmogorov_crespi_full.h
 /pair_kolmogorov_crespi_z.cpp
diff --git a/src/ASPHERE/pair_gayberne.cpp b/src/ASPHERE/pair_gayberne.cpp
index 857541957e..3d4ed3f183 100644
--- a/src/ASPHERE/pair_gayberne.cpp
+++ b/src/ASPHERE/pair_gayberne.cpp
@@ -94,8 +94,7 @@ void PairGayBerne::compute(int eflag, int vflag)
   double *iquat,*jquat;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   AtomVecEllipsoid::Bonus *bonus = avec->bonus;
   int *ellipsoid = atom->ellipsoid;
diff --git a/src/ASPHERE/pair_line_lj.cpp b/src/ASPHERE/pair_line_lj.cpp
index 963ff985c4..4873b44dc4 100644
--- a/src/ASPHERE/pair_line_lj.cpp
+++ b/src/ASPHERE/pair_line_lj.cpp
@@ -77,8 +77,7 @@ void PairLineLJ::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/ASPHERE/pair_resquared.cpp b/src/ASPHERE/pair_resquared.cpp
index c477b1b8cf..b100a5f184 100644
--- a/src/ASPHERE/pair_resquared.cpp
+++ b/src/ASPHERE/pair_resquared.cpp
@@ -85,8 +85,7 @@ void PairRESquared::compute(int eflag, int vflag)
   RE2Vars wi,wj;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/ASPHERE/pair_tri_lj.cpp b/src/ASPHERE/pair_tri_lj.cpp
index 142caf3764..cefd73f976 100644
--- a/src/ASPHERE/pair_tri_lj.cpp
+++ b/src/ASPHERE/pair_tri_lj.cpp
@@ -77,8 +77,7 @@ void PairTriLJ::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   AtomVecTri::Bonus *bonus = avec->bonus;
   double **x = atom->x;
diff --git a/src/BODY/compute_body_local.cpp b/src/BODY/compute_body_local.cpp
index df8a76d0fe..20f7d76708 100644
--- a/src/BODY/compute_body_local.cpp
+++ b/src/BODY/compute_body_local.cpp
@@ -39,8 +39,6 @@ ComputeBodyLocal::ComputeBodyLocal(LAMMPS *lmp, int narg, char **arg) :
 
   local_flag = 1;
   nvalues = narg - 3;
-  if (nvalues == 1) size_local_cols = 0;
-  else size_local_cols = nvalues;
 
   which = new int[nvalues];
   index = new int[nvalues];
@@ -66,6 +64,9 @@ ComputeBodyLocal::ComputeBodyLocal(LAMMPS *lmp, int narg, char **arg) :
       error->all(FLERR,"Invalid index in compute body/local command");
   }
 
+  if (nvalues == 1) size_local_cols = 0;
+  else size_local_cols = nvalues;
+
   nmax = 0;
   vector = NULL;
   array = NULL;
diff --git a/src/BODY/pair_body_nparticle.cpp b/src/BODY/pair_body_nparticle.cpp
index 80b45beb4e..f2eb2aa520 100644
--- a/src/BODY/pair_body_nparticle.cpp
+++ b/src/BODY/pair_body_nparticle.cpp
@@ -77,8 +77,7 @@ void PairBodyNparticle::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/BODY/pair_body_rounded_polygon.cpp b/src/BODY/pair_body_rounded_polygon.cpp
index b6dcab29ae..69495ea57f 100644
--- a/src/BODY/pair_body_rounded_polygon.cpp
+++ b/src/BODY/pair_body_rounded_polygon.cpp
@@ -111,8 +111,7 @@ void PairBodyRoundedPolygon::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/BODY/pair_body_rounded_polyhedron.cpp b/src/BODY/pair_body_rounded_polyhedron.cpp
index 1a4653ce53..60f6df3582 100644
--- a/src/BODY/pair_body_rounded_polyhedron.cpp
+++ b/src/BODY/pair_body_rounded_polyhedron.cpp
@@ -127,8 +127,7 @@ void PairBodyRoundedPolyhedron::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/CLASS2/angle_class2.cpp b/src/CLASS2/angle_class2.cpp
index 24f41bfd58..d550767e5e 100644
--- a/src/CLASS2/angle_class2.cpp
+++ b/src/CLASS2/angle_class2.cpp
@@ -78,8 +78,7 @@ void AngleClass2::compute(int eflag, int vflag)
   double vx11,vx12,vy11,vy12,vz11,vz12,vx21,vx22,vy21,vy22,vz21,vz22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CLASS2/bond_class2.cpp b/src/CLASS2/bond_class2.cpp
index af20313e0a..26c4e63a4d 100644
--- a/src/CLASS2/bond_class2.cpp
+++ b/src/CLASS2/bond_class2.cpp
@@ -56,8 +56,7 @@ void BondClass2::compute(int eflag, int vflag)
   double rsq,r,dr,dr2,dr3,dr4,de_bond;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CLASS2/dihedral_class2.cpp b/src/CLASS2/dihedral_class2.cpp
index c6360dd846..c471b1f353 100644
--- a/src/CLASS2/dihedral_class2.cpp
+++ b/src/CLASS2/dihedral_class2.cpp
@@ -118,8 +118,7 @@ void DihedralClass2::compute(int eflag, int vflag)
   double fabcd[4][3];
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CLASS2/improper_class2.cpp b/src/CLASS2/improper_class2.cpp
index 77f594af9d..ccb81aebd9 100644
--- a/src/CLASS2/improper_class2.cpp
+++ b/src/CLASS2/improper_class2.cpp
@@ -90,8 +90,7 @@ void ImproperClass2::compute(int eflag, int vflag)
   double fabcd[4][3];
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   for (i = 0; i < 3; i++)
     for (j = 0; j < 4; j++)
diff --git a/src/CLASS2/pair_lj_class2.cpp b/src/CLASS2/pair_lj_class2.cpp
index e6546b1acc..f2eef55290 100644
--- a/src/CLASS2/pair_lj_class2.cpp
+++ b/src/CLASS2/pair_lj_class2.cpp
@@ -38,20 +38,20 @@ PairLJClass2::PairLJClass2(LAMMPS *lmp) : Pair(lmp)
 
 PairLJClass2::~PairLJClass2()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
 }
 
@@ -65,8 +65,7 @@ void PairLJClass2::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CLASS2/pair_lj_class2_coul_cut.cpp b/src/CLASS2/pair_lj_class2_coul_cut.cpp
index 49242ecb43..dafa83c8fd 100644
--- a/src/CLASS2/pair_lj_class2_coul_cut.cpp
+++ b/src/CLASS2/pair_lj_class2_coul_cut.cpp
@@ -39,23 +39,23 @@ PairLJClass2CoulCut::PairLJClass2CoulCut(LAMMPS *lmp) : Pair(lmp)
 
 PairLJClass2CoulCut::~PairLJClass2CoulCut()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(cut_coul);
-      memory->destroy(cut_coulsq);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(cut_coul);
+    memory->destroy(cut_coulsq);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
 }
 
@@ -70,8 +70,7 @@ void PairLJClass2CoulCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CLASS2/pair_lj_class2_coul_long.cpp b/src/CLASS2/pair_lj_class2_coul_long.cpp
index bbea2ade6e..85fe0152e2 100644
--- a/src/CLASS2/pair_lj_class2_coul_long.cpp
+++ b/src/CLASS2/pair_lj_class2_coul_long.cpp
@@ -50,21 +50,21 @@ PairLJClass2CoulLong::PairLJClass2CoulLong(LAMMPS *lmp) : Pair(lmp)
 
 PairLJClass2CoulLong::~PairLJClass2CoulLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
   if (ftable) free_tables();
 }
@@ -82,8 +82,7 @@ void PairLJClass2CoulLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/COLLOID/pair_brownian.cpp b/src/COLLOID/pair_brownian.cpp
index e532c06c86..aefa96b1fb 100644
--- a/src/COLLOID/pair_brownian.cpp
+++ b/src/COLLOID/pair_brownian.cpp
@@ -80,8 +80,7 @@ void PairBrownian::compute(int eflag, int vflag)
   double rsq,r,h_sep,radi;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/COLLOID/pair_brownian_poly.cpp b/src/COLLOID/pair_brownian_poly.cpp
index c6d5def2fa..389ae084b7 100644
--- a/src/COLLOID/pair_brownian_poly.cpp
+++ b/src/COLLOID/pair_brownian_poly.cpp
@@ -66,8 +66,7 @@ void PairBrownianPoly::compute(int eflag, int vflag)
   double rsq,r,h_sep,beta0,beta1,radi,radj;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/COLLOID/pair_colloid.cpp b/src/COLLOID/pair_colloid.cpp
index c16dbf41af..04c35a7c00 100644
--- a/src/COLLOID/pair_colloid.cpp
+++ b/src/COLLOID/pair_colloid.cpp
@@ -78,8 +78,7 @@ void PairColloid::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/COLLOID/pair_lubricate.cpp b/src/COLLOID/pair_lubricate.cpp
index de53d91818..4e629bd442 100644
--- a/src/COLLOID/pair_lubricate.cpp
+++ b/src/COLLOID/pair_lubricate.cpp
@@ -88,8 +88,7 @@ void PairLubricate::compute(int eflag, int vflag)
 
   double vxmu2f = force->vxmu2f;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/COLLOID/pair_lubricateU.cpp b/src/COLLOID/pair_lubricateU.cpp
index 35fe33c84e..3ea3d4fe4a 100644
--- a/src/COLLOID/pair_lubricateU.cpp
+++ b/src/COLLOID/pair_lubricateU.cpp
@@ -116,8 +116,7 @@ void PairLubricateU::compute(int eflag, int vflag)
   int nghost = atom->nghost;
   int nall = nlocal + nghost;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // skip compute() if called from integrate::setup()
   // this is b/c do not want compute() to update velocities twice on a restart
diff --git a/src/COLLOID/pair_lubricateU_poly.cpp b/src/COLLOID/pair_lubricateU_poly.cpp
index 90ac848d26..4fec95dcd8 100644
--- a/src/COLLOID/pair_lubricateU_poly.cpp
+++ b/src/COLLOID/pair_lubricateU_poly.cpp
@@ -78,8 +78,7 @@ void PairLubricateUPoly::compute(int eflag, int vflag)
   double **f = atom->f;
   double **torque = atom->torque;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // grow per-atom arrays if necessary
   // need to be atom->nmax in length
diff --git a/src/COLLOID/pair_lubricate_poly.cpp b/src/COLLOID/pair_lubricate_poly.cpp
index 5e52933364..ffbe7fce3c 100644
--- a/src/COLLOID/pair_lubricate_poly.cpp
+++ b/src/COLLOID/pair_lubricate_poly.cpp
@@ -72,8 +72,7 @@ void PairLubricatePoly::compute(int eflag, int vflag)
 
   double vxmu2f = force->vxmu2f;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/COLLOID/pair_yukawa_colloid.cpp b/src/COLLOID/pair_yukawa_colloid.cpp
index d21bc43524..ab7d088508 100644
--- a/src/COLLOID/pair_yukawa_colloid.cpp
+++ b/src/COLLOID/pair_yukawa_colloid.cpp
@@ -46,8 +46,7 @@ void PairYukawaColloid::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_born_coul_dsf_cs.cpp b/src/CORESHELL/pair_born_coul_dsf_cs.cpp
index 549c7c0348..f4d7447ade 100644
--- a/src/CORESHELL/pair_born_coul_dsf_cs.cpp
+++ b/src/CORESHELL/pair_born_coul_dsf_cs.cpp
@@ -57,8 +57,7 @@ void PairBornCoulDSFCS::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_born_coul_long_cs.cpp b/src/CORESHELL/pair_born_coul_long_cs.cpp
index 76f6eb387d..a19f8c34a8 100644
--- a/src/CORESHELL/pair_born_coul_long_cs.cpp
+++ b/src/CORESHELL/pair_born_coul_long_cs.cpp
@@ -68,8 +68,7 @@ void PairBornCoulLongCS::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_born_coul_wolf_cs.cpp b/src/CORESHELL/pair_born_coul_wolf_cs.cpp
index 84179ce50a..7b52c28664 100644
--- a/src/CORESHELL/pair_born_coul_wolf_cs.cpp
+++ b/src/CORESHELL/pair_born_coul_wolf_cs.cpp
@@ -53,8 +53,7 @@ void PairBornCoulWolfCS::compute(int eflag, int vflag)
   double erfcc,erfcd,v_sh,dvdrr,e_self,e_shift,f_shift,qisq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_buck_coul_long_cs.cpp b/src/CORESHELL/pair_buck_coul_long_cs.cpp
index ea072d44a1..8df91f39a3 100644
--- a/src/CORESHELL/pair_buck_coul_long_cs.cpp
+++ b/src/CORESHELL/pair_buck_coul_long_cs.cpp
@@ -68,8 +68,7 @@ void PairBuckCoulLongCS::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_coul_long_cs.cpp b/src/CORESHELL/pair_coul_long_cs.cpp
index b214653841..c8c8387d6d 100644
--- a/src/CORESHELL/pair_coul_long_cs.cpp
+++ b/src/CORESHELL/pair_coul_long_cs.cpp
@@ -69,8 +69,7 @@ void PairCoulLongCS::compute(int eflag, int vflag)
   double rsq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_coul_wolf_cs.cpp b/src/CORESHELL/pair_coul_wolf_cs.cpp
index b50f14833e..36e037bfc8 100644
--- a/src/CORESHELL/pair_coul_wolf_cs.cpp
+++ b/src/CORESHELL/pair_coul_wolf_cs.cpp
@@ -53,8 +53,7 @@ void PairCoulWolfCS::compute(int eflag, int vflag)
   double erfcc,erfcd,v_sh,dvdrr,e_self,e_shift,f_shift,qisq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/CORESHELL/pair_lj_cut_coul_long_cs.cpp b/src/CORESHELL/pair_lj_cut_coul_long_cs.cpp
index 8caefc0e66..56c75f0f5d 100644
--- a/src/CORESHELL/pair_lj_cut_coul_long_cs.cpp
+++ b/src/CORESHELL/pair_lj_cut_coul_long_cs.cpp
@@ -74,8 +74,7 @@ void PairLJCutCoulLongCS::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -399,8 +398,7 @@ void PairLJCutCoulLongCS::compute_outer(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/DIPOLE/pair_lj_cut_dipole_cut.cpp b/src/DIPOLE/pair_lj_cut_dipole_cut.cpp
index 6af9b45724..18b78c55e0 100644
--- a/src/DIPOLE/pair_lj_cut_dipole_cut.cpp
+++ b/src/DIPOLE/pair_lj_cut_dipole_cut.cpp
@@ -69,8 +69,7 @@ void PairLJCutDipoleCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/DIPOLE/pair_lj_cut_dipole_long.cpp b/src/DIPOLE/pair_lj_cut_dipole_long.cpp
index 817a120e3d..0806d1ee73 100644
--- a/src/DIPOLE/pair_lj_cut_dipole_long.cpp
+++ b/src/DIPOLE/pair_lj_cut_dipole_long.cpp
@@ -90,8 +90,7 @@ void PairLJCutDipoleLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/DIPOLE/pair_lj_long_dipole_long.cpp b/src/DIPOLE/pair_lj_long_dipole_long.cpp
index 21fc035854..fbdc47a15b 100644
--- a/src/DIPOLE/pair_lj_long_dipole_long.cpp
+++ b/src/DIPOLE/pair_lj_long_dipole_long.cpp
@@ -405,8 +405,7 @@ void PairLJLongDipoleLong::compute(int eflag, int vflag)
   double evdwl,ecoul,fpair;
   evdwl = ecoul = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x, *x0 = x[0];
   double **mu = atom->mu, *mu0 = mu[0], *imu, *jmu;
diff --git a/src/GPU/pair_beck_gpu.cpp b/src/GPU/pair_beck_gpu.cpp
index e65c53d194..9f76975ef1 100644
--- a/src/GPU/pair_beck_gpu.cpp
+++ b/src/GPU/pair_beck_gpu.cpp
@@ -84,8 +84,7 @@ PairBeckGPU::~PairBeckGPU()
 
 void PairBeckGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_born_coul_long_cs_gpu.cpp b/src/GPU/pair_born_coul_long_cs_gpu.cpp
index 587c7b5215..291ad8ad1f 100644
--- a/src/GPU/pair_born_coul_long_cs_gpu.cpp
+++ b/src/GPU/pair_born_coul_long_cs_gpu.cpp
@@ -106,8 +106,7 @@ PairBornCoulLongCSGPU::~PairBornCoulLongCSGPU()
 
 void PairBornCoulLongCSGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_born_coul_long_gpu.cpp b/src/GPU/pair_born_coul_long_gpu.cpp
index 1549ed79af..eb204691c7 100644
--- a/src/GPU/pair_born_coul_long_gpu.cpp
+++ b/src/GPU/pair_born_coul_long_gpu.cpp
@@ -101,8 +101,7 @@ PairBornCoulLongGPU::~PairBornCoulLongGPU()
 
 void PairBornCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_born_coul_wolf_cs_gpu.cpp b/src/GPU/pair_born_coul_wolf_cs_gpu.cpp
index bf23007bca..4877a442b5 100644
--- a/src/GPU/pair_born_coul_wolf_cs_gpu.cpp
+++ b/src/GPU/pair_born_coul_wolf_cs_gpu.cpp
@@ -94,8 +94,7 @@ PairBornCoulWolfCSGPU::~PairBornCoulWolfCSGPU()
 
 void PairBornCoulWolfCSGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_born_coul_wolf_gpu.cpp b/src/GPU/pair_born_coul_wolf_gpu.cpp
index 06a2769e10..851174988b 100644
--- a/src/GPU/pair_born_coul_wolf_gpu.cpp
+++ b/src/GPU/pair_born_coul_wolf_gpu.cpp
@@ -92,8 +92,7 @@ PairBornCoulWolfGPU::~PairBornCoulWolfGPU()
 
 void PairBornCoulWolfGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_born_gpu.cpp b/src/GPU/pair_born_gpu.cpp
index 01e91a9c0b..253d2d7282 100644
--- a/src/GPU/pair_born_gpu.cpp
+++ b/src/GPU/pair_born_gpu.cpp
@@ -87,8 +87,7 @@ PairBornGPU::~PairBornGPU()
 
 void PairBornGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_buck_coul_cut_gpu.cpp b/src/GPU/pair_buck_coul_cut_gpu.cpp
index ce71e9ac41..ed602f9cab 100644
--- a/src/GPU/pair_buck_coul_cut_gpu.cpp
+++ b/src/GPU/pair_buck_coul_cut_gpu.cpp
@@ -88,8 +88,7 @@ PairBuckCoulCutGPU::~PairBuckCoulCutGPU()
 
 void PairBuckCoulCutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_buck_coul_long_gpu.cpp b/src/GPU/pair_buck_coul_long_gpu.cpp
index a2d14ea25f..d6b9e53282 100644
--- a/src/GPU/pair_buck_coul_long_gpu.cpp
+++ b/src/GPU/pair_buck_coul_long_gpu.cpp
@@ -97,8 +97,7 @@ PairBuckCoulLongGPU::~PairBuckCoulLongGPU()
 
 void PairBuckCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_buck_gpu.cpp b/src/GPU/pair_buck_gpu.cpp
index e6479e46e8..8c85407e6e 100644
--- a/src/GPU/pair_buck_gpu.cpp
+++ b/src/GPU/pair_buck_gpu.cpp
@@ -85,8 +85,7 @@ PairBuckGPU::~PairBuckGPU()
 
 void PairBuckGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_colloid_gpu.cpp b/src/GPU/pair_colloid_gpu.cpp
index 03e5aac5d5..0ee8708b5b 100644
--- a/src/GPU/pair_colloid_gpu.cpp
+++ b/src/GPU/pair_colloid_gpu.cpp
@@ -85,8 +85,7 @@ PairColloidGPU::~PairColloidGPU()
 
 void PairColloidGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_coul_cut_gpu.cpp b/src/GPU/pair_coul_cut_gpu.cpp
index 436d26fb54..fb50c446b1 100644
--- a/src/GPU/pair_coul_cut_gpu.cpp
+++ b/src/GPU/pair_coul_cut_gpu.cpp
@@ -85,8 +85,7 @@ PairCoulCutGPU::~PairCoulCutGPU()
 
 void PairCoulCutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_coul_debye_gpu.cpp b/src/GPU/pair_coul_debye_gpu.cpp
index c17e21f41f..ec771a9935 100644
--- a/src/GPU/pair_coul_debye_gpu.cpp
+++ b/src/GPU/pair_coul_debye_gpu.cpp
@@ -86,8 +86,7 @@ PairCoulDebyeGPU::~PairCoulDebyeGPU()
 
 void PairCoulDebyeGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_coul_dsf_gpu.cpp b/src/GPU/pair_coul_dsf_gpu.cpp
index 15a15660dd..1753b8a91c 100644
--- a/src/GPU/pair_coul_dsf_gpu.cpp
+++ b/src/GPU/pair_coul_dsf_gpu.cpp
@@ -97,8 +97,7 @@ PairCoulDSFGPU::~PairCoulDSFGPU()
 
 void PairCoulDSFGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_coul_long_cs_gpu.cpp b/src/GPU/pair_coul_long_cs_gpu.cpp
index be2a090786..6ca00d6361 100644
--- a/src/GPU/pair_coul_long_cs_gpu.cpp
+++ b/src/GPU/pair_coul_long_cs_gpu.cpp
@@ -99,8 +99,7 @@ PairCoulLongCSGPU::~PairCoulLongCSGPU()
 
 void PairCoulLongCSGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_coul_long_gpu.cpp b/src/GPU/pair_coul_long_gpu.cpp
index 684b0049c0..f75d10b6dd 100644
--- a/src/GPU/pair_coul_long_gpu.cpp
+++ b/src/GPU/pair_coul_long_gpu.cpp
@@ -94,8 +94,7 @@ PairCoulLongGPU::~PairCoulLongGPU()
 
 void PairCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_dpd_gpu.cpp b/src/GPU/pair_dpd_gpu.cpp
index 7d56b47fe5..b1e45fbecd 100644
--- a/src/GPU/pair_dpd_gpu.cpp
+++ b/src/GPU/pair_dpd_gpu.cpp
@@ -225,8 +225,7 @@ PairDPDGPU::~PairDPDGPU()
 
 void PairDPDGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_dpd_tstat_gpu.cpp b/src/GPU/pair_dpd_tstat_gpu.cpp
index f093c03a2d..0693a27344 100644
--- a/src/GPU/pair_dpd_tstat_gpu.cpp
+++ b/src/GPU/pair_dpd_tstat_gpu.cpp
@@ -228,8 +228,7 @@ PairDPDTstatGPU::~PairDPDTstatGPU()
 
 void PairDPDTstatGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // adjust sigma if target T is changing
 
diff --git a/src/GPU/pair_eam_alloy_gpu.cpp b/src/GPU/pair_eam_alloy_gpu.cpp
index c472b91fc8..9b3412d3d1 100644
--- a/src/GPU/pair_eam_alloy_gpu.cpp
+++ b/src/GPU/pair_eam_alloy_gpu.cpp
@@ -94,8 +94,7 @@ double PairEAMAlloyGPU::memory_usage()
 
 void PairEAMAlloyGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // compute density on each atom on GPU
 
diff --git a/src/GPU/pair_eam_fs_gpu.cpp b/src/GPU/pair_eam_fs_gpu.cpp
index 821bb1af1c..11ef28af3e 100644
--- a/src/GPU/pair_eam_fs_gpu.cpp
+++ b/src/GPU/pair_eam_fs_gpu.cpp
@@ -92,8 +92,7 @@ double PairEAMFSGPU::memory_usage()
 
 void PairEAMFSGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // compute density on each atom on GPU
 
diff --git a/src/GPU/pair_eam_gpu.cpp b/src/GPU/pair_eam_gpu.cpp
index 515a349ad2..4788a72417 100644
--- a/src/GPU/pair_eam_gpu.cpp
+++ b/src/GPU/pair_eam_gpu.cpp
@@ -95,8 +95,7 @@ double PairEAMGPU::memory_usage()
 
 void PairEAMGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // compute density on each atom on GPU
 
diff --git a/src/GPU/pair_gauss_gpu.cpp b/src/GPU/pair_gauss_gpu.cpp
index 71fb55f4d0..c596a9d644 100644
--- a/src/GPU/pair_gauss_gpu.cpp
+++ b/src/GPU/pair_gauss_gpu.cpp
@@ -82,8 +82,7 @@ PairGaussGPU::~PairGaussGPU()
 
 void PairGaussGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_gayberne_gpu.cpp b/src/GPU/pair_gayberne_gpu.cpp
index 32b8b979cd..4ed2750e57 100644
--- a/src/GPU/pair_gayberne_gpu.cpp
+++ b/src/GPU/pair_gayberne_gpu.cpp
@@ -92,8 +92,7 @@ PairGayBerneGPU::~PairGayBerneGPU()
 
 void PairGayBerneGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj96_cut_gpu.cpp b/src/GPU/pair_lj96_cut_gpu.cpp
index 707d632d9a..5bc30c809d 100644
--- a/src/GPU/pair_lj96_cut_gpu.cpp
+++ b/src/GPU/pair_lj96_cut_gpu.cpp
@@ -82,8 +82,7 @@ PairLJ96CutGPU::~PairLJ96CutGPU()
 
 void PairLJ96CutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_charmm_coul_long_gpu.cpp b/src/GPU/pair_lj_charmm_coul_long_gpu.cpp
index ebc9f88943..134295c69f 100644
--- a/src/GPU/pair_lj_charmm_coul_long_gpu.cpp
+++ b/src/GPU/pair_lj_charmm_coul_long_gpu.cpp
@@ -99,8 +99,7 @@ PairLJCharmmCoulLongGPU::~PairLJCharmmCoulLongGPU()
 
 void PairLJCharmmCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_class2_coul_long_gpu.cpp b/src/GPU/pair_lj_class2_coul_long_gpu.cpp
index 797680c032..fdffb06a8d 100644
--- a/src/GPU/pair_lj_class2_coul_long_gpu.cpp
+++ b/src/GPU/pair_lj_class2_coul_long_gpu.cpp
@@ -96,8 +96,7 @@ PairLJClass2CoulLongGPU::~PairLJClass2CoulLongGPU()
 
 void PairLJClass2CoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_class2_gpu.cpp b/src/GPU/pair_lj_class2_gpu.cpp
index 8a9b2b31e8..bbb9168169 100644
--- a/src/GPU/pair_lj_class2_gpu.cpp
+++ b/src/GPU/pair_lj_class2_gpu.cpp
@@ -81,8 +81,7 @@ PairLJClass2GPU::~PairLJClass2GPU()
 
 void PairLJClass2GPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cubic_gpu.cpp b/src/GPU/pair_lj_cubic_gpu.cpp
index 669eae4ee4..95eee6ae8f 100644
--- a/src/GPU/pair_lj_cubic_gpu.cpp
+++ b/src/GPU/pair_lj_cubic_gpu.cpp
@@ -86,8 +86,7 @@ PairLJCubicGPU::~PairLJCubicGPU()
 
 void PairLJCubicGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_coul_cut_gpu.cpp b/src/GPU/pair_lj_cut_coul_cut_gpu.cpp
index 99c7bb1c66..69fefbcdea 100644
--- a/src/GPU/pair_lj_cut_coul_cut_gpu.cpp
+++ b/src/GPU/pair_lj_cut_coul_cut_gpu.cpp
@@ -87,8 +87,7 @@ PairLJCutCoulCutGPU::~PairLJCutCoulCutGPU()
 
 void PairLJCutCoulCutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_coul_debye_gpu.cpp b/src/GPU/pair_lj_cut_coul_debye_gpu.cpp
index 450eca5c47..de86c58647 100644
--- a/src/GPU/pair_lj_cut_coul_debye_gpu.cpp
+++ b/src/GPU/pair_lj_cut_coul_debye_gpu.cpp
@@ -89,8 +89,7 @@ ljcd_gpu_clear();
 
 void PairLJCutCoulDebyeGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_coul_dsf_gpu.cpp b/src/GPU/pair_lj_cut_coul_dsf_gpu.cpp
index abe7394a8c..87eac52749 100644
--- a/src/GPU/pair_lj_cut_coul_dsf_gpu.cpp
+++ b/src/GPU/pair_lj_cut_coul_dsf_gpu.cpp
@@ -98,8 +98,7 @@ PairLJCutCoulDSFGPU::~PairLJCutCoulDSFGPU()
 
 void PairLJCutCoulDSFGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_coul_long_gpu.cpp b/src/GPU/pair_lj_cut_coul_long_gpu.cpp
index 943d12b0fe..c854dab83d 100644
--- a/src/GPU/pair_lj_cut_coul_long_gpu.cpp
+++ b/src/GPU/pair_lj_cut_coul_long_gpu.cpp
@@ -99,8 +99,7 @@ PairLJCutCoulLongGPU::~PairLJCutCoulLongGPU()
 
 void PairLJCutCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_coul_msm_gpu.cpp b/src/GPU/pair_lj_cut_coul_msm_gpu.cpp
index 46cf6f19bc..f87dc0ec91 100644
--- a/src/GPU/pair_lj_cut_coul_msm_gpu.cpp
+++ b/src/GPU/pair_lj_cut_coul_msm_gpu.cpp
@@ -88,8 +88,7 @@ PairLJCutCoulMSMGPU::~PairLJCutCoulMSMGPU()
 
 void PairLJCutCoulMSMGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_cut_dipole_cut_gpu.cpp b/src/GPU/pair_lj_cut_dipole_cut_gpu.cpp
index 1f4528cb88..d2c925d950 100644
--- a/src/GPU/pair_lj_cut_dipole_cut_gpu.cpp
+++ b/src/GPU/pair_lj_cut_dipole_cut_gpu.cpp
@@ -89,8 +89,7 @@ PairLJCutDipoleCutGPU::~PairLJCutDipoleCutGPU()
 
 void PairLJCutDipoleCutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
@@ -199,8 +198,7 @@ void PairLJCutDipoleCutGPU::cpu_compute(int start, int inum, int eflag, int vfla
   int *jlist;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/GPU/pair_lj_cut_dipole_long_gpu.cpp b/src/GPU/pair_lj_cut_dipole_long_gpu.cpp
index b209fa0ee7..774ff2fae4 100644
--- a/src/GPU/pair_lj_cut_dipole_long_gpu.cpp
+++ b/src/GPU/pair_lj_cut_dipole_long_gpu.cpp
@@ -100,8 +100,7 @@ PairLJCutDipoleLongGPU::~PairLJCutDipoleLongGPU()
 
 void PairLJCutDipoleLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
@@ -228,8 +227,7 @@ void PairLJCutDipoleLongGPU::cpu_compute(int start, int inum, int eflag, int vfl
   int *jlist;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/GPU/pair_lj_cut_gpu.cpp b/src/GPU/pair_lj_cut_gpu.cpp
index 9a6be3aab9..6dde9689f7 100644
--- a/src/GPU/pair_lj_cut_gpu.cpp
+++ b/src/GPU/pair_lj_cut_gpu.cpp
@@ -86,8 +86,7 @@ PairLJCutGPU::~PairLJCutGPU()
 
 void PairLJCutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_expand_coul_long_gpu.cpp b/src/GPU/pair_lj_expand_coul_long_gpu.cpp
index 4161155980..31f4fd651c 100644
--- a/src/GPU/pair_lj_expand_coul_long_gpu.cpp
+++ b/src/GPU/pair_lj_expand_coul_long_gpu.cpp
@@ -99,8 +99,7 @@ PairLJExpandCoulLongGPU::~PairLJExpandCoulLongGPU()
 
 void PairLJExpandCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_expand_gpu.cpp b/src/GPU/pair_lj_expand_gpu.cpp
index 36378bf10e..a2e1cf54e3 100644
--- a/src/GPU/pair_lj_expand_gpu.cpp
+++ b/src/GPU/pair_lj_expand_gpu.cpp
@@ -85,8 +85,7 @@ PairLJExpandGPU::~PairLJExpandGPU()
 
 void PairLJExpandGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_gromacs_gpu.cpp b/src/GPU/pair_lj_gromacs_gpu.cpp
index cc7010b295..e03f4b2e50 100644
--- a/src/GPU/pair_lj_gromacs_gpu.cpp
+++ b/src/GPU/pair_lj_gromacs_gpu.cpp
@@ -87,8 +87,7 @@ PairLJGromacsGPU::~PairLJGromacsGPU()
 
 void PairLJGromacsGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_sdk_coul_long_gpu.cpp b/src/GPU/pair_lj_sdk_coul_long_gpu.cpp
index 4dbd8874d6..f5029df5dc 100644
--- a/src/GPU/pair_lj_sdk_coul_long_gpu.cpp
+++ b/src/GPU/pair_lj_sdk_coul_long_gpu.cpp
@@ -102,8 +102,7 @@ PairLJSDKCoulLongGPU::~PairLJSDKCoulLongGPU()
 
 void PairLJSDKCoulLongGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_sdk_gpu.cpp b/src/GPU/pair_lj_sdk_gpu.cpp
index 84d224a8c4..4797a34408 100644
--- a/src/GPU/pair_lj_sdk_gpu.cpp
+++ b/src/GPU/pair_lj_sdk_gpu.cpp
@@ -87,8 +87,7 @@ PairLJSDKGPU::~PairLJSDKGPU()
 
 void PairLJSDKGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_lj_sf_dipole_sf_gpu.cpp b/src/GPU/pair_lj_sf_dipole_sf_gpu.cpp
index a5ebb1dbc1..dd25a70eee 100644
--- a/src/GPU/pair_lj_sf_dipole_sf_gpu.cpp
+++ b/src/GPU/pair_lj_sf_dipole_sf_gpu.cpp
@@ -88,8 +88,7 @@ PairLJSFDipoleSFGPU::~PairLJSFDipoleSFGPU()
 
 void PairLJSFDipoleSFGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
@@ -202,8 +201,7 @@ void PairLJSFDipoleSFGPU::cpu_compute(int start, int inum, int eflag, int vflag,
   int *jlist;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/GPU/pair_mie_cut_gpu.cpp b/src/GPU/pair_mie_cut_gpu.cpp
index e52577ee4c..838d28033f 100644
--- a/src/GPU/pair_mie_cut_gpu.cpp
+++ b/src/GPU/pair_mie_cut_gpu.cpp
@@ -83,8 +83,7 @@ PairMIECutGPU::~PairMIECutGPU()
 
 void PairMIECutGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_morse_gpu.cpp b/src/GPU/pair_morse_gpu.cpp
index 7abf78ff30..1f94643e3a 100644
--- a/src/GPU/pair_morse_gpu.cpp
+++ b/src/GPU/pair_morse_gpu.cpp
@@ -81,8 +81,7 @@ PairMorseGPU::~PairMorseGPU()
 
 void PairMorseGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_resquared_gpu.cpp b/src/GPU/pair_resquared_gpu.cpp
index b6fada0897..5e90f788bf 100644
--- a/src/GPU/pair_resquared_gpu.cpp
+++ b/src/GPU/pair_resquared_gpu.cpp
@@ -94,8 +94,7 @@ PairRESquaredGPU::~PairRESquaredGPU()
 
 void PairRESquaredGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_soft_gpu.cpp b/src/GPU/pair_soft_gpu.cpp
index eed1bd5db3..42adb02553 100644
--- a/src/GPU/pair_soft_gpu.cpp
+++ b/src/GPU/pair_soft_gpu.cpp
@@ -86,8 +86,7 @@ PairSoftGPU::~PairSoftGPU()
 
 void PairSoftGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_sw_gpu.cpp b/src/GPU/pair_sw_gpu.cpp
index 5368bee959..0cc858e57d 100644
--- a/src/GPU/pair_sw_gpu.cpp
+++ b/src/GPU/pair_sw_gpu.cpp
@@ -93,8 +93,7 @@ PairSWGPU::~PairSWGPU()
 
 void PairSWGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_table_gpu.cpp b/src/GPU/pair_table_gpu.cpp
index d0185b85e8..a0b6562e5e 100644
--- a/src/GPU/pair_table_gpu.cpp
+++ b/src/GPU/pair_table_gpu.cpp
@@ -89,8 +89,7 @@ PairTableGPU::~PairTableGPU()
 
 void PairTableGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_tersoff_gpu.cpp b/src/GPU/pair_tersoff_gpu.cpp
index 535b56163e..cd0c5e6693 100644
--- a/src/GPU/pair_tersoff_gpu.cpp
+++ b/src/GPU/pair_tersoff_gpu.cpp
@@ -97,8 +97,7 @@ PairTersoffGPU::~PairTersoffGPU()
 
 void PairTersoffGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_tersoff_mod_gpu.cpp b/src/GPU/pair_tersoff_mod_gpu.cpp
index f8b6c50db5..fd55ddc6e6 100644
--- a/src/GPU/pair_tersoff_mod_gpu.cpp
+++ b/src/GPU/pair_tersoff_mod_gpu.cpp
@@ -90,8 +90,7 @@ PairTersoffMODGPU::~PairTersoffMODGPU()
 
 void PairTersoffMODGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_tersoff_zbl_gpu.cpp b/src/GPU/pair_tersoff_zbl_gpu.cpp
index b45503d759..d3828962e2 100644
--- a/src/GPU/pair_tersoff_zbl_gpu.cpp
+++ b/src/GPU/pair_tersoff_zbl_gpu.cpp
@@ -98,8 +98,7 @@ PairTersoffZBLGPU::~PairTersoffZBLGPU()
 
 void PairTersoffZBLGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_ufm_gpu.cpp b/src/GPU/pair_ufm_gpu.cpp
index 688e3ef4dc..31422b0f4d 100644
--- a/src/GPU/pair_ufm_gpu.cpp
+++ b/src/GPU/pair_ufm_gpu.cpp
@@ -88,8 +88,7 @@ PairUFMGPU::~PairUFMGPU()
 
 void PairUFMGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_vashishta_gpu.cpp b/src/GPU/pair_vashishta_gpu.cpp
index 84936f2c26..b496359b8a 100644
--- a/src/GPU/pair_vashishta_gpu.cpp
+++ b/src/GPU/pair_vashishta_gpu.cpp
@@ -94,8 +94,7 @@ PairVashishtaGPU::~PairVashishtaGPU()
 
 void PairVashishtaGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_yukawa_colloid_gpu.cpp b/src/GPU/pair_yukawa_colloid_gpu.cpp
index 556dece7f8..3645f392a2 100644
--- a/src/GPU/pair_yukawa_colloid_gpu.cpp
+++ b/src/GPU/pair_yukawa_colloid_gpu.cpp
@@ -84,8 +84,7 @@ PairYukawaColloidGPU::~PairYukawaColloidGPU()
 
 void PairYukawaColloidGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_yukawa_gpu.cpp b/src/GPU/pair_yukawa_gpu.cpp
index 9d3ea6f5a7..90317fea34 100644
--- a/src/GPU/pair_yukawa_gpu.cpp
+++ b/src/GPU/pair_yukawa_gpu.cpp
@@ -83,8 +83,7 @@ PairYukawaGPU::~PairYukawaGPU()
 
 void PairYukawaGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pair_zbl_gpu.cpp b/src/GPU/pair_zbl_gpu.cpp
index c9b8dd75a1..99471cbe90 100644
--- a/src/GPU/pair_zbl_gpu.cpp
+++ b/src/GPU/pair_zbl_gpu.cpp
@@ -86,8 +86,7 @@ PairZBLGPU::~PairZBLGPU()
 
 void PairZBLGPU::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int nall = atom->nlocal + atom->nghost;
   int inum, host_start;
diff --git a/src/GPU/pppm_gpu.cpp b/src/GPU/pppm_gpu.cpp
index 4b460b1280..1bb1a39703 100644
--- a/src/GPU/pppm_gpu.cpp
+++ b/src/GPU/pppm_gpu.cpp
@@ -199,9 +199,7 @@ void PPPMGPU::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-        eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // If need per-atom energies/virials, allocate per-atom arrays here
   // so that particle map on host can be done concurrently with GPU calculations
diff --git a/src/GRANULAR/fix_wall_gran.cpp b/src/GRANULAR/fix_wall_gran.cpp
index f0957423f9..555c5071e7 100644
--- a/src/GRANULAR/fix_wall_gran.cpp
+++ b/src/GRANULAR/fix_wall_gran.cpp
@@ -39,15 +39,34 @@ using namespace MathConst;
 // XYZ PLANE need to be 0,1,2
 
 enum{XPLANE=0,YPLANE=1,ZPLANE=2,ZCYLINDER,REGION};
-enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY,BONDED_HISTORY};
+enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY,GRANULAR};
 enum{NONE,CONSTANT,EQUAL};
 
+#define PI27SQ 266.47931882941264802866    // 27*PI**2
+#define THREEROOT3 5.19615242270663202362  // 3*sqrt(3)
+#define SIXROOT6 14.69693845669906728801   // 6*sqrt(6)
+#define INVROOT6 0.40824829046386307274    // 1/sqrt(6)
+#define FOURTHIRDS 1.333333333333333       // 4/3
+#define THREEQUARTERS 0.75                 // 3/4
+#define TWOPI 6.28318530717959             // 2*PI
+
+#define EPSILON 1e-10
+
+enum {NORMAL_HOOKE, NORMAL_HERTZ, HERTZ_MATERIAL, DMT, JKR};
+enum {VELOCITY, VISCOELASTIC, TSUJI};
+enum {TANGENTIAL_NOHISTORY, TANGENTIAL_HISTORY,
+      TANGENTIAL_MINDLIN, TANGENTIAL_MINDLIN_RESCALE};
+enum {TWIST_NONE, TWIST_SDS, TWIST_MARSHALL};
+enum {ROLL_NONE, ROLL_SDS};
+
 #define BIG 1.0e20
+#define EPSILON 1e-10
 
 /* ---------------------------------------------------------------------- */
 
 FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
-  Fix(lmp, narg, arg), idregion(NULL), shearone(NULL), fix_rigid(NULL), mass_rigid(NULL)
+  Fix(lmp, narg, arg), idregion(NULL), history_one(NULL),
+  fix_rigid(NULL), mass_rigid(NULL)
 {
   if (narg < 4) error->all(FLERR,"Illegal fix wall/gran command");
 
@@ -62,17 +81,18 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
   if (strcmp(arg[3],"hooke") == 0) pairstyle = HOOKE;
   else if (strcmp(arg[3],"hooke/history") == 0) pairstyle = HOOKE_HISTORY;
   else if (strcmp(arg[3],"hertz/history") == 0) pairstyle = HERTZ_HISTORY;
-  //else if (strcmp(arg[3],"bonded/history") == 0) pairstyle = BONDED_HISTORY;
+  else if (strcmp(arg[3],"granular") == 0) pairstyle = GRANULAR;
   else error->all(FLERR,"Invalid fix wall/gran interaction style");
 
-  history = restart_peratom = 1;
-  if (pairstyle == HOOKE) history = restart_peratom = 0;
+  use_history = restart_peratom = 1;
+  if (pairstyle == HOOKE) use_history = restart_peratom = 0;
 
   // wall/particle coefficients
 
   int iarg;
 
-  if (pairstyle != BONDED_HISTORY) {
+  if (pairstyle != GRANULAR) {
+    size_history = 3;
     if (narg < 11) error->all(FLERR,"Illegal fix wall/gran command");
 
     kn = force->numeric(FLERR,arg[4]);
@@ -97,25 +117,186 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
       kn /= force->nktv2p;
       kt /= force->nktv2p;
     }
-
     iarg = 10;
-  }
-
-  else {
-    if (narg < 10) error->all(FLERR,"Illegal fix wall/gran command");
-
-    E = force->numeric(FLERR,arg[4]);
-    G = force->numeric(FLERR,arg[5]);
-    SurfEnergy = force->numeric(FLERR,arg[6]);
-    // Note: this doesn't get used, check w/ Jeremy?
-    gamman = force->numeric(FLERR,arg[7]);
-
-    xmu = force->numeric(FLERR,arg[8]);
-    // pois = E/(2.0*G) - 1.0;
-    // kn = 2.0*E/(3.0*(1.0+pois)*(1.0-pois));
-    // gammat=0.5*gamman;
-
-    iarg = 9;
+  } else {
+    iarg = 4;
+    damping_model = VISCOELASTIC;
+    roll_model = twist_model = NONE;
+    while (iarg < narg) {
+      if (strcmp(arg[iarg], "hooke") == 0) {
+        if (iarg + 2 >= narg)
+          error->all(FLERR,"Illegal fix wall/gran command, "
+                     "not enough parameters provided for Hooke option");
+        normal_model = NORMAL_HOOKE;
+        normal_coeffs[0] = force->numeric(FLERR,arg[iarg+1]); //kn
+        normal_coeffs[1] = force->numeric(FLERR,arg[iarg+2]); //damping
+        iarg += 3;
+      } else if (strcmp(arg[iarg], "hertz") == 0) {
+        int num_coeffs = 2;
+        if (iarg + num_coeffs >= narg)
+          error->all(FLERR,"Illegal fix wall/gran command, "
+                     "not enough parameters provided for Hertz option");
+        normal_model = NORMAL_HERTZ;
+        normal_coeffs[0] = force->numeric(FLERR,arg[iarg+1]); //kn
+        normal_coeffs[1] = force->numeric(FLERR,arg[iarg+2]); //damping
+        iarg += num_coeffs+1;
+      } else if (strcmp(arg[iarg], "hertz/material") == 0) {
+        int num_coeffs = 3;
+        if (iarg + num_coeffs >= narg)
+          error->all(FLERR,"Illegal fix wall/gran command, "
+                     "not enough parameters provided for Hertz option");
+        normal_model = HERTZ_MATERIAL;
+        Emod = force->numeric(FLERR,arg[iarg+1]); //E
+        normal_coeffs[1] = force->numeric(FLERR,arg[iarg+2]); //damping
+        poiss = force->numeric(FLERR,arg[iarg+3]); //Poisson's ratio
+        normal_coeffs[0] = Emod/(2*(1-poiss))*FOURTHIRDS;
+        normal_coeffs[2] = poiss;
+        iarg += num_coeffs+1;
+      } else if (strcmp(arg[iarg], "dmt") == 0) {
+        if (iarg + 4 >= narg)
+          error->all(FLERR,"Illegal fix wall/gran command, "
+                     "not enough parameters provided for Hertz option");
+        normal_model = DMT;
+        Emod = force->numeric(FLERR,arg[iarg+1]); //E
+        normal_coeffs[1] = force->numeric(FLERR,arg[iarg+2]); //damping
+        poiss = force->numeric(FLERR,arg[iarg+3]); //Poisson's ratio
+        normal_coeffs[0] = Emod/(2*(1-poiss))*FOURTHIRDS;
+        normal_coeffs[2] = poiss;
+        normal_coeffs[3] = force->numeric(FLERR,arg[iarg+4]); //cohesion
+        iarg += 5;
+      } else if (strcmp(arg[iarg], "jkr") == 0) {
+        if (iarg + 4 >= narg)
+          error->all(FLERR,"Illegal wall/gran command, "
+                     "not enough parameters provided for JKR option");
+        normal_model = JKR;
+        Emod = force->numeric(FLERR,arg[iarg+1]); //E
+        normal_coeffs[1] = force->numeric(FLERR,arg[iarg+2]); //damping
+        poiss = force->numeric(FLERR,arg[iarg+3]); //Poisson's ratio
+        normal_coeffs[0] = Emod/(2*(1-poiss))*FOURTHIRDS;
+        normal_coeffs[2] = poiss;
+        normal_coeffs[3] = force->numeric(FLERR,arg[iarg+4]); //cohesion
+        iarg += 5;
+      } else if (strcmp(arg[iarg], "damping") == 0) {
+        if (iarg+1 >= narg)
+          error->all(FLERR, "Illegal wall/gran command, "
+                     "not enough parameters provided for damping model");
+        if (strcmp(arg[iarg+1], "velocity") == 0) {
+          damping_model = VELOCITY;
+          iarg += 1;
+        } else if (strcmp(arg[iarg+1], "viscoelastic") == 0) {
+          damping_model = VISCOELASTIC;
+          iarg += 1;
+        } else if (strcmp(arg[iarg+1], "tsuji") == 0) {
+          damping_model = TSUJI;
+          iarg += 1;
+        } else error->all(FLERR, "Illegal wall/gran command, "
+                          "unrecognized damping model");
+        iarg += 1;
+      } else if (strcmp(arg[iarg], "tangential") == 0) {
+        if (iarg + 1 >= narg)
+          error->all(FLERR,"Illegal pair_coeff command, "
+                     "must specify tangential model after tangential keyword");
+        if (strcmp(arg[iarg+1], "linear_nohistory") == 0) {
+          if (iarg + 3 >= narg)
+            error->all(FLERR,"Illegal pair_coeff command, "
+                       "not enough parameters provided for tangential model");
+          tangential_model = TANGENTIAL_NOHISTORY;
+          tangential_coeffs[0] = 0;
+          // gammat and friction coeff
+          tangential_coeffs[1] = force->numeric(FLERR,arg[iarg+2]);
+          tangential_coeffs[2] = force->numeric(FLERR,arg[iarg+3]);
+          iarg += 4;
+        } else if ((strcmp(arg[iarg+1], "linear_history") == 0) ||
+            (strcmp(arg[iarg+1], "mindlin") == 0) ||
+            (strcmp(arg[iarg+1], "mindlin_rescale") == 0)) {
+          if (iarg + 4 >= narg)
+            error->all(FLERR,"Illegal pair_coeff command, "
+                       "not enough parameters provided for tangential model");
+          if (strcmp(arg[iarg+1], "linear_history") == 0)
+            tangential_model = TANGENTIAL_HISTORY;
+          else if (strcmp(arg[iarg+1], "mindlin") == 0)
+            tangential_model = TANGENTIAL_MINDLIN;
+          else if (strcmp(arg[iarg+1], "mindlin_rescale") == 0)
+            tangential_model = TANGENTIAL_MINDLIN_RESCALE;
+          if ((tangential_model == TANGENTIAL_MINDLIN ||
+               tangential_model == TANGENTIAL_MINDLIN_RESCALE) &&
+              (strcmp(arg[iarg+2], "NULL") == 0)) {
+            if (normal_model == NORMAL_HERTZ || normal_model == NORMAL_HOOKE) {
+              error->all(FLERR, "NULL setting for Mindlin tangential "
+                         "stiffness requires a normal contact model "
+                         "that specifies material properties");
+            }
+            tangential_coeffs[0] = 4*(2-poiss)*(1+poiss)/Emod;
+          } else {
+            tangential_coeffs[0] = force->numeric(FLERR,arg[iarg+2]); //kt
+          }
+          tangential_history = 1;
+          // gammat and friction coeff
+          tangential_coeffs[1] = force->numeric(FLERR,arg[iarg+3]);
+          tangential_coeffs[2] = force->numeric(FLERR,arg[iarg+4]);
+          iarg += 5;
+        } else {
+          error->all(FLERR, "Illegal pair_coeff command, "
+                     "tangential model not recognized");
+        }
+      } else if (strcmp(arg[iarg], "rolling") == 0) {
+        if (iarg + 1 >= narg)
+          error->all(FLERR, "Illegal wall/gran command, not enough parameters");
+        if (strcmp(arg[iarg+1], "none") == 0) {
+          roll_model = ROLL_NONE;
+          iarg += 2;
+        } else if (strcmp(arg[iarg+1], "sds") == 0) {
+          if (iarg + 4 >= narg)
+            error->all(FLERR,"Illegal wall/gran command, "
+                       "not enough parameters provided for rolling model");
+          roll_model = ROLL_SDS;
+          roll_history = 1;
+          // kR, gammaR, rolling friction coeff
+          roll_coeffs[0] = force->numeric(FLERR,arg[iarg+2]);
+          roll_coeffs[1] = force->numeric(FLERR,arg[iarg+3]);
+          roll_coeffs[2] = force->numeric(FLERR,arg[iarg+4]);
+          iarg += 5;
+        } else {
+          error->all(FLERR, "Illegal wall/gran command, "
+                     "rolling friction model not recognized");
+        }
+      } else if (strcmp(arg[iarg], "twisting") == 0) {
+        if (iarg + 1 >= narg)
+          error->all(FLERR, "Illegal wall/gran command, not enough parameters");
+        if (strcmp(arg[iarg+1], "none") == 0) {
+          twist_model = TWIST_NONE;
+          iarg += 2;
+        } else if (strcmp(arg[iarg+1], "marshall") == 0) {
+          twist_model = TWIST_MARSHALL;
+          twist_history = 1;
+          iarg += 2;
+        } else if (strcmp(arg[iarg+1], "sds") == 0) {
+          if (iarg + 4 >= narg)
+            error->all(FLERR,"Illegal wall/gran command, "
+                       "not enough parameters provided for twist model");
+          twist_model = TWIST_SDS;
+          twist_history = 1;
+          twist_coeffs[0] = force->numeric(FLERR,arg[iarg+2]); //kt
+          twist_coeffs[1] = force->numeric(FLERR,arg[iarg+3]); //gammat
+          twist_coeffs[2] = force->numeric(FLERR,arg[iarg+4]); //friction coeff.
+          iarg += 5;
+        } else {
+          error->all(FLERR, "Illegal wall/gran command, "
+                     "twisting friction model not recognized");
+        }
+      } else if (strcmp(arg[iarg], "xplane") == 0 ||
+          strcmp(arg[iarg], "yplane") == 0 ||
+          strcmp(arg[iarg], "zplane") == 0 ||
+          strcmp(arg[iarg], "zcylinder") == 0 ||
+          strcmp(arg[iarg], "region") == 0) {
+        break;
+      } else {
+        error->all(FLERR, "Illegal fix wall/gran command");
+      }
+    }
+    size_history = 3*tangential_history + 3*roll_history + twist_history;
+    if (normal_model == JKR) size_history += 1;
+    if (tangential_model == TANGENTIAL_MINDLIN_RESCALE) size_history += 1;
   }
 
   // wallstyle args
@@ -165,6 +346,7 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
 
   wiggle = 0;
   wshear = 0;
+  peratom_flag = 0;
 
   while (iarg < narg) {
     if (strcmp(arg[iarg],"wiggle") == 0) {
@@ -186,6 +368,11 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
       vshear = force->numeric(FLERR,arg[iarg+2]);
       wshear = 1;
       iarg += 3;
+    } else if (strcmp(arg[iarg],"store_contacts") == 0) {
+      peratom_flag = 1;
+      size_peratom_cols = 8;
+      peratom_freq = 1;
+      iarg += 1;
     } else error->all(FLERR,"Illegal fix wall/gran command");
   }
 
@@ -218,10 +405,7 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
   // perform initial allocation of atom-based arrays
   // register with Atom class
 
-  if (pairstyle == BONDED_HISTORY) sheardim = 7;
-  else sheardim = 3;
-
-  shearone = NULL;
+  history_one = NULL;
   grow_arrays(atom->nmax);
   atom->add_callback(0);
   atom->add_callback(1);
@@ -229,14 +413,21 @@ FixWallGran::FixWallGran(LAMMPS *lmp, int narg, char **arg) :
   nmax = 0;
   mass_rigid = NULL;
 
-  // initialize shear history as if particle is not touching region
-  // shearone will be NULL for wallstyle = REGION
+  // initialize history as if particle is not touching region
+  // history_one will be NULL for wallstyle = REGION
 
-  if (history && shearone) {
+  if (use_history && history_one) {
     int nlocal = atom->nlocal;
     for (int i = 0; i < nlocal; i++)
-      for (int j = 0; j < sheardim; j++)
-        shearone[i][j] = 0.0;
+      for (int j = 0; j < size_history; j++)
+        history_one[i][j] = 0.0;
+  }
+
+  if (peratom_flag) {
+    int nlocal = atom->nlocal;
+    for (int i = 0; i < nlocal; i++)
+      for (int m = 0; m < size_peratom_cols; m++)
+        array_atom[i][m] = 0.0;
   }
 
   time_origin = update->ntimestep;
@@ -254,7 +445,7 @@ FixWallGran::~FixWallGran()
   // delete local storage
 
   delete [] idregion;
-  memory->destroy(shearone);
+  memory->destroy(history_one);
   memory->destroy(mass_rigid);
 }
 
@@ -285,6 +476,38 @@ void FixWallGran::init()
   for (i = 0; i < modify->nfix; i++)
     if (modify->fix[i]->rigid_flag) break;
   if (i < modify->nfix) fix_rigid = modify->fix[i];
+
+  tangential_history_index = 0;
+  if (roll_history) {
+    if (tangential_history) roll_history_index = 3;
+    else roll_history_index = 0;
+  }
+  if (twist_history) {
+    if (tangential_history) {
+      if (roll_history) twist_history_index = 6;
+      else twist_history_index = 3;
+    }
+    else{
+      if (roll_history) twist_history_index = 3;
+      else twist_history_index = 0;
+    }
+  }
+  if (normal_model == JKR) {
+    tangential_history_index += 1;
+    roll_history_index += 1;
+    twist_history_index += 1;
+  }
+  if (tangential_model == TANGENTIAL_MINDLIN_RESCALE) {
+    roll_history_index += 1;
+    twist_history_index += 1;
+  }
+
+  if (damping_model == TSUJI) {
+    double cor = normal_coeffs[1];
+    normal_coeffs[1] = 1.2728-4.2783*cor+11.087*pow(cor,2)-22.348*pow(cor,3)+
+        27.467*pow(cor,4)-18.022*pow(cor,5)+
+        4.8218*pow(cor,6);
+  }
 }
 
 /* ---------------------------------------------------------------------- */
@@ -308,10 +531,10 @@ void FixWallGran::post_force(int /*vflag*/)
   double dx,dy,dz,del1,del2,delxy,delr,rsq,rwall,meff;
   double vwall[3];
 
-  // do not update shear history during setup
+  // do not update history during setup
 
-  shearupdate = 1;
-  if (update->setupflag) shearupdate = 0;
+  history_update = 1;
+  if (update->setupflag) history_update = 0;
 
   // if just reneighbored:
   // update rigid body masses for owned atoms if using FixRigid
@@ -357,7 +580,7 @@ void FixWallGran::post_force(int /*vflag*/)
   //   if wall was set to NULL, it's skipped since lo/hi are infinity
   // compute force and torque on atom if close enough to wall
   //   via wall potential matched to pair potential
-  // set shear if pair potential stores history
+  // set history if pair potential stores history
 
   double **x = atom->x;
   double **v = atom->v;
@@ -412,12 +635,28 @@ void FixWallGran::post_force(int /*vflag*/)
 
       rsq = dx*dx + dy*dy + dz*dz;
 
-      if (rsq > radius[i]*radius[i]) {
-        if (history)
-          for (j = 0; j < sheardim; j++)
-            shearone[i][j] = 0.0;
+      double rad;
+      if (pairstyle == GRANULAR && normal_model == JKR) {
+        rad = radius[i] + pulloff_distance(radius[i]);
+      }
+      else
+        rad = radius[i];
 
-      } else {
+      if (rsq > rad*rad) {
+        if (use_history)
+          for (j = 0; j < size_history; j++)
+            history_one[i][j] = 0.0;
+      }
+      else {
+        if (pairstyle == GRANULAR && normal_model == JKR && use_history) {
+          if ((history_one[i][0] == 0) && (rsq > radius[i]*radius[i])) {
+            // Particles have not contacted yet,
+            // and are outside of contact distance
+            for (j = 0; j < size_history; j++)
+              history_one[i][j] = 0.0;
+            continue;
+          }
+        }
 
         // meff = effective mass of sphere
         // if I is part of rigid body, use body mass
@@ -425,20 +664,37 @@ void FixWallGran::post_force(int /*vflag*/)
         meff = rmass[i];
         if (fix_rigid && mass_rigid[i] > 0.0) meff = mass_rigid[i];
 
+        // store contact info
+        if (peratom_flag) {
+          array_atom[i][0] = (double)atom->tag[i];
+          array_atom[i][4] = x[i][0] - dx;
+          array_atom[i][5] = x[i][1] - dy;
+          array_atom[i][6] = x[i][2] - dz;
+          array_atom[i][7] = radius[i];
+        }
+
         // invoke sphere/wall interaction
+        double *contact;
+        if (peratom_flag)
+          contact = array_atom[i];
+        else
+          contact = NULL;
 
         if (pairstyle == HOOKE)
           hooke(rsq,dx,dy,dz,vwall,v[i],f[i],
-                omega[i],torque[i],radius[i],meff);
+              omega[i],torque[i],radius[i],meff, contact);
         else if (pairstyle == HOOKE_HISTORY)
           hooke_history(rsq,dx,dy,dz,vwall,v[i],f[i],
-                        omega[i],torque[i],radius[i],meff,shearone[i]);
+              omega[i],torque[i],radius[i],meff,history_one[i],
+              contact);
         else if (pairstyle == HERTZ_HISTORY)
           hertz_history(rsq,dx,dy,dz,vwall,rwall,v[i],f[i],
-                        omega[i],torque[i],radius[i],meff,shearone[i]);
-        else if (pairstyle == BONDED_HISTORY)
-          bonded_history(rsq,dx,dy,dz,vwall,rwall,v[i],f[i],
-                         omega[i],torque[i],radius[i],meff,shearone[i]);
+              omega[i],torque[i],radius[i],meff,history_one[i],
+              contact);
+        else if (pairstyle == GRANULAR)
+          granular(rsq,dx,dy,dz,vwall,rwall,v[i],f[i],
+              omega[i],torque[i],radius[i],meff,history_one[i],
+              contact);
       }
     }
   }
@@ -454,9 +710,9 @@ void FixWallGran::post_force_respa(int vflag, int ilevel, int /*iloop*/)
 /* ---------------------------------------------------------------------- */
 
 void FixWallGran::hooke(double rsq, double dx, double dy, double dz,
-                        double *vwall, double *v,
-                        double *f, double *omega, double *torque,
-                        double radius, double meff)
+    double *vwall, double *v,
+    double *f, double *omega, double *torque,
+    double radius, double meff, double* contact)
 {
   double r,vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
   double wr1,wr2,wr3,damp,ccel,vtr1,vtr2,vtr3,vrel;
@@ -523,6 +779,12 @@ void FixWallGran::hooke(double rsq, double dx, double dy, double dz,
   fy = dy*ccel + fs2;
   fz = dz*ccel + fs3;
 
+  if (peratom_flag) {
+    contact[1] = fx;
+    contact[2] = fy;
+    contact[3] = fz;
+  }
+
   f[0] += fx;
   f[1] += fy;
   f[2] += fz;
@@ -538,9 +800,10 @@ void FixWallGran::hooke(double rsq, double dx, double dy, double dz,
 /* ---------------------------------------------------------------------- */
 
 void FixWallGran::hooke_history(double rsq, double dx, double dy, double dz,
-                                double *vwall, double *v,
-                                double *f, double *omega, double *torque,
-                                double radius, double meff, double *shear)
+    double *vwall, double *v,
+    double *f, double *omega, double *torque,
+    double radius, double meff, double *history,
+    double *contact)
 {
   double r,vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
   double wr1,wr2,wr3,damp,ccel,vtr1,vtr2,vtr3,vrel;
@@ -591,28 +854,29 @@ void FixWallGran::hooke_history(double rsq, double dx, double dy, double dz,
 
   // shear history effects
 
-  if (shearupdate) {
-    shear[0] += vtr1*dt;
-    shear[1] += vtr2*dt;
-    shear[2] += vtr3*dt;
+  if (history_update) {
+    history[0] += vtr1*dt;
+    history[1] += vtr2*dt;
+    history[2] += vtr3*dt;
   }
-  shrmag = sqrt(shear[0]*shear[0] + shear[1]*shear[1] + shear[2]*shear[2]);
+  shrmag = sqrt(history[0]*history[0] + history[1]*history[1] +
+                history[2]*history[2]);
 
   // rotate shear displacements
 
-  rsht = shear[0]*dx + shear[1]*dy + shear[2]*dz;
+  rsht = history[0]*dx + history[1]*dy + history[2]*dz;
   rsht = rsht*rsqinv;
-  if (shearupdate) {
-    shear[0] -= rsht*dx;
-    shear[1] -= rsht*dy;
-    shear[2] -= rsht*dz;
+  if (history_update) {
+    history[0] -= rsht*dx;
+    history[1] -= rsht*dy;
+    history[2] -= rsht*dz;
   }
 
   // tangential forces = shear + tangential velocity damping
 
-  fs1 = - (kt*shear[0] + meff*gammat*vtr1);
-  fs2 = - (kt*shear[1] + meff*gammat*vtr2);
-  fs3 = - (kt*shear[2] + meff*gammat*vtr3);
+  fs1 = - (kt*history[0] + meff*gammat*vtr1);
+  fs2 = - (kt*history[1] + meff*gammat*vtr2);
+  fs3 = - (kt*history[2] + meff*gammat*vtr3);
 
   // rescale frictional displacements and forces if needed
 
@@ -621,12 +885,12 @@ void FixWallGran::hooke_history(double rsq, double dx, double dy, double dz,
 
   if (fs > fn) {
     if (shrmag != 0.0) {
-      shear[0] = (fn/fs) * (shear[0] + meff*gammat*vtr1/kt) -
-        meff*gammat*vtr1/kt;
-      shear[1] = (fn/fs) * (shear[1] + meff*gammat*vtr2/kt) -
-        meff*gammat*vtr2/kt;
-      shear[2] = (fn/fs) * (shear[2] + meff*gammat*vtr3/kt) -
-        meff*gammat*vtr3/kt;
+      history[0] = (fn/fs) * (history[0] + meff*gammat*vtr1/kt) -
+          meff*gammat*vtr1/kt;
+      history[1] = (fn/fs) * (history[1] + meff*gammat*vtr2/kt) -
+          meff*gammat*vtr2/kt;
+      history[2] = (fn/fs) * (history[2] + meff*gammat*vtr3/kt) -
+          meff*gammat*vtr3/kt;
       fs1 *= fn/fs ;
       fs2 *= fn/fs;
       fs3 *= fn/fs;
@@ -643,6 +907,12 @@ void FixWallGran::hooke_history(double rsq, double dx, double dy, double dz,
   f[1] += fy;
   f[2] += fz;
 
+  if (peratom_flag) {
+    contact[1] = fx;
+    contact[2] = fy;
+    contact[3] = fz;
+  }
+
   tor1 = rinv * (dy*fs3 - dz*fs2);
   tor2 = rinv * (dz*fs1 - dx*fs3);
   tor3 = rinv * (dx*fs2 - dy*fs1);
@@ -654,9 +924,10 @@ void FixWallGran::hooke_history(double rsq, double dx, double dy, double dz,
 /* ---------------------------------------------------------------------- */
 
 void FixWallGran::hertz_history(double rsq, double dx, double dy, double dz,
-                                double *vwall, double rwall, double *v,
-                                double *f, double *omega, double *torque,
-                                double radius, double meff, double *shear)
+    double *vwall, double rwall, double *v,
+    double *f, double *omega, double *torque,
+    double radius, double meff, double *history,
+    double *contact)
 {
   double r,vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
   double wr1,wr2,wr3,damp,ccel,vtr1,vtr2,vtr3,vrel;
@@ -714,28 +985,29 @@ void FixWallGran::hertz_history(double rsq, double dx, double dy, double dz,
 
   // shear history effects
 
-  if (shearupdate) {
-    shear[0] += vtr1*dt;
-    shear[1] += vtr2*dt;
-    shear[2] += vtr3*dt;
+  if (history_update) {
+    history[0] += vtr1*dt;
+    history[1] += vtr2*dt;
+    history[2] += vtr3*dt;
   }
-  shrmag = sqrt(shear[0]*shear[0] + shear[1]*shear[1] + shear[2]*shear[2]);
+  shrmag = sqrt(history[0]*history[0] + history[1]*history[1] +
+                history[2]*history[2]);
 
-  // rotate shear displacements
+  // rotate history displacements
 
-  rsht = shear[0]*dx + shear[1]*dy + shear[2]*dz;
+  rsht = history[0]*dx + history[1]*dy + history[2]*dz;
   rsht = rsht*rsqinv;
-  if (shearupdate) {
-    shear[0] -= rsht*dx;
-    shear[1] -= rsht*dy;
-    shear[2] -= rsht*dz;
+  if (history_update) {
+    history[0] -= rsht*dx;
+    history[1] -= rsht*dy;
+    history[2] -= rsht*dz;
   }
 
   // tangential forces = shear + tangential velocity damping
 
-  fs1 = -polyhertz * (kt*shear[0] + meff*gammat*vtr1);
-  fs2 = -polyhertz * (kt*shear[1] + meff*gammat*vtr2);
-  fs3 = -polyhertz * (kt*shear[2] + meff*gammat*vtr3);
+  fs1 = -polyhertz * (kt*history[0] + meff*gammat*vtr1);
+  fs2 = -polyhertz * (kt*history[1] + meff*gammat*vtr2);
+  fs3 = -polyhertz * (kt*history[2] + meff*gammat*vtr3);
 
   // rescale frictional displacements and forces if needed
 
@@ -744,12 +1016,12 @@ void FixWallGran::hertz_history(double rsq, double dx, double dy, double dz,
 
   if (fs > fn) {
     if (shrmag != 0.0) {
-      shear[0] = (fn/fs) * (shear[0] + meff*gammat*vtr1/kt) -
-        meff*gammat*vtr1/kt;
-      shear[1] = (fn/fs) * (shear[1] + meff*gammat*vtr2/kt) -
-        meff*gammat*vtr2/kt;
-      shear[2] = (fn/fs) * (shear[2] + meff*gammat*vtr3/kt) -
-        meff*gammat*vtr3/kt;
+      history[0] = (fn/fs) * (history[0] + meff*gammat*vtr1/kt) -
+          meff*gammat*vtr1/kt;
+      history[1] = (fn/fs) * (history[1] + meff*gammat*vtr2/kt) -
+          meff*gammat*vtr2/kt;
+      history[2] = (fn/fs) * (history[2] + meff*gammat*vtr3/kt) -
+          meff*gammat*vtr3/kt;
       fs1 *= fn/fs ;
       fs2 *= fn/fs;
       fs3 *= fn/fs;
@@ -762,6 +1034,12 @@ void FixWallGran::hertz_history(double rsq, double dx, double dy, double dz,
   fy = dy*ccel + fs2;
   fz = dz*ccel + fs3;
 
+  if (peratom_flag) {
+    contact[1] = fx;
+    contact[2] = fy;
+    contact[3] = fz;
+  }
+
   f[0] += fx;
   f[1] += fy;
   f[2] += fz;
@@ -774,33 +1052,62 @@ void FixWallGran::hertz_history(double rsq, double dx, double dy, double dz,
   torque[2] -= radius*tor3;
 }
 
-
 /* ---------------------------------------------------------------------- */
 
-void FixWallGran::bonded_history(double rsq, double dx, double dy, double dz,
-                                 double *vwall, double rwall, double *v,
-                                 double *f, double *omega, double *torque,
-                                 double radius, double meff, double *shear)
+void FixWallGran::granular(double rsq, double dx, double dy, double dz,
+                           double *vwall, double rwall, double *v,
+                           double *f, double *omega, double *torque,
+                           double radius, double meff, double *history,
+                           double *contact)
 {
-  double r,vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
-  double wr1,wr2,wr3,damp,ccel,vtr1,vtr2,vtr3,vrel;
-  double fn,fs,fs1,fs2,fs3,fx,fy,fz,tor1,tor2,tor3;
-  double shrmag,rsht,polyhertz,rinv,rsqinv;
+  double fx,fy,fz,nx,ny,nz;
+  double radsum,r,rinv;
+  double Reff, delta, dR, dR2;
 
-  double pois,E_eff,G_eff,rad_eff;
-  double a0,Fcrit,delcrit,delcritinv;
-  double overlap,olapsq,olapcubed,sqrtterm,tmp,keyterm,keyterm2,keyterm3;
-  double aovera0,foverFc;
-  double gammatsuji;
+  double vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
+  double wr1,wr2,wr3;
+  double vtr1,vtr2,vtr3,vrel;
 
-  double ktwist,kroll,twistcrit,rollcrit;
-  double relrot1,relrot2,relrot3,vrl1,vrl2,vrl3,vrlmag,vrlmaginv;
-  double magtwist,magtortwist;
-  double magrollsq,magroll,magrollinv,magtorroll;
+  double knfac, damp_normal, damp_normal_prefactor;
+  double k_tangential, damp_tangential;
+  double Fne, Ft, Fdamp, Fntot, Fncrit, Fscrit, Frcrit;
+  double fs, fs1, fs2, fs3;
+
+  double tor1,tor2,tor3;
+  double relrot1,relrot2,relrot3,vrl1,vrl2,vrl3;
+
+  // for JKR
+  double R2, coh, F_pulloff, a, a2, E;
+  double t0, t1, t2, t3, t4, t5, t6;
+  double sqrt1, sqrt2, sqrt3;
+
+  // rolling
+  double k_roll, damp_roll;
+  double torroll1, torroll2, torroll3;
+  double rollmag, rolldotn, scalefac;
+  double fr, fr1, fr2, fr3;
+
+  // twisting
+  double k_twist, damp_twist, mu_twist;
+  double signtwist, magtwist, magtortwist, Mtcrit;
+  double tortwist1, tortwist2, tortwist3;
+
+  double shrmag,rsht;
 
   r = sqrt(rsq);
+  radsum = rwall + radius;
+
+  E = normal_coeffs[0];
+
+  radsum = radius + rwall;
+  if (rwall == 0) Reff = radius;
+  else Reff = radius*rwall/(radius+rwall);
+
   rinv = 1.0/r;
-  rsqinv = 1.0/rsq;
+
+  nx = dx*rinv;
+  ny = dy*rinv;
+  nz = dz*rinv;
 
   // relative translational velocity
 
@@ -810,209 +1117,315 @@ void FixWallGran::bonded_history(double rsq, double dx, double dy, double dz,
 
   // normal component
 
-  vnnr = vr1*dx + vr2*dy + vr3*dz;
-  vn1 = dx*vnnr / rsq;
-  vn2 = dy*vnnr / rsq;
-  vn3 = dz*vnnr / rsq;
+  vnnr = vr1*nx + vr2*ny + vr3*nz; //v_R . n
+  vn1 = nx*vnnr;
+  vn2 = ny*vnnr;
+  vn3 = nz*vnnr;
+
+  delta = radsum - r;
+  dR = delta*Reff;
+  if (normal_model == JKR) {
+    history[0] = 1.0;
+    E *= THREEQUARTERS;
+    R2=Reff*Reff;
+    coh = normal_coeffs[3];
+    dR2 = dR*dR;
+    t0 = coh*coh*R2*R2*E;
+    t1 = PI27SQ*t0;
+    t2 = 8*dR*dR2*E*E*E;
+    t3 = 4*dR2*E;
+    sqrt1 = MAX(0, t0*(t1+2*t2)); // in case sqrt(0) < 0 due to precision issues
+    t4 = cbrt(t1+t2+THREEROOT3*M_PI*sqrt(sqrt1));
+    t5 = t3/t4 + t4/E;
+    sqrt2 = MAX(0, 2*dR + t5);
+    t6 = sqrt(sqrt2);
+    sqrt3 = MAX(0, 4*dR - t5 + SIXROOT6*coh*M_PI*R2/(E*t6));
+    a = INVROOT6*(t6 + sqrt(sqrt3));
+    a2 = a*a;
+    knfac = normal_coeffs[0]*a;
+    Fne = knfac*a2/Reff - TWOPI*a2*sqrt(4*coh*E/(M_PI*a));
+  }
+  else{
+    knfac = E; //Hooke
+    a = sqrt(dR);
+    if (normal_model != HOOKE) {
+      Fne *= a;
+      knfac *= a;
+    }
+    Fne = knfac*delta;
+    if (normal_model == DMT)
+      Fne -= 4*MY_PI*normal_coeffs[3]*Reff;
+  }
+
+  if (damping_model == VELOCITY) {
+    damp_normal = 1;
+  }
+  else if (damping_model == VISCOELASTIC) {
+    damp_normal = a*meff;
+  }
+  else if (damping_model == TSUJI) {
+    damp_normal = sqrt(meff*knfac);
+  }
+
+  damp_normal_prefactor = normal_coeffs[1]*damp_normal;
+  Fdamp = -damp_normal_prefactor*vnnr;
+
+  Fntot = Fne + Fdamp;
+
+  //****************************************
+  // tangential force, including history effects
+  //****************************************
 
   // tangential component
-
   vt1 = vr1 - vn1;
   vt2 = vr2 - vn2;
   vt3 = vr3 - vn3;
 
   // relative rotational velocity
-
   wr1 = radius*omega[0] * rinv;
   wr2 = radius*omega[1] * rinv;
   wr3 = radius*omega[2] * rinv;
 
-  // normal forces = Hertzian contact + normal velocity damping
-  // material properties: currently assumes identical materials
-
-  pois = E/(2.0*G) - 1.0;
-  E_eff=0.5*E/(1.0-pois*pois);
-  G_eff=G/(4.0-2.0*pois);
-
-  // rwall = 0 is infinite wall radius of curvature (flat wall)
-
-  if (rwall == 0) rad_eff = radius;
-  else rad_eff = radius*rwall/(radius+rwall);
-
-  Fcrit = rad_eff * (3.0 * M_PI * SurfEnergy);
-  a0=pow(9.0*M_PI*SurfEnergy*rad_eff*rad_eff/E_eff,1.0/3.0);
-  delcrit = 1.0/rad_eff*(0.5 * a0*a0/pow(6.0,1.0/3.0));
-  delcritinv = 1.0/delcrit;
-
-  overlap = (radius-r) * delcritinv;
-  olapsq = overlap*overlap;
-  olapcubed = olapsq*overlap;
-  sqrtterm = sqrt(1.0 + olapcubed);
-  tmp = 2.0 + olapcubed + 2.0*sqrtterm;
-  keyterm = pow(tmp,THIRD);
-  keyterm2 = olapsq/keyterm;
-  keyterm3 = sqrt(overlap + keyterm2 + keyterm);
-  aovera0 = pow(6.0,-TWOTHIRDS) * (keyterm3 +
-            sqrt(2.0*overlap - keyterm2 - keyterm + 4.0/keyterm3));
-  foverFc = 4.0*((aovera0*aovera0*aovera0) - pow(aovera0,1.5));
-  ccel = Fcrit*foverFc*rinv;
-
-  // damp = meff*gamman*vnnr*rsqinv;
-  // ccel = kn*(radius-r)*rinv - damp;
-  // polyhertz = sqrt((radius-r)*radius);
-  // ccel *= polyhertz;
-
-  // use Tsuji et al form
-
-  polyhertz = 1.2728- 4.2783*0.9 + 11.087*0.9*0.9 - 22.348*0.9*0.9*0.9 +
-    27.467*0.9*0.9*0.9*0.9 - 18.022*0.9*0.9*0.9*0.9*0.9 +
-    4.8218*0.9*0.9*0.9*0.9*0.9*0.9;
-
-  gammatsuji = 0.2*sqrt(meff*kn);
-  damp = gammatsuji*vnnr/rsq;
-  ccel = ccel - polyhertz * damp;
-
-  // relative velocities
-
-  vtr1 = vt1 - (dz*wr2-dy*wr3);
-  vtr2 = vt2 - (dx*wr3-dz*wr1);
-  vtr3 = vt3 - (dy*wr1-dx*wr2);
+  // relative tangential velocities
+  vtr1 = vt1 - (nz*wr2-ny*wr3);
+  vtr2 = vt2 - (nx*wr3-nz*wr1);
+  vtr3 = vt3 - (ny*wr1-nx*wr2);
   vrel = vtr1*vtr1 + vtr2*vtr2 + vtr3*vtr3;
   vrel = sqrt(vrel);
 
-  // shear history effects
-
-  if (shearupdate) {
-    shear[0] += vtr1*dt;
-    shear[1] += vtr2*dt;
-    shear[2] += vtr3*dt;
+  if (normal_model == JKR) {
+    F_pulloff = 3*M_PI*coh*Reff;
+    Fncrit = fabs(Fne + 2*F_pulloff);
   }
-  shrmag = sqrt(shear[0]*shear[0] + shear[1]*shear[1] + shear[2]*shear[2]);
-
-  // rotate shear displacements
-
-  rsht = shear[0]*dx + shear[1]*dy + shear[2]*dz;
-  rsht = rsht*rsqinv;
-  if (shearupdate) {
-    shear[0] -= rsht*dx;
-    shear[1] -= rsht*dy;
-    shear[2] -= rsht*dz;
+  else if (normal_model == DMT) {
+    F_pulloff = 4*M_PI*coh*Reff;
+    Fncrit = fabs(Fne + 2*F_pulloff);
+  }
+  else{
+    Fncrit = fabs(Fntot);
   }
 
-  // tangential forces = shear + tangential velocity damping
+  //------------------------------
+  // tangential forces
+  //------------------------------
 
-  fs1 = -polyhertz * (kt*shear[0] + meff*gammat*vtr1);
-  fs2 = -polyhertz * (kt*shear[1] + meff*gammat*vtr2);
-  fs3 = -polyhertz * (kt*shear[2] + meff*gammat*vtr3);
+  k_tangential = tangential_coeffs[0];
+  damp_tangential = tangential_coeffs[1]*damp_normal_prefactor;
 
-  kt=8.0*G_eff*a0*aovera0;
+  int thist0 = tangential_history_index;
+  int thist1 = thist0 + 1;
+  int thist2 = thist1 + 1;
 
-  // shear damping uses Tsuji et al form also
+  if (tangential_history) {
+    if (tangential_model == TANGENTIAL_MINDLIN) {
+      k_tangential *= a;
+    }
+    else if (tangential_model == TANGENTIAL_MINDLIN_RESCALE) {
+      k_tangential *= a;
+      if (a < history[3]) { //On unloading, rescale the shear displacements
+        double factor = a/history[thist2+1];
+        history[thist0] *= factor;
+        history[thist1] *= factor;
+        history[thist2] *= factor;
+      }
+    }
+    shrmag = sqrt(history[thist0]*history[thist0] +
+                  history[thist1]*history[thist1] +
+                  history[thist2]*history[thist2]);
 
-  fs1 = -kt*shear[0] - polyhertz*gammatsuji*vtr1;
-  fs2 = -kt*shear[1] - polyhertz*gammatsuji*vtr2;
-  fs3 = -kt*shear[2] - polyhertz*gammatsuji*vtr3;
+    // rotate and update displacements.
+    // see e.g. eq. 17 of Luding, Gran. Matter 2008, v10,p235
+    if (history_update) {
+      rsht = history[thist0]*nx + history[thist1]*ny + history[thist2]*nz;
+      if (fabs(rsht) < EPSILON) rsht = 0;
+      if (rsht > 0) {
+        // if rhst == shrmag, contacting pair has rotated 90 deg in one step,
+        // in which case you deserve a crash!
+        scalefac = shrmag/(shrmag - rsht);
+        history[thist0] -= rsht*nx;
+        history[thist1] -= rsht*ny;
+        history[thist2] -= rsht*nz;
+        // also rescale to preserve magnitude
+        history[thist0] *= scalefac;
+        history[thist1] *= scalefac;
+        history[thist2] *= scalefac;
+      }
+      // update history
+      history[thist0] += vtr1*dt;
+      history[thist1] += vtr2*dt;
+      history[thist2] += vtr3*dt;
+    }
 
-  // rescale frictional displacements and forces if needed
+    // tangential forces = history + tangential velocity damping
+    fs1 = -k_tangential*history[thist0] - damp_tangential*vtr1;
+    fs2 = -k_tangential*history[thist1] - damp_tangential*vtr2;
+    fs3 = -k_tangential*history[thist2] - damp_tangential*vtr3;
 
-  fs = sqrt(fs1*fs1 + fs2*fs2 + fs3*fs3);
-  fn = xmu * fabs(ccel*r + 2.0*Fcrit);
-
-  if (fs > fn) {
-    if (shrmag != 0.0) {
-      shear[0] = (fn/fs) * (shear[0] + polyhertz*gammatsuji*vtr1/kt) -
-      polyhertz*gammatsuji*vtr1/kt;
-      shear[1] = (fn/fs) * (shear[1] + polyhertz*gammatsuji*vtr2/kt) -
-      polyhertz*gammatsuji*vtr2/kt;
-      shear[2] = (fn/fs) * (shear[2] + polyhertz*gammatsuji*vtr3/kt) -
-      polyhertz*gammatsuji*vtr3/kt;
-      fs1 *= fn/fs ;
-      fs2 *= fn/fs;
-      fs3 *= fn/fs;
-    } else fs1 = fs2 = fs3 = 0.0;
+    // rescale frictional displacements and forces if needed
+    Fscrit = tangential_coeffs[2] * Fncrit;
+    fs = sqrt(fs1*fs1 + fs2*fs2 + fs3*fs3);
+    if (fs > Fscrit) {
+      if (shrmag != 0.0) {
+        history[thist0] = -1.0/k_tangential*(Fscrit*fs1/fs +
+                                             damp_tangential*vtr1);
+        history[thist1] = -1.0/k_tangential*(Fscrit*fs2/fs +
+                                             damp_tangential*vtr2);
+        history[thist2] = -1.0/k_tangential*(Fscrit*fs3/fs +
+                                             damp_tangential*vtr3);
+        fs1 *= Fscrit/fs;
+        fs2 *= Fscrit/fs;
+        fs3 *= Fscrit/fs;
+      } else fs1 = fs2 = fs3 = 0.0;
+    }
+  } else { // classic pair gran/hooke (no history)
+    fs = meff*damp_tangential*vrel;
+    if (vrel != 0.0) Ft = MIN(Fne,fs) / vrel;
+    else Ft = 0.0;
+    fs1 = -Ft*vtr1;
+    fs2 = -Ft*vtr2;
+    fs3 = -Ft*vtr3;
   }
 
-  // calculate twisting and rolling components of torque
-  // NOTE: this assumes spheres!
+  //****************************************
+  // rolling resistance
+  //****************************************
 
-  relrot1 = omega[0];
-  relrot2 = omega[1];
-  relrot3 = omega[2];
+  if (roll_model != ROLL_NONE) {
+    relrot1 = omega[0];
+    relrot2 = omega[1];
+    relrot3 = omega[2];
 
-  // rolling velocity
-  // NOTE: this assumes mondisperse spheres!
+    // rolling velocity, see eq. 31 of Wang et al, Particuology v 23, p 49 (2015)
+    // This is different from the Marshall papers,
+    // which use the Bagi/Kuhn formulation
+    // for rolling velocity (see Wang et al for why the latter is wrong)
+    vrl1 = Reff*(relrot2*nz - relrot3*ny); //- 0.5*((radj-radi)/radsum)*vtr1;
+    vrl2 = Reff*(relrot3*nx - relrot1*nz); //- 0.5*((radj-radi)/radsum)*vtr2;
+    vrl3 = Reff*(relrot1*ny - relrot2*nx); //- 0.5*((radj-radi)/radsum)*vtr3;
 
-  vrl1 = -rad_eff*rinv * (relrot2*dz - relrot3*dy);
-  vrl2 = -rad_eff*rinv * (relrot3*dx - relrot1*dz);
-  vrl3 = -rad_eff*rinv * (relrot1*dy - relrot2*dx);
-  vrlmag = sqrt(vrl1*vrl1+vrl2*vrl2+vrl3*vrl3);
-  if (vrlmag != 0.0) vrlmaginv = 1.0/vrlmag;
-  else vrlmaginv = 0.0;
+    int rhist0 = roll_history_index;
+    int rhist1 = rhist0 + 1;
+    int rhist2 = rhist1 + 1;
 
-  // bond history effects
+    // rolling displacement
+    rollmag = sqrt(history[rhist0]*history[rhist0] +
+                   history[rhist1]*history[rhist1] +
+                   history[rhist2]*history[rhist2]);
 
-  shear[3] += vrl1*dt;
-  shear[4] += vrl2*dt;
-  shear[5] += vrl3*dt;
+    rolldotn = history[rhist0]*nx + history[rhist1]*ny + history[rhist2]*nz;
 
-  // rotate bonded displacements correctly
+    if (history_update) {
+      if (fabs(rolldotn) < EPSILON) rolldotn = 0;
+      if (rolldotn > 0) { // rotate into tangential plane
+        scalefac = rollmag/(rollmag - rolldotn);
+        history[rhist0] -= rolldotn*nx;
+        history[rhist1] -= rolldotn*ny;
+        history[rhist2] -= rolldotn*nz;
+        // also rescale to preserve magnitude
+        history[rhist0] *= scalefac;
+        history[rhist1] *= scalefac;
+        history[rhist2] *= scalefac;
+      }
+      history[rhist0] += vrl1*dt;
+      history[rhist1] += vrl2*dt;
+      history[rhist2] += vrl3*dt;
+    }
 
-  double rlt = shear[3]*dx + shear[4]*dy + shear[5]*dz;
-  rlt /= rsq;
-  shear[3] -= rlt*dx;
-  shear[4] -= rlt*dy;
-  shear[5] -= rlt*dz;
+    k_roll = roll_coeffs[0];
+    damp_roll = roll_coeffs[1];
+    fr1 = -k_roll*history[rhist0] - damp_roll*vrl1;
+    fr2 = -k_roll*history[rhist1] - damp_roll*vrl2;
+    fr3 = -k_roll*history[rhist2] - damp_roll*vrl3;
 
-  // twisting torque
+    // rescale frictional displacements and forces if needed
+    Frcrit = roll_coeffs[2] * Fncrit;
 
-  magtwist = rinv*(relrot1*dx + relrot2*dy + relrot3*dz);
-  shear[6] += magtwist*dt;
+    fr = sqrt(fr1*fr1 + fr2*fr2 + fr3*fr3);
+    if (fr > Frcrit) {
+      if (rollmag != 0.0) {
+        history[rhist0] = -1.0/k_roll*(Frcrit*fr1/fr + damp_roll*vrl1);
+        history[rhist1] = -1.0/k_roll*(Frcrit*fr2/fr + damp_roll*vrl2);
+        history[rhist2] = -1.0/k_roll*(Frcrit*fr3/fr + damp_roll*vrl3);
+        fr1 *= Frcrit/fr;
+        fr2 *= Frcrit/fr;
+        fr3 *= Frcrit/fr;
+      } else fr1 = fr2 = fr3 = 0.0;
+    }
+  }
 
-  ktwist = 0.5*kt*(a0*aovera0)*(a0*aovera0);
-  magtortwist = -ktwist*shear[6] -
-    0.5*polyhertz*gammatsuji*(a0*aovera0)*(a0*aovera0)*magtwist;
+  //****************************************
+  // twisting torque, including history effects
+  //****************************************
 
-  twistcrit=TWOTHIRDS*a0*aovera0*Fcrit;
-  if (fabs(magtortwist) > twistcrit)
-    magtortwist = -twistcrit * magtwist/fabs(magtwist);
+  if (twist_model != TWIST_NONE) {
+    magtwist = relrot1*nx + relrot2*ny + relrot3*nz; //Omega_T (eq 29 of Marshall)
+    if (twist_model == TWIST_MARSHALL) {
+      k_twist = 0.5*k_tangential*a*a;; // eq 32 of Marshall paper
+      damp_twist = 0.5*damp_tangential*a*a;
+      mu_twist = TWOTHIRDS*a*tangential_coeffs[2];
+    }
+    else{
+      k_twist = twist_coeffs[0];
+      damp_twist = twist_coeffs[1];
+      mu_twist = twist_coeffs[2];
+    }
+    if (history_update) {
+      history[twist_history_index] += magtwist*dt;
+    }
+    // M_t torque (eq 30)
+    magtortwist = -k_twist*history[twist_history_index] - damp_twist*magtwist;
+    signtwist = (magtwist > 0) - (magtwist < 0);
+    Mtcrit = mu_twist*Fncrit; // critical torque (eq 44)
+    if (fabs(magtortwist) > Mtcrit) {
+      history[twist_history_index] = 1.0/k_twist*(Mtcrit*signtwist -
+                                                  damp_twist*magtwist);
+      magtortwist = -Mtcrit * signtwist; // eq 34
+    }
+  }
 
-  // rolling torque
+  // apply forces & torques
 
-  magrollsq = shear[3]*shear[3] + shear[4]*shear[4] + shear[5]*shear[5];
-  magroll = sqrt(magrollsq);
-  if (magroll != 0.0) magrollinv = 1.0/magroll;
-  else magrollinv = 0.0;
+  fx = nx*Fntot + fs1;
+  fy = ny*Fntot + fs2;
+  fz = nz*Fntot + fs3;
 
-  kroll = 1.0*4.0*Fcrit*pow(aovera0,1.5);
-  magtorroll = -kroll*magroll - 0.1*gammat*vrlmag;
-
-  rollcrit = 0.01;
-  if (magroll > rollcrit) magtorroll = -kroll*rollcrit;
-
-  // forces & torques
-
-  fx = dx*ccel + fs1;
-  fy = dy*ccel + fs2;
-  fz = dz*ccel + fs3;
+  if (peratom_flag) {
+    contact[1] = fx;
+    contact[2] = fy;
+    contact[3] = fz;
+  }
 
   f[0] += fx;
   f[1] += fy;
   f[2] += fz;
 
-  tor1 = rinv * (dy*fs3 - dz*fs2);
-  tor2 = rinv * (dz*fs1 - dx*fs3);
-  tor3 = rinv * (dx*fs2 - dy*fs1);
+  tor1 = ny*fs3 - nz*fs2;
+  tor2 = nz*fs1 - nx*fs3;
+  tor3 = nx*fs2 - ny*fs1;
+
   torque[0] -= radius*tor1;
   torque[1] -= radius*tor2;
   torque[2] -= radius*tor3;
 
-  torque[0] += magtortwist * dx*rinv;
-  torque[1] += magtortwist * dy*rinv;
-  torque[2] += magtortwist * dz*rinv;
+  if (twist_model != TWIST_NONE) {
+    tortwist1 = magtortwist * nx;
+    tortwist2 = magtortwist * ny;
+    tortwist3 = magtortwist * nz;
 
-  torque[0] += magtorroll * (shear[4]*dz - shear[5]*dy)*rinv*magrollinv;
-  torque[1] += magtorroll * (shear[5]*dx - shear[3]*dz)*rinv*magrollinv;
-  torque[2] += magtorroll * (shear[3]*dy - shear[4]*dx)*rinv*magrollinv;
+    torque[0] += tortwist1;
+    torque[1] += tortwist2;
+    torque[2] += tortwist3;
+  }
+
+  if (roll_model != ROLL_NONE) {
+    torroll1 = Reff*(ny*fr3 - nz*fr2); //n cross fr
+    torroll2 = Reff*(nz*fr1 - nx*fr3);
+    torroll3 = Reff*(nx*fr2 - ny*fr1);
+
+    torque[0] += torroll1;
+    torque[1] += torroll2;
+    torque[2] += torroll3;
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -1023,8 +1436,10 @@ double FixWallGran::memory_usage()
 {
   int nmax = atom->nmax;
   double bytes = 0.0;
-  if (history) bytes += nmax*sheardim * sizeof(double);   // shear history
-  if (fix_rigid) bytes += nmax * sizeof(int);             // mass_rigid
+  if (use_history) bytes += nmax*size_history * sizeof(double);  // shear history
+  if (fix_rigid) bytes += nmax * sizeof(int);                    // mass_rigid
+  // store contacts
+  if (peratom_flag) bytes += nmax*size_peratom_cols*sizeof(double);
   return bytes;
 }
 
@@ -1034,7 +1449,11 @@ double FixWallGran::memory_usage()
 
 void FixWallGran::grow_arrays(int nmax)
 {
-  if (history) memory->grow(shearone,nmax,sheardim,"fix_wall_gran:shearone");
+  if (use_history) memory->grow(history_one,nmax,size_history,
+                                "fix_wall_gran:history_one");
+  if (peratom_flag) {
+    memory->grow(array_atom,nmax,size_peratom_cols,"fix_wall_gran:array_atom");
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -1043,9 +1462,13 @@ void FixWallGran::grow_arrays(int nmax)
 
 void FixWallGran::copy_arrays(int i, int j, int /*delflag*/)
 {
-  if (history)
-    for (int m = 0; m < sheardim; m++)
-      shearone[j][m] = shearone[i][m];
+  if (use_history)
+    for (int m = 0; m < size_history; m++)
+      history_one[j][m] = history_one[i][m];
+  if (peratom_flag) {
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[j][m] = array_atom[i][m];
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -1054,9 +1477,13 @@ void FixWallGran::copy_arrays(int i, int j, int /*delflag*/)
 
 void FixWallGran::set_arrays(int i)
 {
-  if (history)
-    for (int m = 0; m < sheardim; m++)
-      shearone[i][m] = 0;
+  if (use_history)
+    for (int m = 0; m < size_history; m++)
+      history_one[i][m] = 0;
+  if (peratom_flag) {
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[i][m] = 0;
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -1065,11 +1492,15 @@ void FixWallGran::set_arrays(int i)
 
 int FixWallGran::pack_exchange(int i, double *buf)
 {
-  if (!history) return 0;
-
   int n = 0;
-  for (int m = 0; m < sheardim; m++)
-    buf[n++] = shearone[i][m];
+  if (use_history) {
+    for (int m = 0; m < size_history; m++)
+      buf[n++] = history_one[i][m];
+  }
+  if (peratom_flag) {
+    for (int m = 0; m < size_peratom_cols; m++)
+      buf[n++] = array_atom[i][m];
+  }
   return n;
 }
 
@@ -1079,11 +1510,15 @@ int FixWallGran::pack_exchange(int i, double *buf)
 
 int FixWallGran::unpack_exchange(int nlocal, double *buf)
 {
-  if (!history) return 0;
-
   int n = 0;
-  for (int m = 0; m < sheardim; m++)
-    shearone[nlocal][m] = buf[n++];
+  if (use_history) {
+    for (int m = 0; m < size_history; m++)
+      history_one[nlocal][m] = buf[n++];
+  }
+  if (peratom_flag) {
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[nlocal][m] = buf[n++];
+  }
   return n;
 }
 
@@ -1093,12 +1528,12 @@ int FixWallGran::unpack_exchange(int nlocal, double *buf)
 
 int FixWallGran::pack_restart(int i, double *buf)
 {
-  if (!history) return 0;
+  if (!use_history) return 0;
 
   int n = 0;
-  buf[n++] = sheardim + 1;
-  for (int m = 0; m < sheardim; m++)
-    buf[n++] = shearone[i][m];
+  buf[n++] = size_history + 1;
+  for (int m = 0; m < size_history; m++)
+    buf[n++] = history_one[i][m];
   return n;
 }
 
@@ -1108,7 +1543,7 @@ int FixWallGran::pack_restart(int i, double *buf)
 
 void FixWallGran::unpack_restart(int nlocal, int nth)
 {
-  if (!history) return;
+  if (!use_history) return;
 
   double **extra = atom->extra;
 
@@ -1118,8 +1553,8 @@ void FixWallGran::unpack_restart(int nlocal, int nth)
   for (int i = 0; i < nth; i++) m += static_cast<int> (extra[nlocal][m]);
   m++;
 
-  for (int i = 0; i < sheardim; i++)
-    shearone[nlocal][i] = extra[nlocal][m++];
+  for (int i = 0; i < size_history; i++)
+    history_one[nlocal][i] = extra[nlocal][m++];
 }
 
 /* ----------------------------------------------------------------------
@@ -1128,8 +1563,8 @@ void FixWallGran::unpack_restart(int nlocal, int nth)
 
 int FixWallGran::maxsize_restart()
 {
-  if (!history) return 0;
-  return 1 + sheardim;
+  if (!use_history) return 0;
+  return 1 + size_history;
 }
 
 /* ----------------------------------------------------------------------
@@ -1138,8 +1573,8 @@ int FixWallGran::maxsize_restart()
 
 int FixWallGran::size_restart(int /*nlocal*/)
 {
-  if (!history) return 0;
-  return 1 + sheardim;
+  if (!use_history) return 0;
+  return 1 + size_history;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -1148,3 +1583,14 @@ void FixWallGran::reset_dt()
 {
   dt = update->dt;
 }
+
+double FixWallGran::pulloff_distance(double radius)
+{
+  double coh, E, a, dist;
+  coh = normal_coeffs[3];
+  E = normal_coeffs[0]*THREEQUARTERS;
+  a = cbrt(9*M_PI*coh*radius/(4*E));
+  dist = a*a/radius - 2*sqrt(M_PI*coh*a/E);
+  return dist;
+}
+
diff --git a/src/GRANULAR/fix_wall_gran.h b/src/GRANULAR/fix_wall_gran.h
index 2403a31907..f147e29433 100644
--- a/src/GRANULAR/fix_wall_gran.h
+++ b/src/GRANULAR/fix_wall_gran.h
@@ -46,42 +46,70 @@ class FixWallGran : public Fix {
   virtual int maxsize_restart();
   void reset_dt();
 
-  void hooke(double, double, double, double, double *,
-             double *, double *, double *, double *, double, double);
+  void hooke(double, double, double, double, double *, double *,
+             double *, double *, double *, double, double, double*);
   void hooke_history(double, double, double, double, double *,
-                     double *, double *, double *, double *, double, double,
-                     double *);
-  void hertz_history(double, double, double, double, double *, double,
-                     double *, double *, double *, double *, double, double,
-                     double *);
-  void bonded_history(double, double, double, double, double *, double,
-                       double *, double *, double *, double *, double, double,
-                       double *);
+                     double *, double *, double *, double *, double,
+                     double, double *, double *);
+  void hertz_history(double, double, double, double, double *,
+                     double, double *, double *, double *, double *,
+                     double, double, double *, double *);
+  void granular(double, double, double, double, double *, double,
+                double *, double *, double *, double *, double,
+                double, double *, double *);
+
+  double pulloff_distance(double);
 
  protected:
   int wallstyle,wiggle,wshear,axis;
   int pairstyle,nlevels_respa;
   bigint time_origin;
   double kn,kt,gamman,gammat,xmu;
-  double E,G,SurfEnergy;
+
+  // for granular model choices
+  int normal_model, damping_model;
+  int tangential_model, roll_model, twist_model;
+
+  // history flags
+  int normal_history, tangential_history, roll_history, twist_history;
+
+  // indices of history entries
+  int normal_history_index;
+  int tangential_history_index;
+  int roll_history_index;
+  int twist_history_index;
+
+  // material coefficients
+  double Emod, poiss, Gmod;
+
+  // contact model coefficients
+  double normal_coeffs[4];
+  double tangential_coeffs[3];
+  double roll_coeffs[3];
+  double twist_coeffs[3];
+
   double lo,hi,cylradius;
   double amplitude,period,omega,vshear;
   double dt;
   char *idregion;
 
-  int history;       // if particle/wall interaction stores history
-  int shearupdate;   // flag for whether shear history is updated
-  int sheardim;      // # of shear history values per contact
+  int use_history;       // if particle/wall interaction stores history
+  int history_update;    // flag for whether shear history is updated
+  int size_history;      // # of shear history values per contact
 
   // shear history for single contact per particle
 
-  double **shearone;
+  double **history_one;
 
   // rigid body masses for use in granular interactions
 
   class Fix *fix_rigid;    // ptr to rigid body fix, NULL if none
   double *mass_rigid;      // rigid mass for owned+ghost atoms
   int nmax;                // allocated size of mass_rigid
+
+  // store particle interactions
+
+  int store;
 };
 
 }
diff --git a/src/GRANULAR/fix_wall_gran_region.cpp b/src/GRANULAR/fix_wall_gran_region.cpp
index 8633587ad5..7702967504 100644
--- a/src/GRANULAR/fix_wall_gran_region.cpp
+++ b/src/GRANULAR/fix_wall_gran_region.cpp
@@ -39,15 +39,17 @@ using namespace MathConst;
 
 // same as FixWallGran
 
-enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY,BONDED_HISTORY};
+enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY,GRANULAR};
+enum {NORMAL_HOOKE, NORMAL_HERTZ, HERTZ_MATERIAL, DMT, JKR};
 
 #define BIG 1.0e20
 
 /* ---------------------------------------------------------------------- */
 
 FixWallGranRegion::FixWallGranRegion(LAMMPS *lmp, int narg, char **arg) :
-  FixWallGran(lmp, narg, arg), region(NULL), region_style(NULL), ncontact(NULL),
-  walls(NULL), shearmany(NULL), c2r(NULL)
+  FixWallGran(lmp, narg, arg), region(NULL), region_style(NULL),
+  ncontact(NULL),
+  walls(NULL), history_many(NULL), c2r(NULL)
 {
   restart_global = 1;
   motion_resetflag = 0;
@@ -66,17 +68,17 @@ FixWallGranRegion::FixWallGranRegion(LAMMPS *lmp, int narg, char **arg) :
   // re-allocate atom-based arrays with nshear
   // do not register with Atom class, since parent class did that
 
-  memory->destroy(shearone);
-  shearone = NULL;
+  memory->destroy(history_one);
+  history_one = NULL;
 
   ncontact = NULL;
   walls = NULL;
-  shearmany = NULL;
+  history_many = NULL;
   grow_arrays(atom->nmax);
 
   // initialize shear history as if particle is not touching region
 
-  if (history) {
+  if (use_history) {
     int nlocal = atom->nlocal;
     for (int i = 0; i < nlocal; i++)
       ncontact[i] = 0;
@@ -92,7 +94,7 @@ FixWallGranRegion::~FixWallGranRegion()
 
   memory->destroy(ncontact);
   memory->destroy(walls);
-  memory->destroy(shearmany);
+  memory->destroy(history_many);
 }
 
 /* ---------------------------------------------------------------------- */
@@ -138,8 +140,8 @@ void FixWallGranRegion::post_force(int /*vflag*/)
 
   // do not update shear history during setup
 
-  shearupdate = 1;
-  if (update->setupflag) shearupdate = 0;
+  history_update = 1;
+  if (update->setupflag) history_update = 0;
 
   // if just reneighbored:
   // update rigid body masses for owned atoms if using FixRigid
@@ -188,7 +190,13 @@ void FixWallGranRegion::post_force(int /*vflag*/)
     if (mask[i] & groupbit) {
       if (!region->match(x[i][0],x[i][1],x[i][2])) continue;
 
-      nc = region->surface(x[i][0],x[i][1],x[i][2],radius[i]);
+      if (pairstyle == GRANULAR && normal_model == JKR){
+        nc = region->surface(x[i][0],x[i][1],x[i][2],
+                             radius[i]+pulloff_distance(radius[i]));
+      }
+      else{
+        nc = region->surface(x[i][0],x[i][1],x[i][2],radius[i]);
+      }
       if (nc > tmax)
         error->one(FLERR,"Too many wall/gran/region contacts for one particle");
 
@@ -198,7 +206,7 @@ void FixWallGranRegion::post_force(int /*vflag*/)
       // also set c2r[] = indices into region->contact[] for each of N contacts
       // process zero or one contact here, otherwise invoke update_contacts()
 
-      if (history) {
+      if (use_history) {
         if (nc == 0) {
           ncontact[i] = 0;
           continue;
@@ -209,15 +217,14 @@ void FixWallGranRegion::post_force(int /*vflag*/)
           if (ncontact[i] == 0) {
             ncontact[i] = 1;
             walls[i][0] = iwall;
-            for (m = 0; m < sheardim; m++)
-              shearmany[i][0][m] = 0.0;
+            for (m = 0; m < size_history; m++)
+              history_many[i][0][m] = 0.0;
           } else if (ncontact[i] > 1 || iwall != walls[i][0])
             update_contacts(i,nc);
         } else update_contacts(i,nc);
       }
 
       // process current contacts
-
       for (int ic = 0; ic < nc; ic++) {
 
         // rsq = squared contact distance
@@ -225,36 +232,57 @@ void FixWallGranRegion::post_force(int /*vflag*/)
 
         rsq = region->contact[ic].r*region->contact[ic].r;
 
+        if (pairstyle == GRANULAR && normal_model == JKR){
+          if (history_many[i][c2r[ic]][0] == 0.0 && rsq > radius[i]*radius[i]){
+            for (m = 0; m < size_history; m++)
+              history_many[i][0][m] = 0.0;
+            continue;
+          }
+        }
+
         dx = region->contact[ic].delx;
         dy = region->contact[ic].dely;
         dz = region->contact[ic].delz;
 
         if (regiondynamic) region->velocity_contact(vwall, x[i], ic);
 
-
         // meff = effective mass of sphere
         // if I is part of rigid body, use body mass
 
         meff = rmass[i];
         if (fix_rigid && mass_rigid[i] > 0.0) meff = mass_rigid[i];
 
+        // store contact info
+        if (peratom_flag){
+          array_atom[i][0] = (double)atom->tag[i];
+          array_atom[i][4] = x[i][0] - dx;
+          array_atom[i][5] = x[i][1] - dy;
+          array_atom[i][6] = x[i][2] - dz;
+          array_atom[i][7] = radius[i];
+        }
+
         // invoke sphere/wall interaction
+        double *contact;
+        if (peratom_flag)
+          contact = array_atom[i];
+        else
+          contact = NULL;
 
         if (pairstyle == HOOKE)
           hooke(rsq,dx,dy,dz,vwall,v[i],f[i],
-                omega[i],torque[i],radius[i],meff);
+              omega[i],torque[i],radius[i],meff, contact);
         else if (pairstyle == HOOKE_HISTORY)
           hooke_history(rsq,dx,dy,dz,vwall,v[i],f[i],
-                        omega[i],torque[i],radius[i],meff,
-                        shearmany[i][c2r[ic]]);
+              omega[i],torque[i],radius[i],meff,
+              history_many[i][c2r[ic]], contact);
         else if (pairstyle == HERTZ_HISTORY)
           hertz_history(rsq,dx,dy,dz,vwall,region->contact[ic].radius,
-                        v[i],f[i],omega[i],torque[i],
-                        radius[i],meff,shearmany[i][c2r[ic]]);
-        else if (pairstyle == BONDED_HISTORY)
-          bonded_history(rsq,dx,dy,dz,vwall,region->contact[ic].radius,
-                         v[i],f[i],omega[i],torque[i],
-                         radius[i],meff,shearmany[i][c2r[ic]]);
+              v[i],f[i],omega[i],torque[i],
+              radius[i],meff,history_many[i][c2r[ic]], contact);
+        else if (pairstyle == GRANULAR)
+          granular(rsq,dx,dy,dz,vwall,region->contact[ic].radius,
+                   v[i],f[i],omega[i],torque[i],
+                   radius[i],meff,history_many[i][c2r[ic]],contact);
       }
     }
   }
@@ -282,8 +310,8 @@ void FixWallGranRegion::update_contacts(int i, int nc)
       if (region->contact[m].iwall == walls[i][iold]) break;
     if (m >= nc) {
       ilast = ncontact[i]-1;
-      for (j = 0; j < sheardim; j++)
-        shearmany[i][iold][j] = shearmany[i][ilast][j];
+      for (j = 0; j < size_history; j++)
+        history_many[i][iold][j] = history_many[i][ilast][j];
       walls[i][iold] = walls[i][ilast];
       ncontact[i]--;
     } else iold++;
@@ -305,8 +333,8 @@ void FixWallGranRegion::update_contacts(int i, int nc)
       iadd = ncontact[i];
 
       c2r[iadd] = inew;
-      for (j = 0; j < sheardim; j++)
-        shearmany[i][iadd][j] = 0.0;
+      for (j = 0; j < size_history; j++)
+        history_many[i][iadd][j] = 0.0;
       walls[i][iadd] = iwall;
       ncontact[i]++;
     }
@@ -321,10 +349,10 @@ double FixWallGranRegion::memory_usage()
 {
   int nmax = atom->nmax;
   double bytes = 0.0;
-  if (history) {                                   // shear history
+  if (use_history) {                                   // shear history
     bytes += nmax * sizeof(int);                   // ncontact
     bytes += nmax*tmax * sizeof(int);              // walls
-    bytes += nmax*tmax*sheardim * sizeof(double);  // shearmany
+    bytes += nmax*tmax*size_history * sizeof(double);  // history_many
   }
   if (fix_rigid) bytes += nmax * sizeof(int);      // mass_rigid
   return bytes;
@@ -336,11 +364,14 @@ double FixWallGranRegion::memory_usage()
 
 void FixWallGranRegion::grow_arrays(int nmax)
 {
-  if (history) {
+  if (use_history) {
     memory->grow(ncontact,nmax,"fix_wall_gran:ncontact");
     memory->grow(walls,nmax,tmax,"fix_wall_gran:walls");
-    memory->grow(shearmany,nmax,tmax,sheardim,"fix_wall_gran:shearmany");
+    memory->grow(history_many,nmax,tmax,size_history,
+                 "fix_wall_gran:history_many");
   }
+  if (peratom_flag)
+    memory->grow(array_atom,nmax,size_peratom_cols,"fix_wall_gran:array_atom");
 }
 
 /* ----------------------------------------------------------------------
@@ -351,16 +382,20 @@ void FixWallGranRegion::copy_arrays(int i, int j, int /*delflag*/)
 {
   int m,n,iwall;
 
-  if (!history) return;
-
-  n = ncontact[i];
-
-  for (iwall = 0; iwall < n; iwall++) {
-    walls[j][iwall] = walls[i][iwall];
-    for (m = 0; m < sheardim; m++)
-      shearmany[j][iwall][m] = shearmany[i][iwall][m];
+  if (use_history){
+    n = ncontact[i];
+    for (iwall = 0; iwall < n; iwall++) {
+      walls[j][iwall] = walls[i][iwall];
+      for (m = 0; m < size_history; m++)
+        history_many[j][iwall][m] = history_many[i][iwall][m];
+    }
+    ncontact[j] = ncontact[i];
+  }
+
+  if (peratom_flag){
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[j][m] = array_atom[i][m];
   }
-  ncontact[j] = ncontact[i];
 }
 
 /* ----------------------------------------------------------------------
@@ -369,8 +404,12 @@ void FixWallGranRegion::copy_arrays(int i, int j, int /*delflag*/)
 
 void FixWallGranRegion::set_arrays(int i)
 {
-  if (!history) return;
-  ncontact[i] = 0;
+  if (use_history)
+    ncontact[i] = 0;
+  if (peratom_flag){
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[i][m] = 0;
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -381,16 +420,19 @@ int FixWallGranRegion::pack_exchange(int i, double *buf)
 {
   int m;
 
-  if (!history) return 0;
-
   int n = 0;
-  int count = ncontact[i];
-
-  buf[n++] = ubuf(count).d;
-  for (int iwall = 0; iwall < count; iwall++) {
-    buf[n++] = ubuf(walls[i][iwall]).d;
-    for (m = 0; m < sheardim; m++)
-      buf[n++] = shearmany[i][iwall][m];
+  if (use_history){
+    int count = ncontact[i];
+    buf[n++] = ubuf(count).d;
+    for (int iwall = 0; iwall < count; iwall++) {
+      buf[n++] = ubuf(walls[i][iwall]).d;
+      for (m = 0; m < size_history; m++)
+        buf[n++] = history_many[i][iwall][m];
+    }
+  }
+  if (peratom_flag){
+    for (int m = 0; m < size_peratom_cols; m++)
+      buf[n++] = array_atom[i][m];
   }
 
   return n;
@@ -404,15 +446,19 @@ int FixWallGranRegion::unpack_exchange(int nlocal, double *buf)
 {
   int m;
 
-  if (!history) return 0;
 
   int n = 0;
-  int count = ncontact[nlocal] = (int) ubuf(buf[n++]).i;
-
-  for (int iwall = 0; iwall < count; iwall++) {
-    walls[nlocal][iwall] = (int) ubuf(buf[n++]).i;
-    for (m = 0; m < sheardim; m++)
-      shearmany[nlocal][iwall][m] = buf[n++];
+  if (use_history){
+    int count = ncontact[nlocal] = (int) ubuf(buf[n++]).i;
+    for (int iwall = 0; iwall < count; iwall++) {
+      walls[nlocal][iwall] = (int) ubuf(buf[n++]).i;
+      for (m = 0; m < size_history; m++)
+        history_many[nlocal][iwall][m] = buf[n++];
+    }
+  }
+  if (peratom_flag){
+    for (int m = 0; m < size_peratom_cols; m++)
+      array_atom[nlocal][m] = buf[n++];
   }
 
   return n;
@@ -426,7 +472,7 @@ int FixWallGranRegion::pack_restart(int i, double *buf)
 {
   int m;
 
-  if (!history) return 0;
+  if (!use_history) return 0;
 
   int n = 1;
   int count = ncontact[i];
@@ -434,8 +480,8 @@ int FixWallGranRegion::pack_restart(int i, double *buf)
   buf[n++] = ubuf(count).d;
   for (int iwall = 0; iwall < count; iwall++) {
     buf[n++] = ubuf(walls[i][iwall]).d;
-    for (m = 0; m < sheardim; m++)
-      buf[n++] = shearmany[i][iwall][m];
+    for (m = 0; m < size_history; m++)
+      buf[n++] = history_many[i][iwall][m];
   }
   buf[0] = n;
   return n;
@@ -449,7 +495,7 @@ void FixWallGranRegion::unpack_restart(int nlocal, int nth)
 {
   int k;
 
-  if (!history) return;
+  if (!use_history) return;
 
   double **extra = atom->extra;
 
@@ -462,8 +508,8 @@ void FixWallGranRegion::unpack_restart(int nlocal, int nth)
   int count = ncontact[nlocal] = (int) ubuf(extra[nlocal][m++]).i;
   for (int iwall = 0; iwall < count; iwall++) {
     walls[nlocal][iwall] = (int) ubuf(extra[nlocal][m++]).i;
-    for (k = 0; k < sheardim; k++)
-      shearmany[nlocal][iwall][k] = extra[nlocal][m++];
+    for (k = 0; k < size_history; k++)
+      history_many[nlocal][iwall][k] = extra[nlocal][m++];
   }
 }
 
@@ -473,8 +519,8 @@ void FixWallGranRegion::unpack_restart(int nlocal, int nth)
 
 int FixWallGranRegion::maxsize_restart()
 {
-  if (!history) return 0;
-  return 2 + tmax*(sheardim+1);
+  if (!use_history) return 0;
+  return 2 + tmax*(size_history+1);
 }
 
 /* ----------------------------------------------------------------------
@@ -483,8 +529,8 @@ int FixWallGranRegion::maxsize_restart()
 
 int FixWallGranRegion::size_restart(int nlocal)
 {
-  if (!history) return 0;
-  return 2 + ncontact[nlocal]*(sheardim+1);
+  if (!use_history) return 0;
+  return 2 + ncontact[nlocal]*(size_history+1);
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/GRANULAR/fix_wall_gran_region.h b/src/GRANULAR/fix_wall_gran_region.h
index 8d1b6d533a..fd40e27e4c 100644
--- a/src/GRANULAR/fix_wall_gran_region.h
+++ b/src/GRANULAR/fix_wall_gran_region.h
@@ -54,7 +54,7 @@ class FixWallGranRegion : public FixWallGran {
   int tmax;              // max # of region walls one particle can touch
   int *ncontact;         // # of shear contacts per particle
   int **walls;           // which wall each contact is with
-  double ***shearmany;   // shear history per particle per contact
+  double ***history_many;   // history per particle per contact
   int *c2r;              // contact to region mapping
                          // c2r[i] = index of Ith contact in
                          //   region-contact[] list of contacts
diff --git a/src/GRANULAR/pair_gran_hertz_history.cpp b/src/GRANULAR/pair_gran_hertz_history.cpp
index d1f3c7bbe1..728491c17a 100644
--- a/src/GRANULAR/pair_gran_hertz_history.cpp
+++ b/src/GRANULAR/pair_gran_hertz_history.cpp
@@ -55,8 +55,7 @@ void PairGranHertzHistory::compute(int eflag, int vflag)
   int *touch,**firsttouch;
   double *shear,*allshear,**firstshear;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int shearupdate = 1;
   if (update->setupflag) shearupdate = 0;
diff --git a/src/GRANULAR/pair_gran_hooke.cpp b/src/GRANULAR/pair_gran_hooke.cpp
index 5244396ead..cfcc2743ba 100644
--- a/src/GRANULAR/pair_gran_hooke.cpp
+++ b/src/GRANULAR/pair_gran_hooke.cpp
@@ -51,8 +51,7 @@ void PairGranHooke::compute(int eflag, int vflag)
   double fn,fs,ft,fs1,fs2,fs3;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // update rigid body info for owned & ghost atoms if using FixRigid masses
   // body[i] = which body atom I is in, -1 if none
diff --git a/src/GRANULAR/pair_gran_hooke_history.cpp b/src/GRANULAR/pair_gran_hooke_history.cpp
index 83f75c221d..5a78b9d79a 100644
--- a/src/GRANULAR/pair_gran_hooke_history.cpp
+++ b/src/GRANULAR/pair_gran_hooke_history.cpp
@@ -44,6 +44,7 @@ PairGranHookeHistory::PairGranHookeHistory(LAMMPS *lmp) : Pair(lmp)
   single_enable = 1;
   no_virial_fdotr_compute = 1;
   history = 1;
+  size_history = 3;
   fix_history = NULL;
 
   single_extra = 10;
@@ -57,6 +58,10 @@ PairGranHookeHistory::PairGranHookeHistory(LAMMPS *lmp) : Pair(lmp)
   // set comm size needed by this Pair if used with fix rigid
 
   comm_forward = 1;
+
+  // keep default behavior of history[i][j] = -history[j][i]
+
+  nondefault_history_transfer = 0;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -98,8 +103,7 @@ void PairGranHookeHistory::compute(int eflag, int vflag)
   int *touch,**firsttouch;
   double *shear,*allshear,**firstshear;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   int shearupdate = 1;
   if (update->setupflag) shearupdate = 0;
@@ -414,7 +418,7 @@ void PairGranHookeHistory::init_style()
 
   if (history && fix_history == NULL) {
     char dnumstr[16];
-    sprintf(dnumstr,"%d",3);
+    sprintf(dnumstr,"%d",size_history);
     char **fixarg = new char*[4];
     fixarg[0] = (char *) "NEIGH_HISTORY";
     fixarg[1] = (char *) "all";
diff --git a/src/GRANULAR/pair_gran_hooke_history.h b/src/GRANULAR/pair_gran_hooke_history.h
index 3ca5c73116..81f2d8fd4a 100644
--- a/src/GRANULAR/pair_gran_hooke_history.h
+++ b/src/GRANULAR/pair_gran_hooke_history.h
@@ -54,6 +54,8 @@ class PairGranHookeHistory : public Pair {
   double *onerad_dynamic,*onerad_frozen;
   double *maxrad_dynamic,*maxrad_frozen;
 
+  int size_history;
+
   class FixNeighHistory *fix_history;
 
   // storage of rigid body masses for use in granular interactions
diff --git a/src/GRANULAR/pair_granular.cpp b/src/GRANULAR/pair_granular.cpp
new file mode 100644
index 0000000000..ce6cae75e4
--- /dev/null
+++ b/src/GRANULAR/pair_granular.cpp
@@ -0,0 +1,1741 @@
+/* ----------------------------------------------------------------------
+http://lammps.sandia.gov, Sandia National Laboratories
+Steve Plimpton, sjplimp@sandia.gov
+
+Copyright (2003) Sandia Corporation.  Under the terms of Contract
+DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+certain rights in this software.  This software is distributed under
+the GNU General Public License.
+
+See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   Contributing authors:
+   Dan Bolintineanu (SNL), Ishan Srivastava (SNL), Jeremy Lechman(SNL)
+   Leo Silbert (SNL), Gary Grest (SNL)
+----------------------------------------------------------------------- */
+
+#include <cmath>
+#include <cstdlib>
+#include <cstdio>
+#include <cstring>
+#include "pair_granular.h"
+#include "atom.h"
+#include "atom_vec.h"
+#include "domain.h"
+#include "force.h"
+#include "update.h"
+#include "modify.h"
+#include "fix.h"
+#include "fix_neigh_history.h"
+#include "comm.h"
+#include "neighbor.h"
+#include "neigh_list.h"
+#include "neigh_request.h"
+#include "memory.h"
+#include "error.h"
+#include "math_const.h"
+#include "math_special.h"
+
+using namespace LAMMPS_NS;
+using namespace MathConst;
+using namespace MathSpecial;
+
+#define PI27SQ 266.47931882941264802866    // 27*PI**2
+#define THREEROOT3 5.19615242270663202362  // 3*sqrt(3)
+#define SIXROOT6 14.69693845669906728801   // 6*sqrt(6)
+#define INVROOT6 0.40824829046386307274    // 1/sqrt(6)
+#define FOURTHIRDS 4.0/3.0                 // 4/3
+#define THREEQUARTERS 0.75                 // 3/4
+
+#define EPSILON 1e-10
+
+enum {HOOKE, HERTZ, HERTZ_MATERIAL, DMT, JKR};
+enum {VELOCITY, VISCOELASTIC, TSUJI};
+enum {TANGENTIAL_NOHISTORY, TANGENTIAL_HISTORY,
+      TANGENTIAL_MINDLIN, TANGENTIAL_MINDLIN_RESCALE};
+enum {TWIST_NONE, TWIST_SDS, TWIST_MARSHALL};
+enum {ROLL_NONE, ROLL_SDS};
+
+/* ---------------------------------------------------------------------- */
+
+PairGranular::PairGranular(LAMMPS *lmp) : Pair(lmp)
+{
+  single_enable = 1;
+  no_virial_fdotr_compute = 1;
+  fix_history = NULL;
+
+  single_extra = 12;
+  svector = new double[single_extra];
+
+  neighprev = 0;
+
+  nmax = 0;
+  mass_rigid = NULL;
+
+  onerad_dynamic = NULL;
+  onerad_frozen = NULL;
+  maxrad_dynamic = NULL;
+  maxrad_frozen = NULL;
+
+  history_transfer_factors = NULL;
+
+  dt = update->dt;
+
+  // set comm size needed by this Pair if used with fix rigid
+
+  comm_forward = 1;
+
+  use_history = 0;
+  beyond_contact = 0;
+  nondefault_history_transfer = 0;
+  tangential_history_index = 0;
+  roll_history_index = twist_history_index = 0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+PairGranular::~PairGranular()
+{
+  delete [] svector;
+  if (fix_history) modify->delete_fix("NEIGH_HISTORY");
+
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+    memory->destroy(cutoff_type);
+
+    memory->destroy(normal_coeffs);
+    memory->destroy(tangential_coeffs);
+    memory->destroy(roll_coeffs);
+    memory->destroy(twist_coeffs);
+
+    memory->destroy(Emod);
+    memory->destroy(poiss);
+
+    memory->destroy(normal_model);
+    memory->destroy(damping_model);
+    memory->destroy(tangential_model);
+    memory->destroy(roll_model);
+    memory->destroy(twist_model);
+
+    delete [] onerad_dynamic;
+    delete [] onerad_frozen;
+    delete [] maxrad_dynamic;
+    delete [] maxrad_frozen;
+  }
+
+  memory->destroy(mass_rigid);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void PairGranular::compute(int eflag, int vflag)
+{
+  int i,j,ii,jj,inum,jnum,itype,jtype;
+  double xtmp,ytmp,ztmp,delx,dely,delz,fx,fy,fz,nx,ny,nz;
+  double radi,radj,radsum,rsq,r,rinv;
+  double Reff, delta, dR, dR2, dist_to_contact;
+
+  double vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3;
+  double wr1,wr2,wr3;
+  double vtr1,vtr2,vtr3,vrel;
+
+  double knfac, damp_normal, damp_normal_prefactor;
+  double k_tangential, damp_tangential;
+  double Fne, Ft, Fdamp, Fntot, Fncrit, Fscrit, Frcrit;
+  double fs, fs1, fs2, fs3, tor1, tor2, tor3;
+
+  double mi,mj,meff;
+  double relrot1,relrot2,relrot3,vrl1,vrl2,vrl3;
+
+  // for JKR
+  double R2, coh, F_pulloff, delta_pulloff, dist_pulloff, a, a2, E;
+  double t0, t1, t2, t3, t4, t5, t6;
+  double sqrt1, sqrt2, sqrt3;
+
+  // rolling
+  double k_roll, damp_roll;
+  double torroll1, torroll2, torroll3;
+  double rollmag, rolldotn, scalefac;
+  double fr, fr1, fr2, fr3;
+
+  // twisting
+  double k_twist, damp_twist, mu_twist;
+  double signtwist, magtwist, magtortwist, Mtcrit;
+  double tortwist1, tortwist2, tortwist3;
+
+  double shrmag,rsht;
+  int *ilist,*jlist,*numneigh,**firstneigh;
+  int *touch,**firsttouch;
+  double *history,*allhistory,**firsthistory;
+
+  bool touchflag = false;
+  const bool historyupdate = (update->setupflag) ? false : true;
+
+  ev_init(eflag,vflag);
+
+  // update rigid body info for owned & ghost atoms if using FixRigid masses
+  // body[i] = which body atom I is in, -1 if none
+  // mass_body = mass of each rigid body
+
+  if (fix_rigid && neighbor->ago == 0) {
+    int tmp;
+    int *body = (int *) fix_rigid->extract("body",tmp);
+    double *mass_body = (double *) fix_rigid->extract("masstotal",tmp);
+    if (atom->nmax > nmax) {
+      memory->destroy(mass_rigid);
+      nmax = atom->nmax;
+      memory->create(mass_rigid,nmax,"pair:mass_rigid");
+    }
+    int nlocal = atom->nlocal;
+    for (i = 0; i < nlocal; i++)
+      if (body[i] >= 0) mass_rigid[i] = mass_body[body[i]];
+      else mass_rigid[i] = 0.0;
+    comm->forward_comm_pair(this);
+  }
+
+  double **x = atom->x;
+  double **v = atom->v;
+  double **f = atom->f;
+  int *type = atom->type;
+  double **omega = atom->omega;
+  double **torque = atom->torque;
+  double *radius = atom->radius;
+  double *rmass = atom->rmass;
+  int *mask = atom->mask;
+  int nlocal = atom->nlocal;
+
+  inum = list->inum;
+  ilist = list->ilist;
+  numneigh = list->numneigh;
+  firstneigh = list->firstneigh;
+  if (use_history) {
+    firsttouch = fix_history->firstflag;
+    firsthistory = fix_history->firstvalue;
+  }
+
+  for (ii = 0; ii < inum; ii++) {
+    i = ilist[ii];
+    itype = type[i];
+    xtmp = x[i][0];
+    ytmp = x[i][1];
+    ztmp = x[i][2];
+    itype = type[i];
+    radi = radius[i];
+    if (use_history) {
+      touch = firsttouch[i];
+      allhistory = firsthistory[i];
+    }
+    jlist = firstneigh[i];
+    jnum = numneigh[i];
+
+    for (jj = 0; jj < jnum; jj++) {
+      j = jlist[jj];
+      j &= NEIGHMASK;
+
+      delx = xtmp - x[j][0];
+      dely = ytmp - x[j][1];
+      delz = ztmp - x[j][2];
+      jtype = type[j];
+      rsq = delx*delx + dely*dely + delz*delz;
+      radj = radius[j];
+      radsum = radi + radj;
+
+      E = normal_coeffs[itype][jtype][0];
+      Reff = radi*radj/radsum;
+      touchflag = false;
+
+      if (normal_model[itype][jtype] == JKR) {
+        E *= THREEQUARTERS;
+        if (touch[jj]) {
+          R2 = Reff*Reff;
+          coh = normal_coeffs[itype][jtype][3];
+          a = cbrt(9.0*MY_PI*coh*R2/(4*E));
+          delta_pulloff = a*a/Reff - 2*sqrt(MY_PI*coh*a/E);
+          dist_pulloff = radsum-delta_pulloff;
+          touchflag = (rsq < dist_pulloff*dist_pulloff);
+        } else {
+          touchflag = (rsq < radsum*radsum);
+        }
+      } else {
+        touchflag = (rsq < radsum*radsum);
+      }
+
+      if (!touchflag) {
+        // unset non-touching neighbors
+        if (use_history) {
+          touch[jj] = 0;
+          history = &allhistory[size_history*jj];
+          for (int k = 0; k < size_history; k++) history[k] = 0.0;
+        }
+      } else {
+        r = sqrt(rsq);
+        rinv = 1.0/r;
+
+        nx = delx*rinv;
+        ny = dely*rinv;
+        nz = delz*rinv;
+
+        // relative translational velocity
+
+        vr1 = v[i][0] - v[j][0];
+        vr2 = v[i][1] - v[j][1];
+        vr3 = v[i][2] - v[j][2];
+
+        // normal component
+
+        vnnr = vr1*nx + vr2*ny + vr3*nz; //v_R . n
+        vn1 = nx*vnnr;
+        vn2 = ny*vnnr;
+        vn3 = nz*vnnr;
+
+        // meff = effective mass of pair of particles
+        // if I or J part of rigid body, use body mass
+        // if I or J is frozen, meff is other particle
+
+        mi = rmass[i];
+        mj = rmass[j];
+        if (fix_rigid) {
+          if (mass_rigid[i] > 0.0) mi = mass_rigid[i];
+          if (mass_rigid[j] > 0.0) mj = mass_rigid[j];
+        }
+
+        meff = mi*mj / (mi+mj);
+        if (mask[i] & freeze_group_bit) meff = mj;
+        if (mask[j] & freeze_group_bit) meff = mi;
+
+        delta = radsum - r;
+        dR = delta*Reff;
+        if (normal_model[itype][jtype] == JKR) {
+          touch[jj] = 1;
+          R2=Reff*Reff;
+          coh = normal_coeffs[itype][jtype][3];
+          dR2 = dR*dR;
+          t0 = coh*coh*R2*R2*E;
+          t1 = PI27SQ*t0;
+          t2 = 8*dR*dR2*E*E*E;
+          t3 = 4*dR2*E;
+          // in case sqrt(0) < 0 due to precision issues
+          sqrt1 = MAX(0, t0*(t1+2*t2));
+          t4 = cbrt(t1+t2+THREEROOT3*MY_PI*sqrt(sqrt1));
+          t5 = t3/t4 + t4/E;
+          sqrt2 = MAX(0, 2*dR + t5);
+          t6 = sqrt(sqrt2);
+          sqrt3 = MAX(0, 4*dR - t5 + SIXROOT6*coh*MY_PI*R2/(E*t6));
+          a = INVROOT6*(t6 + sqrt(sqrt3));
+          a2 = a*a;
+          knfac = normal_coeffs[itype][jtype][0]*a;
+          Fne = knfac*a2/Reff - MY_2PI*a2*sqrt(4*coh*E/(MY_PI*a));
+        } else {
+          knfac = E; // Hooke
+          Fne = knfac*delta;
+          a = sqrt(dR);
+          if (normal_model[itype][jtype] != HOOKE) {
+            Fne *= a;
+            knfac *= a;
+          }
+          if (normal_model[itype][jtype] == DMT)
+            Fne -= 4*MY_PI*normal_coeffs[itype][jtype][3]*Reff;
+        }
+
+        // NOTE: consider restricting Hooke to only have
+        // 'velocity' as an option for damping?
+
+        if (damping_model[itype][jtype] == VELOCITY) {
+          damp_normal = 1;
+        } else if (damping_model[itype][jtype] == VISCOELASTIC) {
+          damp_normal = a*meff;
+        } else if (damping_model[itype][jtype] == TSUJI) {
+          damp_normal = sqrt(meff*knfac);
+        }
+
+        damp_normal_prefactor = normal_coeffs[itype][jtype][1]*damp_normal;
+        Fdamp = -damp_normal_prefactor*vnnr;
+
+        Fntot = Fne + Fdamp;
+
+        //****************************************
+        // tangential force, including history effects
+        //****************************************
+
+        // tangential component
+        vt1 = vr1 - vn1;
+        vt2 = vr2 - vn2;
+        vt3 = vr3 - vn3;
+
+        // relative rotational velocity
+        wr1 = (radi*omega[i][0] + radj*omega[j][0]);
+        wr2 = (radi*omega[i][1] + radj*omega[j][1]);
+        wr3 = (radi*omega[i][2] + radj*omega[j][2]);
+
+        // relative tangential velocities
+        vtr1 = vt1 - (nz*wr2-ny*wr3);
+        vtr2 = vt2 - (nx*wr3-nz*wr1);
+        vtr3 = vt3 - (ny*wr1-nx*wr2);
+        vrel = vtr1*vtr1 + vtr2*vtr2 + vtr3*vtr3;
+        vrel = sqrt(vrel);
+
+        // if any history is needed
+        if (use_history) {
+          touch[jj] = 1;
+          history = &allhistory[size_history*jj];
+        }
+
+        if (normal_model[itype][jtype] == JKR) {
+          F_pulloff = 3*MY_PI*coh*Reff;
+          Fncrit = fabs(Fne + 2*F_pulloff);
+        } else if (normal_model[itype][jtype] == DMT) {
+          F_pulloff = 4*MY_PI*coh*Reff;
+          Fncrit = fabs(Fne + 2*F_pulloff);
+        } else {
+          Fncrit = fabs(Fntot);
+        }
+
+        //------------------------------
+        // tangential forces
+        //------------------------------
+        k_tangential = tangential_coeffs[itype][jtype][0];
+        damp_tangential = tangential_coeffs[itype][jtype][1] *
+          damp_normal_prefactor;
+
+        if (tangential_history) {
+          if (tangential_model[itype][jtype] == TANGENTIAL_MINDLIN) {
+            k_tangential *= a;
+          } else if (tangential_model[itype][jtype] ==
+                     TANGENTIAL_MINDLIN_RESCALE) {
+            k_tangential *= a;
+            // on unloading, rescale the shear displacements
+            if (a < history[3]) {
+              double factor = a/history[3];
+              history[0] *= factor;
+              history[1] *= factor;
+              history[2] *= factor;
+            }
+          }
+          // rotate and update displacements.
+          // see e.g. eq. 17 of Luding, Gran. Matter 2008, v10,p235
+          if (historyupdate) {
+            rsht = history[0]*nx + history[1]*ny + history[2]*nz;
+            if (fabs(rsht) < EPSILON) rsht = 0;
+            if (rsht > 0) {
+              shrmag = sqrt(history[0]*history[0] + history[1]*history[1] +
+                                               history[2]*history[2]);
+              // if rsht == shrmag, contacting pair has rotated 90 deg
+              // in one step, in which case you deserve a crash!
+              scalefac = shrmag/(shrmag - rsht);
+              history[0] -= rsht*nx;
+              history[1] -= rsht*ny;
+              history[2] -= rsht*nz;
+              // also rescale to preserve magnitude
+              history[0] *= scalefac;
+              history[1] *= scalefac;
+              history[2] *= scalefac;
+            }
+            // update history
+            history[0] += vtr1*dt;
+            history[1] += vtr2*dt;
+            history[2] += vtr3*dt;
+            if (tangential_model[itype][jtype] == TANGENTIAL_MINDLIN_RESCALE)
+              history[3] = a;
+          }
+
+          // tangential forces = history + tangential velocity damping
+          fs1 = -k_tangential*history[0] - damp_tangential*vtr1;
+          fs2 = -k_tangential*history[1] - damp_tangential*vtr2;
+          fs3 = -k_tangential*history[2] - damp_tangential*vtr3;
+
+          // rescale frictional displacements and forces if needed
+          Fscrit = tangential_coeffs[itype][jtype][2] * Fncrit;
+          fs = sqrt(fs1*fs1 + fs2*fs2 + fs3*fs3);
+          if (fs > Fscrit) {
+            shrmag = sqrt(history[0]*history[0] + history[1]*history[1] +
+                                    history[2]*history[2]);
+            if (shrmag != 0.0) {
+              history[0] = -1.0/k_tangential*(Fscrit*fs1/fs +
+                                              damp_tangential*vtr1);
+              history[1] = -1.0/k_tangential*(Fscrit*fs2/fs +
+                                              damp_tangential*vtr2);
+              history[2] = -1.0/k_tangential*(Fscrit*fs3/fs +
+                                              damp_tangential*vtr3);
+              fs1 *= Fscrit/fs;
+              fs2 *= Fscrit/fs;
+              fs3 *= Fscrit/fs;
+            } else fs1 = fs2 = fs3 = 0.0;
+          }
+        } else { // classic pair gran/hooke (no history)
+          fs = meff*damp_tangential*vrel;
+          if (vrel != 0.0) Ft = MIN(Fne,fs) / vrel;
+          else Ft = 0.0;
+          fs1 = -Ft*vtr1;
+          fs2 = -Ft*vtr2;
+          fs3 = -Ft*vtr3;
+        }
+
+        //****************************************
+        // rolling resistance
+        //****************************************
+
+        if (roll_model[itype][jtype] != ROLL_NONE) {
+          relrot1 = omega[i][0] - omega[j][0];
+          relrot2 = omega[i][1] - omega[j][1];
+          relrot3 = omega[i][2] - omega[j][2];
+
+          // rolling velocity,
+          // see eq. 31 of Wang et al, Particuology v 23, p 49 (2015)
+          // this is different from the Marshall papers,
+          // which use the Bagi/Kuhn formulation
+          // for rolling velocity (see Wang et al for why the latter is wrong)
+          // - 0.5*((radj-radi)/radsum)*vtr1;
+          // - 0.5*((radj-radi)/radsum)*vtr2;
+          // - 0.5*((radj-radi)/radsum)*vtr3;
+
+          vrl1 = Reff*(relrot2*nz - relrot3*ny);
+          vrl2 = Reff*(relrot3*nx - relrot1*nz);
+          vrl3 = Reff*(relrot1*ny - relrot2*nx);
+
+          int rhist0 = roll_history_index;
+          int rhist1 = rhist0 + 1;
+          int rhist2 = rhist1 + 1;
+
+          rolldotn = history[rhist0]*nx + history[rhist1]*ny + history[rhist2]*nz;
+          if (historyupdate) {
+            if (fabs(rolldotn) < EPSILON) rolldotn = 0;
+            if (rolldotn > 0) { // rotate into tangential plane
+              rollmag = sqrt(history[rhist0]*history[rhist0] +
+                            history[rhist1]*history[rhist1] +
+                            history[rhist2]*history[rhist2]);
+              scalefac = rollmag/(rollmag - rolldotn);
+              history[rhist0] -= rolldotn*nx;
+              history[rhist1] -= rolldotn*ny;
+              history[rhist2] -= rolldotn*nz;
+              // also rescale to preserve magnitude
+              history[rhist0] *= scalefac;
+              history[rhist1] *= scalefac;
+              history[rhist2] *= scalefac;
+            }
+            history[rhist0] += vrl1*dt;
+            history[rhist1] += vrl2*dt;
+            history[rhist2] += vrl3*dt;
+          }
+
+          k_roll = roll_coeffs[itype][jtype][0];
+          damp_roll = roll_coeffs[itype][jtype][1];
+          fr1 = -k_roll*history[rhist0] - damp_roll*vrl1;
+          fr2 = -k_roll*history[rhist1] - damp_roll*vrl2;
+          fr3 = -k_roll*history[rhist2] - damp_roll*vrl3;
+
+          // rescale frictional displacements and forces if needed
+          Frcrit = roll_coeffs[itype][jtype][2] * Fncrit;
+
+          fr = sqrt(fr1*fr1 + fr2*fr2 + fr3*fr3);
+          if (fr > Frcrit) {
+            rollmag = sqrt(history[rhist0]*history[rhist0] +
+                                    history[rhist1]*history[rhist1] +
+                                    history[rhist2]*history[rhist2]);
+            if (rollmag != 0.0) {
+              history[rhist0] = -1.0/k_roll*(Frcrit*fr1/fr + damp_roll*vrl1);
+              history[rhist1] = -1.0/k_roll*(Frcrit*fr2/fr + damp_roll*vrl2);
+              history[rhist2] = -1.0/k_roll*(Frcrit*fr3/fr + damp_roll*vrl3);
+              fr1 *= Frcrit/fr;
+              fr2 *= Frcrit/fr;
+              fr3 *= Frcrit/fr;
+            } else fr1 = fr2 = fr3 = 0.0;
+          }
+        }
+
+        //****************************************
+        // twisting torque, including history effects
+        //****************************************
+
+        if (twist_model[itype][jtype] != TWIST_NONE) {
+          // omega_T (eq 29 of Marshall)
+          magtwist = relrot1*nx + relrot2*ny + relrot3*nz;
+          if (twist_model[itype][jtype] == TWIST_MARSHALL) {
+            k_twist = 0.5*k_tangential*a*a;; // eq 32 of Marshall paper
+            damp_twist = 0.5*damp_tangential*a*a;
+            mu_twist = TWOTHIRDS*a*tangential_coeffs[itype][jtype][2];
+          } else {
+            k_twist = twist_coeffs[itype][jtype][0];
+            damp_twist = twist_coeffs[itype][jtype][1];
+            mu_twist = twist_coeffs[itype][jtype][2];
+          }
+          if (historyupdate) {
+            history[twist_history_index] += magtwist*dt;
+          }
+          magtortwist = -k_twist*history[twist_history_index] -
+            damp_twist*magtwist; // M_t torque (eq 30)
+          signtwist = (magtwist > 0) - (magtwist < 0);
+          Mtcrit = mu_twist*Fncrit; // critical torque (eq 44)
+          if (fabs(magtortwist) > Mtcrit) {
+            history[twist_history_index] = 1.0/k_twist*(Mtcrit*signtwist -
+                                                        damp_twist*magtwist);
+            magtortwist = -Mtcrit * signtwist; // eq 34
+          }
+        }
+
+        // apply forces & torques
+
+        fx = nx*Fntot + fs1;
+        fy = ny*Fntot + fs2;
+        fz = nz*Fntot + fs3;
+
+        f[i][0] += fx;
+        f[i][1] += fy;
+        f[i][2] += fz;
+
+        tor1 = ny*fs3 - nz*fs2;
+        tor2 = nz*fs1 - nx*fs3;
+        tor3 = nx*fs2 - ny*fs1;
+
+	dist_to_contact = radi-0.5*delta;
+        torque[i][0] -= dist_to_contact*tor1;
+        torque[i][1] -= dist_to_contact*tor2;
+        torque[i][2] -= dist_to_contact*tor3;
+
+        if (twist_model[itype][jtype] != TWIST_NONE) {
+          tortwist1 = magtortwist * nx;
+          tortwist2 = magtortwist * ny;
+          tortwist3 = magtortwist * nz;
+
+          torque[i][0] += tortwist1;
+          torque[i][1] += tortwist2;
+          torque[i][2] += tortwist3;
+        }
+
+        if (roll_model[itype][jtype] != ROLL_NONE) {
+          torroll1 = Reff*(ny*fr3 - nz*fr2); // n cross fr
+          torroll2 = Reff*(nz*fr1 - nx*fr3);
+          torroll3 = Reff*(nx*fr2 - ny*fr1);
+
+          torque[i][0] += torroll1;
+          torque[i][1] += torroll2;
+          torque[i][2] += torroll3;
+        }
+
+        if (force->newton_pair || j < nlocal) {
+          f[j][0] -= fx;
+          f[j][1] -= fy;
+          f[j][2] -= fz;
+
+	  dist_to_contact = radj-0.5*delta;
+          torque[j][0] -= dist_to_contact*tor1;
+          torque[j][1] -= dist_to_contact*tor2;
+          torque[j][2] -= dist_to_contact*tor3;
+
+          if (twist_model[itype][jtype] != TWIST_NONE) {
+            torque[j][0] -= tortwist1;
+            torque[j][1] -= tortwist2;
+            torque[j][2] -= tortwist3;
+          }
+          if (roll_model[itype][jtype] != ROLL_NONE) {
+            torque[j][0] -= torroll1;
+            torque[j][1] -= torroll2;
+            torque[j][2] -= torroll3;
+          }
+        }
+        if (evflag) ev_tally_xyz(i,j,nlocal,0,
+            0.0,0.0,fx,fy,fz,delx,dely,delz);
+      }
+    }
+  }
+}
+
+/* ----------------------------------------------------------------------
+   allocate all arrays
+------------------------------------------------------------------------- */
+
+void PairGranular::allocate()
+{
+  allocated = 1;
+  int n = atom->ntypes;
+
+  memory->create(setflag,n+1,n+1,"pair:setflag");
+  for (int i = 1; i <= n; i++)
+    for (int j = i; j <= n; j++)
+      setflag[i][j] = 0;
+
+  memory->create(cutsq,n+1,n+1,"pair:cutsq");
+  memory->create(cutoff_type,n+1,n+1,"pair:cutoff_type");
+  memory->create(normal_coeffs,n+1,n+1,4,"pair:normal_coeffs");
+  memory->create(tangential_coeffs,n+1,n+1,3,"pair:tangential_coeffs");
+  memory->create(roll_coeffs,n+1,n+1,3,"pair:roll_coeffs");
+  memory->create(twist_coeffs,n+1,n+1,3,"pair:twist_coeffs");
+
+  memory->create(Emod,n+1,n+1,"pair:Emod");
+  memory->create(poiss,n+1,n+1,"pair:poiss");
+
+  memory->create(normal_model,n+1,n+1,"pair:normal_model");
+  memory->create(damping_model,n+1,n+1,"pair:damping_model");
+  memory->create(tangential_model,n+1,n+1,"pair:tangential_model");
+  memory->create(roll_model,n+1,n+1,"pair:roll_model");
+  memory->create(twist_model,n+1,n+1,"pair:twist_model");
+
+  onerad_dynamic = new double[n+1];
+  onerad_frozen = new double[n+1];
+  maxrad_dynamic = new double[n+1];
+  maxrad_frozen = new double[n+1];
+}
+
+/* ----------------------------------------------------------------------
+   global settings
+------------------------------------------------------------------------- */
+
+void PairGranular::settings(int narg, char **arg)
+{
+  if (narg == 1) {
+    cutoff_global = force->numeric(FLERR,arg[0]);
+  } else {
+    cutoff_global = -1; // will be set based on particle sizes, model choice
+  }
+
+  normal_history = tangential_history = 0;
+  roll_history = twist_history = 0;
+}
+
+/* ----------------------------------------------------------------------
+  set coeffs for one or more type pairs
+------------------------------------------------------------------------- */
+
+void PairGranular::coeff(int narg, char **arg)
+{
+  int normal_model_one, damping_model_one;
+  int tangential_model_one, roll_model_one, twist_model_one;
+
+  double normal_coeffs_one[4];
+  double tangential_coeffs_one[4];
+  double roll_coeffs_one[4];
+  double twist_coeffs_one[4];
+
+  double cutoff_one = -1;
+
+  if (narg < 2)
+    error->all(FLERR,"Incorrect args for pair coefficients");
+
+  if (!allocated) allocate();
+
+  int ilo,ihi,jlo,jhi;
+  force->bounds(FLERR,arg[0],atom->ntypes,ilo,ihi);
+  force->bounds(FLERR,arg[1],atom->ntypes,jlo,jhi);
+
+  //Defaults
+  normal_model_one = tangential_model_one = -1;
+  roll_model_one = twist_model_one = 0;
+  damping_model_one = VISCOELASTIC;
+
+  int iarg = 2;
+  while (iarg < narg) {
+    if (strcmp(arg[iarg], "hooke") == 0) {
+      if (iarg + 2 >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, "
+                   "not enough parameters provided for Hooke option");
+      normal_model_one = HOOKE;
+      normal_coeffs_one[0] = force->numeric(FLERR,arg[iarg+1]); // kn
+      normal_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]); // damping
+      iarg += 3;
+    } else if (strcmp(arg[iarg], "hertz") == 0) {
+      int num_coeffs = 2;
+      if (iarg + num_coeffs >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, "
+                   "not enough parameters provided for Hertz option");
+      normal_model_one = HERTZ;
+      normal_coeffs_one[0] = force->numeric(FLERR,arg[iarg+1]); // kn
+      normal_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]); // damping
+      iarg += num_coeffs+1;
+    } else if (strcmp(arg[iarg], "hertz/material") == 0) {
+      int num_coeffs = 3;
+      if (iarg + num_coeffs >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, "
+                   "not enough parameters provided for Hertz/material option");
+      normal_model_one = HERTZ_MATERIAL;
+      normal_coeffs_one[0] = force->numeric(FLERR,arg[iarg+1]); // E
+      normal_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]); // damping
+      normal_coeffs_one[2] = force->numeric(FLERR,arg[iarg+3]); // Poisson's ratio
+      iarg += num_coeffs+1;
+    } else if (strcmp(arg[iarg], "dmt") == 0) {
+      if (iarg + 4 >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, "
+                   "not enough parameters provided for Hertz option");
+      normal_model_one = DMT;
+      normal_coeffs_one[0] = force->numeric(FLERR,arg[iarg+1]); // E
+      normal_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]); // damping
+      normal_coeffs_one[2] = force->numeric(FLERR,arg[iarg+3]); // Poisson's ratio
+      normal_coeffs_one[3] = force->numeric(FLERR,arg[iarg+4]); // cohesion
+      iarg += 5;
+    } else if (strcmp(arg[iarg], "jkr") == 0) {
+      if (iarg + 4 >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, "
+                   "not enough parameters provided for JKR option");
+      beyond_contact = 1;
+      normal_model_one = JKR;
+      normal_coeffs_one[0] = force->numeric(FLERR,arg[iarg+1]); // E
+      normal_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]); // damping
+      normal_coeffs_one[2] = force->numeric(FLERR,arg[iarg+3]); // Poisson's ratio
+      normal_coeffs_one[3] = force->numeric(FLERR,arg[iarg+4]); // cohesion
+      iarg += 5;
+    } else if (strcmp(arg[iarg], "damping") == 0) {
+      if (iarg+1 >= narg)
+        error->all(FLERR, "Illegal pair_coeff command, "
+                   "not enough parameters provided for damping model");
+      if (strcmp(arg[iarg+1], "velocity") == 0) {
+        damping_model_one = VELOCITY;
+        iarg += 1;
+      } else if (strcmp(arg[iarg+1], "viscoelastic") == 0) {
+        damping_model_one = VISCOELASTIC;
+        iarg += 1;
+      } else if (strcmp(arg[iarg+1], "tsuji") == 0) {
+        damping_model_one = TSUJI;
+        iarg += 1;
+      } else error->all(FLERR, "Illegal pair_coeff command, "
+                        "unrecognized damping model");
+      iarg += 1;
+    } else if (strcmp(arg[iarg], "tangential") == 0) {
+      if (iarg + 1 >= narg)
+        error->all(FLERR,"Illegal pair_coeff command, must specify "
+                   "tangential model after tangential keyword");
+      if (strcmp(arg[iarg+1], "linear_nohistory") == 0) {
+        if (iarg + 3 >= narg)
+          error->all(FLERR,"Illegal pair_coeff command, "
+                     "not enough parameters provided for tangential model");
+        tangential_model_one = TANGENTIAL_NOHISTORY;
+        tangential_coeffs_one[0] = 0;
+        // gammat and friction coeff
+        tangential_coeffs_one[1] = force->numeric(FLERR,arg[iarg+2]);
+        tangential_coeffs_one[2] = force->numeric(FLERR,arg[iarg+3]);
+        iarg += 4;
+      } else if ((strcmp(arg[iarg+1], "linear_history") == 0) ||
+               (strcmp(arg[iarg+1], "mindlin") == 0) ||
+               (strcmp(arg[iarg+1], "mindlin_rescale") == 0)) {
+        if (iarg + 4 >= narg)
+          error->all(FLERR,"Illegal pair_coeff command, "
+                     "not enough parameters provided for tangential model");
+        if (strcmp(arg[iarg+1], "linear_history") == 0)
+          tangential_model_one = TANGENTIAL_HISTORY;
+        else if (strcmp(arg[iarg+1], "mindlin") == 0)
+          tangential_model_one = TANGENTIAL_MINDLIN;
+        else if (strcmp(arg[iarg+1], "mindlin_rescale") == 0)
+          tangential_model_one = TANGENTIAL_MINDLIN_RESCALE;
+        tangential_history = 1;
+        if ((tangential_model_one == TANGENTIAL_MINDLIN ||
+             tangential_model_one == TANGENTIAL_MINDLIN_RESCALE) &&
+            (strcmp(arg[iarg+2], "NULL") == 0)) {
+          if (normal_model_one == HERTZ || normal_model_one == HOOKE) {
+            error->all(FLERR, "NULL setting for Mindlin tangential "
+                       "stiffness requires a normal contact model that "
+                       "specifies material properties");
+          }
+          tangential_coeffs_one[0] = -1;
+        } else {
+          tangential_coeffs_one[0] = force->numeric(FLERR,arg[iarg+2]); // kt
+        }
+        // gammat and friction coeff
+        tangential_coeffs_one[1] = force->numeric(FLERR,arg[iarg+3]);
+        tangential_coeffs_one[2] = force->numeric(FLERR,arg[iarg+4]);
+        iarg += 5;
+      } else {
+        error->all(FLERR, "Illegal pair_coeff command, "
+                   "tangential model not recognized");
+      }
+    } else if (strcmp(arg[iarg], "rolling") == 0) {
+      if (iarg + 1 >= narg)
+        error->all(FLERR, "Illegal pair_coeff command, not enough parameters");
+      if (strcmp(arg[iarg+1], "none") == 0) {
+        roll_model_one = ROLL_NONE;
+        iarg += 2;
+      } else if (strcmp(arg[iarg+1], "sds") == 0) {
+        if (iarg + 4 >= narg)
+          error->all(FLERR,"Illegal pair_coeff command, "
+                     "not enough parameters provided for rolling model");
+        roll_model_one = ROLL_SDS;
+        roll_history = 1;
+        // kR and gammaR and rolling friction coeff
+        roll_coeffs_one[0] = force->numeric(FLERR,arg[iarg+2]);
+        roll_coeffs_one[1] = force->numeric(FLERR,arg[iarg+3]);
+        roll_coeffs_one[2] = force->numeric(FLERR,arg[iarg+4]);
+        iarg += 5;
+      } else {
+        error->all(FLERR, "Illegal pair_coeff command, "
+                   "rolling friction model not recognized");
+      }
+    } else if (strcmp(arg[iarg], "twisting") == 0) {
+      if (iarg + 1 >= narg)
+        error->all(FLERR, "Illegal pair_coeff command, not enough parameters");
+      if (strcmp(arg[iarg+1], "none") == 0) {
+        twist_model_one = TWIST_NONE;
+        iarg += 2;
+      } else if (strcmp(arg[iarg+1], "marshall") == 0) {
+        twist_model_one = TWIST_MARSHALL;
+        twist_history = 1;
+        iarg += 2;
+      } else if (strcmp(arg[iarg+1], "sds") == 0) {
+        if (iarg + 4 >= narg)
+          error->all(FLERR,"Illegal pair_coeff command, "
+                     "not enough parameters provided for twist model");
+        twist_model_one = TWIST_SDS;
+        twist_history = 1;
+        // kt and gammat and friction coeff
+        twist_coeffs_one[0] = force->numeric(FLERR,arg[iarg+2]);
+        twist_coeffs_one[1] = force->numeric(FLERR,arg[iarg+3]);
+        twist_coeffs_one[2] = force->numeric(FLERR,arg[iarg+4]);
+        iarg += 5;
+      } else {
+        error->all(FLERR, "Illegal pair_coeff command, "
+                   "twisting friction model not recognized");
+      }
+    } else if (strcmp(arg[iarg], "cutoff") == 0) {
+      if (iarg + 1 >= narg)
+        error->all(FLERR, "Illegal pair_coeff command, not enough parameters");
+      cutoff_one = force->numeric(FLERR,arg[iarg+1]);
+    } else error->all(FLERR, "Illegal pair coeff command");
+  }
+
+  // error not to specify normal or tangential model
+  if ((normal_model_one < 0) || (tangential_model_one < 0))
+    error->all(FLERR, "Illegal pair coeff command, "
+               "must specify normal or tangential contact model");
+
+  int count = 0;
+  double damp;
+  if (damping_model_one == TSUJI) {
+    double cor;
+    cor = normal_coeffs_one[1];
+    damp = 1.2728-4.2783*cor+11.087*square(cor)-22.348*cube(cor)+
+        27.467*powint(cor,4)-18.022*powint(cor,5)+4.8218*powint(cor,6);
+  } else damp = normal_coeffs_one[1];
+
+  for (int i = ilo; i <= ihi; i++) {
+    for (int j = MAX(jlo,i); j <= jhi; j++) {
+      normal_model[i][j] = normal_model[j][i] = normal_model_one;
+      normal_coeffs[i][j][1] = normal_coeffs[j][i][1] = damp;
+      if (normal_model_one != HERTZ && normal_model_one != HOOKE) {
+        Emod[i][j] = Emod[j][i] = normal_coeffs_one[0];
+        poiss[i][j] = poiss[j][i] = normal_coeffs_one[2];
+        normal_coeffs[i][j][0] = normal_coeffs[j][i][0] =
+          FOURTHIRDS*mix_stiffnessE(Emod[i][j],Emod[i][j],
+                                    poiss[i][j],poiss[i][j]);
+      } else {
+        normal_coeffs[i][j][0] = normal_coeffs[j][i][0] = normal_coeffs_one[0];
+      }
+      if ((normal_model_one == JKR) || (normal_model_one == DMT))
+        normal_coeffs[i][j][3] = normal_coeffs[j][i][3] = normal_coeffs_one[3];
+
+      damping_model[i][j] = damping_model[j][i] = damping_model_one;
+
+      tangential_model[i][j] = tangential_model[j][i] = tangential_model_one;
+      if (tangential_coeffs_one[0] == -1) {
+        tangential_coeffs[i][j][0] = tangential_coeffs[j][i][0] =
+          8*mix_stiffnessG(Emod[i][j],Emod[i][j],poiss[i][j],poiss[i][j]);
+      } else {
+        tangential_coeffs[i][j][0] = tangential_coeffs[j][i][0] =
+          tangential_coeffs_one[0];
+      }
+      for (int k = 1; k < 3; k++)
+        tangential_coeffs[i][j][k] = tangential_coeffs[j][i][k] =
+          tangential_coeffs_one[k];
+
+      roll_model[i][j] = roll_model[j][i] = roll_model_one;
+      if (roll_model_one != ROLL_NONE)
+        for (int k = 0; k < 3; k++)
+          roll_coeffs[i][j][k] = roll_coeffs[j][i][k] = roll_coeffs_one[k];
+
+      twist_model[i][j] = twist_model[j][i] = twist_model_one;
+      if (twist_model_one != TWIST_NONE && twist_model_one != TWIST_MARSHALL)
+        for (int k = 0; k < 3; k++)
+          twist_coeffs[i][j][k] = twist_coeffs[j][i][k] = twist_coeffs_one[k];
+
+      cutoff_type[i][j] = cutoff_type[j][i] = cutoff_one;
+
+      setflag[i][j] = 1;
+      count++;
+    }
+  }
+
+  if (count == 0) error->all(FLERR,"Incorrect args for pair coefficients");
+}
+
+/* ----------------------------------------------------------------------
+	 init specific to this pair style
+------------------------------------------------------------------------- */
+
+void PairGranular::init_style()
+{
+  int i;
+
+  // error and warning checks
+
+  if (!atom->radius_flag || !atom->rmass_flag)
+    error->all(FLERR,"Pair granular requires atom attributes radius, rmass");
+  if (comm->ghost_velocity == 0)
+    error->all(FLERR,"Pair granular requires ghost atoms store velocity");
+
+  // determine whether we need a granular neigh list, how large it needs to be
+
+  use_history = normal_history || tangential_history ||
+    roll_history || twist_history;
+
+  // for JKR, will need fix/neigh/history to keep track of touch arrays
+
+  for (int i = 1; i <= atom->ntypes; i++)
+    for (int j = i; j <= atom->ntypes; j++)
+      if (normal_model[i][j] == JKR) use_history = 1;
+
+  size_history = 3*tangential_history + 3*roll_history + twist_history;
+
+  // determine location of tangential/roll/twist histories in array
+
+  if (roll_history) {
+    if (tangential_history) roll_history_index = 3;
+    else roll_history_index = 0;
+  }
+  if (twist_history) {
+    if (tangential_history) {
+      if (roll_history) twist_history_index = 6;
+      else twist_history_index = 3;
+    } else {
+      if (roll_history) twist_history_index = 3;
+      else twist_history_index = 0;
+    }
+  }
+  for (int i = 1; i <= atom->ntypes; i++)
+    for (int j = i; j <= atom->ntypes; j++)
+      if (tangential_model[i][j] == TANGENTIAL_MINDLIN_RESCALE) {
+        size_history += 1;
+        roll_history_index += 1;
+        twist_history_index += 1;
+        nondefault_history_transfer = 1;
+        history_transfer_factors = new int[size_history];
+        for (int ii = 0; ii < size_history; ++ii)
+          history_transfer_factors[ii] = -1;
+        history_transfer_factors[3] = 1;
+        break;
+      }
+
+  int irequest = neighbor->request(this,instance_me);
+  neighbor->requests[irequest]->size = 1;
+  if (use_history) neighbor->requests[irequest]->history = 1;
+
+  dt = update->dt;
+
+  // if history is stored:
+  // if first init, create Fix needed for storing history
+
+  if (use_history && fix_history == NULL) {
+    char dnumstr[16];
+    sprintf(dnumstr,"%d",size_history);
+    char **fixarg = new char*[4];
+    fixarg[0] = (char *) "NEIGH_HISTORY";
+    fixarg[1] = (char *) "all";
+    fixarg[2] = (char *) "NEIGH_HISTORY";
+    fixarg[3] = dnumstr;
+    modify->add_fix(4,fixarg,1);
+    delete [] fixarg;
+    fix_history = (FixNeighHistory *) modify->fix[modify->nfix-1];
+    fix_history->pair = this;
+  }
+
+  // check for FixFreeze and set freeze_group_bit
+
+  for (i = 0; i < modify->nfix; i++)
+    if (strcmp(modify->fix[i]->style,"freeze") == 0) break;
+  if (i < modify->nfix) freeze_group_bit = modify->fix[i]->groupbit;
+  else freeze_group_bit = 0;
+
+  // check for FixRigid so can extract rigid body masses
+
+  fix_rigid = NULL;
+  for (i = 0; i < modify->nfix; i++)
+    if (modify->fix[i]->rigid_flag) break;
+  if (i < modify->nfix) fix_rigid = modify->fix[i];
+
+  // check for FixPour and FixDeposit so can extract particle radii
+
+  int ipour;
+  for (ipour = 0; ipour < modify->nfix; ipour++)
+    if (strcmp(modify->fix[ipour]->style,"pour") == 0) break;
+  if (ipour == modify->nfix) ipour = -1;
+
+  int idep;
+  for (idep = 0; idep < modify->nfix; idep++)
+    if (strcmp(modify->fix[idep]->style,"deposit") == 0) break;
+  if (idep == modify->nfix) idep = -1;
+
+  // set maxrad_dynamic and maxrad_frozen for each type
+  // include future FixPour and FixDeposit particles as dynamic
+
+  int itype;
+  for (i = 1; i <= atom->ntypes; i++) {
+    onerad_dynamic[i] = onerad_frozen[i] = 0.0;
+    if (ipour >= 0) {
+      itype = i;
+      double radmax = *((double *) modify->fix[ipour]->extract("radius",itype));
+      onerad_dynamic[i] = radmax;
+    }
+    if (idep >= 0) {
+      itype = i;
+      double radmax = *((double *) modify->fix[idep]->extract("radius",itype));
+      onerad_dynamic[i] = radmax;
+    }
+  }
+
+  double *radius = atom->radius;
+  int *mask = atom->mask;
+  int *type = atom->type;
+  int nlocal = atom->nlocal;
+
+  for (i = 0; i < nlocal; i++) {
+    double radius_cut = radius[i];
+    if (mask[i] & freeze_group_bit) {
+      onerad_frozen[type[i]] = MAX(onerad_frozen[type[i]],radius_cut);
+    } else {
+      onerad_dynamic[type[i]] = MAX(onerad_dynamic[type[i]],radius_cut);
+    }
+  }
+
+  MPI_Allreduce(&onerad_dynamic[1],&maxrad_dynamic[1],atom->ntypes,
+                MPI_DOUBLE,MPI_MAX,world);
+  MPI_Allreduce(&onerad_frozen[1],&maxrad_frozen[1],atom->ntypes,
+                MPI_DOUBLE,MPI_MAX,world);
+
+  // set fix which stores history info
+
+  if (size_history > 0) {
+    int ifix = modify->find_fix("NEIGH_HISTORY");
+    if (ifix < 0) error->all(FLERR,"Could not find pair fix neigh history ID");
+    fix_history = (FixNeighHistory *) modify->fix[ifix];
+  }
+}
+
+/* ----------------------------------------------------------------------
+   init for one type pair i,j and corresponding j,i
+------------------------------------------------------------------------- */
+
+double PairGranular::init_one(int i, int j)
+{
+  double cutoff;
+
+  if (setflag[i][j] == 0) {
+    if ((normal_model[i][i] != normal_model[j][j]) ||
+        (damping_model[i][i] != damping_model[j][j]) ||
+        (tangential_model[i][i] != tangential_model[j][j]) ||
+        (roll_model[i][i] != roll_model[j][j]) ||
+        (twist_model[i][i] != twist_model[j][j])) {
+
+      char str[512];
+      sprintf(str,"Granular pair style functional forms are different, "
+              "cannot mix coefficients for types %d and %d. \n"
+              "This combination must be set explicitly "
+              "via pair_coeff command",i,j);
+      error->one(FLERR,str);
+    }
+
+    if (normal_model[i][j] == HERTZ || normal_model[i][j] == HOOKE)
+      normal_coeffs[i][j][0] = normal_coeffs[j][i][0] =
+        mix_geom(normal_coeffs[i][i][0], normal_coeffs[j][j][0]);
+    else
+      normal_coeffs[i][j][0] = normal_coeffs[j][i][0] =
+        mix_stiffnessE(Emod[i][i], Emod[j][j], poiss[i][i], poiss[j][j]);
+
+    normal_coeffs[i][j][1] = normal_coeffs[j][i][1] =
+      mix_geom(normal_coeffs[i][i][1], normal_coeffs[j][j][1]);
+    if ((normal_model[i][j] == JKR) || (normal_model[i][j] == DMT))
+      normal_coeffs[i][j][3] = normal_coeffs[j][i][3] =
+        mix_geom(normal_coeffs[i][i][3], normal_coeffs[j][j][3]);
+
+    for (int k = 0; k < 3; k++)
+      tangential_coeffs[i][j][k] = tangential_coeffs[j][i][k] =
+        mix_geom(tangential_coeffs[i][i][k], tangential_coeffs[j][j][k]);
+
+    if (roll_model[i][j] != ROLL_NONE) {
+      for (int k = 0; k < 3; k++)
+        roll_coeffs[i][j][k] = roll_coeffs[j][i][k] =
+          mix_geom(roll_coeffs[i][i][k], roll_coeffs[j][j][k]);
+    }
+
+    if (twist_model[i][j] != TWIST_NONE && twist_model[i][j] != TWIST_MARSHALL) {
+      for (int k = 0; k < 3; k++)
+        twist_coeffs[i][j][k] = twist_coeffs[j][i][k] =
+          mix_geom(twist_coeffs[i][i][k], twist_coeffs[j][j][k]);
+    }
+  }
+
+  // It is possible that cut[i][j] at this point is still 0.0.
+  // This can happen when
+  // there is a future fix_pour after the current run. A cut[i][j] = 0.0 creates
+  // problems because neighbor.cpp uses min(cut[i][j]) to decide on the bin size
+  // To avoid this issue, for cases involving  cut[i][j] = 0.0 (possible only
+  // if there is no current information about radius/cutoff of type i and j).
+  // we assign cutoff = max(cut[i][j]) for i,j such that cut[i][j] > 0.0.
+
+  double pulloff;
+
+  if (cutoff_type[i][j] < 0 && cutoff_global < 0) {
+    if (((maxrad_dynamic[i] > 0.0) && (maxrad_dynamic[j] > 0.0)) ||
+        ((maxrad_dynamic[i] > 0.0) &&  (maxrad_frozen[j] > 0.0)) ||
+        // radius info about both i and j exist
+        ((maxrad_frozen[i] > 0.0)  && (maxrad_dynamic[j] > 0.0))) {
+      cutoff = maxrad_dynamic[i]+maxrad_dynamic[j];
+      pulloff = 0.0;
+      if (normal_model[i][j] == JKR) {
+        pulloff = pulloff_distance(maxrad_dynamic[i], maxrad_dynamic[j], i, j);
+        cutoff += pulloff;
+      }
+
+      if (normal_model[i][j] == JKR)
+        pulloff = pulloff_distance(maxrad_frozen[i], maxrad_dynamic[j], i, j);
+      cutoff = MAX(cutoff, maxrad_frozen[i]+maxrad_dynamic[j]+pulloff);
+
+      if (normal_model[i][j] == JKR)
+        pulloff = pulloff_distance(maxrad_dynamic[i], maxrad_frozen[j], i, j);
+      cutoff = MAX(cutoff,maxrad_dynamic[i]+maxrad_frozen[j]+pulloff);
+
+    } else {
+
+      // radius info about either i or j does not exist
+      // (i.e. not present and not about to get poured;
+      // set to largest value to not interfere with neighbor list)
+
+      double cutmax = 0.0;
+      for (int k = 1; k <= atom->ntypes; k++) {
+        cutmax = MAX(cutmax,2.0*maxrad_dynamic[k]);
+        cutmax = MAX(cutmax,2.0*maxrad_frozen[k]);
+      }
+      cutoff = cutmax;
+    }
+  } else if (cutoff_type[i][j] > 0) {
+    cutoff = cutoff_type[i][j];
+  } else if (cutoff_global > 0) {
+    cutoff = cutoff_global;
+  }
+
+  return cutoff;
+}
+
+/* ----------------------------------------------------------------------
+   proc 0 writes to restart file
+------------------------------------------------------------------------- */
+
+void PairGranular::write_restart(FILE *fp)
+{
+  int i,j;
+  for (i = 1; i <= atom->ntypes; i++) {
+    for (j = i; j <= atom->ntypes; j++) {
+      fwrite(&setflag[i][j],sizeof(int),1,fp);
+      if (setflag[i][j]) {
+        fwrite(&normal_model[i][j],sizeof(int),1,fp);
+        fwrite(&damping_model[i][j],sizeof(int),1,fp);
+        fwrite(&tangential_model[i][j],sizeof(int),1,fp);
+        fwrite(&roll_model[i][j],sizeof(int),1,fp);
+        fwrite(&twist_model[i][j],sizeof(int),1,fp);
+        fwrite(&normal_coeffs[i][j],sizeof(double),4,fp);
+        fwrite(&tangential_coeffs[i][j],sizeof(double),3,fp);
+        fwrite(&roll_coeffs[i][j],sizeof(double),3,fp);
+        fwrite(&twist_coeffs[i][j],sizeof(double),3,fp);
+        fwrite(&cut[i][j],sizeof(double),1,fp);
+      }
+    }
+  }
+}
+
+/* ----------------------------------------------------------------------
+   proc 0 reads from restart file, bcasts
+------------------------------------------------------------------------- */
+
+void PairGranular::read_restart(FILE *fp)
+{
+  allocate();
+  int i,j;
+  int me = comm->me;
+  for (i = 1; i <= atom->ntypes; i++) {
+    for (j = i; j <= atom->ntypes; j++) {
+      if (me == 0) fread(&setflag[i][j],sizeof(int),1,fp);
+      MPI_Bcast(&setflag[i][j],1,MPI_INT,0,world);
+      if (setflag[i][j]) {
+        if (me == 0) {
+          fread(&normal_model[i][j],sizeof(int),1,fp);
+          fread(&damping_model[i][j],sizeof(int),1,fp);
+          fread(&tangential_model[i][j],sizeof(int),1,fp);
+          fread(&roll_model[i][j],sizeof(int),1,fp);
+          fread(&twist_model[i][j],sizeof(int),1,fp);
+          fread(&normal_coeffs[i][j],sizeof(double),4,fp);
+          fread(&tangential_coeffs[i][j],sizeof(double),3,fp);
+          fread(&roll_coeffs[i][j],sizeof(double),3,fp);
+          fread(&twist_coeffs[i][j],sizeof(double),3,fp);
+          fread(&cut[i][j],sizeof(double),1,fp);
+        }
+        MPI_Bcast(&normal_model[i][j],1,MPI_INT,0,world);
+        MPI_Bcast(&damping_model[i][j],1,MPI_INT,0,world);
+        MPI_Bcast(&tangential_model[i][j],1,MPI_INT,0,world);
+        MPI_Bcast(&roll_model[i][j],1,MPI_INT,0,world);
+        MPI_Bcast(&twist_model[i][j],1,MPI_INT,0,world);
+        MPI_Bcast(&normal_coeffs[i][j],4,MPI_DOUBLE,0,world);
+        MPI_Bcast(&tangential_coeffs[i][j],3,MPI_DOUBLE,0,world);
+        MPI_Bcast(&roll_coeffs[i][j],3,MPI_DOUBLE,0,world);
+        MPI_Bcast(&twist_coeffs[i][j],3,MPI_DOUBLE,0,world);
+        MPI_Bcast(&cut[i][j],1,MPI_DOUBLE,0,world);
+      }
+    }
+  }
+}
+
+/* ---------------------------------------------------------------------- */
+
+void PairGranular::reset_dt()
+{
+  dt = update->dt;
+}
+
+/* ---------------------------------------------------------------------- */
+
+double PairGranular::single(int i, int j, int itype, int jtype,
+                            double rsq, double /* factor_coul */,
+                            double /* factor_lj */, double &fforce)
+{
+  double radi,radj,radsum;
+  double r,rinv,delx,dely,delz, nx, ny, nz, Reff;
+  double dR, dR2;
+  double vr1,vr2,vr3,vnnr,vn1,vn2,vn3,vt1,vt2,vt3,wr1,wr2,wr3;
+  double vtr1,vtr2,vtr3,vrel;
+  double mi,mj,meff;
+  double relrot1,relrot2,relrot3,vrl1,vrl2,vrl3;
+
+  double knfac, damp_normal, damp_normal_prefactor;
+  double k_tangential, damp_tangential;
+  double Fne, Ft, Fdamp, Fntot, Fncrit, Fscrit, Frcrit;
+  double fs, fs1, fs2, fs3;
+
+  // for JKR
+  double R2, coh, F_pulloff, delta_pulloff, dist_pulloff, a, a2, E;
+  double delta, t0, t1, t2, t3, t4, t5, t6;
+  double sqrt1, sqrt2, sqrt3;
+
+  // rolling
+  double k_roll, damp_roll;
+  double rollmag;
+  double fr, fr1, fr2, fr3;
+
+  // twisting
+  double k_twist, damp_twist, mu_twist;
+  double signtwist, magtwist, magtortwist, Mtcrit;
+
+  double shrmag;
+  int jnum;
+  int *jlist;
+  double *history,*allhistory;
+
+  double *radius = atom->radius;
+  radi = radius[i];
+  radj = radius[j];
+  radsum = radi + radj;
+  Reff = radi*radj/radsum;
+
+  bool touchflag;
+  E = normal_coeffs[itype][jtype][0];
+  if (normal_model[itype][jtype] == JKR) {
+    E *= THREEQUARTERS;
+    R2 = Reff*Reff;
+    coh = normal_coeffs[itype][jtype][3];
+    a = cbrt(9.0*MY_PI*coh*R2/(4*E));
+    delta_pulloff = a*a/Reff - 2*sqrt(MY_PI*coh*a/E);
+    dist_pulloff = radsum+delta_pulloff;
+    touchflag = (rsq <= dist_pulloff*dist_pulloff);
+  } else touchflag = (rsq <= radsum*radsum);
+
+  if (!touchflag) {
+    fforce = 0.0;
+    for (int m = 0; m < single_extra; m++) svector[m] = 0.0;
+    return 0.0;
+  }
+
+  double **x = atom->x;
+  delx = x[i][0] - x[j][0];
+  dely = x[i][1] - x[j][1];
+  delz = x[i][2] - x[j][2];
+  r = sqrt(rsq);
+  rinv = 1.0/r;
+
+  nx = delx*rinv;
+  ny = dely*rinv;
+  nz = delz*rinv;
+
+  // relative translational velocity
+
+  double **v = atom->v;
+  vr1 = v[i][0] - v[j][0];
+  vr2 = v[i][1] - v[j][1];
+  vr3 = v[i][2] - v[j][2];
+
+  // normal component
+
+  vnnr = vr1*nx + vr2*ny + vr3*nz;
+  vn1 = nx*vnnr;
+  vn2 = ny*vnnr;
+  vn3 = nz*vnnr;
+
+  double *rmass = atom->rmass;
+  int *mask = atom->mask;
+  mi = rmass[i];
+  mj = rmass[j];
+  if (fix_rigid) {
+    if (mass_rigid[i] > 0.0) mi = mass_rigid[i];
+    if (mass_rigid[j] > 0.0) mj = mass_rigid[j];
+  }
+
+  meff = mi*mj / (mi+mj);
+  if (mask[i] & freeze_group_bit) meff = mj;
+  if (mask[j] & freeze_group_bit) meff = mi;
+
+  delta = radsum - r;
+  dR = delta*Reff;
+
+  // tangential component
+
+  vt1 = vr1 - vn1;
+  vt2 = vr2 - vn2;
+  vt3 = vr3 - vn3;
+
+  // relative rotational velocity
+
+  double **omega = atom->omega;
+  wr1 = (radi*omega[i][0] + radj*omega[j][0]);
+  wr2 = (radi*omega[i][1] + radj*omega[j][1]);
+  wr3 = (radi*omega[i][2] + radj*omega[j][2]);
+
+  // meff = effective mass of pair of particles
+  // if I or J part of rigid body, use body mass
+  // if I or J is frozen, meff is other particle
+
+  mi = rmass[i];
+  mj = rmass[j];
+  if (fix_rigid) {
+    // NOTE: ensure mass_rigid is current for owned+ghost atoms?
+    if (mass_rigid[i] > 0.0) mi = mass_rigid[i];
+    if (mass_rigid[j] > 0.0) mj = mass_rigid[j];
+  }
+
+  meff = mi*mj / (mi+mj);
+  if (mask[i] & freeze_group_bit) meff = mj;
+  if (mask[j] & freeze_group_bit) meff = mi;
+
+  delta = radsum - r;
+  dR = delta*Reff;
+  if (normal_model[itype][jtype] == JKR) {
+    dR2 = dR*dR;
+    t0 = coh*coh*R2*R2*E;
+    t1 = PI27SQ*t0;
+    t2 = 8*dR*dR2*E*E*E;
+    t3 = 4*dR2*E;
+    // in case sqrt(0) < 0 due to precision issues
+    sqrt1 = MAX(0, t0*(t1+2*t2));
+    t4 = cbrt(t1+t2+THREEROOT3*MY_PI*sqrt(sqrt1));
+    t5 = t3/t4 + t4/E;
+    sqrt2 = MAX(0, 2*dR + t5);
+    t6 = sqrt(sqrt2);
+    sqrt3 = MAX(0, 4*dR - t5 + SIXROOT6*coh*MY_PI*R2/(E*t6));
+    a = INVROOT6*(t6 + sqrt(sqrt3));
+    a2 = a*a;
+    knfac = normal_coeffs[itype][jtype][0]*a;
+    Fne = knfac*a2/Reff - MY_2PI*a2*sqrt(4*coh*E/(MY_PI*a));
+  } else {
+    knfac = E;
+    Fne = knfac*delta;
+    a = sqrt(dR);
+    if (normal_model[itype][jtype] != HOOKE) {
+      Fne *= a;
+      knfac *= a;
+    }
+    if (normal_model[itype][jtype] == DMT)
+      Fne -= 4*MY_PI*normal_coeffs[itype][jtype][3]*Reff;
+  }
+
+  if (damping_model[itype][jtype] == VELOCITY) {
+    damp_normal = normal_coeffs[itype][jtype][1];
+  } else if (damping_model[itype][jtype] == VISCOELASTIC) {
+    damp_normal = normal_coeffs[itype][jtype][1]*a*meff;
+  } else if (damping_model[itype][jtype] == TSUJI) {
+    damp_normal = normal_coeffs[itype][jtype][1]*sqrt(meff*knfac);
+  }
+
+  damp_normal_prefactor = normal_coeffs[itype][jtype][1]*damp_normal;
+  Fdamp = -damp_normal_prefactor*vnnr;
+
+  Fntot = Fne + Fdamp;
+
+  jnum = list->numneigh[i];
+  jlist = list->firstneigh[i];
+
+  if (use_history) {
+    allhistory = fix_history->firstvalue[i];
+    for (int jj = 0; jj < jnum; jj++) {
+      neighprev++;
+      if (neighprev >= jnum) neighprev = 0;
+      if (jlist[neighprev] == j) break;
+    }
+    history = &allhistory[size_history*neighprev];
+  }
+
+  //****************************************
+  // tangential force, including history effects
+  //****************************************
+
+  // tangential component
+  vt1 = vr1 - vn1;
+  vt2 = vr2 - vn2;
+  vt3 = vr3 - vn3;
+
+  // relative rotational velocity
+  wr1 = (radi*omega[i][0] + radj*omega[j][0]);
+  wr2 = (radi*omega[i][1] + radj*omega[j][1]);
+  wr3 = (radi*omega[i][2] + radj*omega[j][2]);
+
+  // relative tangential velocities
+  vtr1 = vt1 - (nz*wr2-ny*wr3);
+  vtr2 = vt2 - (nx*wr3-nz*wr1);
+  vtr3 = vt3 - (ny*wr1-nx*wr2);
+  vrel = vtr1*vtr1 + vtr2*vtr2 + vtr3*vtr3;
+  vrel = sqrt(vrel);
+
+  if (normal_model[itype][jtype] == JKR) {
+    F_pulloff = 3*MY_PI*coh*Reff;
+    Fncrit = fabs(Fne + 2*F_pulloff);
+  } else if (normal_model[itype][jtype] == DMT) {
+    F_pulloff = 4*MY_PI*coh*Reff;
+    Fncrit = fabs(Fne + 2*F_pulloff);
+  } else {
+    Fncrit = fabs(Fntot);
+  }
+
+  //------------------------------
+  // tangential forces
+  //------------------------------
+  k_tangential = tangential_coeffs[itype][jtype][0];
+  damp_tangential = tangential_coeffs[itype][jtype][1]*damp_normal_prefactor;
+
+  if (tangential_history) {
+    if (tangential_model[itype][jtype] == TANGENTIAL_MINDLIN) {
+      k_tangential *= a;
+    } else if (tangential_model[itype][jtype] == TANGENTIAL_MINDLIN_RESCALE) {
+      k_tangential *= a;
+      // on unloading, rescale the shear displacements
+      if (a < history[3]) {
+        double factor = a/history[3];
+        history[0] *= factor;
+        history[1] *= factor;
+        history[2] *= factor;
+      }
+    }
+
+    shrmag = sqrt(history[0]*history[0] + history[1]*history[1] +
+        history[2]*history[2]);
+
+    // tangential forces = history + tangential velocity damping
+    fs1 = -k_tangential*history[0] - damp_tangential*vtr1;
+    fs2 = -k_tangential*history[1] - damp_tangential*vtr2;
+    fs3 = -k_tangential*history[2] - damp_tangential*vtr3;
+
+    // rescale frictional displacements and forces if needed
+    Fscrit = tangential_coeffs[itype][jtype][2] * Fncrit;
+    fs = sqrt(fs1*fs1 + fs2*fs2 + fs3*fs3);
+    if (fs > Fscrit) {
+      if (shrmag != 0.0) {
+        history[0] = -1.0/k_tangential*(Fscrit*fs1/fs + damp_tangential*vtr1);
+        history[1] = -1.0/k_tangential*(Fscrit*fs2/fs + damp_tangential*vtr2);
+        history[2] = -1.0/k_tangential*(Fscrit*fs3/fs + damp_tangential*vtr3);
+        fs1 *= Fscrit/fs;
+        fs2 *= Fscrit/fs;
+        fs3 *= Fscrit/fs;
+      } else fs1 = fs2 = fs3 = 0.0;
+    }
+
+  // classic pair gran/hooke (no history)
+  } else {
+    fs = meff*damp_tangential*vrel;
+    if (vrel != 0.0) Ft = MIN(Fne,fs) / vrel;
+    else Ft = 0.0;
+    fs1 = -Ft*vtr1;
+    fs2 = -Ft*vtr2;
+    fs3 = -Ft*vtr3;
+  }
+
+  //****************************************
+  // rolling resistance
+  //****************************************
+
+  if (roll_model[itype][jtype] != ROLL_NONE) {
+    relrot1 = omega[i][0] - omega[j][0];
+    relrot2 = omega[i][1] - omega[j][1];
+    relrot3 = omega[i][2] - omega[j][2];
+
+    // rolling velocity, see eq. 31 of Wang et al, Particuology v 23, p 49 (2015)
+    // this is different from the Marshall papers,
+    // which use the Bagi/Kuhn formulation
+    // for rolling velocity (see Wang et al for why the latter is wrong)
+
+    vrl1 = Reff*(relrot2*nz - relrot3*ny); //- 0.5*((radj-radi)/radsum)*vtr1;
+    vrl2 = Reff*(relrot3*nx - relrot1*nz); //- 0.5*((radj-radi)/radsum)*vtr2;
+    vrl3 = Reff*(relrot1*ny - relrot2*nx); //- 0.5*((radj-radi)/radsum)*vtr3;
+
+    int rhist0 = roll_history_index;
+    int rhist1 = rhist0 + 1;
+    int rhist2 = rhist1 + 1;
+
+    // rolling displacement
+    rollmag = sqrt(history[rhist0]*history[rhist0] +
+        history[rhist1]*history[rhist1] +
+        history[rhist2]*history[rhist2]);
+
+    k_roll = roll_coeffs[itype][jtype][0];
+    damp_roll = roll_coeffs[itype][jtype][1];
+    fr1 = -k_roll*history[rhist0] - damp_roll*vrl1;
+    fr2 = -k_roll*history[rhist1] - damp_roll*vrl2;
+    fr3 = -k_roll*history[rhist2] - damp_roll*vrl3;
+
+    // rescale frictional displacements and forces if needed
+    Frcrit = roll_coeffs[itype][jtype][2] * Fncrit;
+
+    fr = sqrt(fr1*fr1 + fr2*fr2 + fr3*fr3);
+    if (fr > Frcrit) {
+      if (rollmag != 0.0) {
+        fr1 *= Frcrit/fr;
+        fr2 *= Frcrit/fr;
+        fr3 *= Frcrit/fr;
+      } else fr1 = fr2 = fr3 = 0.0;
+    }
+
+  }
+
+  //****************************************
+  // twisting torque, including history effects
+  //****************************************
+
+  if (twist_model[itype][jtype] != TWIST_NONE) {
+    // omega_T (eq 29 of Marshall)
+    magtwist = relrot1*nx + relrot2*ny + relrot3*nz;
+    if (twist_model[itype][jtype] == TWIST_MARSHALL) {
+      k_twist = 0.5*k_tangential*a*a;; //eq 32
+      damp_twist = 0.5*damp_tangential*a*a;
+      mu_twist = TWOTHIRDS*a*tangential_coeffs[itype][jtype][2];;
+    } else {
+      k_twist = twist_coeffs[itype][jtype][0];
+      damp_twist = twist_coeffs[itype][jtype][1];
+      mu_twist = twist_coeffs[itype][jtype][2];
+    }
+    // M_t torque (eq 30)
+    magtortwist = -k_twist*history[twist_history_index] - damp_twist*magtwist;
+    signtwist = (magtwist > 0) - (magtwist < 0);
+    Mtcrit = mu_twist*Fncrit; // critical torque (eq 44)
+    if (fabs(magtortwist) > Mtcrit) {
+      magtortwist = -Mtcrit * signtwist; // eq 34
+    }
+  }
+
+  // set single_extra quantities
+
+  svector[0] = fs1;
+  svector[1] = fs2;
+  svector[2] = fs3;
+  svector[3] = fs;
+  svector[4] = fr1;
+  svector[5] = fr2;
+  svector[6] = fr3;
+  svector[7] = fr;
+  svector[8] = magtortwist;
+  svector[9] = delx;
+  svector[10] = dely;
+  svector[11] = delz;
+  return 0.0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int PairGranular::pack_forward_comm(int n, int *list, double *buf,
+                                    int /* pbc_flag */, int * /* pbc */)
+{
+  int i,j,m;
+
+  m = 0;
+  for (i = 0; i < n; i++) {
+    j = list[i];
+    buf[m++] = mass_rigid[j];
+  }
+  return m;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void PairGranular::unpack_forward_comm(int n, int first, double *buf)
+{
+  int i,m,last;
+
+  m = 0;
+  last = first + n;
+  for (i = first; i < last; i++)
+    mass_rigid[i] = buf[m++];
+}
+
+/* ----------------------------------------------------------------------
+   memory usage of local atom-based arrays
+------------------------------------------------------------------------- */
+
+double PairGranular::memory_usage()
+{
+  double bytes = nmax * sizeof(double);
+  return bytes;
+}
+
+/* ----------------------------------------------------------------------
+   mixing of Young's modulus (E)
+------------------------------------------------------------------------- */
+
+double PairGranular::mix_stiffnessE(double Eii, double Ejj,
+                                    double poisii, double poisjj)
+{
+  return 1/((1-poisii*poisii)/Eii+(1-poisjj*poisjj)/Ejj);
+}
+
+/* ----------------------------------------------------------------------
+   mixing of shear modulus (G)
+------------------------------------------------------------------------ */
+
+double PairGranular::mix_stiffnessG(double Eii, double Ejj,
+                                    double poisii, double poisjj)
+{
+  return 1/((2*(2-poisii)*(1+poisii)/Eii) + (2*(2-poisjj)*(1+poisjj)/Ejj));
+}
+
+/* ----------------------------------------------------------------------
+   mixing of everything else
+------------------------------------------------------------------------- */
+
+double PairGranular::mix_geom(double valii, double valjj)
+{
+  return sqrt(valii*valjj);
+}
+
+
+/* ----------------------------------------------------------------------
+   compute pull-off distance (beyond contact) for a given radius and atom type
+------------------------------------------------------------------------- */
+
+double PairGranular::pulloff_distance(double radi, double radj,
+                                      int itype, int jtype)
+{
+  double E, coh, a, Reff;
+  Reff = radi*radj/(radi+radj);
+  if (Reff <= 0) return 0;
+  coh = normal_coeffs[itype][itype][3];
+  E = normal_coeffs[itype][jtype][0]*THREEQUARTERS;
+  a = cbrt(9*MY_PI*coh*Reff/(4*E));
+  return a*a/Reff - 2*sqrt(MY_PI*coh*a/E);
+}
+
+/* ----------------------------------------------------------------------
+   transfer history during fix/neigh/history exchange
+   only needed if any history entries i-j are not just negative of j-i entries
+------------------------------------------------------------------------- */
+
+void PairGranular::transfer_history(double* source, double* target)
+{
+  for (int i = 0; i < size_history; i++)
+    target[i] = history_transfer_factors[i]*source[i];
+}
diff --git a/src/GRANULAR/pair_granular.h b/src/GRANULAR/pair_granular.h
new file mode 100644
index 0000000000..d799acb733
--- /dev/null
+++ b/src/GRANULAR/pair_granular.h
@@ -0,0 +1,114 @@
+/* ----------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+#ifdef PAIR_CLASS
+
+PairStyle(granular,PairGranular)
+
+#else
+
+#ifndef LMP_PAIR_GRANULAR_H
+#define LMP_PAIR_GRANULAR_H
+
+#include "pair.h"
+
+namespace LAMMPS_NS {
+
+class PairGranular : public Pair {
+ public:
+  PairGranular(class LAMMPS *);
+  ~PairGranular();
+  void compute(int, int);
+  void settings(int, char **);
+  void coeff(int, char **);
+  void init_style();
+  double init_one(int, int);
+  void write_restart(FILE *);
+  void read_restart(FILE *);
+  void reset_dt();
+  double single(int, int, int, int, double, double, double, double &);
+  int pack_forward_comm(int, int *, double *, int, int *);
+  void unpack_forward_comm(int, int, double *);
+  double memory_usage();
+
+ protected:
+  double dt;
+  int freeze_group_bit;
+  int use_history;
+
+  int neighprev;
+  double *onerad_dynamic,*onerad_frozen;
+  double *maxrad_dynamic,*maxrad_frozen;
+  double **cut;
+
+  class FixNeighHistory *fix_history;
+
+  // storage of rigid body masses for use in granular interactions
+
+  class Fix *fix_rigid;    // ptr to rigid body fix, NULL if none
+  double *mass_rigid;      // rigid mass for owned+ghost atoms
+  int nmax;                // allocated size of mass_rigid
+
+  void allocate();
+  void transfer_history(double*, double*);
+
+ private:
+  int size_history;
+  int *history_transfer_factors;
+
+  // model choices
+  int **normal_model, **damping_model;
+  int **tangential_model, **roll_model, **twist_model;
+
+  // history flags
+  int normal_history, tangential_history, roll_history, twist_history;
+
+  // indices of history entries
+  int normal_history_index;
+  int tangential_history_index;
+  int roll_history_index;
+  int twist_history_index;
+
+  // per-type material coefficients
+  double **Emod, **poiss, **Gmod;
+
+  // per-type coefficients, set in pair coeff command
+  double ***normal_coeffs;
+  double ***tangential_coeffs;
+  double ***roll_coeffs;
+  double ***twist_coeffs;
+
+  // optional user-specified global cutoff, per-type user-specified cutoffs
+  double **cutoff_type;
+  double cutoff_global;
+
+  double mix_stiffnessE(double, double, double, double);
+  double mix_stiffnessG(double, double, double, double);
+  double mix_geom(double, double);
+  double pulloff_distance(double, double, int, int);
+};
+
+}
+
+#endif
+#endif
+
+/* ERROR/WARNING messages:
+
+E: Illegal ... command
+
+Self-explanatory.  Check the input script syntax and compare to the
+documentation for the command.  You can use -echo screen as a
+command-line option when running LAMMPS to see the offending line.
+
+ */
diff --git a/src/KIM/kim_query.cpp b/src/KIM/kim_query.cpp
new file mode 100644
index 0000000000..fedc976110
--- /dev/null
+++ b/src/KIM/kim_query.cpp
@@ -0,0 +1,237 @@
+/* ----------------------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+
+/* ----------------------------------------------------------------------
+   Contributing authors: Axel Kohlmeyer (Temple U),
+                         Ryan S. Elliott (UMN)
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   This program is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the Free
+   Software Foundation; either version 2 of the License, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful, but WITHOUT
+   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+   FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+   more details.
+
+   You should have received a copy of the GNU General Public License along with
+   this program; if not, see <https://www.gnu.org/licenses>.
+
+   Linking LAMMPS statically or dynamically with other modules is making a
+   combined work based on LAMMPS. Thus, the terms and conditions of the GNU
+   General Public License cover the whole combination.
+
+   In addition, as a special exception, the copyright holders of LAMMPS give
+   you permission to combine LAMMPS with free software programs or libraries
+   that are released under the GNU LGPL and with code included in the standard
+   release of the "kim-api" under the CDDL (or modified versions of such code,
+   with unchanged license). You may copy and distribute such a system following
+   the terms of the GNU GPL for LAMMPS and the licenses of the other code
+   concerned, provided that you include the source code of that other code
+   when and as the GNU GPL requires distribution of source code.
+
+   Note that people who make modified versions of LAMMPS are not obligated to
+   grant this special exception for their modified versions; it is their choice
+   whether to do so. The GNU General Public License gives permission to release
+   a modified version without this exception; this exception also makes it
+   possible to release a modified version which carries forward this exception.
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   Designed for use with the kim-api-2.0.2 (and newer) package
+------------------------------------------------------------------------- */
+
+#include <mpi.h>
+#include <cstring>
+#include <string>
+#include "kim_query.h"
+#include "comm.h"
+#include "error.h"
+#include "input.h"
+#include "variable.h"
+
+#if defined(LMP_KIM_CURL)
+#include <sys/types.h>
+#include <curl/curl.h>
+#endif
+
+using namespace LAMMPS_NS;
+
+#if defined(LMP_KIM_CURL)
+
+struct WriteBuf {
+  char *dataptr;
+  size_t sizeleft;
+};
+
+static char *do_query(char *, int, char **, int, MPI_Comm);
+static size_t write_callback(void *, size_t, size_t, void *);
+
+#endif
+
+/* ---------------------------------------------------------------------- */
+
+void KimQuery::command(int narg, char **arg)
+{
+  char *varname, *function, *value;
+
+  if (narg < 2) error->all(FLERR,"Illegal kim_query command");
+
+  varname = arg[0];
+  function = arg[1];
+
+#if defined(LMP_KIM_CURL)
+
+  value = do_query(function, narg-2, arg+2, comm->me, world);
+
+  // check for valid result
+  // on error the content of "value" is a '\0' byte
+  // as the first element, and then the error message
+  // that was returned by the web server
+
+  if (0 == strlen(value)) {
+    char errmsg[512];
+
+    sprintf(errmsg,"OpenKIM query failed: %s",value+1);
+        error->all(FLERR,errmsg);
+  }
+
+  char **varcmd = new char*[3];
+  varcmd[0] = varname;
+  varcmd[1] = (char *) "string";
+  varcmd[2] = value;
+
+  input->variable->set(3,varcmd);
+
+  delete[] varcmd;
+  delete[] value;
+#else
+  error->all(FLERR,"Cannot use 'kim_query' command when KIM package "
+             "is compiled without support for libcurl");
+#endif
+}
+
+#if defined(LMP_KIM_CURL)
+
+// copy data to the user provided data structure, optionally in increments
+
+size_t write_callback(void *data, size_t size, size_t nmemb, void *userp)
+{
+  struct WriteBuf *buf = (struct WriteBuf *)userp;
+  size_t buffer_size = size*nmemb;
+
+  // copy chunks into the buffer for as long as there is space left
+  if (buf->sizeleft) {
+    size_t copy_this_much = buf->sizeleft;
+    if (copy_this_much > buffer_size)
+      copy_this_much = buffer_size;
+    memcpy(buf->dataptr, data, copy_this_much);
+
+    buf->dataptr += copy_this_much;
+    buf->sizeleft -= copy_this_much;
+    return copy_this_much;
+  }
+  return 0; // done
+}
+
+char *do_query(char *qfunction, int narg, char **arg, int rank, MPI_Comm comm)
+{
+  char value[512], *retval;
+
+  // run the web query from rank 0 only
+
+  if (rank == 0) {
+    CURL *handle;
+    CURLcode res;
+
+    // set up and clear receive buffer
+
+    struct WriteBuf buf;
+    buf.dataptr = value;
+    buf.sizeleft = 511;
+    memset(value,0,512);
+
+    // create curl web query instance
+    curl_global_init(CURL_GLOBAL_DEFAULT);
+    handle = curl_easy_init();
+
+    if (handle) {
+      std::string url("https://query.openkim.org/api/");
+      url += qfunction;
+
+      std::string query(arg[0]);
+      for (int i=1; i < narg; ++i) {
+        query += '&';
+        query += arg[i];
+      }
+
+#if LMP_DEBUG_CURL
+      curl_easy_setopt(handle, CURLOPT_VERBOSE, 1L);
+#endif
+
+#if defined(LMP_NO_SSL_CHECK)
+      // disable verifying SSL certificate and host name
+      curl_easy_setopt(handle, CURLOPT_SSL_VERIFYPEER, 0L);
+      curl_easy_setopt(handle, CURLOPT_SSL_VERIFYHOST, 0L);
+#endif
+
+      curl_easy_setopt(handle, CURLOPT_URL, url.c_str());
+      curl_easy_setopt(handle, CURLOPT_FOLLOWLOCATION, 1L);
+      curl_easy_setopt(handle, CURLOPT_POSTFIELDS, query.c_str());
+
+      curl_easy_setopt(handle, CURLOPT_WRITEFUNCTION,write_callback);
+      curl_easy_setopt(handle, CURLOPT_WRITEDATA,&buf);
+
+      // perform OpenKIM query and check for errors
+      res = curl_easy_perform(handle);
+      if (res != CURLE_OK) {
+        // on error we return an "empty" string but add error message after it
+        value[0]= '\0';
+        strcpy(value+1,curl_easy_strerror(res));
+      }
+      curl_easy_cleanup(handle);
+    }
+    curl_global_cleanup();
+  }
+  MPI_Bcast(value, 512, MPI_CHAR, 0, comm);
+
+  // we must make a proper copy of the query, as the stack allocation
+  // for "value" will go out of scope. a valid query has a '[' as
+  // the first character. skip over it (and the last character ']', too)
+  // an error messages starts with a '\0' character. copy that and
+  // the remaining string, as that is the error message.
+
+  if (value[0] == '[') {
+    int len = strlen(value)-1;
+    retval = new char[len];
+    value[len] = '\0';
+    strcpy(retval,value+1);
+  } else if (value[0] == '\0') {
+    int len = strlen(value+1)+2;
+    retval = new char[len];
+    retval[0] = '\0';
+    strcpy(retval+1,value+1);
+  } else {
+    // unknown response type. we should not get here.
+    // copy response without modifications.
+    int len = strlen(value)+1;
+    retval = new char[len];
+    strcpy(retval,value);
+  }
+  return retval;
+}
+#endif
diff --git a/src/KIM/kim_query.h b/src/KIM/kim_query.h
new file mode 100644
index 0000000000..3644e4519b
--- /dev/null
+++ b/src/KIM/kim_query.h
@@ -0,0 +1,85 @@
+/* -*- c++ -*- ----------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   Contributing authors: Axel Kohlmeyer (Temple U),
+                         Ryan S. Elliott (UMN)
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   This program is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by the Free
+   Software Foundation; either version 2 of the License, or (at your option)
+   any later version.
+
+   This program is distributed in the hope that it will be useful, but WITHOUT
+   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+   FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+   more details.
+
+   You should have received a copy of the GNU General Public License along with
+   this program; if not, see <https://www.gnu.org/licenses>.
+
+   Linking LAMMPS statically or dynamically with other modules is making a
+   combined work based on LAMMPS. Thus, the terms and conditions of the GNU
+   General Public License cover the whole combination.
+
+   In addition, as a special exception, the copyright holders of LAMMPS give
+   you permission to combine LAMMPS with free software programs or libraries
+   that are released under the GNU LGPL and with code included in the standard
+   release of the "kim-api" under the CDDL (or modified versions of such code,
+   with unchanged license). You may copy and distribute such a system following
+   the terms of the GNU GPL for LAMMPS and the licenses of the other code
+   concerned, provided that you include the source code of that other code
+   when and as the GNU GPL requires distribution of source code.
+
+   Note that people who make modified versions of LAMMPS are not obligated to
+   grant this special exception for their modified versions; it is their choice
+   whether to do so. The GNU General Public License gives permission to release
+   a modified version without this exception; this exception also makes it
+   possible to release a modified version which carries forward this exception.
+------------------------------------------------------------------------- */
+
+/* ----------------------------------------------------------------------
+   Designed for use with the kim-api-2.0.2 (and newer) package
+------------------------------------------------------------------------- */
+
+#ifdef COMMAND_CLASS
+
+CommandStyle(kim_query,KimQuery)
+
+#else
+
+#ifndef LMP_KIM_QUERY_H
+#define LMP_KIM_QUERY_H
+
+#include "pointers.h"
+
+namespace LAMMPS_NS {
+
+class KimQuery : protected Pointers {
+ public:
+  KimQuery(class LAMMPS *lmp) : Pointers(lmp) {};
+  void command(int, char **);
+
+};
+
+}
+
+#endif
+#endif
+
+/* ERROR/WARNING messages:
+
+
+*/
diff --git a/src/KIM/pair_kim.cpp b/src/KIM/pair_kim.cpp
index a4517b848c..a1c13ae81f 100644
--- a/src/KIM/pair_kim.cpp
+++ b/src/KIM/pair_kim.cpp
@@ -50,7 +50,7 @@
 ------------------------------------------------------------------------- */
 
 /* ----------------------------------------------------------------------
-   Designed for use with the kim-api-v2-2.0.0 (and newer) package
+   Designed for use with the kim-api-2.0.2 (and newer) package
 ------------------------------------------------------------------------- */
 
 #include <cstring>
@@ -189,12 +189,7 @@ void PairKIM::set_contributing()
 
 void PairKIM::compute(int eflag , int vflag)
 {
-   int kimerror;
-
-   if (eflag || vflag)
-      ev_setup(eflag,vflag);
-   else
-      ev_unset();
+   ev_init(eflag,vflag);
 
    // grow kim_particleSpecies and kim_particleContributing array if necessary
    // needs to be atom->nmax in length
@@ -241,7 +236,7 @@ void PairKIM::compute(int eflag , int vflag)
    lmps_local_tot_num_atoms = (int) nall;
 
    // compute via KIM model
-   kimerror = KIM_Model_Compute(pkim, pargs);
+   int kimerror = KIM_Model_Compute(pkim, pargs);
    if (kimerror) error->all(FLERR,"KIM Compute returned error");
 
    // compute virial before reverse comm!
@@ -316,7 +311,7 @@ void PairKIM::settings(int narg, char **arg)
                         (0 == strcmp("LAMMPSvirial", arg[0]))))
      {
        error->all(FLERR,"'KIMvirial' or 'LAMMPSvirial' not supported with "
-                  "kim-api-v2.");
+                  "kim-api.");
      }
      else
        error->all(FLERR,"Illegal pair_style command");
@@ -437,10 +432,9 @@ void PairKIM::coeff(int narg, char **arg)
    kim_particle_codes = new int[lmps_num_unique_elements];
    kim_particle_codes_ok = true;
    for(int i = 0; i < lmps_num_unique_elements; i++){
-      int kimerror;
       int supported;
       int code;
-      kimerror = KIM_Model_GetSpeciesSupportAndCode(
+      KIM_Model_GetSpeciesSupportAndCode(
           pkim,
           KIM_SpeciesName_FromString(lmps_unique_elements[i]),
           &supported,
@@ -471,8 +465,6 @@ void PairKIM::init_style()
    if (domain->dimension != 3)
       error->all(FLERR,"PairKIM only works with 3D problems");
 
-   int kimerror;
-
    // setup lmps_stripped_neigh_list for neighbors of one atom, if needed
    if (lmps_using_molecular) {
       memory->destroy(lmps_stripped_neigh_list);
@@ -484,7 +476,7 @@ void PairKIM::init_style()
       for (int i = 0; i < kim_number_of_neighbor_lists; ++i)
       {
         lmps_stripped_neigh_ptr[i]
-            = &(lmps_stripped_neigh_list[(i-1)*(neighbor->oneatom)]);
+            = &(lmps_stripped_neigh_list[i*(neighbor->oneatom)]);
       }
 
    }
@@ -679,9 +671,9 @@ void PairKIM::unpack_reverse_comm(int n, int *list, double *buf)
          va[j*6+4]+=buf[m++];
          va[j*6+5]+=buf[m++];
       }
+   } else {
+     ; // do nothing
    }
-   else
-      ;// do nothing
 
    return;
 }
@@ -723,11 +715,8 @@ int PairKIM::get_neigh(void const * const dataObject,
    *numberOfNeighbors = 0;
 
    NeighList * neiobj = Model->neighborLists[neighborListIndex];
-   int nAtoms = Model->lmps_local_tot_num_atoms;
 
-   int j, jj, inum, *ilist, *numneigh, **firstneigh;
-   inum = neiobj->inum;             //# of I atoms neighbors are stored for
-   ilist = neiobj->ilist;           //local indices of I atoms
+   int *numneigh, **firstneigh;
    numneigh = neiobj->numneigh;     // # of J neighbors for each I atom
    firstneigh = neiobj->firstneigh; // ptr to 1st J int value of each I atom
 
@@ -753,8 +742,6 @@ int PairKIM::get_neigh(void const * const dataObject,
 
 void PairKIM::kim_free()
 {
-   int kimerror;
-
    if (kim_init_ok)
    {
      int kimerror = KIM_Model_ComputeArgumentsDestroy(pkim, &pargs);
@@ -1046,10 +1033,10 @@ void PairKIM::set_kim_model_has_flags()
   for (int i = 0; i < numberOfComputeArgumentNames; ++i)
   {
     KIM_ComputeArgumentName computeArgumentName;
-    int kimerror = KIM_COMPUTE_ARGUMENT_NAME_GetComputeArgumentName(
+    KIM_COMPUTE_ARGUMENT_NAME_GetComputeArgumentName(
         i, &computeArgumentName);
     KIM_SupportStatus supportStatus;
-    kimerror = KIM_ComputeArguments_GetArgumentSupportStatus(
+    KIM_ComputeArguments_GetArgumentSupportStatus(
         pargs, computeArgumentName, &supportStatus);
 
     if (KIM_ComputeArgumentName_Equal(computeArgumentName,
@@ -1108,10 +1095,10 @@ void PairKIM::set_kim_model_has_flags()
   for (int i = 0; i < numberOfComputeCallbackNames; ++i)
   {
     KIM_ComputeCallbackName computeCallbackName;
-    int kimerror = KIM_COMPUTE_CALLBACK_NAME_GetComputeCallbackName(
+    KIM_COMPUTE_CALLBACK_NAME_GetComputeCallbackName(
         i, &computeCallbackName);
     KIM_SupportStatus supportStatus;
-    kimerror = KIM_ComputeArguments_GetCallbackSupportStatus(
+    KIM_ComputeArguments_GetCallbackSupportStatus(
         pargs, computeCallbackName, &supportStatus);
 
     if (KIM_SupportStatus_Equal(supportStatus, KIM_SUPPORT_STATUS_required))
diff --git a/src/KIM/pair_kim.h b/src/KIM/pair_kim.h
index a6f882347d..27bab6c687 100644
--- a/src/KIM/pair_kim.h
+++ b/src/KIM/pair_kim.h
@@ -50,7 +50,7 @@
 ------------------------------------------------------------------------- */
 
 /* ----------------------------------------------------------------------
-   Designed for use with the kim-api-v2-2.0.0 (and newer) package
+   Designed for use with the kim-api-2.0.2 (and newer) package
 ------------------------------------------------------------------------- */
 
 #ifdef PAIR_CLASS
@@ -182,9 +182,9 @@ E: KIM Compute returned error
 
 The KIM model was unable, for some reason, to complete the computation.
 
-E: 'KIMvirial' or 'LAMMPSvirial' not supported with kim-api-v2.
+E: 'KIMvirial' or 'LAMMPSvirial' not supported with kim-api.
 
-"KIMvirial or "LAMMPSvirial" found on the pair_style line.  These keys are not supported kim-api-v2. (The virial computation is always performed by LAMMPS.) Please remove these keys, make sure the KIM model you are using supports kim-api-v2, and rerun.
+"KIMvirial or "LAMMPSvirial" found on the pair_style line.  These keys are not supported kim-api. (The virial computation is always performed by LAMMPS.) Please remove these keys, make sure the KIM model you are using supports kim-api, and rerun.
 
 E: Illegal pair_style command
 
diff --git a/src/KOKKOS/angle_charmm_kokkos.cpp b/src/KOKKOS/angle_charmm_kokkos.cpp
index ec2955b28d..0f46c958d6 100644
--- a/src/KOKKOS/angle_charmm_kokkos.cpp
+++ b/src/KOKKOS/angle_charmm_kokkos.cpp
@@ -64,8 +64,7 @@ void AngleCharmmKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/angle_class2_kokkos.cpp b/src/KOKKOS/angle_class2_kokkos.cpp
index fe5b1895fe..836714764d 100644
--- a/src/KOKKOS/angle_class2_kokkos.cpp
+++ b/src/KOKKOS/angle_class2_kokkos.cpp
@@ -64,8 +64,7 @@ void AngleClass2Kokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/angle_cosine_kokkos.cpp b/src/KOKKOS/angle_cosine_kokkos.cpp
index 08faa254f4..4a4866948f 100644
--- a/src/KOKKOS/angle_cosine_kokkos.cpp
+++ b/src/KOKKOS/angle_cosine_kokkos.cpp
@@ -64,8 +64,7 @@ void AngleCosineKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/angle_harmonic_kokkos.cpp b/src/KOKKOS/angle_harmonic_kokkos.cpp
index 8cdab2063a..dbe705800c 100644
--- a/src/KOKKOS/angle_harmonic_kokkos.cpp
+++ b/src/KOKKOS/angle_harmonic_kokkos.cpp
@@ -64,8 +64,7 @@ void AngleHarmonicKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/bond_class2_kokkos.cpp b/src/KOKKOS/bond_class2_kokkos.cpp
index d84b3d390c..798fb41c92 100644
--- a/src/KOKKOS/bond_class2_kokkos.cpp
+++ b/src/KOKKOS/bond_class2_kokkos.cpp
@@ -60,8 +60,7 @@ void BondClass2Kokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/bond_fene_kokkos.cpp b/src/KOKKOS/bond_fene_kokkos.cpp
index d37943ba82..b5cdc1a05a 100644
--- a/src/KOKKOS/bond_fene_kokkos.cpp
+++ b/src/KOKKOS/bond_fene_kokkos.cpp
@@ -69,8 +69,7 @@ void BondFENEKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/bond_harmonic_kokkos.cpp b/src/KOKKOS/bond_harmonic_kokkos.cpp
index 6cdd4fe856..51a9fa4389 100644
--- a/src/KOKKOS/bond_harmonic_kokkos.cpp
+++ b/src/KOKKOS/bond_harmonic_kokkos.cpp
@@ -61,8 +61,7 @@ void BondHarmonicKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/dihedral_charmm_kokkos.cpp b/src/KOKKOS/dihedral_charmm_kokkos.cpp
index 3931309dc1..61ddcc425a 100644
--- a/src/KOKKOS/dihedral_charmm_kokkos.cpp
+++ b/src/KOKKOS/dihedral_charmm_kokkos.cpp
@@ -69,8 +69,7 @@ void DihedralCharmmKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/KOKKOS/dihedral_class2_kokkos.cpp b/src/KOKKOS/dihedral_class2_kokkos.cpp
index c7db07a6cb..98436bc696 100644
--- a/src/KOKKOS/dihedral_class2_kokkos.cpp
+++ b/src/KOKKOS/dihedral_class2_kokkos.cpp
@@ -69,8 +69,7 @@ void DihedralClass2Kokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/dihedral_opls_kokkos.cpp b/src/KOKKOS/dihedral_opls_kokkos.cpp
index 9d01cf1a54..f50dea2c36 100644
--- a/src/KOKKOS/dihedral_opls_kokkos.cpp
+++ b/src/KOKKOS/dihedral_opls_kokkos.cpp
@@ -69,8 +69,7 @@ void DihedralOPLSKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/domain_kokkos.h b/src/KOKKOS/domain_kokkos.h
index 7b8504dba8..eccc36a021 100644
--- a/src/KOKKOS/domain_kokkos.h
+++ b/src/KOKKOS/domain_kokkos.h
@@ -36,10 +36,12 @@ class DomainKokkos : public Domain {
   void image_flip(int, int, int);
   void x2lamda(int);
   void lamda2x(int);
-  // these lines bring in the x2lamda signatures from Domain
-  // that are not overloaded here
-  using Domain::x2lamda;
-  using Domain::lamda2x;
+  // forward remaining x2lamda() and lambda2x() variants to parent class
+  void x2lamda(double *a, double *b) { Domain::x2lamda(a,b); }
+  void lamda2x(double *a, double *b) { Domain::lamda2x(a,b); }
+  void x2lamda(double *a, double *b, double *c, double *d) {
+    Domain::x2lamda(a,b,c,d);
+  }
 
   int closest_image(const int, int) const;
 
diff --git a/src/KOKKOS/fix_nh_kokkos.cpp b/src/KOKKOS/fix_nh_kokkos.cpp
index ba6e8919ea..fae9ef8f30 100644
--- a/src/KOKKOS/fix_nh_kokkos.cpp
+++ b/src/KOKKOS/fix_nh_kokkos.cpp
@@ -106,8 +106,8 @@ void FixNHKokkos<DeviceType>::setup(int vflag)
 
     if (t0 == 0.0) {
       atomKK->sync(temperature->execution_space,temperature->datamask_read);
-      atomKK->modified(temperature->execution_space,temperature->datamask_modify);
       t0 = temperature->compute_scalar();
+      atomKK->modified(temperature->execution_space,temperature->datamask_modify);
       if (t0 == 0.0) {
         if (strcmp(update->unit_style,"lj") == 0) t0 = 1.0;
         else t0 = 300.0;
@@ -119,8 +119,8 @@ void FixNHKokkos<DeviceType>::setup(int vflag)
   if (pstat_flag) compute_press_target();
 
   atomKK->sync(temperature->execution_space,temperature->datamask_read);
-  atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   t_current = temperature->compute_scalar();
+  atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   tdof = temperature->dof;
 
   if (pstat_flag) {
@@ -250,10 +250,11 @@ void FixNHKokkos<DeviceType>::final_integrate()
   //   per-atom values are invalid if reneigh/comm occurred
   //     since temp->compute() in initial_integrate()
 
-  if (which == BIAS && neighbor->ago == 0)
+  if (which == BIAS && neighbor->ago == 0) {
     atomKK->sync(temperature->execution_space,temperature->datamask_read);
-    atomKK->modified(temperature->execution_space,temperature->datamask_modify);
     t_current = temperature->compute_scalar();
+    atomKK->modified(temperature->execution_space,temperature->datamask_modify);
+  }
 
   if (pstat_flag) nh_v_press();
 
@@ -261,8 +262,8 @@ void FixNHKokkos<DeviceType>::final_integrate()
   // compute appropriately coupled elements of mvv_current
 
   atomKK->sync(temperature->execution_space,temperature->datamask_read);
-  atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   t_current = temperature->compute_scalar();
+  atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   tdof = temperature->dof;
 
   if (pstat_flag) {
@@ -476,8 +477,6 @@ void FixNHKokkos<DeviceType>::remap()
 template<class DeviceType>
 void FixNHKokkos<DeviceType>::nh_v_press()
 {
-  atomKK->sync(execution_space,V_MASK | MASK_MASK);
-
   v = atomKK->k_v.view<DeviceType>();
   mask = atomKK->k_mask.view<DeviceType>();
   int nlocal = atomKK->nlocal;
@@ -493,6 +492,8 @@ void FixNHKokkos<DeviceType>::nh_v_press()
     atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   }
 
+  atomKK->sync(execution_space,V_MASK | MASK_MASK);
+
   copymode = 1;
   if (pstyle == TRICLINIC)
     Kokkos::parallel_for(Kokkos::RangePolicy<DeviceType, TagFixNH_nh_v_press<1> >(0,nlocal),*this);
@@ -536,7 +537,6 @@ template<class DeviceType>
 void FixNHKokkos<DeviceType>::nve_v()
 {
   atomKK->sync(execution_space,X_MASK | V_MASK | F_MASK | MASK_MASK | RMASS_MASK | TYPE_MASK);
-  atomKK->modified(execution_space,V_MASK);
 
   v = atomKK->k_v.view<DeviceType>();
   f = atomKK->k_f.view<DeviceType>();
@@ -553,6 +553,8 @@ void FixNHKokkos<DeviceType>::nve_v()
   else
     Kokkos::parallel_for(Kokkos::RangePolicy<DeviceType, TagFixNH_nve_v<0> >(0,nlocal),*this);
   copymode = 0;
+
+  atomKK->modified(execution_space,V_MASK);
 }
 
 template<class DeviceType>
@@ -616,8 +618,6 @@ void FixNHKokkos<DeviceType>::operator()(TagFixNH_nve_x, const int &i) const {
 template<class DeviceType>
 void FixNHKokkos<DeviceType>::nh_v_temp()
 {
-  atomKK->sync(execution_space,V_MASK | MASK_MASK);
-
   v = atomKK->k_v.view<DeviceType>();
   mask = atomKK->k_mask.view<DeviceType>();
   int nlocal = atomKK->nlocal;
@@ -629,6 +629,8 @@ void FixNHKokkos<DeviceType>::nh_v_temp()
     atomKK->modified(temperature->execution_space,temperature->datamask_modify);
   }
 
+  atomKK->sync(execution_space,V_MASK | MASK_MASK);
+
   copymode = 1;
   Kokkos::parallel_for(Kokkos::RangePolicy<DeviceType, TagFixNH_nh_v_temp>(0,nlocal),*this);
   copymode = 0;
diff --git a/src/KOKKOS/improper_class2_kokkos.cpp b/src/KOKKOS/improper_class2_kokkos.cpp
index e3af52b494..ad32e6da4e 100644
--- a/src/KOKKOS/improper_class2_kokkos.cpp
+++ b/src/KOKKOS/improper_class2_kokkos.cpp
@@ -71,8 +71,7 @@ void ImproperClass2Kokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/improper_harmonic_kokkos.cpp b/src/KOKKOS/improper_harmonic_kokkos.cpp
index 4d41f3ef48..bb397a2c2f 100644
--- a/src/KOKKOS/improper_harmonic_kokkos.cpp
+++ b/src/KOKKOS/improper_harmonic_kokkos.cpp
@@ -71,8 +71,7 @@ void ImproperHarmonicKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   eflag = eflag_in;
   vflag = vflag_in;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_buck_coul_cut_kokkos.cpp b/src/KOKKOS/pair_buck_coul_cut_kokkos.cpp
index 18d09965be..57ac3a9c57 100644
--- a/src/KOKKOS/pair_buck_coul_cut_kokkos.cpp
+++ b/src/KOKKOS/pair_buck_coul_cut_kokkos.cpp
@@ -92,8 +92,7 @@ void PairBuckCoulCutKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_buck_coul_long_kokkos.cpp b/src/KOKKOS/pair_buck_coul_long_kokkos.cpp
index 0b44a83ebb..349c4c0601 100644
--- a/src/KOKKOS/pair_buck_coul_long_kokkos.cpp
+++ b/src/KOKKOS/pair_buck_coul_long_kokkos.cpp
@@ -111,8 +111,7 @@ void PairBuckCoulLongKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_buck_kokkos.cpp b/src/KOKKOS/pair_buck_kokkos.cpp
index 999aefe4c3..02c02c986e 100644
--- a/src/KOKKOS/pair_buck_kokkos.cpp
+++ b/src/KOKKOS/pair_buck_kokkos.cpp
@@ -81,8 +81,7 @@ void PairBuckKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_coul_cut_kokkos.cpp b/src/KOKKOS/pair_coul_cut_kokkos.cpp
index 7d29adc625..54ba0b63ce 100644
--- a/src/KOKKOS/pair_coul_cut_kokkos.cpp
+++ b/src/KOKKOS/pair_coul_cut_kokkos.cpp
@@ -80,8 +80,7 @@ void PairCoulCutKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_coul_debye_kokkos.cpp b/src/KOKKOS/pair_coul_debye_kokkos.cpp
index 3de83b5bc4..8966e30394 100644
--- a/src/KOKKOS/pair_coul_debye_kokkos.cpp
+++ b/src/KOKKOS/pair_coul_debye_kokkos.cpp
@@ -87,8 +87,7 @@ void PairCoulDebyeKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_coul_dsf_kokkos.cpp b/src/KOKKOS/pair_coul_dsf_kokkos.cpp
index 7d03ee4968..748fed71a7 100644
--- a/src/KOKKOS/pair_coul_dsf_kokkos.cpp
+++ b/src/KOKKOS/pair_coul_dsf_kokkos.cpp
@@ -80,8 +80,7 @@ void PairCoulDSFKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_coul_long_kokkos.cpp b/src/KOKKOS/pair_coul_long_kokkos.cpp
index 73b9521da0..a21cb050ff 100644
--- a/src/KOKKOS/pair_coul_long_kokkos.cpp
+++ b/src/KOKKOS/pair_coul_long_kokkos.cpp
@@ -104,8 +104,7 @@ void PairCoulLongKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_coul_wolf_kokkos.cpp b/src/KOKKOS/pair_coul_wolf_kokkos.cpp
index fe9c581cc1..20391d9530 100644
--- a/src/KOKKOS/pair_coul_wolf_kokkos.cpp
+++ b/src/KOKKOS/pair_coul_wolf_kokkos.cpp
@@ -75,8 +75,7 @@ void PairCoulWolfKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_dpd_fdt_energy_kokkos.cpp b/src/KOKKOS/pair_dpd_fdt_energy_kokkos.cpp
index d2fcc81ea4..a44ef1790e 100644
--- a/src/KOKKOS/pair_dpd_fdt_energy_kokkos.cpp
+++ b/src/KOKKOS/pair_dpd_fdt_energy_kokkos.cpp
@@ -165,8 +165,7 @@ void PairDPDfdtEnergyKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   vflag = vflag_in;
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_eam_alloy_kokkos.cpp b/src/KOKKOS/pair_eam_alloy_kokkos.cpp
index 6039282141..b580f00ed0 100644
--- a/src/KOKKOS/pair_eam_alloy_kokkos.cpp
+++ b/src/KOKKOS/pair_eam_alloy_kokkos.cpp
@@ -74,8 +74,7 @@ void PairEAMAlloyKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_eam_fs_kokkos.cpp b/src/KOKKOS/pair_eam_fs_kokkos.cpp
index 81d9ba8326..1b1ec5c31e 100644
--- a/src/KOKKOS/pair_eam_fs_kokkos.cpp
+++ b/src/KOKKOS/pair_eam_fs_kokkos.cpp
@@ -74,8 +74,7 @@ void PairEAMFSKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_eam_kokkos.cpp b/src/KOKKOS/pair_eam_kokkos.cpp
index 22383f57c5..d423f2c927 100644
--- a/src/KOKKOS/pair_eam_kokkos.cpp
+++ b/src/KOKKOS/pair_eam_kokkos.cpp
@@ -68,8 +68,7 @@ void PairEAMKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_exp6_rx_kokkos.cpp b/src/KOKKOS/pair_exp6_rx_kokkos.cpp
index df24a5f4c7..0a6372fdf8 100644
--- a/src/KOKKOS/pair_exp6_rx_kokkos.cpp
+++ b/src/KOKKOS/pair_exp6_rx_kokkos.cpp
@@ -36,6 +36,10 @@
 #include "atom_kokkos.h"
 #include "kokkos.h"
 
+#ifdef _OPENMP
+#include <omp.h>
+#endif
+
 using namespace LAMMPS_NS;
 using namespace MathConst;
 using namespace MathSpecialKokkos;
@@ -147,8 +151,7 @@ void PairExp6rxKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
   vflag = vflag_in;
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_gran_hooke_history_kokkos.cpp b/src/KOKKOS/pair_gran_hooke_history_kokkos.cpp
index 189407b541..068580b525 100644
--- a/src/KOKKOS/pair_gran_hooke_history_kokkos.cpp
+++ b/src/KOKKOS/pair_gran_hooke_history_kokkos.cpp
@@ -111,8 +111,7 @@ void PairGranHookeHistoryKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   int shearupdate = 1;
   if (update->setupflag) shearupdate = 0;
diff --git a/src/KOKKOS/pair_hybrid_kokkos.cpp b/src/KOKKOS/pair_hybrid_kokkos.cpp
index 03ad77c34a..00df4a8f3c 100644
--- a/src/KOKKOS/pair_hybrid_kokkos.cpp
+++ b/src/KOKKOS/pair_hybrid_kokkos.cpp
@@ -78,9 +78,7 @@ void PairHybridKokkos::compute(int eflag, int vflag)
 
   if (no_virial_fdotr_compute && vflag % 4 == 2) vflag = 1 + vflag/4 * 4;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // check if global component of incoming vflag = 2
   // if so, reset vflag passed to substyle as if it were 0
diff --git a/src/KOKKOS/pair_lj_charmm_coul_charmm_implicit_kokkos.cpp b/src/KOKKOS/pair_lj_charmm_coul_charmm_implicit_kokkos.cpp
index ce7df2bec1..510740112a 100644
--- a/src/KOKKOS/pair_lj_charmm_coul_charmm_implicit_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_charmm_coul_charmm_implicit_kokkos.cpp
@@ -112,8 +112,7 @@ void PairLJCharmmCoulCharmmImplicitKokkos<DeviceType>::compute(int eflag_in, int
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_charmm_coul_charmm_kokkos.cpp b/src/KOKKOS/pair_lj_charmm_coul_charmm_kokkos.cpp
index b31282e595..51c96354f9 100644
--- a/src/KOKKOS/pair_lj_charmm_coul_charmm_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_charmm_coul_charmm_kokkos.cpp
@@ -112,8 +112,7 @@ void PairLJCharmmCoulCharmmKokkos<DeviceType>::compute(int eflag_in, int vflag_i
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_charmm_coul_long_kokkos.cpp b/src/KOKKOS/pair_lj_charmm_coul_long_kokkos.cpp
index 5d8a202aa4..22faa98935 100644
--- a/src/KOKKOS/pair_lj_charmm_coul_long_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_charmm_coul_long_kokkos.cpp
@@ -112,8 +112,7 @@ void PairLJCharmmCoulLongKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_class2_coul_cut_kokkos.cpp b/src/KOKKOS/pair_lj_class2_coul_cut_kokkos.cpp
index 6eb3028101..60d480188b 100644
--- a/src/KOKKOS/pair_lj_class2_coul_cut_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_class2_coul_cut_kokkos.cpp
@@ -89,8 +89,7 @@ void PairLJClass2CoulCutKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_class2_coul_long_kokkos.cpp b/src/KOKKOS/pair_lj_class2_coul_long_kokkos.cpp
index a388694876..4c8aea8e92 100644
--- a/src/KOKKOS/pair_lj_class2_coul_long_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_class2_coul_long_kokkos.cpp
@@ -97,8 +97,7 @@ void PairLJClass2CoulLongKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_class2_kokkos.cpp b/src/KOKKOS/pair_lj_class2_kokkos.cpp
index 33d1477443..dd42baa4e0 100644
--- a/src/KOKKOS/pair_lj_class2_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_class2_kokkos.cpp
@@ -89,8 +89,7 @@ void PairLJClass2Kokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_cut_coul_cut_kokkos.cpp b/src/KOKKOS/pair_lj_cut_coul_cut_kokkos.cpp
index 6001fabbed..cb5ab96871 100644
--- a/src/KOKKOS/pair_lj_cut_coul_cut_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_cut_coul_cut_kokkos.cpp
@@ -89,8 +89,7 @@ void PairLJCutCoulCutKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_cut_coul_debye_kokkos.cpp b/src/KOKKOS/pair_lj_cut_coul_debye_kokkos.cpp
index 10923bc5da..800092a09b 100644
--- a/src/KOKKOS/pair_lj_cut_coul_debye_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_cut_coul_debye_kokkos.cpp
@@ -93,8 +93,7 @@ void PairLJCutCoulDebyeKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_cut_coul_dsf_kokkos.cpp b/src/KOKKOS/pair_lj_cut_coul_dsf_kokkos.cpp
index 47aa2ea7cc..f793485b47 100644
--- a/src/KOKKOS/pair_lj_cut_coul_dsf_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_cut_coul_dsf_kokkos.cpp
@@ -101,8 +101,7 @@ void PairLJCutCoulDSFKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_cut_coul_long_kokkos.cpp b/src/KOKKOS/pair_lj_cut_coul_long_kokkos.cpp
index fa36cb1866..02150586f4 100644
--- a/src/KOKKOS/pair_lj_cut_coul_long_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_cut_coul_long_kokkos.cpp
@@ -101,8 +101,7 @@ void PairLJCutCoulLongKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
 
   // reallocate per-atom arrays if necessary
diff --git a/src/KOKKOS/pair_lj_cut_kokkos.cpp b/src/KOKKOS/pair_lj_cut_kokkos.cpp
index 9b0ff902af..4ba8c00f88 100644
--- a/src/KOKKOS/pair_lj_cut_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_cut_kokkos.cpp
@@ -89,8 +89,7 @@ void PairLJCutKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_expand_kokkos.cpp b/src/KOKKOS/pair_lj_expand_kokkos.cpp
index 3b8b9343d8..5ea6c9e438 100644
--- a/src/KOKKOS/pair_lj_expand_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_expand_kokkos.cpp
@@ -88,8 +88,7 @@ void PairLJExpandKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_gromacs_coul_gromacs_kokkos.cpp b/src/KOKKOS/pair_lj_gromacs_coul_gromacs_kokkos.cpp
index d06ad9b44e..2421d059da 100644
--- a/src/KOKKOS/pair_lj_gromacs_coul_gromacs_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_gromacs_coul_gromacs_kokkos.cpp
@@ -103,8 +103,7 @@ void PairLJGromacsCoulGromacsKokkos<DeviceType>::compute(int eflag_in, int vflag
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_gromacs_kokkos.cpp b/src/KOKKOS/pair_lj_gromacs_kokkos.cpp
index d447846333..09a0261ae1 100644
--- a/src/KOKKOS/pair_lj_gromacs_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_gromacs_kokkos.cpp
@@ -100,8 +100,7 @@ void PairLJGromacsKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_lj_sdk_kokkos.cpp b/src/KOKKOS/pair_lj_sdk_kokkos.cpp
index 990e464341..c2375fa7a8 100644
--- a/src/KOKKOS/pair_lj_sdk_kokkos.cpp
+++ b/src/KOKKOS/pair_lj_sdk_kokkos.cpp
@@ -88,8 +88,7 @@ void PairLJSDKKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_morse_kokkos.cpp b/src/KOKKOS/pair_morse_kokkos.cpp
index ab5eb817a1..b308330ead 100644
--- a/src/KOKKOS/pair_morse_kokkos.cpp
+++ b/src/KOKKOS/pair_morse_kokkos.cpp
@@ -93,8 +93,7 @@ void PairMorseKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_multi_lucy_rx_kokkos.cpp b/src/KOKKOS/pair_multi_lucy_rx_kokkos.cpp
index 5f19d73dfa..7d17ac3f43 100644
--- a/src/KOKKOS/pair_multi_lucy_rx_kokkos.cpp
+++ b/src/KOKKOS/pair_multi_lucy_rx_kokkos.cpp
@@ -148,8 +148,7 @@ void PairMultiLucyRXKokkos<DeviceType>::compute_style(int eflag_in, int vflag_in
   vflag = vflag_in;
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_reaxc_kokkos.cpp b/src/KOKKOS/pair_reaxc_kokkos.cpp
index 56d2ebd8aa..dda75782b2 100644
--- a/src/KOKKOS/pair_reaxc_kokkos.cpp
+++ b/src/KOKKOS/pair_reaxc_kokkos.cpp
@@ -447,23 +447,23 @@ int PairReaxCKokkos<DeviceType>::Init_Lookup_Tables()
   num_atom_types = atom->ntypes;
   dr = control->nonb_cut / control->tabulate;
   h = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:h", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:h");
   fh = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fh", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:fh");
   fvdw = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fvdw", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:fvdw");
   fCEvd = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fCEvd", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:fCEvd");
   fele = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fele", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:fele");
   fCEclmb = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fCEclmb", world );
+    smalloc( control->error_ptr, (control->tabulate+2) * sizeof(double), "lookup:fCEclmb");
 
   LR = (LR_lookup_table**)
-    scalloc( num_atom_types+1, sizeof(LR_lookup_table*), "lookup:LR", world );
+    scalloc( control->error_ptr, num_atom_types+1, sizeof(LR_lookup_table*), "lookup:LR");
   for( i = 0; i < num_atom_types+1; ++i )
     LR[i] = (LR_lookup_table*)
-      scalloc( num_atom_types+1, sizeof(LR_lookup_table), "lookup:LR[i]", world );
+      scalloc( control->error_ptr, num_atom_types+1, sizeof(LR_lookup_table), "lookup:LR[i]");
 
   for( i = 1; i <= num_atom_types; ++i ) {
     for( j = i; j <= num_atom_types; ++j ) {
@@ -473,22 +473,18 @@ int PairReaxCKokkos<DeviceType>::Init_Lookup_Tables()
       LR[i][j].dx = dr;
       LR[i][j].inv_dx = control->tabulate / control->nonb_cut;
       LR[i][j].y = (LR_data*)
-        smalloc( LR[i][j].n * sizeof(LR_data), "lookup:LR[i,j].y", world );
+        smalloc( control->error_ptr, LR[i][j].n * sizeof(LR_data), "lookup:LR[i,j].y");
       LR[i][j].H = (cubic_spline_coef*)
-        smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].H" ,
-                 world );
+        smalloc( control->error_ptr, LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].H");
       LR[i][j].vdW = (cubic_spline_coef*)
-        smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].vdW",
-                 world);
+        smalloc( control->error_ptr, LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].vdW");
       LR[i][j].CEvd = (cubic_spline_coef*)
-        smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].CEvd",
-                 world);
+        smalloc( control->error_ptr, LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].CEvd");
       LR[i][j].ele = (cubic_spline_coef*)
-        smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].ele",
-                 world );
+        smalloc( control->error_ptr, LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].ele");
       LR[i][j].CEclmb = (cubic_spline_coef*)
-        smalloc( LR[i][j].n*sizeof(cubic_spline_coef),
-                 "lookup:LR[i,j].CEclmb", world );
+        smalloc( control->error_ptr, LR[i][j].n*sizeof(cubic_spline_coef),
+                 "lookup:LR[i,j].CEclmb");
 
       for( r = 1; r <= control->tabulate; ++r ) {
         LR_vdW_Coulomb(i, j, r * dr, &(LR[i][j].y[r]) );
@@ -512,24 +508,20 @@ int PairReaxCKokkos<DeviceType>::Init_Lookup_Tables()
       vlast_vdw = fCEvd[r-1];
       vlast_ele = fele[r-1];
 
-      Natural_Cubic_Spline( &h[1], &fh[1],
-                            &(LR[i][j].H[1]), control->tabulate+1, world );
+      Natural_Cubic_Spline( control->error_ptr, &h[1], &fh[1],
+                            &(LR[i][j].H[1]), control->tabulate+1 );
 
-      Complete_Cubic_Spline( &h[1], &fvdw[1], v0_vdw, vlast_vdw,
-                             &(LR[i][j].vdW[1]), control->tabulate+1,
-                             world );
+      Complete_Cubic_Spline( control->error_ptr, &h[1], &fvdw[1], v0_vdw, vlast_vdw,
+                             &(LR[i][j].vdW[1]), control->tabulate+1 );
 
-      Natural_Cubic_Spline( &h[1], &fCEvd[1],
-                            &(LR[i][j].CEvd[1]), control->tabulate+1,
-                            world );
+      Natural_Cubic_Spline( control->error_ptr, &h[1], &fCEvd[1],
+                            &(LR[i][j].CEvd[1]), control->tabulate+1 );
 
-      Complete_Cubic_Spline( &h[1], &fele[1], v0_ele, vlast_ele,
-                             &(LR[i][j].ele[1]), control->tabulate+1,
-                             world );
+      Complete_Cubic_Spline( control->error_ptr, &h[1], &fele[1], v0_ele, vlast_ele,
+                             &(LR[i][j].ele[1]), control->tabulate+1 );
 
-      Natural_Cubic_Spline( &h[1], &fCEclmb[1],
-                            &(LR[i][j].CEclmb[1]), control->tabulate+1,
-                            world );
+      Natural_Cubic_Spline( control->error_ptr, &h[1], &fCEclmb[1],
+                            &(LR[i][j].CEclmb[1]), control->tabulate+1 );
     }
   }
   free(h);
@@ -555,16 +547,16 @@ void PairReaxCKokkos<DeviceType>::Deallocate_Lookup_Tables()
   for( i = 0; i <= ntypes; ++i ) {
     for( j = i; j <= ntypes; ++j )
       if (LR[i][j].n) {
-        sfree( LR[i][j].y, "LR[i,j].y" );
-        sfree( LR[i][j].H, "LR[i,j].H" );
-        sfree( LR[i][j].vdW, "LR[i,j].vdW" );
-        sfree( LR[i][j].CEvd, "LR[i,j].CEvd" );
-        sfree( LR[i][j].ele, "LR[i,j].ele" );
-        sfree( LR[i][j].CEclmb, "LR[i,j].CEclmb" );
+        sfree( control->error_ptr, LR[i][j].y, "LR[i,j].y" );
+        sfree( control->error_ptr, LR[i][j].H, "LR[i,j].H" );
+        sfree( control->error_ptr, LR[i][j].vdW, "LR[i,j].vdW" );
+        sfree( control->error_ptr, LR[i][j].CEvd, "LR[i,j].CEvd" );
+        sfree( control->error_ptr, LR[i][j].ele, "LR[i,j].ele" );
+        sfree( control->error_ptr, LR[i][j].CEclmb, "LR[i,j].CEclmb" );
       }
-    sfree( LR[i], "LR[i]" );
+    sfree( control->error_ptr, LR[i], "LR[i]" );
   }
-  sfree( LR, "LR" );
+  sfree( control->error_ptr, LR, "LR" );
 }
 
 /* ---------------------------------------------------------------------- */
@@ -677,8 +669,7 @@ void PairReaxCKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   atomKK->sync(execution_space,datamask_read);
   k_params_sing.template sync<DeviceType>();
diff --git a/src/KOKKOS/pair_snap_kokkos_impl.h b/src/KOKKOS/pair_snap_kokkos_impl.h
index 998e75fabe..bb2a5e9171 100644
--- a/src/KOKKOS/pair_snap_kokkos_impl.h
+++ b/src/KOKKOS/pair_snap_kokkos_impl.h
@@ -32,7 +32,7 @@
 #define MAXLINE 1024
 #define MAXWORD 3
 
-using namespace LAMMPS_NS;
+namespace LAMMPS_NS {
 
 // Outstanding issues with quadratic term
 // 1. there seems to a problem with compute_optimized energy calc
@@ -137,8 +137,7 @@ void PairSNAPKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
@@ -675,3 +674,4 @@ double PairSNAPKokkos<DeviceType>::memory_usage()
   bytes += snaKK.memory_usage();
   return bytes;
 }
+}
diff --git a/src/KOKKOS/pair_sw_kokkos.cpp b/src/KOKKOS/pair_sw_kokkos.cpp
index 24022475ab..da4737a2c1 100644
--- a/src/KOKKOS/pair_sw_kokkos.cpp
+++ b/src/KOKKOS/pair_sw_kokkos.cpp
@@ -80,8 +80,7 @@ void PairSWKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_table_kokkos.cpp b/src/KOKKOS/pair_table_kokkos.cpp
index 9522e94706..737d600d1e 100644
--- a/src/KOKKOS/pair_table_kokkos.cpp
+++ b/src/KOKKOS/pair_table_kokkos.cpp
@@ -86,8 +86,7 @@ void PairTableKokkos<DeviceType>::compute_style(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_table_rx_kokkos.cpp b/src/KOKKOS/pair_table_rx_kokkos.cpp
index 376984afa2..ec7a2ffb94 100644
--- a/src/KOKKOS/pair_table_rx_kokkos.cpp
+++ b/src/KOKKOS/pair_table_rx_kokkos.cpp
@@ -619,8 +619,7 @@ void PairTableRXKokkos<DeviceType>::compute_style(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   if (eflag_atom) {
     memoryKK->destroy_kokkos(k_eatom,eatom);
diff --git a/src/KOKKOS/pair_tersoff_kokkos.cpp b/src/KOKKOS/pair_tersoff_kokkos.cpp
index a6668ca064..9252e3de52 100644
--- a/src/KOKKOS/pair_tersoff_kokkos.cpp
+++ b/src/KOKKOS/pair_tersoff_kokkos.cpp
@@ -164,8 +164,7 @@ void PairTersoffKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_tersoff_mod_kokkos.cpp b/src/KOKKOS/pair_tersoff_mod_kokkos.cpp
index 303d2bdfda..585074b128 100644
--- a/src/KOKKOS/pair_tersoff_mod_kokkos.cpp
+++ b/src/KOKKOS/pair_tersoff_mod_kokkos.cpp
@@ -164,8 +164,7 @@ void PairTersoffMODKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_tersoff_zbl_kokkos.cpp b/src/KOKKOS/pair_tersoff_zbl_kokkos.cpp
index ad4a2d444e..e1e2211ab5 100644
--- a/src/KOKKOS/pair_tersoff_zbl_kokkos.cpp
+++ b/src/KOKKOS/pair_tersoff_zbl_kokkos.cpp
@@ -178,8 +178,7 @@ void PairTersoffZBLKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_vashishta_kokkos.cpp b/src/KOKKOS/pair_vashishta_kokkos.cpp
index 78ab8bfc85..4a1f291b17 100644
--- a/src/KOKKOS/pair_vashishta_kokkos.cpp
+++ b/src/KOKKOS/pair_vashishta_kokkos.cpp
@@ -79,8 +79,7 @@ void PairVashishtaKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_yukawa_kokkos.cpp b/src/KOKKOS/pair_yukawa_kokkos.cpp
index 951613a33e..27e18533a2 100644
--- a/src/KOKKOS/pair_yukawa_kokkos.cpp
+++ b/src/KOKKOS/pair_yukawa_kokkos.cpp
@@ -177,8 +177,7 @@ void PairYukawaKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pair_zbl_kokkos.cpp b/src/KOKKOS/pair_zbl_kokkos.cpp
index bcf33b405d..06c84e5189 100644
--- a/src/KOKKOS/pair_zbl_kokkos.cpp
+++ b/src/KOKKOS/pair_zbl_kokkos.cpp
@@ -129,8 +129,7 @@ void PairZBLKokkos<DeviceType>::compute(int eflag_in, int vflag_in)
 
   if (neighflag == FULL) no_virial_fdotr_compute = 1;
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag,0);
 
   // reallocate per-atom arrays if necessary
 
diff --git a/src/KOKKOS/pppm_kokkos.cpp b/src/KOKKOS/pppm_kokkos.cpp
index bcac29ba9b..c233ca6264 100644
--- a/src/KOKKOS/pppm_kokkos.cpp
+++ b/src/KOKKOS/pppm_kokkos.cpp
@@ -615,8 +615,7 @@ void PPPMKokkos<DeviceType>::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag,0);
-  else evflag = evflag_atom = eflag_global = vflag_global =
+  ev_init(eflag,vflag,0);
          eflag_atom = vflag_atom = 0;
 
   // reallocate per-atom arrays if necessary
diff --git a/src/KOKKOS/sna_kokkos_impl.h b/src/KOKKOS/sna_kokkos_impl.h
index 6a19c57829..0f2a450a3d 100644
--- a/src/KOKKOS/sna_kokkos_impl.h
+++ b/src/KOKKOS/sna_kokkos_impl.h
@@ -20,7 +20,7 @@
 #include <cstring>
 #include <cstdlib>
 
-using namespace LAMMPS_NS;
+namespace LAMMPS_NS {
 
 static const double MY_PI  = 3.14159265358979323846; // pi
 
@@ -1300,3 +1300,5 @@ double SNAKokkos<DeviceType>::memory_usage()
   bytes += jdim * jdim * jdim * jdim * jdim * sizeof(std::complex<double>);
   return bytes;
 }
+
+} // namespace LAMMPS_NS
diff --git a/src/KSPACE/ewald.cpp b/src/KSPACE/ewald.cpp
index 283c672bad..ccbb3ed708 100644
--- a/src/KSPACE/ewald.cpp
+++ b/src/KSPACE/ewald.cpp
@@ -365,9 +365,7 @@ void Ewald::compute(int eflag, int vflag)
 
   // set energy/virial flags
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // if atom count has changed, update qsum and qsqsum
 
diff --git a/src/KSPACE/ewald_disp.cpp b/src/KSPACE/ewald_disp.cpp
index 4cbdf7b9cb..0603d68eb2 100644
--- a/src/KSPACE/ewald_disp.cpp
+++ b/src/KSPACE/ewald_disp.cpp
@@ -688,8 +688,7 @@ void EwaldDisp::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (!peratom_allocate_flag && (eflag_atom || vflag_atom)) {
       allocate_peratom();
diff --git a/src/KSPACE/fix_tune_kspace.cpp b/src/KSPACE/fix_tune_kspace.cpp
index 3e90988cba..0c726985dc 100644
--- a/src/KSPACE/fix_tune_kspace.cpp
+++ b/src/KSPACE/fix_tune_kspace.cpp
@@ -99,8 +99,8 @@ void FixTuneKspace::init()
     error->all(FLERR,"Cannot use fix tune/kspace with dipole long-range solver");
 
   double old_acc = force->kspace->accuracy/force->kspace->two_charge_force;
-  char old_acc_str[12];
-  sprintf(old_acc_str,"%g",old_acc);
+  char old_acc_str[16];
+  snprintf(old_acc_str,16,"%g",old_acc);
   strcpy(new_acc_str,old_acc_str);
 
   int itmp;
@@ -210,8 +210,8 @@ void FixTuneKspace::store_old_kspace_settings()
   strcpy(old_kspace_style,force->kspace_style);
   strcpy(new_kspace_style,old_kspace_style);
   double old_acc = force->kspace->accuracy_relative;
-  char old_acc_str[12];
-  sprintf(old_acc_str,"%g",old_acc);
+  char old_acc_str[16];
+  snprintf(old_acc_str,16,"%g",old_acc);
   strcpy(new_pair_style,force->pair_style);
   strcpy(base_pair_style,force->pair_style);
   char *trunc;
diff --git a/src/KSPACE/msm.cpp b/src/KSPACE/msm.cpp
index d8964ffa67..d7cc3f6876 100644
--- a/src/KSPACE/msm.cpp
+++ b/src/KSPACE/msm.cpp
@@ -454,9 +454,7 @@ void MSM::compute(int eflag, int vflag)
 
   // set energy/virial flags
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-    eflag_atom = vflag_atom = eflag_either = vflag_either = 0;
+  ev_init(eflag,vflag);
 
   if (scalar_pressure_flag && vflag_either) {
     if (vflag_atom)
diff --git a/src/KSPACE/msm_cg.cpp b/src/KSPACE/msm_cg.cpp
index 55435e5a6e..c7896db50c 100644
--- a/src/KSPACE/msm_cg.cpp
+++ b/src/KSPACE/msm_cg.cpp
@@ -90,9 +90,7 @@ void MSMCG::compute(int eflag, int vflag)
 
   // set energy/virial flags
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-    eflag_atom = vflag_atom = eflag_either = vflag_either = 0;
+  ev_init(eflag,vflag);
 
   // invoke allocate_peratom() if needed for first time
 
diff --git a/src/KSPACE/pair_born_coul_long.cpp b/src/KSPACE/pair_born_coul_long.cpp
index d55a5a3afe..f12f5779d9 100644
--- a/src/KSPACE/pair_born_coul_long.cpp
+++ b/src/KSPACE/pair_born_coul_long.cpp
@@ -87,8 +87,7 @@ void PairBornCoulLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_born_coul_msm.cpp b/src/KSPACE/pair_born_coul_msm.cpp
index 775d26df95..eaa1c116c1 100644
--- a/src/KSPACE/pair_born_coul_msm.cpp
+++ b/src/KSPACE/pair_born_coul_msm.cpp
@@ -82,8 +82,7 @@ void PairBornCoulMSM::compute(int eflag, int vflag)
   }
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_buck_coul_long.cpp b/src/KSPACE/pair_buck_coul_long.cpp
index a37e4ab4e9..0a1ec88da5 100644
--- a/src/KSPACE/pair_buck_coul_long.cpp
+++ b/src/KSPACE/pair_buck_coul_long.cpp
@@ -50,23 +50,23 @@ PairBuckCoulLong::PairBuckCoulLong(LAMMPS *lmp) : Pair(lmp)
 
 PairBuckCoulLong::~PairBuckCoulLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(a);
-      memory->destroy(rho);
-      memory->destroy(c);
-      memory->destroy(rhoinv);
-      memory->destroy(buck1);
-      memory->destroy(buck2);
-      memory->destroy(offset);
-    }
-    if (ftable) free_tables();
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(a);
+    memory->destroy(rho);
+    memory->destroy(c);
+    memory->destroy(rhoinv);
+    memory->destroy(buck1);
+    memory->destroy(buck2);
+    memory->destroy(offset);
   }
+  if (ftable) free_tables();
 }
 
 /* ---------------------------------------------------------------------- */
@@ -82,8 +82,7 @@ void PairBuckCoulLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_buck_coul_msm.cpp b/src/KSPACE/pair_buck_coul_msm.cpp
index fc72f1a4d6..257d1b661f 100644
--- a/src/KSPACE/pair_buck_coul_msm.cpp
+++ b/src/KSPACE/pair_buck_coul_msm.cpp
@@ -79,8 +79,7 @@ void PairBuckCoulMSM::compute(int eflag, int vflag)
   }
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_buck_long_coul_long.cpp b/src/KSPACE/pair_buck_long_coul_long.cpp
index d5bb7b6c5b..c7a4a4b2f6 100644
--- a/src/KSPACE/pair_buck_long_coul_long.cpp
+++ b/src/KSPACE/pair_buck_long_coul_long.cpp
@@ -445,8 +445,7 @@ void PairBuckLongCoulLong::compute(int eflag, int vflag)
 
   double evdwl,ecoul,fpair;
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x, *x0 = x[0];
   double **f = atom->f, *f0 = f[0], *fi = f0;
@@ -785,8 +784,7 @@ void PairBuckLongCoulLong::compute_outer(int eflag, int vflag)
 {
   double evdwl,ecoul,fpair,fvirial;
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x, *x0 = x[0];
   double **f = atom->f, *f0 = f[0], *fi = f0;
diff --git a/src/KSPACE/pair_coul_long.cpp b/src/KSPACE/pair_coul_long.cpp
index 8db5979b39..ae268b9857 100644
--- a/src/KSPACE/pair_coul_long.cpp
+++ b/src/KSPACE/pair_coul_long.cpp
@@ -55,15 +55,15 @@ PairCoulLong::PairCoulLong(LAMMPS *lmp) : Pair(lmp)
 
 PairCoulLong::~PairCoulLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(scale);
-    }
-    if (ftable) free_tables();
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(scale);
   }
+  if (ftable) free_tables();
 }
 
 /* ---------------------------------------------------------------------- */
@@ -79,8 +79,7 @@ void PairCoulLong::compute(int eflag, int vflag)
   double rsq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_coul_msm.cpp b/src/KSPACE/pair_coul_msm.cpp
index ab59dfa4c1..960505142c 100644
--- a/src/KSPACE/pair_coul_msm.cpp
+++ b/src/KSPACE/pair_coul_msm.cpp
@@ -67,8 +67,7 @@ void PairCoulMSM::compute(int eflag, int vflag)
   }
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_charmm_coul_long.cpp b/src/KSPACE/pair_lj_charmm_coul_long.cpp
index 749d9657aa..b40eab244b 100644
--- a/src/KSPACE/pair_lj_charmm_coul_long.cpp
+++ b/src/KSPACE/pair_lj_charmm_coul_long.cpp
@@ -59,27 +59,27 @@ PairLJCharmmCoulLong::PairLJCharmmCoulLong(LAMMPS *lmp) : Pair(lmp)
 
 PairLJCharmmCoulLong::~PairLJCharmmCoulLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(eps14);
-      memory->destroy(sigma14);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(lj14_1);
-      memory->destroy(lj14_2);
-      memory->destroy(lj14_3);
-      memory->destroy(lj14_4);
-      memory->destroy(offset);
-    }
-    if (ftable) free_tables();
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(eps14);
+    memory->destroy(sigma14);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(lj14_1);
+    memory->destroy(lj14_2);
+    memory->destroy(lj14_3);
+    memory->destroy(lj14_4);
+    memory->destroy(offset);
   }
+  if (ftable) free_tables();
 }
 
 /* ---------------------------------------------------------------------- */
@@ -96,8 +96,7 @@ void PairLJCharmmCoulLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -404,8 +403,7 @@ void PairLJCharmmCoulLong::compute_outer(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_charmm_coul_msm.cpp b/src/KSPACE/pair_lj_charmm_coul_msm.cpp
index aecadcf127..72a8e340bc 100644
--- a/src/KSPACE/pair_lj_charmm_coul_msm.cpp
+++ b/src/KSPACE/pair_lj_charmm_coul_msm.cpp
@@ -87,8 +87,7 @@ void PairLJCharmmCoulMSM::compute(int eflag, int vflag)
   }
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -265,8 +264,7 @@ void PairLJCharmmCoulMSM::compute_outer(int eflag, int vflag)
      "for rRESPA with kspace_style MSM");
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_charmmfsw_coul_long.cpp b/src/KSPACE/pair_lj_charmmfsw_coul_long.cpp
index 614980117e..4aecc8453a 100644
--- a/src/KSPACE/pair_lj_charmmfsw_coul_long.cpp
+++ b/src/KSPACE/pair_lj_charmmfsw_coul_long.cpp
@@ -77,27 +77,6 @@ PairLJCharmmfswCoulLong::PairLJCharmmfswCoulLong(LAMMPS *lmp) : Pair(lmp)
 
 PairLJCharmmfswCoulLong::~PairLJCharmmfswCoulLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
-
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(eps14);
-      memory->destroy(sigma14);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(lj14_1);
-      memory->destroy(lj14_2);
-      memory->destroy(lj14_3);
-      memory->destroy(lj14_4);
-    }
-    if (ftable) free_tables();
-  }
-
   // switch qqr2e back from CHARMM value to LAMMPS value
 
   if (update && strcmp(update->unit_style,"real") == 0) {
@@ -106,6 +85,27 @@ PairLJCharmmfswCoulLong::~PairLJCharmmfswCoulLong()
                      " conversion constant");
     force->qqr2e = force->qqr2e_lammps_real;
   }
+
+  if (copymode) return;
+
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(eps14);
+    memory->destroy(sigma14);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(lj14_1);
+    memory->destroy(lj14_2);
+    memory->destroy(lj14_3);
+    memory->destroy(lj14_4);
+  }
+  if (ftable) free_tables();
 }
 
 /* ---------------------------------------------------------------------- */
@@ -121,8 +121,7 @@ void PairLJCharmmfswCoulLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -452,8 +451,7 @@ void PairLJCharmmfswCoulLong::compute_outer(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_cut_coul_long.cpp b/src/KSPACE/pair_lj_cut_coul_long.cpp
index c9530fe157..fde7fa8e35 100644
--- a/src/KSPACE/pair_lj_cut_coul_long.cpp
+++ b/src/KSPACE/pair_lj_cut_coul_long.cpp
@@ -90,8 +90,7 @@ void PairLJCutCoulLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -397,8 +396,7 @@ void PairLJCutCoulLong::compute_outer(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_cut_coul_msm.cpp b/src/KSPACE/pair_lj_cut_coul_msm.cpp
index 78c364bd6a..c2e566a117 100644
--- a/src/KSPACE/pair_lj_cut_coul_msm.cpp
+++ b/src/KSPACE/pair_lj_cut_coul_msm.cpp
@@ -87,8 +87,7 @@ void PairLJCutCoulMSM::compute(int eflag, int vflag)
   }
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -252,8 +251,7 @@ void PairLJCutCoulMSM::compute_outer(int eflag, int vflag)
      "for rRESPA with kspace_style MSM");
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/KSPACE/pair_lj_cut_tip4p_long.cpp b/src/KSPACE/pair_lj_cut_tip4p_long.cpp
index d622a83b39..f5889fd520 100644
--- a/src/KSPACE/pair_lj_cut_tip4p_long.cpp
+++ b/src/KSPACE/pair_lj_cut_tip4p_long.cpp
@@ -94,8 +94,7 @@ void PairLJCutTIP4PLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/KSPACE/pair_lj_long_coul_long.cpp b/src/KSPACE/pair_lj_long_coul_long.cpp
index 2de527ab39..493866a895 100644
--- a/src/KSPACE/pair_lj_long_coul_long.cpp
+++ b/src/KSPACE/pair_lj_long_coul_long.cpp
@@ -441,8 +441,7 @@ void PairLJLongCoulLong::compute(int eflag, int vflag)
 {
   double evdwl,ecoul,fpair;
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x, *x0 = x[0];
   double **f = atom->f, *f0 = f[0], *fi = f0;
@@ -778,8 +777,7 @@ void PairLJLongCoulLong::compute_outer(int eflag, int vflag)
 {
   double evdwl,ecoul,fvirial,fpair;
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x, *x0 = x[0];
   double **f = atom->f, *f0 = f[0], *fi = f0;
diff --git a/src/KSPACE/pair_lj_long_tip4p_long.cpp b/src/KSPACE/pair_lj_long_tip4p_long.cpp
index a571e30fc3..3137b9d79a 100644
--- a/src/KSPACE/pair_lj_long_tip4p_long.cpp
+++ b/src/KSPACE/pair_lj_long_tip4p_long.cpp
@@ -92,8 +92,7 @@ void PairLJLongTIP4PLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
@@ -1004,8 +1003,7 @@ void PairLJLongTIP4PLong::compute_outer(int eflag, int vflag)
   int respa_flag;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/KSPACE/pair_tip4p_long.cpp b/src/KSPACE/pair_tip4p_long.cpp
index ac428d483a..9419fdf196 100644
--- a/src/KSPACE/pair_tip4p_long.cpp
+++ b/src/KSPACE/pair_tip4p_long.cpp
@@ -90,8 +90,7 @@ void PairTIP4PLong::compute(int eflag, int vflag)
   double rsq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/KSPACE/pppm.cpp b/src/KSPACE/pppm.cpp
index 8fd74d00dc..773305bb5e 100644
--- a/src/KSPACE/pppm.cpp
+++ b/src/KSPACE/pppm.cpp
@@ -630,9 +630,7 @@ void PPPM::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/KSPACE/pppm_cg.cpp b/src/KSPACE/pppm_cg.cpp
index fa73588363..3285dba21c 100644
--- a/src/KSPACE/pppm_cg.cpp
+++ b/src/KSPACE/pppm_cg.cpp
@@ -88,9 +88,7 @@ void PPPMCG::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/KSPACE/pppm_disp.cpp b/src/KSPACE/pppm_disp.cpp
index 687ea0b3f9..45dce0895b 100644
--- a/src/KSPACE/pppm_disp.cpp
+++ b/src/KSPACE/pppm_disp.cpp
@@ -928,9 +928,7 @@ void PPPMDisp::compute(int eflag, int vflag)
   int i;
   // convert atoms from box to lamda coords
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/KSPACE/pppm_stagger.cpp b/src/KSPACE/pppm_stagger.cpp
index ca369cf260..a5ed6de626 100644
--- a/src/KSPACE/pppm_stagger.cpp
+++ b/src/KSPACE/pppm_stagger.cpp
@@ -124,9 +124,7 @@ void PPPMStagger::compute(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/LATTE/fix_latte.cpp b/src/LATTE/fix_latte.cpp
index d1a96d32c6..645b298e09 100644
--- a/src/LATTE/fix_latte.cpp
+++ b/src/LATTE/fix_latte.cpp
@@ -239,8 +239,7 @@ void FixLatte::pre_reverse(int eflag, int /*vflag*/)
 void FixLatte::post_force(int vflag)
 {
   int eflag = eflag_caller;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // compute Coulombic potential = pe[i]/q[i]
   // invoke compute pe/atom
diff --git a/src/MAKE/Makefile.mpi b/src/MAKE/Makefile.mpi
index aebb465454..f30220da3d 100644
--- a/src/MAKE/Makefile.mpi
+++ b/src/MAKE/Makefile.mpi
@@ -12,7 +12,7 @@ SHFLAGS =	-fPIC
 DEPFLAGS =	-M
 
 LINK =		mpicxx
-LINKFLAGS =	-g -O
+LINKFLAGS =	-g -O3
 LIB = 
 SIZE =		size
 
diff --git a/src/MANYBODY/pair_adp.cpp b/src/MANYBODY/pair_adp.cpp
index 4fd19a36c4..68511b8709 100644
--- a/src/MANYBODY/pair_adp.cpp
+++ b/src/MANYBODY/pair_adp.cpp
@@ -133,8 +133,7 @@ void PairADP::compute(int eflag, int vflag)
   double sumlamxx,sumlamyy,sumlamzz,sumlamyz,sumlamxz,sumlamxy;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // grow local arrays if necessary
   // need to be atom->nmax in length
diff --git a/src/MANYBODY/pair_airebo.cpp b/src/MANYBODY/pair_airebo.cpp
index f8221e6381..4502bd9a82 100644
--- a/src/MANYBODY/pair_airebo.cpp
+++ b/src/MANYBODY/pair_airebo.cpp
@@ -108,8 +108,7 @@ PairAIREBO::~PairAIREBO()
 
 void PairAIREBO::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
   pvector[0] = pvector[1] = pvector[2] = 0.0;
 
   REBO_neigh();
diff --git a/src/MANYBODY/pair_atm.cpp b/src/MANYBODY/pair_atm.cpp
index e3be72443e..c157e0763c 100644
--- a/src/MANYBODY/pair_atm.cpp
+++ b/src/MANYBODY/pair_atm.cpp
@@ -82,8 +82,7 @@ void PairATM::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_bop.cpp b/src/MANYBODY/pair_bop.cpp
index 6540dedf98..ac157e071c 100644
--- a/src/MANYBODY/pair_bop.cpp
+++ b/src/MANYBODY/pair_bop.cpp
@@ -297,8 +297,7 @@ void PairBOP::compute(int eflag, int vflag)
   ilist = list->ilist;
   firstneigh = list->firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // BOP Neighbor lists must be updated every timestep
   maxnall=nall;
diff --git a/src/MANYBODY/pair_comb.cpp b/src/MANYBODY/pair_comb.cpp
index 85ea4812bf..980aa84b2a 100644
--- a/src/MANYBODY/pair_comb.cpp
+++ b/src/MANYBODY/pair_comb.cpp
@@ -144,8 +144,7 @@ void PairComb::compute(int eflag, int vflag)
   int sht_jnum, *sht_jlist, nj;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // Build short range neighbor list
 
diff --git a/src/MANYBODY/pair_comb3.cpp b/src/MANYBODY/pair_comb3.cpp
index d82f6dfed0..097f235ff2 100644
--- a/src/MANYBODY/pair_comb3.cpp
+++ b/src/MANYBODY/pair_comb3.cpp
@@ -987,8 +987,7 @@ void PairComb3::compute(int eflag, int vflag)
 
   evdwl = eng_tmp = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // Build short range neighbor list
   Short_neigh();
diff --git a/src/MANYBODY/pair_eam.cpp b/src/MANYBODY/pair_eam.cpp
index f4b4901075..b7957349b6 100644
--- a/src/MANYBODY/pair_eam.cpp
+++ b/src/MANYBODY/pair_eam.cpp
@@ -142,8 +142,7 @@ void PairEAM::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // grow energy and fp arrays if necessary
   // need to be atom->nmax in length
diff --git a/src/MANYBODY/pair_eam_cd.cpp b/src/MANYBODY/pair_eam_cd.cpp
index 8db1b6dd9a..c111c6d950 100644
--- a/src/MANYBODY/pair_eam_cd.cpp
+++ b/src/MANYBODY/pair_eam_cd.cpp
@@ -73,8 +73,7 @@ void PairEAMCD::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // Grow per-atom arrays if necessary
 
diff --git a/src/MANYBODY/pair_eim.cpp b/src/MANYBODY/pair_eim.cpp
index b0fa1b1eef..f1c028ef38 100644
--- a/src/MANYBODY/pair_eim.cpp
+++ b/src/MANYBODY/pair_eim.cpp
@@ -113,8 +113,7 @@ void PairEIM::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // grow energy array if necessary
 
diff --git a/src/MANYBODY/pair_gw.cpp b/src/MANYBODY/pair_gw.cpp
index 7649090a99..e4b74f7a29 100644
--- a/src/MANYBODY/pair_gw.cpp
+++ b/src/MANYBODY/pair_gw.cpp
@@ -87,8 +87,7 @@ void PairGW::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_lcbop.cpp b/src/MANYBODY/pair_lcbop.cpp
index 0c8b3ef2a6..05cdea8055 100644
--- a/src/MANYBODY/pair_lcbop.cpp
+++ b/src/MANYBODY/pair_lcbop.cpp
@@ -87,8 +87,7 @@ PairLCBOP::~PairLCBOP()
 
 void PairLCBOP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   SR_neigh();
   FSR(eflag,vflag);
diff --git a/src/MANYBODY/pair_nb3b_harmonic.cpp b/src/MANYBODY/pair_nb3b_harmonic.cpp
index ce449e4890..a61b403459 100644
--- a/src/MANYBODY/pair_nb3b_harmonic.cpp
+++ b/src/MANYBODY/pair_nb3b_harmonic.cpp
@@ -87,8 +87,7 @@ void PairNb3bHarmonic::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_polymorphic.cpp b/src/MANYBODY/pair_polymorphic.cpp
index 41c5892d4e..d3aca4e889 100644
--- a/src/MANYBODY/pair_polymorphic.cpp
+++ b/src/MANYBODY/pair_polymorphic.cpp
@@ -117,8 +117,7 @@ void PairPolymorphic::compute(int eflag, int vflag)
   double emb;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_sw.cpp b/src/MANYBODY/pair_sw.cpp
index 91e11b3d26..5a148fb152 100644
--- a/src/MANYBODY/pair_sw.cpp
+++ b/src/MANYBODY/pair_sw.cpp
@@ -91,8 +91,7 @@ void PairSW::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_tersoff.cpp b/src/MANYBODY/pair_tersoff.cpp
index 54101aef9e..213b1037bb 100644
--- a/src/MANYBODY/pair_tersoff.cpp
+++ b/src/MANYBODY/pair_tersoff.cpp
@@ -93,8 +93,7 @@ void PairTersoff::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_vashishta.cpp b/src/MANYBODY/pair_vashishta.cpp
index b4c3086ca8..3d4b1d900e 100644
--- a/src/MANYBODY/pair_vashishta.cpp
+++ b/src/MANYBODY/pair_vashishta.cpp
@@ -93,8 +93,7 @@ void PairVashishta::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MANYBODY/pair_vashishta_table.cpp b/src/MANYBODY/pair_vashishta_table.cpp
index 1055db99fa..d4eaa59f1a 100644
--- a/src/MANYBODY/pair_vashishta_table.cpp
+++ b/src/MANYBODY/pair_vashishta_table.cpp
@@ -64,8 +64,7 @@ void PairVashishtaTable::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MC/fix_bond_break.cpp b/src/MC/fix_bond_break.cpp
index a1c9bb3ab0..05edc0509e 100644
--- a/src/MC/fix_bond_break.cpp
+++ b/src/MC/fix_bond_break.cpp
@@ -800,26 +800,27 @@ void FixBondBreak::print_bb()
   for (int i = 0; i < atom->nlocal; i++) {
     printf("TAG " TAGINT_FORMAT ": %d nbonds: ",atom->tag[i],atom->num_bond[i]);
     for (int j = 0; j < atom->num_bond[i]; j++) {
-      printf(" %d",atom->bond_atom[i][j]);
+      printf(" " TAGINT_FORMAT, atom->bond_atom[i][j]);
     }
     printf("\n");
     printf("TAG " TAGINT_FORMAT ": %d nangles: ",atom->tag[i],atom->num_angle[i]);
     for (int j = 0; j < atom->num_angle[i]; j++) {
-      printf(" %d %d %d,",atom->angle_atom1[i][j],
-             atom->angle_atom2[i][j],atom->angle_atom3[i][j]);
+      printf(" " TAGINT_FORMAT " " TAGINT_FORMAT " " TAGINT_FORMAT ",",
+             atom->angle_atom1[i][j],atom->angle_atom2[i][j],
+             atom->angle_atom3[i][j]);
     }
     printf("\n");
     printf("TAG " TAGINT_FORMAT ": %d ndihedrals: ",atom->tag[i],atom->num_dihedral[i]);
     for (int j = 0; j < atom->num_dihedral[i]; j++) {
-      printf(" %d %d %d %d,",atom->dihedral_atom1[i][j],
-             atom->dihedral_atom2[i][j],atom->dihedral_atom3[i][j],
-             atom->dihedral_atom4[i][j]);
+      printf(" " TAGINT_FORMAT " " TAGINT_FORMAT " " TAGINT_FORMAT " " TAGINT_FORMAT ",",
+             atom->dihedral_atom1[i][j],atom->dihedral_atom2[i][j],
+             atom->dihedral_atom3[i][j],atom->dihedral_atom4[i][j]);
     }
     printf("\n");
     printf("TAG " TAGINT_FORMAT ": %d %d %d nspecial: ",atom->tag[i],
            atom->nspecial[i][0],atom->nspecial[i][1],atom->nspecial[i][2]);
     for (int j = 0; j < atom->nspecial[i][2]; j++) {
-      printf(" %d",atom->special[i][j]);
+      printf(" " TAGINT_FORMAT, atom->special[i][j]);
     }
     printf("\n");
   }
@@ -830,7 +831,7 @@ void FixBondBreak::print_bb()
 void FixBondBreak::print_copy(const char *str, tagint m,
                               int n1, int n2, int n3, int *v)
 {
-  printf("%s %i: %d %d %d nspecial: ",str,m,n1,n2,n3);
+  printf("%s " TAGINT_FORMAT ": %d %d %d nspecial: ",str,m,n1,n2,n3);
   for (int j = 0; j < n3; j++) printf(" %d",v[j]);
   printf("\n");
 }
diff --git a/src/MESSAGE/fix_client_md.cpp b/src/MESSAGE/fix_client_md.cpp
index 9c1bfcc796..727481dcc0 100644
--- a/src/MESSAGE/fix_client_md.cpp
+++ b/src/MESSAGE/fix_client_md.cpp
@@ -89,7 +89,7 @@ FixClientMD::~FixClientMD()
 
   int nfield;
   int *fieldID,*fieldtype,*fieldlen;
-  int msgID = cs->recv(nfield,fieldID,fieldtype,fieldlen);
+  cs->recv(nfield,fieldID,fieldtype,fieldlen);
 
   // clean-up
 
@@ -173,8 +173,6 @@ void FixClientMD::min_setup(int vflag)
 
 void FixClientMD::post_force(int vflag)
 {
-  int i,j,m;
-
   // energy and virial setup
 
   if (vflag) v_setup(vflag);
@@ -286,7 +284,7 @@ void FixClientMD::receive_fev(int vflag)
   int nfield;
   int *fieldID,*fieldtype,*fieldlen;
 
-  int msgID = cs->recv(nfield,fieldID,fieldtype,fieldlen);
+  cs->recv(nfield,fieldID,fieldtype,fieldlen);
 
   double *forces = (double *) cs->unpack(FORCES);
   double **f = atom->f;
diff --git a/src/MESSAGE/message.cpp b/src/MESSAGE/message.cpp
index e9bff7d38a..61221ca26e 100644
--- a/src/MESSAGE/message.cpp
+++ b/src/MESSAGE/message.cpp
@@ -22,10 +22,6 @@
 using namespace LAMMPS_NS;
 using namespace CSLIB_NS;
 
-// customize by adding a new server protocol enum
-
-enum{MD,MC};
-
 /* ---------------------------------------------------------------------- */
 
 void Message::command(int narg, char **arg)
@@ -38,12 +34,10 @@ void Message::command(int narg, char **arg)
   else error->all(FLERR,"Illegal message command");
   lmp->clientserver = clientserver;
 
-  // customize by adding a new server protocol
+  // validate supported protocols
 
-  int protocol;
-  if (strcmp(arg[1],"md") == 0) protocol = MD;
-  else if (strcmp(arg[1],"mc") == 0) protocol = MC;
-  else error->all(FLERR,"Unknown message protocol");
+  if ((strcmp(arg[1],"md") != 0) && (strcmp(arg[1],"mc") != 0))
+    error->all(FLERR,"Unknown message protocol");
 
   // instantiate CSlib with chosen communication mode
 
diff --git a/src/MESSAGE/server_mc.cpp b/src/MESSAGE/server_mc.cpp
index 8e9a297912..8152b1f772 100644
--- a/src/MESSAGE/server_mc.cpp
+++ b/src/MESSAGE/server_mc.cpp
@@ -37,8 +37,8 @@ ServerMC::ServerMC(LAMMPS *lmp) : Pointers(lmp) {}
 
 void ServerMC::loop()
 {
-  int i,j,m;
-  double xold[3],xnew[3];
+  int m;
+  double xold[3];
   tagint atomid;
 
   CSlib *cs = (CSlib *) lmp->cslib;
diff --git a/src/MESSAGE/server_md.cpp b/src/MESSAGE/server_md.cpp
index 8debd3a987..bef327616e 100644
--- a/src/MESSAGE/server_md.cpp
+++ b/src/MESSAGE/server_md.cpp
@@ -78,7 +78,7 @@ ServerMD::~ServerMD()
 
 void ServerMD::loop()
 {
-  int i,j,m;
+  int j,m;
 
   // cs = instance of CSlib
 
diff --git a/src/MISC/pair_nm_cut.cpp b/src/MISC/pair_nm_cut.cpp
index 4b1611b137..124832b63e 100644
--- a/src/MISC/pair_nm_cut.cpp
+++ b/src/MISC/pair_nm_cut.cpp
@@ -70,8 +70,7 @@ void PairNMCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MISC/pair_nm_cut_coul_cut.cpp b/src/MISC/pair_nm_cut_coul_cut.cpp
index 999fab1d6e..6a09d579b7 100644
--- a/src/MISC/pair_nm_cut_coul_cut.cpp
+++ b/src/MISC/pair_nm_cut_coul_cut.cpp
@@ -74,8 +74,7 @@ void PairNMCutCoulCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MISC/pair_nm_cut_coul_long.cpp b/src/MISC/pair_nm_cut_coul_long.cpp
index fb82436dba..af21f02881 100644
--- a/src/MISC/pair_nm_cut_coul_long.cpp
+++ b/src/MISC/pair_nm_cut_coul_long.cpp
@@ -90,8 +90,7 @@ void PairNMCutCoulLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_charmm.cpp b/src/MOLECULE/angle_charmm.cpp
index 3608601c1f..efd1c682f7 100644
--- a/src/MOLECULE/angle_charmm.cpp
+++ b/src/MOLECULE/angle_charmm.cpp
@@ -61,8 +61,7 @@ void AngleCharmm::compute(int eflag, int vflag)
   double delxUB,delyUB,delzUB,rsqUB,rUB,dr,rk,forceUB;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_cosine.cpp b/src/MOLECULE/angle_cosine.cpp
index 18763e1b76..6e1b9fa2fb 100644
--- a/src/MOLECULE/angle_cosine.cpp
+++ b/src/MOLECULE/angle_cosine.cpp
@@ -52,8 +52,7 @@ void AngleCosine::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_cosine_delta.cpp b/src/MOLECULE/angle_cosine_delta.cpp
index 6f4f5c20d7..eca10970f2 100644
--- a/src/MOLECULE/angle_cosine_delta.cpp
+++ b/src/MOLECULE/angle_cosine_delta.cpp
@@ -44,8 +44,7 @@ void AngleCosineDelta::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,a,cot,a11,a12,a22,b11,b12,b22,c0,s0,s;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_cosine_periodic.cpp b/src/MOLECULE/angle_cosine_periodic.cpp
index e8dd970b3b..cb0a26871a 100644
--- a/src/MOLECULE/angle_cosine_periodic.cpp
+++ b/src/MOLECULE/angle_cosine_periodic.cpp
@@ -61,8 +61,7 @@ void AngleCosinePeriodic::compute(int eflag, int vflag)
   double tn,tn_1,tn_2,un,un_1,un_2;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_cosine_squared.cpp b/src/MOLECULE/angle_cosine_squared.cpp
index c83ba90a60..28d63344a4 100644
--- a/src/MOLECULE/angle_cosine_squared.cpp
+++ b/src/MOLECULE/angle_cosine_squared.cpp
@@ -62,8 +62,7 @@ void AngleCosineSquared::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_harmonic.cpp b/src/MOLECULE/angle_harmonic.cpp
index d28afd76d6..48b493d9b2 100644
--- a/src/MOLECULE/angle_harmonic.cpp
+++ b/src/MOLECULE/angle_harmonic.cpp
@@ -58,8 +58,7 @@ void AngleHarmonic::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/angle_table.cpp b/src/MOLECULE/angle_table.cpp
index 6c1af54dcf..7dd56ffb76 100644
--- a/src/MOLECULE/angle_table.cpp
+++ b/src/MOLECULE/angle_table.cpp
@@ -72,8 +72,7 @@ void AngleTable::compute(int eflag, int vflag)
   double theta,u,mdu; //mdu: minus du, -du/dx=f
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_fene.cpp b/src/MOLECULE/bond_fene.cpp
index 671290b0ad..c023a7e81e 100644
--- a/src/MOLECULE/bond_fene.cpp
+++ b/src/MOLECULE/bond_fene.cpp
@@ -54,8 +54,7 @@ void BondFENE::compute(int eflag, int vflag)
   double rsq,r0sq,rlogarg,sr2,sr6;
 
   ebond = sr6 = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_fene_expand.cpp b/src/MOLECULE/bond_fene_expand.cpp
index 3e191683fb..b1bfdc6a1b 100644
--- a/src/MOLECULE/bond_fene_expand.cpp
+++ b/src/MOLECULE/bond_fene_expand.cpp
@@ -56,8 +56,7 @@ void BondFENEExpand::compute(int eflag, int vflag)
   double r,rshift,rshiftsq;
 
   ebond = sr6 = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_gromos.cpp b/src/MOLECULE/bond_gromos.cpp
index 57091903af..f65adeb2cb 100644
--- a/src/MOLECULE/bond_gromos.cpp
+++ b/src/MOLECULE/bond_gromos.cpp
@@ -55,8 +55,7 @@ void BondGromos::compute(int eflag, int vflag)
   double delx,dely,delz,ebond,fbond;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_harmonic.cpp b/src/MOLECULE/bond_harmonic.cpp
index fb4581d0d6..cb8434ce6e 100644
--- a/src/MOLECULE/bond_harmonic.cpp
+++ b/src/MOLECULE/bond_harmonic.cpp
@@ -52,8 +52,7 @@ void BondHarmonic::compute(int eflag, int vflag)
   double rsq,r,dr,rk;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_morse.cpp b/src/MOLECULE/bond_morse.cpp
index 06af28f2b0..91dd2dbc49 100644
--- a/src/MOLECULE/bond_morse.cpp
+++ b/src/MOLECULE/bond_morse.cpp
@@ -53,8 +53,7 @@ void BondMorse::compute(int eflag, int vflag)
   double rsq,r,dr,ralpha;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_nonlinear.cpp b/src/MOLECULE/bond_nonlinear.cpp
index 645b081779..9999ead47f 100644
--- a/src/MOLECULE/bond_nonlinear.cpp
+++ b/src/MOLECULE/bond_nonlinear.cpp
@@ -49,8 +49,7 @@ void BondNonlinear::compute(int eflag, int vflag)
   double rsq,r,dr,drsq,lamdasq,denom,denomsq;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/bond_quartic.cpp b/src/MOLECULE/bond_quartic.cpp
index f200030d6c..895202ff00 100644
--- a/src/MOLECULE/bond_quartic.cpp
+++ b/src/MOLECULE/bond_quartic.cpp
@@ -60,8 +60,7 @@ void BondQuartic::compute(int eflag, int vflag)
   double r,rsq,dr,r2,ra,rb,sr2,sr6;
 
   ebond = evdwl = sr6 = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/MOLECULE/bond_table.cpp b/src/MOLECULE/bond_table.cpp
index c75779922a..94e843eb65 100644
--- a/src/MOLECULE/bond_table.cpp
+++ b/src/MOLECULE/bond_table.cpp
@@ -68,8 +68,7 @@ void BondTable::compute(int eflag, int vflag)
   double u,mdu;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/dihedral_charmm.cpp b/src/MOLECULE/dihedral_charmm.cpp
index 2372fae38b..68c62eb4fd 100644
--- a/src/MOLECULE/dihedral_charmm.cpp
+++ b/src/MOLECULE/dihedral_charmm.cpp
@@ -76,8 +76,7 @@ void DihedralCharmm::compute(int eflag, int vflag)
   double forcecoul,forcelj,fpair,ecoul,evdwl;
 
   edihedral = evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/MOLECULE/dihedral_charmmfsw.cpp b/src/MOLECULE/dihedral_charmmfsw.cpp
index 99a5333620..f65d01e9ed 100644
--- a/src/MOLECULE/dihedral_charmmfsw.cpp
+++ b/src/MOLECULE/dihedral_charmmfsw.cpp
@@ -79,8 +79,7 @@ void DihedralCharmmfsw::compute(int eflag, int vflag)
   double forcecoul,forcelj,fpair,ecoul,evdwl;
 
   edihedral = evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/MOLECULE/dihedral_harmonic.cpp b/src/MOLECULE/dihedral_harmonic.cpp
index cb122f4bc2..ddb94dc571 100644
--- a/src/MOLECULE/dihedral_harmonic.cpp
+++ b/src/MOLECULE/dihedral_harmonic.cpp
@@ -67,8 +67,7 @@ void DihedralHarmonic::compute(int eflag, int vflag)
   double c,s,p,sx2,sy2,sz2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/dihedral_helix.cpp b/src/MOLECULE/dihedral_helix.cpp
index ae23b77951..d19731c097 100644
--- a/src/MOLECULE/dihedral_helix.cpp
+++ b/src/MOLECULE/dihedral_helix.cpp
@@ -39,7 +39,10 @@ using namespace MathConst;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralHelix::DihedralHelix(LAMMPS *lmp) : Dihedral(lmp) {}
+DihedralHelix::DihedralHelix(LAMMPS *lmp) : Dihedral(lmp)
+{
+  writedata = 1;
+}
 
 /* ---------------------------------------------------------------------- */
 
@@ -67,8 +70,7 @@ void DihedralHelix::compute(int eflag, int vflag)
   double s2,cx,cy,cz,cmag,dx,phi,si,siinv,sin2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/dihedral_multi_harmonic.cpp b/src/MOLECULE/dihedral_multi_harmonic.cpp
index f6461abb6e..04e7bbb627 100644
--- a/src/MOLECULE/dihedral_multi_harmonic.cpp
+++ b/src/MOLECULE/dihedral_multi_harmonic.cpp
@@ -34,7 +34,10 @@ using namespace LAMMPS_NS;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralMultiHarmonic::DihedralMultiHarmonic(LAMMPS *lmp) : Dihedral(lmp) {}
+DihedralMultiHarmonic::DihedralMultiHarmonic(LAMMPS *lmp) : Dihedral(lmp)
+{
+  writedata = 1;
+}
 
 /* ---------------------------------------------------------------------- */
 
@@ -64,8 +67,7 @@ void DihedralMultiHarmonic::compute(int eflag, int vflag)
   double s2,sin2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/dihedral_opls.cpp b/src/MOLECULE/dihedral_opls.cpp
index b5103413b2..293245e411 100644
--- a/src/MOLECULE/dihedral_opls.cpp
+++ b/src/MOLECULE/dihedral_opls.cpp
@@ -67,8 +67,7 @@ void DihedralOPLS::compute(int eflag, int vflag)
   double s2,cx,cy,cz,cmag,dx,phi,si,siinv,sin2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/fix_cmap.cpp b/src/MOLECULE/fix_cmap.cpp
index ec2588e61b..3395c7ef14 100644
--- a/src/MOLECULE/fix_cmap.cpp
+++ b/src/MOLECULE/fix_cmap.cpp
@@ -341,8 +341,7 @@ void FixCMAP::post_force(int vflag)
 
   ecmap = 0.0;
   int eflag = eflag_caller;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   for (n = 0; n < ncrosstermlist; n++) {
     i1 = crosstermlist[n][0];
diff --git a/src/MOLECULE/improper_cvff.cpp b/src/MOLECULE/improper_cvff.cpp
index 641eea74a8..01e9729e80 100644
--- a/src/MOLECULE/improper_cvff.cpp
+++ b/src/MOLECULE/improper_cvff.cpp
@@ -61,8 +61,7 @@ void ImproperCvff::compute(int eflag, int vflag)
   double a33,a12,a13,a23,sx2,sy2,sz2;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/improper_harmonic.cpp b/src/MOLECULE/improper_harmonic.cpp
index 091bd46316..c5421fffdb 100644
--- a/src/MOLECULE/improper_harmonic.cpp
+++ b/src/MOLECULE/improper_harmonic.cpp
@@ -61,8 +61,7 @@ void ImproperHarmonic::compute(int eflag, int vflag)
   double sx2,sy2,sz2;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/improper_umbrella.cpp b/src/MOLECULE/improper_umbrella.cpp
index 8ed3d3a84c..3de46df0f3 100644
--- a/src/MOLECULE/improper_umbrella.cpp
+++ b/src/MOLECULE/improper_umbrella.cpp
@@ -65,8 +65,7 @@ void ImproperUmbrella::compute(int eflag, int vflag)
   double ax,ay,az,ra2,rh2,ra,rh,rar,rhr,arx,ary,arz,hrx,hry,hrz;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_hbond_dreiding_lj.cpp b/src/MOLECULE/pair_hbond_dreiding_lj.cpp
index c0c885d4d4..ddc1110081 100644
--- a/src/MOLECULE/pair_hbond_dreiding_lj.cpp
+++ b/src/MOLECULE/pair_hbond_dreiding_lj.cpp
@@ -91,8 +91,7 @@ void PairHbondDreidingLJ::compute(int eflag, int vflag)
   tagint *klist;
 
   evdwl = ehbond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_hbond_dreiding_morse.cpp b/src/MOLECULE/pair_hbond_dreiding_morse.cpp
index f464d2c621..055f0ed46b 100644
--- a/src/MOLECULE/pair_hbond_dreiding_morse.cpp
+++ b/src/MOLECULE/pair_hbond_dreiding_morse.cpp
@@ -61,8 +61,7 @@ void PairHbondDreidingMorse::compute(int eflag, int vflag)
   tagint *klist;
 
   evdwl = ehbond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_lj_charmm_coul_charmm.cpp b/src/MOLECULE/pair_lj_charmm_coul_charmm.cpp
index 688c675815..af4611e014 100644
--- a/src/MOLECULE/pair_lj_charmm_coul_charmm.cpp
+++ b/src/MOLECULE/pair_lj_charmm_coul_charmm.cpp
@@ -43,8 +43,9 @@ PairLJCharmmCoulCharmm::PairLJCharmmCoulCharmm(LAMMPS *lmp) : Pair(lmp)
 
 PairLJCharmmCoulCharmm::~PairLJCharmmCoulCharmm()
 {
-  if (!copymode) {
-   if (allocated) {
+  if (copymode) return;
+
+  if (allocated) {
     memory->destroy(setflag);
     memory->destroy(cutsq);
 
@@ -60,7 +61,6 @@ PairLJCharmmCoulCharmm::~PairLJCharmmCoulCharmm()
     memory->destroy(lj14_2);
     memory->destroy(lj14_3);
     memory->destroy(lj14_4);
-   }
   }
 }
 
@@ -75,8 +75,7 @@ void PairLJCharmmCoulCharmm::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_lj_charmm_coul_charmm_implicit.cpp b/src/MOLECULE/pair_lj_charmm_coul_charmm_implicit.cpp
index 6c083a49b0..d68d5e8f6d 100644
--- a/src/MOLECULE/pair_lj_charmm_coul_charmm_implicit.cpp
+++ b/src/MOLECULE/pair_lj_charmm_coul_charmm_implicit.cpp
@@ -39,8 +39,7 @@ void PairLJCharmmCoulCharmmImplicit::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_lj_charmmfsw_coul_charmmfsh.cpp b/src/MOLECULE/pair_lj_charmmfsw_coul_charmmfsh.cpp
index 4b9147c169..0e1cbd85a5 100644
--- a/src/MOLECULE/pair_lj_charmmfsw_coul_charmmfsh.cpp
+++ b/src/MOLECULE/pair_lj_charmmfsw_coul_charmmfsh.cpp
@@ -62,26 +62,6 @@ PairLJCharmmfswCoulCharmmfsh::PairLJCharmmfswCoulCharmmfsh(LAMMPS *lmp) :
 
 PairLJCharmmfswCoulCharmmfsh::~PairLJCharmmfswCoulCharmmfsh()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
-
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(eps14);
-      memory->destroy(sigma14);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(lj14_1);
-      memory->destroy(lj14_2);
-      memory->destroy(lj14_3);
-      memory->destroy(lj14_4);
-    }
-  }
-
   // switch qqr2e back from CHARMM value to LAMMPS value
 
   if (update && strcmp(update->unit_style,"real") == 0) {
@@ -90,6 +70,26 @@ PairLJCharmmfswCoulCharmmfsh::~PairLJCharmmfswCoulCharmmfsh()
                      " conversion constant");
     force->qqr2e = force->qqr2e_lammps_real;
   }
+
+  if (copymode) return;
+
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(eps14);
+    memory->destroy(sigma14);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(lj14_1);
+    memory->destroy(lj14_2);
+    memory->destroy(lj14_3);
+    memory->destroy(lj14_4);
+  }
 }
 
 /* ---------------------------------------------------------------------- */
@@ -103,8 +103,7 @@ void PairLJCharmmfswCoulCharmmfsh::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/MOLECULE/pair_lj_cut_tip4p_cut.cpp b/src/MOLECULE/pair_lj_cut_tip4p_cut.cpp
index 92dead8435..2b3d2c60f5 100644
--- a/src/MOLECULE/pair_lj_cut_tip4p_cut.cpp
+++ b/src/MOLECULE/pair_lj_cut_tip4p_cut.cpp
@@ -91,8 +91,7 @@ void PairLJCutTIP4PCut::compute(int eflag, int vflag)
   double *x1,*x2,*xH1,*xH2;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/MOLECULE/pair_tip4p_cut.cpp b/src/MOLECULE/pair_tip4p_cut.cpp
index 79dd79b180..e6fb9aab99 100644
--- a/src/MOLECULE/pair_tip4p_cut.cpp
+++ b/src/MOLECULE/pair_tip4p_cut.cpp
@@ -79,8 +79,7 @@ void PairTIP4PCut::compute(int eflag, int vflag)
   double *x1,*x2,*xH1,*xH2;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/Makefile b/src/Makefile
index f1030ae08f..3be4e3e78f 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -275,7 +275,8 @@ mpi-stubs:
 
 sinclude ../lib/python/Makefile.lammps
 install-python:
-	@$(PYTHON) ../python/install.py
+	@$(PYTHON) ../python/install.py -v ../src/version.h \
+		-m ../python/lammps.py -l ../src/liblammps.so
 
 # Create a tarball of src dir and packages
 
diff --git a/src/OPT/pair_eam_opt.cpp b/src/OPT/pair_eam_opt.cpp
index 5345d7f8d6..fc2b6731ee 100644
--- a/src/OPT/pair_eam_opt.cpp
+++ b/src/OPT/pair_eam_opt.cpp
@@ -38,8 +38,7 @@ PairEAMOpt::PairEAMOpt(LAMMPS *lmp) : PairEAM(lmp) {}
 
 void PairEAMOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/OPT/pair_lj_charmm_coul_long_opt.cpp b/src/OPT/pair_lj_charmm_coul_long_opt.cpp
index 43f4ba7f5a..d80d3d1ec4 100644
--- a/src/OPT/pair_lj_charmm_coul_long_opt.cpp
+++ b/src/OPT/pair_lj_charmm_coul_long_opt.cpp
@@ -44,8 +44,7 @@ PairLJCharmmCoulLongOpt::PairLJCharmmCoulLongOpt(LAMMPS *lmp) :
 
 void PairLJCharmmCoulLongOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/OPT/pair_lj_cut_coul_long_opt.cpp b/src/OPT/pair_lj_cut_coul_long_opt.cpp
index 98683a67a4..a25010cf1f 100644
--- a/src/OPT/pair_lj_cut_coul_long_opt.cpp
+++ b/src/OPT/pair_lj_cut_coul_long_opt.cpp
@@ -38,8 +38,7 @@ PairLJCutCoulLongOpt::PairLJCutCoulLongOpt(LAMMPS *lmp) : PairLJCutCoulLong(lmp)
 
 void PairLJCutCoulLongOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (!ncoultablebits) {
     if (evflag) {
diff --git a/src/OPT/pair_lj_cut_opt.cpp b/src/OPT/pair_lj_cut_opt.cpp
index ed35178c1f..c6684461be 100644
--- a/src/OPT/pair_lj_cut_opt.cpp
+++ b/src/OPT/pair_lj_cut_opt.cpp
@@ -34,8 +34,7 @@ PairLJCutOpt::PairLJCutOpt(LAMMPS *lmp) : PairLJCut(lmp) {}
 
 void PairLJCutOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/OPT/pair_lj_cut_tip4p_long_opt.cpp b/src/OPT/pair_lj_cut_tip4p_long_opt.cpp
index 4842cc4fc0..92facca43e 100644
--- a/src/OPT/pair_lj_cut_tip4p_long_opt.cpp
+++ b/src/OPT/pair_lj_cut_tip4p_long_opt.cpp
@@ -53,8 +53,7 @@ PairLJCutTIP4PLongOpt::PairLJCutTIP4PLongOpt(LAMMPS *lmp) :
 
 void PairLJCutTIP4PLongOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/OPT/pair_lj_long_coul_long_opt.cpp b/src/OPT/pair_lj_long_coul_long_opt.cpp
index 6bd1e8cb96..243b64391f 100644
--- a/src/OPT/pair_lj_long_coul_long_opt.cpp
+++ b/src/OPT/pair_lj_long_coul_long_opt.cpp
@@ -44,8 +44,7 @@ PairLJLongCoulLongOpt::PairLJLongCoulLongOpt(LAMMPS *lmp) : PairLJLongCoulLong(l
 void PairLJLongCoulLongOpt::compute(int eflag, int vflag)
 {
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
   int order1 = ewald_order&(1<<1), order6 = ewald_order&(1<<6);
 
   if (order6) {
@@ -290,8 +289,7 @@ void PairLJLongCoulLongOpt::compute(int eflag, int vflag)
 void PairLJLongCoulLongOpt::compute_outer(int eflag, int vflag)
 {
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
   int order1 = ewald_order&(1<<1), order6 = ewald_order&(1<<6);
 
   if (order6) {
diff --git a/src/OPT/pair_morse_opt.cpp b/src/OPT/pair_morse_opt.cpp
index 6299136f46..c9c6bba355 100644
--- a/src/OPT/pair_morse_opt.cpp
+++ b/src/OPT/pair_morse_opt.cpp
@@ -35,8 +35,7 @@ PairMorseOpt::PairMorseOpt(LAMMPS *lmp) : PairMorse(lmp) {}
 
 void PairMorseOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/OPT/pair_ufm_opt.cpp b/src/OPT/pair_ufm_opt.cpp
index 85c76d624d..f463dac3f1 100644
--- a/src/OPT/pair_ufm_opt.cpp
+++ b/src/OPT/pair_ufm_opt.cpp
@@ -34,8 +34,7 @@ PairUFMOpt::PairUFMOpt(LAMMPS *lmp) : PairUFM(lmp) {}
 
 void PairUFMOpt::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/PERI/pair_peri_eps.cpp b/src/PERI/pair_peri_eps.cpp
index 76267426c6..c00495ba4d 100644
--- a/src/PERI/pair_peri_eps.cpp
+++ b/src/PERI/pair_peri_eps.cpp
@@ -96,8 +96,7 @@ void PairPeriEPS::compute(int eflag, int vflag)
   double d_ij,delta,stretch;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **f = atom->f;
   double **x = atom->x;
diff --git a/src/PERI/pair_peri_lps.cpp b/src/PERI/pair_peri_lps.cpp
index 383b91c6f5..f0418c8c8d 100644
--- a/src/PERI/pair_peri_lps.cpp
+++ b/src/PERI/pair_peri_lps.cpp
@@ -93,8 +93,7 @@ void PairPeriLPS::compute(int eflag, int vflag)
   double d_ij,delta,stretch;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **f = atom->f;
   double **x = atom->x;
diff --git a/src/PERI/pair_peri_pmb.cpp b/src/PERI/pair_peri_pmb.cpp
index 772e47f2d6..ad2f3fb7c7 100644
--- a/src/PERI/pair_peri_pmb.cpp
+++ b/src/PERI/pair_peri_pmb.cpp
@@ -84,8 +84,7 @@ void PairPeriPMB::compute(int eflag, int vflag)
   double d_ij,delta,stretch;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **f = atom->f;
   double **x = atom->x;
diff --git a/src/PERI/pair_peri_ves.cpp b/src/PERI/pair_peri_ves.cpp
index 7590077f0e..24a9f92a97 100644
--- a/src/PERI/pair_peri_ves.cpp
+++ b/src/PERI/pair_peri_ves.cpp
@@ -98,8 +98,7 @@ void PairPeriVES::compute(int eflag, int vflag)
   double d_ij,delta,stretch;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   double **f = atom->f;
   double **x = atom->x;
diff --git a/src/PYTHON/pair_python.cpp b/src/PYTHON/pair_python.cpp
index 4899e5e2ef..2148fc67b8 100644
--- a/src/PYTHON/pair_python.cpp
+++ b/src/PYTHON/pair_python.cpp
@@ -82,8 +82,7 @@ void PairPython::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/Purge.list b/src/Purge.list
index 59c35efca5..a02697d2bf 100644
--- a/src/Purge.list
+++ b/src/Purge.list
@@ -25,6 +25,9 @@ style_ntopo.h
 # other auto-generated files
 lmpinstalledpkgs.h
 lmpgitversion.h
+# removed on 15 March 2019
+fix_wall_gran_omp.h
+fix_wall_gran_omp.cpp
 # renamed on 7 January 2019
 pair_lebedeva.cpp
 pair_lebedeva.h
diff --git a/src/REPLICA/fix_hyper_global.cpp b/src/REPLICA/fix_hyper_global.cpp
index d235b06dc0..0c76b29911 100644
--- a/src/REPLICA/fix_hyper_global.cpp
+++ b/src/REPLICA/fix_hyper_global.cpp
@@ -32,12 +32,12 @@
 using namespace LAMMPS_NS;
 using namespace FixConst;
 
-#define DELTA 16384
+#define DELTABOND 16384
 #define VECLEN 5
 
-// NOTE: count/output # of timesteps on which bias is non-zero
-// NOTE: should there be a virial contribution from boosted bond?
-// NOTE: allow newton off?  see Note in pre_reverse()
+// possible enhancements
+//   should there be a virial contribution from boosted bond?
+//   allow newton off?
 
 /* ---------------------------------------------------------------------- */
 
@@ -52,7 +52,7 @@ FixHyperGlobal::FixHyperGlobal(LAMMPS *lmp, int narg, char **arg) :
   hyperflag = 1;
   scalar_flag = 1;
   vector_flag = 1;
-  size_vector = 11;
+  size_vector = 12;
   global_freq = 1;
   extscalar = 0;
   extvector = 0;
@@ -76,6 +76,7 @@ FixHyperGlobal::FixHyperGlobal(LAMMPS *lmp, int narg, char **arg) :
   maxold = 0;
   xold = NULL;
   tagold = NULL;
+  old2now = NULL;
 
   me = comm->me;
   firstflag = 1;
@@ -94,6 +95,7 @@ FixHyperGlobal::~FixHyperGlobal()
   memory->sfree(blist);
   memory->destroy(xold);
   memory->destroy(tagold);
+  memory->destroy(old2now);
 }
 
 /* ---------------------------------------------------------------------- */
@@ -102,7 +104,6 @@ int FixHyperGlobal::setmask()
 {
   int mask = 0;
   mask |= PRE_NEIGHBOR;
-  mask |= PRE_FORCE;
   mask |= PRE_REVERSE;
   mask |= THERMO_ENERGY;
   return mask;
@@ -115,6 +116,7 @@ void FixHyperGlobal::init_hyper()
   maxdriftsq = 0.0;
   maxbondlen = 0.0;
   nobias = 0;
+  negstrain = 0;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -124,6 +126,10 @@ void FixHyperGlobal::init()
   if (force->newton_pair == 0)
     error->all(FLERR,"Hyper global requires newton pair on");
 
+  if (atom->molecular && me == 0)
+    error->warning(FLERR,"Hyper global for molecular systems "
+                   "requires care in defining hyperdynamic bonds");
+
   dt = update->dt;
 
   // need an occasional half neighbor list
@@ -152,14 +158,16 @@ void FixHyperGlobal::setup_pre_neighbor()
 
 void FixHyperGlobal::setup_pre_reverse(int eflag, int vflag)
 {
-  // no increment in nobias or hyper time when pre-run forces are calculated
+  // no increment in these quantities when pre-run forces are calculated
 
   int nobias_hold = nobias;
+  int negstrain_hold = negstrain;
   double t_hyper_hold = t_hyper;
 
   pre_reverse(eflag,vflag);
 
   nobias = nobias_hold;
+  negstrain = negstrain_hold;
   t_hyper = t_hyper_hold;
 }
 
@@ -167,35 +175,50 @@ void FixHyperGlobal::setup_pre_reverse(int eflag, int vflag)
 
 void FixHyperGlobal::pre_neighbor()
 {
-  int m,iold,jold,ilocal,jlocal;
-  double distsq;
+  int i,m,iold,jold,ilocal,jlocal;
+  // double distsq;
 
-  // reset local IDs for owned bond atoms, since atoms have migrated
-  // uses xold and tagold from when bonds were created
+  // reset local indices for owned bond atoms, since atoms have migrated
   // must be done after ghost atoms are setup via comm->borders()
+  // first time this is done for a particular I or J atom:
+  //   use tagold and xold from when bonds were created
+  //   atom->map() finds atom ID if it exists, owned index if possible
+  //   closest current I or J atoms to old I may now be ghost atoms
+  //   closest_image() returns the ghost atom index in that case
+  // also compute max drift of any atom in a bond
+  //   drift = displacement from quenched coord while event has not yet occured
+  // NOTE: drift calc is now done in bond_build(), between 2 quenched states
 
-  double **x = atom->x;
-
-  int flag = 0;
+  for (i = 0; i < nall_old; i++) old2now[i] = -1;
 
   for (m = 0; m < nblocal; m++) {
     iold = blist[m].iold;
     jold = blist[m].jold;
-    ilocal = atom->map(tagold[iold]);
-    jlocal = atom->map(tagold[jold]);
-    ilocal = domain->closest_image(xold[iold],ilocal);
-    jlocal = domain->closest_image(xold[iold],jlocal);
+    ilocal = old2now[iold];
+    jlocal = old2now[jold];
+
+    if (ilocal < 0) {
+      ilocal = atom->map(tagold[iold]);
+      ilocal = domain->closest_image(xold[iold],ilocal);
+      if (ilocal < 0)
+        error->one(FLERR,"Fix hyper/global bond atom not found");
+      old2now[iold] = ilocal;
+      //distsq = MathExtra::distsq3(x[ilocal],xold[iold]);
+      //maxdriftsq = MAX(distsq,maxdriftsq);
+    }
+    if (jlocal < 0) {
+      jlocal = atom->map(tagold[jold]);
+      jlocal = domain->closest_image(xold[iold],jlocal);   // closest to iold
+      if (jlocal < 0)
+        error->one(FLERR,"Fix hyper/global bond atom not found");
+      old2now[jold] = jlocal;
+      //distsq = MathExtra::distsq3(x[jlocal],xold[jold]);
+      //maxdriftsq = MAX(distsq,maxdriftsq);
+    }
+
     blist[m].i = ilocal;
     blist[m].j = jlocal;
-
-    if (ilocal < 0 || jlocal < 0) flag++;
-    else {
-      distsq = MathExtra::distsq3(x[ilocal],xold[iold]);
-      maxdriftsq = MAX(distsq,maxdriftsq);
-    }
   }
-
-  if (flag) error->one(FLERR,"Fix hyper/global bond atom not found");
 }
 
 /* ---------------------------------------------------------------------- */
@@ -204,15 +227,16 @@ void FixHyperGlobal::pre_reverse(int /* eflag */, int /* vflag */)
 {
   int i,j,m,imax,jmax;
   double delx,dely,delz;
-  double r,r0,estrain,rmax,r0max,emax,dt_boost;
-  double vbias,fbias,fbiasr;
+  double r,r0,estrain,rmax,r0max,dt_boost;
+  double ebias,vbias,fbias,fbiasr;
 
   // compute current strain of each owned bond
-  // emax = maximum strain of any bond I own
+  // emax = maximum abs value of strain of any bond I own
   // imax,jmax = local indices of my 2 atoms in that bond
+  // rmax,r0max = current and relaxed lengths of that bond
 
   double **x = atom->x;
-  emax = 0.0;
+  double emax = 0.0;
 
   for (m = 0; m < nblocal; m++) {
     i = blist[m].i;
@@ -255,9 +279,15 @@ void FixHyperGlobal::pre_reverse(int /* eflag */, int /* vflag */)
     return;
   }
 
-  // I own the bond with max strain
-  // compute Vbias and apply force to atoms imax,jmax
-  // NOTE: logic would need to be different for newton off
+  // I own the bond with max absolute value of strain
+  // compute bias force on atoms imax,jmax if strain < q, else zero
+  // Ebias = current strain = (r-r0) / r0
+  // Vbias = bias potential = Vmax (1 - Ebias^2/q^2)
+  // Fbias = bias force as function of strain
+  //       = -dVbias/dEbias = 2 Vmax Ebias / q^2
+  // Fix = x component of force on atom I
+  //     = Fbias dEbias/dr dr/dxi, dEbias/dr = 1/r0, dr/dxi = delx/r
+  // dt_boost = time boost factor = exp(Vbias/kT)
 
   double **f = atom->f;
 
@@ -265,15 +295,16 @@ void FixHyperGlobal::pre_reverse(int /* eflag */, int /* vflag */)
   dt_boost = 1.0;
 
   if (emax < qfactor) {
-    vbias = vmax * (1.0 - emax*emax*invqfactorsq);
-    fbias = 2.0 * vmax * emax / (qfactor*qfactor * r0max);
+    ebias = (rmax-r0max) / r0max;
+    vbias = vmax * (1.0 - ebias*ebias*invqfactorsq);
+    fbias = 2.0 * vmax * ebias * invqfactorsq;
     dt_boost = exp(beta*vbias);
 
     delx = x[imax][0] - x[jmax][0];
     dely = x[imax][1] - x[jmax][1];
     delz = x[imax][2] - x[jmax][2];
 
-    fbiasr = fbias / rmax;
+    fbiasr = fbias / r0max / rmax;
     f[imax][0] += delx*fbiasr;
     f[imax][1] += dely*fbiasr;
     f[imax][2] += delz*fbiasr;
@@ -281,6 +312,9 @@ void FixHyperGlobal::pre_reverse(int /* eflag */, int /* vflag */)
     f[jmax][0] -= delx*fbiasr;
     f[jmax][1] -= dely*fbiasr;
     f[jmax][2] -= delz*fbiasr;
+
+    if (ebias < 0.0) negstrain++;
+
   } else nobias++;
 
   // output quantities
@@ -299,8 +333,8 @@ void FixHyperGlobal::pre_reverse(int /* eflag */, int /* vflag */)
 
 void FixHyperGlobal::build_bond_list(int natom)
 {
-  int i,j,ii,jj,inum,jnum;
-  double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
+  int i,j,m,ii,jj,iold,jold,ilocal,jlocal,inum,jnum;
+  double xtmp,ytmp,ztmp,delx,dely,delz,rsq,distsq;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   if (natom) {
@@ -308,6 +342,27 @@ void FixHyperGlobal::build_bond_list(int natom)
     nevent_atom += natom;
   }
 
+  // compute max distance any bond atom has moved between 2 quenched states
+  // xold[iold] = last quenched coord for iold
+  // x[ilocal] = current quenched coord for same atom
+
+  double **x = atom->x;
+  int nlocal = atom->nlocal;
+  int nall = nlocal + atom->nghost;
+
+  for (m = 0; m < nblocal; m++) {
+    iold = blist[m].iold;
+    ilocal = atom->map(tagold[iold]);
+    ilocal = domain->closest_image(xold[iold],ilocal);
+    distsq = MathExtra::distsq3(x[ilocal],xold[iold]);
+    maxdriftsq = MAX(distsq,maxdriftsq);
+    jold = blist[m].jold;
+    jlocal = atom->map(tagold[jold]);
+    jlocal = domain->closest_image(xold[iold],jlocal);
+    distsq = MathExtra::distsq3(x[jlocal],xold[jold]);
+    maxdriftsq = MAX(distsq,maxdriftsq);
+  }
+
   // trigger neighbor list build
 
   neighbor->build_one(list);
@@ -315,7 +370,6 @@ void FixHyperGlobal::build_bond_list(int natom)
   // identify bonds assigned to each owned atom
   // do not create a bond between two non-group atoms
 
-  double **x = atom->x;
   int *mask = atom->mask;
 
   inum = list->inum;
@@ -358,26 +412,26 @@ void FixHyperGlobal::build_bond_list(int natom)
     }
   }
 
-  // store IDs and coords for owned+ghost atoms at time of bond creation
-  // realloc xold and tagold as needed
+  // store per-atom quantities for owned+ghost atoms at time of bond creation
+  // nall_old = value of nall at time bonds are built
 
-  if (atom->nmax > maxold) {
+  tagint *tag = atom->tag;
+
+  if (nall > maxold) {
     memory->destroy(xold);
     memory->destroy(tagold);
+    memory->destroy(old2now);
     maxold = atom->nmax;
     memory->create(xold,maxold,3,"hyper/global:xold");
     memory->create(tagold,maxold,"hyper/global:tagold");
+    memory->create(old2now,maxold,"hyper/global:old2now");
   }
 
-  tagint *tag = atom->tag;
-  int nall = atom->nlocal + atom->nghost;
+  memcpy(&xold[0][0],&x[0][0],3*nall*sizeof(double));
+  for (i = 0; i < nall; i++) tagold[i] = tag[i];
 
-  for (i = 0; i < nall; i++) {
-    xold[i][0] = x[i][0];
-    xold[i][1] = x[i][1];
-    xold[i][2] = x[i][2];
-    tagold[i] = tag[i];
-  }
+  nlocal_old = nlocal;
+  nall_old = nall;
 }
 
 /* ----------------------------------------------------------------------
@@ -386,14 +440,11 @@ void FixHyperGlobal::build_bond_list(int natom)
 
 void FixHyperGlobal::grow_bond()
 {
-  // NOTE: could add int arg to do initial large alloc:
-  // maxbond = maxbond/DELTA * DELTA; maxbond += DELTA;
-
-  maxbond += DELTA;
-  if (maxbond < 0 || maxbond > MAXSMALLINT)
-    error->one(FLERR,"Fix hyper/local per-processor bond count is too big");
+  if (maxbond + DELTABOND > MAXSMALLINT)
+    error->one(FLERR,"Fix hyper/global bond count is too big");
+  maxbond += DELTABOND;
   blist = (OneBond *)
-    memory->srealloc(blist,maxbond*sizeof(OneBond),"hyper/local:blist");
+    memory->srealloc(blist,maxbond*sizeof(OneBond),"hyper/global:blist");
 }
 
 /* ---------------------------------------------------------------------- */
@@ -416,21 +467,22 @@ double FixHyperGlobal::compute_vector(int i)
     bcastflag = 0;
   }
 
-  // 11 vector outputs returned for i = 0-10
+  // 12 vector outputs returned for i = 0-11
 
   // i = 0 = boost factor on this step
-  // i = 1 = max strain of any bond on this step
+  // i = 1 = max strain of any bond on this step (positive or negative)
   // i = 2 = ID of atom I in max-strain bond on this step
   // i = 3 = ID of atom J in max-strain bond on this step
   // i = 4 = ave bonds/atom on this step
 
-  // i = 5 = fraction of steps with no bias during this run
-  // i = 6 = max drift of any atom during this run
-  // i = 7 = max bond length during this run
+  // i = 5 = fraction of steps where bond has no bias during this run
+  // i = 6 = fraction of steps where bond has negative strain during this run
+  // i = 7 = max drift distance of any atom during this run
+  // i = 8 = max bond length during this run
 
-  // i = 8 = cummulative hyper time since fix created
-  // i = 9 = cummulative # of event timesteps since fix created
-  // i = 10 = cummulative # of atoms in events since fix created
+  // i = 9 = cummulative hyper time since fix created
+  // i = 10 = cummulative # of event timesteps since fix created
+  // i = 11 = cummulative # of atoms in events since fix created
 
   if (i == 0) return outvec[1];
   if (i == 1) return outvec[2];
@@ -438,8 +490,9 @@ double FixHyperGlobal::compute_vector(int i)
   if (i == 3) return outvec[4];
 
   if (i == 4) {
-    int allbonds;     // NOTE: bigint?
-    MPI_Allreduce(&nblocal,&allbonds,1,MPI_INT,MPI_SUM,world);
+    bigint mybonds = nblocal;
+    bigint allbonds;
+    MPI_Allreduce(&mybonds,&allbonds,1,MPI_LMP_BIGINT,MPI_SUM,world);
     return 2.0*allbonds/atom->natoms;
   }
 
@@ -451,20 +504,27 @@ double FixHyperGlobal::compute_vector(int i)
   }
 
   if (i == 6) {
+    if (update->ntimestep == update->firststep) return 0.0;
+    int allnegstrain;
+    MPI_Allreduce(&negstrain,&allnegstrain,1,MPI_INT,MPI_SUM,world);
+    return 1.0*allnegstrain / (update->ntimestep - update->firststep);
+  }
+
+  if (i == 7) {
     double alldriftsq;
     MPI_Allreduce(&maxdriftsq,&alldriftsq,1,MPI_DOUBLE,MPI_MAX,world);
     return sqrt(alldriftsq);
   }
 
-  if (i == 7) {
+  if (i == 8) {
     double allbondlen;
     MPI_Allreduce(&maxbondlen,&allbondlen,1,MPI_DOUBLE,MPI_MAX,world);
     return allbondlen;
   }
 
-  if (i == 8) return t_hyper;
-  if (i == 9) return (double) nevent;
-  if (i == 10) return (double) nevent_atom;
+  if (i == 9) return t_hyper;
+  if (i == 10) return (double) nevent;
+  if (i == 11) return (double) nevent_atom;
 
   return 0.0;
 }
@@ -476,13 +536,14 @@ double FixHyperGlobal::compute_vector(int i)
 
 double FixHyperGlobal::query(int i)
 {
-  if (i == 1) return compute_vector(8);  // cummulative hyper time
-  if (i == 2) return compute_vector(9);  // nevent
-  if (i == 3) return compute_vector(10); // nevent_atom
+  if (i == 1) return compute_vector(9);  // cummulative hyper time
+  if (i == 2) return compute_vector(10); // nevent
+  if (i == 3) return compute_vector(11); // nevent_atom
   if (i == 4) return compute_vector(4);  // ave bonds/atom
-  if (i == 5) return compute_vector(6);  // maxdrift
-  if (i == 6) return compute_vector(7);  // maxbondlen
+  if (i == 5) return compute_vector(7);  // maxdrift
+  if (i == 6) return compute_vector(8);  // maxbondlen
   if (i == 7) return compute_vector(5);  // fraction with zero bias
+  if (i == 8) return compute_vector(6);  // fraction with negative strain
 
   error->all(FLERR,"Invalid query to fix hyper/global");
 
diff --git a/src/REPLICA/fix_hyper_global.h b/src/REPLICA/fix_hyper_global.h
index d8b1cef425..a62f80b54a 100644
--- a/src/REPLICA/fix_hyper_global.h
+++ b/src/REPLICA/fix_hyper_global.h
@@ -56,6 +56,7 @@ class FixHyperGlobal : public FixHyper {
   double maxbondlen;       // max length of any bond
   double maxdriftsq;       // max distance any atom drifts from original pos
   int nobias;              // # of steps when bias = 0, b/c bond too long
+  int negstrain;           // # of steps when biased bond has negative strain
 
   class NeighList *list;
 
@@ -70,16 +71,19 @@ class FixHyperGlobal : public FixHyper {
     double r0;                 // relaxed bond length
   };
 
-  struct OneBond *blist;        // list of owned bonds
-  int nblocal;                  // # of owned bonds
+  OneBond *blist;              // list of owned bonds
+  int nblocal;                 // # of owned bonds
 
   // coords and IDs of owned+ghost atoms when bonds were formed
   // persists on a proc from one event until the next
 
+  int nlocal_old;               // nlocal for old atoms
+  int nall_old;                 // nlocal+nghost for old atoms
   int maxold;                   // allocated size of old atoms
 
   double **xold;                // coords of atoms when bonds were formed
-  tagint *tagold;               // IDs of atoms when bonds were formed
+  tagint *tagold;               // IDs of atoms when bonds were forme
+  int *old2now;                 // o2n[i] = current local index of old atom I
 
   // MPI data struct for finding bond with max strain via Allreduce
 
diff --git a/src/REPLICA/fix_hyper_local.cpp b/src/REPLICA/fix_hyper_local.cpp
index 60198f4ddf..a6db4419f0 100644
--- a/src/REPLICA/fix_hyper_local.cpp
+++ b/src/REPLICA/fix_hyper_local.cpp
@@ -1,4 +1,4 @@
-/* ----------------------------------------------------------------------
+ /* ----------------------------------------------------------------------
    LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
    http://lammps.sandia.gov, Sandia National Laboratories
    Steve Plimpton, sjplimp@sandia.gov
@@ -33,33 +33,28 @@
 using namespace LAMMPS_NS;
 using namespace FixConst;
 
-#define DELTABOOST 16
-#define BOOSTINIT 1.0
-#define COEFFMAX 1.2
+#define DELTABOND 16384
+#define DELTABIAS 16
+#define COEFFINIT 1.0
+#define FCCBONDS 12
 #define BIG 1.0e20
 
-enum{STRAIN,STRAINREGION,BIASFLAG};
+enum{STRAIN,STRAINDOMAIN,BIASFLAG,BIASCOEFF};
 enum{IGNORE,WARN,ERROR};
 
 /* ---------------------------------------------------------------------- */
 
 FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
-  FixHyper(lmp, narg, arg), old2now(NULL), xold(NULL), tagold(NULL),
-  bonds(NULL), numbond(NULL), maxstrain(NULL), maxstrain_region(NULL),
-  maxstrain_bondindex(NULL), biasflag(NULL), boost(NULL),
-  histo(NULL), allhisto(NULL)
+  FixHyper(lmp, narg, arg), blist(NULL), biascoeff(NULL), numbond(NULL),
+  maxhalf(NULL), eligible(NULL), maxhalfstrain(NULL), old2now(NULL),
+  tagold(NULL), xold(NULL), maxstrain(NULL), maxstrain_domain(NULL),
+  biasflag(NULL), bias(NULL), cpage(NULL), clist(NULL), numcoeff(NULL)
 {
   // error checks
-  // solution for tagint != int is to worry about storing
-  //   local index vs global ID in same variable
-  //   maybe need to declare them all tagint, not int
 
   if (atom->map_style == 0)
     error->all(FLERR,"Fix hyper/local command requires atom map");
 
-  if (sizeof(tagint) != sizeof(int))
-     error->all(FLERR,"Fix hyper/local requires tagint = int");
-
   // parse args
 
   if (narg < 10) error->all(FLERR,"Illegal fix hyper/local command");
@@ -67,7 +62,11 @@ FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
   hyperflag = 2;
   scalar_flag = 1;
   vector_flag = 1;
-  size_vector = 23;
+  size_vector = 21;
+  local_flag = 1;
+  size_local_rows = 0;
+  size_local_cols = 0;
+  local_freq = 1;
 
   global_freq = 1;
   extscalar = 0;
@@ -79,10 +78,10 @@ FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
   tequil = force->numeric(FLERR,arg[6]);
   dcut = force->numeric(FLERR,arg[7]);
   alpha_user = force->numeric(FLERR,arg[8]);
-  boosttarget = force->numeric(FLERR,arg[9]);
+  boost_target = force->numeric(FLERR,arg[9]);
 
   if (cutbond < 0.0 || qfactor < 0.0 || vmax < 0.0 ||
-      tequil <= 0.0 || dcut <= 0.0 || alpha_user <= 0.0 || boosttarget < 1.0)
+      tequil <= 0.0 || dcut <= 0.0 || alpha_user <= 0.0 || boost_target < 1.0)
     error->all(FLERR,"Illegal fix hyper/local command");
 
   invqfactorsq = 1.0 / (qfactor*qfactor);
@@ -92,35 +91,14 @@ FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
 
   // optional args
 
-  histoflag = 0;
-  lostbond = IGNORE;
+  checkghost = 0;
   checkbias = 0;
-  checkcoeff = 0;
 
   int iarg = 10;
   while (iarg < narg) {
-    /*  NOTE: do not enable this yet, need to think about it differently
-    if (strcmp(arg[iarg],"histo") == 0) {
-      if (iarg+5 > narg) error->all(FLERR,"Illegal fix hyper/local command");
-      histoflag = 1;
-      histo_every = force->inumeric(FLERR,arg[iarg+1]);
-      histo_count = force->inumeric(FLERR,arg[iarg+2]);
-      histo_delta = force->numeric(FLERR,arg[iarg+3]);
-      histo_print = force->inumeric(FLERR,arg[iarg+4]);
-      if (histo_every <= 0 || histo_count % 2 ||
-          histo_delta <= 0.0 || histo_print <= 0)
-        error->all(FLERR,"Illegal fix hyper/local command");
-      iarg += 5;
-    */
-
-    if (strcmp(arg[iarg],"lostbond") == 0) {
-      if (iarg+2 > narg) error->all(FLERR,"Illegal fix hyper/local command");
-      if (strcmp(arg[iarg+1],"error") == 0) lostbond = ERROR;
-      else if (strcmp(arg[iarg+1],"warn") == 0) lostbond = WARN;
-      else if (strcmp(arg[iarg+1],"ignore") == 0) lostbond = IGNORE;
-      else error->all(FLERR,"Illegal fix hyper/local command");
-      iarg += 2;
-
+    if (strcmp(arg[iarg],"check/ghost") == 0) {
+      checkghost = 1;
+      iarg++;
     } else if (strcmp(arg[iarg],"check/bias") == 0) {
       if (iarg+3 > narg) error->all(FLERR,"Illegal fix hyper/local command");
       checkbias = 1;
@@ -130,57 +108,59 @@ FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
       else if (strcmp(arg[iarg+2],"ignore") == 0) checkbias_flag = IGNORE;
       else error->all(FLERR,"Illegal fix hyper/local command");
       iarg += 3;
-
-    } else if (strcmp(arg[iarg],"check/coeff") == 0) {
-      if (iarg+3 > narg) error->all(FLERR,"Illegal fix hyper/local command");
-      checkcoeff = 1;
-      checkcoeff_every = force->inumeric(FLERR,arg[iarg+1]);
-      if (strcmp(arg[iarg+2],"error") == 0) checkcoeff_flag = ERROR;
-      else if (strcmp(arg[iarg+2],"warn") == 0) checkcoeff_flag = WARN;
-      else if (strcmp(arg[iarg+2],"ignore") == 0) checkcoeff_flag = IGNORE;
-      else error->all(FLERR,"Illegal fix hyper/local command");
-      iarg += 3;
-
     } else error->all(FLERR,"Illegal fix hyper/local command");
   }
 
   // per-atom data structs
 
-  maxbond = 0;
-  bonds = NULL;
-  numbond = NULL;
+  maxbond = nblocal = 0;
+  blist = NULL;
+  biascoeff = NULL;
+  allbonds = 0;
+
+  maxatom = 0;
   maxstrain = NULL;
-  maxstrain_region = NULL;
-  maxstrain_bondindex = NULL;
+  maxstrain_domain = NULL;
   biasflag = NULL;
 
-  maxold = old_nall = 0;
-  old2now = NULL;
-  xold = NULL;      // NOTE: don't really need except to monitor drift
+  maxlocal = nlocal_old = 0;
+  numbond = NULL;
+  maxhalf = NULL;
+  eligible = NULL;
+  maxhalfstrain = NULL;
+
+  maxall = nall_old = 0;
+  xold = NULL;
   tagold = NULL;
+  old2now = NULL;
 
-  nboost = maxboost = 0;
-  boost = NULL;
+  nbias = maxbias = 0;
+  bias = NULL;
 
+  // data structs for persisting bias coeffs when bond list is reformed
   // maxbondperatom = max # of bonds any atom is part of
-  // will be reset in bond_build()
-  // set comm size needed by this fix
+  // FCCBONDS = 12 is a good estimate for fcc lattices
+  // will be reset in build_bond() if necessary
+
+  maxcoeff = 0;
+  maxbondperatom = FCCBONDS;
+  numcoeff = NULL;
+  clist = NULL;
+  cpage = new MyPage<OneCoeff>;
+  cpage->init(maxbondperatom,1024*maxbondperatom,1);
+
+  // set comm sizes needed by this fix
+  // reverse = 2 is for sending atom index + value, though total likely < 1
+  // reverse comm for bias coeffs has variable size, so not tallied here
 
-  maxbondperatom = 1;
   comm_forward = 1;
-  comm_reverse = 1;
-
-  // perform initial allocation of atom-based arrays
-  // register with Atom class
-
-  grow_arrays(atom->nmax);
-  atom->add_callback(0);
+  comm_reverse = 2;
 
   me = comm->me;
   firstflag = 1;
 
-  allbonds = 0;
-  allboost = 0.0;
+  sumbiascoeff = 0.0;
+  avebiascoeff = 0.0;
 
   starttime = update->ntimestep;
   nostrainyet = 1;
@@ -188,36 +168,33 @@ FixHyperLocal::FixHyperLocal(LAMMPS *lmp, int narg, char **arg) :
   nevent = 0;
   nevent_atom = 0;
   mybias = 0.0;
-
-  histo = allhisto = NULL;
-  if (histoflag) {
-    invhisto_delta = 1.0 / histo_delta;
-    histo_lo = 1.0 - (histo_count/2 * histo_delta);
-    histo = new bigint[histo_count+2];
-    allhisto = new bigint[histo_count+2];
-  }
 }
 
 /* ---------------------------------------------------------------------- */
 
 FixHyperLocal::~FixHyperLocal()
 {
-  memory->destroy(bonds);
-  memory->destroy(numbond);
-
-  atom->delete_callback(id,0);
+  memory->destroy(blist);
+  memory->destroy(biascoeff);
 
   memory->destroy(maxstrain);
-  memory->destroy(maxstrain_region);
-  memory->destroy(maxstrain_bondindex);
+  memory->destroy(maxstrain_domain);
   memory->destroy(biasflag);
 
-  memory->destroy(old2now);
+  memory->destroy(numbond);
+  memory->destroy(maxhalf);
+  memory->destroy(eligible);
+  memory->destroy(maxhalfstrain);
+
   memory->destroy(xold);
   memory->destroy(tagold);
-  memory->destroy(boost);
-  delete [] histo;
-  delete [] allhisto;
+  memory->destroy(old2now);
+
+  memory->destroy(bias);
+
+  memory->destroy(numcoeff);
+  memory->sfree(clist);
+  delete cpage;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -237,24 +214,20 @@ int FixHyperLocal::setmask()
 void FixHyperLocal::init_hyper()
 {
   ghost_toofar = 0;
-  lostbond_partner = 0;
-  lostbond_coeff = 0.0;
   checkbias_count = 0;
-  checkcoeff_count = 0;
   maxdriftsq = 0.0;
   maxbondlen = 0.0;
-  maxboostcoeff = 0.0;
-  minboostcoeff = BIG;
-  sumboostcoeff = 0.0;
-  nboost_running = 0;
+  avebiascoeff = 0.0;
+  minbiascoeff = BIG;
+  maxbiascoeff = 0.0;
+  nbias_running = 0;
   nobias_running = 0;
+  negstrain_running = 0;
   rmaxever = 0.0;
   rmaxeverbig = 0.0;
 
   nbondbuild = 0;
   time_bondbuild = 0.0;
-
-  if (histoflag) histo_steps = 0;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -262,7 +235,7 @@ void FixHyperLocal::init_hyper()
 void FixHyperLocal::init()
 {
   // for newton off, bond force bias will not be applied correctly
-  //   bonds that straddle 2 procs
+  //   for bonds that straddle 2 procs
   // warn if molecular system, since near-neighbors may not appear in neigh list
   //   user should not be including bonded atoms as hyper "bonds"
 
@@ -271,7 +244,7 @@ void FixHyperLocal::init()
 
   if (atom->molecular && me == 0)
     error->warning(FLERR,"Hyper local for molecular systems "
-                   "requires care in defining hyperdynamics bonds");
+                   "requires care in defining hyperdynamic bonds");
 
   // cutghost = communication cutoff as calculated by Neighbor and Comm
   // error if cutghost is smaller than Dcut
@@ -285,30 +258,43 @@ void FixHyperLocal::init()
       cutghost = comm->cutghostuser;
 
     if (cutghost < dcut)
-      error->all(FLERR,"Fix hyper/local bond cutoff exceeds ghost atom range - "
+      error->all(FLERR,"Fix hyper/local domain cutoff exceeds ghost atom range - "
                  "use comm_modify cutoff command");
     if (cutghost < dcut+cutbond/2.0 && me == 0)
       error->warning(FLERR,"Fix hyper/local ghost atom range "
                      "may not allow for atom drift between events");
   }
 
-
   alpha = update->dt / alpha_user;
 
-  // need an occasional full neighbor list with cutoff = Dcut
+  // need occasional full neighbor list with cutoff = Dcut
+  // used for finding maxstrain of neighbor bonds out to Dcut
   // do not need to include neigh skin in cutoff,
-  //   b/c this list will be built every time bond_build() is called
+  //   b/c this list will be built every time build_bond() is called
   // NOTE: what if pair style list cutoff > Dcut
   //   or what if neigh skin is huge?
 
-  int irequest = neighbor->request(this,instance_me);
-  neighbor->requests[irequest]->pair = 0;
-  neighbor->requests[irequest]->fix = 1;
-  neighbor->requests[irequest]->half = 0;
-  neighbor->requests[irequest]->full = 1;
-  neighbor->requests[irequest]->cut = 1;
-  neighbor->requests[irequest]->cutoff = dcut;
-  neighbor->requests[irequest]->occasional = 1;
+  int irequest_full = neighbor->request(this,instance_me);
+  neighbor->requests[irequest_full]->id = 1;
+  neighbor->requests[irequest_full]->pair = 0;
+  neighbor->requests[irequest_full]->fix = 1;
+  neighbor->requests[irequest_full]->half = 0;
+  neighbor->requests[irequest_full]->full = 1;
+  neighbor->requests[irequest_full]->cut = 1;
+  neighbor->requests[irequest_full]->cutoff = dcut;
+  neighbor->requests[irequest_full]->occasional = 1;
+
+  // also need occasional half neighbor list derived from pair style
+  // used for building local bond list
+  // no specified cutoff, should be longer than cutbond
+  // this list will also be built (or derived/copied)
+  //   every time build_bond() is called
+
+  int irequest_half = neighbor->request(this,instance_me);
+  neighbor->requests[irequest_half]->id = 2;
+  neighbor->requests[irequest_half]->pair = 0;
+  neighbor->requests[irequest_half]->fix = 1;
+  neighbor->requests[irequest_half]->occasional = 1;
 
   // extra timing output
 
@@ -318,16 +304,17 @@ void FixHyperLocal::init()
 
 /* ---------------------------------------------------------------------- */
 
-void FixHyperLocal::init_list(int /* id */, NeighList *ptr)
+void FixHyperLocal::init_list(int id, NeighList *ptr)
 {
-  list = ptr;
+  if (id == 1) listfull = ptr;
+  else if (id == 2) listhalf = ptr;
 }
 
 /* ---------------------------------------------------------------------- */
 
 void FixHyperLocal::setup_pre_neighbor()
 {
-  // called for dynamics and minimization   NOTE: check if min is needed?
+  // called for dynamics and minimization
 
   pre_neighbor();
 }
@@ -337,8 +324,9 @@ void FixHyperLocal::setup_pre_neighbor()
 void FixHyperLocal::setup_pre_reverse(int eflag, int vflag)
 {
   // only called for dynamics, not minimization
-  // setupflag prevents boostostat update of boost coeffs in setup
-  // also prevents increments of nboost_running, nbias_running, sumboostcoeff
+  // setupflag prevents boostostat update of bias coeffs in setup
+  // also prevents increments of nbias_running, nobias_running,
+  //   negstrain_running, sumbiascoeff
 
   setupflag = 1;
   pre_reverse(eflag,vflag);
@@ -349,67 +337,66 @@ void FixHyperLocal::setup_pre_reverse(int eflag, int vflag)
 
 void FixHyperLocal::pre_neighbor()
 {
-  int i,m,n,ilocal,jlocal;
+  int i,m,iold,jold,ilocal,jlocal;
+  // double distsq;
 
-  // convert global ID bond partners back to local indices
-  // need to use closest_image() so can calculate bond lengths
-  // error flag should not happen for a well-behaved system
-  // b/c are only looking up bond partners inside or near my sub-domain
+  // reset local indices for owned bond atoms, since atoms have migrated
+  // must be done after ghost atoms are setup via comm->borders()
+  // first time this is done for a particular I or J atom:
+  //   use tagold and xold from when bonds were created
+  //   atom->map() finds atom ID if it exists, owned index if possible
+  //   closest current I or J atoms to old I may now be ghost atoms
+  //   closest_image() returns the ghost atom index in that case
+  // also compute max drift of any atom in a bond
+  //   drift = displacement from quenched coord while event has not yet occured
+  // NOTE: drift calc is now done in bond_build(), between 2 quenched states
 
-  double **x = atom->x;
-  int nlocal = atom->nlocal;
+  for (i = 0; i < nall_old; i++) old2now[i] = -1;
 
-  int missing = 0;
-  double missing_coeff = 0.0;
+  for (m = 0; m < nblocal; m++) {
+    iold = blist[m].iold;
+    jold = blist[m].jold;
+    ilocal = old2now[iold];
+    jlocal = old2now[jold];
 
-  for (i = 0; i < nlocal; i++) {
-    n = numbond[i];
-    for (m = 0; m < n; m++) {
-      jlocal = atom->map(bonds[i][m].jtag);
-      if (jlocal >= 0) bonds[i][m].j = domain->closest_image(i,jlocal);
-      else {
-        bonds[i][m].j = -1;
-        missing++;
-        missing_coeff += bonds[i][m].boostcoeff;
-        if (lostbond != IGNORE) {
-          char str[128];
-          sprintf(str,"Fix hyper/local bond info missing for bond "
-                  TAGINT_FORMAT "," TAGINT_FORMAT
-                  " with coeff %g at step " BIGINT_FORMAT,
-                  atom->tag[i],bonds[i][m].jtag,bonds[i][m].boostcoeff,
-                  update->ntimestep);
-          if (lostbond == ERROR) error->one(FLERR,str);
-          if (lostbond == WARN) error->warning(FLERR,str);
-        }
-      }
+    if (ilocal < 0) {
+      ilocal = atom->map(tagold[iold]);
+      ilocal = domain->closest_image(xold[iold],ilocal);
+      if (ilocal < 0)
+        error->one(FLERR,"Fix hyper/local bond atom not found");
+      old2now[iold] = ilocal;
+      //distsq = MathExtra::distsq3(x[ilocal],xold[iold]);
+      //maxdriftsq = MAX(distsq,maxdriftsq);
     }
+    if (jlocal < 0) {
+      jlocal = atom->map(tagold[jold]);
+      jlocal = domain->closest_image(xold[iold],jlocal);   // close to I atom
+      if (jlocal < 0)
+        error->one(FLERR,"Fix hyper/local bond atom not found");
+      old2now[jold] = jlocal;
+      //distsq = MathExtra::distsq3(x[jlocal],xold[jold]);
+      //maxdriftsq = MAX(distsq,maxdriftsq);
+    }
+
+    blist[m].i = ilocal;
+    blist[m].j = jlocal;
   }
 
-  lostbond_partner += missing;
-  lostbond_coeff += missing_coeff;
-
-  // set old2now to point to current local atom indices
+  // set remaining old2now values to point to current local atom indices
+  // if old2now >= 0, already set by bond loop above
   // only necessary for tagold entries > 0
   //   because if tagold = 0, atom is not active in Dcut neighbor list
   // must be done after atoms migrate and ghost atoms setup via comm->borders()
-  // does not matter if there are multiple ghost copies of a global ID
-  //   since only need the ghost atom strain, not its coordinates
-  // NOTE: maybe need not use closest image, b/c old2now only used to access
-  //   maxstrain values, which will be same for any copy of ghost atom ??
-  //   also need it to compute maxdriftsq correctly when a proc spans a PBC
+  // does not matter which atom (owned or ghost) that atom->map() finds
+  //   b/c old2now is only used to access maxstrain() or biasflag()
+  //   which will be identical for every copy of the same atom ID
 
-  double distsq;
-
-  for (i = 0; i < old_nall; i++) {
-    if (tagold[i] == 0) continue;
-    ilocal = atom->map(tagold[i]);
-    ilocal = domain->closest_image(xold[i],ilocal);
-    old2now[i] = ilocal;
-
-    if (ilocal >= 0) {
-      distsq = MathExtra::distsq3(x[ilocal],xold[i]);
-      maxdriftsq = MAX(distsq,maxdriftsq);
-    } else ghost_toofar++;
+  for (iold = 0; iold < nall_old; iold++) {
+    if (old2now[iold] >= 0) continue;
+    if (tagold[iold] == 0) continue;
+    ilocal = atom->map(tagold[iold]);
+    old2now[iold] = ilocal;
+    if (ilocal < 0) ghost_toofar++;
   }
 }
 
@@ -417,223 +404,262 @@ void FixHyperLocal::pre_neighbor()
 
 void FixHyperLocal::pre_reverse(int /* eflag */, int /* vflag */)
 {
-  int i,j,m,ii,jj,inum,jnum,iold,jold,nbond,bondindex;
-  tagint itag,jtag;
-  double xtmp,ytmp,ztmp,delx,dely,delz;
-  double r,r0,estrain,emax,vbias,fbias,fbiasr,boostcoeff;
+  int i,j,m,ii,jj,inum,jnum,iold,jold,ibond,nbond,ijhalf,ncount;
+  double delx,dely,delz;
+  double r,r0,estrain,emax,ebias,vbias,fbias,fbiasr;
+  double halfstrain,selfstrain;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   //double time1,time2,time3,time4,time5,time6,time7,time8;
   //time1 = MPI_Wtime();
 
-  // compute current maxstrain and maxstrain_bond for each owned atom
-  // use per-atom full bond list
-  // this is double-calculating for IJ and JI bonds
-  //   could compute once, but would have to find/store index of JI bond
-  // order two I,J atoms consistently for IJ and JI calcs
-  //   to insure no round-off issue when comparing maxstrain values of I,J
-
-  double **x = atom->x;
-  tagint *tag = atom->tag;
-  int nlocal = atom->nlocal;
-
-  int mybonds = 0;
   nostrainyet = 0;
 
-  for (i = 0; i < nlocal; i++) {
-    xtmp = x[i][0];
-    ytmp = x[i][1];
-    ztmp = x[i][2];
-    itag = tag[i];
-    emax = 0.0;
-    bondindex = -1;
-    jtag = 0;
+  // reallocate per-atom maxstrain and biasflag vectors if necessary
 
-    nbond = numbond[i];
-    mybonds += nbond;
-    for (m = 0; m < nbond; m++) {
-      j = bonds[i][m].j;
-      if (j < 0) continue;
-      jtag = bonds[i][m].jtag;
-      r0 = bonds[i][m].r0;
-      if (itag < jtag) {
-        delx = xtmp - x[j][0];
-        dely = ytmp - x[j][1];
-        delz = ztmp - x[j][2];
-      } else {
-        delx = x[j][0] - xtmp;
-        dely = x[j][1] - ytmp;
-        delz = x[j][2] - ztmp;;
-      }
+  int nlocal = atom->nlocal;
+  int nall = nlocal + atom->nghost;
+
+  if (maxatom < nall) {
+    memory->destroy(maxstrain);
+    memory->destroy(maxstrain_domain);
+    if (checkbias) memory->destroy(biasflag);
+    maxatom = atom->nmax;
+    memory->create(maxstrain,maxatom,"hyper/local:maxstrain");
+    memory->create(maxstrain_domain,maxatom,"hyper/local:maxstrain_domain");
+    if (checkbias) memory->create(biasflag,maxatom,"hyper/local:biasflag");
+  }
+
+  // one max strain bond per old owned atom is eligible for biasing
+
+  for (iold = 0; iold < nlocal_old; iold++) eligible[iold] = 1;
+
+  // -------------------------------------------------------------
+  // stage 1:
+  // maxstrain[i] = max abs value of strain of any bond atom I is part of
+  // reverse/forward comm so know it for all current owned and ghost atoms
+  // -------------------------------------------------------------
+
+  // compute estrain = current abs value strain of each owned bond
+  // blist = bondlist from last event
+  // mark atom I ineligible if it has no bonds
+  // also store:
+  //   maxhalf = which owned bond is maxstrain for each old atom I
+  //   maxhalfstrain = abs value strain of that bond for each old atom I
+
+  for (i = 0; i < nall; i++) maxstrain[i] = 0.0;
+
+  double **x = atom->x;
+
+  m = 0;
+  for (iold = 0; iold < nlocal_old; iold++) {
+    nbond = numbond[iold];
+    if (!nbond) {
+      eligible[iold] = 0;
+      continue;
+    }
+    halfstrain = 0.0;
+    for (ibond = 0; ibond < nbond; ibond++) {
+      i = blist[m].i;
+      j = blist[m].j;
+      delx = x[i][0] - x[j][0];
+      dely = x[i][1] - x[j][1];
+      delz = x[i][2] - x[j][2];
       r = sqrt(delx*delx + dely*dely + delz*delz);
       maxbondlen = MAX(r,maxbondlen);
+      r0 = blist[m].r0;
       estrain = fabs(r-r0) / r0;
-      if (estrain > emax) {
-        emax = estrain;
-        bondindex = m;
+      maxstrain[i] = MAX(maxstrain[i],estrain);
+      maxstrain[j] = MAX(maxstrain[j],estrain);
+      if (estrain > halfstrain) {
+        halfstrain = estrain;
+        ijhalf = m;
       }
+      m++;
     }
-    maxstrain[i] = emax;
-    maxstrain_bondindex[i] = bondindex;
+    maxhalf[iold] = ijhalf;
+    maxhalfstrain[iold] = halfstrain;
   }
 
   //time2 = MPI_Wtime();
 
-  // forward comm to acquire maxstrain of all ghost atoms
+  // reverse comm acquires maxstrain of all current owned atoms
+  //   needed b/c only saw half the bonds of each atom
+  //   also needed b/c bond list may refer to old owned atoms that are now ghost
+  // forward comm acquires maxstrain of all current ghost atoms
 
   commflag = STRAIN;
+  comm->reverse_comm_fix(this);
   comm->forward_comm_fix(this);
 
   //time3 = MPI_Wtime();
 
-  // use original Dcut neighbor list to check maxstrain of all neighbor atoms
-  // set maxstrain_region of I atoms = maxstrain of I and all J neighs
-  // neighbor list has old indices for IJ b/c reneighboring may have occurred
+  // -------------------------------------------------------------
+  // stage 2:
+  // maxstrain_domain[i] = maxstrain of atom I and all its J neighs out to Dcut
+  // reverse/forward comm so know it for all current owned and ghost atoms
+  // -------------------------------------------------------------
+
+  // use full Dcut neighbor list to check maxstrain of all neighbor atoms
+  // neighlist is from last event
+  //   has old indices for I,J (reneighboring may have occurred)
   //   use old2now[] to convert to current indices
-  // if neighbor is not currently known (too far away),
-  //   then assume it was part of an event and its strain = qfactor
-  // this double loop sets maxstrain_region of mostly owned atoms
-  //   but possibly some ghost atoms as well
+  //   if J is unknown (drifted ghost),
+  //     assume it was part of an event and its strain = qfactor
+  // mark atom I ineligible for biasing if:
+  //   its maxhalfstrain < maxstrain (J atom owns the IJ bond)
+  //   its maxstrain < maxstrain_domain
+  //   ncount > 1 (break tie by making all atoms with tie value ineligible)
+  // if ncount > 1, also flip sign of maxstrain_domain for atom I
 
-  int nall = nlocal + atom->nghost;
-  for (i = 0; i < nall; i++) maxstrain_region[i] = 0.0;
+  for (i = 0; i < nall; i++) maxstrain_domain[i] = 0.0;
 
-  inum = list->inum;
-  ilist = list->ilist;
-  numneigh = list->numneigh;
-  firstneigh = list->firstneigh;
-
-  // find largest distance from subbox that a ghost atom is with strain < qfactor
+  inum = listfull->inum;
+  ilist = listfull->ilist;
+  numneigh = listfull->numneigh;
+  firstneigh = listfull->firstneigh;
 
   double rmax = rmaxever;
   double rmaxbig = rmaxeverbig;
   double *sublo = domain->sublo;
   double *subhi = domain->subhi;
 
+  // first two lines of outer loop should be identical to this:
+  // for (iold = 0; iold < nlocal_old; iold++)
+
   for (ii = 0; ii < inum; ii++) {
     iold = ilist[ii];
+    if (eligible[iold] == 0) continue;
     jlist = firstneigh[iold];
     jnum = numneigh[iold];
 
-    // I and J may be ghost atoms
+    // I or J may be ghost atoms
     // will always know I b/c atoms do not drift that far
     // but may no longer know J if hops outside cutghost
     // in that case, assume it performed an event, its strain = qfactor
+    // this assumes cutghost is sufficiently longer than Dcut
 
     i = old2now[iold];
-    emax = maxstrain[i];
+    emax = selfstrain = maxstrain[i];
+    ncount = 0;
 
     for (jj = 0; jj < jnum; jj++) {
       jold = jlist[jj];
       j = old2now[jold];
-      if (j >= 0) emax = MAX(emax,maxstrain[j]);
-      else {
+
+      // special case for missing (drifted) J atom
+
+      if (j < 0) {
         emax = MAX(emax,qfactor);
+        if (selfstrain == qfactor) ncount++;
         continue;
       }
 
-      if (j >= nlocal) {
-        if (x[j][0] < sublo[0]) rmaxbig = MAX(rmaxbig,sublo[0]-x[j][0]);
-        if (x[j][1] < sublo[1]) rmaxbig = MAX(rmaxbig,sublo[1]-x[j][1]);
-        if (x[j][2] < sublo[2]) rmaxbig = MAX(rmaxbig,sublo[2]-x[j][2]);
-        if (x[j][0] > subhi[0]) rmaxbig = MAX(rmaxbig,x[j][0]-subhi[0]);
-        if (x[j][1] > subhi[1]) rmaxbig = MAX(rmaxbig,x[j][1]-subhi[1]);
-        if (x[j][2] > subhi[2]) rmaxbig = MAX(rmaxbig,x[j][2]-subhi[2]);
-        if (maxstrain[j] < qfactor) {
-          if (x[j][0] < sublo[0]) rmax = MAX(rmax,sublo[0]-x[j][0]);
-          if (x[j][1] < sublo[1]) rmax = MAX(rmax,sublo[1]-x[j][1]);
-          if (x[j][2] < sublo[2]) rmax = MAX(rmax,sublo[2]-x[j][2]);
-          if (x[j][0] > subhi[0]) rmax = MAX(rmax,x[j][0]-subhi[0]);
-          if (x[j][1] > subhi[1]) rmax = MAX(rmax,x[j][1]-subhi[1]);
-          if (x[j][2] > subhi[2]) rmax = MAX(rmax,x[j][2]-subhi[2]);
+      emax = MAX(emax,maxstrain[j]);
+      if (selfstrain == maxstrain[j]) ncount++;
+
+      // optional diagnostic
+      // tally largest distance from subbox that a ghost atom is (rmaxbig)
+      // and the largest distance if strain < qfactor (rmax)
+
+      if (checkghost) {
+        if (j >= nlocal) {
+          if (x[j][0] < sublo[0]) rmaxbig = MAX(rmaxbig,sublo[0]-x[j][0]);
+          if (x[j][1] < sublo[1]) rmaxbig = MAX(rmaxbig,sublo[1]-x[j][1]);
+          if (x[j][2] < sublo[2]) rmaxbig = MAX(rmaxbig,sublo[2]-x[j][2]);
+          if (x[j][0] > subhi[0]) rmaxbig = MAX(rmaxbig,x[j][0]-subhi[0]);
+          if (x[j][1] > subhi[1]) rmaxbig = MAX(rmaxbig,x[j][1]-subhi[1]);
+          if (x[j][2] > subhi[2]) rmaxbig = MAX(rmaxbig,x[j][2]-subhi[2]);
+          if (maxstrain[j] < qfactor) {
+            if (x[j][0] < sublo[0]) rmax = MAX(rmax,sublo[0]-x[j][0]);
+            if (x[j][1] < sublo[1]) rmax = MAX(rmax,sublo[1]-x[j][1]);
+            if (x[j][2] < sublo[2]) rmax = MAX(rmax,sublo[2]-x[j][2]);
+            if (x[j][0] > subhi[0]) rmax = MAX(rmax,x[j][0]-subhi[0]);
+            if (x[j][1] > subhi[1]) rmax = MAX(rmax,x[j][1]-subhi[1]);
+            if (x[j][2] > subhi[2]) rmax = MAX(rmax,x[j][2]-subhi[2]);
+          }
         }
       }
     }
 
-    maxstrain_region[i] = emax;
+    if (maxhalfstrain[iold] < selfstrain) eligible[iold] = 0;
+    if (selfstrain < emax) eligible[iold] = 0;
+    else if (ncount > 1) {
+      eligible[iold] = 0;
+      emax = -emax;
+    }
+    maxstrain_domain[i] = emax;
   }
 
-  double rmax2[2],rmax2all[2];
-  rmax2[0] = rmax;
-  rmax2[1] = rmaxbig;
-  MPI_Allreduce(&rmax2,&rmax2all,2,MPI_DOUBLE,MPI_MAX,world);
-  rmaxever = rmax2all[0];
-  rmaxeverbig = rmax2all[1];
-
-  MPI_Allreduce(&mybonds,&allbonds,1,MPI_INT,MPI_SUM,world);
-
   //time4 = MPI_Wtime();
 
-  // reverse comm to acquire maxstrain_region from ghost atoms
-  // needed b/c neighbor list referred to old owned atoms,
-  //   so above loop may set maxstrain_region of ghost atoms
-  // forward comm to acquire maxstrain_region of all ghost atoms
+  // reverse comm to acquire maxstrain_domain from ghost atoms
+  //   needed b/c neigh list may refer to old owned atoms that are now ghost
+  // forward comm acquires maxstrain_domain of all current ghost atoms
 
-  commflag = STRAINREGION;
+  commflag = STRAINDOMAIN;
   comm->reverse_comm_fix(this);
   comm->forward_comm_fix(this);
 
   //time5 = MPI_Wtime();
 
-  // identify biased bonds and add to boost list
-  // for each max-strain bond IJ of atom I:
-  //   bias this bond only if all these conditions hold:
-  //     itag < jtag, so bond is only biased once
-  //     maxstrain[i] = maxstrain_region[i]
-  //     maxstrain[j] = maxstrain_region[j]
-  // NOTE: also need to check that maxstrain[i] = maxstrain[j] ??
-  //       don't think so, b/c maxstrain_region[i] includes maxstrain[i]
+  // -------------------------------------------------------------
+  // stage 3:
+  // create bias = list of Nbias biased bonds this proc owns
+  // -------------------------------------------------------------
 
-  nboost = 0;
+  // identify biased bonds and add to bias list
+  // bias the I,J maxhalf bond of atom I only if all these conditions hold:
+  //   maxstrain[i] = maxstrain_domain[i] (checked in stage 2)
+  //   maxstrain[j] = maxstrain_domain[j] (checked here)
+  //   I is not part of an I,J bond with > strain owned by some J (checked in 2)
+  //   no ties with other maxstrain bonds in atom I's domain (chedcked in 2)
 
-  for (i = 0; i < nlocal; i++) {
-    if (numbond[i] == 0) continue;
-    itag = tag[i];
-    j = bonds[i][maxstrain_bondindex[i]].j;
-    jtag = tag[j];
-    if (itag > jtag) continue;
-
-    if (maxstrain[i] != maxstrain_region[i]) continue;
-    if (maxstrain[j] != maxstrain_region[j]) continue;
-
-    if (nboost == maxboost) {
-      maxboost += DELTABOOST;
-      memory->grow(boost,maxboost,"hyper/local:boost");
+  nbias = 0;
+  for (iold = 0; iold < nlocal_old; iold++) {
+    if (eligible[iold] == 0) continue;
+    j = blist[maxhalf[iold]].j;
+    if (maxstrain[j] != maxstrain_domain[j]) continue;
+    if (nbias == maxbias) {
+      maxbias += DELTABIAS;
+      memory->grow(bias,maxbias,"hyper/local:bias");
     }
-    boost[nboost++] = i;
+    bias[nbias++] = maxhalf[iold];
   }
 
   //time6 = MPI_Wtime();
 
-  // apply boost force to bonds with locally max strain
+  // -------------------------------------------------------------
+  // stage 4:
+  // apply bias force to bonds with locally max strain
+  // -------------------------------------------------------------
 
   double **f = atom->f;
 
   int nobias = 0;
+  int negstrain = 0;
   mybias = 0.0;
 
-  for (int iboost = 0; iboost < nboost; iboost++) {
-    i = boost[iboost];
-    emax = maxstrain[i];
-    if (emax >= qfactor) {
+  for (int ibias = 0; ibias < nbias; ibias++) {
+    m = bias[ibias];
+    i = blist[m].i;
+    j = blist[m].j;
+
+    if (maxstrain[i] >= qfactor) {
       nobias++;
       continue;
     }
 
-    m = maxstrain_bondindex[i];
-    j = bonds[i][m].j;
-    r0 = bonds[i][m].r0;
-    boostcoeff = bonds[i][m].boostcoeff;
-
-    vbias = boostcoeff * vmax * (1.0 - emax*emax*invqfactorsq);
-    fbias = boostcoeff * 2.0 * vmax * emax / (qfactor*qfactor * r0);
-
     delx = x[i][0] - x[j][0];
     dely = x[i][1] - x[j][1];
     delz = x[i][2] - x[j][2];
     r = sqrt(delx*delx + dely*dely + delz*delz);
-    fbiasr = fbias / r;
+    r0 = blist[m].r0;
+    ebias = (r-r0) / r0;
+    vbias = biascoeff[m] * vmax * (1.0 - ebias*ebias*invqfactorsq);
+    fbias = biascoeff[m] * 2.0 * vmax * ebias * invqfactorsq;
 
+    fbiasr = fbias / r0 / r;
     f[i][0] += delx*fbiasr;
     f[i][1] += dely*fbiasr;
     f[i][2] += delz*fbiasr;
@@ -642,131 +668,102 @@ void FixHyperLocal::pre_reverse(int /* eflag */, int /* vflag */)
     f[j][1] -= dely*fbiasr;
     f[j][2] -= delz*fbiasr;
 
+    if (ebias < 0.0) negstrain++;
     mybias += vbias;
   }
 
   //time7 = MPI_Wtime();
 
-  // no boostostat update of boost coeffs when pre_reverse called from setup()
-  // nboost_running, nobias_running, sumboostcoeff only incremented on run steps
-  // NOTE: maybe should also not bias any bonds on firststep of this fix
+  // -------------------------------------------------------------
+  // apply boostostat to bias coeffs of all bonds I own
+  // -------------------------------------------------------------
+
+  // no boostostat update when pre_reverse called from setup()
+  // nbias_running, nobias_running, negstrain_running only incremented
+  //   on run steps
 
   if (setupflag) return;
-  nboost_running += nboost;
+  nbias_running += nbias;
   nobias_running += nobias;
+  negstrain_running += negstrain;
 
-  // apply boostostat to boost coefficients of all bonds of all owned atoms
-  // use per-atom full bond list
-  // this is double-calculating for IJ and JI bonds
-  //   should be identical for both, b/c emax is the same
-  //   could compute once, but would have to find/store index of JI bond
-  // delta in boost coeff is function of maxboost_region vs target boost
-  // maxboost_region is function of two maxstrain_regions for I,J
-  // NOTE: if J is lost to I but not vice versa, then biascoeff IJ != JI
+  // loop over bonds I own to adjust bias coeff
+  // delta in boost coeff is function of maxboost_domain vs target boost
+  // maxboost_domain is function of two maxstrain_domains for I,J
 
-  double myboost = 0.0;
-  double emaxi,emaxj,maxboost_region;
+  double emaxi,emaxj,maxboost_domain,bc;
+  double mybiascoeff = 0.0;
 
-  for (i = 0; i < nlocal; i++) {
-    emaxi = maxstrain_region[i];
-    nbond = numbond[i];
-    for (m = 0; m < nbond; m++) {
-      j = bonds[i][m].j;
-      if (j < 0) continue;
-      emaxj = maxstrain_region[j];
-      emax = MAX(emaxi,emaxj);
-      if (emax < qfactor) vbias = vmax * (1.0 - emax*emax*invqfactorsq);
-      else vbias = 0.0;
-      boostcoeff = bonds[i][m].boostcoeff;
-      maxboost_region = exp(beta * boostcoeff*vbias);
-      boostcoeff -= alpha * (maxboost_region-boosttarget) / boosttarget;
-      // COMMENT OUT for now - need better way to bound boostcoeff
-      //boostcoeff = MIN(boostcoeff,COEFFMAX);
-      myboost += boostcoeff;
-      maxboostcoeff = MAX(maxboostcoeff,boostcoeff);
-      minboostcoeff = MIN(minboostcoeff,boostcoeff);
-      bonds[i][m].boostcoeff = boostcoeff;
-    }
+  for (m = 0; m < nblocal; m++) {
+    i = blist[m].i;
+    j = blist[m].j;
+    emaxi = maxstrain_domain[i];
+    emaxj = maxstrain_domain[j];
+    emax = MAX(emaxi,emaxj);
+    if (emax < qfactor) vbias = vmax * (1.0 - emax*emax*invqfactorsq);
+    else vbias = 0.0;
+
+    maxboost_domain = exp(beta * biascoeff[m]*vbias);
+    biascoeff[m] -= alpha * (maxboost_domain-boost_target) / boost_target;
+
+    // stats
+
+    bc = biascoeff[m];
+    mybiascoeff += bc;
+    minbiascoeff = MIN(minbiascoeff,bc);
+    maxbiascoeff = MAX(maxbiascoeff,bc);
   }
 
-  // running stats
+  // -------------------------------------------------------------
+  // diagnostics, some optional
+  // -------------------------------------------------------------
 
-  MPI_Allreduce(&myboost,&allboost,1,MPI_DOUBLE,MPI_SUM,world);
-  if (allbonds) sumboostcoeff += allboost/allbonds;
+  MPI_Allreduce(&mybiascoeff,&sumbiascoeff,1,MPI_DOUBLE,MPI_SUM,world);
+  if (allbonds) avebiascoeff += sumbiascoeff/allbonds;
 
-  // histogram the bond coeffs and output as requested
-  // do not double count each bond
+  // if requested, monitor ghost distance from processor sub-boxes
 
-  if (histoflag && update->ntimestep % histo_every == 0) {
-    if (histo_steps == 0)
-      for (i = 0; i < histo_count+2; i++) histo[i] = 0;
-    histo_steps++;
-
-    int ihisto;
-    for (i = 0; i < nlocal; i++) {
-      nbond = numbond[i];
-      for (m = 0; m < nbond; m++) {
-        if (tag[i] > bonds[i][m].jtag) continue;
-        boostcoeff = bonds[i][m].boostcoeff;
-        if (boostcoeff < histo_lo) ihisto = -1;
-        else ihisto = static_cast<int> ((boostcoeff-histo_lo) * invhisto_delta);
-        if (ihisto >= histo_count) ihisto = histo_count;
-        histo[ihisto+1]++;
-      }
-    }
-
-    if (update->ntimestep % histo_print == 0) {
-      MPI_Allreduce(histo,allhisto,histo_count+2,MPI_LMP_BIGINT,MPI_SUM,world);
-
-      bigint total = 0;
-      for (i = 0; i < histo_count+2; i++) total += allhisto[i];
-
-      if (me == 0) {
-        if (screen) {
-          fprintf(screen,"Histogram of bias coeffs:\n");
-          for (i = 0; i < histo_count+2; i++)
-            fprintf(screen,"  %g",1.0*allhisto[i]/total);
-          fprintf(screen,"\n");
-        }
-        if (logfile) {
-          fprintf(logfile,"Histogram of bias coeffs:\n");
-          for (i = 0; i < histo_count+2; i++)
-            fprintf(logfile,"  %g",1.0*allhisto[i]/total);
-          fprintf(logfile,"\n");
-        }
-      }
-    }
+  if (checkghost) {
+    double rmax2[2],rmax2all[2];
+    rmax2[0] = rmax;
+    rmax2[1] = rmaxbig;
+    MPI_Allreduce(&rmax2,&rmax2all,2,MPI_DOUBLE,MPI_MAX,world);
+    rmaxever = rmax2all[0];
+    rmaxeverbig = rmax2all[1];
   }
 
-  // check for any biased bonds that are too close to each other
+  // if requsted, check for any biased bonds that are too close to each other
   // keep a running count for output
+  // requires 2 additional local comm operations
 
   if (checkbias && update->ntimestep % checkbias_every == 0) {
 
     // mark each atom in a biased bond with ID of partner
-    // nboost loop will mark some ghost atoms
+    // this may mark some ghost atoms
 
     for (i = 0; i < nall; i++) biasflag[i] = 0;
 
-    for (int iboost = 0; iboost < nboost; iboost++) {
-      i = boost[iboost];
-      m = maxstrain_bondindex[i];
-      j = bonds[i][m].j;
+    tagint *tag = atom->tag;
+
+    for (int ibias = 0; ibias < nbias; ibias++) {
+      m = bias[ibias];
+      i = blist[m].i;
+      j = blist[m].j;
       biasflag[i] = tag[j];
       biasflag[j] = tag[i];
     }
 
     // reverse comm to acquire biasflag from ghost atoms
-    // needed b/c above loop may set biasflag of ghost atoms
-    // forward comm to acquire biasflag of all ghost atoms
+    // forward comm to set biasflag for all ghost atoms
 
     commflag = BIASFLAG;
     comm->reverse_comm_fix(this);
     comm->forward_comm_fix(this);
 
+    // loop over Dcut full neighbor list
     // I and J may be ghost atoms
     // only continue if I is a biased atom
-    // if J is unknonw (drifted ghost) just ignore
+    // if J is unknown (drifted ghost) just ignore
     // if J is biased and is not bonded to I, then flag as too close
 
     for (ii = 0; ii < inum; ii++) {
@@ -784,30 +781,17 @@ void FixHyperLocal::pre_reverse(int /* eflag */, int /* vflag */)
         if (biasflag[j] && biasflag[j] != tag[i]) checkbias_count++;
       }
     }
-  }
 
-  // check for any bond bias coeffcients that do not match
-  // cannot check unless both atoms IJ are owned by this proc
-  // keep a running count for output
-
-  if (checkcoeff && update->ntimestep % checkcoeff_every == 0) {
-    int jb,jbonds;
-
-    for (i = 0; i < nlocal; i++) {
-      nbond = numbond[i];
-      for (m = 0; m < nbond; m++) {
-        if (tag[i] > bonds[i][m].jtag) continue;
-        j = bonds[i][m].j;
-        if (j < 0) continue;
-        if (j >= nlocal) continue;
-        itag = tag[i];
-        jbonds = numbond[j];
-        for (jb = 0; jb < jbonds; jb++)
-          if (bonds[j][jb].jtag == itag) break;
-        if (jb == jbonds)
-          error->one(FLERR,"Fix hyper/local could not find duplicate bond");
-        if (bonds[i][m].boostcoeff != bonds[j][jb].boostcoeff)
-          checkcoeff_count++;
+    if (checkbias_flag != IGNORE) {
+      int allcount;
+      MPI_Allreduce(&checkbias_count,&allcount,1,MPI_INT,MPI_SUM,world);
+      if (allcount) {
+        char str[128];
+        sprintf(str,"Fix hyper/local biased bonds too close: "
+                "cumulative atom count %d",allcount);
+        if (checkbias_flag == WARN) {
+          if (me == 0) error->warning(FLERR,str);
+        } else error->all(FLERR,str);
       }
     }
   }
@@ -824,9 +808,9 @@ void FixHyperLocal::min_pre_neighbor()
 
 void FixHyperLocal::build_bond_list(int natom)
 {
-  int i,j,ii,jj,m,n,inum,jnum,nbond;
-  tagint itag,jtag;
-  double xtmp,ytmp,ztmp,delx,dely,delz,rsq,oldcoeff;
+  int i,j,ii,jj,m,n,iold,jold,ilocal,jlocal,inum,jnum,nbond;
+  tagint jtag;
+  double xtmp,ytmp,ztmp,delx,dely,delz,rsq,distsq,oldcoeff;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   double time1,time2;
@@ -837,159 +821,260 @@ void FixHyperLocal::build_bond_list(int natom)
     nevent_atom += natom;
   }
 
-  // trigger Dcut neighbor list build
-  // NOTE: turn off special bonds in this Dcut neigh list?
-
-  neighbor->build_one(list);
-
-  // make copy of old bonds to preserve boostcoeffs for bonds that persist
-  // allocate new numbond
-
-  OneBond **old_bonds = bonds;
-  int *old_numbond = numbond;
-
-  int nmax = atom->nmax;
-  memory->create(numbond,nmax,"hyper/local:numbond");
-
-  // old_nall = value of nall at time bonds are built
-  // reallocate new xold and tagold if necessary
-  // initialize xold to current coords
-  // initialize tagold to zero, so atoms not in neighbor list will remain zero
-
-  old_nall = atom->nlocal + atom->nghost;
-
-  if (old_nall > maxold) {
-    memory->destroy(xold);
-    memory->destroy(tagold);
-    memory->destroy(old2now);
-    maxold = atom->nmax;
-    memory->create(xold,maxold,3,"hyper/local:xold");
-    memory->create(tagold,maxold,"hyper/local:tagold");
-    memory->create(old2now,maxold,"hyper/local:old2now");
-  }
+  // compute max distance any bond atom has moved between 2 quenched states
+  // xold[iold] = last quenched coord for iold
+  // x[ilocal] = current quenched coord for same atom
+  // use of old2now calculates distsq only once per atom
 
   double **x = atom->x;
 
-  memcpy(&xold[0][0],&x[0][0],3*old_nall*sizeof(double));
-  for (i = 0; i < old_nall; i++) tagold[i] = 0;
+  for (i = 0; i < nall_old; i++) old2now[i] = -1;
 
-  // create and populate new bonds data struct
-  // while loop allows maxbondperatom to increase once if necessary
-  //   don't know new maxbondperatom value until end of loop
-  // in practice maxbondperatom will hardly ever increase
-  //   since there is a physical max value
-
-  tagint *tag = atom->tag;
-  int *mask = atom->mask;
-  int nlocal = atom->nlocal;
-
-  inum = list->inum;
-  ilist = list->ilist;
-  numneigh = list->numneigh;
-  firstneigh = list->firstneigh;
-
-  while (1) {
-    bonds = (OneBond **) memory->create(bonds,nmax,maxbondperatom,
-                                        "hyper/local:bonds");
-    if (bonds) memset(bonds[0],0,nmax*sizeof(OneBond));
-    for (i = 0; i < nlocal; i++) numbond[i] = 0;
-
-    // identify bonds assigned to each owned atom
-    // do not create a bond between two non-group atoms
-    // set tagold = global ID for all I,J atoms used in neighbor list
-    //   tagold remains 0 for unused atoms, skipped in pre_neighbor
-
-    int nbondmax = 0;
-
-    for (ii = 0; ii < inum; ii++) {
-      i = ilist[ii];
-      xtmp = x[i][0];
-      ytmp = x[i][1];
-      ztmp = x[i][2];
-      itag = tag[i];
-      tagold[i] = tag[i];
-      jlist = firstneigh[i];
-      jnum = numneigh[i];
-      nbond = 0;
-
-      for (jj = 0; jj < jnum; jj++) {
-        j = jlist[jj];
-        j &= NEIGHMASK;
-        jtag = tag[j];
-        tagold[j] = jtag;
-
-        // skip if neither atom I or J are in fix group
-        // order IJ to insure IJ and JI bonds are stored consistently
-
-        if (!(mask[i] & groupbit) && !(mask[j] & groupbit)) continue;
-
-        if (itag < jtag) {
-          delx = xtmp - x[j][0];
-          dely = ytmp - x[j][1];
-          delz = ztmp - x[j][2];
-        } else {
-          delx = x[j][0] - xtmp;
-          dely = x[j][1] - ytmp;
-          delz = x[j][2] - ztmp;
-        }
-
-        rsq = delx*delx + dely*dely + delz*delz;
-
-        // NOTE: could create two bonds for IJ both owned from one calc?
-        //       have to skip one of 2 bonds in that case
-
-        if (rsq < cutbondsq) {
-          if (nbond >= maxbondperatom) {
-            nbond++;
-            continue;
-          }
-
-          bonds[i][nbond].r0 = sqrt(rsq);
-          bonds[i][nbond].jtag = tag[j];
-          bonds[i][nbond].j = j;
-
-          if (firstflag) oldcoeff = 0.0;
-          else {
-            oldcoeff = 0.0;
-            jtag = tag[j];
-            n = old_numbond[i];
-            for (m = 0; m < n; m++) {
-              if (old_bonds[i][m].jtag == jtag) {
-                oldcoeff = old_bonds[i][m].boostcoeff;
-                break;
-              }
-            }
-          }
-
-          if (oldcoeff > 0.0) bonds[i][nbond].boostcoeff = oldcoeff;
-          else {
-            bonds[i][nbond].boostcoeff = BOOSTINIT;
-            nnewbond++;
-          }
-          nbond++;
-        }
-      }
-      numbond[i] = nbond;
-      nbondmax = MAX(nbondmax,nbond);
+  for (m = 0; m < nblocal; m++) {
+    iold = blist[m].iold;
+    if (old2now[iold] < 0) {
+      ilocal = atom->map(tagold[iold]);
+      ilocal = domain->closest_image(xold[iold],ilocal);
+      if (ilocal < 0) error->one(FLERR,"Fix hyper/local bond atom not found");
+      old2now[iold] = ilocal;
+      distsq = MathExtra::distsq3(x[ilocal],xold[iold]);
+      maxdriftsq = MAX(distsq,maxdriftsq);
+    }
+    jold = blist[m].jold;
+    if (old2now[jold] < 0) {
+      jold = blist[m].jold;
+      jlocal = atom->map(tagold[jold]);
+      jlocal = domain->closest_image(xold[iold],jlocal);  // close to I atom
+      if (jlocal < 0) error->one(FLERR,"Fix hyper/local bond atom not found");
+      old2now[jold] = jlocal;
+      distsq = MathExtra::distsq3(x[jlocal],xold[jold]);
+      maxdriftsq = MAX(distsq,maxdriftsq);
     }
-
-    // maxbondperatom must increase uniformly on all procs
-    // since bonds are comunicated when atoms migrate
-
-    int allnbondmax;
-    MPI_Allreduce(&nbondmax,&allnbondmax,1,MPI_INT,MPI_MAX,world);
-    if (allnbondmax <= maxbondperatom) break;
-
-    maxbondperatom = allnbondmax;
-    memory->destroy(bonds);
   }
 
-  // deallocate old_bonds and old_numbond
+  // store old bond coeffs so can persist them in new blist
+  // while loop allows growing value of maxbondperatom
+  // will loop at most 2 times, stops when maxbondperatom is large enough
+  // requires reverse comm, no forward comm:
+  //    b/c new coeff list is stored only by current owned atoms
 
-  memory->destroy(old_bonds);
-  memory->destroy(old_numbond);
+  tagint *tag = atom->tag;
+  int nlocal = atom->nlocal;
+  int nall = nlocal + atom->nghost;
+
+  if (maxcoeff < nall) {
+    memory->destroy(numcoeff);
+    memory->sfree(clist);
+    maxcoeff = atom->nmax;
+    memory->create(numcoeff,maxcoeff,"hyper/local:numcoeff");
+    clist = (OneCoeff **) memory->smalloc(maxcoeff*sizeof(OneCoeff *),
+                                         "hyper/local:clist");
+  }
+
+  while (1) {
+    if (firstflag) break;
+    for (i = 0; i < nall; i++) numcoeff[i] = 0;
+    for (i = 0; i < nall; i++) clist[i] = NULL;
+    cpage->reset();
+
+    for (m = 0; m < nblocal; m++) {
+      i = blist[m].i;
+      j = blist[m].j;
+
+      if (numcoeff[i] == 0) clist[i] = cpage->get(maxbondperatom);
+      if (numcoeff[j] == 0) clist[j] = cpage->get(maxbondperatom);
+
+      if (numcoeff[i] < maxbondperatom) {
+        clist[i][numcoeff[i]].biascoeff = biascoeff[m];
+        clist[i][numcoeff[i]].tag = tag[j];
+      }
+      numcoeff[i]++;
+
+      if (numcoeff[j] < maxbondperatom) {
+        clist[j][numcoeff[j]].biascoeff = biascoeff[m];
+        clist[j][numcoeff[j]].tag = tag[i];
+      }
+      numcoeff[j]++;
+    }
+
+    int mymax = 0;
+    for (i = 0; i < nall; i++) mymax = MAX(mymax,numcoeff[i]);
+    int maxcoeffall;
+    MPI_Allreduce(&mymax,&maxcoeffall,1,MPI_INT,MPI_MAX,world);
+
+    if (maxcoeffall > maxbondperatom) {
+      maxbondperatom = maxcoeffall;
+      cpage->init(maxbondperatom,1024*maxbondperatom,1);
+      continue;
+    }
+
+    commflag = BIASCOEFF;
+    comm->reverse_comm_fix_variable(this);
+
+    mymax = 0;
+    for (i = 0; i < nall; i++) mymax = MAX(mymax,numcoeff[i]);
+    MPI_Allreduce(&mymax,&maxcoeffall,1,MPI_INT,MPI_MAX,world);
+    if (maxcoeffall <= maxbondperatom) break;
+
+    maxbondperatom = maxcoeffall;
+    cpage->init(maxbondperatom,1024*maxbondperatom,1);
+  }
+
+  // reallocate vectors that are maxlocal and maxall length if necessary
+
+  if (nlocal > maxlocal) {
+    memory->destroy(eligible);
+    memory->destroy(numbond);
+    memory->destroy(maxhalf);
+    memory->destroy(maxhalfstrain);
+    maxlocal = nlocal;
+    memory->create(eligible,maxlocal,"hyper/local:eligible");
+    memory->create(numbond,maxlocal,"hyper/local:numbond");
+    memory->create(maxhalf,maxlocal,"hyper/local:maxhalf");
+    memory->create(maxhalfstrain,maxlocal,"hyper/local:maxhalfstrain");
+  }
+
+  if (nall > maxall) {
+    memory->destroy(xold);
+    memory->destroy(tagold);
+    memory->destroy(old2now);
+    maxall = atom->nmax;
+    memory->create(xold,maxall,3,"hyper/local:xold");
+    memory->create(tagold,maxall,"hyper/local:tagold");
+    memory->create(old2now,maxall,"hyper/local:old2now");
+  }
+
+  // nlocal_old = value of nlocal at time bonds are built
+  // nall_old = value of nall at time bonds are built
+  // archive current atom coords in xold
+  // tagold will be set to non-zero below for accessed atoms
+  // numbond will be set below
+
+  nlocal_old = nlocal;
+  nall_old = nall;
+
+  memcpy(&xold[0][0],&x[0][0],3*nall*sizeof(double));
+  for (i = 0; i < nall; i++) tagold[i] = 0;
+  for (i = 0; i < nlocal; i++) numbond[i] = 0;
+
+  // trigger neighbor list builds for both lists
+  // insure the I loops in both are from 1 to nlocal
+
+  neighbor->build_one(listfull);
+  neighbor->build_one(listhalf);
+
+  if (listfull->inum != nlocal || listhalf->inum != nlocal)
+    error->one(FLERR,"Invalid neighbor list in fix hyper/local bond build");
+
+  // set tagold = 1 for all J atoms used in full neighbor list
+  // tagold remains 0 for unused atoms, skipped in pre_neighbor
+
+  inum = listfull->inum;
+  ilist = listfull->ilist;
+  numneigh = listfull->numneigh;
+  firstneigh = listfull->firstneigh;
+
+  for (ii = 0; ii < inum; ii++) {
+    i = ilist[ii];
+    tagold[i] = tag[i];
+    jlist = firstneigh[i];
+    jnum = numneigh[i];
+    for (jj = 0; jj < jnum; jj++) {
+      j = jlist[jj];
+      j &= NEIGHMASK;
+      tagold[j] = tag[j];
+    }
+  }
+
+  // identify bonds assigned to each owned atom
+  // do not create a bond between two non-group atoms
+
+  int *mask = atom->mask;
+
+  inum = listhalf->inum;
+  ilist = listhalf->ilist;
+  numneigh = listhalf->numneigh;
+  firstneigh = listhalf->firstneigh;
+
+  nblocal = 0;
+
+  for (ii = 0; ii < inum; ii++) {
+    i = ilist[ii];
+    xtmp = x[i][0];
+    ytmp = x[i][1];
+    ztmp = x[i][2];
+
+    tagold[i] = tag[i];
+
+    jlist = firstneigh[i];
+    jnum = numneigh[i];
+    nbond = 0;
+
+    for (jj = 0; jj < jnum; jj++) {
+      j = jlist[jj];
+      j &= NEIGHMASK;
+
+      jtag = tag[j];
+      tagold[j] = jtag;
+
+      // skip if neither atom I or J are in fix group
+
+      if (!(mask[i] & groupbit) && !(mask[j] & groupbit)) continue;
+
+      delx = xtmp - x[j][0];
+      dely = ytmp - x[j][1];
+      delz = ztmp - x[j][2];
+      rsq = delx*delx + dely*dely + delz*delz;
+
+      if (rsq < cutbondsq) {
+        nbond++;
+
+        if (nblocal == maxbond) grow_bond();
+        blist[nblocal].i = i;
+        blist[nblocal].j = j;
+        blist[nblocal].iold = i;
+        blist[nblocal].jold = j;
+        blist[nblocal].r0 = sqrt(rsq);
+
+        // set biascoeff to old coeff for same I,J pair or to default
+
+        if (firstflag) oldcoeff = 0.0;
+        else {
+          oldcoeff = 0.0;
+          jtag = tag[j];
+          n = numcoeff[i];
+          for (m = 0; m < n; m++) {
+            if (clist[i][m].tag == jtag) {
+              oldcoeff = clist[i][m].biascoeff;
+              break;
+            }
+          }
+        }
+
+        if (oldcoeff > 0.0) biascoeff[nblocal] = oldcoeff;
+        else {
+          biascoeff[nblocal] = COEFFINIT;
+          nnewbond++;
+        }
+
+        nblocal++;
+      }
+    }
+
+    numbond[i] = nbond;
+  }
+
+  // this fix allows access to biascoeffs as local data
+
+  size_local_rows = nblocal;
+
+  // allbonds = total # of bonds in system
+
+  bigint bondcount = nblocal;
+  MPI_Allreduce(&bondcount,&allbonds,1,MPI_LMP_BIGINT,MPI_SUM,world);
 
   time2 = MPI_Wtime();
+
   if (firstflag) nnewbond = 0;
   else {
     time_bondbuild += time2-time1;
@@ -1009,6 +1094,7 @@ int FixHyperLocal::pack_forward_comm(int n, int *list, double *buf,
 
   // STRAIN
   // pack maxstrain vector
+  // must send to all ghosts out to Dcut
 
   if (commflag == STRAIN) {
     for (i = 0; i < n; i++) {
@@ -1016,17 +1102,20 @@ int FixHyperLocal::pack_forward_comm(int n, int *list, double *buf,
       buf[m++] = maxstrain[j];
     }
 
-  // STRAINREGION
-  // pack maxstrain_region vector
+  // STRAINDOMAIN
+  // pack maxstrain_domain vector
+  // could just send to nearby ghosts in bonds
+  // don't see easy way to determine precisely which atoms that is
 
-  } else if (commflag == STRAINREGION) {
+  } else if (commflag == STRAINDOMAIN) {
     for (i = 0; i < n; i++) {
       j = list[i];
-      buf[m++] = maxstrain_region[j];
+      buf[m++] = maxstrain_domain[j];
     }
 
   // BIASFLAG
   // pack biasflag vector
+  // must send to all ghosts out to Dcut
 
   } else if (commflag == BIASFLAG) {
     for (i = 0; i < n; i++) {
@@ -1056,11 +1145,11 @@ void FixHyperLocal::unpack_forward_comm(int n, int first, double *buf)
     }
 
   // STRAINREGION
-  // unpack maxstrain_region vector
+  // unpack maxstrain_domain vector
 
-  } else if (commflag == STRAINREGION) {
+  } else if (commflag == STRAINDOMAIN) {
     for (i = first; i < last; i++) {
-      maxstrain_region[i] = buf[m++];
+      maxstrain_domain[i] = buf[m++];
     }
 
   // BIASFLAG
@@ -1077,46 +1166,136 @@ void FixHyperLocal::unpack_forward_comm(int n, int first, double *buf)
 
 int FixHyperLocal::pack_reverse_comm(int n, int first, double *buf)
 {
-  int i,m,last;
+  int i,j,m,last;
 
   m = 0;
   last = first + n;
 
-  // STRAINREGION
-  // pack maxstrain_region vector
+  // STRAIN
+  // pack maxstrain vector
+  // only pack for nonzero values
 
-  if (commflag == STRAINREGION) {
+  if (commflag == STRAIN) {
+    int nonzero = 0;
+    m++;                           // placeholder for count of atoms
     for (i = first; i < last; i++) {
-      buf[m++] = maxstrain_region[i];
+      if (maxstrain[i] == 0.0) continue;
+      nonzero++;
+      buf[m++] = ubuf(i-first).d;  // which atom is next
+      buf[m++] = maxstrain[i];     // value
     }
+    buf[0] = ubuf(nonzero).d;
+
+  // STRAINDOMAIN
+  // pack maxstrain_domain vector
+  // only pack for nonzero values
+
+  } else if (commflag == STRAINDOMAIN) {
+    int nonzero = 0;
+    m++;                           // placeholder for count of atoms
+    for (i = first; i < last; i++) {
+      if (maxstrain_domain[i] == 0.0) continue;
+      nonzero++;
+      buf[m++] = ubuf(i-first).d;      // which atom is next
+      buf[m++] = maxstrain_domain[i];  // value
+    }
+    buf[0] = ubuf(nonzero).d;
 
   // BIASFLAG
   // pack biasflag vector
+  // could just pack for nonzero values, like STRAIN and STRAINDOMAIN
 
   } else if (commflag == BIASFLAG) {
     for (i = first; i < last; i++) {
       buf[m++] = ubuf(biasflag[i]).d;
     }
+
+  // BIASCOEFF
+  // pack list of biascoeffs
+  // only pack for atoms with nonzero # of bias coeffs
+  // this will skip majority of ghost atoms
+
+  } else if (commflag == BIASCOEFF) {
+    int ncoeff;
+    int nonzero = 0;
+    m++;                             // placeholder for count of atoms
+    for (i = first; i < last; i++) {
+      if (numcoeff[i] == 0) continue;
+      nonzero++;
+      ncoeff = numcoeff[i];
+      buf[m++] = ubuf(i-first).d;   // which atom is next
+      buf[m++] = ubuf(ncoeff).d;    // # of bias coeffs
+      for (j = 0; j < ncoeff; j++) {
+        buf[m++] = clist[i][j].biascoeff;
+        buf[m++] = ubuf(clist[i][j].tag).d;
+      }
+    }
+    buf[0] = ubuf(nonzero).d;
   }
 
   return m;
 }
 
+/* ----------------------------------------------------------------------
+   callback by comm->reverse_comm_fix_variable() in build_bond()
+   same logic as BIASCOEFF option in pack_reverse_comm()
+   m = returned size of message
+------------------------------------------------------------------------- */
+
+int FixHyperLocal::pack_reverse_comm_size(int n, int first)
+{
+  int last = first + n;
+  int m = 1;
+  for (int i = first; i < last; i++) {
+    if (numcoeff[i]) m += 2 + 2*numcoeff[i];
+  }
+  return m;
+}
+
 /* ---------------------------------------------------------------------- */
 
 void FixHyperLocal::unpack_reverse_comm(int n, int *list, double *buf)
 {
-  int i,j,m;
+  int i,j,k,m;
+
+  // return if n = 0
+  // b/c if there are no atoms (n = 0), the message will not have
+  //   been sent by Comm::reverse_comm_fix() or reverse_comm_fix_variable()
+  // so must not read nonzero from first buf location (would be zero anyway)
+
+  if (n == 0) return;
+
+  // STRAIN
+  // unpack maxstrain vector
+  // nonzero # of entries, each has offset to which atom in receiver's list
+  // use MAX, b/c want maximum abs value strain for each atom's bonds
 
   m = 0;
 
-  // STRAINREGION
-  // unpack maxstrain_region vector
+  if (commflag == STRAIN) {
+    int offset;
+    int nonzero = (int) ubuf(buf[m++]).i;   // # of atoms with values
 
-  if (commflag == STRAINREGION) {
-    for (i = 0; i < n; i++) {
-      j = list[i];
-      maxstrain_region[j] += buf[m++];
+    for (int iatom = 0; iatom < nonzero; iatom++) {
+      offset = (int) ubuf(buf[m++]).i;      // offset into list for which atom
+      j = list[offset];
+      maxstrain[j] = MAX(maxstrain[j],buf[m]);
+      m++;
+    }
+
+  // STRAINDOMAIN
+  // unpack maxstrain_domain vector
+  // use MAX, b/c want maximum abs value strain for each atom's domain
+  // could also use SUM, b/c exactly one ghost or owned value is non-zero
+
+  } else if (commflag == STRAINDOMAIN) {
+    int offset;
+    int nonzero = (int) ubuf(buf[m++]).i;   // # of atoms with values
+    for (int iatom = 0; iatom < nonzero; iatom++) {
+      offset = (int) ubuf(buf[m++]).i;      // offset into list for which atom
+      j = list[offset];
+      maxstrain_domain[j] = MAX(maxstrain_domain[j],buf[m]);
+      m++;
     }
 
   // BIASFLAG
@@ -1127,84 +1306,45 @@ void FixHyperLocal::unpack_reverse_comm(int n, int *list, double *buf)
       j = list[i];
       biasflag[j] = (tagint) ubuf(buf[m++]).i;
     }
+
+  // BIASCOEFF
+  // unpack list of biascoeffs
+  // nonzero # of entries, each has offset to which atom in receiver's list
+  // protect against overflow of clist vector
+  // if that happens, caller will re-setup cpage and reverse comm again
+
+  } else if (commflag == BIASCOEFF) {
+    int offset,ncoeff;
+    int nonzero = (int) ubuf(buf[m++]).i;   // # of atoms with coeffs
+    for (int iatom = 0; iatom < nonzero; iatom++) {
+      offset = (int) ubuf(buf[m++]).i;      // offset into list for which atom
+      j = list[offset];
+      ncoeff = (int) ubuf(buf[m++]).i;      // # of bias coeffs
+      for (k = 0; k < ncoeff; k++) {
+        if (numcoeff[j] == 0) clist[j] = cpage->get(maxbondperatom);
+        if (numcoeff[j] < maxbondperatom) {
+          clist[j][numcoeff[j]].biascoeff = buf[m++];
+          clist[j][numcoeff[j]].tag = (tagint) ubuf(buf[m++]).i;
+        } else m += 2;
+        numcoeff[j]++;
+      }
+    }
   }
 }
 
 /* ----------------------------------------------------------------------
-   allocate atom-based arrays
+   grow bond list and bias coeff vector by a chunk
 ------------------------------------------------------------------------- */
 
-void FixHyperLocal::grow_arrays(int nmax)
+void FixHyperLocal::grow_bond()
 {
-  // NOTE: not all of these need to be Nmax in length, could allocate elsewhere
-
-  memory->grow(maxstrain,nmax,"hyper/local:maxstrain");
-  memory->grow(maxstrain_bondindex,nmax,"hyper/local:maxstrain_bondindex");
-  memory->grow(maxstrain_region,nmax,"hyper/local:maxstrain_region");
-  if (checkbias) memory->grow(biasflag,nmax,"hyper/local:biasflag");
-
-  memory->grow(numbond,nmax,"hyper/local:numbond");
-  memory->grow(bonds,nmax,maxbondperatom,"hyper/local:bonds");
-
-  // zero so valgrind does not complain about memcpy() in copy()
-  // also so loops in pre_neighbor() are OK before
-  //   bonds are setup for the first time
-
-  if (bonds) {
-    memset(bonds[maxbond],0,(nmax-maxbond)*maxbondperatom*sizeof(OneBond));
-    memset(&numbond[maxbond],0,(nmax-maxbond)*sizeof(int));
-    maxbond = nmax;
-  }
-}
-
-/* ----------------------------------------------------------------------
-   copy values within local atom-based arrays
-------------------------------------------------------------------------- */
-
-void FixHyperLocal::copy_arrays(int i, int j, int /* delflag */)
-{
-  // avoid valgrind copy-to-self warning
-
-  if (i != j) memcpy(bonds[j],bonds[i],numbond[i]*sizeof(OneBond));
-  numbond[j] = numbond[i];
-}
-
-/* ----------------------------------------------------------------------
-   pack values in local atom-based array for exchange with another proc
-------------------------------------------------------------------------- */
-
-int FixHyperLocal::pack_exchange(int i, double *buf)
-{
-  int m = 1;
-  int n = numbond[i];
-  buf[m++] = ubuf(n).d;
-  for (int j = 0; j < n; j++) {
-    buf[m++] = bonds[i][j].r0;
-    buf[m++] = bonds[i][j].boostcoeff;
-    buf[m++] = ubuf(bonds[i][j].jtag).d;
-    buf[m++] = ubuf(bonds[i][j].j).d;
-  }
-
-  buf[0] = m;
-  return m;
-}
-
-/* ----------------------------------------------------------------------
-   unpack values in local atom-based array from exchange with another proc
-------------------------------------------------------------------------- */
-
-int FixHyperLocal::unpack_exchange(int nlocal, double *buf)
-{
-  int m = 1;
-  int n = numbond[nlocal] = (int) ubuf(buf[m++]).i;
-  for (int j = 0; j < n; j++) {
-    bonds[nlocal][j].r0 = buf[m++];
-    bonds[nlocal][j].boostcoeff = buf[m++];
-    bonds[nlocal][j].jtag = (tagint) ubuf(buf[m++]).i;
-    bonds[nlocal][j].j = (int) ubuf(buf[m++]).i;
-  }
-
-  return m;
+  if (maxbond + DELTABOND > MAXSMALLINT)
+    error->one(FLERR,"Fix hyper/local bond count is too big");
+  maxbond += DELTABOND;
+  blist = (OneBond *)
+    memory->srealloc(blist,maxbond*sizeof(OneBond),"hyper/local:blist");
+  memory->grow(biascoeff,maxbond,"hyper/local:biascoeff");
+  vector_local = biascoeff;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -1220,41 +1360,40 @@ double FixHyperLocal::compute_scalar()
 
 double FixHyperLocal::compute_vector(int i)
 {
-  // 23 vector outputs returned for i = 0-22
+  // 21 vector outputs returned for i = 0-20
 
-  // i = 0 = # of boosted bonds on this step
+  // i = 0 = # of biased bonds on this step
   // i = 1 = max strain of any bond on this step
-  // i = 2 = average bias potential for all bonds on this step
+  // i = 2 = average bias coeff for all bonds on this step
   // i = 3 = ave bonds/atom on this step
   // i = 4 = ave neighbor bonds/bond on this step
 
-  // i = 5 = fraction of steps and bonds with no bias during this run
-  // i = 6 = max drift distance of any atom during this run
-  // i = 7 = max bond length during this run
-  // i = 8 = average # of boosted bonds/step during this run
-  // i = 9 = average bias potential for all bonds during this run
-  // i = 10 = max bias potential for any bond during this run
-  // i = 11 = min bias potential for any bond during this run
-  // i = 12 = max dist from my box of any ghost atom with
-  //          maxstain < qfactor during this run
-  // i = 13 = max dist from my box of any ghost atom with
-  //          any maxstrain during this run
-  // i = 14 = count of ghost atoms that could not be found
-  //          by any proc at any reneighbor step during this run
-  // i = 15 = count of lost bond partners during this run
-  // i = 16 = average bias coeff for lost bond partners during this run
-  // i = 17 = count of bias overlaps found during this run
-  // i = 18 = count of non-matching bias coefficients found during this run
+  // i = 5 = max bond length during this run
+  // i = 6 = average # of biased bonds/step during this run
+  // i = 7 = fraction of biased bonds with no bias during this run
+  // i = 8 = fraction of biased bonds with negative strain during this run
+  // i = 9 = average bias coeff for all bonds during this run
+  // i = 10 = min bias coeff for any bond during this run
+  // i = 11 = max bias coeff for any bond during this run
 
-  // i = 19 = cummulative hyper time
-  // i = 20 = cummulative # of event timesteps since fix created
-  // i = 21 = cummulative # of atoms in events since fix created
-  // i = 22 = cummulative # of new bonds formed since fix created
+  // i = 12 = max drift distance of any atom during this run
+  // i = 13 = max distance from proc subbox of any ghost atom with
+  //          maxstrain < qfactor during this run
+  // i = 14 = max distance from proc subbox of any ghost atom with
+  //          any maxstrain during this run
+  // i = 15 = count of ghost atoms that could not be found
+  //          on reneighbor steps during this run
+  // i = 16 = count of bias overlaps (< Dcut) found during this run
+
+  // i = 17 = cumulative hyper time since fix created
+  // i = 18 = cumulative # of event timesteps since fix created
+  // i = 19 = cumulative # of atoms in events since fix created
+  // i = 20 = cumulative # of new bonds formed since fix created
 
   if (i == 0) {
-    int nboostall;
-    MPI_Allreduce(&nboost,&nboostall,1,MPI_INT,MPI_SUM,world);
-    return (double) nboostall;
+    int nbiasall;
+    MPI_Allreduce(&nbias,&nbiasall,1,MPI_INT,MPI_SUM,world);
+    return (double) nbiasall;
   }
 
   if (i == 1) {
@@ -1269,119 +1408,103 @@ double FixHyperLocal::compute_vector(int i)
   }
 
   if (i == 2) {
-    if (allboost && allbonds) return allboost/allbonds * vmax;
+    if (allbonds) return sumbiascoeff/allbonds;
     return 1.0;
   }
 
-  if (i == 3) return 1.0*allbonds/atom->natoms;
+  if (i == 3) {
+    return 2.0*allbonds/atom->natoms;
+  }
 
   if (i == 4) {
-    const int nlocal = atom->nlocal;
-    bigint nbonds = 0;
-    for (int j = 0; j < nlocal; j++)
-      nbonds += numbond[j];
-    bigint allbonds;
-    MPI_Allreduce(&nbonds,&allbonds,1,MPI_LMP_BIGINT,MPI_SUM,world);
     bigint allneigh,thisneigh;
-    thisneigh = list->ipage->ndatum;
+    thisneigh = listfull->ipage->ndatum;
     MPI_Allreduce(&thisneigh,&allneigh,1,MPI_LMP_BIGINT,MPI_SUM,world);
     const double natoms = atom->natoms;
     const double neighsperatom = static_cast<double>(allneigh)/natoms;
-    const double bondsperatom = 0.5*static_cast<double>(allbonds)/natoms;
+    const double bondsperatom = static_cast<double>(allbonds)/natoms;
     return neighsperatom * bondsperatom;
   }
 
   if (i == 5) {
-    int allboost_running,allnobias_running;
-    MPI_Allreduce(&nboost_running,&allboost_running,1,MPI_INT,MPI_SUM,world);
-    MPI_Allreduce(&nobias_running,&allnobias_running,1,MPI_INT,MPI_SUM,world);
-    if (allboost_running) return 1.0*allnobias_running / allboost_running;
-    return 0.0;
-  }
-
-  if (i == 6) {
-    double alldriftsq;
-    MPI_Allreduce(&maxdriftsq,&alldriftsq,1,MPI_DOUBLE,MPI_MAX,world);
-    return (double) sqrt(alldriftsq);
-  }
-
-  if (i == 7) {
     double allbondlen;
     MPI_Allreduce(&maxbondlen,&allbondlen,1,MPI_DOUBLE,MPI_MAX,world);
     return allbondlen;
   }
 
-  if (i == 8) {
+  if (i == 6) {
     if (update->ntimestep == update->firststep) return 0.0;
-    int allboost_running;
-    MPI_Allreduce(&nboost_running,&allboost_running,1,MPI_INT,MPI_SUM,world);
-    return 1.0*allboost_running / (update->ntimestep - update->firststep);
+    int allbias_running;
+    MPI_Allreduce(&nbias_running,&allbias_running,1,MPI_INT,MPI_SUM,world);
+    return 1.0*allbias_running / (update->ntimestep - update->firststep);
+  }
+
+  if (i == 7) {
+    int allbias_running,allnobias_running;
+    MPI_Allreduce(&nbias_running,&allbias_running,1,MPI_INT,MPI_SUM,world);
+    MPI_Allreduce(&nobias_running,&allnobias_running,1,MPI_INT,MPI_SUM,world);
+    if (allbias_running) return 1.0*allnobias_running / allbias_running;
+    return 0.0;
+  }
+
+  if (i == 8) {
+    int allbias_running,allnegstrain_running;
+    MPI_Allreduce(&nbias_running,&allbias_running,1,MPI_INT,MPI_SUM,world);
+    MPI_Allreduce(&negstrain_running,&allnegstrain_running,1,MPI_INT,
+                  MPI_SUM,world);
+    if (allbias_running) return 1.0*allnegstrain_running / allbias_running;
+    return 0.0;
   }
 
   if (i == 9) {
     if (update->ntimestep == update->firststep) return 0.0;
-    return sumboostcoeff * vmax / (update->ntimestep - update->firststep);
+    return avebiascoeff / (update->ntimestep - update->firststep);
   }
 
   if (i == 10) {
-    double allboostcoeff;
-    MPI_Allreduce(&maxboostcoeff,&allboostcoeff,1,MPI_DOUBLE,MPI_MAX,world);
-    return allboostcoeff * vmax;
+    double biascoeff;
+    MPI_Allreduce(&minbiascoeff,&biascoeff,1,MPI_DOUBLE,MPI_MIN,world);
+    return biascoeff;
   }
 
   if (i == 11) {
-    double allboostcoeff;
-    MPI_Allreduce(&minboostcoeff,&allboostcoeff,1,MPI_DOUBLE,MPI_MAX,world);
-    return allboostcoeff * vmax;
+    double biascoeff;
+    MPI_Allreduce(&maxbiascoeff,&biascoeff,1,MPI_DOUBLE,MPI_MAX,world);
+    return biascoeff;
   }
 
-  if (i == 12) return rmaxever;
-  if (i == 13) return rmaxeverbig;
+  if (i == 12) {
+    double alldriftsq;
+    MPI_Allreduce(&maxdriftsq,&alldriftsq,1,MPI_DOUBLE,MPI_MAX,world);
+    return (double) sqrt(alldriftsq);
+  }
 
-  if (i == 14) {
+  if (i == 13) return rmaxever;
+  if (i == 14) return rmaxeverbig;
+
+  if (i == 15) {
     int allghost_toofar;
     MPI_Allreduce(&ghost_toofar,&allghost_toofar,1,MPI_INT,MPI_SUM,world);
     return 1.0*allghost_toofar;
   }
 
-  if (i == 15) {
-    int alllost;
-    MPI_Allreduce(&lostbond_partner,&alllost,1,MPI_INT,MPI_SUM,world);
-    return 1.0*alllost;
-  }
-
   if (i == 16) {
-    int alllost;
-    MPI_Allreduce(&lostbond_partner,&alllost,1,MPI_INT,MPI_SUM,world);
-    double allcoeff;
-    MPI_Allreduce(&lostbond_coeff,&allcoeff,1,MPI_DOUBLE,MPI_SUM,world);
-    if (alllost == 0) return 0;
-    return allcoeff/alllost;
-  }
-
-  if (i == 17) {
     int allclose;
     MPI_Allreduce(&checkbias_count,&allclose,1,MPI_INT,MPI_SUM,world);
     return 1.0*allclose;
   }
 
-  if (i == 18) {
-    int allcoeff;
-    MPI_Allreduce(&checkcoeff_count,&allcoeff,1,MPI_INT,MPI_SUM,world);
-    return 1.0*allcoeff;
+  if (i == 17) {
+    return boost_target * update->dt * (update->ntimestep - starttime);
   }
 
-  if (i == 19) {
-    return boosttarget * update->dt * (update->ntimestep - starttime);
-  }
+  if (i == 18) return (double) nevent;
+  if (i == 19) return (double) nevent_atom;
 
-  if (i == 20) return (double) nevent;
-  if (i == 21) return (double) nevent_atom;
-
-  if (i == 22) {
-    int allnew;
-    MPI_Allreduce(&nnewbond,&allnew,1,MPI_INT,MPI_SUM,world);
-    return (double) 0.5*allnew;
+  if (i == 20) {
+    int allnewbond;
+    MPI_Allreduce(&nnewbond,&allnewbond,1,MPI_INT,MPI_SUM,world);
+    return (double) allnewbond;
   }
 
   return 0.0;
@@ -1394,32 +1517,30 @@ double FixHyperLocal::compute_vector(int i)
 
 double FixHyperLocal::query(int i)
 {
-  if (i == 1) return compute_vector(19);  // cummulative hyper time
-  if (i == 2) return compute_vector(20);  // nevent
-  if (i == 3) return compute_vector(21);  // nevent_atom
+  if (i == 1) return compute_vector(17);  // cummulative hyper time
+  if (i == 2) return compute_vector(18);  // nevent
+  if (i == 3) return compute_vector(19);  // nevent_atom
   if (i == 4) return compute_vector(3);   // ave bonds/atom
-  if (i == 5) return compute_vector(6);   // maxdrift
-  if (i == 6) return compute_vector(7);   // maxbondlen
-  if (i == 7) return compute_vector(5);   // fraction with zero bias
+  if (i == 5) return compute_vector(12);  // maxdrift
+  if (i == 6) return compute_vector(5);   // maxbondlen
+  if (i == 7) return compute_vector(7);   // fraction with zero bias
+  if (i == 8) return compute_vector(8);   // fraction with negative strain
 
   // unique to local hyper
 
-  if (i == 8) return compute_vector(22);   // number of new bonds
-  if (i == 9) return 1.0*maxbondperatom;   // max bonds/atom
-  if (i == 10) return compute_vector(8);   // ave # of boosted bonds/step
-  if (i == 11) return compute_vector(9);   // ave boost coeff over all bonds
-  if (i == 12) return compute_vector(10);  // max boost cooef for any bond
-  if (i == 13) return compute_vector(11);  // max boost cooef for any bond
-  if (i == 14) return compute_vector(4);   // neighbor bonds/bond
-  if (i == 15) return compute_vector(2);   // ave boost cooef now
-  if (i == 16) return time_bondbuild;      // CPU time for bond_build calls
-  if (i == 17) return rmaxever;            // ghost atom distance for < maxstrain
-  if (i == 18) return rmaxeverbig;         // ghost atom distance for any strain
-  if (i == 19) return compute_vector(14);  // count of ghost atoms not found
-  if (i == 20) return compute_vector(15);  // count of lost bond partners
-  if (i == 21) return compute_vector(16);  // ave bias coeff of long bonds
-  if (i == 22) return compute_vector(17);  // count of bias overlaps
-  if (i == 23) return compute_vector(18);  // count of non-matching bias coeffs
+  if (i == 9) return compute_vector(20);   // number of new bonds
+  if (i == 10) return 1.0*maxbondperatom;  // max bonds/atom
+  if (i == 11) return compute_vector(6);   // ave # of biased bonds/step
+  if (i == 12) return compute_vector(9);   // ave bias coeff over all bonds
+  if (i == 13) return compute_vector(10);  // min bias cooef for any bond
+  if (i == 14) return compute_vector(11);  // max bias cooef for any bond
+  if (i == 15) return compute_vector(4);   // neighbor bonds/bond
+  if (i == 16) return compute_vector(2);   // ave bias coeff now
+  if (i == 17) return time_bondbuild;      // CPU time for build_bond calls
+  if (i == 18) return rmaxever;            // ghost atom distance for < maxstrain
+  if (i == 19) return rmaxeverbig;         // ghost atom distance for any strain
+  if (i == 20) return compute_vector(15);  // count of ghost atoms not found
+  if (i == 21) return compute_vector(16);  // count of bias overlaps
 
   error->all(FLERR,"Invalid query to fix hyper/local");
 
@@ -1427,17 +1548,22 @@ double FixHyperLocal::query(int i)
 }
 
 /* ----------------------------------------------------------------------
-   memory usage of per-atom and per-bond arrays
+   memory usage of per-atom and per-bond data structs
 ------------------------------------------------------------------------- */
 
 double FixHyperLocal::memory_usage()
 {
-  int nmax = atom->nmax;
-  double bytes = 2*nmax * sizeof(int);     // numbond, maxstrain_bondindex
-  bytes = 2*nmax * sizeof(double);         // maxstrain, maxstrain_region
-  bytes += maxbondperatom*nmax * sizeof(OneBond);      // bonds
-  bytes += 3*maxold * sizeof(double);      // xold
-  bytes += maxold * sizeof(tagint);        // tagold
-  bytes += maxold * sizeof(int);           // old2now
+  double bytes = maxbond * sizeof(OneBond);       // blist
+  bytes = maxbond * sizeof(double);               // per-bond bias coeffs
+  bytes += 3*maxlocal * sizeof(int);              // numbond,maxhalf,eligible
+  bytes += maxlocal * sizeof(double);             // maxhalfstrain
+  bytes += maxall * sizeof(int);                  // old2now
+  bytes += maxall * sizeof(tagint);               // tagold
+  bytes += 3*maxall * sizeof(double);             // xold
+  bytes += 2*maxall * sizeof(double);             // maxstrain,maxstrain_domain
+  if (checkbias) bytes += maxall * sizeof(tagint);  // biasflag
+  bytes += maxcoeff * sizeof(int);                // numcoeff
+  bytes += maxcoeff * sizeof(OneCoeff *);         // clist
+  bytes += maxlocal*maxbondperatom * sizeof(OneCoeff);  // cpage estimate
   return bytes;
 }
diff --git a/src/REPLICA/fix_hyper_local.h b/src/REPLICA/fix_hyper_local.h
index 147e3ef1ef..6f13acb606 100644
--- a/src/REPLICA/fix_hyper_local.h
+++ b/src/REPLICA/fix_hyper_local.h
@@ -21,6 +21,7 @@ FixStyle(hyper/local,FixHyperLocal)
 #define LMP_FIX_HYPER_LOCAL_H
 
 #include "fix_hyper.h"
+#include "my_page.h"
 
 namespace LAMMPS_NS {
 
@@ -43,13 +44,9 @@ class FixHyperLocal : public FixHyper {
   int pack_forward_comm(int, int *, double *, int, int *);
   void unpack_forward_comm(int, int, double *);
   int pack_reverse_comm(int, int, double *);
+  int pack_reverse_comm_size(int, int);
   void unpack_reverse_comm(int, int *, double *);
 
-  void grow_arrays(int);
-  void copy_arrays(int, int, int);
-  int pack_exchange(int, double *);
-  int unpack_exchange(int, double *);
-
   double memory_usage();
 
   // extra methods visible to callers
@@ -59,97 +56,133 @@ class FixHyperLocal : public FixHyper {
 
  private:
   int me;
+
+  // inputs and derived quantities
+
   double cutbond,qfactor,vmax,tequil,dcut;
   double alpha_user;         // timescale to apply boostostat (time units)
   double alpha;              // unitless dt/alpha_user
-  double boosttarget;        // target value of boost
-  int histoflag;
-  int lostbond,lostbond_partner;
-  double lostbond_coeff;
-  int checkbias,checkbias_every,checkbias_flag,checkbias_count;
-  int checkcoeff,checkcoeff_every,checkcoeff_flag,checkcoeff_count;
+  double boost_target;       // target value of boost
+  int checkghost,checkbias;  // flags for optional stats
+
+  double cutbondsq,dcutsq;
+  double beta,invqfactorsq;
+
+  // flags
 
   int setupflag;             // 1 during setup, 0 during run
   int firstflag;             // set for first time bond_build takes place
-  int nostrainyet;           // 1 until maxstrain is first computed
-
-  int nboost_running,nobias_running;
-  int nbondbuild;
-  double time_bondbuild;
-  bigint starttime;
-  double sumboostcoeff;  // sum of aveboost at every timestep
-  int allbonds;          // sum of bond count on this step
-  double allboost;       // sum of boostcoeff on all bonds on this step
-
-  int nnewbond;              // running tally of number of new bonds created
-  int maxbondperatom;        // max # of bonds any atom ever has
+  int nostrainyet;           // 1 until maxstrain is first compute
+  bigint starttime;          // timestep when this fix was invoked
   int commflag;              // flag for communication mode
+
+  // stats
+
+  int nbondbuild;            // # of rebuilds of bond list
+  double time_bondbuild;     // CPU time for bond builds
+
+  bigint allbonds;           // current total # of bonds
+  int nnewbond;              // running tally of # of new bonds created
+  int maxbondperatom;        // max # of bonds any atom ever has
   int nevent;                // # of events that trigger bond rebuild
   int nevent_atom;           // # of atoms that experienced an event
-  double cutbondsq,dcutsq;
-  double beta,invqfactorsq;
-  double mybias;
+
+  int nbias_running;         // running count of biased bonds
+  int nobias_running;        // ditto for bonds with bias = 0, b/c too long
+  int negstrain_running;     // ditto for bonds with negative strain
+
+  double mybias;             // sum of bias potentials for biased bonds
   double maxbondlen;         // cummulative max length of any bond
-  double maxdriftsq;         // max distance any atom drifts from original pos
-  double maxboostcoeff;      // cummulative max boost coeff for any bond
-  double minboostcoeff;      // cummulative min boost coeff for any bond
+  double maxdriftsq;         // max distance any bond atom drifts from quenched x
+
+  double sumbiascoeff;       // sum of all bond bias coeffs at each timestep
+  double avebiascoeff;       // cummulative sumbiascoeff/allbonds across steps
+  double minbiascoeff;       // cummulative min bias coeff for any bond
+  double maxbiascoeff;       // cummulative max bias coeff for any bond
+
   double rmaxever,rmaxeverbig;
-  int ghost_toofar;
+  int ghost_toofar;          // # of ghost atoms not found in Dcut neigh list
+
+  int checkbias_every,checkbias_flag,checkbias_count;
+
+  // 2 neighbor lists
+
+  class NeighList *listfull;   // full neigh list up to Dcut distance
+  class NeighList *listhalf;   // half neigh list up to pair distance
+                               // both created only when bonds are rebuilt
+
+  // list of my owned bonds and bias coeffs
+  // persists on a proc from one event until the next
+
+  struct OneBond {             // single IJ bond, atom I is owner
+    int i,j;                   // current local indices of 2 bond atoms
+    int iold,jold;             // local indices when bonds were formed
+    double r0;                 // relaxed bond length
+  };
+
+  OneBond *blist;              // list of owned bonds
+  double *biascoeff;           // biasing coefficient Cij for each bond
+  int nblocal;                 // # of owned bonds
+  int maxbond;                 // allocated size of blist
+
+  // old data from last timestep bonds were formed
+  // persists on a proc from one event until the next
+  // first set of vectors are maxlocal in length
+  // second set of vectors are maxall in length
+
+  int nlocal_old;               // nlocal for old atoms
+  int nall_old;                 // nlocal+nghost for old atoms
+  int maxlocal;                 // allocated size of old local atom vecs
+  int maxall;                   // allocated size of old all atom vecs
+
+  int *numbond;                 // # of bonds owned by old owned atoms
+  int *maxhalf;                 // bond index for maxstrain bond of old atoms
+  int *eligible;                // 0/1 flag for bias on one of old atom's bonds
+  double *maxhalfstrain;        // strain value for maxstrain bond of old atoms
+
+  int *old2now;                 // o2n[i] = current local index of old atom I
+                                // may be -1 if ghost atom has drifted
+  tagint *tagold;               // IDs of atoms when bonds were formed
+                                // 0 if a ghost atom is not in Dcut neigh list
+  double **xold;                // coords of atoms when bonds were formed
+
+  // vectors used to find maxstrain bonds within a local domain
+
+  int maxatom;                 // size of these vectors, nlocal + nghost
+
+  double *maxstrain;           // max-strain of any bond atom I is part of
+                               //   for owned and ghost atoms
+  double *maxstrain_domain;    // max-strain of any neighbor atom J of atom I
+                               //   for owned and ghost atoms
+  tagint *biasflag;            // atoms in biased bonds marked with bond partner
+                               //   for owned and ghost atoms
+
+  // list of biased bonds this proc owns
+
+  int maxbias;                 // allocated size of bias list
+  int nbias;                   // # of biased bonds I own
+  int *bias;                   // index of biased bonds in my bond list
+
+  // data structs for persisting bias coeffs when bond list is reformed
+
+  struct OneCoeff {
+    double biascoeff;
+    tagint tag;
+  };
+
+  MyPage<OneCoeff> *cpage;     // pages of OneCoeff datums for clist
+  OneCoeff **clist;            // ptrs to vectors of bias coeffs for each atom
+  int *numcoeff;               // # of bias coeffs per atom (one per bond)
+  int maxcoeff;                // allocate sized of clist and numcoeff
 
   // extra timers
 
   //double timefirst,timesecond,timethird,timefourth;
   //double timefifth,timesixth,timeseventh,timetotal;
 
-  // data structs for per-atom and per-bond info
-  // all of these are for current owned and ghost atoms
-  // except list and old2now are for atom indices at time of last bond build
+  // private methods
 
-  class NeighList *list;       // full neigh list up to Dcut distance
-                               // created only when bonds are rebuilt
-
-  int *old2now;                // o2n[i] = current local index of old atom i
-                               //   stored for old owned and ghost atoms
-                               //   I = old index when bonds were last created
-                               //   old indices are stored in old neighbor list
-
-  double **xold;               // coords of owned+ghost atoms when bonds created
-  tagint *tagold;              // global IDs of owned+ghost atoms when b created
-
-  int maxold;                  // allocated size of old2now
-  int maxbond;                 // allocated size of bonds
-  int old_nall;                // nlocal+nghost when old2now was last setup
-
-  struct OneBond {             // single IJ bond, atom I is owner
-    double r0;                 // original relaxed bond length
-    double boostcoeff;         // boost coefficient
-    tagint jtag;               // global index of J atom in bond IJ
-    int j;                     // local index of J atom in bond IJ
-  };
-
-  struct OneBond **bonds;      // 2d array of bonds for owned atoms
-  int *numbond;                // number of bonds for each owned atom
-
-  double *maxstrain;           // max-strain of any bond atom I is part of
-                               //   for owned and ghost atoms
-  double *maxstrain_region;    // max-strain of any neighbor atom J of atom I
-                               //   for owned and ghost atoms
-  int *maxstrain_bondindex;    // index of max-strain bond of each atom I
-                               //   just for owned atoms
-  tagint *biasflag;            // atoms in biased bonds marked with bond partner
-                               //   for owned and ghost atoms
-
-  // list of boosted bonds that this proc will bias
-
-  int maxboost;                // allocated size of boost list
-  int nboost;                  // # of boosted bonds I own
-  int *boost;                  // index of atom I in each boosted bond
-
-  // histogramming of bond boost cooeficients
-
-  int histo_every,histo_count,histo_print,histo_steps;
-  double histo_delta,invhisto_delta,histo_lo;
-  bigint *histo,*allhisto;
+  void grow_bond();
 };
 
 }
diff --git a/src/REPLICA/hyper.cpp b/src/REPLICA/hyper.cpp
index 22940de221..00b91684e9 100644
--- a/src/REPLICA/hyper.cpp
+++ b/src/REPLICA/hyper.cpp
@@ -40,9 +40,7 @@ enum{NOHYPER,GLOBAL,LOCAL};
 
 /* ---------------------------------------------------------------------- */
 
-Hyper::Hyper(LAMMPS *lmp) :
-  Pointers(lmp), dumplist(NULL)
-{}
+Hyper::Hyper(LAMMPS *lmp) : Pointers(lmp), dumplist(NULL) {}
 
 /* ----------------------------------------------------------------------
    perform hyperdynamics simulation
@@ -183,9 +181,6 @@ void Hyper::command(int narg, char **arg)
 
   if (hyperenable) fix_hyper->init_hyper();
 
-  timer->barrier_start();
-  time_start = timer->get_wall(Timer::TOTAL);
-
   // perform initial minimization and bond list creation
 
   int nevent = 0;
@@ -200,6 +195,14 @@ void Hyper::command(int narg, char **arg)
   if (hyperenable) fix_hyper->build_bond_list(0);
   fix_event->restore_state_quench();
 
+  // reset stats and timers to skip HD setup
+
+  nbuild = ndanger = 0;
+  time_dynamics = time_quench = 0.0;
+
+  timer->barrier_start();
+  time_start = timer->get_wall(Timer::TOTAL);
+
   // main loop: dynamics, store state, quench, check event, restore state
 
   int ecount;
@@ -260,11 +263,12 @@ void Hyper::command(int narg, char **arg)
   double maxdrift = 0.0;
   double maxbondlen = 0.0;
   double fraczero = 1.0;
+  double fracneg = 1.0;
 
-  double nnewbond,avenboost,aveboostcoeff,maxboostcoeff,minboostcoeff;
-  double maxbondperatom,neighbondperbond,aveboostnow;
+  double nnewbond,avenbias,avebiascoeff,minbiascoeff,maxbiascoeff;
+  double maxbondperatom,neighbondperbond,avebiasnow;
   double tbondbuild,rmaxever,rmaxeverbig,allghost_toofar;
-  double lostbond,lostbondcoeff,biasoverlap,nonmatchbiascoeff;
+  double biasoverlap;
 
   if (hyperenable) {
     t_hyper = fix_hyper->query(1);
@@ -274,115 +278,70 @@ void Hyper::command(int narg, char **arg)
     maxdrift = fix_hyper->query(5);
     maxbondlen = fix_hyper->query(6);
     fraczero = fix_hyper->query(7);
+    fracneg = fix_hyper->query(8);
 
     if (hyperstyle == LOCAL) {
-      nnewbond = fix_hyper->query(8);
-      maxbondperatom = fix_hyper->query(9);
-      avenboost = fix_hyper->query(10);
-      aveboostcoeff = fix_hyper->query(11);
-      maxboostcoeff = fix_hyper->query(12);
-      minboostcoeff = fix_hyper->query(13);
-      neighbondperbond = fix_hyper->query(14);
-      aveboostnow = fix_hyper->query(15);
-      tbondbuild = fix_hyper->query(16);
-      rmaxever = fix_hyper->query(17);
-      rmaxeverbig = fix_hyper->query(18);
-      allghost_toofar = fix_hyper->query(19);
-      lostbond = fix_hyper->query(20);
-      lostbondcoeff = fix_hyper->query(21);
-      biasoverlap = fix_hyper->query(22);
-      nonmatchbiascoeff = fix_hyper->query(23);
+      nnewbond = fix_hyper->query(9);
+      maxbondperatom = fix_hyper->query(10);
+      avenbias = fix_hyper->query(11);
+      avebiascoeff = fix_hyper->query(12);
+      minbiascoeff = fix_hyper->query(13);
+      maxbiascoeff = fix_hyper->query(14);
+      neighbondperbond = fix_hyper->query(15);
+      avebiasnow = fix_hyper->query(16);
+      tbondbuild = fix_hyper->query(17);
+      rmaxever = fix_hyper->query(18);
+      rmaxeverbig = fix_hyper->query(19);
+      allghost_toofar = fix_hyper->query(20);
+      biasoverlap = fix_hyper->query(21);
     }
   }
 
   if (me == 0) {
-    if (screen) {
-      fprintf(screen,"Cummulative quantities for fix hyper:\n");
-      fprintf(screen,"  hyper time = %g\n",t_hyper);
-      fprintf(screen,"  time boost factor = %g\n",t_hyper/(nsteps*update->dt));
-      fprintf(screen,"  event timesteps = %d\n",nevent_running);
-      fprintf(screen,"  # of atoms in events = %d\n",nevent_atoms_running);
-      fprintf(screen,"Quantities for this hyper run:\n");
-      fprintf(screen,"  event timesteps = %d\n",nevent);
-      fprintf(screen,"  # of atoms in events = %d\n",nevent_atoms);
-      fprintf(screen,"  max length of any bond = %g\n",maxbondlen);
-      fprintf(screen,"  max drift distance of any atom = %g\n",maxdrift);
-      fprintf(screen,"  fraction of steps & bonds with zero bias = %g\n",
-              fraczero);
-      fprintf(screen,"Current quantities:\n");
-      fprintf(screen,"  ave bonds/atom = %g\n",avebonds);
+    FILE *out;
+    for (int iout = 0; iout < 2; iout++) {
+      if (iout == 0) out = screen;
+      if (iout == 1) out = logfile;
+      if (!out) continue;
+      fprintf(out,"Cummulative quantities for fix hyper:\n");
+      fprintf(out,"  hyper time = %g\n",t_hyper);
+      fprintf(out,"  time boost factor = %g\n",t_hyper/(nsteps*update->dt));
+      fprintf(out,"  event timesteps = %d\n",nevent_running);
+      fprintf(out,"  # of atoms in events = %d\n",nevent_atoms_running);
+      fprintf(out,"Quantities for this hyper run:\n");
+      fprintf(out,"  event timesteps = %d\n",nevent);
+      fprintf(out,"  # of atoms in events = %d\n",nevent_atoms);
+      fprintf(out,"  max length of any bond = %g\n",maxbondlen);
+      fprintf(out,"  max drift distance of any atom = %g\n",maxdrift);
+      fprintf(out,"  fraction of biased bonds with zero bias = %g\n",fraczero);
+      fprintf(out,"  fraction of biased bonds with negative strain = %g\n",
+              fracneg);
+      fprintf(out,"Current quantities:\n");
+      fprintf(out,"  ave bonds/atom = %g\n",avebonds);
 
       if (hyperstyle == LOCAL) {
-        fprintf(screen,"Cummulative quantities specific to fix hyper/local:\n");
-        fprintf(screen,"  # of new bonds formed = %g\n",nnewbond);
-        fprintf(screen,"  max bonds/atom = %g\n",maxbondperatom);
-        fprintf(screen,"Quantities for this hyper run specific to "
+        fprintf(out,"Cummulative quantities specific to fix hyper/local:\n");
+        fprintf(out,"  # of new bonds formed = %g\n",nnewbond);
+        fprintf(out,"  max bonds/atom = %g\n",maxbondperatom);
+        fprintf(out,"Quantities for this hyper run specific to "
                 "fix hyper/local:\n");
-        fprintf(screen,"  ave boosted bonds/step = %g\n",avenboost);
-        fprintf(screen,"  ave boost coeff of all bonds = %g\n",aveboostcoeff);
-        fprintf(screen,"  max boost coeff of any bond = %g\n",maxboostcoeff);
-        fprintf(screen,"  min boost coeff of any bond = %g\n",minboostcoeff);
-        fprintf(screen,"  max dist from my box of any "
+        fprintf(out,"  ave biased bonds/step = %g\n",avenbias);
+        fprintf(out,"  ave bias coeff of all bonds = %g\n",avebiascoeff);
+        fprintf(out,"  min bias coeff of any bond = %g\n",minbiascoeff);
+        fprintf(out,"  max bias coeff of any bond = %g\n",maxbiascoeff);
+        fprintf(out,"  max dist from my subbox of any "
                 "non-maxstrain bond ghost atom = %g\n",rmaxever);
-        fprintf(screen,"  max dist from my box of any bond ghost atom = %g\n",
+        fprintf(out,"  max dist from my box of any bond ghost atom = %g\n",
                 rmaxeverbig);
-        fprintf(screen,"  count of bond ghost neighbors "
+        fprintf(out,"  count of bond ghost neighbors "
                 "not found on reneighbor steps = %g\n",allghost_toofar);
-        fprintf(screen,"  lost bond partners = %g\n",lostbond);
-        fprintf(screen,"  ave bias coeff for lost bond partners = %g\n",
-                lostbondcoeff);
-        fprintf(screen,"  bias overlaps = %g\n",biasoverlap);
-        fprintf(screen,"  non-matching bias coeffs = %g\n",nonmatchbiascoeff);
-        fprintf(screen,"  CPU time for bond builds = %g\n",tbondbuild);
-        fprintf(screen,"Current quantities specific to fix hyper/local:\n");
-        fprintf(screen,"  neighbor bonds/bond = %g\n",neighbondperbond);
-        fprintf(screen,"  ave boost coeff for all bonds = %g\n",aveboostnow);
+        fprintf(out,"  bias overlaps = %g\n",biasoverlap);
+        fprintf(out,"  CPU time for bond builds = %g\n",tbondbuild);
+        fprintf(out,"Current quantities specific to fix hyper/local:\n");
+        fprintf(out,"  neighbor bonds/bond = %g\n",neighbondperbond);
+        fprintf(out,"  ave boost coeff for all bonds = %g\n",avebiasnow);
       }
-      fprintf(screen,"\n");
-    }
-
-    if (logfile) {
-      fprintf(logfile,"Cummulative quantities for fix hyper:\n");
-      fprintf(logfile,"  hyper time = %g\n",t_hyper);
-      fprintf(logfile,"  event timesteps = %d\n",nevent_running);
-      fprintf(logfile,"  # of atoms in events = %d\n",nevent_atoms_running);
-      fprintf(logfile,"Quantities for this hyper run:\n");
-      fprintf(logfile,"  event timesteps = %d\n",nevent);
-      fprintf(logfile,"  # of atoms in events = %d\n",nevent_atoms);
-      fprintf(logfile,"  max length of any bond = %g\n",maxbondlen);
-      fprintf(logfile,"  max drift distance of any atom = %g\n",maxdrift);
-      fprintf(logfile,"  fraction of steps & bonds with zero bias = %g\n",
-              fraczero);
-      fprintf(logfile,"Current quantities:\n");
-      fprintf(logfile,"  ave bonds/atom = %g\n",avebonds);
-
-      if (hyperstyle == LOCAL) {
-        fprintf(logfile,"Cummulative quantities specific tofix hyper/local:\n");
-        fprintf(logfile,"  # of new bonds formed = %g\n",nnewbond);
-        fprintf(logfile,"  max bonds/atom = %g\n",maxbondperatom);
-        fprintf(logfile,"Quantities for this hyper run specific to "
-                "fix hyper/local:\n");
-        fprintf(logfile,"  ave boosted bonds/step = %g\n",avenboost);
-        fprintf(logfile,"  ave boost coeff of all bonds = %g\n",aveboostcoeff);
-        fprintf(logfile,"  max boost coeff of any bond = %g\n",maxboostcoeff);
-        fprintf(logfile,"  min boost coeff of any bond = %g\n",minboostcoeff);
-        fprintf(logfile,"  max dist from my box of any "
-                "non-maxstrain bond ghost atom = %g\n",rmaxever);
-        fprintf(logfile,"  max dist from my box of any bond ghost atom = %g\n",
-                rmaxeverbig);
-        fprintf(logfile,"  count of ghost bond neighbors "
-                "not found on reneighbor steps = %g\n",allghost_toofar);
-        fprintf(logfile,"  lost bond partners = %g\n",lostbond);
-        fprintf(logfile,"  ave bias coeff for lost bond partners = %g\n",
-                lostbondcoeff);
-        fprintf(logfile,"  bias overlaps = %g\n",biasoverlap);
-        fprintf(logfile,"  non-matching bias coeffs = %g\n",nonmatchbiascoeff);
-        fprintf(logfile,"  CPU time for bond builds = %g\n",tbondbuild);
-        fprintf(logfile,"Current quantities specific to fix hyper/local:\n");
-        fprintf(logfile,"  neighbor bonds/bond = %g\n",neighbondperbond);
-        fprintf(logfile,"  ave boost coeff for all bonds = %g\n",aveboostnow);
-      }
-      fprintf(logfile,"\n");
+      fprintf(out,"\n");
     }
   }
 
diff --git a/src/RIGID/compute_rigid_local.cpp b/src/RIGID/compute_rigid_local.cpp
index bcb778ab86..ec2799b6bc 100644
--- a/src/RIGID/compute_rigid_local.cpp
+++ b/src/RIGID/compute_rigid_local.cpp
@@ -40,8 +40,6 @@ ComputeRigidLocal::ComputeRigidLocal(LAMMPS *lmp, int narg, char **arg) :
 
   local_flag = 1;
   nvalues = narg - 4;
-  if (nvalues == 1) size_local_cols = 0;
-  else size_local_cols = nvalues;
 
   int n = strlen(arg[3]) + 1;
   idrigid = new char[n];
@@ -88,7 +86,10 @@ ComputeRigidLocal::ComputeRigidLocal(LAMMPS *lmp, int narg, char **arg) :
     else error->all(FLERR,"Invalid keyword in compute rigid/local command");
   }
 
-  ncount = nmax = 0;
+  if (nvalues == 1) size_local_cols = 0;
+  else size_local_cols = nvalues;
+
+ncount = nmax = 0;
   vlocal = NULL;
   alocal = NULL;
 }
diff --git a/src/RIGID/fix_rigid_small.cpp b/src/RIGID/fix_rigid_small.cpp
index fb185d7702..54fb83f0aa 100644
--- a/src/RIGID/fix_rigid_small.cpp
+++ b/src/RIGID/fix_rigid_small.cpp
@@ -28,12 +28,14 @@
 #include "modify.h"
 #include "group.h"
 #include "comm.h"
+#include "neighbor.h"
 #include "force.h"
 #include "input.h"
 #include "output.h"
 #include "variable.h"
 #include "random_mars.h"
 #include "math_const.h"
+#include "hashlittle.h"
 #include "memory.h"
 #include "error.h"
 
@@ -43,6 +45,8 @@ using namespace LAMMPS_NS;
 using namespace FixConst;
 using namespace MathConst;
 
+#define RVOUS 1   // 0 for irregular, 1 for all2all
+
 #define MAXLINE 1024
 #define CHUNK 1024
 #define ATTRIBUTE_PERBODY 20
@@ -70,8 +74,7 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
   xcmimage(NULL), displace(NULL), eflags(NULL), orient(NULL), dorient(NULL),
   avec_ellipsoid(NULL), avec_line(NULL), avec_tri(NULL), counts(NULL),
   itensor(NULL), mass_body(NULL), langextra(NULL), random(NULL),
-  id_dilate(NULL), onemols(NULL), hash(NULL), bbox(NULL), ctr(NULL),
-  idclose(NULL), rsqclose(NULL)
+  id_dilate(NULL), onemols(NULL)
 {
   int i;
 
@@ -107,18 +110,18 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
   // parse args for rigid body specification
 
   int *mask = atom->mask;
-  tagint *bodyid = NULL;
+  tagint *bodyID = NULL;
   int nlocal = atom->nlocal;
 
   if (narg < 4) error->all(FLERR,"Illegal fix rigid/small command");
   if (strcmp(arg[3],"molecule") == 0) {
     if (atom->molecule_flag == 0)
       error->all(FLERR,"Fix rigid/small requires atom attribute molecule");
-    bodyid = atom->molecule;
+    bodyID = atom->molecule;
 
   } else if (strcmp(arg[3],"custom") == 0) {
     if (narg < 5) error->all(FLERR,"Illegal fix rigid/small command");
-      bodyid = new tagint[nlocal];
+      bodyID = new tagint[nlocal];
       customflag = 1;
 
       // determine whether atom-style variable or atom property is used.
@@ -126,9 +129,11 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
         int is_double=0;
         int custom_index = atom->find_custom(arg[4]+2,is_double);
         if (custom_index == -1)
-          error->all(FLERR,"Fix rigid/small custom requires previously defined property/atom");
+          error->all(FLERR,"Fix rigid/small custom requires "
+                     "previously defined property/atom");
         else if (is_double)
-          error->all(FLERR,"Fix rigid/small custom requires integer-valued property/atom");
+          error->all(FLERR,"Fix rigid/small custom requires "
+                     "integer-valued property/atom");
 
         int minval = INT_MAX;
         int *value = atom->ivector[custom_index];
@@ -139,15 +144,17 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
 
         for (i = 0; i < nlocal; i++)
           if (mask[i] & groupbit)
-            bodyid[i] = (tagint)(value[i] - minval + 1);
-          else bodyid[i] = 0;
+            bodyID[i] = (tagint)(value[i] - minval + 1);
+          else bodyID[i] = 0;
 
       } else if (strstr(arg[4],"v_") == arg[4]) {
         int ivariable = input->variable->find(arg[4]+2);
         if (ivariable < 0)
-          error->all(FLERR,"Variable name for fix rigid/small custom does not exist");
+          error->all(FLERR,"Variable name for fix rigid/small custom "
+                     "does not exist");
         if (input->variable->atomstyle(ivariable) == 0)
-          error->all(FLERR,"Fix rigid/small custom variable is no atom-style variable");
+          error->all(FLERR,"Fix rigid/small custom variable is not "
+                     "atom-style variable");
         double *value = new double[nlocal];
         input->variable->compute_atom(ivariable,0,value,1,0);
         int minval = INT_MAX;
@@ -158,8 +165,8 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
 
         for (i = 0; i < nlocal; i++)
           if (mask[i] & groupbit)
-            bodyid[i] = (tagint)((tagint)value[i] - minval + 1);
-          else bodyid[0] = 0;
+            bodyID[i] = (tagint)((tagint)value[i] - minval + 1);
+          else bodyID[0] = 0;
         delete[] value;
       } else error->all(FLERR,"Unsupported fix rigid custom property");
   } else error->all(FLERR,"Illegal fix rigid/small command");
@@ -167,10 +174,11 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
   if (atom->map_style == 0)
     error->all(FLERR,"Fix rigid/small requires an atom map, see atom_modify");
 
-  // maxmol = largest bodyid #
+  // maxmol = largest bodyID #
+
   maxmol = -1;
   for (i = 0; i < nlocal; i++)
-    if (mask[i] & groupbit) maxmol = MAX(maxmol,bodyid[i]);
+    if (mask[i] & groupbit) maxmol = MAX(maxmol,bodyID[i]);
 
   tagint itmp;
   MPI_Allreduce(&maxmol,&itmp,1,MPI_LMP_TAGINT,MPI_MAX,world);
@@ -400,8 +408,19 @@ FixRigidSmall::FixRigidSmall(LAMMPS *lmp, int narg, char **arg) :
   // sets bodytag for owned atoms
   // body attributes are computed later by setup_bodies()
 
-  create_bodies(bodyid);
-  if (customflag) delete [] bodyid;
+  double time1 = MPI_Wtime();
+
+  create_bodies(bodyID);
+  if (customflag) delete [] bodyID;
+
+  double time2 = MPI_Wtime();
+
+  if (comm->me == 0) {
+    if (screen)
+      fprintf(screen,"  create bodies CPU = %g secs\n",time2-time1);
+    if (logfile)
+      fprintf(logfile,"  create bodies CPU = %g secs\n",time2-time1);
+  }
 
   // set nlocal_body and allocate bodies I own
 
@@ -569,7 +588,8 @@ void FixRigidSmall::init()
       if (rflag && (modify->fmask[i] & POST_FORCE) &&
           !modify->fix[i]->rigid_flag) {
         char str[128];
-        snprintf(str,128,"Fix %s alters forces after fix rigid",modify->fix[i]->id);
+        snprintf(str,128,"Fix %s alters forces after fix rigid",
+                 modify->fix[i]->id);
         error->warning(FLERR,str);
       }
     }
@@ -633,6 +653,16 @@ void FixRigidSmall::setup(int vflag)
 {
   int i,n,ibody;
 
+  // error if maxextent > comm->cutghost
+  // NOTE: could just warn if an override flag set
+  // NOTE: this could fail for comm multi mode if user sets a wrong cutoff
+  //       for atom types in rigid bodies - need a more careful test
+  // must check here, not in init, b/c neigh/comm values set after fix init
+
+  double cutghost = MAX(neighbor->cutneighmax,comm->cutghostuser);
+  if (maxextent > cutghost)
+    error->all(FLERR,"Rigid body extent > ghost cutoff - use comm_modify cutoff");
+
   //check(1);
 
   // sum fcm, torque across all rigid bodies
@@ -1514,175 +1544,72 @@ void FixRigidSmall::set_v()
    set bodytag for all owned atoms
 ------------------------------------------------------------------------- */
 
-void FixRigidSmall::create_bodies(tagint *bodyid)
+void FixRigidSmall::create_bodies(tagint *bodyID)
 {
-  int i,m,n;
-  double unwrap[3];
+  int i,m;
 
-  // error check on image flags of atoms in rigid bodies
+  // allocate buffer for input to rendezvous comm
+  // ncount = # of my atoms in bodies
 
-  imageint *image = atom->image;
   int *mask = atom->mask;
   int nlocal = atom->nlocal;
 
-  int *periodicity = domain->periodicity;
-  int xbox,ybox,zbox;
-
-  int flag = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (!(mask[i] & groupbit)) continue;
-    xbox = (image[i] & IMGMASK) - IMGMAX;
-    ybox = (image[i] >> IMGBITS & IMGMASK) - IMGMAX;
-    zbox = (image[i] >> IMG2BITS) - IMGMAX;
-    if ((xbox && !periodicity[0]) || (ybox && !periodicity[1]) ||
-        (zbox && !periodicity[2])) flag = 1;
-  }
-
-  int flagall;
-  MPI_Allreduce(&flag,&flagall,1,MPI_INT,MPI_SUM,world);
-  if (flagall) error->all(FLERR,"Fix rigid/small atom has non-zero image flag "
-                          "in a non-periodic dimension");
-
-  // allocate buffer for passing messages around ring of procs
-  // percount = max number of values to put in buffer for each of ncount
-
   int ncount = 0;
   for (i = 0; i < nlocal; i++)
     if (mask[i] & groupbit) ncount++;
 
-  int percount = 5;
-  double *buf;
-  memory->create(buf,ncount*percount,"rigid/small:buf");
+  int *proclist;
+  memory->create(proclist,ncount,"rigid/small:proclist");
+  InRvous *inbuf = (InRvous *)
+    memory->smalloc(ncount*sizeof(InRvous),"rigid/small:inbuf");
 
-  // create map hash for storing unique body IDs of my atoms
-  // key = body ID
-  // value = index into per-body data structure
-  // n = # of entries in hash
-
-  hash = new std::map<tagint,int>();
-  hash->clear();
-
-  // setup hash
-  // key = body ID
-  // value = index into N-length data structure
-  // n = count of unique bodies my atoms are part of
-
-  n = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (!(mask[i] & groupbit)) continue;
-    if (hash->find(bodyid[i]) == hash->end()) (*hash)[bodyid[i]] = n++;
-  }
-
-  // bbox = bounding box of each rigid body my atoms are part of
-
-  memory->create(bbox,n,6,"rigid/small:bbox");
-
-  for (i = 0; i < n; i++) {
-    bbox[i][0] = bbox[i][2] = bbox[i][4] = BIG;
-    bbox[i][1] = bbox[i][3] = bbox[i][5] = -BIG;
-  }
-
-  // pack my atoms into buffer as body ID, unwrapped coords
+  // setup buf to pass to rendezvous comm
+  // one BodyMsg datum for each constituent atom
+  // datum = me, local index of atom, atomID, bodyID, unwrapped coords
+  // owning proc for each datum = random hash of bodyID
 
   double **x = atom->x;
-
-  m = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (!(mask[i] & groupbit)) continue;
-    domain->unmap(x[i],image[i],unwrap);
-    buf[m++] = bodyid[i];
-    buf[m++] = unwrap[0];
-    buf[m++] = unwrap[1];
-    buf[m++] = unwrap[2];
-  }
-
-  // pass buffer around ring of procs
-  // func = update bbox with atom coords from every proc
-  // when done, have full bbox for every rigid body my atoms are part of
-
-  comm->ring(m,sizeof(double),buf,1,ring_bbox,NULL,(void *)this);
-
-  // check if any bbox is size 0.0, meaning rigid body is a single particle
-
-  flag = 0;
-  for (i = 0; i < n; i++)
-    if (bbox[i][0] == bbox[i][1] && bbox[i][2] == bbox[i][3] &&
-        bbox[i][4] == bbox[i][5]) flag = 1;
-  MPI_Allreduce(&flag,&flagall,1,MPI_INT,MPI_SUM,world);
-  if (flagall)
-    error->all(FLERR,"One or more rigid bodies are a single particle");
-
-  // ctr = center pt of each rigid body my atoms are part of
-
-  memory->create(ctr,n,6,"rigid/small:bbox");
-
-  for (i = 0; i < n; i++) {
-    ctr[i][0] = 0.5 * (bbox[i][0] + bbox[i][1]);
-    ctr[i][1] = 0.5 * (bbox[i][2] + bbox[i][3]);
-    ctr[i][2] = 0.5 * (bbox[i][4] + bbox[i][5]);
-  }
-
-  // idclose = ID of atom in body closest to center pt (smaller ID if tied)
-  // rsqclose = distance squared from idclose to center pt
-
-  memory->create(idclose,n,"rigid/small:idclose");
-  memory->create(rsqclose,n,"rigid/small:rsqclose");
-
-  for (i = 0; i < n; i++) rsqclose[i] = BIG;
-
-  // pack my atoms into buffer as body ID, atom ID, unwrapped coords
-
   tagint *tag = atom->tag;
+  imageint *image = atom->image;
 
   m = 0;
   for (i = 0; i < nlocal; i++) {
     if (!(mask[i] & groupbit)) continue;
-    domain->unmap(x[i],image[i],unwrap);
-    buf[m++] = bodyid[i];
-    buf[m++] = ubuf(tag[i]).d;
-    buf[m++] = unwrap[0];
-    buf[m++] = unwrap[1];
-    buf[m++] = unwrap[2];
+    proclist[m] = hashlittle(&bodyID[i],sizeof(tagint),0) % nprocs;
+    inbuf[m].me = me;
+    inbuf[m].ilocal = i;
+    inbuf[m].atomID = tag[i];
+    inbuf[m].bodyID = bodyID[i];
+    domain->unmap(x[i],image[i],inbuf[m].x);
+    m++;
   }
 
-  // pass buffer around ring of procs
-  // func = update idclose,rsqclose with atom IDs from every proc
-  // when done, have idclose for every rigid body my atoms are part of
+  // perform rendezvous operation
+  // each proc owns random subset of bodies
+  // receives all atoms in those bodies
+  // func = compute bbox of each body, find atom closest to geometric center
 
-  comm->ring(m,sizeof(double),buf,2,ring_nearest,NULL,(void *)this);
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,ncount,(char *) inbuf,sizeof(InRvous),
+                                 0,proclist,
+                                 rendezvous_body,0,buf,sizeof(OutRvous),
+                                 (void *) this);
+  OutRvous *outbuf = (OutRvous *) buf;
 
-  // set bodytag of all owned atoms, based on idclose
-  // find max value of rsqclose across all procs
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
 
-  double rsqmax = 0.0;
-  for (i = 0; i < nlocal; i++) {
-    bodytag[i] = 0;
-    if (!(mask[i] & groupbit)) continue;
-    m = hash->find(bodyid[i])->second;
-    bodytag[i] = idclose[m];
-    rsqmax = MAX(rsqmax,rsqclose[m]);
-  }
+  // set bodytag of all owned atoms based on outbuf info for constituent atoms
 
-  // pack my atoms into buffer as bodytag of owning atom, unwrapped coords
+  for (i = 0; i < nlocal; i++)
+    if (!(mask[i] & groupbit)) bodytag[i] = 0;
 
-  m = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (!(mask[i] & groupbit)) continue;
-    domain->unmap(x[i],image[i],unwrap);
-    buf[m++] = ubuf(bodytag[i]).d;
-    buf[m++] = unwrap[0];
-    buf[m++] = unwrap[1];
-    buf[m++] = unwrap[2];
-  }
+  for (m = 0; m < nreturn; m++)
+    bodytag[outbuf[m].ilocal] = outbuf[m].atomID;
 
-  // pass buffer around ring of procs
-  // func = update rsqfar for atoms belonging to bodies I own
-  // when done, have rsqfar for all atoms in bodies I own
+  memory->sfree(outbuf);
 
-  rsqfar = 0.0;
-  comm->ring(m,sizeof(double),buf,3,ring_farthest,NULL,(void *)this);
-
-  // find maxextent of rsqfar across all procs
+  // maxextent = max of rsqfar across all procs
   // if defined, include molecule->maxextent
 
   MPI_Allreduce(&rsqfar,&maxextent,1,MPI_DOUBLE,MPI_MAX,world);
@@ -1691,125 +1618,156 @@ void FixRigidSmall::create_bodies(tagint *bodyid)
     for (int i = 0; i < nmol; i++)
       maxextent = MAX(maxextent,onemols[i]->maxextent);
   }
+}
+
+/* ----------------------------------------------------------------------
+   process rigid bodies assigned to me
+   buf = list of N BodyMsg datums
+------------------------------------------------------------------------- */
+
+int FixRigidSmall::rendezvous_body(int n, char *inbuf,
+                                   int &rflag, int *&proclist, char *&outbuf,
+                                   void *ptr)
+{
+  int i,m;
+  double delx,dely,delz,rsq;
+  int *iclose;
+  tagint *idclose;
+  double *x,*xown,*rsqclose;
+  double **bbox,**ctr;
+
+  FixRigidSmall *frsptr = (FixRigidSmall *) ptr;
+  Memory *memory = frsptr->memory;
+  Error *error = frsptr->error;
+  MPI_Comm world = frsptr->world;
+
+  // setup hash
+  // use STL map instead of atom->map
+  //   b/c know nothing about body ID values specified by user
+  // ncount = number of bodies assigned to me
+  // key = body ID
+  // value = index into Ncount-length data structure
+
+  InRvous *in = (InRvous *) inbuf;
+  std::map<tagint,int> hash;
+  tagint id;
+
+  int ncount = 0;
+  for (i = 0; i < n; i++) {
+    id = in[i].bodyID;
+    if (hash.find(id) == hash.end()) hash[id] = ncount++;
+  }
+
+  // bbox = bounding box of each rigid body
+
+  memory->create(bbox,ncount,6,"rigid/small:bbox");
+
+  for (m = 0; m < ncount; m++) {
+    bbox[m][0] = bbox[m][2] = bbox[m][4] = BIG;
+    bbox[m][1] = bbox[m][3] = bbox[m][5] = -BIG;
+  }
+
+  for (i = 0; i < n; i++) {
+    m = hash.find(in[i].bodyID)->second;
+    x = in[i].x;
+    bbox[m][0] = MIN(bbox[m][0],x[0]);
+    bbox[m][1] = MAX(bbox[m][1],x[0]);
+    bbox[m][2] = MIN(bbox[m][2],x[1]);
+    bbox[m][3] = MAX(bbox[m][3],x[1]);
+    bbox[m][4] = MIN(bbox[m][4],x[2]);
+    bbox[m][5] = MAX(bbox[m][5],x[2]);
+  }
+
+  // check if any bbox is size 0.0, meaning rigid body is a single particle
+
+  int flag = 0;
+  for (m = 0; m < ncount; m++)
+    if (bbox[m][0] == bbox[m][1] && bbox[m][2] == bbox[m][3] &&
+        bbox[m][4] == bbox[m][5]) flag = 1;
+  int flagall;
+  MPI_Allreduce(&flag,&flagall,1,MPI_INT,MPI_SUM,world);    // sync here?
+  if (flagall)
+    error->all(FLERR,"One or more rigid bodies are a single particle");
+
+  // ctr = geometric center pt of each rigid body
+
+  memory->create(ctr,ncount,3,"rigid/small:bbox");
+
+  for (m = 0; m < ncount; m++) {
+    ctr[m][0] = 0.5 * (bbox[m][0] + bbox[m][1]);
+    ctr[m][1] = 0.5 * (bbox[m][2] + bbox[m][3]);
+    ctr[m][2] = 0.5 * (bbox[m][4] + bbox[m][5]);
+  }
+
+  // idclose = atomID closest to center point of each body
+
+  memory->create(idclose,ncount,"rigid/small:idclose");
+  memory->create(iclose,ncount,"rigid/small:iclose");
+  memory->create(rsqclose,ncount,"rigid/small:rsqclose");
+  for (m = 0; m < ncount; m++) rsqclose[m] = BIG;
+
+  for (i = 0; i < n; i++) {
+    m = hash.find(in[i].bodyID)->second;
+    x = in[i].x;
+    delx = x[0] - ctr[m][0];
+    dely = x[1] - ctr[m][1];
+    delz = x[2] - ctr[m][2];
+    rsq = delx*delx + dely*dely + delz*delz;
+    if (rsq <= rsqclose[m]) {
+      if (rsq == rsqclose[m] && in[i].atomID > idclose[m]) continue;
+      iclose[m] = i;
+      idclose[m] = in[i].atomID;
+      rsqclose[m] = rsq;
+    }
+  }
+
+  // compute rsqfar for all bodies I own
+  // set rsqfar back in caller
+
+  double rsqfar = 0.0;
+
+  for (int i = 0; i < n; i++) {
+    m = hash.find(in[i].bodyID)->second;
+    xown = in[iclose[m]].x;
+    x = in[i].x;
+    delx = x[0] - xown[0];
+    dely = x[1] - xown[1];
+    delz = x[2] - xown[2];
+    rsq = delx*delx + dely*dely + delz*delz;
+    rsqfar = MAX(rsqfar,rsq);
+  }
+
+  frsptr->rsqfar = rsqfar;
+
+  // pass list of OutRvous datums back to comm->rendezvous
+
+  int nout = n;
+  memory->create(proclist,nout,"rigid/small:proclist");
+  OutRvous *out = (OutRvous *)
+    memory->smalloc(nout*sizeof(OutRvous),"rigid/small:out");
+
+  for (int i = 0; i < nout; i++) {
+    proclist[i] = in[i].me;
+    out[i].ilocal = in[i].ilocal;
+    m = hash.find(in[i].bodyID)->second;
+    out[i].atomID = idclose[m];
+  }
+
+  outbuf = (char *) out;
 
   // clean up
+  // Comm::rendezvous will delete proclist and out (outbuf)
 
-  delete hash;
-  memory->destroy(buf);
   memory->destroy(bbox);
   memory->destroy(ctr);
   memory->destroy(idclose);
+  memory->destroy(iclose);
   memory->destroy(rsqclose);
-}
 
-/* ----------------------------------------------------------------------
-   process rigid body atoms from another proc
-   update bounding box for rigid bodies my atoms are part of
-------------------------------------------------------------------------- */
+  // flag = 2: new outbuf
 
-void FixRigidSmall::ring_bbox(int n, char *cbuf, void *ptr)
-{
-  FixRigidSmall *frsptr = (FixRigidSmall *) ptr;
-  std::map<tagint,int> *hash = frsptr->hash;
-  double **bbox = frsptr->bbox;
-
-  double *buf = (double *) cbuf;
-  int ndatums = n/4;
-
-  int j,imol;
-  double *x;
-
-  int m = 0;
-  for (int i = 0; i < ndatums; i++, m += 4) {
-    imol = static_cast<int> (buf[m]);
-    if (hash->find(imol) != hash->end()) {
-      j = hash->find(imol)->second;
-      x = &buf[m+1];
-      bbox[j][0] = MIN(bbox[j][0],x[0]);
-      bbox[j][1] = MAX(bbox[j][1],x[0]);
-      bbox[j][2] = MIN(bbox[j][2],x[1]);
-      bbox[j][3] = MAX(bbox[j][3],x[1]);
-      bbox[j][4] = MIN(bbox[j][4],x[2]);
-      bbox[j][5] = MAX(bbox[j][5],x[2]);
-    }
-  }
-}
-
-/* ----------------------------------------------------------------------
-   process rigid body atoms from another proc
-   update nearest atom to body center for rigid bodies my atoms are part of
-------------------------------------------------------------------------- */
-
-void FixRigidSmall::ring_nearest(int n, char *cbuf, void *ptr)
-{
-  FixRigidSmall *frsptr = (FixRigidSmall *) ptr;
-  std::map<tagint,int> *hash = frsptr->hash;
-  double **ctr = frsptr->ctr;
-  tagint *idclose = frsptr->idclose;
-  double *rsqclose = frsptr->rsqclose;
-
-  double *buf = (double *) cbuf;
-  int ndatums = n/5;
-
-  int j,imol;
-  tagint tag;
-  double delx,dely,delz,rsq;
-  double *x;
-
-  int m = 0;
-  for (int i = 0; i < ndatums; i++, m += 5) {
-    imol = static_cast<int> (buf[m]);
-    if (hash->find(imol) != hash->end()) {
-      j = hash->find(imol)->second;
-      tag = (tagint) ubuf(buf[m+1]).i;
-      x = &buf[m+2];
-      delx = x[0] - ctr[j][0];
-      dely = x[1] - ctr[j][1];
-      delz = x[2] - ctr[j][2];
-      rsq = delx*delx + dely*dely + delz*delz;
-      if (rsq <= rsqclose[j]) {
-        if (rsq == rsqclose[j] && tag > idclose[j]) continue;
-        idclose[j] = tag;
-        rsqclose[j] = rsq;
-      }
-    }
-  }
-}
-
-/* ----------------------------------------------------------------------
-   process rigid body atoms from another proc
-   update rsqfar = distance from owning atom to other atom
-------------------------------------------------------------------------- */
-
-void FixRigidSmall::ring_farthest(int n, char *cbuf, void *ptr)
-{
-  FixRigidSmall *frsptr = (FixRigidSmall *) ptr;
-  double **x = frsptr->atom->x;
-  imageint *image = frsptr->atom->image;
-  int nlocal = frsptr->atom->nlocal;
-
-  double *buf = (double *) cbuf;
-  int ndatums = n/4;
-
-  int iowner;
-  tagint tag;
-  double delx,dely,delz,rsq;
-  double *xx;
-  double unwrap[3];
-
-  int m = 0;
-  for (int i = 0; i < ndatums; i++, m += 4) {
-    tag = (tagint) ubuf(buf[m]).i;
-    iowner = frsptr->atom->map(tag);
-    if (iowner < 0 || iowner >= nlocal) continue;
-    frsptr->domain->unmap(x[iowner],image[iowner],unwrap);
-    xx = &buf[m+1];
-    delx = xx[0] - unwrap[0];
-    dely = xx[1] - unwrap[1];
-    delz = xx[2] - unwrap[2];
-    rsq = delx*delx + dely*dely + delz*delz;
-    frsptr->rsqfar = MAX(frsptr->rsqfar,rsq);
-  }
+  rflag = 2;
+  return nout;
 }
 
 /* ----------------------------------------------------------------------
@@ -2472,9 +2430,9 @@ void FixRigidSmall::readfile(int which, double **array, int *inbody)
 
   int nlocal = atom->nlocal;
 
-  hash = new std::map<tagint,int>();
+  std::map<tagint,int> hash;
   for (i = 0; i < nlocal; i++)
-    if (bodyown[i] >= 0) (*hash)[atom->molecule[i]] = bodyown[i];
+    if (bodyown[i] >= 0) hash[atom->molecule[i]] = bodyown[i];
 
   // open file and read header
 
@@ -2533,11 +2491,11 @@ void FixRigidSmall::readfile(int which, double **array, int *inbody)
       id = ATOTAGINT(values[0]);
       if (id <= 0 || id > maxmol)
         error->all(FLERR,"Invalid rigid body ID in fix rigid/small file");
-      if (hash->find(id) == hash->end()) {
+      if (hash.find(id) == hash.end()) {
         buf = next + 1;
         continue;
       }
-      m = (*hash)[id];
+      m = hash[id];
       inbody[m] = 1;
 
       if (which == 0) {
@@ -2576,7 +2534,6 @@ void FixRigidSmall::readfile(int which, double **array, int *inbody)
 
   delete [] buffer;
   delete [] values;
-  delete hash;
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/RIGID/fix_rigid_small.h b/src/RIGID/fix_rigid_small.h
index 3f6826f9bb..b5a3d5208d 100644
--- a/src/RIGID/fix_rigid_small.h
+++ b/src/RIGID/fix_rigid_small.h
@@ -22,9 +22,6 @@ FixStyle(rigid/small,FixRigidSmall)
 
 #include "fix.h"
 
-// replace this later
-#include <map>
-
 namespace LAMMPS_NS {
 
 class FixRigidSmall : public Fix {
@@ -180,13 +177,21 @@ class FixRigidSmall : public Fix {
 
   // class data used by ring communication callbacks
 
-  std::map<tagint,int> *hash;
-  double **bbox;
-  double **ctr;
-  tagint *idclose;
-  double *rsqclose;
   double rsqfar;
 
+  struct InRvous {
+    int me,ilocal;
+    tagint atomID,bodyID;
+    double x[3];
+  };
+
+  struct OutRvous {
+    int ilocal;
+    tagint atomID;
+  };
+
+  // local methods
+
   void image_shift();
   void set_xv();
   void set_v();
@@ -199,11 +204,9 @@ class FixRigidSmall : public Fix {
   void grow_body();
   void reset_atom2body();
 
-  // callback functions for ring communication
+  // callback function for rendezvous communication
 
-  static void ring_bbox(int, char *, void *);
-  static void ring_nearest(int, char *, void *);
-  static void ring_farthest(int, char *, void *);
+  static int rendezvous_body(int, char *, int &, int *&, char *&, void *);
 
   // debug
 
diff --git a/src/RIGID/fix_shake.cpp b/src/RIGID/fix_shake.cpp
index e0d1bf132b..23ced2d0e7 100644
--- a/src/RIGID/fix_shake.cpp
+++ b/src/RIGID/fix_shake.cpp
@@ -39,6 +39,8 @@ using namespace LAMMPS_NS;
 using namespace FixConst;
 using namespace MathConst;
 
+#define RVOUS 1   // 0 for irregular, 1 for all2all
+
 #define BIG 1.0e20
 #define MASSDELTA 0.1
 
@@ -219,8 +221,19 @@ FixShake::FixShake(LAMMPS *lmp, int narg, char **arg) :
 
   // identify all SHAKE clusters
 
+  double time1 = MPI_Wtime();
+
   find_clusters();
 
+  double time2 = MPI_Wtime();
+
+  if (comm->me == 0) {
+    if (screen)
+      fprintf(screen,"  find clusters CPU = %g secs\n",time2-time1);
+    if (logfile)
+      fprintf(logfile,"  find clusters CPU = %g secs\n",time2-time1);
+  }
+
   // initialize list of SHAKE clusters to constrain
 
   maxlist = 0;
@@ -681,10 +694,9 @@ int FixShake::dof(int igroup)
 void FixShake::find_clusters()
 {
   int i,j,m,n,imol,iatom;
-  int flag,flag_all,nbuf,size;
+  int flag,flag_all;
   tagint tagprev;
   double massone;
-  tagint *buf;
 
   if (me == 0 && screen) {
     if (!rattle) fprintf(screen,"Finding SHAKE clusters ...\n");
@@ -707,13 +719,6 @@ void FixShake::find_clusters()
   int nlocal = atom->nlocal;
   int angles_allow = atom->avec->angles_allow;
 
-  // setup ring of procs
-
-  int next = me + 1;
-  int prev = me -1;
-  if (next == nprocs) next = 0;
-  if (prev < 0) prev = nprocs - 1;
-
   // -----------------------------------------------------
   // allocate arrays for self (1d) and bond partners (2d)
   // max = max # of bond partners for owned atoms = 2nd dim of partner arrays
@@ -755,6 +760,10 @@ void FixShake::find_clusters()
   memory->create(partner_shake,nlocal,max,"shake:partner_shake");
   memory->create(partner_nshake,nlocal,max,"shake:partner_nshake");
 
+  // setup atomIDs and procowner vectors in rendezvous decomposition
+
+  atom_owners();
+
   // -----------------------------------------------------
   // set npartner and partner_tag from special arrays
   // -----------------------------------------------------
@@ -778,86 +787,13 @@ void FixShake::find_clusters()
   }
 
   // -----------------------------------------------------
-  // set partner_mask, partner_type, partner_massflag, partner_bondtype
-  //   for bonded partners
-  // requires communication for off-proc partners
+  // set partner_mask, partner_type, partner_massflag,
+  //   partner_bondtype for all my bonded partners
+  // requires rendezvous communication for off-proc partners
   // -----------------------------------------------------
 
-  // fill in mask, type, massflag, bondtype if own bond partner
-  // info to store in buf for each off-proc bond = nper = 6
-  //   2 atoms IDs in bond, space for mask, type, massflag, bondtype
-  // nbufmax = largest buffer needed to hold info from any proc
-
-  int nper = 6;
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) {
-    for (j = 0; j < npartner[i]; j++) {
-      partner_mask[i][j] = 0;
-      partner_type[i][j] = 0;
-      partner_massflag[i][j] = 0;
-      partner_bondtype[i][j] = 0;
-
-      m = atom->map(partner_tag[i][j]);
-      if (m >= 0 && m < nlocal) {
-        partner_mask[i][j] = mask[m];
-        partner_type[i][j] = type[m];
-        if (nmass) {
-          if (rmass) massone = rmass[m];
-          else massone = mass[type[m]];
-          partner_massflag[i][j] = masscheck(massone);
-        }
-        n = bondtype_findset(i,tag[i],partner_tag[i][j],0);
-        if (n) partner_bondtype[i][j] = n;
-        else {
-          n = bondtype_findset(m,tag[i],partner_tag[i][j],0);
-          if (n) partner_bondtype[i][j] = n;
-        }
-      } else nbuf += nper;
-    }
-  }
-
-  memory->create(buf,nbuf,"shake:buf");
-
-  // fill buffer with info
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    for (j = 0; j < npartner[i]; j++) {
-      m = atom->map(partner_tag[i][j]);
-      if (m < 0 || m >= nlocal) {
-        buf[size] = tag[i];
-        buf[size+1] = partner_tag[i][j];
-        buf[size+2] = 0;
-        buf[size+3] = 0;
-        buf[size+4] = 0;
-        n = bondtype_findset(i,tag[i],partner_tag[i][j],0);
-        if (n) buf[size+5] = n;
-        else buf[size+5] = 0;
-        size += nper;
-      }
-    }
-  }
-
-  // cycle buffer around ring of procs back to self
-
-  comm->ring(size,sizeof(tagint),buf,1,ring_bonds,buf,(void *)this);
-
-  // store partner info returned to me
-
-  m = 0;
-  while (m < size) {
-    i = atom->map(buf[m]);
-    for (j = 0; j < npartner[i]; j++)
-      if (buf[m+1] == partner_tag[i][j]) break;
-    partner_mask[i][j] = buf[m+2];
-    partner_type[i][j] = buf[m+3];
-    partner_massflag[i][j] = buf[m+4];
-    partner_bondtype[i][j] = buf[m+5];
-    m += nper;
-  }
-
-  memory->destroy(buf);
+  partner_info(npartner,partner_tag,partner_mask,partner_type,
+               partner_massflag,partner_bondtype);
 
   // error check for unfilled partner info
   // if partner_type not set, is an error
@@ -868,12 +804,13 @@ void FixShake::find_clusters()
   // else it's an error
 
   flag = 0;
+  int flag2 = 0;
   for (i = 0; i < nlocal; i++)
     for (j = 0; j < npartner[i]; j++) {
-      if (partner_type[i][j] == 0) flag = 1;
+      if (partner_type[i][j] == 0) flag++;
       if (!(mask[i] & groupbit)) continue;
       if (!(partner_mask[i][j] & groupbit)) continue;
-      if (partner_bondtype[i][j] == 0) flag = 1;
+      if (partner_bondtype[i][j] == 0) flag2++;
     }
 
   MPI_Allreduce(&flag,&flag_all,1,MPI_INT,MPI_SUM,world);
@@ -931,55 +868,10 @@ void FixShake::find_clusters()
 
   // -----------------------------------------------------
   // set partner_nshake for bonded partners
-  // requires communication for off-proc partners
+  // requires rendezvous communication for off-proc partners
   // -----------------------------------------------------
 
-  // fill in partner_nshake if own bond partner
-  // info to store in buf for each off-proc bond =
-  //   2 atoms IDs in bond, space for nshake value
-  // nbufmax = largest buffer needed to hold info from any proc
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) {
-    for (j = 0; j < npartner[i]; j++) {
-      m = atom->map(partner_tag[i][j]);
-      if (m >= 0 && m < nlocal) partner_nshake[i][j] = nshake[m];
-      else nbuf += 3;
-    }
-  }
-
-  memory->create(buf,nbuf,"shake:buf");
-
-  // fill buffer with info
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    for (j = 0; j < npartner[i]; j++) {
-      m = atom->map(partner_tag[i][j]);
-      if (m < 0 || m >= nlocal) {
-        buf[size] = tag[i];
-        buf[size+1] = partner_tag[i][j];
-        size += 3;
-      }
-    }
-  }
-
-  // cycle buffer around ring of procs back to self
-
-  comm->ring(size,sizeof(tagint),buf,2,ring_nshake,buf,(void *)this);
-
-  // store partner info returned to me
-
-  m = 0;
-  while (m < size) {
-    i = atom->map(buf[m]);
-    for (j = 0; j < npartner[i]; j++)
-      if (buf[m+1] == partner_tag[i][j]) break;
-    partner_nshake[i][j] = buf[m+2];
-    m += 3;
-  }
-
-  memory->destroy(buf);
+  nshake_info(npartner,partner_tag,partner_nshake);
 
   // -----------------------------------------------------
   // error checks
@@ -988,7 +880,7 @@ void FixShake::find_clusters()
   // -----------------------------------------------------
 
   flag = 0;
-  for (i = 0; i < nlocal; i++) if (nshake[i] > 3) flag = 1;
+  for (i = 0; i < nlocal; i++) if (nshake[i] > 3) flag++;
   MPI_Allreduce(&flag,&flag_all,1,MPI_INT,MPI_SUM,world);
   if (flag_all) error->all(FLERR,"Shake cluster of more than 4 atoms");
 
@@ -996,7 +888,7 @@ void FixShake::find_clusters()
   for (i = 0; i < nlocal; i++) {
     if (nshake[i] <= 1) continue;
     for (j = 0; j < npartner[i]; j++)
-      if (partner_shake[i][j] && partner_nshake[i][j] > 1) flag = 1;
+      if (partner_shake[i][j] && partner_nshake[i][j] > 1) flag++;
   }
   MPI_Allreduce(&flag,&flag_all,1,MPI_INT,MPI_SUM,world);
   if (flag_all) error->all(FLERR,"Shake clusters are connected");
@@ -1064,68 +956,18 @@ void FixShake::find_clusters()
 
   // -----------------------------------------------------
   // set shake_flag,shake_atom,shake_type for non-central atoms
-  // requires communication for off-proc atoms
+  // requires rendezvous communication for off-proc atoms
   // -----------------------------------------------------
 
-  // fill in shake arrays for each bond partner I own
-  // info to store in buf for each off-proc bond =
-  //   all values from shake_flag, shake_atom, shake_type
-  // nbufmax = largest buffer needed to hold info from any proc
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (shake_flag[i] == 0) continue;
-    for (j = 0; j < npartner[i]; j++) {
-      if (partner_shake[i][j] == 0) continue;
-      m = atom->map(partner_tag[i][j]);
-      if (m >= 0 && m < nlocal) {
-        shake_flag[m] = shake_flag[i];
-        shake_atom[m][0] = shake_atom[i][0];
-        shake_atom[m][1] = shake_atom[i][1];
-        shake_atom[m][2] = shake_atom[i][2];
-        shake_atom[m][3] = shake_atom[i][3];
-        shake_type[m][0] = shake_type[i][0];
-        shake_type[m][1] = shake_type[i][1];
-        shake_type[m][2] = shake_type[i][2];
-      } else nbuf += 9;
-    }
-  }
-
-  memory->create(buf,nbuf,"shake:buf");
-
-  // fill buffer with info
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (shake_flag[i] == 0) continue;
-    for (j = 0; j < npartner[i]; j++) {
-      if (partner_shake[i][j] == 0) continue;
-      m = atom->map(partner_tag[i][j]);
-      if (m < 0 || m >= nlocal) {
-        buf[size] = partner_tag[i][j];
-        buf[size+1] = shake_flag[i];
-        buf[size+2] = shake_atom[i][0];
-        buf[size+3] = shake_atom[i][1];
-        buf[size+4] = shake_atom[i][2];
-        buf[size+5] = shake_atom[i][3];
-        buf[size+6] = shake_type[i][0];
-        buf[size+7] = shake_type[i][1];
-        buf[size+8] = shake_type[i][2];
-        size += 9;
-      }
-    }
-  }
-
-  // cycle buffer around ring of procs back to self
-
-  comm->ring(size,sizeof(tagint),buf,3,ring_shake,NULL,(void *)this);
-
-  memory->destroy(buf);
+  shake_info(npartner,partner_tag,partner_shake);
 
   // -----------------------------------------------------
   // free local memory
   // -----------------------------------------------------
 
+  memory->destroy(atomIDs);
+  memory->destroy(procowner);
+
   memory->destroy(npartner);
   memory->destroy(nshake);
   memory->destroy(partner_tag);
@@ -1199,98 +1041,548 @@ void FixShake::find_clusters()
 }
 
 /* ----------------------------------------------------------------------
-   when receive buffer, scan bond partner IDs for atoms I own
-   if I own partner:
-     fill in mask and type and massflag
-     search for bond with 1st atom and fill in bondtype
+   setup atomIDs and procowner
 ------------------------------------------------------------------------- */
 
-void FixShake::ring_bonds(int ndatum, char *cbuf, void *ptr)
+void FixShake::atom_owners()
 {
-  FixShake *fsptr = (FixShake *)ptr;
-  Atom *atom = fsptr->atom;
+  tagint *tag = atom->tag;
+  int nlocal = atom->nlocal;
+
+  int *proclist;
+  memory->create(proclist,nlocal,"shake:proclist");
+  IDRvous *idbuf = (IDRvous *)
+    memory->smalloc((bigint) nlocal*sizeof(IDRvous),"shake:idbuf");
+
+  // setup input buf to rendezvous comm
+  // input datums = pairs of bonded atoms
+  // owning proc for each datum = random hash of atomID
+  // one datum for each owned atom: datum = owning proc, atomID
+
+  for (int i = 0; i < nlocal; i++) {
+    proclist[i] = tag[i] % nprocs;
+    idbuf[i].me = me;
+    idbuf[i].atomID = tag[i];
+  }
+
+  // perform rendezvous operation
+  // each proc assigned every 1/Pth atom
+
+  char *buf;
+  comm->rendezvous(RVOUS,nlocal,(char *) idbuf,sizeof(IDRvous),
+                   0,proclist,
+                   rendezvous_ids,0,buf,0,(void *) this);
+
+  memory->destroy(proclist);
+  memory->sfree(idbuf);
+}
+
+/* ----------------------------------------------------------------------
+   setup partner_mask, partner_type, partner_massflag, partner_bondtype
+------------------------------------------------------------------------- */
+
+void FixShake::partner_info(int *npartner, tagint **partner_tag,
+                            int **partner_mask, int **partner_type,
+                            int **partner_massflag, int **partner_bondtype)
+{
+  int i,j,m,n;
+  int nlocal = atom->nlocal;
+
+  // nsend = # of my datums to send
+  // one datum for every off-processor partner
+
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < npartner[i]; j++) {
+      m = atom->map(partner_tag[i][j]);
+      if (m < 0 || m >= nlocal) nsend++;
+    }
+  }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  PartnerInfo *inbuf = (PartnerInfo *)
+    memory->smalloc((bigint) nsend*sizeof(PartnerInfo),"special:inbuf");
+
+  // set values in 4 partner arrays for all partner atoms I own
+  // also setup input buf to rendezvous comm
+  // input datums = pair of bonded atoms where I do not own partner
+  // owning proc for each datum = partner_tag % nprocs
+  // datum: atomID = partner_tag (off-proc), partnerID = tag (on-proc)
+  //        4 values for my owned atom
+
   double *rmass = atom->rmass;
   double *mass = atom->mass;
-  int *mask = atom->mask;
   int *type = atom->type;
-  int nlocal = atom->nlocal;
-  int nmass = fsptr->nmass;
+  int *mask = atom->mask;
+  tagint *tag = atom->tag;
 
-  tagint *buf = (tagint *) cbuf;
-  int m,n;
   double massone;
 
-  for (int i = 0; i < ndatum; i += 6) {
-    m = atom->map(buf[i+1]);
-    if (m >= 0 && m < nlocal) {
-      buf[i+2] = mask[m];
-      buf[i+3] = type[m];
-      if (nmass) {
-        if (rmass) massone = rmass[m];
-        else massone = mass[type[m]];
-        buf[i+4] = fsptr->masscheck(massone);
-      }
-      if (buf[i+5] == 0) {
-        n = fsptr->bondtype_findset(m,buf[i],buf[i+1],0);
-        if (n) buf[i+5] = n;
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < npartner[i]; j++) {
+      partner_mask[i][j] = 0;
+      partner_type[i][j] = 0;
+      partner_massflag[i][j] = 0;
+      partner_bondtype[i][j] = 0;
+
+      m = atom->map(partner_tag[i][j]);
+
+      if (m >= 0 && m < nlocal) {
+        partner_mask[i][j] = mask[m];
+        partner_type[i][j] = type[m];
+        if (nmass) {
+          if (rmass) massone = rmass[m];
+          else massone = mass[type[m]];
+          partner_massflag[i][j] = masscheck(massone);
+        }
+        n = bondtype_findset(i,tag[i],partner_tag[i][j],0);
+        if (n) partner_bondtype[i][j] = n;
+        else {
+          n = bondtype_findset(m,tag[i],partner_tag[i][j],0);
+          if (n) partner_bondtype[i][j] = n;
+        }
+
+      } else {
+        proclist[nsend] = partner_tag[i][j] % nprocs;
+        inbuf[nsend].atomID = partner_tag[i][j];
+        inbuf[nsend].partnerID = tag[i];
+        inbuf[nsend].mask = mask[i];
+        inbuf[nsend].type = type[i];
+        if (nmass) {
+          if (rmass) massone = rmass[i];
+          else massone = mass[type[i]];
+          inbuf[nsend].massflag = masscheck(massone);
+        } else inbuf[nsend].massflag = 0;
+
+        // my atom may own bond, in which case set partner_bondtype
+        // else receiver of this datum will own the bond and return the value
+
+        n = bondtype_findset(i,tag[i],partner_tag[i][j],0);
+        if (n) {
+          partner_bondtype[i][j] = n;
+          inbuf[nsend].bondtype = n;
+        } else inbuf[nsend].bondtype = 0;
+
+        nsend++;
       }
     }
   }
-}
 
-/* ----------------------------------------------------------------------
-   when receive buffer, scan bond partner IDs for atoms I own
-   if I own partner, fill in nshake value
-------------------------------------------------------------------------- */
+  // perform rendezvous operation
+  // each proc owns random subset of atoms
+  // receives all data needed to populate un-owned partner 4 values
 
-void FixShake::ring_nshake(int ndatum, char *cbuf, void *ptr)
-{
-  FixShake *fsptr = (FixShake *)ptr;
-  Atom *atom = fsptr->atom;
-  int nlocal = atom->nlocal;
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PartnerInfo),
+                                 0,proclist,
+                                 rendezvous_partners_info,
+                                 0,buf,sizeof(PartnerInfo),
+                                 (void *) this);
+  PartnerInfo *outbuf = (PartnerInfo *) buf;
 
-  int *nshake = fsptr->nshake;
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
 
-  tagint *buf = (tagint *) cbuf;
-  int m;
+  // set partner 4 values for un-onwed partners based on output info
+  // outbuf.atomID = my owned atom, outbuf.partnerID = partner the info is for
 
-  for (int i = 0; i < ndatum; i += 3) {
-    m = atom->map(buf[i+1]);
-    if (m >= 0 && m < nlocal) buf[i+2] = nshake[m];
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    for (j = 0; j < npartner[i]; j++)
+      if (partner_tag[i][j] == outbuf[m].partnerID) break;
+    partner_mask[i][j] = outbuf[m].mask;
+    partner_type[i][j] = outbuf[m].type;
+    partner_massflag[i][j] = outbuf[m].massflag;
+
+    // only set partner_bondtype if my atom did not set it
+    //   when setting up rendezvous
+    // if this proc set it, then sender of this datum set outbuf.bondtype = 0
+
+    if (partner_bondtype[i][j] == 0)
+      partner_bondtype[i][j] = outbuf[m].bondtype;
   }
+
+  memory->sfree(outbuf);
 }
 
 /* ----------------------------------------------------------------------
-   when receive buffer, scan bond partner IDs for atoms I own
-   if I own partner, fill in nshake value
+   setup partner_nshake
 ------------------------------------------------------------------------- */
 
-void FixShake::ring_shake(int ndatum, char *cbuf, void *ptr)
+void FixShake::nshake_info(int *npartner, tagint **partner_tag,
+                           int **partner_nshake)
 {
-  FixShake *fsptr = (FixShake *)ptr;
-  Atom *atom = fsptr->atom;
+  int i,j,m;
   int nlocal = atom->nlocal;
 
-  int *shake_flag = fsptr->shake_flag;
-  tagint **shake_atom = fsptr->shake_atom;
-  int **shake_type = fsptr->shake_type;
+  // nsend = # of my datums to send
+  // one datum for every off-processor partner
 
-  tagint *buf = (tagint *) cbuf;
-  int m;
-
-  for (int i = 0; i < ndatum; i += 9) {
-    m = atom->map(buf[i]);
-    if (m >= 0 && m < nlocal) {
-      shake_flag[m] = buf[i+1];
-      shake_atom[m][0] = buf[i+2];
-      shake_atom[m][1] = buf[i+3];
-      shake_atom[m][2] = buf[i+4];
-      shake_atom[m][3] = buf[i+5];
-      shake_type[m][0] = buf[i+6];
-      shake_type[m][1] = buf[i+7];
-      shake_type[m][2] = buf[i+8];
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < npartner[i]; j++) {
+      m = atom->map(partner_tag[i][j]);
+      if (m < 0 || m >= nlocal) nsend++;
     }
   }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  NShakeInfo *inbuf = (NShakeInfo *)
+    memory->smalloc((bigint) nsend*sizeof(NShakeInfo),"special:inbuf");
+
+  // set partner_nshake for all partner atoms I own
+  // also setup input buf to rendezvous comm
+  // input datums = pair of bonded atoms where I do not own partner
+  // owning proc for each datum = partner_tag % nprocs
+  // datum: atomID = partner_tag (off-proc), partnerID = tag (on-proc)
+  //        nshake value for my owned atom
+
+  tagint *tag = atom->tag;
+
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < npartner[i]; j++) {
+      partner_nshake[i][j] = 0;
+      m = atom->map(partner_tag[i][j]);
+      if (m >= 0 && m < nlocal) {
+        partner_nshake[i][j] = nshake[m];
+      } else {
+        proclist[nsend] = partner_tag[i][j] % nprocs;
+        inbuf[nsend].atomID = partner_tag[i][j];
+        inbuf[nsend].partnerID = tag[i];
+        inbuf[nsend].nshake = nshake[i];
+        nsend++;
+      }
+    }
+  }
+
+  // perform rendezvous operation
+  // each proc owns random subset of atoms
+  // receives all data needed to populate un-owned partner nshake
+
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(NShakeInfo),
+                                 0,proclist,
+                                 rendezvous_nshake,0,buf,sizeof(NShakeInfo),
+                                 (void *) this);
+  NShakeInfo *outbuf = (NShakeInfo *) buf;
+
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
+
+  // set partner nshake for un-onwed partners based on output info
+  // outbuf.atomID = my owned atom, outbuf.partnerID = partner the info is for
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    for (j = 0; j < npartner[i]; j++)
+      if (partner_tag[i][j] == outbuf[m].partnerID) break;
+    partner_nshake[i][j] = outbuf[m].nshake;
+  }
+
+  memory->sfree(outbuf);
+}
+
+/* ----------------------------------------------------------------------
+   setup shake_flag, shake_atom, shake_type
+------------------------------------------------------------------------- */
+
+void FixShake::shake_info(int *npartner, tagint **partner_tag,
+                          int **partner_shake)
+{
+  int i,j,m;
+  int nlocal = atom->nlocal;
+
+  // nsend = # of my datums to send
+  // one datum for every off-processor partner
+
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < npartner[i]; j++) {
+      m = atom->map(partner_tag[i][j]);
+      if (m < 0 || m >= nlocal) nsend++;
+    }
+  }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  ShakeInfo *inbuf = (ShakeInfo *)
+    memory->smalloc((bigint) nsend*sizeof(ShakeInfo),"special:inbuf");
+
+  // set 3 shake arrays for all partner atoms I own
+  // also setup input buf to rendezvous comm
+  // input datums = partner atom where I do not own partner
+  // owning proc for each datum = partner_tag % nprocs
+  // datum: atomID = partner_tag (off-proc)
+  //        values in 3 shake arrays
+
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    if (shake_flag[i] == 0) continue;
+    for (j = 0; j < npartner[i]; j++) {
+      if (partner_shake[i][j] == 0) continue;
+      m = atom->map(partner_tag[i][j]);
+
+      if (m >= 0 && m < nlocal) {
+        shake_flag[m] = shake_flag[i];
+        shake_atom[m][0] = shake_atom[i][0];
+        shake_atom[m][1] = shake_atom[i][1];
+        shake_atom[m][2] = shake_atom[i][2];
+        shake_atom[m][3] = shake_atom[i][3];
+        shake_type[m][0] = shake_type[i][0];
+        shake_type[m][1] = shake_type[i][1];
+        shake_type[m][2] = shake_type[i][2];
+
+      } else {
+        proclist[nsend] = partner_tag[i][j] % nprocs;
+        inbuf[nsend].atomID = partner_tag[i][j];
+        inbuf[nsend].shake_flag = shake_flag[i];
+        inbuf[nsend].shake_atom[0] = shake_atom[i][0];
+        inbuf[nsend].shake_atom[1] = shake_atom[i][1];
+        inbuf[nsend].shake_atom[2] = shake_atom[i][2];
+        inbuf[nsend].shake_atom[3] = shake_atom[i][3];
+        inbuf[nsend].shake_type[0] = shake_type[i][0];
+        inbuf[nsend].shake_type[1] = shake_type[i][1];
+        inbuf[nsend].shake_type[2] = shake_type[i][2];
+        nsend++;
+      }
+    }
+  }
+
+  // perform rendezvous operation
+  // each proc owns random subset of atoms
+  // receives all data needed to populate un-owned shake info
+
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(ShakeInfo),
+                                 0,proclist,
+                                 rendezvous_shake,0,buf,sizeof(ShakeInfo),
+                                 (void *) this);
+  ShakeInfo *outbuf = (ShakeInfo *) buf;
+
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
+
+  // set shake info for un-onwed partners based on output info
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    shake_flag[i] = outbuf[m].shake_flag;
+    shake_atom[i][0] = outbuf[m].shake_atom[0];
+    shake_atom[i][1] = outbuf[m].shake_atom[1];
+    shake_atom[i][2] = outbuf[m].shake_atom[2];
+    shake_atom[i][3] = outbuf[m].shake_atom[3];
+    shake_type[i][0] = outbuf[m].shake_type[0];
+    shake_type[i][1] = outbuf[m].shake_type[1];
+    shake_type[i][2] = outbuf[m].shake_type[2];
+  }
+
+  memory->sfree(outbuf);
+}
+
+/* ----------------------------------------------------------------------
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N IDRvous datums
+   no outbuf
+------------------------------------------------------------------------- */
+
+int FixShake::rendezvous_ids(int n, char *inbuf,
+                             int &flag, int *& /*proclist*/, char *& /*outbuf*/,
+                             void *ptr)
+{
+  FixShake *fsptr = (FixShake *) ptr;
+  Memory *memory = fsptr->memory;
+
+  tagint *atomIDs;
+  int *procowner;
+
+  memory->create(atomIDs,n,"special:atomIDs");
+  memory->create(procowner,n,"special:procowner");
+
+  IDRvous *in = (IDRvous *) inbuf;
+
+  for (int i = 0; i < n; i++) {
+    atomIDs[i] = in[i].atomID;
+    procowner[i] = in[i].me;
+  }
+
+  // store rendezvous data in FixShake class
+
+  fsptr->nrvous = n;
+  fsptr->atomIDs = atomIDs;
+  fsptr->procowner = procowner;
+
+  // flag = 0: no second comm needed in rendezvous
+
+  flag = 0;
+  return 0;
+}
+
+/* ----------------------------------------------------------------------
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N PairRvous datums
+   outbuf = same list of N PairRvous datums, routed to different procs
+------------------------------------------------------------------------- */
+
+int FixShake::rendezvous_partners_info(int n, char *inbuf,
+                                       int &flag, int *&proclist, char *&outbuf,
+                                       void *ptr)
+{
+  int i,m;
+
+  FixShake *fsptr = (FixShake *) ptr;
+  Atom *atom = fsptr->atom;
+  Memory *memory = fsptr->memory;
+
+  // clear atom map so it can be here as a hash table
+  // faster than an STL map for large atom counts
+
+  atom->map_clear();
+
+  // hash atom IDs stored in rendezvous decomposition
+
+  int nrvous = fsptr->nrvous;
+  tagint *atomIDs = fsptr->atomIDs;
+
+  for (i = 0; i < nrvous; i++)
+    atom->map_one(atomIDs[i],i);
+
+  // proclist = owner of atomID in caller decomposition
+  // outbuf = info about owned atomID = 4 values
+
+  PartnerInfo *in = (PartnerInfo *) inbuf;
+  int *procowner = fsptr->procowner;
+  memory->create(proclist,n,"shake:proclist");
+
+  for (i = 0; i < n; i++) {
+    m = atom->map(in[i].atomID);
+    proclist[i] = procowner[m];
+  }
+
+  outbuf = inbuf;
+
+  // re-create atom map
+
+  atom->map_init(0);
+  atom->nghost = 0;
+  atom->map_set();
+
+  // flag = 1: outbuf = inbuf
+
+  flag = 1;
+  return n;
+}
+
+/* ----------------------------------------------------------------------
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N NShakeInfo datums
+   outbuf = same list of N NShakeInfo datums, routed to different procs
+------------------------------------------------------------------------- */
+
+int FixShake::rendezvous_nshake(int n, char *inbuf,
+                                int &flag, int *&proclist, char *&outbuf,
+                                void *ptr)
+{
+  int i,m;
+
+  FixShake *fsptr = (FixShake *) ptr;
+  Atom *atom = fsptr->atom;
+  Memory *memory = fsptr->memory;
+
+  // clear atom map so it can be here as a hash table
+  // faster than an STL map for large atom counts
+
+  atom->map_clear();
+
+  // hash atom IDs stored in rendezvous decomposition
+
+  int nrvous = fsptr->nrvous;
+  tagint *atomIDs = fsptr->atomIDs;
+
+  for (i = 0; i < nrvous; i++)
+    atom->map_one(atomIDs[i],i);
+
+  // proclist = owner of atomID in caller decomposition
+  // outbuf = info about owned atomID
+
+  NShakeInfo *in = (NShakeInfo *) inbuf;
+  int *procowner = fsptr->procowner;
+  memory->create(proclist,n,"shake:proclist");
+
+  for (i = 0; i < n; i++) {
+    m = atom->map(in[i].atomID);
+    proclist[i] = procowner[m];
+  }
+
+  outbuf = inbuf;
+
+  // re-create atom map
+
+  atom->map_init(0);
+  atom->nghost = 0;
+  atom->map_set();
+
+  // flag = 1: outbuf = inbuf
+
+  flag = 1;
+  return n;
+}
+/* ----------------------------------------------------------------------
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N PairRvous datums
+   outbuf = same list of N PairRvous datums, routed to different procs
+------------------------------------------------------------------------- */
+
+int FixShake::rendezvous_shake(int n, char *inbuf,
+                               int &flag, int *&proclist, char *&outbuf,
+                               void *ptr)
+{
+  int i,m;
+
+  FixShake *fsptr = (FixShake *) ptr;
+  Atom *atom = fsptr->atom;
+  Memory *memory = fsptr->memory;
+
+  // clear atom map so it can be here as a hash table
+  // faster than an STL map for large atom counts
+
+  atom->map_clear();
+
+  // hash atom IDs stored in rendezvous decomposition
+
+  int nrvous = fsptr->nrvous;
+  tagint *atomIDs = fsptr->atomIDs;
+
+  for (i = 0; i < nrvous; i++)
+    atom->map_one(atomIDs[i],i);
+
+  // proclist = owner of atomID in caller decomposition
+  // outbuf = info about owned atomID
+
+  ShakeInfo *in = (ShakeInfo *) inbuf;
+  int *procowner = fsptr->procowner;
+  memory->create(proclist,n,"shake:proclist");
+
+  for (i = 0; i < n; i++) {
+    m = atom->map(in[i].atomID);
+    proclist[i] = procowner[m];
+  }
+
+  outbuf = inbuf;
+
+  // re-create atom map
+
+  atom->map_init(0);
+  atom->nghost = 0;
+  atom->map_set();
+
+  // flag = 1: outbuf = inbuf;
+
+  flag = 1;
+  return n;
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/RIGID/fix_shake.h b/src/RIGID/fix_shake.h
index d4e7b85ec4..ee9f520fea 100644
--- a/src/RIGID/fix_shake.h
+++ b/src/RIGID/fix_shake.h
@@ -120,6 +120,11 @@ class FixShake : public Fix {
   int nmol;
 
   void find_clusters();
+  void atom_owners();
+  void partner_info(int *, tagint **, int **, int **, int **, int **);
+  void nshake_info(int *, tagint **, int **);
+  void shake_info(int *, tagint **, int **);
+
   int masscheck(double);
   void unconstrained_update();
   void unconstrained_update_respa(int);
@@ -131,12 +136,40 @@ class FixShake : public Fix {
   int bondtype_findset(int, tagint, tagint, int);
   int angletype_findset(int, tagint, tagint, int);
 
-  // static variable for ring communication callback to access class data
-  // callback functions for ring communication
+  // data used by rendezvous callback methods
 
-  static void ring_bonds(int, char *, void *);
-  static void ring_nshake(int, char *, void *);
-  static void ring_shake(int, char *, void *);
+  int nrvous;
+  tagint *atomIDs;
+  int *procowner;
+
+  struct IDRvous {
+    int me;
+    tagint atomID;
+  };
+
+  struct PartnerInfo {
+    tagint atomID,partnerID;
+    int mask,type,massflag,bondtype;
+  };
+
+  struct NShakeInfo {
+    tagint atomID,partnerID;
+    int nshake;
+  };
+
+  struct ShakeInfo {
+    tagint atomID;
+    tagint shake_atom[4];
+    int shake_flag;
+    int shake_type[3];
+  };
+
+  // callback functions for rendezvous communication
+
+  static int rendezvous_ids(int, char *, int &, int *&, char *&, void *);
+  static int rendezvous_partners_info(int, char *, int &, int *&, char *&, void *);
+  static int rendezvous_nshake(int, char *, int &, int *&, char *&, void *);
+  static int rendezvous_shake(int, char *, int &, int *&, char *&, void *);
 };
 
 }
diff --git a/src/SNAP/pair_snap.cpp b/src/SNAP/pair_snap.cpp
index 81c5e9f6d1..8b547e6e73 100644
--- a/src/SNAP/pair_snap.cpp
+++ b/src/SNAP/pair_snap.cpp
@@ -176,8 +176,7 @@ void PairSNAP::compute_regular(int eflag, int vflag)
   int *jlist,*numneigh,**firstneigh;
   evdwl = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -486,8 +485,7 @@ void PairSNAP::compute_optimized(int eflag, int vflag)
 #pragma omp master
 #endif
     {
-      if (eflag || vflag) ev_setup(eflag,vflag);
-      else evflag = vflag_fdotr = 0;
+      ev_init(eflag,vflag);
     }
 
 #if defined(_OPENMP)
diff --git a/src/SPIN/README b/src/SPIN/README
index e371e39767..53e456bacb 100644
--- a/src/SPIN/README
+++ b/src/SPIN/README
@@ -9,6 +9,7 @@ atom in the system
 * implementing magnetic pair interactions and magnetic forces
 * thermostating and applying a transverse damping to the magnetic spins
 * computing and outputing magnetic quantities
+* minimizing the energy or total torque of a magnetic system
 
 The different options provided by this package are explained in the 
 LAMMPS documentation.
diff --git a/src/SPIN/compute_spin.cpp b/src/SPIN/compute_spin.cpp
index dc16190c98..0a881e1de6 100644
--- a/src/SPIN/compute_spin.cpp
+++ b/src/SPIN/compute_spin.cpp
@@ -84,7 +84,7 @@ void ComputeSpin::compute_vector()
 
   invoked_vector = update->ntimestep;
 
-  countsp = countsptot = 0.0;	
+  countsp = countsptot = 0.0;
   mag[0] = mag[1] = mag[2] = mag[3] = 0.0;
   magtot[0] = magtot[1] = magtot[2] = magtot[3] = 0.0;
   magenergy = magenergytot = 0.0;
@@ -96,7 +96,7 @@ void ComputeSpin::compute_vector()
   double **sp = atom->sp;
   double **fm = atom->fm;
   double tx,ty,tz;
-	
+
   int nlocal = atom->nlocal;
 
   // compute total magnetization and magnetic energy
@@ -105,16 +105,16 @@ void ComputeSpin::compute_vector()
   for (i = 0; i < nlocal; i++) {
     if (mask[i] & groupbit) {
       if (atom->sp_flag) {
-	mag[0] += sp[i][0];
-	mag[1] += sp[i][1];
-	mag[2] += sp[i][2];
-	magenergy -= (sp[i][0]*fm[i][0] + sp[i][1]*fm[i][1] + sp[i][2]*fm[i][2]);
+        mag[0] += sp[i][0];
+        mag[1] += sp[i][1];
+        mag[2] += sp[i][2];
+        magenergy -= (sp[i][0]*fm[i][0] + sp[i][1]*fm[i][1] + sp[i][2]*fm[i][2]);
         tx = sp[i][1]*fm[i][2]-sp[i][2]*fm[i][1];
         ty = sp[i][2]*fm[i][0]-sp[i][0]*fm[i][2];
         tz = sp[i][0]*fm[i][1]-sp[i][1]*fm[i][0];
         tempnum += tx*tx+ty*ty+tz*tz;
-        tempdenom += sp[i][0]*fm[i][0]+fm[i][1]*sp[i][1]+sp[i][2]*fm[i][2];  	
-	countsp++;
+        tempdenom += sp[i][0]*fm[i][0]+fm[i][1]*sp[i][1]+sp[i][2]*fm[i][2];
+        countsp++;
       }
     }
     else error->all(FLERR,"Compute compute/spin requires atom/spin style");
diff --git a/src/SPIN/fix_langevin_spin.cpp b/src/SPIN/fix_langevin_spin.cpp
index 55b4d8dfec..ec6f719a77 100644
--- a/src/SPIN/fix_langevin_spin.cpp
+++ b/src/SPIN/fix_langevin_spin.cpp
@@ -131,8 +131,8 @@ void FixLangevinSpin::init()
   gil_factor = 1.0/(1.0+(alpha_t)*(alpha_t));
   dts = update->dt;
 
-  double hbar = force->hplanck/MY_2PI;	// eV/(rad.THz)
-  double kb = force->boltz;		// eV/K
+  double hbar = force->hplanck/MY_2PI;  // eV/(rad.THz)
+  double kb = force->boltz;             // eV/K
   D = (MY_2PI*alpha_t*gil_factor*kb*temp);
   D /= (hbar*dts);
   sigma = sqrt(2.0*D);
@@ -158,7 +158,7 @@ void FixLangevinSpin::add_tdamping(double spi[3], double fmi[3])
   double cpx = fmi[1]*spi[2] - fmi[2]*spi[1];
   double cpy = fmi[2]*spi[0] - fmi[0]*spi[2];
   double cpz = fmi[0]*spi[1] - fmi[1]*spi[0];
-	
+
   // adding the transverse damping
 
   fmi[0] -= alpha_t*cpx;
diff --git a/src/SPIN/fix_nve_spin.cpp b/src/SPIN/fix_nve_spin.cpp
index 7d96aca6d4..8d549ed64a 100644
--- a/src/SPIN/fix_nve_spin.cpp
+++ b/src/SPIN/fix_nve_spin.cpp
@@ -183,7 +183,7 @@ void FixNVESpin::init()
     npairs = pair->instance_total;
     for (int i = 0; i<npairs; i++) {
       if (force->pair_match("spin",0,i)) {
-	npairspin ++;
+        npairspin ++;
       }
     }
   }
@@ -203,8 +203,8 @@ void FixNVESpin::init()
   } else if (npairspin > 1) {
     for (int i = 0; i<npairs; i++) {
       if (force->pair_match("spin",0,i)) {
-	spin_pairs[count] = (PairSpin *) force->pair_match("spin",0,i);
-	count++;
+        spin_pairs[count] = (PairSpin *) force->pair_match("spin",0,i);
+        count++;
       }
     }
   }
@@ -264,8 +264,8 @@ void FixNVESpin::init()
 void FixNVESpin::initial_integrate(int /*vflag*/)
 {
   double dtfm;
-	
-  double **x = atom->x;	
+
+  double **x = atom->x;
   double **v = atom->v;
   double **f = atom->f;
   double *rmass = atom->rmass;
@@ -291,32 +291,32 @@ void FixNVESpin::initial_integrate(int /*vflag*/)
 
   // update half s for all atoms
 
-  if (sector_flag) {				// sectoring seq. update
-    for (int j = 0; j < nsectors; j++) {	// advance quarter s for nlocal
+  if (sector_flag) {                            // sectoring seq. update
+    for (int j = 0; j < nsectors; j++) {        // advance quarter s for nlocal
       comm->forward_comm();
       int i = stack_foot[j];
       while (i >= 0) {
         ComputeInteractionsSpin(i);
-    	AdvanceSingleSpin(i);
-	i = forward_stacks[i];
+        AdvanceSingleSpin(i);
+        i = forward_stacks[i];
       }
     }
-    for (int j = nsectors-1; j >= 0; j--) {	// advance quarter s for nlocal
+    for (int j = nsectors-1; j >= 0; j--) {     // advance quarter s for nlocal
       comm->forward_comm();
       int i = stack_head[j];
       while (i >= 0) {
         ComputeInteractionsSpin(i);
-    	AdvanceSingleSpin(i);
-	i = backward_stacks[i];
+        AdvanceSingleSpin(i);
+        i = backward_stacks[i];
       }
     }
-  } else if (sector_flag == 0) {		// serial seq. update
-    comm->forward_comm();			// comm. positions of ghost atoms
-    for (int i = 0; i < nlocal; i++){		// advance quarter s for nlocal
+  } else if (sector_flag == 0) {                // serial seq. update
+    comm->forward_comm();                       // comm. positions of ghost atoms
+    for (int i = 0; i < nlocal; i++){           // advance quarter s for nlocal
       ComputeInteractionsSpin(i);
       AdvanceSingleSpin(i);
     }
-    for (int i = nlocal-1; i >= 0; i--){	// advance quarter s for nlocal
+    for (int i = nlocal-1; i >= 0; i--){        // advance quarter s for nlocal
       ComputeInteractionsSpin(i);
       AdvanceSingleSpin(i);
     }
@@ -336,32 +336,32 @@ void FixNVESpin::initial_integrate(int /*vflag*/)
 
   // update half s for all particles
 
-  if (sector_flag) {				// sectoring seq. update
-    for (int j = 0; j < nsectors; j++) {	// advance quarter s for nlocal
+  if (sector_flag) {                            // sectoring seq. update
+    for (int j = 0; j < nsectors; j++) {        // advance quarter s for nlocal
       comm->forward_comm();
       int i = stack_foot[j];
       while (i >= 0) {
         ComputeInteractionsSpin(i);
-    	AdvanceSingleSpin(i);
-	i = forward_stacks[i];
+        AdvanceSingleSpin(i);
+        i = forward_stacks[i];
       }
     }
-    for (int j = nsectors-1; j >= 0; j--) {	// advance quarter s for nlocal
+    for (int j = nsectors-1; j >= 0; j--) {     // advance quarter s for nlocal
       comm->forward_comm();
       int i = stack_head[j];
       while (i >= 0) {
         ComputeInteractionsSpin(i);
-    	AdvanceSingleSpin(i);
-	i = backward_stacks[i];
+        AdvanceSingleSpin(i);
+        i = backward_stacks[i];
       }
     }
-  } else if (sector_flag == 0) {		// serial seq. update
-    comm->forward_comm();			// comm. positions of ghost atoms
-    for (int i = 0; i < nlocal; i++){		// advance quarter s for nlocal-1
+  } else if (sector_flag == 0) {                // serial seq. update
+    comm->forward_comm();                       // comm. positions of ghost atoms
+    for (int i = 0; i < nlocal; i++){           // advance quarter s for nlocal-1
       ComputeInteractionsSpin(i);
       AdvanceSingleSpin(i);
     }
-    for (int i = nlocal-1; i >= 0; i--){	// advance quarter s for nlocal-1
+    for (int i = nlocal-1; i >= 0; i--){        // advance quarter s for nlocal-1
       ComputeInteractionsSpin(i);
       AdvanceSingleSpin(i);
     }
@@ -384,10 +384,10 @@ void FixNVESpin::setup_pre_neighbor()
 
 void FixNVESpin::pre_neighbor()
 {
-  double **x = atom->x;	
+  double **x = atom->x;
   int nlocal = atom->nlocal;
 
-  if (nlocal_max < nlocal) {			// grow linked lists if necessary
+  if (nlocal_max < nlocal) {                    // grow linked lists if necessary
     nlocal_max = nlocal;
     backward_stacks = memory->grow(backward_stacks,nlocal_max,"NVE/spin:backward_stacks");
     forward_stacks = memory->grow(forward_stacks,nlocal_max,"NVE/spin:forward_stacks");
@@ -399,7 +399,7 @@ void FixNVESpin::pre_neighbor()
   }
 
   int nseci;
-  for (int j = 0; j < nsectors; j++) {		// stacking backward order
+  for (int j = 0; j < nsectors; j++) {          // stacking backward order
     for (int i = 0; i < nlocal; i++) {
       nseci = coords2sector(x[i]);
       if (j != nseci) continue;
@@ -407,7 +407,7 @@ void FixNVESpin::pre_neighbor()
       stack_head[j] = i;
     }
   }
-  for (int j = nsectors-1; j >= 0; j--) {	// stacking forward order
+  for (int j = nsectors-1; j >= 0; j--) {       // stacking forward order
     for (int i = nlocal-1; i >= 0; i--) {
       nseci = coords2sector(x[i]);
       if (j != nseci) continue;
@@ -453,11 +453,11 @@ void FixNVESpin::ComputeInteractionsSpin(int i)
 
   // update langevin damping and random force
 
-  if (maglangevin_flag) {		// mag. langevin
-    if (tdamp_flag) {			// transverse damping
+  if (maglangevin_flag) {               // mag. langevin
+    if (tdamp_flag) {                   // transverse damping
       locklangevinspin->add_tdamping(spi,fmi);
     }
-    if (temp_flag) { 			// spin temperature
+    if (temp_flag) {                    // spin temperature
       locklangevinspin->add_temperature(fmi);
     }
   }
@@ -567,7 +567,7 @@ void FixNVESpin::AdvanceSingleSpin(int i)
   g[0] = g[1] = g[2] = 0.0;
   fm2 = (fm[i][0]*fm[i][0])+(fm[i][1]*fm[i][1])+(fm[i][2]*fm[i][2]);
   energy = (sp[i][0]*fm[i][0])+(sp[i][1]*fm[i][1])+(sp[i][2]*fm[i][2]);
-  dts2 = dts*dts;		
+  dts2 = dts*dts;
 
   cp[0] = fm[i][1]*sp[i][2]-fm[i][2]*sp[i][1];
   cp[1] = fm[i][2]*sp[i][0]-fm[i][0]*sp[i][2];
@@ -576,18 +576,18 @@ void FixNVESpin::AdvanceSingleSpin(int i)
   g[0] = sp[i][0]+cp[0]*dts;
   g[1] = sp[i][1]+cp[1]*dts;
   g[2] = sp[i][2]+cp[2]*dts;
-			
+
   g[0] += (fm[i][0]*energy-0.5*sp[i][0]*fm2)*0.5*dts2;
   g[1] += (fm[i][1]*energy-0.5*sp[i][1]*fm2)*0.5*dts2;
   g[2] += (fm[i][2]*energy-0.5*sp[i][2]*fm2)*0.5*dts2;
-			
+
   g[0] /= (1+0.25*fm2*dts2);
   g[1] /= (1+0.25*fm2*dts2);
   g[2] /= (1+0.25*fm2*dts2);
-			
+
   sp[i][0] = g[0];
   sp[i][1] = g[1];
-  sp[i][2] = g[2];			
+  sp[i][2] = g[2];
 
   // renormalization (check if necessary)
 
@@ -616,9 +616,9 @@ void FixNVESpin::AdvanceSingleSpin(int i)
 /* ---------------------------------------------------------------------- */
 
 void FixNVESpin::final_integrate()
-{	
+{
   double dtfm;
-	
+
   double **v = atom->v;
   double **f = atom->f;
   double *rmass = atom->rmass;
diff --git a/src/SPIN/fix_precession_spin.cpp b/src/SPIN/fix_precession_spin.cpp
index d3edb3ae8a..9ee691c227 100644
--- a/src/SPIN/fix_precession_spin.cpp
+++ b/src/SPIN/fix_precession_spin.cpp
@@ -115,6 +115,7 @@ int FixPrecessionSpin::setmask()
 {
   int mask = 0;
   mask |= POST_FORCE;
+  mask |= MIN_POST_FORCE;
   mask |= THERMO_ENERGY;
   mask |= POST_FORCE_RESPA;
   return mask;
@@ -169,8 +170,16 @@ void FixPrecessionSpin::setup(int vflag)
 
 /* ---------------------------------------------------------------------- */
 
-void FixPrecessionSpin::post_force(int /*vflag*/)
+void FixPrecessionSpin::min_setup(int vflag)
 {
+  post_force(vflag);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixPrecessionSpin::post_force(int /* vflag */)
+{
+
   // update mag field with time (potential improvement)
 
   if (varflag != CONSTANT) {
@@ -200,7 +209,7 @@ void FixPrecessionSpin::post_force(int /*vflag*/)
 
     if (aniso_flag) {           // compute magnetic anisotropy
       compute_anisotropy(spi,fmi);
-      emag -= (spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
+      emag -= 0.5*(spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
     }
 
     fm[i][0] += fmi[0];
@@ -228,9 +237,9 @@ void FixPrecessionSpin::compute_single_precession(int i, double spi[3], double f
 void FixPrecessionSpin::compute_zeeman(int i, double fmi[3])
 {
   double **sp = atom->sp;
-  fmi[0] -= sp[i][3]*hx;
-  fmi[1] -= sp[i][3]*hy;
-  fmi[2] -= sp[i][3]*hz;
+  fmi[0] += sp[i][3]*hx;
+  fmi[1] += sp[i][3]*hy;
+  fmi[2] += sp[i][3]*hz;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -280,3 +289,10 @@ double FixPrecessionSpin::compute_scalar()
   }
   return emag_all;
 }
+
+/* ---------------------------------------------------------------------- */
+
+void FixPrecessionSpin::min_post_force(int vflag)
+{
+  post_force(vflag);
+}
diff --git a/src/SPIN/fix_precession_spin.h b/src/SPIN/fix_precession_spin.h
index 53ae4ba124..1db4d32ae9 100644
--- a/src/SPIN/fix_precession_spin.h
+++ b/src/SPIN/fix_precession_spin.h
@@ -33,8 +33,10 @@ class FixPrecessionSpin : public Fix {
   int setmask();
   void init();
   void setup(int);
-  virtual void post_force(int);
-  virtual void post_force_respa(int, int, int);
+  void min_setup(int);
+  void post_force(int);
+  void post_force_respa(int, int, int);
+  void min_post_force(int);
   double compute_scalar();
 
   int zeeman_flag, aniso_flag;
diff --git a/src/SPIN/min_spin.cpp b/src/SPIN/min_spin.cpp
new file mode 100644
index 0000000000..2bddc110e7
--- /dev/null
+++ b/src/SPIN/min_spin.cpp
@@ -0,0 +1,333 @@
+/* ----------------------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+/* ------------------------------------------------------------------------
+   Contributing authors: Julien Tranchida (SNL)
+
+   Please cite the related publication:
+------------------------------------------------------------------------- */
+
+#include <mpi.h>
+#include <cmath>
+#include <cstdlib>
+#include <cstring>
+#include "min_spin.h"
+#include "universe.h"
+#include "atom.h"
+#include "force.h"
+#include "update.h"
+#include "output.h"
+#include "timer.h"
+#include "error.h"
+#include "modify.h"
+#include "math_special.h"
+#include "math_const.h"
+
+using namespace LAMMPS_NS;
+using namespace MathConst;
+
+// EPS_ENERGY = minimum normalization for energy tolerance
+
+#define EPS_ENERGY 1.0e-8
+
+#define DELAYSTEP 5
+
+/* ---------------------------------------------------------------------- */
+
+MinSpin::MinSpin(LAMMPS *lmp) : Min(lmp) {}
+
+/* ---------------------------------------------------------------------- */
+
+void MinSpin::init()
+{
+  alpha_damp = 1.0;
+  discrete_factor = 10.0;
+
+  Min::init();
+
+  dts = dt = update->dt;
+  last_negative = update->ntimestep;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void MinSpin::setup_style()
+{
+  double **v = atom->v;
+  int nlocal = atom->nlocal;
+
+  // check if the atom/spin style is defined
+
+  if (!atom->sp_flag)
+    error->all(FLERR,"min/spin requires atom/spin style");
+
+  for (int i = 0; i < nlocal; i++)
+    v[i][0] = v[i][1] = v[i][2] = 0.0;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int MinSpin::modify_param(int narg, char **arg)
+{
+  if (strcmp(arg[0],"alpha_damp") == 0) {
+    if (narg < 2) error->all(FLERR,"Illegal fix_modify command");
+    alpha_damp = force->numeric(FLERR,arg[1]);
+    return 2;
+  }
+  if (strcmp(arg[0],"discrete_factor") == 0) {
+    if (narg < 2) error->all(FLERR,"Illegal fix_modify command");
+    discrete_factor = force->numeric(FLERR,arg[1]);
+    return 2;
+  }
+  return 0;
+}
+
+/* ----------------------------------------------------------------------
+   set current vector lengths and pointers
+   called after atoms have migrated
+------------------------------------------------------------------------- */
+
+void MinSpin::reset_vectors()
+{
+  // atomic dof
+
+  // size sp is 4N vector
+  nvec = 4 * atom->nlocal;
+  if (nvec) spvec = atom->sp[0];
+
+  nvec = 3 * atom->nlocal;
+  if (nvec) fmvec = atom->fm[0];
+
+  if (nvec) xvec = atom->x[0];
+  if (nvec) fvec = atom->f[0];
+}
+
+/* ----------------------------------------------------------------------
+   minimization via damped spin dynamics
+------------------------------------------------------------------------- */
+
+int MinSpin::iterate(int maxiter)
+{
+  bigint ntimestep;
+  double fmdotfm;
+  int flag,flagall;
+
+  for (int iter = 0; iter < maxiter; iter++) {
+
+    if (timer->check_timeout(niter))
+      return TIMEOUT;
+
+    ntimestep = ++update->ntimestep;
+    niter++;
+
+    // optimize timestep accross processes / replicas
+    // need a force calculation for timestep optimization
+
+    energy_force(0);
+    dts = evaluate_dt();
+
+    // apply damped precessional dynamics to the spins
+
+    advance_spins(dts);
+
+    eprevious = ecurrent;
+    ecurrent = energy_force(0);
+    neval++;
+
+    //// energy tolerance criterion
+    //// only check after DELAYSTEP elapsed since velocties reset to 0
+    //// sync across replicas if running multi-replica minimization
+
+    if (update->etol > 0.0 && ntimestep-last_negative > DELAYSTEP) {
+      if (update->multireplica == 0) {
+        if (fabs(ecurrent-eprevious) <
+            update->etol * 0.5*(fabs(ecurrent) + fabs(eprevious) + EPS_ENERGY))
+          return ETOL;
+      } else {
+        if (fabs(ecurrent-eprevious) <
+            update->etol * 0.5*(fabs(ecurrent) + fabs(eprevious) + EPS_ENERGY))
+          flag = 0;
+        else flag = 1;
+        MPI_Allreduce(&flag,&flagall,1,MPI_INT,MPI_SUM,universe->uworld);
+        if (flagall == 0) return ETOL;
+      }
+    }
+
+    // magnetic torque tolerance criterion
+    // sync across replicas if running multi-replica minimization
+
+    if (update->ftol > 0.0) {
+      fmdotfm = fmnorm_sqr();
+      if (update->multireplica == 0) {
+        if (fmdotfm < update->ftol*update->ftol) return FTOL;
+      } else {
+        if (fmdotfm < update->ftol*update->ftol) flag = 0;
+        else flag = 1;
+        MPI_Allreduce(&flag,&flagall,1,MPI_INT,MPI_SUM,universe->uworld);
+        if (flagall == 0) return FTOL;
+      }
+    }
+
+    // output for thermo, dump, restart files
+
+    if (output->next == ntimestep) {
+      timer->stamp();
+      output->write(ntimestep);
+      timer->stamp(Timer::OUTPUT);
+    }
+  }
+
+  return MAXITER;
+}
+
+/* ----------------------------------------------------------------------
+   evaluate max timestep
+---------------------------------------------------------------------- */
+
+double MinSpin::evaluate_dt()
+{
+  double dtmax;
+  double fmsq;
+  double fmaxsqone,fmaxsqloc,fmaxsqall;
+  int nlocal = atom->nlocal;
+  double **fm = atom->fm;
+
+  // finding max fm on this proc.
+
+  fmsq = fmaxsqone = fmaxsqloc = fmaxsqall = 0.0;
+  for (int i = 0; i < nlocal; i++) {
+    fmsq = fm[i][0]*fm[i][0]+fm[i][1]*fm[i][1]+fm[i][2]*fm[i][2];
+    fmaxsqone = MAX(fmaxsqone,fmsq);
+  }
+
+  // finding max fm on this replica
+
+  fmaxsqloc = fmaxsqone;
+  MPI_Allreduce(&fmaxsqone,&fmaxsqloc,1,MPI_DOUBLE,MPI_MAX,world);
+
+  // finding max fm over all replicas, if necessary
+  // this communicator would be invalid for multiprocess replicas
+
+  fmaxsqall = fmaxsqloc;
+  if (update->multireplica == 1) {
+    fmaxsqall = fmaxsqloc;
+    MPI_Allreduce(&fmaxsqloc,&fmaxsqall,1,MPI_DOUBLE,MPI_MAX,universe->uworld);
+  }
+
+  if (fmaxsqall == 0.0)
+    error->all(FLERR,"Incorrect fmaxsqall calculation");
+
+  // define max timestep by dividing by the
+  // inverse of max frequency by discrete_factor
+
+  dtmax = MY_2PI/(discrete_factor*sqrt(fmaxsqall));
+
+  return dtmax;
+}
+
+/* ----------------------------------------------------------------------
+   geometric damped advance of spins
+---------------------------------------------------------------------- */
+
+void MinSpin::advance_spins(double dts)
+{
+  int nlocal = atom->nlocal;
+  double **sp = atom->sp;
+  double **fm = atom->fm;
+  double tdampx,tdampy,tdampz;
+  double msq,scale,fm2,energy,dts2;
+  double cp[3],g[3];
+
+  dts2 = dts*dts;
+
+  // loop on all spins on proc.
+
+  for (int i = 0; i < nlocal; i++) {
+
+    // calc. damping torque
+
+    tdampx = -alpha_damp*(fm[i][1]*sp[i][2] - fm[i][2]*sp[i][1]);
+    tdampy = -alpha_damp*(fm[i][2]*sp[i][0] - fm[i][0]*sp[i][2]);
+    tdampz = -alpha_damp*(fm[i][0]*sp[i][1] - fm[i][1]*sp[i][0]);
+
+    // apply advance algorithm (geometric, norm preserving)
+
+    fm2 = (tdampx*tdampx+tdampy*tdampy+tdampz*tdampz);
+    energy = (sp[i][0]*tdampx)+(sp[i][1]*tdampy)+(sp[i][2]*tdampz);
+
+    cp[0] = tdampy*sp[i][2]-tdampz*sp[i][1];
+    cp[1] = tdampz*sp[i][0]-tdampx*sp[i][2];
+    cp[2] = tdampx*sp[i][1]-tdampy*sp[i][0];
+
+    g[0] = sp[i][0]+cp[0]*dts;
+    g[1] = sp[i][1]+cp[1]*dts;
+    g[2] = sp[i][2]+cp[2]*dts;
+
+    g[0] += (tdampx*energy-0.5*sp[i][0]*fm2)*0.5*dts2;
+    g[1] += (tdampy*energy-0.5*sp[i][1]*fm2)*0.5*dts2;
+    g[2] += (tdampz*energy-0.5*sp[i][2]*fm2)*0.5*dts2;
+
+    g[0] /= (1+0.25*fm2*dts2);
+    g[1] /= (1+0.25*fm2*dts2);
+    g[2] /= (1+0.25*fm2*dts2);
+
+    sp[i][0] = g[0];
+    sp[i][1] = g[1];
+    sp[i][2] = g[2];
+
+    // renormalization (check if necessary)
+
+    msq = g[0]*g[0] + g[1]*g[1] + g[2]*g[2];
+    scale = 1.0/sqrt(msq);
+    sp[i][0] *= scale;
+    sp[i][1] *= scale;
+    sp[i][2] *= scale;
+
+    // no comm. to atoms with same tag
+    // because no need for simplecticity
+  }
+}
+
+/* ----------------------------------------------------------------------
+   compute and return ||mag. torque||_2^2
+------------------------------------------------------------------------- */
+
+double MinSpin::fmnorm_sqr()
+{
+  int nlocal = atom->nlocal;
+  double tx,ty,tz;
+  double **sp = atom->sp;
+  double **fm = atom->fm;
+
+  // calc. magnetic torques
+
+  double local_norm2_sqr = 0.0;
+  for (int i = 0; i < nlocal; i++) {
+    tx = (fm[i][1]*sp[i][2] - fm[i][2]*sp[i][1]);
+    ty = (fm[i][2]*sp[i][0] - fm[i][0]*sp[i][2]);
+    tz = (fm[i][0]*sp[i][1] - fm[i][1]*sp[i][0]);
+
+    local_norm2_sqr += tx*tx + ty*ty + tz*tz;
+  }
+
+  // no extra atom calc. for spins
+
+  if (nextra_atom)
+    error->all(FLERR,"extra atom option not available yet");
+
+  double norm2_sqr = 0.0;
+  MPI_Allreduce(&local_norm2_sqr,&norm2_sqr,1,MPI_DOUBLE,MPI_SUM,world);
+
+  return norm2_sqr;
+}
+
diff --git a/src/SPIN/min_spin.h b/src/SPIN/min_spin.h
new file mode 100644
index 0000000000..224d205000
--- /dev/null
+++ b/src/SPIN/min_spin.h
@@ -0,0 +1,59 @@
+/* -*- c++ -*- ----------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+
+#ifdef MINIMIZE_CLASS
+
+MinimizeStyle(spin,MinSpin)
+
+#else
+
+#ifndef LMP_MIN_SPIN_H
+#define LMP_MIN_SPIN_H
+
+#include "min.h"
+
+namespace LAMMPS_NS {
+
+class MinSpin : public Min {
+ public:
+  MinSpin(class LAMMPS *);
+  ~MinSpin() {}
+  void init();
+  void setup_style();
+  int modify_param(int, char **);
+  void reset_vectors();
+  int iterate(int);
+  double evaluate_dt();
+  void advance_spins(double);
+  double fmnorm_sqr();
+
+ private:
+
+  // global and spin timesteps
+  
+  double dt;
+  double dts;
+
+  double alpha_damp;            // damping for spin minimization
+  double discrete_factor;       // factor for spin timestep evaluation
+
+  double *spvec;               // variables for atomic dof, as 1d vector
+  double *fmvec;               // variables for atomic dof, as 1d vector
+
+  bigint last_negative;
+};
+
+}
+
+#endif
+#endif
diff --git a/src/SPIN/pair_spin_dmi.cpp b/src/SPIN/pair_spin_dmi.cpp
index 8496e40f99..d0506e972d 100644
--- a/src/SPIN/pair_spin_dmi.cpp
+++ b/src/SPIN/pair_spin_dmi.cpp
@@ -173,8 +173,8 @@ void PairSpinDmi::init_style()
     if (strcmp(modify->fix[ifix]->style,"nve/spin") == 0) break;
     ifix++;
   }
-  if (ifix == modify->nfix)
-    error->all(FLERR,"pair/spin style requires nve/spin");
+  if ((ifix == modify->nfix) && (comm->me == 0))
+    error->warning(FLERR,"Using pair/spin style without nve/spin");
 
   // get the lattice_flag from nve/spin
 
@@ -233,13 +233,12 @@ void PairSpinDmi::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
   double **fm = atom->fm;
-  double **sp = atom->sp;	
+  double **sp = atom->sp;
   int *type = atom->type;
   int nlocal = atom->nlocal;
   int newton_pair = force->newton_pair;
@@ -296,32 +295,32 @@ void PairSpinDmi::compute(int eflag, int vflag)
       // compute dmi interaction
 
       if (rsq <= local_cut2) {
-	compute_dmi(i,j,eij,fmi,spj);
-	if (lattice_flag) {
-	  compute_dmi_mech(i,j,rsq,eij,fi,spi,spj);
-	}
+        compute_dmi(i,j,eij,fmi,spj);
+        if (lattice_flag) {
+          compute_dmi_mech(i,j,rsq,eij,fi,spi,spj);
+        }
       }
 
-      f[i][0] += fi[0];	
-      f[i][1] += fi[1];	  	
+      f[i][0] += fi[0];
+      f[i][1] += fi[1];
       f[i][2] += fi[2];
-      fm[i][0] += fmi[0];	
-      fm[i][1] += fmi[1];	  	
+      fm[i][0] += fmi[0];
+      fm[i][1] += fmi[1];
       fm[i][2] += fmi[2];
 
       if (newton_pair || j < nlocal) {
-	f[j][0] -= fi[0];	
-        f[j][1] -= fi[1];	  	
+        f[j][0] -= fi[0];
+        f[j][1] -= fi[1];
         f[j][2] -= fi[2];
       }
 
       if (eflag) {
-	evdwl -= (spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
-	evdwl *= hbar;
+        evdwl -= (spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
+        evdwl *= hbar;
       } else evdwl = 0.0;
 
       if (evflag) ev_tally_xyz(i,j,nlocal,newton_pair,
-	  evdwl,ecoul,fi[0],fi[1],fi[2],delx,dely,delz);
+          evdwl,ecoul,fi[0],fi[1],fi[2],delx,dely,delz);
     }
   }
 
@@ -343,7 +342,7 @@ void PairSpinDmi::compute_single_pair(int ii, double fmi[3])
   double delx,dely,delz;
   double spj[3];
 
-  int i,j,jnum,itype,jtype,ntypes;
+  int j,jnum,itype,jtype,ntypes;
   int k,locflag;
   int *jlist,*numneigh,**firstneigh;
 
@@ -351,7 +350,7 @@ void PairSpinDmi::compute_single_pair(int ii, double fmi[3])
 
   numneigh = list->numneigh;
   firstneigh = list->firstneigh;
- 
+
   // check if interaction applies to type of ii
 
   itype = type[ii];
@@ -361,20 +360,20 @@ void PairSpinDmi::compute_single_pair(int ii, double fmi[3])
   while (k <= ntypes) {
     if (k <= itype) {
       if (setflag[k][itype] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else if (k > itype) {
       if (setflag[itype][k] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else error->all(FLERR,"Wrong type number");
   }
 
-  // if interaction applies to type ii, 
+  // if interaction applies to type ii,
   // locflag = 1 and compute pair interaction
 
   //i = ilist[ii];
@@ -423,7 +422,7 @@ void PairSpinDmi::compute_dmi(int i, int j, double eij[3], double fmi[3], double
 {
   int *type = atom->type;
   int itype, jtype;
-  double dmix, dmiy, dmiz;	
+  double dmix, dmiy, dmiz;
   itype = type[i];
   jtype = type[j];
 
@@ -445,7 +444,7 @@ void PairSpinDmi::compute_dmi_mech(int i, int j, double rsq, double /*eij*/[3],
 {
   int *type = atom->type;
   int itype, jtype;
-  double dmix,dmiy,dmiz;	
+  double dmix,dmiy,dmiz;
   itype = type[i];
   jtype = type[j];
   double csx,csy,csz,cdmx,cdmy,cdmz,irij;
@@ -510,7 +509,7 @@ void PairSpinDmi::write_restart(FILE *fp)
     for (j = i; j <= atom->ntypes; j++) {
       fwrite(&setflag[i][j],sizeof(int),1,fp);
       if (setflag[i][j]) {
-	fwrite(&DM[i][j],sizeof(double),1,fp);
+        fwrite(&DM[i][j],sizeof(double),1,fp);
         fwrite(&v_dmx[i][j],sizeof(double),1,fp);
         fwrite(&v_dmy[i][j],sizeof(double),1,fp);
         fwrite(&v_dmz[i][j],sizeof(double),1,fp);
diff --git a/src/SPIN/pair_spin_exchange.cpp b/src/SPIN/pair_spin_exchange.cpp
index b2955aafb2..cb3242c711 100644
--- a/src/SPIN/pair_spin_exchange.cpp
+++ b/src/SPIN/pair_spin_exchange.cpp
@@ -160,8 +160,8 @@ void PairSpinExchange::init_style()
     if (strcmp(modify->fix[ifix]->style,"nve/spin") == 0) break;
     ifix++;
   }
-  if (ifix == modify->nfix)
-    error->all(FLERR,"pair/spin style requires nve/spin");
+  if ((ifix == modify->nfix) && (comm->me == 0))
+    error->warning(FLERR,"Using pair/spin style without nve/spin");
 
   // get the lattice_flag from nve/spin
 
@@ -218,13 +218,12 @@ void PairSpinExchange::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
   double **fm = atom->fm;
-  double **sp = atom->sp;	
+  double **sp = atom->sp;
   int *type = atom->type;
   int nlocal = atom->nlocal;
   int newton_pair = force->newton_pair;
@@ -279,32 +278,32 @@ void PairSpinExchange::compute(int eflag, int vflag)
       // compute exchange interaction
 
       if (rsq <= local_cut2) {
-	compute_exchange(i,j,rsq,fmi,spj);
+        compute_exchange(i,j,rsq,fmi,spj);
         if (lattice_flag) {
-	  compute_exchange_mech(i,j,rsq,eij,fi,spi,spj);
-	}
+          compute_exchange_mech(i,j,rsq,eij,fi,spi,spj);
+        }
       }
 
-      f[i][0] += fi[0];	
-      f[i][1] += fi[1];	  	
+      f[i][0] += fi[0];
+      f[i][1] += fi[1];
       f[i][2] += fi[2];
-      fm[i][0] += fmi[0];	
-      fm[i][1] += fmi[1];	  	
+      fm[i][0] += fmi[0];
+      fm[i][1] += fmi[1];
       fm[i][2] += fmi[2];
 
       if (newton_pair || j < nlocal) {
-	f[j][0] -= fi[0];	
-        f[j][1] -= fi[1];	  	
+        f[j][0] -= fi[0];
+        f[j][1] -= fi[1];
         f[j][2] -= fi[2];
       }
 
       if (eflag) {
-	evdwl -= (spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
-	evdwl *= hbar;
+        evdwl -= (spi[0]*fmi[0] + spi[1]*fmi[1] + spi[2]*fmi[2]);
+        evdwl *= hbar;
       } else evdwl = 0.0;
 
       if (evflag) ev_tally_xyz(i,j,nlocal,newton_pair,
-	  evdwl,ecoul,fi[0],fi[1],fi[2],delx,dely,delz);
+          evdwl,ecoul,fi[0],fi[1],fi[2],delx,dely,delz);
     }
   }
 
@@ -326,7 +325,7 @@ void PairSpinExchange::compute_single_pair(int ii, double fmi[3])
   double delx,dely,delz;
   double spj[3];
 
-  int i,j,jnum,itype,jtype,ntypes;
+  int j,jnum,itype,jtype,ntypes;
   int k,locflag;
   int *jlist,*numneigh,**firstneigh;
 
@@ -344,24 +343,24 @@ void PairSpinExchange::compute_single_pair(int ii, double fmi[3])
   while (k <= ntypes) {
     if (k <= itype) {
       if (setflag[k][itype] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else if (k > itype) {
       if (setflag[itype][k] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else error->all(FLERR,"Wrong type number");
   }
 
-  // if interaction applies to type ii, 
+  // if interaction applies to type ii,
   // locflag = 1 and compute pair interaction
 
   if (locflag == 1) {
-    
+
     xi[0] = x[ii][0];
     xi[1] = x[ii][1];
     xi[2] = x[ii][2];
@@ -389,7 +388,7 @@ void PairSpinExchange::compute_single_pair(int ii, double fmi[3])
         compute_exchange(ii,j,rsq,fmi,spj);
       }
     }
-  }	
+  }
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/SPIN/pair_spin_magelec.cpp b/src/SPIN/pair_spin_magelec.cpp
index a7357f61e3..6ff003521d 100644
--- a/src/SPIN/pair_spin_magelec.cpp
+++ b/src/SPIN/pair_spin_magelec.cpp
@@ -166,8 +166,8 @@ void PairSpinMagelec::init_style()
     if (strcmp(modify->fix[ifix]->style,"nve/spin") == 0) break;
     ifix++;
   }
-  if (ifix == modify->nfix)
-    error->all(FLERR,"pair/spin style requires nve/spin");
+  if ((ifix == modify->nfix) && (comm->me == 0))
+    error->warning(FLERR,"Using pair/spin style without nve/spin");
 
   // get the lattice_flag from nve/spin
 
@@ -225,8 +225,7 @@ void PairSpinMagelec::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -333,7 +332,7 @@ void PairSpinMagelec::compute_single_pair(int ii, double fmi[3])
   double delx,dely,delz;
   double spj[3];
 
-  int i,j,jnum,itype,jtype,ntypes;
+  int j,jnum,itype,jtype,ntypes;
   int k,locflag;
   int *jlist,*numneigh,**firstneigh;
 
@@ -341,7 +340,7 @@ void PairSpinMagelec::compute_single_pair(int ii, double fmi[3])
 
   numneigh = list->numneigh;
   firstneigh = list->firstneigh;
- 
+
   // check if interaction applies to type of ii
 
   itype = type[ii];
@@ -351,42 +350,42 @@ void PairSpinMagelec::compute_single_pair(int ii, double fmi[3])
   while (k <= ntypes) {
     if (k <= itype) {
       if (setflag[k][itype] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else if (k > itype) {
       if (setflag[itype][k] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else error->all(FLERR,"Wrong type number");
   }
 
-  // if interaction applies to type ii, 
+  // if interaction applies to type ii,
   // locflag = 1 and compute pair interaction
 
   if (locflag == 1) {
-    
+
     xi[0] = x[ii][0];
     xi[1] = x[ii][1];
     xi[2] = x[ii][2];
-    
+
     jlist = firstneigh[ii];
     jnum = numneigh[ii];
-    
+
     for (int jj = 0; jj < jnum; jj++) {
-    
+
       j = jlist[jj];
       j &= NEIGHMASK;
       jtype = type[j];
       local_cut2 = cut_spin_magelec[itype][jtype]*cut_spin_magelec[itype][jtype];
-    
+
       spj[0] = sp[j][0];
       spj[1] = sp[j][1];
       spj[2] = sp[j][2];
-    
+
       delx = xi[0] - x[j][0];
       dely = xi[1] - x[j][1];
       delz = xi[2] - x[j][2];
@@ -395,7 +394,7 @@ void PairSpinMagelec::compute_single_pair(int ii, double fmi[3])
       eij[0] = -inorm*delx;
       eij[1] = -inorm*dely;
       eij[2] = -inorm*delz;
-    
+
       if (rsq <= local_cut2) {
         compute_magelec(ii,j,eij,fmi,spj);
       }
diff --git a/src/SPIN/pair_spin_neel.cpp b/src/SPIN/pair_spin_neel.cpp
index bd12832a8d..a39d6f3461 100644
--- a/src/SPIN/pair_spin_neel.cpp
+++ b/src/SPIN/pair_spin_neel.cpp
@@ -173,8 +173,8 @@ void PairSpinNeel::init_style()
     if (strcmp(modify->fix[ifix]->style,"nve/spin") == 0) break;
     ifix++;
   }
-  if (ifix == modify->nfix)
-    error->all(FLERR,"pair/spin style requires nve/spin");
+  if ((ifix == modify->nfix) && (comm->me == 0))
+    error->warning(FLERR,"Using pair/spin style without nve/spin");
 
   // get the lattice_flag from nve/spin
 
@@ -232,8 +232,7 @@ void PairSpinNeel::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -344,7 +343,7 @@ void PairSpinNeel::compute_single_pair(int ii, double fmi[3])
   double xi[3], rij[3], eij[3];
   double spi[3], spj[3];
 
-  int i,j,jnum,itype,jtype,ntypes;
+  int j,jnum,itype,jtype,ntypes;
   int k,locflag;
   int *jlist,*numneigh,**firstneigh;
 
@@ -352,7 +351,7 @@ void PairSpinNeel::compute_single_pair(int ii, double fmi[3])
 
   numneigh = list->numneigh;
   firstneigh = list->firstneigh;
-  
+
   // check if interaction applies to type of ii
 
   itype = type[ii];
@@ -362,20 +361,20 @@ void PairSpinNeel::compute_single_pair(int ii, double fmi[3])
   while (k <= ntypes) {
     if (k <= itype) {
       if (setflag[k][itype] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else if (k > itype) {
       if (setflag[itype][k] == 1) {
-	locflag =1;
-	break;
+        locflag =1;
+        break;
       }
       k++;
     } else error->all(FLERR,"Wrong type number");
   }
 
-  // if interaction applies to type ii, 
+  // if interaction applies to type ii,
   // locflag = 1 and compute pair interaction
 
   if (locflag == 1) {
diff --git a/src/STUBS/mpi.c b/src/STUBS/mpi.c
index 053108fee8..09bb48ecdc 100644
--- a/src/STUBS/mpi.c
+++ b/src/STUBS/mpi.c
@@ -200,7 +200,11 @@ int MPI_Request_free(MPI_Request *request)
 int MPI_Send(const void *buf, int count, MPI_Datatype datatype,
              int dest, int tag, MPI_Comm comm)
 {
-  printf("MPI Stub WARNING: Should not send message to self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not send message to self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -209,7 +213,11 @@ int MPI_Send(const void *buf, int count, MPI_Datatype datatype,
 int MPI_Isend(const void *buf, int count, MPI_Datatype datatype,
               int source, int tag, MPI_Comm comm, MPI_Request *request)
 {
-  printf("MPI Stub WARNING: Should not send message to self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not send message to self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -218,7 +226,11 @@ int MPI_Isend(const void *buf, int count, MPI_Datatype datatype,
 int MPI_Rsend(const void *buf, int count, MPI_Datatype datatype,
               int dest, int tag, MPI_Comm comm)
 {
-  printf("MPI Stub WARNING: Should not rsend message to self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not rsend message to self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -227,7 +239,11 @@ int MPI_Rsend(const void *buf, int count, MPI_Datatype datatype,
 int MPI_Recv(void *buf, int count, MPI_Datatype datatype,
              int source, int tag, MPI_Comm comm, MPI_Status *status)
 {
-  printf("MPI Stub WARNING: Should not recv message from self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not recv message from self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -236,7 +252,11 @@ int MPI_Recv(void *buf, int count, MPI_Datatype datatype,
 int MPI_Irecv(void *buf, int count, MPI_Datatype datatype,
               int source, int tag, MPI_Comm comm, MPI_Request *request)
 {
-  printf("MPI Stub WARNING: Should not recv message from self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not recv message from self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -244,7 +264,11 @@ int MPI_Irecv(void *buf, int count, MPI_Datatype datatype,
 
 int MPI_Wait(MPI_Request *request, MPI_Status *status)
 {
-  printf("MPI Stub WARNING: Should not wait on message from self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not wait on message from self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -252,7 +276,11 @@ int MPI_Wait(MPI_Request *request, MPI_Status *status)
 
 int MPI_Waitall(int n, MPI_Request *request, MPI_Status *status)
 {
-  printf("MPI Stub WARNING: Should not wait on message from self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not wait on message from self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -261,7 +289,11 @@ int MPI_Waitall(int n, MPI_Request *request, MPI_Status *status)
 int MPI_Waitany(int count, MPI_Request *request, int *index,
                 MPI_Status *status)
 {
-  printf("MPI Stub WARNING: Should not wait on message from self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not wait on message from self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -272,7 +304,11 @@ int MPI_Sendrecv(const void *sbuf, int scount, MPI_Datatype sdatatype,
                  MPI_Datatype rdatatype, int source, int rtag,
                  MPI_Comm comm, MPI_Status *status)
 {
-  printf("MPI Stub WARNING: Should not send message to self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not send message to self\n");
+    ++callcount;
+  }
   return 0;
 }
 
@@ -280,7 +316,11 @@ int MPI_Sendrecv(const void *sbuf, int scount, MPI_Datatype sdatatype,
 
 int MPI_Get_count(MPI_Status *status, MPI_Datatype datatype, int *count)
 {
-  printf("MPI Stub WARNING: Should not get count of message to self\n");
+  static int callcount=0;
+  if (callcount == 0) {
+    printf("MPI Stub WARNING: Should not get count of message to self\n");
+    ++callcount;
+  }
   return 0;
 }
 
diff --git a/src/USER-AWPMD/pair_awpmd_cut.cpp b/src/USER-AWPMD/pair_awpmd_cut.cpp
index 806e4f3a14..1b7bf35c28 100644
--- a/src/USER-AWPMD/pair_awpmd_cut.cpp
+++ b/src/USER-AWPMD/pair_awpmd_cut.cpp
@@ -108,10 +108,7 @@ void PairAWPMDCut::compute(int eflag, int vflag)
   // pvector = [KE, Pauli, ecoul, radial_restraint]
   for (int i=0; i<4; i++) pvector[i] = 0.0;
 
-  if (eflag || vflag)
-    ev_setup(eflag,vflag);
-  else
-    evflag = vflag_fdotr = 0; //??
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-CGDNA/bond_oxdna_fene.cpp b/src/USER-CGDNA/bond_oxdna_fene.cpp
index 34a25a9b5a..8271668e3f 100644
--- a/src/USER-CGDNA/bond_oxdna_fene.cpp
+++ b/src/USER-CGDNA/bond_oxdna_fene.cpp
@@ -96,8 +96,7 @@ void BondOxdnaFene::compute(int eflag, int vflag)
   int newton_bond = force->newton_bond;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // loop over FENE bonds
 
diff --git a/src/USER-CGDNA/pair_oxdna2_coaxstk.cpp b/src/USER-CGDNA/pair_oxdna2_coaxstk.cpp
index 0b220a3275..f54197aea7 100644
--- a/src/USER-CGDNA/pair_oxdna2_coaxstk.cpp
+++ b/src/USER-CGDNA/pair_oxdna2_coaxstk.cpp
@@ -144,8 +144,7 @@ void PairOxdna2Coaxstk::compute(int eflag, int vflag)
   double df2,df4f6t1,df4t4,df4t5,df4t6,rsint;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGDNA/pair_oxdna2_dh.cpp b/src/USER-CGDNA/pair_oxdna2_dh.cpp
index da6e1f8bbd..10e7121427 100644
--- a/src/USER-CGDNA/pair_oxdna2_dh.cpp
+++ b/src/USER-CGDNA/pair_oxdna2_dh.cpp
@@ -114,8 +114,7 @@ void PairOxdna2Dh::compute(int eflag, int vflag)
   int a,b,ia,ib,anum,bnum,atype,btype;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGDNA/pair_oxdna_coaxstk.cpp b/src/USER-CGDNA/pair_oxdna_coaxstk.cpp
index ef0ff16150..6d3061620d 100644
--- a/src/USER-CGDNA/pair_oxdna_coaxstk.cpp
+++ b/src/USER-CGDNA/pair_oxdna_coaxstk.cpp
@@ -156,8 +156,7 @@ void PairOxdnaCoaxstk::compute(int eflag, int vflag)
   double df2,df4t1,df4t4,df4t5,df4t6,df5c3,rsint;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGDNA/pair_oxdna_excv.cpp b/src/USER-CGDNA/pair_oxdna_excv.cpp
index 719a63b5f4..82af5ed1c7 100644
--- a/src/USER-CGDNA/pair_oxdna_excv.cpp
+++ b/src/USER-CGDNA/pair_oxdna_excv.cpp
@@ -144,8 +144,7 @@ void PairOxdnaExcv::compute(int eflag, int vflag)
   int a,b,ia,ib,anum,bnum,atype,btype;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGDNA/pair_oxdna_hbond.cpp b/src/USER-CGDNA/pair_oxdna_hbond.cpp
index d8305e30de..d2aa236a05 100644
--- a/src/USER-CGDNA/pair_oxdna_hbond.cpp
+++ b/src/USER-CGDNA/pair_oxdna_hbond.cpp
@@ -161,8 +161,7 @@ void PairOxdnaHbond::compute(int eflag, int vflag)
   double df1,df4t1,df4t4,df4t2,df4t3,df4t7,df4t8;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGDNA/pair_oxdna_stk.cpp b/src/USER-CGDNA/pair_oxdna_stk.cpp
index f713e4d27c..4cbc0317dd 100644
--- a/src/USER-CGDNA/pair_oxdna_stk.cpp
+++ b/src/USER-CGDNA/pair_oxdna_stk.cpp
@@ -154,8 +154,7 @@ void PairOxdnaStk::compute(int eflag, int vflag)
   double tptofp;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // loop over stacking interaction neighours using bond topology
 
diff --git a/src/USER-CGDNA/pair_oxdna_xstk.cpp b/src/USER-CGDNA/pair_oxdna_xstk.cpp
index a354a604fd..071886556c 100644
--- a/src/USER-CGDNA/pair_oxdna_xstk.cpp
+++ b/src/USER-CGDNA/pair_oxdna_xstk.cpp
@@ -153,8 +153,7 @@ void PairOxdnaXstk::compute(int eflag, int vflag)
   double df2,df4t1,df4t4,df4t2,df4t3,df4t7,df4t8,rsint;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   anum = list->inum;
   alist = list->ilist;
diff --git a/src/USER-CGSDK/angle_sdk.cpp b/src/USER-CGSDK/angle_sdk.cpp
index 6b8245b491..823c725e07 100644
--- a/src/USER-CGSDK/angle_sdk.cpp
+++ b/src/USER-CGSDK/angle_sdk.cpp
@@ -68,8 +68,7 @@ void AngleSDK::compute(int eflag, int vflag)
   double rsq1,rsq2,rsq3,r1,r2,c,s,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-CGSDK/pair_lj_sdk.cpp b/src/USER-CGSDK/pair_lj_sdk.cpp
index 3404beb58a..7dd6c04436 100644
--- a/src/USER-CGSDK/pair_lj_sdk.cpp
+++ b/src/USER-CGSDK/pair_lj_sdk.cpp
@@ -78,9 +78,7 @@ PairLJSDK::~PairLJSDK()
 
 void PairLJSDK::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/USER-CGSDK/pair_lj_sdk_coul_long.cpp b/src/USER-CGSDK/pair_lj_sdk_coul_long.cpp
index c51235518b..33a1659df9 100644
--- a/src/USER-CGSDK/pair_lj_sdk_coul_long.cpp
+++ b/src/USER-CGSDK/pair_lj_sdk_coul_long.cpp
@@ -90,9 +90,7 @@ PairLJSDKCoulLong::~PairLJSDKCoulLong()
 
 void PairLJSDKCoulLong::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/USER-CGSDK/pair_lj_sdk_coul_msm.cpp b/src/USER-CGSDK/pair_lj_sdk_coul_msm.cpp
index c4882fdbdb..d26f8efcdc 100644
--- a/src/USER-CGSDK/pair_lj_sdk_coul_msm.cpp
+++ b/src/USER-CGSDK/pair_lj_sdk_coul_msm.cpp
@@ -57,9 +57,7 @@ void PairLJSDKCoulMSM::compute(int eflag, int vflag)
   if (force->kspace->scalar_pressure_flag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' with Pair style");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   if (evflag) {
     if (eflag) {
diff --git a/src/USER-COLVARS/fix_colvars.cpp b/src/USER-COLVARS/fix_colvars.cpp
index 0e4e151c3d..545ceb7b0e 100644
--- a/src/USER-COLVARS/fix_colvars.cpp
+++ b/src/USER-COLVARS/fix_colvars.cpp
@@ -645,7 +645,7 @@ void FixColvars::setup(int vflag)
 /* ---------------------------------------------------------------------- */
 /* Main colvars handler:
  * Send coodinates and add colvar forces to atoms. */
-void FixColvars::post_force(int vflag)
+void FixColvars::post_force(int /*vflag*/)
 {
   // some housekeeping: update status of the proxy as needed.
   if (me == 0) {
@@ -816,7 +816,7 @@ void FixColvars::min_post_force(int vflag)
 }
 
 /* ---------------------------------------------------------------------- */
-void FixColvars::post_force_respa(int vflag, int ilevel, int iloop)
+void FixColvars::post_force_respa(int vflag, int ilevel, int /*iloop*/)
 {
   /* only process colvar forces on the outmost RESPA level. */
   if (ilevel == nlevels_respa-1) post_force(vflag);
diff --git a/src/USER-DPD/pair_dpd_fdt.cpp b/src/USER-DPD/pair_dpd_fdt.cpp
index 12e6d9f257..07ef8190f0 100644
--- a/src/USER-DPD/pair_dpd_fdt.cpp
+++ b/src/USER-DPD/pair_dpd_fdt.cpp
@@ -76,8 +76,7 @@ void PairDPDfdt::compute(int eflag, int vflag)
   double gamma_ij;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/USER-DPD/pair_dpd_fdt_energy.cpp b/src/USER-DPD/pair_dpd_fdt_energy.cpp
index 42c23e3ad2..12e6989c00 100644
--- a/src/USER-DPD/pair_dpd_fdt_energy.cpp
+++ b/src/USER-DPD/pair_dpd_fdt_energy.cpp
@@ -85,8 +85,7 @@ void PairDPDfdtEnergy::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/USER-DPD/pair_exp6_rx.cpp b/src/USER-DPD/pair_exp6_rx.cpp
index 0251f019c5..13521b52b1 100644
--- a/src/USER-DPD/pair_exp6_rx.cpp
+++ b/src/USER-DPD/pair_exp6_rx.cpp
@@ -121,8 +121,7 @@ void PairExp6rx::compute(int eflag, int vflag)
 
   evdwlOld = 0.0;
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-DPD/pair_multi_lucy.cpp b/src/USER-DPD/pair_multi_lucy.cpp
index 19a4a02f0b..ffc1562f88 100644
--- a/src/USER-DPD/pair_multi_lucy.cpp
+++ b/src/USER-DPD/pair_multi_lucy.cpp
@@ -95,8 +95,7 @@ void PairMultiLucy::compute(int eflag, int vflag)
   int tlm1 = tablength - 1;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-DPD/pair_multi_lucy_rx.cpp b/src/USER-DPD/pair_multi_lucy_rx.cpp
index f3ad86eb2f..801e8ff039 100644
--- a/src/USER-DPD/pair_multi_lucy_rx.cpp
+++ b/src/USER-DPD/pair_multi_lucy_rx.cpp
@@ -111,8 +111,7 @@ void PairMultiLucyRX::compute(int eflag, int vflag)
 
   evdwlOld = 0.0;
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-DPD/pair_table_rx.cpp b/src/USER-DPD/pair_table_rx.cpp
index 1e7bc440d1..f2d0d7b1fb 100644
--- a/src/USER-DPD/pair_table_rx.cpp
+++ b/src/USER-DPD/pair_table_rx.cpp
@@ -78,8 +78,7 @@ void PairTableRX::compute(int eflag, int vflag)
 
   evdwlOld = 0.0;
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-DRUDE/pair_lj_cut_thole_long.cpp b/src/USER-DRUDE/pair_lj_cut_thole_long.cpp
index f9da40dfb9..1ebe4a4c2d 100644
--- a/src/USER-DRUDE/pair_lj_cut_thole_long.cpp
+++ b/src/USER-DRUDE/pair_lj_cut_thole_long.cpp
@@ -98,8 +98,7 @@ void PairLJCutTholeLong::compute(int eflag, int vflag)
   int di_closest;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-DRUDE/pair_thole.cpp b/src/USER-DRUDE/pair_thole.cpp
index 5a518d819b..1bb75af825 100644
--- a/src/USER-DRUDE/pair_thole.cpp
+++ b/src/USER-DRUDE/pair_thole.cpp
@@ -64,8 +64,7 @@ void PairThole::compute(int eflag, int vflag)
   double dcoul,asr,exp_asr;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-EFF/pair_eff_cut.cpp b/src/USER-EFF/pair_eff_cut.cpp
index b4e9011e33..f566922ef7 100644
--- a/src/USER-EFF/pair_eff_cut.cpp
+++ b/src/USER-EFF/pair_eff_cut.cpp
@@ -81,8 +81,7 @@ void PairEffCut::compute(int eflag, int vflag)
   // pvector = [KE, Pauli, ecoul, radial_restraint]
   for (i=0; i<4; i++) pvector[i] = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_coul_cut_soft.cpp b/src/USER-FEP/pair_coul_cut_soft.cpp
index 529ffe6b09..86a6d02819 100644
--- a/src/USER-FEP/pair_coul_cut_soft.cpp
+++ b/src/USER-FEP/pair_coul_cut_soft.cpp
@@ -60,8 +60,7 @@ void PairCoulCutSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_coul_long_soft.cpp b/src/USER-FEP/pair_coul_long_soft.cpp
index e45dbe72d6..9d3ffc0da1 100644
--- a/src/USER-FEP/pair_coul_long_soft.cpp
+++ b/src/USER-FEP/pair_coul_long_soft.cpp
@@ -78,8 +78,7 @@ void PairCoulLongSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_charmm_coul_long_soft.cpp b/src/USER-FEP/pair_lj_charmm_coul_long_soft.cpp
index 34758b159b..ac6f1e6384 100644
--- a/src/USER-FEP/pair_lj_charmm_coul_long_soft.cpp
+++ b/src/USER-FEP/pair_lj_charmm_coul_long_soft.cpp
@@ -92,8 +92,7 @@ void PairLJCharmmCoulLongSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -415,8 +414,7 @@ void PairLJCharmmCoulLongSoft::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_class2_coul_cut_soft.cpp b/src/USER-FEP/pair_lj_class2_coul_cut_soft.cpp
index 7970097cfe..ae79515488 100644
--- a/src/USER-FEP/pair_lj_class2_coul_cut_soft.cpp
+++ b/src/USER-FEP/pair_lj_class2_coul_cut_soft.cpp
@@ -39,24 +39,24 @@ PairLJClass2CoulCutSoft::PairLJClass2CoulCutSoft(LAMMPS *lmp) : Pair(lmp)
 
 PairLJClass2CoulCutSoft::~PairLJClass2CoulCutSoft()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(cut_coul);
-      memory->destroy(cut_coulsq);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lambda);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(cut_coul);
+    memory->destroy(cut_coulsq);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lambda);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
 }
 
@@ -72,8 +72,7 @@ void PairLJClass2CoulCutSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_class2_coul_long_soft.cpp b/src/USER-FEP/pair_lj_class2_coul_long_soft.cpp
index 13096a64c6..6410f83fa1 100644
--- a/src/USER-FEP/pair_lj_class2_coul_long_soft.cpp
+++ b/src/USER-FEP/pair_lj_class2_coul_long_soft.cpp
@@ -49,22 +49,22 @@ PairLJClass2CoulLongSoft::PairLJClass2CoulLongSoft(LAMMPS *lmp) : Pair(lmp)
 
 PairLJClass2CoulLongSoft::~PairLJClass2CoulLongSoft()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lambda);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lambda);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
 }
 
@@ -82,8 +82,7 @@ void PairLJClass2CoulLongSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_class2_soft.cpp b/src/USER-FEP/pair_lj_class2_soft.cpp
index b7f21fc59c..d22cd53883 100644
--- a/src/USER-FEP/pair_lj_class2_soft.cpp
+++ b/src/USER-FEP/pair_lj_class2_soft.cpp
@@ -32,28 +32,26 @@ using namespace MathConst;
 PairLJClass2Soft::PairLJClass2Soft(LAMMPS *lmp) : Pair(lmp)
 {
   writedata = 1;
-  allocated = 0;
 }
 
 /* ---------------------------------------------------------------------- */
 
 PairLJClass2Soft::~PairLJClass2Soft()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lambda);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(offset);
-      allocated=0;
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lambda);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(offset);
   }
 }
 
@@ -68,8 +66,7 @@ void PairLJClass2Soft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_cut_coul_cut_soft.cpp b/src/USER-FEP/pair_lj_cut_coul_cut_soft.cpp
index fc887fbec5..35c9162dbc 100644
--- a/src/USER-FEP/pair_lj_cut_coul_cut_soft.cpp
+++ b/src/USER-FEP/pair_lj_cut_coul_cut_soft.cpp
@@ -73,8 +73,7 @@ void PairLJCutCoulCutSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_cut_coul_long_soft.cpp b/src/USER-FEP/pair_lj_cut_coul_long_soft.cpp
index a9032ab4d7..79253d2b9c 100644
--- a/src/USER-FEP/pair_lj_cut_coul_long_soft.cpp
+++ b/src/USER-FEP/pair_lj_cut_coul_long_soft.cpp
@@ -89,8 +89,7 @@ void PairLJCutCoulLongSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -390,8 +389,7 @@ void PairLJCutCoulLongSoft::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_cut_soft.cpp b/src/USER-FEP/pair_lj_cut_soft.cpp
index 1322565473..4192d6546b 100644
--- a/src/USER-FEP/pair_lj_cut_soft.cpp
+++ b/src/USER-FEP/pair_lj_cut_soft.cpp
@@ -77,8 +77,7 @@ void PairLJCutSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -323,8 +322,7 @@ void PairLJCutSoft::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_lj_cut_tip4p_long_soft.cpp b/src/USER-FEP/pair_lj_cut_tip4p_long_soft.cpp
index 8653800ee6..8ac28f9fa9 100644
--- a/src/USER-FEP/pair_lj_cut_tip4p_long_soft.cpp
+++ b/src/USER-FEP/pair_lj_cut_tip4p_long_soft.cpp
@@ -92,8 +92,7 @@ void PairLJCutTIP4PLongSoft::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/USER-FEP/pair_morse_soft.cpp b/src/USER-FEP/pair_morse_soft.cpp
index f4c5a4b910..21f616a082 100644
--- a/src/USER-FEP/pair_morse_soft.cpp
+++ b/src/USER-FEP/pair_morse_soft.cpp
@@ -53,8 +53,7 @@ void PairMorseSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-FEP/pair_tip4p_long_soft.cpp b/src/USER-FEP/pair_tip4p_long_soft.cpp
index 5e8c5000f8..9b6a6841fe 100644
--- a/src/USER-FEP/pair_tip4p_long_soft.cpp
+++ b/src/USER-FEP/pair_tip4p_long_soft.cpp
@@ -91,8 +91,7 @@ void PairTIP4PLongSoft::compute(int eflag, int vflag)
   double rsq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh & newsite if necessary
   // initialize hneigh[0] to -1 on steps when reneighboring occurred
diff --git a/src/USER-INTEL/README b/src/USER-INTEL/README
index 871d881f39..786033ca85 100644
--- a/src/USER-INTEL/README
+++ b/src/USER-INTEL/README
@@ -2,13 +2,13 @@
                      --------------------------------
                           LAMMPS Intel(R) Package
                      --------------------------------
-                     
+
              W. Michael Brown (Intel) michael.w.brown at intel.com
                   Markus Hohnerbach (RWTH Aachen University)
                    William McDoniel (RWTH Aachen University)
                    Rodrigo Canales (RWTH Aachen University)
                            Stan Moore (Sandia)
-		   Ahmed E. Ismail (RWTH Aachen University)
+                   Ahmed E. Ismail (RWTH Aachen University)
                    Paolo Bientinesi (RWTH Aachen University)
                           Anupama Kurpad (Intel)
                           Biswajit Mishra (Shell)
@@ -20,23 +20,29 @@ This package provides LAMMPS styles that:
    1. include support for single and mixed precision in addition to double.
    2. include modifications to support vectorization for key routines
    3. include modifications for data layouts to improve cache efficiency
-   3. include modifications to support offload to Intel(R) Xeon Phi(TM) 
+   3. include modifications to support offload to Intel(R) Xeon Phi(TM)
       coprocessors
 
 -----------------------------------------------------------------------------
 
+As of 2019/03/28 none of the styles provided in this package support
+tallying per-atom stresses. Any attempt to compute/access it will
+cause an error termination.
+
+-----------------------------------------------------------------------------
+
 For Intel server processors codenamed "Skylake", the following flags should
 be added or changed in the Makefile depending on the version:
 
 2017 update 2         - No changes needed
 2017 updates 3 or 4   - Use -xCOMMON-AVX512 and not -xHost or -xCORE-AVX512
 2018 inital release   - Use -xCOMMON-AVX512 and not -xHost or -xCORE-AVX512
-2018u1 or newer       - Use -xHost or -xCORE-AVX512 and -qopt-zmm-usage=high 
+2018u1 or newer       - Use -xHost or -xCORE-AVX512 and -qopt-zmm-usage=high
 
 -----------------------------------------------------------------------------
 
 When using the suffix command with "intel", intel styles will be used if they
-exist. If the suffix command is used with "hybrid intel omp" and the USER-OMP 
+exist. If the suffix command is used with "hybrid intel omp" and the USER-OMP
 is installed, USER-OMP styles will be used whenever USER-INTEL styles are not
 available. This allow for running most styles in LAMMPS with threading.
 
@@ -55,21 +61,21 @@ need to be changed.
 
 Unless Intel Math Kernel Library (MKL) is unavailable, -DLMP_USE_MKL_RNG
 should be added to the compile flags. This will enable using the MKL Mersenne
-Twister random number generator (RNG) for Dissipative Particle Dynamics 
-(DPD). This RNG can allow significantly faster performance and it also has a 
+Twister random number generator (RNG) for Dissipative Particle Dynamics
+(DPD). This RNG can allow significantly faster performance and it also has a
 significantly longer period than the standard RNG for DPD.
 
 -----------------------------------------------------------------------------
 
-In order to use offload to Intel(R) Xeon Phi(TM) coprocessors, the flag 
--DLMP_INTEL_OFFLOAD should be set in the Makefile. Offload requires the use of 
+In order to use offload to Intel(R) Xeon Phi(TM) coprocessors, the flag
+-DLMP_INTEL_OFFLOAD should be set in the Makefile. Offload requires the use of
 Intel compilers.
 
 -----------------------------------------------------------------------------
 
-For portability reasons, vectorization directives are currently only enabled 
+For portability reasons, vectorization directives are currently only enabled
 for Intel compilers. Using other compilers may result in significantly
-lower performance. This behavior can be changed by defining 
+lower performance. This behavior can be changed by defining
 LMP_SIMD_COMPILER for the preprocessor (see intel_preprocess.h).
 
 -----------------------------------------------------------------------------
@@ -81,9 +87,9 @@ compile with -DINTEL_OFFLOAD_NOAFFINITY.
 
 -----------------------------------------------------------------------------
 
-Vector intrinsics are temporarily being used for the Stillinger-Weber 
+Vector intrinsics are temporarily being used for the Stillinger-Weber
 potential to allow for advanced features in the AVX512 instruction set to
 be exploited on early hardware. We hope to see compiler improvements for
 AVX512 that will eliminate this requirement, so it is not recommended to
-develop code based on the intrinsics implementation. Please e-mail the 
+develop code based on the intrinsics implementation. Please e-mail the
 authors for more details.
diff --git a/src/USER-INTEL/angle_charmm_intel.cpp b/src/USER-INTEL/angle_charmm_intel.cpp
index f2542fc0c7..43de50e7fa 100644
--- a/src/USER-INTEL/angle_charmm_intel.cpp
+++ b/src/USER-INTEL/angle_charmm_intel.cpp
@@ -78,8 +78,9 @@ void AngleCharmmIntel::compute(int eflag, int vflag,
                                IntelBuffers<flt_t,acc_t> *buffers,
                                const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/angle_harmonic_intel.cpp b/src/USER-INTEL/angle_harmonic_intel.cpp
index 6d8901a5ee..d073e7bc56 100644
--- a/src/USER-INTEL/angle_harmonic_intel.cpp
+++ b/src/USER-INTEL/angle_harmonic_intel.cpp
@@ -78,8 +78,9 @@ void AngleHarmonicIntel::compute(int eflag, int vflag,
                                IntelBuffers<flt_t,acc_t> *buffers,
                                const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/bond_fene_intel.cpp b/src/USER-INTEL/bond_fene_intel.cpp
index bff3722a44..6578706a9b 100644
--- a/src/USER-INTEL/bond_fene_intel.cpp
+++ b/src/USER-INTEL/bond_fene_intel.cpp
@@ -74,8 +74,9 @@ void BondFENEIntel::compute(int eflag, int vflag,
                                 IntelBuffers<flt_t,acc_t> *buffers,
                                 const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/bond_harmonic_intel.cpp b/src/USER-INTEL/bond_harmonic_intel.cpp
index 65894efa05..55dda9fa15 100644
--- a/src/USER-INTEL/bond_harmonic_intel.cpp
+++ b/src/USER-INTEL/bond_harmonic_intel.cpp
@@ -74,8 +74,9 @@ void BondHarmonicIntel::compute(int eflag, int vflag,
                                 IntelBuffers<flt_t,acc_t> *buffers,
                                 const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/dihedral_charmm_intel.cpp b/src/USER-INTEL/dihedral_charmm_intel.cpp
index c9237e7309..2ea4eb6d21 100644
--- a/src/USER-INTEL/dihedral_charmm_intel.cpp
+++ b/src/USER-INTEL/dihedral_charmm_intel.cpp
@@ -84,9 +84,9 @@ void DihedralCharmmIntel::compute(int eflag, int vflag,
                                   IntelBuffers<flt_t,acc_t> *buffers,
                                   const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/USER-INTEL/dihedral_fourier_intel.cpp b/src/USER-INTEL/dihedral_fourier_intel.cpp
index 6ccc165c61..8c4a2ce921 100644
--- a/src/USER-INTEL/dihedral_fourier_intel.cpp
+++ b/src/USER-INTEL/dihedral_fourier_intel.cpp
@@ -73,9 +73,9 @@ void DihedralFourierIntel::compute(int eflag, int vflag,
                                    IntelBuffers<flt_t,acc_t> *buffers,
                                    const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/dihedral_harmonic_intel.cpp b/src/USER-INTEL/dihedral_harmonic_intel.cpp
index ae5eb914e7..60655f2618 100644
--- a/src/USER-INTEL/dihedral_harmonic_intel.cpp
+++ b/src/USER-INTEL/dihedral_harmonic_intel.cpp
@@ -73,9 +73,9 @@ void DihedralHarmonicIntel::compute(int eflag, int vflag,
                                   IntelBuffers<flt_t,acc_t> *buffers,
                                   const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/dihedral_opls_intel.cpp b/src/USER-INTEL/dihedral_opls_intel.cpp
index 7a60b62cae..5b580cd7d9 100644
--- a/src/USER-INTEL/dihedral_opls_intel.cpp
+++ b/src/USER-INTEL/dihedral_opls_intel.cpp
@@ -77,9 +77,9 @@ void DihedralOPLSIntel::compute(int eflag, int vflag,
                                   IntelBuffers<flt_t,acc_t> *buffers,
                                   const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/improper_cvff_intel.cpp b/src/USER-INTEL/improper_cvff_intel.cpp
index 03bd134b40..f198e47d5c 100644
--- a/src/USER-INTEL/improper_cvff_intel.cpp
+++ b/src/USER-INTEL/improper_cvff_intel.cpp
@@ -83,8 +83,9 @@ void ImproperCvffIntel::compute(int eflag, int vflag,
                                     IntelBuffers<flt_t,acc_t> *buffers,
                                     const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/improper_harmonic_intel.cpp b/src/USER-INTEL/improper_harmonic_intel.cpp
index 167095150e..d638e6a66e 100644
--- a/src/USER-INTEL/improper_harmonic_intel.cpp
+++ b/src/USER-INTEL/improper_harmonic_intel.cpp
@@ -84,8 +84,9 @@ void ImproperHarmonicIntel::compute(int eflag, int vflag,
                                     IntelBuffers<flt_t,acc_t> *buffers,
                                     const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   if (evflag) {
     if (vflag && !eflag) {
diff --git a/src/USER-INTEL/pair_airebo_intel.cpp b/src/USER-INTEL/pair_airebo_intel.cpp
index 198f8798fa..eedf45d75e 100644
--- a/src/USER-INTEL/pair_airebo_intel.cpp
+++ b/src/USER-INTEL/pair_airebo_intel.cpp
@@ -292,8 +292,10 @@ template<class flt_t, class acc_t>
 void PairAIREBOIntel::compute(
     int eflag, int vflag, IntelBuffers<flt_t,acc_t> * buffers
 ) {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
+
   pvector[0] = pvector[1] = pvector[2] = 0.0;
 
   const int inum = list->inum;
diff --git a/src/USER-INTEL/pair_buck_coul_cut_intel.cpp b/src/USER-INTEL/pair_buck_coul_cut_intel.cpp
index f82f4c1c7a..4ad4398fbe 100644
--- a/src/USER-INTEL/pair_buck_coul_cut_intel.cpp
+++ b/src/USER-INTEL/pair_buck_coul_cut_intel.cpp
@@ -73,9 +73,9 @@ void PairBuckCoulCutIntel::compute(int eflag, int vflag,
                                    IntelBuffers<flt_t,acc_t> *buffers,
                                    const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_buck_coul_long_intel.cpp b/src/USER-INTEL/pair_buck_coul_long_intel.cpp
index 059413c3d9..150cfd3ee0 100644
--- a/src/USER-INTEL/pair_buck_coul_long_intel.cpp
+++ b/src/USER-INTEL/pair_buck_coul_long_intel.cpp
@@ -73,9 +73,9 @@ void PairBuckCoulLongIntel::compute(int eflag, int vflag,
                                     IntelBuffers<flt_t,acc_t> *buffers,
                                     const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_buck_intel.cpp b/src/USER-INTEL/pair_buck_intel.cpp
index 0e0bd0f56f..b21ce13a34 100644
--- a/src/USER-INTEL/pair_buck_intel.cpp
+++ b/src/USER-INTEL/pair_buck_intel.cpp
@@ -66,9 +66,9 @@ void PairBuckIntel::compute(int eflag, int vflag,
                             IntelBuffers<flt_t,acc_t> *buffers,
                             const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_dpd_intel.cpp b/src/USER-INTEL/pair_dpd_intel.cpp
index 5d67a60c4b..4ebdce9a96 100644
--- a/src/USER-INTEL/pair_dpd_intel.cpp
+++ b/src/USER-INTEL/pair_dpd_intel.cpp
@@ -82,9 +82,9 @@ void PairDPDIntel::compute(int eflag, int vflag,
                            IntelBuffers<flt_t,acc_t> *buffers,
                            const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_eam_intel.cpp b/src/USER-INTEL/pair_eam_intel.cpp
index 95d0272d33..9d2629ef1c 100644
--- a/src/USER-INTEL/pair_eam_intel.cpp
+++ b/src/USER-INTEL/pair_eam_intel.cpp
@@ -78,9 +78,9 @@ void PairEAMIntel::compute(int eflag, int vflag,
                            IntelBuffers<flt_t,acc_t> *buffers,
                            const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_gayberne_intel.cpp b/src/USER-INTEL/pair_gayberne_intel.cpp
index 51524355d5..862dee2287 100644
--- a/src/USER-INTEL/pair_gayberne_intel.cpp
+++ b/src/USER-INTEL/pair_gayberne_intel.cpp
@@ -72,9 +72,9 @@ void PairGayBerneIntel::compute(int eflag, int vflag,
                                 IntelBuffers<flt_t,acc_t> *buffers,
                                 const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nall = atom->nlocal + atom->nghost;
diff --git a/src/USER-INTEL/pair_lj_charmm_coul_charmm_intel.cpp b/src/USER-INTEL/pair_lj_charmm_coul_charmm_intel.cpp
index 0b6ac3ffa5..f3f81651fc 100644
--- a/src/USER-INTEL/pair_lj_charmm_coul_charmm_intel.cpp
+++ b/src/USER-INTEL/pair_lj_charmm_coul_charmm_intel.cpp
@@ -66,9 +66,9 @@ void PairLJCharmmCoulCharmmIntel::compute(int eflag, int vflag,
                                         IntelBuffers<flt_t,acc_t> *buffers,
                                         const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_lj_charmm_coul_long_intel.cpp b/src/USER-INTEL/pair_lj_charmm_coul_long_intel.cpp
index 753a9afdd9..b4697ad122 100644
--- a/src/USER-INTEL/pair_lj_charmm_coul_long_intel.cpp
+++ b/src/USER-INTEL/pair_lj_charmm_coul_long_intel.cpp
@@ -70,9 +70,9 @@ void PairLJCharmmCoulLongIntel::compute(int eflag, int vflag,
                                         IntelBuffers<flt_t,acc_t> *buffers,
                                         const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_lj_cut_coul_long_intel.cpp b/src/USER-INTEL/pair_lj_cut_coul_long_intel.cpp
index 35ed9061ce..929ac2123f 100644
--- a/src/USER-INTEL/pair_lj_cut_coul_long_intel.cpp
+++ b/src/USER-INTEL/pair_lj_cut_coul_long_intel.cpp
@@ -71,9 +71,9 @@ void PairLJCutCoulLongIntel::compute(int eflag, int vflag,
                                      IntelBuffers<flt_t,acc_t> *buffers,
                                      const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_lj_cut_intel.cpp b/src/USER-INTEL/pair_lj_cut_intel.cpp
index 94133a7f47..39db9c7333 100644
--- a/src/USER-INTEL/pair_lj_cut_intel.cpp
+++ b/src/USER-INTEL/pair_lj_cut_intel.cpp
@@ -62,9 +62,9 @@ void PairLJCutIntel::compute(int eflag, int vflag,
                              IntelBuffers<flt_t,acc_t> *buffers,
                              const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_rebo_intel.cpp b/src/USER-INTEL/pair_rebo_intel.cpp
index 3decc0154b..b7cc3d1c71 100644
--- a/src/USER-INTEL/pair_rebo_intel.cpp
+++ b/src/USER-INTEL/pair_rebo_intel.cpp
@@ -28,7 +28,7 @@ PairREBOIntel::PairREBOIntel(LAMMPS *lmp) : PairAIREBOIntel(lmp) {}
    global settings
 ------------------------------------------------------------------------- */
 
-void PairREBOIntel::settings(int narg, char **/*arg*/)
+void PairREBOIntel::settings(int narg, char ** /* arg */)
 {
   if (narg != 0) error->all(FLERR,"Illegal pair_style command");
 
diff --git a/src/USER-INTEL/pair_sw_intel.cpp b/src/USER-INTEL/pair_sw_intel.cpp
index 9e00516087..1955cd2e6d 100644
--- a/src/USER-INTEL/pair_sw_intel.cpp
+++ b/src/USER-INTEL/pair_sw_intel.cpp
@@ -95,9 +95,9 @@ void PairSWIntel::compute(int eflag, int vflag,
                           IntelBuffers<flt_t,acc_t> *buffers,
                           const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pair_tersoff_intel.cpp b/src/USER-INTEL/pair_tersoff_intel.cpp
index 5d4c5f2cb6..76d06b02dd 100644
--- a/src/USER-INTEL/pair_tersoff_intel.cpp
+++ b/src/USER-INTEL/pair_tersoff_intel.cpp
@@ -107,9 +107,9 @@ void PairTersoffIntel::compute(int eflag, int vflag,
                                      IntelBuffers<flt_t,acc_t> *buffers,
                                      const ForceConst<flt_t> &fc)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+  if (vflag_atom)
+    error->all(FLERR,"USER-INTEL package does not support per-atom stress");
 
   const int inum = list->inum;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-INTEL/pppm_disp_intel.cpp b/src/USER-INTEL/pppm_disp_intel.cpp
index 795fe1a47d..9d075c78a1 100644
--- a/src/USER-INTEL/pppm_disp_intel.cpp
+++ b/src/USER-INTEL/pppm_disp_intel.cpp
@@ -174,9 +174,7 @@ void PPPMDispIntel::compute(int eflag, int vflag)
   int i;
   // convert atoms from box to lamda coords
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/USER-INTEL/pppm_intel.cpp b/src/USER-INTEL/pppm_intel.cpp
index 59455bcf52..e3d1e7d4aa 100644
--- a/src/USER-INTEL/pppm_intel.cpp
+++ b/src/USER-INTEL/pppm_intel.cpp
@@ -161,9 +161,7 @@ void PPPMIntel::compute_first(int eflag, int vflag)
   // set energy/virial flags
   // invoke allocate_peratom() if needed for first time
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   if (evflag_atom && !peratom_allocate_flag) {
     allocate_peratom();
diff --git a/src/USER-MANIFOLD/fix_nve_manifold_rattle.cpp b/src/USER-MANIFOLD/fix_nve_manifold_rattle.cpp
index 794a324f03..de134e32ed 100644
--- a/src/USER-MANIFOLD/fix_nve_manifold_rattle.cpp
+++ b/src/USER-MANIFOLD/fix_nve_manifold_rattle.cpp
@@ -559,7 +559,8 @@ void FixNVEManifoldRattle::rattle_manifold_x(double *x, double *v,
 
   if (iters >= max_iter && res > tolerance) {
     char msg[2048];
-    sprintf(msg,"Failed to constrain atom %d (x = (%f, %f, %f)! res = %e, iters = %d\n",
+    sprintf(msg,"Failed to constrain atom " TAGINT_FORMAT
+            " (x = (%f, %f, %f)! res = %e, iters = %d\n",
             tagi, x[0], x[1], x[2], res, iters);
     error->one(FLERR,msg);
   }
@@ -652,7 +653,8 @@ void FixNVEManifoldRattle::rattle_manifold_v(double *v, double *f,
 
   if (iters >= max_iter && res >= tolerance) {
           char msg[2048];
-          sprintf(msg,"Failed to constrain atom %d (x = (%f, %f, %f)! res = %e, iters = %d\n",
+          sprintf(msg,"Failed to constrain atom " TAGINT_FORMAT
+                  " (x = (%f, %f, %f)! res = %e, iters = %d\n",
                   tagi, x[0], x[1], x[2], res, iters);
           error->all(FLERR,msg);
   }
diff --git a/src/USER-MEAMC/pair_meamc.cpp b/src/USER-MEAMC/pair_meamc.cpp
index b74416a46d..a70fb77aae 100644
--- a/src/USER-MEAMC/pair_meamc.cpp
+++ b/src/USER-MEAMC/pair_meamc.cpp
@@ -93,9 +93,7 @@ void PairMEAMC::compute(int eflag, int vflag)
   int *ilist_half,*numneigh_half,**firstneigh_half;
   int *numneigh_full,**firstneigh_full;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // neighbor list info
 
@@ -228,6 +226,9 @@ void PairMEAMC::coeff(int narg, char **arg)
   }
   nelements = narg - 4 - atom->ntypes;
   if (nelements < 1) error->all(FLERR,"Incorrect args for pair coefficients");
+  if (nelements > maxelt)
+    error->all(FLERR,"Too many elements extracted from MEAM library. "
+                      "Increase 'maxelt' in meam.h and recompile.");
   elements = new char*[nelements];
   mass = new double[nelements];
 
diff --git a/src/USER-MESO/pair_edpd.cpp b/src/USER-MESO/pair_edpd.cpp
index 1f6222944a..e428b02822 100644
--- a/src/USER-MESO/pair_edpd.cpp
+++ b/src/USER-MESO/pair_edpd.cpp
@@ -99,8 +99,7 @@ PairEDPD::~PairEDPD()
 void PairEDPD::compute(int eflag, int vflag)
 {
   double evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/USER-MESO/pair_mdpd.cpp b/src/USER-MESO/pair_mdpd.cpp
index f9acd3dbe1..4102499d46 100644
--- a/src/USER-MESO/pair_mdpd.cpp
+++ b/src/USER-MESO/pair_mdpd.cpp
@@ -88,8 +88,7 @@ void PairMDPD::compute(int eflag, int vflag)
   double rhoi, rhoj;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/USER-MESO/pair_mdpd_rhosum.cpp b/src/USER-MESO/pair_mdpd_rhosum.cpp
index 806a63f898..2fd238088c 100644
--- a/src/USER-MESO/pair_mdpd_rhosum.cpp
+++ b/src/USER-MESO/pair_mdpd_rhosum.cpp
@@ -84,10 +84,7 @@ void PairMDPDRhoSum::compute(int eflag, int vflag) {
   // neighbor list variables
   int inum, *ilist, *numneigh, **firstneigh;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **x = atom->x;
   double *rho = atom->rho;
diff --git a/src/USER-MESO/pair_tdpd.cpp b/src/USER-MESO/pair_tdpd.cpp
index a41282c0d8..7df9d6d163 100644
--- a/src/USER-MESO/pair_tdpd.cpp
+++ b/src/USER-MESO/pair_tdpd.cpp
@@ -91,8 +91,7 @@ PairTDPD::~PairTDPD()
 void PairTDPD::compute(int eflag, int vflag)
 {
   double evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/USER-MGPT/pair_mgpt.cpp b/src/USER-MGPT/pair_mgpt.cpp
index 347bc9cc69..91c624eec5 100644
--- a/src/USER-MGPT/pair_mgpt.cpp
+++ b/src/USER-MGPT/pair_mgpt.cpp
@@ -1673,8 +1673,7 @@ void PairMGPT::compute_x(const int *nnei,const int * const *nlist,
 
 void PairMGPT::compute(int eflag, int vflag)
 {
-  if(eflag || vflag) ev_setup(eflag, vflag);
-  else evflag = vflag_fdotr = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag, vflag);
 
   int newton_pair = force->newton_pair;
   double e_s,e_p,e_t,e_q;
diff --git a/src/USER-MISC/README b/src/USER-MISC/README
index 13e406d42f..9adc817986 100644
--- a/src/USER-MISC/README
+++ b/src/USER-MISC/README
@@ -45,6 +45,7 @@ dihedral_style table/cut, Mike Salerno, ksalerno@pha.jhu.edu, 11 May 18
 fix addtorque, Laurent Joly (U Lyon), ljoly.ulyon at gmail.com, 8 Aug 11
 fix ave/correlate/long, Jorge Ramirez (UPM Madrid), jorge.ramirez at upm.es, 21 Oct 2015
 fix bond/react, Jacob Gissinger (CU Boulder), info at disarmmd.org, 24 Feb 2018
+fix electron/stopping, Konstantin Avchaciov, k.avchachov at gmail.com, 26 Feb 2019
 fix ffl, David Wilkins (EPFL Lausanne), david.wilkins @ epfl.ch, 28 Sep 2018
 fix filter/corotate, Lukas Fath (KIT), lukas.fath at kit.edu, 15 Mar 2017
 fix flow/gauss, Joel Eaves (CU Boulder), Joel.Eaves@Colorado.edu, 23 Aug 2016
@@ -67,14 +68,17 @@ improper_style distance, Paolo Raiteri, p.raiteri at curtin.edu.au, 2 Dec 15
 pair_style agni, Axel Kohlmeyer, akohlmey at gmail.com, 9 Nov 16
 pair_style buck/mdf, Paolo Raiteri, p.raiteri at curtin.edu.au, 2 Dec 15
 pair_style coul/diel, Axel Kohlmeyer, akohlmey at gmail.com, 1 Dec 11
+pair_style coul/shield, Wengen Ouyang (Tel Aviv University), w.g.ouyang at gmail dot com, 30 Mar 18
 pair_style dipole/sf, Mario Orsi, orsimario at gmail.com, 8 Aug 11
 pair_style edip, Luca Ferraro, luca.ferraro at caspur.it, 15 Sep 11
 pair_style extep, Jaap Kroes (Radboud U), jaapkroes at gmail dot com, 28 Nov 17
 pair_style gauss/cut, Axel Kohlmeyer, akohlmey at gmail.com, 1 Dec 11
+pair_style ilp/graphene/hbn, Wengen Ouyang (Tel Aviv University), w.g.ouyang at gmail dot com, 30 Mar 18
 pair_style lebedeva/z, Zbigniew Koziol (National Center for Nuclear Research), softquake at gmail dot com, 4 Jan 19
 pair_style lennard/mdf, Paolo Raiteri, p.raiteri at curtin.edu.au, 2 Dec 15
 pair_style list, Axel Kohlmeyer (Temple U), akohlmey at gmail.com, 1 Jun 13
 pair_style lj/mdf, Paolo Raiteri, p.raiteri at curtin.edu.au, 2 Dec 15
+pair_style kolmogorov/crespi/full, Wengen Ouyang (Tel Aviv University), w.g.ouyang at gmail dot com, 30 Mar 18
 pair_style kolmogorov/crespi/z, Jaap Kroes (Radboud U), jaapkroes at gmail dot com, 28 Feb 17
 pair_style meam/spline, Alexander Stukowski (LLNL), alex at stukowski.com, 1 Feb 12
 pair_style meam/sw/spline, Robert Rudd (LLNL), robert.rudd at llnl.gov, 1 Oct 12
diff --git a/src/USER-MISC/angle_cosine_shift.cpp b/src/USER-MISC/angle_cosine_shift.cpp
index a361db4970..18c87c81e3 100644
--- a/src/USER-MISC/angle_cosine_shift.cpp
+++ b/src/USER-MISC/angle_cosine_shift.cpp
@@ -62,8 +62,7 @@ void AngleCosineShift::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,s,cps,kcos,ksin,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/angle_cosine_shift_exp.cpp b/src/USER-MISC/angle_cosine_shift_exp.cpp
index c87c73171a..8c6282de20 100644
--- a/src/USER-MISC/angle_cosine_shift_exp.cpp
+++ b/src/USER-MISC/angle_cosine_shift_exp.cpp
@@ -72,8 +72,7 @@ void AngleCosineShiftExp::compute(int eflag, int vflag)
   double exp2,aa,uumin,cccpsss,cssmscc;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/angle_dipole.cpp b/src/USER-MISC/angle_dipole.cpp
index c4186da472..781da46869 100644
--- a/src/USER-MISC/angle_dipole.cpp
+++ b/src/USER-MISC/angle_dipole.cpp
@@ -59,8 +59,7 @@ void AngleDipole::compute(int eflag, int vflag)
   double r,cosGamma,deltaGamma,kdg,rmu;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x; // position vector
   double **mu = atom->mu; // point-dipole components and moment magnitude
diff --git a/src/USER-MISC/angle_fourier.cpp b/src/USER-MISC/angle_fourier.cpp
index e6cc1f1a7e..8f5074ff5d 100644
--- a/src/USER-MISC/angle_fourier.cpp
+++ b/src/USER-MISC/angle_fourier.cpp
@@ -67,8 +67,7 @@ void AngleFourier::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,c2,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/angle_fourier_simple.cpp b/src/USER-MISC/angle_fourier_simple.cpp
index 8464fe815c..615556bbe7 100644
--- a/src/USER-MISC/angle_fourier_simple.cpp
+++ b/src/USER-MISC/angle_fourier_simple.cpp
@@ -65,8 +65,7 @@ void AngleFourierSimple::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,cn,th,nth,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/angle_quartic.cpp b/src/USER-MISC/angle_quartic.cpp
index 356f2df5d4..21a96100aa 100644
--- a/src/USER-MISC/angle_quartic.cpp
+++ b/src/USER-MISC/angle_quartic.cpp
@@ -61,8 +61,7 @@ void AngleQuartic::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/bond_harmonic_shift.cpp b/src/USER-MISC/bond_harmonic_shift.cpp
index b34f71e888..c7e4444cce 100644
--- a/src/USER-MISC/bond_harmonic_shift.cpp
+++ b/src/USER-MISC/bond_harmonic_shift.cpp
@@ -53,8 +53,7 @@ void BondHarmonicShift::compute(int eflag, int vflag)
   double rsq,r,dr,rk;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/bond_harmonic_shift_cut.cpp b/src/USER-MISC/bond_harmonic_shift_cut.cpp
index a58df70878..5b396f5d72 100644
--- a/src/USER-MISC/bond_harmonic_shift_cut.cpp
+++ b/src/USER-MISC/bond_harmonic_shift_cut.cpp
@@ -53,8 +53,7 @@ void BondHarmonicShiftCut::compute(int eflag, int vflag)
   double rsq,r,dr,rk;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/compute_pressure_cylinder.cpp b/src/USER-MISC/compute_pressure_cylinder.cpp
index 6fcd343e38..c250eaf677 100644
--- a/src/USER-MISC/compute_pressure_cylinder.cpp
+++ b/src/USER-MISC/compute_pressure_cylinder.cpp
@@ -63,7 +63,7 @@ ComputePressureCyl::ComputePressureCyl(LAMMPS *lmp, int narg, char **arg) :
   Rmax=force->numeric(FLERR,arg[5]);
   bin_width=force->numeric(FLERR,arg[6]);
 
-  if ((bin_width <= 0.0) || (bin_width < Rmax))
+  if ((bin_width <= 0.0) || (bin_width > Rmax))
     error->all(FLERR,"Illegal compute pressure/cylinder command");
   if ((zhi < zlo) || ((zhi-zlo) < bin_width))
     error->all(FLERR,"Illegal compute pressure/cylinder command");
@@ -76,7 +76,7 @@ ComputePressureCyl::ComputePressureCyl(LAMMPS *lmp, int narg, char **arg) :
   // NOTE: at 2^22 = 4.2M bins, we will be close to exhausting allocatable
   // memory on a 32-bit environment. so we use this as an upper limit.
 
-  if ((nbins < 1) || (nzbins < 1) || (nbins > 2>>22) || (nbins > 2>>22))
+  if ((nbins < 1) || (nzbins < 1) || (nbins > 2<<22) || (nzbins > 2<<22))
     error->all(FLERR,"Illegal compute pressure/cylinder command");
 
   array_flag=1;
diff --git a/src/USER-MISC/dihedral_cosine_shift_exp.cpp b/src/USER-MISC/dihedral_cosine_shift_exp.cpp
index 82da173f8e..c411ea8150 100644
--- a/src/USER-MISC/dihedral_cosine_shift_exp.cpp
+++ b/src/USER-MISC/dihedral_cosine_shift_exp.cpp
@@ -36,7 +36,10 @@ using namespace LAMMPS_NS;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralCosineShiftExp::DihedralCosineShiftExp(LAMMPS *lmp) : Dihedral(lmp) {}
+DihedralCosineShiftExp::DihedralCosineShiftExp(LAMMPS *lmp) : Dihedral(lmp)
+{
+  writedata = 1;
+}
 
 /* ---------------------------------------------------------------------- */
 
@@ -68,8 +71,7 @@ void DihedralCosineShiftExp::compute(int eflag, int vflag)
   double cccpsss,cssmscc,exp2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/dihedral_fourier.cpp b/src/USER-MISC/dihedral_fourier.cpp
index 7c405ee28c..af86259c01 100644
--- a/src/USER-MISC/dihedral_fourier.cpp
+++ b/src/USER-MISC/dihedral_fourier.cpp
@@ -79,8 +79,7 @@ void DihedralFourier::compute(int eflag, int vflag)
   double dtfx,dtfy,dtfz,dtgx,dtgy,dtgz,dthx,dthy,dthz;
   double c,s,p_,sx2,sy2,sz2;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/dihedral_nharmonic.cpp b/src/USER-MISC/dihedral_nharmonic.cpp
index f8e8850680..ea2b76f415 100644
--- a/src/USER-MISC/dihedral_nharmonic.cpp
+++ b/src/USER-MISC/dihedral_nharmonic.cpp
@@ -35,7 +35,8 @@ using namespace LAMMPS_NS;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralNHarmonic::DihedralNHarmonic(LAMMPS *lmp) : Dihedral(lmp) {
+DihedralNHarmonic::DihedralNHarmonic(LAMMPS *lmp) : Dihedral(lmp)
+{
   writedata = 1;
 }
 
@@ -66,8 +67,7 @@ void DihedralNHarmonic::compute(int eflag, int vflag)
   double s2,sin2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/dihedral_quadratic.cpp b/src/USER-MISC/dihedral_quadratic.cpp
index 1b64b52faf..8436e73c5c 100644
--- a/src/USER-MISC/dihedral_quadratic.cpp
+++ b/src/USER-MISC/dihedral_quadratic.cpp
@@ -38,7 +38,10 @@ using namespace MathConst;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralQuadratic::DihedralQuadratic(LAMMPS *lmp) : Dihedral(lmp) {}
+DihedralQuadratic::DihedralQuadratic(LAMMPS *lmp) : Dihedral(lmp)
+{
+  writedata = 1;
+}
 
 /* ---------------------------------------------------------------------- */
 
@@ -65,8 +68,7 @@ void DihedralQuadratic::compute(int eflag, int vflag)
   double s2,cx,cy,cz,cmag,dx,phi,si,siinv,sin2;
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/dihedral_spherical.cpp b/src/USER-MISC/dihedral_spherical.cpp
index 77fa885b7a..3b30121551 100644
--- a/src/USER-MISC/dihedral_spherical.cpp
+++ b/src/USER-MISC/dihedral_spherical.cpp
@@ -41,7 +41,10 @@ using namespace MathExtra;
 
 /* ---------------------------------------------------------------------- */
 
-DihedralSpherical::DihedralSpherical(LAMMPS *lmp) : Dihedral(lmp) {}
+DihedralSpherical::DihedralSpherical(LAMMPS *lmp) : Dihedral(lmp)
+{
+  writedata = 1;
+}
 
 /* ---------------------------------------------------------------------- */
 
@@ -213,8 +216,7 @@ void DihedralSpherical::compute(int eflag, int vflag)
   //    perp34on23[d] = v34[d] - proj34on23[d]
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
 
   for (n = 0; n < ndihedrallist; n++) {
@@ -817,10 +819,11 @@ void DihedralSpherical::write_data(FILE *fp)
   for (int i = 1; i <= atom->ndihedraltypes; i++) {
     fprintf(fp,"%d %d ", i , nterms[i]);
     for (int j = 0; j < nterms[i]; j++) {
-      fprintf(fp, "%g %g %g %g %g %g %g %g %g ",
-              phi_mult[i][j],    phi_shift[i][j],    phi_offset[i][j],
-              theta1_mult[i][j], theta1_shift[i][j], theta1_offset[i][j],
-              theta2_mult[i][j], theta2_shift[i][j], theta2_offset[i][j]);
+      fprintf(fp, "%g %g %g %g %g %g %g %g %g %g ", Ccoeff[i][j],
+              phi_mult[i][j], phi_shift[i][j]*180.0/MY_PI, phi_offset[i][j],
+              theta1_mult[i][j], theta1_shift[i][j]*180.0/MY_PI,
+              theta1_offset[i][j], theta2_mult[i][j],
+              theta2_shift[i][j]*180.0/MY_PI, theta2_offset[i][j]);
     }
     fprintf(fp,"\n");
   }
diff --git a/src/USER-MISC/dihedral_table.cpp b/src/USER-MISC/dihedral_table.cpp
index e221a54a82..a97ae3649f 100644
--- a/src/USER-MISC/dihedral_table.cpp
+++ b/src/USER-MISC/dihedral_table.cpp
@@ -549,8 +549,7 @@ void DihedralTable::compute(int eflag, int vflag)
 
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
 
   for (n = 0; n < ndihedrallist; n++) {
diff --git a/src/USER-MISC/dihedral_table_cut.cpp b/src/USER-MISC/dihedral_table_cut.cpp
index 6ebe094e50..18a645cd75 100644
--- a/src/USER-MISC/dihedral_table_cut.cpp
+++ b/src/USER-MISC/dihedral_table_cut.cpp
@@ -425,17 +425,6 @@ DihedralTableCut::DihedralTableCut(LAMMPS *lmp) : Dihedral(lmp)
 DihedralTableCut::~DihedralTableCut()
 {
   if (allocated) {
-    memory->destroy(setflag);
-    memory->destroy(setflag_d);
-    memory->destroy(setflag_aat);
-
-    memory->destroy(k1);
-    memory->destroy(k2);
-    memory->destroy(k3);
-    memory->destroy(phi1);
-    memory->destroy(phi2);
-    memory->destroy(phi3);
-
     memory->destroy(aat_k);
     memory->destroy(aat_theta0_1);
     memory->destroy(aat_theta0_2);
@@ -472,8 +461,7 @@ void DihedralTableCut::compute(int eflag, int vflag)
   double fabcd[4][3];
 
   edihedral = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -761,27 +749,15 @@ void DihedralTableCut::allocate()
   allocated = 1;
   int n = atom->ndihedraltypes;
 
-  memory->create(k1,n+1,"dihedral:k1");
-  memory->create(k2,n+1,"dihedral:k2");
-  memory->create(k3,n+1,"dihedral:k3");
-  memory->create(phi1,n+1,"dihedral:phi1");
-  memory->create(phi2,n+1,"dihedral:phi2");
-  memory->create(phi3,n+1,"dihedral:phi3");
-
   memory->create(aat_k,n+1,"dihedral:aat_k");
   memory->create(aat_theta0_1,n+1,"dihedral:aat_theta0_1");
   memory->create(aat_theta0_2,n+1,"dihedral:aat_theta0_2");
 
-  memory->create(setflag,n+1,"dihedral:setflag");
-  memory->create(setflag_d,n+1,"dihedral:setflag_d");
-  memory->create(setflag_aat,n+1,"dihedral:setflag_aat");
-
   memory->create(tabindex,n+1,"dihedral:tabindex");
-  //memory->create(phi0,n+1,"dihedral:phi0"); <-equilibrium angles not supported
   memory->create(setflag,n+1,"dihedral:setflag");
 
   for (int i = 1; i <= n; i++)
-    setflag[i] = setflag_d[i] = setflag_aat[i] = 0;
+    setflag[i] = 0;
 }
 
 void DihedralTableCut::settings(int narg, char **arg)
@@ -824,9 +800,6 @@ void DihedralTableCut::coeff(int narg, char **arg)
   int ilo,ihi;
   force->bounds(FLERR,arg[0],atom->ndihedraltypes,ilo,ihi);
 
-  int count = 0;
-
-
   double k_one = force->numeric(FLERR,arg[2]);
   double theta0_1_one = force->numeric(FLERR,arg[3]);
   double theta0_2_one = force->numeric(FLERR,arg[4]);
@@ -837,8 +810,6 @@ void DihedralTableCut::coeff(int narg, char **arg)
     aat_k[i] = k_one;
     aat_theta0_1[i] = theta0_1_one/180.0 * MY_PI;
     aat_theta0_2[i] = theta0_2_one/180.0 * MY_PI;
-    setflag_aat[i] = 1;
-    count++;
   }
 
   int me;
@@ -998,8 +969,7 @@ void DihedralTableCut::coeff(int narg, char **arg)
             //  To be nice and report something, I do the same thing here.)
             cyc_splintD(tb->phi, tb->e, tb->e2, tablength, MY_2PI,phi);
           f = -dU_dphi;
-        }
-        else
+        } else
           // Otherwise we calculated the tb->f[] array.  Report its contents.
           f = tb->f[i];
         if (tb->use_degrees) {
@@ -1015,9 +985,8 @@ void DihedralTableCut::coeff(int narg, char **arg)
   } // if (me == 0)
 
   // store ptr to table in tabindex
-  count = 0;
-  for (int i = ilo; i <= ihi; i++)
-  {
+  int count = 0;
+  for (int i = ilo; i <= ihi; i++) {
     tabindex[i] = ntables;
     //phi0[i] = tb->phi0; <- equilibrium dihedral angles not supported
     setflag[i] = 1;
@@ -1025,12 +994,7 @@ void DihedralTableCut::coeff(int narg, char **arg)
   }
   ntables++;
 
-
   if (count == 0) error->all(FLERR,"Incorrect args for dihedral coefficients");
-
-  for (int i = ilo; i <= ihi; i++)
-    if (setflag_d[i] == 1 && setflag_aat[i] == 1 )
-      setflag[i] = 1;
 }
 
 /* ----------------------------------------------------------------------
@@ -1041,16 +1005,6 @@ void DihedralTableCut::write_restart(FILE *fp)
 {
   fwrite(&tabstyle,sizeof(int),1,fp);
   fwrite(&tablength,sizeof(int),1,fp);
-  fwrite(&k1[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&k2[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&k3[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&phi1[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&phi2[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&phi3[1],sizeof(double),atom->ndihedraltypes,fp);
-
-  fwrite(&aat_k[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&aat_theta0_1[1],sizeof(double),atom->ndihedraltypes,fp);
-  fwrite(&aat_theta0_2[1],sizeof(double),atom->ndihedraltypes,fp);
 }
 
 /* ----------------------------------------------------------------------
@@ -1064,33 +1018,10 @@ void DihedralTableCut::read_restart(FILE *fp)
   if (comm->me == 0) {
     fread(&tabstyle,sizeof(int),1,fp);
     fread(&tablength,sizeof(int),1,fp);
-    fread(&k1[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&k2[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&k3[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&phi1[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&phi2[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&phi3[1],sizeof(double),atom->ndihedraltypes,fp);
-
-    fread(&aat_k[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&aat_theta0_1[1],sizeof(double),atom->ndihedraltypes,fp);
-    fread(&aat_theta0_2[1],sizeof(double),atom->ndihedraltypes,fp);
   }
 
-  MPI_Bcast(&k1[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&k2[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&k3[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&phi1[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&phi2[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&phi3[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-
-  MPI_Bcast(&aat_k[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&aat_theta0_1[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
-  MPI_Bcast(&aat_theta0_2[1],atom->ndihedraltypes,MPI_DOUBLE,0,world);
   MPI_Bcast(&tabstyle,1,MPI_INT,0,world);
   MPI_Bcast(&tablength,1,MPI_INT,0,world);
-
-  allocate();
-  for (int i = 1; i <= atom->ndihedraltypes; i++) setflag[i] = 1;
 }
 
 /* ---------------------------------------------------------------------- */
@@ -1474,22 +1405,3 @@ void DihedralTableCut::bcast_table(Table *tb)
 }
 
 
-
-/* ----------------------------------------------------------------------
-   proc 0 writes to data file
-------------------------------------------------------------------------- */
-
-void DihedralTableCut::write_data(FILE *fp)
-{
-  for (int i = 1; i <= atom->ndihedraltypes; i++)
-    fprintf(fp,"%d %g %g %g %g %g %g\n",i,
-            k1[i],phi1[i]*180.0/MY_PI,
-            k2[i],phi2[i]*180.0/MY_PI,
-            k3[i],phi3[i]*180.0/MY_PI);
-
-  fprintf(fp,"\nAngleAngleTorsion Coeffs\n\n");
-  for (int i = 1; i <= atom->ndihedraltypes; i++)
-    fprintf(fp,"%d %g %g %g\n",i,aat_k[i],
-            aat_theta0_1[i]*180.0/MY_PI,aat_theta0_2[i]*180.0/MY_PI);
-
-}
diff --git a/src/USER-MISC/dihedral_table_cut.h b/src/USER-MISC/dihedral_table_cut.h
index d01903c88b..dd645bedda 100644
--- a/src/USER-MISC/dihedral_table_cut.h
+++ b/src/USER-MISC/dihedral_table_cut.h
@@ -20,7 +20,6 @@ DihedralStyle(table/cut,DihedralTableCut)
 #ifndef LMP_DIHEDRAL_TABLE_CUT_H
 #define LMP_DIHEDRAL_TABLE_CUT_H
 
-#include <stdio.h>
 #include "dihedral.h"
 
 namespace LAMMPS_NS {
@@ -34,26 +33,18 @@ class DihedralTableCut : public Dihedral {
   void coeff(int, char **);
   void write_restart(FILE *);
   void read_restart(FILE *);
-  void write_data(FILE *);
-  double single(int type, int i1, int i2, int i3, int i4);
 
  protected:
-  double *k1,*k2,*k3;
-  double *phi1,*phi2,*phi3;
   double *aat_k,*aat_theta0_1,*aat_theta0_2;
-  int *setflag_d;
-  int *setflag_aat;
 
   void allocate();
 
   int tabstyle,tablength;
-  // double *phi0;       <- equilibrium angles not supported
   char *checkU_fname;
   char *checkF_fname;
 
   struct Table {
     int ninput;
-    //double phi0;      <-equilibrium angles not supported
     int f_unspecified; // boolean (but MPI does not like type "bool")
     int use_degrees;   // boolean (but MPI does not like type "bool")
     double *phifile,*efile,*ffile;
diff --git a/src/USER-MISC/fix_bond_react.cpp b/src/USER-MISC/fix_bond_react.cpp
index c5df3ed438..5d624ad7f4 100644
--- a/src/USER-MISC/fix_bond_react.cpp
+++ b/src/USER-MISC/fix_bond_react.cpp
@@ -457,8 +457,6 @@ FixBondReact::~FixBondReact()
   memory->destroy(global_mega_glove);
 
   if (stabilization_flag == 1) {
-    delete [] exclude_group;
-
     // check nfix in case all fixes have already been deleted
     if (id_fix1 && modify->nfix) modify->delete_fix(id_fix1);
     delete [] id_fix1;
@@ -473,6 +471,18 @@ FixBondReact::~FixBondReact()
   delete [] statted_id;
   delete [] guess_branch;
   delete [] pioneer_count;
+
+  char **newarg;
+  newarg = new char*[2];
+  newarg[0] = master_group;
+  newarg[1] = (char *) "delete";
+  group->assign(2,newarg);
+  if (stabilization_flag == 1) {
+    newarg[0] = exclude_group;
+    group->assign(2,newarg);
+    delete [] exclude_group;
+  }
+  delete [] newarg;
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/USER-MISC/fix_electron_stopping.cpp b/src/USER-MISC/fix_electron_stopping.cpp
new file mode 100644
index 0000000000..0831ebcf89
--- /dev/null
+++ b/src/USER-MISC/fix_electron_stopping.cpp
@@ -0,0 +1,303 @@
+/* ----------------------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+/* ----------------------------------------------------------------------
+   Electronic stopping power
+   Contributing authors: K. Avchaciov and T. Metspalu
+   Information: k.avchachov@gmail.com
+------------------------------------------------------------------------- */
+
+#include <cmath>
+#include <cstdio>
+#include <cstring>
+#include "fix_electron_stopping.h"
+#include "mpi.h"
+#include "atom.h"
+#include "update.h"
+#include "domain.h"
+#include "region.h"
+#include "group.h"
+#include "force.h"
+#include "fix.h"
+#include "memory.h"
+#include "comm.h"
+#include "error.h"
+#include "neighbor.h"
+#include "neigh_list.h"
+#include "neigh_request.h"
+
+using namespace LAMMPS_NS;
+using namespace FixConst;
+
+#define MAXLINE 1024
+
+/* ---------------------------------------------------------------------- */
+
+FixElectronStopping::FixElectronStopping(LAMMPS *lmp, int narg, char **arg) :
+  Fix(lmp, narg, arg)
+{
+  scalar_flag = 1;  // Has compute_scalar
+  global_freq = 1;  // SeLoss computed every step
+  extscalar = 0;    // SeLoss compute_scalar is intensive
+  nevery = 1;       // Run fix every step
+
+
+  // args: 0 = fix ID, 1 = group ID,  2 = "electron/stopping"
+  //       3 = Ecut,   4 = file path
+  // optional rest: "region" <region name>
+  //                "minneigh" <min number of neighbors>
+
+  if (narg < 5) error->all(FLERR,
+      "Illegal fix electron/stopping command: too few arguments");
+
+  Ecut = force->numeric(FLERR, arg[3]);
+  if (Ecut <= 0.0) error->all(FLERR,
+      "Illegal fix electron/stopping command: Ecut <= 0");
+
+  int iarg = 5;
+  iregion = -1;
+  minneigh = 1;
+  bool minneighflag = false;
+
+  while (iarg < narg) {
+    if (strcmp(arg[iarg], "region") == 0) {
+      if (iregion >= 0) error->all(FLERR,
+          "Illegal fix electron/stopping command: region given twice");
+      if (iarg+2 > narg) error->all(FLERR,
+          "Illegal fix electron/stopping command: region name missing");
+      iregion = domain->find_region(arg[iarg+1]);
+      if (iregion < 0) error->all(FLERR,
+          "Region ID for fix electron/stopping does not exist");
+      iarg += 2;
+    }
+    else if (strcmp(arg[iarg], "minneigh") == 0) {
+      if (minneighflag) error->all(FLERR,
+          "Illegal fix electron/stopping command: minneigh given twice");
+      minneighflag = true;
+      if (iarg+2 > narg) error->all(FLERR,
+          "Illegal fix electron/stopping command: minneigh number missing");
+      minneigh = force->inumeric(FLERR, arg[iarg+1]);
+      if (minneigh < 0) error->all(FLERR,
+          "Illegal fix electron/stopping command: minneigh < 0");
+      iarg += 2;
+    }
+    else error->all(FLERR,
+        "Illegal fix electron/stopping command: unknown argument");
+  }
+
+
+  // Read the input file for energy ranges and stopping powers.
+  // First proc 0 reads the file, then bcast to others.
+  const int ncol = atom->ntypes + 1;
+  if (comm->me == 0) {
+    maxlines = 300;
+    memory->create(elstop_ranges, ncol, maxlines, "electron/stopping:table");
+    read_table(arg[4]);
+  }
+
+  MPI_Bcast(&maxlines, 1 , MPI_INT, 0, world);
+  MPI_Bcast(&table_entries, 1 , MPI_INT, 0, world);
+
+  if (comm->me != 0)
+    memory->create(elstop_ranges, ncol, maxlines, "electron/stopping:table");
+
+  MPI_Bcast(&elstop_ranges[0][0], ncol*maxlines, MPI_DOUBLE, 0, world);
+}
+
+/* ---------------------------------------------------------------------- */
+
+FixElectronStopping::~FixElectronStopping()
+{
+  memory->destroy(elstop_ranges);
+}
+
+/* ---------------------------------------------------------------------- */
+
+int FixElectronStopping::setmask()
+{
+  int mask = 0;
+  mask |= POST_FORCE;
+  return mask;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixElectronStopping::init()
+{
+  SeLoss_sync_flag = 0;
+  SeLoss = 0.0;
+
+  // need an occasional full neighbor list
+  int irequest = neighbor->request(this, instance_me);
+  neighbor->requests[irequest]->pair = 0;
+  neighbor->requests[irequest]->fix = 1;
+  neighbor->requests[irequest]->half = 0;
+  neighbor->requests[irequest]->full = 1;
+  neighbor->requests[irequest]->occasional = 1;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixElectronStopping::init_list(int /*id*/, NeighList *ptr)
+{
+  list = ptr;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixElectronStopping::post_force(int /*vflag*/)
+{
+  SeLoss_sync_flag = 0;
+
+  double **x = atom->x;
+  double **v = atom->v;
+  double **f = atom->f;
+  double dt = update->dt;
+
+  int *type = atom->type;
+  int *mask = atom->mask;
+  int nlocal = atom->nlocal;
+
+  neighbor->build_one(list);
+  int *numneigh = list->numneigh;
+
+  for (int i = 0; i < nlocal; ++i) {
+
+    // Do fast checks first, only then the region check
+    if (!(mask[i] & groupbit)) continue;
+
+    // Avoid atoms outside bulk material
+    if (numneigh[i] < minneigh) continue;
+
+    int itype = type[i];
+    double massone = (atom->rmass) ? atom->rmass[i] : atom->mass[itype];
+    double v2 = v[i][0]*v[i][0] + v[i][1]*v[i][1] + v[i][2]*v[i][2];
+    double energy = 0.5 * force->mvv2e * massone * v2;
+
+    if (energy < Ecut) continue;
+    if (energy < elstop_ranges[0][0]) continue;
+    if (energy > elstop_ranges[0][table_entries - 1]) error->one(FLERR,
+          "Atom kinetic energy too high for fix electron/stopping");
+
+    if (iregion >= 0) {
+      // Only apply in the given region
+      if (domain->regions[iregion]->match(x[i][0], x[i][1], x[i][2]) != 1)
+        continue;
+    }
+
+    // Binary search to find correct energy range
+    int iup = table_entries - 1;
+    int idown = 0;
+    while (true) {
+      int ihalf = idown + (iup - idown) / 2;
+      if (ihalf == idown) break;
+      if (elstop_ranges[0][ihalf] < energy) idown = ihalf;
+      else iup = ihalf;
+    }
+
+    double Se_lo = elstop_ranges[itype][idown];
+    double Se_hi = elstop_ranges[itype][iup];
+    double E_lo = elstop_ranges[0][idown];
+    double E_hi = elstop_ranges[0][iup];
+
+    // Get electronic stopping with a simple linear interpolation
+    double Se = (Se_hi - Se_lo) / (E_hi - E_lo) * (energy - E_lo) + Se_lo;
+
+    double vabs = sqrt(v2);
+    double factor = -Se / vabs;
+
+    f[i][0] += v[i][0] * factor;
+    f[i][1] += v[i][1] * factor;
+    f[i][2] += v[i][2] * factor;
+
+    SeLoss += Se * vabs * dt; // very rough approx
+  }
+}
+
+/* ---------------------------------------------------------------------- */
+
+double FixElectronStopping::compute_scalar()
+{
+  // only sum across procs when changed since last call
+
+  if (SeLoss_sync_flag == 0) {
+    MPI_Allreduce(&SeLoss, &SeLoss_all, 1, MPI_DOUBLE, MPI_SUM, world);
+    SeLoss_sync_flag = 1;
+  }
+  return SeLoss_all;
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixElectronStopping::read_table(const char *file)
+{
+  char line[MAXLINE];
+
+  FILE *fp = force->open_potential(file);
+  if (fp == NULL) {
+    char str[128];
+    snprintf(str, 128, "Cannot open stopping range table %s", file);
+    error->one(FLERR, str);
+  }
+
+  const int ncol = atom->ntypes + 1;
+
+  int l = 0;
+  while (true) {
+    if (fgets(line, MAXLINE, fp) == NULL) break; // end of file
+    if (line[0] == '#') continue; // comment
+
+    char *pch = strtok(line, " \t\n\r");
+    if (pch == NULL) continue; // blank line
+
+    if (l >= maxlines) grow_table();
+
+    int i = 0;
+    for ( ; i < ncol && pch != NULL; i++) {
+      elstop_ranges[i][l] = force->numeric(FLERR, pch);
+      pch = strtok(NULL, " \t\n\r");
+    }
+
+    if (i != ncol || pch != NULL) // too short or too long
+      error->one(FLERR, "fix electron/stopping: Invalid table line");
+
+    if (l >= 1 && elstop_ranges[0][l] <= elstop_ranges[0][l-1])
+      error->one(FLERR,
+          "fix electron/stopping: Energies must be in ascending order");
+
+    l++;
+  }
+  table_entries = l;
+
+  if (table_entries == 0)
+    error->one(FLERR, "Did not find any data in electron/stopping table file");
+
+  fclose(fp);
+}
+
+/* ---------------------------------------------------------------------- */
+
+void FixElectronStopping::grow_table()
+{
+  const int ncol = atom->ntypes + 1;
+  int new_maxlines = 2 * maxlines;
+
+  double **new_array;
+  memory->create(new_array, ncol, new_maxlines, "electron/stopping:table");
+
+  for (int i = 0; i < ncol; i++)
+    memcpy(new_array[i], elstop_ranges[i], maxlines*sizeof(double));
+
+  memory->destroy(elstop_ranges);
+  elstop_ranges = new_array;
+  maxlines = new_maxlines;
+}
diff --git a/src/USER-MISC/fix_electron_stopping.h b/src/USER-MISC/fix_electron_stopping.h
new file mode 100644
index 0000000000..f0f47698c6
--- /dev/null
+++ b/src/USER-MISC/fix_electron_stopping.h
@@ -0,0 +1,105 @@
+/* -*- c++ -*- ----------------------------------------------------------
+   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
+   http://lammps.sandia.gov, Sandia National Laboratories
+   Steve Plimpton, sjplimp@sandia.gov
+
+   Copyright (2003) Sandia Corporation.  Under the terms of Contract
+   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
+   certain rights in this software.  This software is distributed under
+   the GNU General Public License.
+
+   See the README file in the top-level LAMMPS directory.
+------------------------------------------------------------------------- */
+/* ----------------------------------------------------------------------
+   Electronic stopping power
+   Contributing authors: K. Avchaciov and T. Metspalu
+   Information: k.avchachov@gmail.com
+------------------------------------------------------------------------- */
+
+#ifdef FIX_CLASS
+
+FixStyle(electron/stopping,FixElectronStopping)
+
+#else
+
+#ifndef LMP_FIX_ELECTRON_STOPPING_H
+#define LMP_FIX_ELECTRON_STOPPING_H
+
+#include "fix.h"
+
+
+namespace LAMMPS_NS {
+
+class FixElectronStopping : public Fix {
+ public:
+  FixElectronStopping(class LAMMPS *, int, char **);
+  ~FixElectronStopping();
+  int setmask();
+  void init();
+  void post_force(int);
+  void init_list(int, class NeighList *);
+  double compute_scalar();
+
+ private:
+  void read_table(const char *);
+  void grow_table();
+
+  double Ecut;               // cutoff energy
+  double SeLoss, SeLoss_all; // electronic energy loss
+  int SeLoss_sync_flag;      // sync done since last change?
+
+  int maxlines;           // max number of lines in table
+  int table_entries;      // number of table entries actually read
+  double **elstop_ranges; // [ 0][i]: energies
+                          // [>0][i]: stopping powers per type
+
+  int iregion; // region index if used, else -1
+  int minneigh; // minimum number of neighbors
+
+  class NeighList *list;
+};
+
+}
+
+#endif
+#endif
+
+/* ERROR/WARNING messages:
+
+E: Illegal ... command
+
+Self-explanatory.  Check the input script syntax and compare to the
+documentation for the command.  You can use -echo screen as a
+command-line option when running LAMMPS to see the offending line.
+
+E: Region ID for fix electron/stopping does not exist
+
+Self-explanatory.
+
+E: Atom kinetic energy too high for fix electron/stopping
+
+The group given in the fix electron/stopping command includes an atom
+that has a kinetic energy higher than the largest energy in the stopping
+table. Reconsider whether the table is physically applicable to your system.
+
+E: Cannot open stopping range table ...
+
+The file containing the electronic stopping table could not be opened.
+Check the given path and the file's permissions.
+
+E: fix electron/stopping: Invalid table line
+
+A line in the stopping table file contained too many or too few columns.
+
+E: fix electron/stopping: Energies must be in ascending order
+
+The first column in the stopping table must be sorted from the smallest
+energy to the largest.
+
+E: Did not find any data in electronic stopping table file
+
+Parsing the stopping table file produced no lines that were identifiable
+as energies/stopping powers. Most likely the file is empty or contains
+only comments.
+
+*/
diff --git a/src/USER-MISC/fix_pimd.cpp b/src/USER-MISC/fix_pimd.cpp
index eba8ed5d0c..3929d47d6b 100644
--- a/src/USER-MISC/fix_pimd.cpp
+++ b/src/USER-MISC/fix_pimd.cpp
@@ -637,14 +637,14 @@ void FixPIMD::comm_exec(double **ptr)
     if(nsend > max_nsend)
     {
       max_nsend = nsend+200;
-      tag_send = (int*) memory->srealloc(tag_send, sizeof(int)*max_nsend, "FixPIMD:tag_send");
+      tag_send = (tagint*) memory->srealloc(tag_send, sizeof(tagint)*max_nsend, "FixPIMD:tag_send");
       buf_send = (double*) memory->srealloc(buf_send, sizeof(double)*max_nsend*3, "FixPIMD:x_send");
     }
 
     // send tags
 
-    MPI_Sendrecv( atom->tag, nlocal, MPI_INT, plan_send[iplan], 0,
-                  tag_send,  nsend,  MPI_INT, plan_recv[iplan], 0, universe->uworld, MPI_STATUS_IGNORE);
+    MPI_Sendrecv( atom->tag, nlocal, MPI_LMP_TAGINT, plan_send[iplan], 0,
+                  tag_send,  nsend,  MPI_LMP_TAGINT, plan_recv[iplan], 0, universe->uworld, MPI_STATUS_IGNORE);
 
     // wrap positions
 
@@ -661,7 +661,7 @@ void FixPIMD::comm_exec(double **ptr)
 
         sprintf(error_line, "Atom " TAGINT_FORMAT " is missing at world [%d] "
                 "rank [%d] required by  rank [%d] (" TAGINT_FORMAT ", "
-                TAGINT_FORMAT ", " TAGINT_FORMAT ").\n",tag_send[i],
+                TAGINT_FORMAT ", " TAGINT_FORMAT ").\n", tag_send[i],
                 universe->iworld, comm->me, plan_recv[iplan],
                 atom->tag[0], atom->tag[1], atom->tag[2]);
 
diff --git a/src/USER-MISC/fix_pimd.h b/src/USER-MISC/fix_pimd.h
index 411fa42c81..c298af0b69 100644
--- a/src/USER-MISC/fix_pimd.h
+++ b/src/USER-MISC/fix_pimd.h
@@ -68,7 +68,7 @@ class FixPIMD : public Fix {
   /* inter-partition communication */
 
   int max_nsend;
-  int* tag_send;
+  tagint* tag_send;
   double *buf_send;
 
   int max_nlocal;
diff --git a/src/USER-MISC/improper_cossq.cpp b/src/USER-MISC/improper_cossq.cpp
index 2483840e42..c8eb0808fb 100644
--- a/src/USER-MISC/improper_cossq.cpp
+++ b/src/USER-MISC/improper_cossq.cpp
@@ -63,8 +63,7 @@ void ImproperCossq::compute(int eflag, int vflag)
 
 
    eimproper = 0.0;
-   if (eflag || vflag) ev_setup(eflag,vflag);
-   else evflag = 0;
+   ev_init(eflag,vflag);
 
    double **x = atom->x;
    double **f = atom->f;
diff --git a/src/USER-MISC/improper_distance.cpp b/src/USER-MISC/improper_distance.cpp
index 2edf37ec5c..50babcc84e 100644
--- a/src/USER-MISC/improper_distance.cpp
+++ b/src/USER-MISC/improper_distance.cpp
@@ -67,8 +67,7 @@ void ImproperDistance::compute(int eflag, int vflag)
   double domega,a;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/improper_fourier.cpp b/src/USER-MISC/improper_fourier.cpp
index 927478fa1a..288d888d12 100644
--- a/src/USER-MISC/improper_fourier.cpp
+++ b/src/USER-MISC/improper_fourier.cpp
@@ -59,8 +59,7 @@ void ImproperFourier::compute(int eflag, int vflag)
   int i1,i2,i3,i4,n,type;
   double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   int **improperlist = neighbor->improperlist;
diff --git a/src/USER-MISC/improper_ring.cpp b/src/USER-MISC/improper_ring.cpp
index 70124b2ed1..36ba73af0f 100644
--- a/src/USER-MISC/improper_ring.cpp
+++ b/src/USER-MISC/improper_ring.cpp
@@ -95,8 +95,7 @@ void ImproperRing::compute(int eflag, int vflag)
    double   cjiji, ckjji, ckjkj, fix, fiy, fiz, fjx, fjy, fjz, fkx, fky, fkz;
 
    eimproper = 0.0;
-   if (eflag || vflag) ev_setup(eflag,vflag);
-   else evflag = 0;
+   ev_init(eflag,vflag);
 
    /* References to simulation data. */
    double **x = atom->x;
diff --git a/src/USER-MISC/pair_agni.cpp b/src/USER-MISC/pair_agni.cpp
index 0277969d15..21a6f1deee 100644
--- a/src/USER-MISC/pair_agni.cpp
+++ b/src/USER-MISC/pair_agni.cpp
@@ -136,8 +136,7 @@ void PairAGNI::compute(int eflag, int vflag)
   double rsq;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_buck_mdf.cpp b/src/USER-MISC/pair_buck_mdf.cpp
index 38de1c7c50..b5e81417ee 100644
--- a/src/USER-MISC/pair_buck_mdf.cpp
+++ b/src/USER-MISC/pair_buck_mdf.cpp
@@ -68,8 +68,7 @@ void PairBuckMDF::compute(int eflag, int vflag)
   double dp, d, tt, dt, dd;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_coul_diel.cpp b/src/USER-MISC/pair_coul_diel.cpp
index 0154e89731..a86921d296 100644
--- a/src/USER-MISC/pair_coul_diel.cpp
+++ b/src/USER-MISC/pair_coul_diel.cpp
@@ -58,8 +58,7 @@ void PairCoulDiel::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_coul_shield.cpp b/src/USER-MISC/pair_coul_shield.cpp
index 11df975c19..f74dcfe7d8 100644
--- a/src/USER-MISC/pair_coul_shield.cpp
+++ b/src/USER-MISC/pair_coul_shield.cpp
@@ -64,8 +64,7 @@ void PairCoulShield::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_edip.cpp b/src/USER-MISC/pair_edip.cpp
index 491268567f..0b5220fdfd 100644
--- a/src/USER-MISC/pair_edip.cpp
+++ b/src/USER-MISC/pair_edip.cpp
@@ -149,8 +149,7 @@ void PairEDIP::compute(int eflag, int vflag)
   double potential2B_factor;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_edip_multi.cpp b/src/USER-MISC/pair_edip_multi.cpp
index f56650d2f6..ab48fbaa73 100644
--- a/src/USER-MISC/pair_edip_multi.cpp
+++ b/src/USER-MISC/pair_edip_multi.cpp
@@ -118,8 +118,7 @@ void PairEDIPMulti::compute(int eflag, int vflag)
  // vflag != 0 means compute virial contributions in this step
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_extep.cpp b/src/USER-MISC/pair_extep.cpp
index 364fd45016..132b857dde 100644
--- a/src/USER-MISC/pair_extep.cpp
+++ b/src/USER-MISC/pair_extep.cpp
@@ -190,8 +190,7 @@ void PairExTeP::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   SR_neigh();
 
diff --git a/src/USER-MISC/pair_gauss_cut.cpp b/src/USER-MISC/pair_gauss_cut.cpp
index a000eff028..24d0b191d8 100644
--- a/src/USER-MISC/pair_gauss_cut.cpp
+++ b/src/USER-MISC/pair_gauss_cut.cpp
@@ -69,8 +69,7 @@ void PairGaussCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_ilp_graphene_hbn.cpp b/src/USER-MISC/pair_ilp_graphene_hbn.cpp
index 6257c1d72b..a8c9c686f1 100644
--- a/src/USER-MISC/pair_ilp_graphene_hbn.cpp
+++ b/src/USER-MISC/pair_ilp_graphene_hbn.cpp
@@ -111,14 +111,13 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
   tagint itag,jtag;
   double prodnorm1,prodnorm2,fkcx,fkcy,fkcz;
   double xtmp,ytmp,ztmp,delx,dely,delz,evdwl,fpair,fpair1,fpair2;
-  double rsq,r,Rcut,rhosq1,rhosq2,exp0,exp1,exp2,r2inv,r6inv,r8inv,Tap,dTap,Vkc;
+  double rsq,r,Rcut,rhosq1,rhosq2,exp0,exp1,exp2,r2inv,r6inv,r8inv,Tap,dTap,Vilp;
   double frho1,frho2,TSvdw,TSvdw2inv,Erep,fsum,rdsq1,rdsq2;
   int *ilist,*jlist,*numneigh,**firstneigh;
   int *ILP_neighs_i,*ILP_neighs_j;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -132,6 +131,10 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
   double fp2[3] = {0.0, 0.0, 0.0};
   double fprod1[3] = {0.0, 0.0, 0.0};
   double fprod2[3] = {0.0, 0.0, 0.0};
+  double fk[3] = {0.0, 0.0, 0.0};
+  double fl[3] = {0.0, 0.0, 0.0};
+  double delkj[3] = {0.0, 0.0, 0.0};
+  double delli[3] = {0.0, 0.0, 0.0};
 
   inum = list->inum;
   ilist = list->ilist;
@@ -214,7 +217,7 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
         frho1 = exp1*p.C;
         frho2 = exp2*p.C;
         Erep = p.epsilon + frho1 + frho2;
-        Vkc = -p.C6*r6inv/TSvdw + exp0*Erep;
+        Vilp = -p.C6*r6inv/TSvdw + exp0*Erep;
 
         // derivatives
         fpair = -6.0*p.C6*r8inv/TSvdw + p.d/p.seff*p.C6*(TSvdw-1.0)*TSvdw2inv*r8inv*r + p.lambda*exp0/r*Erep;
@@ -241,9 +244,9 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
         fprod2[0] = prodnorm2*dprodnorm2[0]*fpair2;
         fprod2[1] = prodnorm2*dprodnorm2[1]*fpair2;
         fprod2[2] = prodnorm2*dprodnorm2[2]*fpair2;
-        fkcx = (delx*fsum - fp1[0] - fp2[0])*Tap - Vkc*dTap*delx/r;
-        fkcy = (dely*fsum - fp1[1] - fp2[1])*Tap - Vkc*dTap*dely/r;
-        fkcz = (delz*fsum - fp1[2] - fp2[2])*Tap - Vkc*dTap*delz/r;
+        fkcx = (delx*fsum - fp1[0] - fp2[0])*Tap - Vilp*dTap*delx/r;
+        fkcy = (dely*fsum - fp1[1] - fp2[1])*Tap - Vilp*dTap*dely/r;
+        fkcz = (delz*fsum - fp1[2] - fp2[2])*Tap - Vilp*dTap*delz/r;
 
         f[i][0] += fkcx - fprod1[0]*Tap;
         f[i][1] += fkcy - fprod1[1]*Tap;
@@ -261,9 +264,16 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
           dprodnorm1[0] = dnormal[0][0][kk][i]*delx + dnormal[1][0][kk][i]*dely + dnormal[2][0][kk][i]*delz;
           dprodnorm1[1] = dnormal[0][1][kk][i]*delx + dnormal[1][1][kk][i]*dely + dnormal[2][1][kk][i]*delz;
           dprodnorm1[2] = dnormal[0][2][kk][i]*delx + dnormal[1][2][kk][i]*dely + dnormal[2][2][kk][i]*delz;
-          f[k][0] += (-prodnorm1*dprodnorm1[0]*fpair1)*Tap;
-          f[k][1] += (-prodnorm1*dprodnorm1[1]*fpair1)*Tap;
-          f[k][2] += (-prodnorm1*dprodnorm1[2]*fpair1)*Tap;
+          fk[0] = (-prodnorm1*dprodnorm1[0]*fpair1)*Tap;
+          fk[1] = (-prodnorm1*dprodnorm1[1]*fpair1)*Tap;
+          fk[2] = (-prodnorm1*dprodnorm1[2]*fpair1)*Tap;
+          f[k][0] += fk[0];
+          f[k][1] += fk[1];
+          f[k][2] += fk[2];
+          delkj[0] = x[k][0] - x[j][0];
+          delkj[1] = x[k][1] - x[j][1];
+          delkj[2] = x[k][2] - x[j][2];
+          if (evflag) ev_tally_xyz(k,j,nlocal,newton_pair,0.0,0.0,fk[0],fk[1],fk[2],delkj[0],delkj[1],delkj[2]);
         }
 
         // calculate the forces acted on the neighbors of atom j from atom i
@@ -275,20 +285,24 @@ void PairILPGrapheneHBN::compute(int eflag, int vflag)
           dprodnorm2[0] = dnormal[0][0][ll][j]*delx + dnormal[1][0][ll][j]*dely + dnormal[2][0][ll][j]*delz;
           dprodnorm2[1] = dnormal[0][1][ll][j]*delx + dnormal[1][1][ll][j]*dely + dnormal[2][1][ll][j]*delz;
           dprodnorm2[2] = dnormal[0][2][ll][j]*delx + dnormal[1][2][ll][j]*dely + dnormal[2][2][ll][j]*delz;
-          f[l][0] += (-prodnorm2*dprodnorm2[0]*fpair2)*Tap;
-          f[l][1] += (-prodnorm2*dprodnorm2[1]*fpair2)*Tap;
-          f[l][2] += (-prodnorm2*dprodnorm2[2]*fpair2)*Tap;
+          fl[0] = (-prodnorm2*dprodnorm2[0]*fpair2)*Tap;
+          fl[1] = (-prodnorm2*dprodnorm2[1]*fpair2)*Tap;
+          fl[2] = (-prodnorm2*dprodnorm2[2]*fpair2)*Tap;
+          f[l][0] += fl[0];
+          f[l][1] += fl[1];
+          f[l][2] += fl[2];
+          delli[0] = x[l][0] - x[i][0];
+          delli[1] = x[l][1] - x[i][1];
+          delli[2] = x[l][2] - x[i][2];
+          if (evflag) ev_tally_xyz(l,i,nlocal,newton_pair,0.0,0.0,fl[0],fl[1],fl[2],delli[0],delli[1],delli[2]);
         }
 
         if (eflag) {
-          if (tap_flag) evdwl = Tap*Vkc;
-          else  evdwl = Vkc - offset[itype][jtype];
+          if (tap_flag) evdwl = Tap*Vilp;
+          else  evdwl = Vilp - offset[itype][jtype];
         }
 
-        if (evflag){
-          ev_tally_xyz(i,j,nlocal,newton_pair,evdwl,0,
-                       fkcx,fkcy,fkcz,delx,dely,delz);
-        }
+        if (evflag) ev_tally_xyz(i,j,nlocal,newton_pair,evdwl,0.0,fkcx,fkcy,fkcz,delx,dely,delz);
       }
     }
   }
@@ -434,7 +448,7 @@ void PairILPGrapheneHBN::calc_normal()
       // the magnitude of the normal vector
       nn2 = n1[0]*n1[0] + n1[1]*n1[1] + n1[2]*n1[2];
       nn = sqrt(nn2);
-      if (nn == 0) error->all(FLERR,"The magnitude of the normal vector is zero");
+      if (nn == 0) error->one(FLERR,"The magnitude of the normal vector is zero");
       // the unit normal vector
       normal[i][0] = n1[0]/nn;
       normal[i][1] = n1[1]/nn;
@@ -577,7 +591,7 @@ void PairILPGrapheneHBN::calc_normal()
       // the magnitude of the normal vector
       nn2 = n1[0]*n1[0] + n1[1]*n1[1] + n1[2]*n1[2];
       nn = sqrt(nn2);
-      if (nn == 0) error->all(FLERR,"The magnitude of the normal vector is zero");
+      if (nn == 0) error->one(FLERR,"The magnitude of the normal vector is zero");
       // the unit normal vector
       normal[i][0] = n1[0]/nn;
       normal[i][1] = n1[1]/nn;
@@ -617,7 +631,7 @@ void PairILPGrapheneHBN::calc_normal()
       }
     }
     else {
-      error->all(FLERR,"There are too many neighbors for calculating normals");
+      error->one(FLERR,"There are too many neighbors for calculating normals");
     }
 
 //##############################################################################################
@@ -724,8 +738,7 @@ void PairILPGrapheneHBN::ILP_neigh()
 
     ILP_firstneigh[i] = neighptr;
     ILP_numneigh[i] = n;
-    if (n == 0) error->all(FLERR,"Could not build neighbor list to calculate normals, please check your configuration");
-    if (n > 3) error->all(FLERR,"There are too many neighbors for some atoms, please check your configuration");
+    if (n > 3) error->one(FLERR,"There are too many neighbors for some atoms, please check your configuration");
     ipage->vgot(n);
     if (ipage->status())
       error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
@@ -1011,7 +1024,7 @@ double PairILPGrapheneHBN::single(int /*i*/, int /*j*/, int itype, int jtype, do
                          double &fforce)
 {
   double r,r2inv,r6inv,r8inv,forcelj,philj,fpair;
-  double Tap,dTap,Vkc,TSvdw,TSvdw2inv;
+  double Tap,dTap,Vilp,TSvdw,TSvdw2inv;
 
   int iparam_ij = elem2param[map[itype]][map[jtype]];
   Param& p = params[iparam_ij];
@@ -1029,13 +1042,13 @@ double PairILPGrapheneHBN::single(int /*i*/, int /*j*/, int itype, int jtype, do
 
   TSvdw = 1.0 + exp(-p.d*(r/p.seff - 1.0));
   TSvdw2inv = pow(TSvdw,-2.0);
-  Vkc = -p.C6*r6inv/TSvdw;
+  Vilp = -p.C6*r6inv/TSvdw;
   // derivatives
   fpair = -6.0*p.C6*r8inv/TSvdw + p.d/p.seff*p.C6*(TSvdw - 1.0)*r6inv*TSvdw2inv/r;
   forcelj = fpair;
-  fforce = factor_lj*(forcelj*Tap - Vkc*dTap/r);
+  fforce = factor_lj*(forcelj*Tap - Vilp*dTap/r);
 
-  philj = Vkc*Tap;
+  philj = Vilp*Tap;
   return factor_lj*philj;
 }
 
diff --git a/src/USER-MISC/pair_kolmogorov_crespi_full.cpp b/src/USER-MISC/pair_kolmogorov_crespi_full.cpp
index cbcf6c7934..39535109cd 100644
--- a/src/USER-MISC/pair_kolmogorov_crespi_full.cpp
+++ b/src/USER-MISC/pair_kolmogorov_crespi_full.cpp
@@ -115,8 +115,7 @@ void PairKolmogorovCrespiFull::compute(int eflag, int vflag)
   int *KC_neighs_i,*KC_neighs_j;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -130,6 +129,10 @@ void PairKolmogorovCrespiFull::compute(int eflag, int vflag)
   double fp2[3] = {0.0, 0.0, 0.0};
   double fprod1[3] = {0.0, 0.0, 0.0};
   double fprod2[3] = {0.0, 0.0, 0.0};
+  double fk[3] = {0.0, 0.0, 0.0};
+  double fl[3] = {0.0, 0.0, 0.0};
+  double delkj[3] = {0.0, 0.0, 0.0};
+  double delli[3] = {0.0, 0.0, 0.0};
 
   inum = list->inum;	
   ilist = list->ilist;
@@ -260,9 +263,16 @@ void PairKolmogorovCrespiFull::compute(int eflag, int vflag)
           dprodnorm1[0] = dnormal[0][0][kk][i]*delx + dnormal[1][0][kk][i]*dely + dnormal[2][0][kk][i]*delz;
           dprodnorm1[1] = dnormal[0][1][kk][i]*delx + dnormal[1][1][kk][i]*dely + dnormal[2][1][kk][i]*delz;
           dprodnorm1[2] = dnormal[0][2][kk][i]*delx + dnormal[1][2][kk][i]*dely + dnormal[2][2][kk][i]*delz;
-	  f[k][0] += (-prodnorm1*dprodnorm1[0]*fpair1)*Tap;
-	  f[k][1] += (-prodnorm1*dprodnorm1[1]*fpair1)*Tap;
-	  f[k][2] += (-prodnorm1*dprodnorm1[2]*fpair1)*Tap;
+          fk[0] = (-prodnorm1*dprodnorm1[0]*fpair1)*Tap;
+          fk[1] = (-prodnorm1*dprodnorm1[1]*fpair1)*Tap;
+          fk[2] = (-prodnorm1*dprodnorm1[2]*fpair1)*Tap;
+          f[k][0] += fk[0];
+          f[k][1] += fk[1];
+          f[k][2] += fk[2];
+          delkj[0] = x[k][0] - x[j][0];
+          delkj[1] = x[k][1] - x[j][1];
+          delkj[2] = x[k][2] - x[j][2];
+          if (evflag) ev_tally_xyz(k,j,nlocal,newton_pair,0.0,0.0,fk[0],fk[1],fk[2],delkj[0],delkj[1],delkj[2]);
 	}
 
 	// calculate the forces acted on the neighbors of atom j from atom i
@@ -274,9 +284,16 @@ void PairKolmogorovCrespiFull::compute(int eflag, int vflag)
           dprodnorm2[0] = dnormal[0][0][ll][j]*delx + dnormal[1][0][ll][j]*dely + dnormal[2][0][ll][j]*delz;
           dprodnorm2[1] = dnormal[0][1][ll][j]*delx + dnormal[1][1][ll][j]*dely + dnormal[2][1][ll][j]*delz;
           dprodnorm2[2] = dnormal[0][2][ll][j]*delx + dnormal[1][2][ll][j]*dely + dnormal[2][2][ll][j]*delz;
-	  f[l][0] += (-prodnorm2*dprodnorm2[0]*fpair2)*Tap;
-	  f[l][1] += (-prodnorm2*dprodnorm2[1]*fpair2)*Tap;
-	  f[l][2] += (-prodnorm2*dprodnorm2[2]*fpair2)*Tap;
+          fl[0] = (-prodnorm2*dprodnorm2[0]*fpair2)*Tap;
+          fl[1] = (-prodnorm2*dprodnorm2[1]*fpair2)*Tap;
+          fl[2] = (-prodnorm2*dprodnorm2[2]*fpair2)*Tap;
+          f[l][0] += fl[0];
+          f[l][1] += fl[1];
+          f[l][2] += fl[2];
+          delli[0] = x[l][0] - x[i][0];
+          delli[1] = x[l][1] - x[i][1];
+          delli[2] = x[l][2] - x[i][2];
+          if (evflag) ev_tally_xyz(l,i,nlocal,newton_pair,0.0,0.0,fl[0],fl[1],fl[2],delli[0],delli[1],delli[2]);
 	}
 
         if (eflag) {
@@ -284,10 +301,7 @@ void PairKolmogorovCrespiFull::compute(int eflag, int vflag)
           else  evdwl = Vkc - offset[itype][jtype];
         }
 
-        if (evflag){
-          ev_tally_xyz(i,j,nlocal,newton_pair,evdwl,0,
-                       fkcx,fkcy,fkcz,delx,dely,delz);
-        }
+        if (evflag) ev_tally_xyz(i,j,nlocal,newton_pair,evdwl,0,fkcx,fkcy,fkcz,delx,dely,delz);
       }
     }
   }
@@ -432,7 +446,7 @@ void PairKolmogorovCrespiFull::calc_normal()
       // the magnitude of the normal vector
       nn2 = n1[0]*n1[0] + n1[1]*n1[1] + n1[2]*n1[2];
       nn = sqrt(nn2);
-      if (nn == 0) error->all(FLERR,"The magnitude of the normal vector is zero");
+      if (nn == 0) error->one(FLERR,"The magnitude of the normal vector is zero");
       // the unit normal vector
       normal[i][0] = n1[0]/nn;
       normal[i][1] = n1[1]/nn;
@@ -580,7 +594,7 @@ void PairKolmogorovCrespiFull::calc_normal()
       // the magnitude of the normal vector
       nn2 = n1[0]*n1[0] + n1[1]*n1[1] + n1[2]*n1[2];
       nn = sqrt(nn2);
-      if (nn == 0) error->all(FLERR,"The magnitude of the normal vector is zero");
+      if (nn == 0) error->one(FLERR,"The magnitude of the normal vector is zero");
       // the unit normal vector
       normal[i][0] = n1[0]/nn;
       normal[i][1] = n1[1]/nn;
@@ -620,7 +634,7 @@ void PairKolmogorovCrespiFull::calc_normal()
       }
     }
     else {
-      error->all(FLERR,"There are too many neighbors for calculating normals");
+      error->one(FLERR,"There are too many neighbors for calculating normals");
     }
 
 //##############################################################################################
@@ -728,8 +742,7 @@ void PairKolmogorovCrespiFull::KC_neigh()
 
     KC_firstneigh[i] = neighptr;
     KC_numneigh[i] = n;
-    if (n == 0) error->all(FLERR,"Could not build neighbor list to calculate normals, please check your configuration");
-    if (n > 3) error->all(FLERR,"There are too many neighbors for some atoms, please check your configuration");
+    if (n > 3) error->one(FLERR,"There are too many neighbors for some atoms, please check your configuration");
     ipage->vgot(n);
     if (ipage->status())
       error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
diff --git a/src/USER-MISC/pair_kolmogorov_crespi_z.cpp b/src/USER-MISC/pair_kolmogorov_crespi_z.cpp
index e9583032fe..dcea990a3b 100644
--- a/src/USER-MISC/pair_kolmogorov_crespi_z.cpp
+++ b/src/USER-MISC/pair_kolmogorov_crespi_z.cpp
@@ -87,8 +87,7 @@ void PairKolmogorovCrespiZ::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_lebedeva_z.cpp b/src/USER-MISC/pair_lebedeva_z.cpp
index 5153857c2f..0ab22e04c1 100644
--- a/src/USER-MISC/pair_lebedeva_z.cpp
+++ b/src/USER-MISC/pair_lebedeva_z.cpp
@@ -87,8 +87,7 @@ void PairLebedevaZ::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_lennard_mdf.cpp b/src/USER-MISC/pair_lennard_mdf.cpp
index 4bc2da23f8..b51639e80e 100644
--- a/src/USER-MISC/pair_lennard_mdf.cpp
+++ b/src/USER-MISC/pair_lennard_mdf.cpp
@@ -65,8 +65,7 @@ void PairLJ_AB_MDF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_list.cpp b/src/USER-MISC/pair_list.cpp
index aaeb586c1d..562a60aa99 100644
--- a/src/USER-MISC/pair_list.cpp
+++ b/src/USER-MISC/pair_list.cpp
@@ -80,9 +80,7 @@ PairList::~PairList()
 
 void PairList::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global =
-         vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int newton_pair = force->newton_pair;
diff --git a/src/USER-MISC/pair_lj_expand_coul_long.cpp b/src/USER-MISC/pair_lj_expand_coul_long.cpp
index 79a3c2a497..fe21538f2d 100644
--- a/src/USER-MISC/pair_lj_expand_coul_long.cpp
+++ b/src/USER-MISC/pair_lj_expand_coul_long.cpp
@@ -91,8 +91,7 @@ void PairLJExpandCoulLong::compute(int eflag, int vflag)
   double rsq,rshift,rshiftsq,rshift2inv;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -412,8 +411,7 @@ void PairLJExpandCoulLong::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_lj_mdf.cpp b/src/USER-MISC/pair_lj_mdf.cpp
index 4cd21b1dbe..ca0118ffb0 100644
--- a/src/USER-MISC/pair_lj_mdf.cpp
+++ b/src/USER-MISC/pair_lj_mdf.cpp
@@ -65,8 +65,7 @@ void PairLJMDF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_lj_sf_dipole_sf.cpp b/src/USER-MISC/pair_lj_sf_dipole_sf.cpp
index 523b2ca71a..af7d23370d 100644
--- a/src/USER-MISC/pair_lj_sf_dipole_sf.cpp
+++ b/src/USER-MISC/pair_lj_sf_dipole_sf.cpp
@@ -79,8 +79,7 @@ void PairLJSFDipoleSF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_meam_spline.cpp b/src/USER-MISC/pair_meam_spline.cpp
index 0300e2c7a2..f09919ce0f 100644
--- a/src/USER-MISC/pair_meam_spline.cpp
+++ b/src/USER-MISC/pair_meam_spline.cpp
@@ -103,12 +103,7 @@ void PairMEAMSpline::compute(int eflag, int vflag)
   double* const * const forces = atom->f;
   const int ntypes = atom->ntypes;
 
-  if (eflag || vflag) {
-    ev_setup(eflag, vflag);
-  } else {
-    evflag = vflag_fdotr = eflag_global = 0;
-    vflag_global = eflag_atom = vflag_atom = 0;
-  }
+  ev_init(eflag, vflag);
 
   // Grow per-atom array if necessary
 
diff --git a/src/USER-MISC/pair_meam_sw_spline.cpp b/src/USER-MISC/pair_meam_sw_spline.cpp
index e17c13865d..af1e8788bd 100644
--- a/src/USER-MISC/pair_meam_sw_spline.cpp
+++ b/src/USER-MISC/pair_meam_sw_spline.cpp
@@ -85,9 +85,7 @@ PairMEAMSWSpline::~PairMEAMSWSpline()
 
 void PairMEAMSWSpline::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag, vflag);
-  else evflag = vflag_fdotr =
-         eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag, vflag);
 
   double cutforcesq = cutoff*cutoff;
 
diff --git a/src/USER-MISC/pair_momb.cpp b/src/USER-MISC/pair_momb.cpp
index 927181ebf6..1716149a98 100644
--- a/src/USER-MISC/pair_momb.cpp
+++ b/src/USER-MISC/pair_momb.cpp
@@ -81,8 +81,7 @@ void PairMomb::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_morse_smooth_linear.cpp b/src/USER-MISC/pair_morse_smooth_linear.cpp
index a88e7a1a27..7c7973f830 100644
--- a/src/USER-MISC/pair_morse_smooth_linear.cpp
+++ b/src/USER-MISC/pair_morse_smooth_linear.cpp
@@ -60,8 +60,7 @@ void PairMorseSmoothLinear::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MISC/pair_srp.cpp b/src/USER-MISC/pair_srp.cpp
index 8f34e846c5..01deaf0fbe 100644
--- a/src/USER-MISC/pair_srp.cpp
+++ b/src/USER-MISC/pair_srp.cpp
@@ -143,10 +143,7 @@ void PairSRP::compute(int eflag, int vflag)
 
 {
     // setup energy and virial
-    if (eflag || vflag)
-        ev_setup(eflag, vflag);
-    else
-        evflag = vflag_fdotr = 0;
+    ev_init(eflag, vflag);
 
     double **x = atom->x;
     double **f = atom->f;
diff --git a/src/USER-MISC/pair_tersoff_table.cpp b/src/USER-MISC/pair_tersoff_table.cpp
index d1044cc336..e0985d1dce 100644
--- a/src/USER-MISC/pair_tersoff_table.cpp
+++ b/src/USER-MISC/pair_tersoff_table.cpp
@@ -117,8 +117,7 @@ void PairTersoffTable::compute(int eflag, int vflag)
 
   double evdwl = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MOFFF/angle_class2_p6.cpp b/src/USER-MOFFF/angle_class2_p6.cpp
index d2a6e21e6b..e8e6f279de 100644
--- a/src/USER-MOFFF/angle_class2_p6.cpp
+++ b/src/USER-MOFFF/angle_class2_p6.cpp
@@ -79,8 +79,7 @@ void AngleClass2P6::compute(int eflag, int vflag)
   double vx11,vx12,vy11,vy12,vz11,vz12,vx21,vx22,vy21,vy22,vz21,vz22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MOFFF/angle_cosine_buck6d.cpp b/src/USER-MOFFF/angle_cosine_buck6d.cpp
index f358097802..3829d2b8dc 100644
--- a/src/USER-MOFFF/angle_cosine_buck6d.cpp
+++ b/src/USER-MOFFF/angle_cosine_buck6d.cpp
@@ -69,8 +69,7 @@ void AngleCosineBuck6d::compute(int eflag, int vflag)
   double rcu,rqu,sme,smf;
 
   eangle = evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-3 virial contribution
 
diff --git a/src/USER-MOFFF/improper_inversion_harmonic.cpp b/src/USER-MOFFF/improper_inversion_harmonic.cpp
index 8404984b53..3f1e61e54a 100644
--- a/src/USER-MOFFF/improper_inversion_harmonic.cpp
+++ b/src/USER-MOFFF/improper_inversion_harmonic.cpp
@@ -66,8 +66,7 @@ void ImproperInversionHarmonic::compute(int eflag, int vflag)
   double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
   double rrvb1,rrvb2,rrvb3,rr2vb1,rr2vb2,rr2vb3;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   int **improperlist = neighbor->improperlist;
diff --git a/src/USER-MOFFF/pair_buck6d_coul_gauss_dsf.cpp b/src/USER-MOFFF/pair_buck6d_coul_gauss_dsf.cpp
index 1fc4644420..282bb0c58f 100644
--- a/src/USER-MOFFF/pair_buck6d_coul_gauss_dsf.cpp
+++ b/src/USER-MOFFF/pair_buck6d_coul_gauss_dsf.cpp
@@ -48,29 +48,29 @@ PairBuck6dCoulGaussDSF::PairBuck6dCoulGaussDSF(LAMMPS *lmp) : Pair(lmp)
 
 PairBuck6dCoulGaussDSF::~PairBuck6dCoulGaussDSF()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(alpha_ij);
-      memory->destroy(f_shift_ij);
-      memory->destroy(e_shift_ij);
-      memory->destroy(buck6d1);
-      memory->destroy(buck6d2);
-      memory->destroy(buck6d3);
-      memory->destroy(buck6d4);
-      memory->destroy(c0);
-      memory->destroy(c1);
-      memory->destroy(c2);
-      memory->destroy(c3);
-      memory->destroy(c4);
-      memory->destroy(c5);
-      memory->destroy(rsmooth_sq);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(alpha_ij);
+    memory->destroy(f_shift_ij);
+    memory->destroy(e_shift_ij);
+    memory->destroy(buck6d1);
+    memory->destroy(buck6d2);
+    memory->destroy(buck6d3);
+    memory->destroy(buck6d4);
+    memory->destroy(c0);
+    memory->destroy(c1);
+    memory->destroy(c2);
+    memory->destroy(c3);
+    memory->destroy(c4);
+    memory->destroy(c5);
+    memory->destroy(rsmooth_sq);
+    memory->destroy(offset);
   }
 }
 
@@ -87,8 +87,7 @@ void PairBuck6dCoulGaussDSF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-MOFFF/pair_buck6d_coul_gauss_long.cpp b/src/USER-MOFFF/pair_buck6d_coul_gauss_long.cpp
index 1ca42d864e..d6a4121d21 100644
--- a/src/USER-MOFFF/pair_buck6d_coul_gauss_long.cpp
+++ b/src/USER-MOFFF/pair_buck6d_coul_gauss_long.cpp
@@ -51,27 +51,27 @@ PairBuck6dCoulGaussLong::PairBuck6dCoulGaussLong(LAMMPS *lmp) : Pair(lmp)
 
 PairBuck6dCoulGaussLong::~PairBuck6dCoulGaussLong()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(alpha_ij);
-      memory->destroy(buck6d1);
-      memory->destroy(buck6d2);
-      memory->destroy(buck6d3);
-      memory->destroy(buck6d4);
-      memory->destroy(c0);
-      memory->destroy(c1);
-      memory->destroy(c2);
-      memory->destroy(c3);
-      memory->destroy(c4);
-      memory->destroy(c5);
-      memory->destroy(rsmooth_sq);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(alpha_ij);
+    memory->destroy(buck6d1);
+    memory->destroy(buck6d2);
+    memory->destroy(buck6d3);
+    memory->destroy(buck6d4);
+    memory->destroy(c0);
+    memory->destroy(c1);
+    memory->destroy(c2);
+    memory->destroy(c3);
+    memory->destroy(c4);
+    memory->destroy(c5);
+    memory->destroy(rsmooth_sq);
+    memory->destroy(offset);
   }
 }
 
@@ -89,8 +89,7 @@ void PairBuck6dCoulGaussLong::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-OMP/angle_charmm_omp.cpp b/src/USER-OMP/angle_charmm_omp.cpp
index 1f24438df3..118ba00226 100644
--- a/src/USER-OMP/angle_charmm_omp.cpp
+++ b/src/USER-OMP/angle_charmm_omp.cpp
@@ -44,10 +44,7 @@ using namespace MathConst;
 
 void AngleCharmmOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_class2_omp.cpp b/src/USER-OMP/angle_class2_omp.cpp
index bd13e20bcc..e072d136e1 100644
--- a/src/USER-OMP/angle_class2_omp.cpp
+++ b/src/USER-OMP/angle_class2_omp.cpp
@@ -44,10 +44,7 @@ AngleClass2OMP::AngleClass2OMP(class LAMMPS *lmp)
 
 void AngleClass2OMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_delta_omp.cpp b/src/USER-OMP/angle_cosine_delta_omp.cpp
index b3bb3e1f8a..a6dfb20433 100644
--- a/src/USER-OMP/angle_cosine_delta_omp.cpp
+++ b/src/USER-OMP/angle_cosine_delta_omp.cpp
@@ -44,10 +44,7 @@ AngleCosineDeltaOMP::AngleCosineDeltaOMP(class LAMMPS *lmp)
 
 void AngleCosineDeltaOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_omp.cpp b/src/USER-OMP/angle_cosine_omp.cpp
index 04b3870bc4..9097c8569c 100644
--- a/src/USER-OMP/angle_cosine_omp.cpp
+++ b/src/USER-OMP/angle_cosine_omp.cpp
@@ -44,10 +44,7 @@ AngleCosineOMP::AngleCosineOMP(class LAMMPS *lmp)
 
 void AngleCosineOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_periodic_omp.cpp b/src/USER-OMP/angle_cosine_periodic_omp.cpp
index 8060ebec7b..3fcea7ad1d 100644
--- a/src/USER-OMP/angle_cosine_periodic_omp.cpp
+++ b/src/USER-OMP/angle_cosine_periodic_omp.cpp
@@ -46,10 +46,7 @@ AngleCosinePeriodicOMP::AngleCosinePeriodicOMP(class LAMMPS *lmp)
 
 void AngleCosinePeriodicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_shift_exp_omp.cpp b/src/USER-OMP/angle_cosine_shift_exp_omp.cpp
index 3e00681ec9..6bd2feb023 100644
--- a/src/USER-OMP/angle_cosine_shift_exp_omp.cpp
+++ b/src/USER-OMP/angle_cosine_shift_exp_omp.cpp
@@ -44,10 +44,7 @@ AngleCosineShiftExpOMP::AngleCosineShiftExpOMP(class LAMMPS *lmp)
 
 void AngleCosineShiftExpOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_shift_omp.cpp b/src/USER-OMP/angle_cosine_shift_omp.cpp
index 0ab3df4359..56486faac1 100644
--- a/src/USER-OMP/angle_cosine_shift_omp.cpp
+++ b/src/USER-OMP/angle_cosine_shift_omp.cpp
@@ -44,10 +44,7 @@ AngleCosineShiftOMP::AngleCosineShiftOMP(class LAMMPS *lmp)
 
 void AngleCosineShiftOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_cosine_squared_omp.cpp b/src/USER-OMP/angle_cosine_squared_omp.cpp
index a1b1ffdf1a..6dd2a3bb3b 100644
--- a/src/USER-OMP/angle_cosine_squared_omp.cpp
+++ b/src/USER-OMP/angle_cosine_squared_omp.cpp
@@ -44,10 +44,7 @@ AngleCosineSquaredOMP::AngleCosineSquaredOMP(class LAMMPS *lmp)
 
 void AngleCosineSquaredOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_dipole_omp.cpp b/src/USER-OMP/angle_dipole_omp.cpp
index 92a5ba092e..da2e819ee2 100644
--- a/src/USER-OMP/angle_dipole_omp.cpp
+++ b/src/USER-OMP/angle_dipole_omp.cpp
@@ -45,10 +45,7 @@ AngleDipoleOMP::AngleDipoleOMP(class LAMMPS *lmp)
 
 void AngleDipoleOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   if (!force->newton_bond)
     error->all(FLERR,"'newton' flag for bonded interactions must be 'on'");
diff --git a/src/USER-OMP/angle_fourier_omp.cpp b/src/USER-OMP/angle_fourier_omp.cpp
index dfc713c372..b2f9b47e05 100644
--- a/src/USER-OMP/angle_fourier_omp.cpp
+++ b/src/USER-OMP/angle_fourier_omp.cpp
@@ -44,10 +44,7 @@ AngleFourierOMP::AngleFourierOMP(class LAMMPS *lmp)
 
 void AngleFourierOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_fourier_simple_omp.cpp b/src/USER-OMP/angle_fourier_simple_omp.cpp
index dea7a88723..93532a30e5 100644
--- a/src/USER-OMP/angle_fourier_simple_omp.cpp
+++ b/src/USER-OMP/angle_fourier_simple_omp.cpp
@@ -44,10 +44,7 @@ AngleFourierSimpleOMP::AngleFourierSimpleOMP(class LAMMPS *lmp)
 
 void AngleFourierSimpleOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_harmonic_omp.cpp b/src/USER-OMP/angle_harmonic_omp.cpp
index 0a71e5c9dd..824b254287 100644
--- a/src/USER-OMP/angle_harmonic_omp.cpp
+++ b/src/USER-OMP/angle_harmonic_omp.cpp
@@ -44,10 +44,7 @@ AngleHarmonicOMP::AngleHarmonicOMP(class LAMMPS *lmp)
 
 void AngleHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_quartic_omp.cpp b/src/USER-OMP/angle_quartic_omp.cpp
index 97a9b14f1d..fff08ddb39 100644
--- a/src/USER-OMP/angle_quartic_omp.cpp
+++ b/src/USER-OMP/angle_quartic_omp.cpp
@@ -44,10 +44,7 @@ AngleQuarticOMP::AngleQuarticOMP(class LAMMPS *lmp)
 
 void AngleQuarticOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_sdk_omp.cpp b/src/USER-OMP/angle_sdk_omp.cpp
index 9383a9af83..e8c762092c 100644
--- a/src/USER-OMP/angle_sdk_omp.cpp
+++ b/src/USER-OMP/angle_sdk_omp.cpp
@@ -46,10 +46,7 @@ AngleSDKOMP::AngleSDKOMP(class LAMMPS *lmp)
 
 void AngleSDKOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/angle_table_omp.cpp b/src/USER-OMP/angle_table_omp.cpp
index c3d2307489..d9d80b744d 100644
--- a/src/USER-OMP/angle_table_omp.cpp
+++ b/src/USER-OMP/angle_table_omp.cpp
@@ -44,10 +44,7 @@ AngleTableOMP::AngleTableOMP(class LAMMPS *lmp)
 
 void AngleTableOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_class2_omp.cpp b/src/USER-OMP/bond_class2_omp.cpp
index 1f9bcaa320..fdd73c20b0 100644
--- a/src/USER-OMP/bond_class2_omp.cpp
+++ b/src/USER-OMP/bond_class2_omp.cpp
@@ -40,10 +40,7 @@ BondClass2OMP::BondClass2OMP(class LAMMPS *lmp)
 
 void BondClass2OMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_fene_expand_omp.cpp b/src/USER-OMP/bond_fene_expand_omp.cpp
index d002d454dd..a8eec11760 100644
--- a/src/USER-OMP/bond_fene_expand_omp.cpp
+++ b/src/USER-OMP/bond_fene_expand_omp.cpp
@@ -41,10 +41,7 @@ BondFENEExpandOMP::BondFENEExpandOMP(class LAMMPS *lmp)
 
 void BondFENEExpandOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_fene_omp.cpp b/src/USER-OMP/bond_fene_omp.cpp
index ba958e1d6f..be7dcd4b49 100644
--- a/src/USER-OMP/bond_fene_omp.cpp
+++ b/src/USER-OMP/bond_fene_omp.cpp
@@ -41,10 +41,7 @@ BondFENEOMP::BondFENEOMP(class LAMMPS *lmp)
 
 void BondFENEOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_gromos_omp.cpp b/src/USER-OMP/bond_gromos_omp.cpp
index bcfde436d5..8f0926c0e9 100644
--- a/src/USER-OMP/bond_gromos_omp.cpp
+++ b/src/USER-OMP/bond_gromos_omp.cpp
@@ -39,10 +39,7 @@ BondGromosOMP::BondGromosOMP(class LAMMPS *lmp)
 
 void BondGromosOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_harmonic_omp.cpp b/src/USER-OMP/bond_harmonic_omp.cpp
index 46a93cbbdd..a3bb69c53c 100644
--- a/src/USER-OMP/bond_harmonic_omp.cpp
+++ b/src/USER-OMP/bond_harmonic_omp.cpp
@@ -39,10 +39,7 @@ BondHarmonicOMP::BondHarmonicOMP(class LAMMPS *lmp)
 
 void BondHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_harmonic_shift_cut_omp.cpp b/src/USER-OMP/bond_harmonic_shift_cut_omp.cpp
index 5f39bb1b64..5c16e27a32 100644
--- a/src/USER-OMP/bond_harmonic_shift_cut_omp.cpp
+++ b/src/USER-OMP/bond_harmonic_shift_cut_omp.cpp
@@ -39,10 +39,7 @@ BondHarmonicShiftCutOMP::BondHarmonicShiftCutOMP(class LAMMPS *lmp)
 
 void BondHarmonicShiftCutOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_harmonic_shift_omp.cpp b/src/USER-OMP/bond_harmonic_shift_omp.cpp
index 8c260bfc9b..39e957c137 100644
--- a/src/USER-OMP/bond_harmonic_shift_omp.cpp
+++ b/src/USER-OMP/bond_harmonic_shift_omp.cpp
@@ -39,10 +39,7 @@ BondHarmonicShiftOMP::BondHarmonicShiftOMP(class LAMMPS *lmp)
 
 void BondHarmonicShiftOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_morse_omp.cpp b/src/USER-OMP/bond_morse_omp.cpp
index 0c3cded71a..c0203de0d6 100644
--- a/src/USER-OMP/bond_morse_omp.cpp
+++ b/src/USER-OMP/bond_morse_omp.cpp
@@ -39,10 +39,7 @@ BondMorseOMP::BondMorseOMP(class LAMMPS *lmp)
 
 void BondMorseOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_nonlinear_omp.cpp b/src/USER-OMP/bond_nonlinear_omp.cpp
index cdc70eac8d..8fa3daf8ab 100644
--- a/src/USER-OMP/bond_nonlinear_omp.cpp
+++ b/src/USER-OMP/bond_nonlinear_omp.cpp
@@ -39,10 +39,7 @@ BondNonlinearOMP::BondNonlinearOMP(class LAMMPS *lmp)
 
 void BondNonlinearOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/bond_quartic_omp.cpp b/src/USER-OMP/bond_quartic_omp.cpp
index b2b1696bb4..fd0ccaf79d 100644
--- a/src/USER-OMP/bond_quartic_omp.cpp
+++ b/src/USER-OMP/bond_quartic_omp.cpp
@@ -40,10 +40,7 @@ BondQuarticOMP::BondQuarticOMP(class LAMMPS *lmp)
 
 void BondQuarticOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/USER-OMP/bond_table_omp.cpp b/src/USER-OMP/bond_table_omp.cpp
index 71dc237496..1616988385 100644
--- a/src/USER-OMP/bond_table_omp.cpp
+++ b/src/USER-OMP/bond_table_omp.cpp
@@ -39,10 +39,7 @@ BondTableOMP::BondTableOMP(class LAMMPS *lmp)
 
 void BondTableOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_charmm_omp.cpp b/src/USER-OMP/dihedral_charmm_omp.cpp
index 1bed449774..b09863613e 100644
--- a/src/USER-OMP/dihedral_charmm_omp.cpp
+++ b/src/USER-OMP/dihedral_charmm_omp.cpp
@@ -45,10 +45,7 @@ DihedralCharmmOMP::DihedralCharmmOMP(class LAMMPS *lmp)
 
 void DihedralCharmmOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   // insure pair->ev_tally() will use 1-4 virial contribution
 
diff --git a/src/USER-OMP/dihedral_class2_omp.cpp b/src/USER-OMP/dihedral_class2_omp.cpp
index c7ae1572c7..03ac9d9bab 100644
--- a/src/USER-OMP/dihedral_class2_omp.cpp
+++ b/src/USER-OMP/dihedral_class2_omp.cpp
@@ -43,10 +43,7 @@ DihedralClass2OMP::DihedralClass2OMP(class LAMMPS *lmp)
 
 void DihedralClass2OMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_cosine_shift_exp_omp.cpp b/src/USER-OMP/dihedral_cosine_shift_exp_omp.cpp
index c43b990028..c64cad9fc3 100644
--- a/src/USER-OMP/dihedral_cosine_shift_exp_omp.cpp
+++ b/src/USER-OMP/dihedral_cosine_shift_exp_omp.cpp
@@ -43,10 +43,7 @@ DihedralCosineShiftExpOMP::DihedralCosineShiftExpOMP(class LAMMPS *lmp)
 
 void DihedralCosineShiftExpOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_fourier_omp.cpp b/src/USER-OMP/dihedral_fourier_omp.cpp
index 319acb0beb..94bdae3795 100644
--- a/src/USER-OMP/dihedral_fourier_omp.cpp
+++ b/src/USER-OMP/dihedral_fourier_omp.cpp
@@ -44,10 +44,7 @@ DihedralFourierOMP::DihedralFourierOMP(class LAMMPS *lmp)
 
 void DihedralFourierOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_harmonic_omp.cpp b/src/USER-OMP/dihedral_harmonic_omp.cpp
index bb659cf262..10ccbd3d9f 100644
--- a/src/USER-OMP/dihedral_harmonic_omp.cpp
+++ b/src/USER-OMP/dihedral_harmonic_omp.cpp
@@ -43,10 +43,7 @@ DihedralHarmonicOMP::DihedralHarmonicOMP(class LAMMPS *lmp)
 
 void DihedralHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_helix_omp.cpp b/src/USER-OMP/dihedral_helix_omp.cpp
index e40f084e54..8c8e29cac0 100644
--- a/src/USER-OMP/dihedral_helix_omp.cpp
+++ b/src/USER-OMP/dihedral_helix_omp.cpp
@@ -46,10 +46,7 @@ DihedralHelixOMP::DihedralHelixOMP(class LAMMPS *lmp)
 
 void DihedralHelixOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_multi_harmonic_omp.cpp b/src/USER-OMP/dihedral_multi_harmonic_omp.cpp
index e10fc7b94a..38961e1746 100644
--- a/src/USER-OMP/dihedral_multi_harmonic_omp.cpp
+++ b/src/USER-OMP/dihedral_multi_harmonic_omp.cpp
@@ -43,10 +43,7 @@ DihedralMultiHarmonicOMP::DihedralMultiHarmonicOMP(class LAMMPS *lmp)
 
 void DihedralMultiHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_nharmonic_omp.cpp b/src/USER-OMP/dihedral_nharmonic_omp.cpp
index ad758fc892..e74238265d 100644
--- a/src/USER-OMP/dihedral_nharmonic_omp.cpp
+++ b/src/USER-OMP/dihedral_nharmonic_omp.cpp
@@ -43,10 +43,7 @@ DihedralNHarmonicOMP::DihedralNHarmonicOMP(class LAMMPS *lmp)
 
 void DihedralNHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_opls_omp.cpp b/src/USER-OMP/dihedral_opls_omp.cpp
index 53fddf51cb..64eaffe6fe 100644
--- a/src/USER-OMP/dihedral_opls_omp.cpp
+++ b/src/USER-OMP/dihedral_opls_omp.cpp
@@ -44,10 +44,7 @@ DihedralOPLSOMP::DihedralOPLSOMP(class LAMMPS *lmp)
 
 void DihedralOPLSOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_quadratic_omp.cpp b/src/USER-OMP/dihedral_quadratic_omp.cpp
index f6110cd505..8df622b847 100644
--- a/src/USER-OMP/dihedral_quadratic_omp.cpp
+++ b/src/USER-OMP/dihedral_quadratic_omp.cpp
@@ -44,10 +44,7 @@ DihedralQuadraticOMP::DihedralQuadraticOMP(class LAMMPS *lmp)
 
 void DihedralQuadraticOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/dihedral_table_omp.cpp b/src/USER-OMP/dihedral_table_omp.cpp
index 1457f7b2bf..792ee90c26 100644
--- a/src/USER-OMP/dihedral_table_omp.cpp
+++ b/src/USER-OMP/dihedral_table_omp.cpp
@@ -111,10 +111,7 @@ DihedralTableOMP::DihedralTableOMP(class LAMMPS *lmp)
 
 void DihedralTableOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/ewald_omp.cpp b/src/USER-OMP/ewald_omp.cpp
index 1fece5c31b..b56fc25142 100644
--- a/src/USER-OMP/ewald_omp.cpp
+++ b/src/USER-OMP/ewald_omp.cpp
@@ -61,9 +61,7 @@ void EwaldOMP::compute(int eflag, int vflag)
 {
   // set energy/virial flags
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // extend size of per-atom arrays if necessary
 
diff --git a/src/USER-OMP/fix_wall_gran_omp.cpp b/src/USER-OMP/fix_wall_gran_omp.cpp
deleted file mode 100644
index f015135385..0000000000
--- a/src/USER-OMP/fix_wall_gran_omp.cpp
+++ /dev/null
@@ -1,186 +0,0 @@
-/* ----------------------------------------------------------------------
-   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
-   http://lammps.sandia.gov, Sandia National Laboratories
-   Steve Plimpton, sjplimp@sandia.gov
-
-   Copyright (2003) Sandia Corporation.  Under the terms of Contract
-   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
-   certain rights in this software.  This software is distributed under
-   the GNU General Public License.
-
-   See the README file in the top-level LAMMPS directory.
-------------------------------------------------------------------------- */
-
-/* ----------------------------------------------------------------------
-   Contributing author: Axel Kohlmeyer (Temple U)
-------------------------------------------------------------------------- */
-
-#include <cmath>
-#include "fix_wall_gran_omp.h"
-#include "atom.h"
-#include "memory.h"
-#include "neighbor.h"
-#include "update.h"
-
-using namespace LAMMPS_NS;
-using namespace FixConst;
-
-enum{XPLANE=0,YPLANE=1,ZPLANE=2,ZCYLINDER,REGION};    // XYZ PLANE need to be 0,1,2
-enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY,BONDED_HISTORY};
-
-#define BIG 1.0e20
-
-/* ---------------------------------------------------------------------- */
-
-FixWallGranOMP::FixWallGranOMP(LAMMPS *lmp, int narg, char **arg) :
-  FixWallGran(lmp, narg, arg) { }
-
-/* ---------------------------------------------------------------------- */
-
-void FixWallGranOMP::post_force(int /* vflag */)
-{
-  double vwall[3];
-
-  // if just reneighbored:
-  // update rigid body masses for owned atoms if using FixRigid
-  //   body[i] = which body atom I is in, -1 if none
-  //   mass_body = mass of each rigid body
-
-  if (neighbor->ago == 0 && fix_rigid) {
-    int tmp;
-    const int * const body = (const int *) fix_rigid->extract("body",tmp);
-    double *mass_body = (double *) fix_rigid->extract("masstotal",tmp);
-    if (atom->nmax > nmax) {
-      memory->destroy(mass_rigid);
-      nmax = atom->nmax;
-      memory->create(mass_rigid,nmax,"wall/gran:mass_rigid");
-    }
-    const int nlocal = atom->nlocal;
-    for (int i = 0; i < nlocal; i++) {
-      if (body[i] >= 0) mass_rigid[i] = mass_body[body[i]];
-      else mass_rigid[i] = 0.0;
-    }
-  }
-
-  // set position of wall to initial settings and velocity to 0.0
-  // if wiggle or shear, set wall position and velocity accordingly
-
-  double wlo = lo;
-  double whi = hi;
-  vwall[0] = vwall[1] = vwall[2] = 0.0;
-  if (wiggle) {
-    double arg = omega * (update->ntimestep - time_origin) * dt;
-    if (wallstyle == axis) {
-      wlo = lo + amplitude - amplitude*cos(arg);
-      whi = hi + amplitude - amplitude*cos(arg);
-    }
-    vwall[axis] = amplitude*omega*sin(arg);
-  } else if (wshear) vwall[axis] = vshear;
-
-  // loop over all my atoms
-  // rsq = distance from wall
-  // dx,dy,dz = signed distance from wall
-  // for rotating cylinder, reset vwall based on particle position
-  // skip atom if not close enough to wall
-  //   if wall was set to NULL, it's skipped since lo/hi are infinity
-  // compute force and torque on atom if close enough to wall
-  //   via wall potential matched to pair potential
-  // set shear if pair potential stores history
-
-  double * const * const x = atom->x;
-  double * const * const v = atom->v;
-  double * const * const f = atom->f;
-  double * const * const omega = atom->omega;
-  double * const * const torque = atom->torque;
-  double * const radius = atom->radius;
-  double * const rmass = atom->rmass;
-  const int * const mask = atom->mask;
-  const int nlocal = atom->nlocal;
-
-  shearupdate = (update->setupflag) ? 0 : 1;
-
-  int i;
-#if defined(_OPENMP)
-#pragma omp parallel for private(i) default(none) firstprivate(vwall,wlo,whi)
-#endif
-  for (i = 0; i < nlocal; i++) {
-
-    if (mask[i] & groupbit) {
-      double dx,dy,dz,del1,del2,delxy,delr,rsq;
-      double rwall = 0.0;
-
-      dx = dy = dz = 0.0;
-
-      if (wallstyle == XPLANE) {
-        del1 = x[i][0] - wlo;
-        del2 = whi - x[i][0];
-        if (del1 < del2) dx = del1;
-        else dx = -del2;
-      } else if (wallstyle == YPLANE) {
-        del1 = x[i][1] - wlo;
-        del2 = whi - x[i][1];
-        if (del1 < del2) dy = del1;
-        else dy = -del2;
-      } else if (wallstyle == ZPLANE) {
-        del1 = x[i][2] - wlo;
-        del2 = whi - x[i][2];
-        if (del1 < del2) dz = del1;
-        else dz = -del2;
-      } else if (wallstyle == ZCYLINDER) {
-        delxy = sqrt(x[i][0]*x[i][0] + x[i][1]*x[i][1]);
-        delr = cylradius - delxy;
-        if (delr > radius[i]) {
-          dz = cylradius;
-          rwall = 0.0;
-        } else {
-          dx = -delr/delxy * x[i][0];
-          dy = -delr/delxy * x[i][1];
-          rwall = (delxy < cylradius) ? -2*cylradius : 2*cylradius;
-          if (wshear && axis != 2) {
-            vwall[0] += vshear * x[i][1]/delxy;
-            vwall[1] += -vshear * x[i][0]/delxy;
-            vwall[2] = 0.0;
-          }
-        }
-      }
-
-      rsq = dx*dx + dy*dy + dz*dz;
-
-      if (rsq > radius[i]*radius[i]) {
-        if (history)
-          for (int j = 0; j < sheardim; j++)
-            shearone[i][j] = 0.0;
-
-      } else {
-
-        // meff = effective mass of sphere
-        // if I is part of rigid body, use body mass
-
-        double meff = rmass[i];
-        if (fix_rigid && mass_rigid[i] > 0.0) meff = mass_rigid[i];
-
-        // invoke sphere/wall interaction
-
-        if (pairstyle == HOOKE)
-          hooke(rsq,dx,dy,dz,vwall,v[i],f[i],
-                omega[i],torque[i],radius[i],meff);
-        else if (pairstyle == HOOKE_HISTORY)
-          hooke_history(rsq,dx,dy,dz,vwall,v[i],f[i],
-                        omega[i],torque[i],radius[i],meff,shearone[i]);
-        else if (pairstyle == HERTZ_HISTORY)
-          hertz_history(rsq,dx,dy,dz,vwall,rwall,v[i],f[i],
-                        omega[i],torque[i],radius[i],meff,shearone[i]);
-        else if (pairstyle == BONDED_HISTORY)
-          bonded_history(rsq,dx,dy,dz,vwall,rwall,v[i],f[i],
-                         omega[i],torque[i],radius[i],meff,shearone[i]);
-      }
-    }
-  }
-}
-
-/* ---------------------------------------------------------------------- */
-
-void FixWallGranOMP::post_force_respa(int vflag, int ilevel, int /* iloop */)
-{
-  if (ilevel == nlevels_respa-1) post_force(vflag);
-}
diff --git a/src/USER-OMP/fix_wall_gran_omp.h b/src/USER-OMP/fix_wall_gran_omp.h
deleted file mode 100644
index cd26a7b40a..0000000000
--- a/src/USER-OMP/fix_wall_gran_omp.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* -*- c++ -*- ----------------------------------------------------------
-   LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
-   http://lammps.sandia.gov, Sandia National Laboratories
-   Steve Plimpton, sjplimp@sandia.gov
-
-   Copyright (2003) Sandia Corporation.  Under the terms of Contract
-   DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
-   certain rights in this software.  This software is distributed under
-   the GNU General Public License.
-
-   See the README file in the top-level LAMMPS directory.
-------------------------------------------------------------------------- */
-
-#ifdef FIX_CLASS
-
-FixStyle(wall/gran/omp,FixWallGranOMP)
-
-#else
-
-#ifndef LMP_FIX_WALL_GRAN_OMP_H
-#define LMP_FIX_WALL_GRAN_OMP_H
-
-#include "fix_wall_gran.h"
-
-namespace LAMMPS_NS {
-
-class FixWallGranOMP : public FixWallGran {
-
- public:
-  FixWallGranOMP(class LAMMPS *, int, char **);
-  virtual void post_force(int);
-  virtual void post_force_respa(int, int, int);
-};
-
-}
-
-#endif
-#endif
diff --git a/src/USER-OMP/improper_class2_omp.cpp b/src/USER-OMP/improper_class2_omp.cpp
index 7184cbeb69..c2b493f425 100644
--- a/src/USER-OMP/improper_class2_omp.cpp
+++ b/src/USER-OMP/improper_class2_omp.cpp
@@ -43,10 +43,7 @@ ImproperClass2OMP::ImproperClass2OMP(class LAMMPS *lmp)
 
 void ImproperClass2OMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_cossq_omp.cpp b/src/USER-OMP/improper_cossq_omp.cpp
index 022cfa6adf..3b328e5b78 100644
--- a/src/USER-OMP/improper_cossq_omp.cpp
+++ b/src/USER-OMP/improper_cossq_omp.cpp
@@ -43,10 +43,7 @@ ImproperCossqOMP::ImproperCossqOMP(class LAMMPS *lmp)
 
 void ImproperCossqOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_cvff_omp.cpp b/src/USER-OMP/improper_cvff_omp.cpp
index 78c5a55e05..fe1fc45bec 100644
--- a/src/USER-OMP/improper_cvff_omp.cpp
+++ b/src/USER-OMP/improper_cvff_omp.cpp
@@ -43,10 +43,7 @@ ImproperCvffOMP::ImproperCvffOMP(class LAMMPS *lmp)
 
 void ImproperCvffOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_fourier_omp.cpp b/src/USER-OMP/improper_fourier_omp.cpp
index 77dd36b64f..b5af428cb9 100644
--- a/src/USER-OMP/improper_fourier_omp.cpp
+++ b/src/USER-OMP/improper_fourier_omp.cpp
@@ -43,10 +43,7 @@ ImproperFourierOMP::ImproperFourierOMP(class LAMMPS *lmp)
 
 void ImproperFourierOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_harmonic_omp.cpp b/src/USER-OMP/improper_harmonic_omp.cpp
index 3f1895142d..6e02d0968e 100644
--- a/src/USER-OMP/improper_harmonic_omp.cpp
+++ b/src/USER-OMP/improper_harmonic_omp.cpp
@@ -43,10 +43,7 @@ ImproperHarmonicOMP::ImproperHarmonicOMP(class LAMMPS *lmp)
 
 void ImproperHarmonicOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_ring_omp.cpp b/src/USER-OMP/improper_ring_omp.cpp
index 7970de3839..e198b99337 100644
--- a/src/USER-OMP/improper_ring_omp.cpp
+++ b/src/USER-OMP/improper_ring_omp.cpp
@@ -45,10 +45,7 @@ ImproperRingOMP::ImproperRingOMP(class LAMMPS *lmp)
 
 void ImproperRingOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/improper_umbrella_omp.cpp b/src/USER-OMP/improper_umbrella_omp.cpp
index 69d41176c6..ceaca35074 100644
--- a/src/USER-OMP/improper_umbrella_omp.cpp
+++ b/src/USER-OMP/improper_umbrella_omp.cpp
@@ -43,10 +43,7 @@ ImproperUmbrellaOMP::ImproperUmbrellaOMP(class LAMMPS *lmp)
 
 void ImproperUmbrellaOMP::compute(int eflag, int vflag)
 {
-
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/msm_cg_omp.cpp b/src/USER-OMP/msm_cg_omp.cpp
index dee9fd85b6..8a920e05d5 100644
--- a/src/USER-OMP/msm_cg_omp.cpp
+++ b/src/USER-OMP/msm_cg_omp.cpp
@@ -90,9 +90,7 @@ void MSMCGOMP::compute(int eflag, int vflag)
 
   // set energy/virial flags
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-    eflag_atom = vflag_atom = eflag_either = vflag_either = 0;
+  ev_init(eflag,vflag);
 
   // invoke allocate_peratom() if needed for first time
 
diff --git a/src/USER-OMP/pair_adp_omp.cpp b/src/USER-OMP/pair_adp_omp.cpp
index 264169773b..645d697994 100644
--- a/src/USER-OMP/pair_adp_omp.cpp
+++ b/src/USER-OMP/pair_adp_omp.cpp
@@ -39,9 +39,7 @@ PairADPOMP::PairADPOMP(LAMMPS *lmp) :
 
 void PairADPOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_agni_omp.cpp b/src/USER-OMP/pair_agni_omp.cpp
index e8f003ea88..854bcbebf3 100644
--- a/src/USER-OMP/pair_agni_omp.cpp
+++ b/src/USER-OMP/pair_agni_omp.cpp
@@ -42,9 +42,7 @@ PairAGNIOMP::PairAGNIOMP(LAMMPS *lmp) :
 
 void PairAGNIOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_airebo_omp.cpp b/src/USER-OMP/pair_airebo_omp.cpp
index ec5c02d727..bed6c81ee4 100644
--- a/src/USER-OMP/pair_airebo_omp.cpp
+++ b/src/USER-OMP/pair_airebo_omp.cpp
@@ -49,9 +49,7 @@ void PairAIREBOOMP::compute(int eflag, int vflag)
 {
   double pv0=0.0,pv1=0.0,pv2=0.0;
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   REBO_neigh_thr();
 
diff --git a/src/USER-OMP/pair_beck_omp.cpp b/src/USER-OMP/pair_beck_omp.cpp
index 1494ec2987..90c3777932 100644
--- a/src/USER-OMP/pair_beck_omp.cpp
+++ b/src/USER-OMP/pair_beck_omp.cpp
@@ -38,9 +38,7 @@ PairBeckOMP::PairBeckOMP(LAMMPS *lmp) :
 
 void PairBeckOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_born_coul_long_omp.cpp b/src/USER-OMP/pair_born_coul_long_omp.cpp
index f198184406..a5df8f8182 100644
--- a/src/USER-OMP/pair_born_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_born_coul_long_omp.cpp
@@ -44,9 +44,7 @@ PairBornCoulLongOMP::PairBornCoulLongOMP(LAMMPS *lmp) :
 
 void PairBornCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_born_coul_msm_omp.cpp b/src/USER-OMP/pair_born_coul_msm_omp.cpp
index 1b4757359f..ad1e5e63cd 100644
--- a/src/USER-OMP/pair_born_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_born_coul_msm_omp.cpp
@@ -41,9 +41,7 @@ void PairBornCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' "
       "with OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_born_coul_wolf_omp.cpp b/src/USER-OMP/pair_born_coul_wolf_omp.cpp
index 7904181ba5..567eddc9cb 100644
--- a/src/USER-OMP/pair_born_coul_wolf_omp.cpp
+++ b/src/USER-OMP/pair_born_coul_wolf_omp.cpp
@@ -38,9 +38,7 @@ PairBornCoulWolfOMP::PairBornCoulWolfOMP(LAMMPS *lmp) :
 
 void PairBornCoulWolfOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_born_omp.cpp b/src/USER-OMP/pair_born_omp.cpp
index f75d4b9f35..fce2013745 100644
--- a/src/USER-OMP/pair_born_omp.cpp
+++ b/src/USER-OMP/pair_born_omp.cpp
@@ -36,9 +36,7 @@ PairBornOMP::PairBornOMP(LAMMPS *lmp) :
 
 void PairBornOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_brownian_omp.cpp b/src/USER-OMP/pair_brownian_omp.cpp
index b1af821bba..cef9fb0955 100644
--- a/src/USER-OMP/pair_brownian_omp.cpp
+++ b/src/USER-OMP/pair_brownian_omp.cpp
@@ -68,9 +68,7 @@ PairBrownianOMP::~PairBrownianOMP()
 
 void PairBrownianOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int inum = list->inum;
diff --git a/src/USER-OMP/pair_brownian_poly_omp.cpp b/src/USER-OMP/pair_brownian_poly_omp.cpp
index 2e677ed535..239a820242 100644
--- a/src/USER-OMP/pair_brownian_poly_omp.cpp
+++ b/src/USER-OMP/pair_brownian_poly_omp.cpp
@@ -68,9 +68,7 @@ PairBrownianPolyOMP::~PairBrownianPolyOMP()
 
 void PairBrownianPolyOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int inum = list->inum;
diff --git a/src/USER-OMP/pair_buck_coul_cut_omp.cpp b/src/USER-OMP/pair_buck_coul_cut_omp.cpp
index 8fa6be06b2..b9b77dc2b6 100644
--- a/src/USER-OMP/pair_buck_coul_cut_omp.cpp
+++ b/src/USER-OMP/pair_buck_coul_cut_omp.cpp
@@ -36,9 +36,7 @@ PairBuckCoulCutOMP::PairBuckCoulCutOMP(LAMMPS *lmp) :
 
 void PairBuckCoulCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_buck_coul_long_omp.cpp b/src/USER-OMP/pair_buck_coul_long_omp.cpp
index 4d30eb3e82..951ba0688c 100644
--- a/src/USER-OMP/pair_buck_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_buck_coul_long_omp.cpp
@@ -44,9 +44,7 @@ PairBuckCoulLongOMP::PairBuckCoulLongOMP(LAMMPS *lmp) :
 
 void PairBuckCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_buck_coul_msm_omp.cpp b/src/USER-OMP/pair_buck_coul_msm_omp.cpp
index a8bca36394..6226191627 100644
--- a/src/USER-OMP/pair_buck_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_buck_coul_msm_omp.cpp
@@ -41,9 +41,7 @@ void PairBuckCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' "
       "with OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_buck_long_coul_long_omp.cpp b/src/USER-OMP/pair_buck_long_coul_long_omp.cpp
index acb95ab76c..20d380a464 100644
--- a/src/USER-OMP/pair_buck_long_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_buck_long_coul_long_omp.cpp
@@ -46,9 +46,8 @@ PairBuckLongCoulLongOMP::PairBuckLongCoulLongOMP(LAMMPS *lmp) :
 
 void PairBuckLongCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+
   const int order1 = ewald_order&(1<<1);
   const int order6 = ewald_order&(1<<6);
 
diff --git a/src/USER-OMP/pair_buck_omp.cpp b/src/USER-OMP/pair_buck_omp.cpp
index f3fa32a5ea..cc7e81b9c5 100644
--- a/src/USER-OMP/pair_buck_omp.cpp
+++ b/src/USER-OMP/pair_buck_omp.cpp
@@ -36,9 +36,7 @@ PairBuckOMP::PairBuckOMP(LAMMPS *lmp) :
 
 void PairBuckOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_colloid_omp.cpp b/src/USER-OMP/pair_colloid_omp.cpp
index 536b7644bd..64613cb31d 100644
--- a/src/USER-OMP/pair_colloid_omp.cpp
+++ b/src/USER-OMP/pair_colloid_omp.cpp
@@ -39,9 +39,7 @@ PairColloidOMP::PairColloidOMP(LAMMPS *lmp) :
 
 void PairColloidOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_comb_omp.cpp b/src/USER-OMP/pair_comb_omp.cpp
index 8a77ab955f..be641dd0b9 100644
--- a/src/USER-OMP/pair_comb_omp.cpp
+++ b/src/USER-OMP/pair_comb_omp.cpp
@@ -41,9 +41,7 @@ PairCombOMP::PairCombOMP(LAMMPS *lmp) :
 
 void PairCombOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_cut_omp.cpp b/src/USER-OMP/pair_coul_cut_omp.cpp
index b9ac72421e..056daf210a 100644
--- a/src/USER-OMP/pair_coul_cut_omp.cpp
+++ b/src/USER-OMP/pair_coul_cut_omp.cpp
@@ -36,9 +36,7 @@ PairCoulCutOMP::PairCoulCutOMP(LAMMPS *lmp) :
 
 void PairCoulCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_cut_soft_omp.cpp b/src/USER-OMP/pair_coul_cut_soft_omp.cpp
index c7e8c5e560..70997da62b 100644
--- a/src/USER-OMP/pair_coul_cut_soft_omp.cpp
+++ b/src/USER-OMP/pair_coul_cut_soft_omp.cpp
@@ -36,9 +36,7 @@ PairCoulCutSoftOMP::PairCoulCutSoftOMP(LAMMPS *lmp) :
 
 void PairCoulCutSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_debye_omp.cpp b/src/USER-OMP/pair_coul_debye_omp.cpp
index cb7a9025ce..d202e314bf 100644
--- a/src/USER-OMP/pair_coul_debye_omp.cpp
+++ b/src/USER-OMP/pair_coul_debye_omp.cpp
@@ -36,9 +36,7 @@ PairCoulDebyeOMP::PairCoulDebyeOMP(LAMMPS *lmp) :
 
 void PairCoulDebyeOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_diel_omp.cpp b/src/USER-OMP/pair_coul_diel_omp.cpp
index c75e36b55e..f2bb6a46bf 100644
--- a/src/USER-OMP/pair_coul_diel_omp.cpp
+++ b/src/USER-OMP/pair_coul_diel_omp.cpp
@@ -36,9 +36,7 @@ PairCoulDielOMP::PairCoulDielOMP(LAMMPS *lmp) :
 
 void PairCoulDielOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_dsf_omp.cpp b/src/USER-OMP/pair_coul_dsf_omp.cpp
index 740e3242ad..217fb844c3 100644
--- a/src/USER-OMP/pair_coul_dsf_omp.cpp
+++ b/src/USER-OMP/pair_coul_dsf_omp.cpp
@@ -46,9 +46,7 @@ PairCoulDSFOMP::PairCoulDSFOMP(LAMMPS *lmp) :
 
 void PairCoulDSFOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_long_omp.cpp b/src/USER-OMP/pair_coul_long_omp.cpp
index eb74bb9615..1e3170c73c 100644
--- a/src/USER-OMP/pair_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_coul_long_omp.cpp
@@ -45,9 +45,7 @@ PairCoulLongOMP::PairCoulLongOMP(LAMMPS *lmp) :
 
 void PairCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_long_soft_omp.cpp b/src/USER-OMP/pair_coul_long_soft_omp.cpp
index 4e65483a17..dd1fc1030d 100644
--- a/src/USER-OMP/pair_coul_long_soft_omp.cpp
+++ b/src/USER-OMP/pair_coul_long_soft_omp.cpp
@@ -44,9 +44,7 @@ PairCoulLongSoftOMP::PairCoulLongSoftOMP(LAMMPS *lmp) :
 
 void PairCoulLongSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_msm_omp.cpp b/src/USER-OMP/pair_coul_msm_omp.cpp
index f4bc279532..9b50b86954 100644
--- a/src/USER-OMP/pair_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_coul_msm_omp.cpp
@@ -42,9 +42,7 @@ void PairCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' with "
       "OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_coul_wolf_omp.cpp b/src/USER-OMP/pair_coul_wolf_omp.cpp
index bc86cdbf5d..0913a2b188 100644
--- a/src/USER-OMP/pair_coul_wolf_omp.cpp
+++ b/src/USER-OMP/pair_coul_wolf_omp.cpp
@@ -38,9 +38,7 @@ PairCoulWolfOMP::PairCoulWolfOMP(LAMMPS *lmp) :
 
 void PairCoulWolfOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_dpd_omp.cpp b/src/USER-OMP/pair_dpd_omp.cpp
index 29b5568def..77db3d9183 100644
--- a/src/USER-OMP/pair_dpd_omp.cpp
+++ b/src/USER-OMP/pair_dpd_omp.cpp
@@ -55,9 +55,7 @@ PairDPDOMP::~PairDPDOMP()
 
 void PairDPDOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int inum = list->inum;
diff --git a/src/USER-OMP/pair_dpd_tstat_omp.cpp b/src/USER-OMP/pair_dpd_tstat_omp.cpp
index 0a9e96fa0c..d7233a16c5 100644
--- a/src/USER-OMP/pair_dpd_tstat_omp.cpp
+++ b/src/USER-OMP/pair_dpd_tstat_omp.cpp
@@ -55,9 +55,7 @@ PairDPDTstatOMP::~PairDPDTstatOMP()
 
 void PairDPDTstatOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int inum = list->inum;
diff --git a/src/USER-OMP/pair_eam_cd_omp.cpp b/src/USER-OMP/pair_eam_cd_omp.cpp
index 68c01c83d2..51b83f3bf5 100644
--- a/src/USER-OMP/pair_eam_cd_omp.cpp
+++ b/src/USER-OMP/pair_eam_cd_omp.cpp
@@ -55,9 +55,7 @@ PairEAMCDOMP::PairEAMCDOMP(LAMMPS *lmp, int _cdeamVersion) :
 
 void PairEAMCDOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_eam_omp.cpp b/src/USER-OMP/pair_eam_omp.cpp
index 492ff79769..99417f27da 100644
--- a/src/USER-OMP/pair_eam_omp.cpp
+++ b/src/USER-OMP/pair_eam_omp.cpp
@@ -39,9 +39,7 @@ PairEAMOMP::PairEAMOMP(LAMMPS *lmp) :
 
 void PairEAMOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_edip_omp.cpp b/src/USER-OMP/pair_edip_omp.cpp
index 3392160d92..144d893c1c 100644
--- a/src/USER-OMP/pair_edip_omp.cpp
+++ b/src/USER-OMP/pair_edip_omp.cpp
@@ -43,9 +43,7 @@ PairEDIPOMP::PairEDIPOMP(LAMMPS *lmp) :
 
 void PairEDIPOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_eim_omp.cpp b/src/USER-OMP/pair_eim_omp.cpp
index 6a3e0bc529..2ecd6f8ec7 100644
--- a/src/USER-OMP/pair_eim_omp.cpp
+++ b/src/USER-OMP/pair_eim_omp.cpp
@@ -39,9 +39,7 @@ PairEIMOMP::PairEIMOMP(LAMMPS *lmp) :
 
 void PairEIMOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_gauss_cut_omp.cpp b/src/USER-OMP/pair_gauss_cut_omp.cpp
index 9a41dcc87e..928312240b 100644
--- a/src/USER-OMP/pair_gauss_cut_omp.cpp
+++ b/src/USER-OMP/pair_gauss_cut_omp.cpp
@@ -36,9 +36,7 @@ PairGaussCutOMP::PairGaussCutOMP(LAMMPS *lmp) :
 
 void PairGaussCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_gauss_omp.cpp b/src/USER-OMP/pair_gauss_omp.cpp
index 059c77c677..159f1c3e31 100644
--- a/src/USER-OMP/pair_gauss_omp.cpp
+++ b/src/USER-OMP/pair_gauss_omp.cpp
@@ -37,9 +37,7 @@ PairGaussOMP::PairGaussOMP(LAMMPS *lmp) :
 
 void PairGaussOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_gayberne_omp.cpp b/src/USER-OMP/pair_gayberne_omp.cpp
index 5b0ff67afe..cfa05745ff 100644
--- a/src/USER-OMP/pair_gayberne_omp.cpp
+++ b/src/USER-OMP/pair_gayberne_omp.cpp
@@ -38,9 +38,7 @@ PairGayBerneOMP::PairGayBerneOMP(LAMMPS *lmp) :
 
 void PairGayBerneOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_gran_hertz_history_omp.cpp b/src/USER-OMP/pair_gran_hertz_history_omp.cpp
index 9854b8f9ff..271c70e9b9 100644
--- a/src/USER-OMP/pair_gran_hertz_history_omp.cpp
+++ b/src/USER-OMP/pair_gran_hertz_history_omp.cpp
@@ -40,9 +40,7 @@ PairGranHertzHistoryOMP::PairGranHertzHistoryOMP(LAMMPS *lmp) :
 
 void PairGranHertzHistoryOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_gran_hooke_history_omp.cpp b/src/USER-OMP/pair_gran_hooke_history_omp.cpp
index 2327fc815a..9a0e8aab76 100644
--- a/src/USER-OMP/pair_gran_hooke_history_omp.cpp
+++ b/src/USER-OMP/pair_gran_hooke_history_omp.cpp
@@ -41,9 +41,7 @@ PairGranHookeHistoryOMP::PairGranHookeHistoryOMP(LAMMPS *lmp) :
 
 void PairGranHookeHistoryOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int shearupdate = (update->setupflag) ? 0 : 1;
 
diff --git a/src/USER-OMP/pair_gran_hooke_omp.cpp b/src/USER-OMP/pair_gran_hooke_omp.cpp
index 876fe9c4de..d226ceaa14 100644
--- a/src/USER-OMP/pair_gran_hooke_omp.cpp
+++ b/src/USER-OMP/pair_gran_hooke_omp.cpp
@@ -38,9 +38,7 @@ PairGranHookeOMP::PairGranHookeOMP(LAMMPS *lmp) :
 
 void PairGranHookeOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_hbond_dreiding_lj_omp.cpp b/src/USER-OMP/pair_hbond_dreiding_lj_omp.cpp
index ec9da78b16..ea56ff51b5 100644
--- a/src/USER-OMP/pair_hbond_dreiding_lj_omp.cpp
+++ b/src/USER-OMP/pair_hbond_dreiding_lj_omp.cpp
@@ -57,9 +57,7 @@ PairHbondDreidingLJOMP::~PairHbondDreidingLJOMP()
 
 void PairHbondDreidingLJOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_hbond_dreiding_morse_omp.cpp b/src/USER-OMP/pair_hbond_dreiding_morse_omp.cpp
index 4965be43b8..1cff2de3b2 100644
--- a/src/USER-OMP/pair_hbond_dreiding_morse_omp.cpp
+++ b/src/USER-OMP/pair_hbond_dreiding_morse_omp.cpp
@@ -57,9 +57,7 @@ PairHbondDreidingMorseOMP::~PairHbondDreidingMorseOMP()
 
 void PairHbondDreidingMorseOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj96_cut_omp.cpp b/src/USER-OMP/pair_lj96_cut_omp.cpp
index 1cca674369..9ba8e09a54 100644
--- a/src/USER-OMP/pair_lj96_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj96_cut_omp.cpp
@@ -37,9 +37,7 @@ PairLJ96CutOMP::PairLJ96CutOMP(LAMMPS *lmp) :
 
 void PairLJ96CutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_charmm_coul_charmm_implicit_omp.cpp b/src/USER-OMP/pair_lj_charmm_coul_charmm_implicit_omp.cpp
index 2f72f3851e..3dc9b77c0f 100644
--- a/src/USER-OMP/pair_lj_charmm_coul_charmm_implicit_omp.cpp
+++ b/src/USER-OMP/pair_lj_charmm_coul_charmm_implicit_omp.cpp
@@ -36,9 +36,7 @@ PairLJCharmmCoulCharmmImplicitOMP::PairLJCharmmCoulCharmmImplicitOMP(LAMMPS *lmp
 
 void PairLJCharmmCoulCharmmImplicitOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_charmm_coul_charmm_omp.cpp b/src/USER-OMP/pair_lj_charmm_coul_charmm_omp.cpp
index b61a80a178..f9230996f0 100644
--- a/src/USER-OMP/pair_lj_charmm_coul_charmm_omp.cpp
+++ b/src/USER-OMP/pair_lj_charmm_coul_charmm_omp.cpp
@@ -36,9 +36,7 @@ PairLJCharmmCoulCharmmOMP::PairLJCharmmCoulCharmmOMP(LAMMPS *lmp) :
 
 void PairLJCharmmCoulCharmmOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_charmm_coul_long_omp.cpp b/src/USER-OMP/pair_lj_charmm_coul_long_omp.cpp
index 5351ab9aea..4bdaa3519f 100644
--- a/src/USER-OMP/pair_lj_charmm_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_charmm_coul_long_omp.cpp
@@ -37,9 +37,7 @@ PairLJCharmmCoulLongOMP::PairLJCharmmCoulLongOMP(LAMMPS *lmp) :
 
 void PairLJCharmmCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_charmm_coul_long_soft_omp.cpp b/src/USER-OMP/pair_lj_charmm_coul_long_soft_omp.cpp
index ea5d739e49..1f6daf052c 100644
--- a/src/USER-OMP/pair_lj_charmm_coul_long_soft_omp.cpp
+++ b/src/USER-OMP/pair_lj_charmm_coul_long_soft_omp.cpp
@@ -37,9 +37,7 @@ PairLJCharmmCoulLongSoftOMP::PairLJCharmmCoulLongSoftOMP(LAMMPS *lmp) :
 
 void PairLJCharmmCoulLongSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_charmm_coul_msm_omp.cpp b/src/USER-OMP/pair_lj_charmm_coul_msm_omp.cpp
index 3baa9597a8..eab62d919e 100644
--- a/src/USER-OMP/pair_lj_charmm_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_lj_charmm_coul_msm_omp.cpp
@@ -42,9 +42,7 @@ void PairLJCharmmCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' "
       "with OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_class2_coul_cut_omp.cpp b/src/USER-OMP/pair_lj_class2_coul_cut_omp.cpp
index 38390918c7..b9ffad134b 100644
--- a/src/USER-OMP/pair_lj_class2_coul_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj_class2_coul_cut_omp.cpp
@@ -36,9 +36,7 @@ PairLJClass2CoulCutOMP::PairLJClass2CoulCutOMP(LAMMPS *lmp) :
 
 void PairLJClass2CoulCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_class2_coul_long_omp.cpp b/src/USER-OMP/pair_lj_class2_coul_long_omp.cpp
index f47672c9bc..e5995363ad 100644
--- a/src/USER-OMP/pair_lj_class2_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_class2_coul_long_omp.cpp
@@ -44,9 +44,7 @@ PairLJClass2CoulLongOMP::PairLJClass2CoulLongOMP(LAMMPS *lmp) :
 
 void PairLJClass2CoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_class2_omp.cpp b/src/USER-OMP/pair_lj_class2_omp.cpp
index 7ab4626c3e..67715572ae 100644
--- a/src/USER-OMP/pair_lj_class2_omp.cpp
+++ b/src/USER-OMP/pair_lj_class2_omp.cpp
@@ -36,9 +36,7 @@ PairLJClass2OMP::PairLJClass2OMP(LAMMPS *lmp) :
 
 void PairLJClass2OMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cubic_omp.cpp b/src/USER-OMP/pair_lj_cubic_omp.cpp
index 3e8adb33b8..5fa4f92f45 100644
--- a/src/USER-OMP/pair_lj_cubic_omp.cpp
+++ b/src/USER-OMP/pair_lj_cubic_omp.cpp
@@ -37,9 +37,7 @@ PairLJCubicOMP::PairLJCubicOMP(LAMMPS *lmp) :
 
 void PairLJCubicOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_cut_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_cut_omp.cpp
index ea560a09bf..69cc2d3042 100644
--- a/src/USER-OMP/pair_lj_cut_coul_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_cut_omp.cpp
@@ -36,9 +36,7 @@ PairLJCutCoulCutOMP::PairLJCutCoulCutOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_cut_soft_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_cut_soft_omp.cpp
index 4ef12bb1bb..5dfa414bd4 100644
--- a/src/USER-OMP/pair_lj_cut_coul_cut_soft_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_cut_soft_omp.cpp
@@ -36,9 +36,7 @@ PairLJCutCoulCutSoftOMP::PairLJCutCoulCutSoftOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulCutSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_debye_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_debye_omp.cpp
index 9163e98edd..4644e565a7 100644
--- a/src/USER-OMP/pair_lj_cut_coul_debye_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_debye_omp.cpp
@@ -36,9 +36,7 @@ PairLJCutCoulDebyeOMP::PairLJCutCoulDebyeOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulDebyeOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_dsf_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_dsf_omp.cpp
index 9d9c098f87..13d877ec07 100644
--- a/src/USER-OMP/pair_lj_cut_coul_dsf_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_dsf_omp.cpp
@@ -46,9 +46,7 @@ PairLJCutCoulDSFOMP::PairLJCutCoulDSFOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulDSFOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_long_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_long_omp.cpp
index d2eaae4ca4..d4fe5fd2a7 100644
--- a/src/USER-OMP/pair_lj_cut_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_long_omp.cpp
@@ -45,9 +45,7 @@ PairLJCutCoulLongOMP::PairLJCutCoulLongOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_long_soft_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_long_soft_omp.cpp
index 725bfe4724..4a0ef73f60 100644
--- a/src/USER-OMP/pair_lj_cut_coul_long_soft_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_long_soft_omp.cpp
@@ -45,9 +45,7 @@ PairLJCutCoulLongSoftOMP::PairLJCutCoulLongSoftOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulLongSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_msm_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_msm_omp.cpp
index 234204af93..4c34b73622 100644
--- a/src/USER-OMP/pair_lj_cut_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_msm_omp.cpp
@@ -42,9 +42,7 @@ void PairLJCutCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' "
       "with OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_coul_wolf_omp.cpp b/src/USER-OMP/pair_lj_cut_coul_wolf_omp.cpp
index 36ef9d54f9..052be0a2fa 100644
--- a/src/USER-OMP/pair_lj_cut_coul_wolf_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_coul_wolf_omp.cpp
@@ -38,9 +38,7 @@ PairLJCutCoulWolfOMP::PairLJCutCoulWolfOMP(LAMMPS *lmp) :
 
 void PairLJCutCoulWolfOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_dipole_cut_omp.cpp b/src/USER-OMP/pair_lj_cut_dipole_cut_omp.cpp
index d4145d9835..55359db3be 100644
--- a/src/USER-OMP/pair_lj_cut_dipole_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_dipole_cut_omp.cpp
@@ -36,9 +36,7 @@ PairLJCutDipoleCutOMP::PairLJCutDipoleCutOMP(LAMMPS *lmp) :
 
 void PairLJCutDipoleCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_omp.cpp b/src/USER-OMP/pair_lj_cut_omp.cpp
index 319257b56b..34068185d2 100644
--- a/src/USER-OMP/pair_lj_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_omp.cpp
@@ -37,9 +37,7 @@ PairLJCutOMP::PairLJCutOMP(LAMMPS *lmp) :
 
 void PairLJCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_soft_omp.cpp b/src/USER-OMP/pair_lj_cut_soft_omp.cpp
index 7698f19b95..9bbe58146c 100644
--- a/src/USER-OMP/pair_lj_cut_soft_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_soft_omp.cpp
@@ -37,9 +37,7 @@ PairLJCutSoftOMP::PairLJCutSoftOMP(LAMMPS *lmp) :
 
 void PairLJCutSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_thole_long_omp.cpp b/src/USER-OMP/pair_lj_cut_thole_long_omp.cpp
index 536d5bcb86..85cab4fe7b 100644
--- a/src/USER-OMP/pair_lj_cut_thole_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_thole_long_omp.cpp
@@ -57,9 +57,7 @@ PairLJCutTholeLongOMP::PairLJCutTholeLongOMP(LAMMPS *lmp) :
 
 void PairLJCutTholeLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_cut_tip4p_cut_omp.cpp b/src/USER-OMP/pair_lj_cut_tip4p_cut_omp.cpp
index 619e970bb0..288724cd77 100644
--- a/src/USER-OMP/pair_lj_cut_tip4p_cut_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_tip4p_cut_omp.cpp
@@ -62,8 +62,7 @@ PairLJCutTIP4PCutOMP::~PairLJCutTIP4PCutOMP()
 
 void PairLJCutTIP4PCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_lj_cut_tip4p_long_omp.cpp b/src/USER-OMP/pair_lj_cut_tip4p_long_omp.cpp
index ca8f450dc6..e2c1da1a89 100644
--- a/src/USER-OMP/pair_lj_cut_tip4p_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_tip4p_long_omp.cpp
@@ -62,8 +62,7 @@ PairLJCutTIP4PLongOMP::~PairLJCutTIP4PLongOMP()
 
 void PairLJCutTIP4PLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_lj_cut_tip4p_long_soft_omp.cpp b/src/USER-OMP/pair_lj_cut_tip4p_long_soft_omp.cpp
index 80b17fba96..6baba8aec4 100644
--- a/src/USER-OMP/pair_lj_cut_tip4p_long_soft_omp.cpp
+++ b/src/USER-OMP/pair_lj_cut_tip4p_long_soft_omp.cpp
@@ -62,8 +62,7 @@ PairLJCutTIP4PLongSoftOMP::~PairLJCutTIP4PLongSoftOMP()
 
 void PairLJCutTIP4PLongSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_lj_expand_omp.cpp b/src/USER-OMP/pair_lj_expand_omp.cpp
index 064ea97809..6c6ddb045e 100644
--- a/src/USER-OMP/pair_lj_expand_omp.cpp
+++ b/src/USER-OMP/pair_lj_expand_omp.cpp
@@ -36,9 +36,7 @@ PairLJExpandOMP::PairLJExpandOMP(LAMMPS *lmp) :
 
 void PairLJExpandOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_gromacs_coul_gromacs_omp.cpp b/src/USER-OMP/pair_lj_gromacs_coul_gromacs_omp.cpp
index c87f369d11..77c5bc0da0 100644
--- a/src/USER-OMP/pair_lj_gromacs_coul_gromacs_omp.cpp
+++ b/src/USER-OMP/pair_lj_gromacs_coul_gromacs_omp.cpp
@@ -36,9 +36,7 @@ PairLJGromacsCoulGromacsOMP::PairLJGromacsCoulGromacsOMP(LAMMPS *lmp) :
 
 void PairLJGromacsCoulGromacsOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_gromacs_omp.cpp b/src/USER-OMP/pair_lj_gromacs_omp.cpp
index 1d7cec5eef..15bcb08eed 100644
--- a/src/USER-OMP/pair_lj_gromacs_omp.cpp
+++ b/src/USER-OMP/pair_lj_gromacs_omp.cpp
@@ -36,9 +36,7 @@ PairLJGromacsOMP::PairLJGromacsOMP(LAMMPS *lmp) :
 
 void PairLJGromacsOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_long_coul_long_omp.cpp b/src/USER-OMP/pair_lj_long_coul_long_omp.cpp
index 391840285b..c9edc087b6 100644
--- a/src/USER-OMP/pair_lj_long_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_long_coul_long_omp.cpp
@@ -46,9 +46,8 @@ PairLJLongCoulLongOMP::PairLJLongCoulLongOMP(LAMMPS *lmp) :
 
 void PairLJLongCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
+
   const int order1 = ewald_order&(1<<1);
   const int order6 = ewald_order&(1<<6);
 
diff --git a/src/USER-OMP/pair_lj_long_tip4p_long_omp.cpp b/src/USER-OMP/pair_lj_long_tip4p_long_omp.cpp
index 19278d19bb..6d7c5b5638 100644
--- a/src/USER-OMP/pair_lj_long_tip4p_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_long_tip4p_long_omp.cpp
@@ -63,9 +63,7 @@ PairLJLongTIP4PLongOMP::~PairLJLongTIP4PLongOMP()
 
 void PairLJLongTIP4PLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // reallocate hneigh_thr & newsite_thr if necessary
   // initialize hneigh_thr[0] to -1 on steps when reneighboring occured
diff --git a/src/USER-OMP/pair_lj_sdk_coul_long_omp.cpp b/src/USER-OMP/pair_lj_sdk_coul_long_omp.cpp
index c87f26204e..16c87d5ed4 100644
--- a/src/USER-OMP/pair_lj_sdk_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_lj_sdk_coul_long_omp.cpp
@@ -38,9 +38,7 @@ PairLJSDKCoulLongOMP::PairLJSDKCoulLongOMP(LAMMPS *lmp) :
 
 void PairLJSDKCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_sdk_coul_msm_omp.cpp b/src/USER-OMP/pair_lj_sdk_coul_msm_omp.cpp
index 8ff0cfe921..1002cc193e 100644
--- a/src/USER-OMP/pair_lj_sdk_coul_msm_omp.cpp
+++ b/src/USER-OMP/pair_lj_sdk_coul_msm_omp.cpp
@@ -44,9 +44,7 @@ void PairLJSDKCoulMSMOMP::compute(int eflag, int vflag)
     error->all(FLERR,"Must use 'kspace_modify pressure/scalar no' "
       "with OMP MSM Pair styles");
 
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_sdk_omp.cpp b/src/USER-OMP/pair_lj_sdk_omp.cpp
index e107399316..1e64973cbb 100644
--- a/src/USER-OMP/pair_lj_sdk_omp.cpp
+++ b/src/USER-OMP/pair_lj_sdk_omp.cpp
@@ -40,9 +40,7 @@ PairLJSDKOMP::PairLJSDKOMP(LAMMPS *lmp) :
 
 void PairLJSDKOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_sf_dipole_sf_omp.cpp b/src/USER-OMP/pair_lj_sf_dipole_sf_omp.cpp
index 250f6ff272..aea22fc4df 100644
--- a/src/USER-OMP/pair_lj_sf_dipole_sf_omp.cpp
+++ b/src/USER-OMP/pair_lj_sf_dipole_sf_omp.cpp
@@ -36,9 +36,7 @@ PairLJSFDipoleSFOMP::PairLJSFDipoleSFOMP(LAMMPS *lmp) :
 
 void PairLJSFDipoleSFOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_smooth_linear_omp.cpp b/src/USER-OMP/pair_lj_smooth_linear_omp.cpp
index b06de641f5..420c55b0ed 100644
--- a/src/USER-OMP/pair_lj_smooth_linear_omp.cpp
+++ b/src/USER-OMP/pair_lj_smooth_linear_omp.cpp
@@ -36,9 +36,7 @@ PairLJSmoothLinearOMP::PairLJSmoothLinearOMP(LAMMPS *lmp) :
 
 void PairLJSmoothLinearOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lj_smooth_omp.cpp b/src/USER-OMP/pair_lj_smooth_omp.cpp
index 36935616bf..d61dc19ff1 100644
--- a/src/USER-OMP/pair_lj_smooth_omp.cpp
+++ b/src/USER-OMP/pair_lj_smooth_omp.cpp
@@ -36,9 +36,7 @@ PairLJSmoothOMP::PairLJSmoothOMP(LAMMPS *lmp) :
 
 void PairLJSmoothOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lubricate_omp.cpp b/src/USER-OMP/pair_lubricate_omp.cpp
index a7f9fc65b5..132dbc575e 100644
--- a/src/USER-OMP/pair_lubricate_omp.cpp
+++ b/src/USER-OMP/pair_lubricate_omp.cpp
@@ -54,9 +54,7 @@ PairLubricateOMP::~PairLubricateOMP()
 
 void PairLubricateOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_lubricate_poly_omp.cpp b/src/USER-OMP/pair_lubricate_poly_omp.cpp
index 3f0ef1dba6..3a5f03364d 100644
--- a/src/USER-OMP/pair_lubricate_poly_omp.cpp
+++ b/src/USER-OMP/pair_lubricate_poly_omp.cpp
@@ -54,9 +54,7 @@ PairLubricatePolyOMP::~PairLubricatePolyOMP()
 
 void PairLubricatePolyOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_meam_spline_omp.cpp b/src/USER-OMP/pair_meam_spline_omp.cpp
index dfc3b978a2..e9307c8666 100644
--- a/src/USER-OMP/pair_meam_spline_omp.cpp
+++ b/src/USER-OMP/pair_meam_spline_omp.cpp
@@ -39,9 +39,7 @@ PairMEAMSplineOMP::PairMEAMSplineOMP(LAMMPS *lmp) :
 
 void PairMEAMSplineOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_morse_omp.cpp b/src/USER-OMP/pair_morse_omp.cpp
index 922b67b463..bf57019f11 100644
--- a/src/USER-OMP/pair_morse_omp.cpp
+++ b/src/USER-OMP/pair_morse_omp.cpp
@@ -36,9 +36,7 @@ PairMorseOMP::PairMorseOMP(LAMMPS *lmp) :
 
 void PairMorseOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_morse_smooth_linear_omp.cpp b/src/USER-OMP/pair_morse_smooth_linear_omp.cpp
index 61cef69c37..5ba6acb439 100644
--- a/src/USER-OMP/pair_morse_smooth_linear_omp.cpp
+++ b/src/USER-OMP/pair_morse_smooth_linear_omp.cpp
@@ -40,9 +40,7 @@ PairMorseSmoothLinearOMP::PairMorseSmoothLinearOMP(LAMMPS *lmp) :
 
 void PairMorseSmoothLinearOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_nm_cut_coul_cut_omp.cpp b/src/USER-OMP/pair_nm_cut_coul_cut_omp.cpp
index fcbf5dbabb..d62b4e5c62 100644
--- a/src/USER-OMP/pair_nm_cut_coul_cut_omp.cpp
+++ b/src/USER-OMP/pair_nm_cut_coul_cut_omp.cpp
@@ -36,9 +36,7 @@ PairNMCutCoulCutOMP::PairNMCutCoulCutOMP(LAMMPS *lmp) :
 
 void PairNMCutCoulCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_nm_cut_coul_long_omp.cpp b/src/USER-OMP/pair_nm_cut_coul_long_omp.cpp
index b31387dbfe..a8696c74a1 100644
--- a/src/USER-OMP/pair_nm_cut_coul_long_omp.cpp
+++ b/src/USER-OMP/pair_nm_cut_coul_long_omp.cpp
@@ -44,9 +44,7 @@ PairNMCutCoulLongOMP::PairNMCutCoulLongOMP(LAMMPS *lmp) :
 
 void PairNMCutCoulLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_nm_cut_omp.cpp b/src/USER-OMP/pair_nm_cut_omp.cpp
index 79cd046311..9304b10ef0 100644
--- a/src/USER-OMP/pair_nm_cut_omp.cpp
+++ b/src/USER-OMP/pair_nm_cut_omp.cpp
@@ -36,9 +36,7 @@ PairNMCutOMP::PairNMCutOMP(LAMMPS *lmp) :
 
 void PairNMCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_peri_lps_omp.cpp b/src/USER-OMP/pair_peri_lps_omp.cpp
index 7b174face7..61db45363e 100644
--- a/src/USER-OMP/pair_peri_lps_omp.cpp
+++ b/src/USER-OMP/pair_peri_lps_omp.cpp
@@ -45,9 +45,7 @@ PairPeriLPSOMP::PairPeriLPSOMP(LAMMPS *lmp) :
 
 void PairPeriLPSOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = eflag_global = eflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_peri_pmb_omp.cpp b/src/USER-OMP/pair_peri_pmb_omp.cpp
index 8199d8aa47..b1816e4052 100644
--- a/src/USER-OMP/pair_peri_pmb_omp.cpp
+++ b/src/USER-OMP/pair_peri_pmb_omp.cpp
@@ -43,9 +43,7 @@ PairPeriPMBOMP::PairPeriPMBOMP(LAMMPS *lmp) :
 
 void PairPeriPMBOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_reaxc_omp.cpp b/src/USER-OMP/pair_reaxc_omp.cpp
index 63beb61be6..927a63a90f 100644
--- a/src/USER-OMP/pair_reaxc_omp.cpp
+++ b/src/USER-OMP/pair_reaxc_omp.cpp
@@ -113,7 +113,7 @@ PairReaxCOMP::~PairReaxCOMP()
   if (setup_flag) {
     reax_list * bonds = lists+BONDS;
     for (int i=0; i<bonds->num_intrs; ++i)
-      sfree(bonds->select.bond_list[i].bo_data.CdboReduction, "CdboReduction");
+      sfree(error, bonds->select.bond_list[i].bo_data.CdboReduction, "CdboReduction");
   }
   memory->destroy(num_nbrs_offset);
 
@@ -191,12 +191,15 @@ void PairReaxCOMP::compute(int eflag, int vflag)
   int *num_hbonds = fix_reax->num_hbonds;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else ev_unset();
+  ev_init(eflag,vflag);
 
   if (vflag_global) control->virial = 1;
   else control->virial = 0;
 
+  if (vflag_atom)
+     error->all(FLERR,"Pair style reax/c/omp does not support "
+                "computing per-atom stress");
+
   system->n = atom->nlocal; // my atoms
   system->N = atom->nlocal + atom->nghost; // mine + ghosts
   system->bigN = static_cast<int> (atom->natoms);  // all atoms in the system
@@ -210,7 +213,7 @@ void PairReaxCOMP::compute(int eflag, int vflag)
 
   setup();
 
-  Reset( system, control, data, workspace, &lists, world );
+  Reset( system, control, data, workspace, &lists );
 
   // Why not update workspace like in MPI-only code?
   // Using the MPI-only way messes up the hb energy
@@ -344,6 +347,15 @@ void PairReaxCOMP::init_style( )
   if (force->newton_pair == 0)
     error->all(FLERR,"Pair style reax/c/omp requires newton pair on");
 
+ if ((atom->map_tag_max > 99999999) && (comm->me == 0))
+    error->warning(FLERR,"Some Atom-IDs are too large. Pair style reax/c/omp "
+                   "native output files may get misformatted or corrupted");
+
+  // because system->bigN is an int, we cannot have more atoms than MAXSMALLINT
+
+  if (atom->natoms > MAXSMALLINT)
+    error->all(FLERR,"Too many atoms for pair style reax/c/omp");
+
   // need a half neighbor list w/ Newton off and ghost neighbors
   // built whenever re-neighboring occurs
 
@@ -411,12 +423,12 @@ void PairReaxCOMP::setup( )
 
     // initialize my data structures
 
-    PreAllocate_Space( system, control, workspace, world );
+    PreAllocate_Space( system, control, workspace );
     write_reax_atoms();
 
     int num_nbrs = estimate_reax_lists();
     if(!Make_List(system->total_cap, num_nbrs, TYP_FAR_NEIGHBOR,
-                  lists+FAR_NBRS, world))
+                  lists+FAR_NBRS))
       error->all(FLERR,"Pair reax/c problem in far neighbor list");
 
     write_reax_lists();
@@ -446,7 +458,7 @@ void PairReaxCOMP::setup( )
 
     // check if I need to shrink/extend my data-structs
 
-    ReAllocate( system, control, data, workspace, &lists, mpi_data );
+    ReAllocate( system, control, data, workspace, &lists );
   }
 }
 
diff --git a/src/USER-OMP/pair_resquared_omp.cpp b/src/USER-OMP/pair_resquared_omp.cpp
index 1736e794f5..d9e0059a9f 100644
--- a/src/USER-OMP/pair_resquared_omp.cpp
+++ b/src/USER-OMP/pair_resquared_omp.cpp
@@ -38,9 +38,7 @@ PairRESquaredOMP::PairRESquaredOMP(LAMMPS *lmp) :
 
 void PairRESquaredOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_soft_omp.cpp b/src/USER-OMP/pair_soft_omp.cpp
index a860ad97d9..eb151bc0df 100644
--- a/src/USER-OMP/pair_soft_omp.cpp
+++ b/src/USER-OMP/pair_soft_omp.cpp
@@ -40,9 +40,7 @@ PairSoftOMP::PairSoftOMP(LAMMPS *lmp) :
 
 void PairSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_sw_omp.cpp b/src/USER-OMP/pair_sw_omp.cpp
index e323fc4c37..745b3a1f04 100644
--- a/src/USER-OMP/pair_sw_omp.cpp
+++ b/src/USER-OMP/pair_sw_omp.cpp
@@ -37,9 +37,7 @@ PairSWOMP::PairSWOMP(LAMMPS *lmp) :
 
 void PairSWOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_table_omp.cpp b/src/USER-OMP/pair_table_omp.cpp
index d27456e1b5..b55817e75c 100644
--- a/src/USER-OMP/pair_table_omp.cpp
+++ b/src/USER-OMP/pair_table_omp.cpp
@@ -37,9 +37,7 @@ PairTableOMP::PairTableOMP(LAMMPS *lmp) :
 
 void PairTableOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_tersoff_mod_c_omp.cpp b/src/USER-OMP/pair_tersoff_mod_c_omp.cpp
index fad077ca12..a11bd87640 100644
--- a/src/USER-OMP/pair_tersoff_mod_c_omp.cpp
+++ b/src/USER-OMP/pair_tersoff_mod_c_omp.cpp
@@ -36,9 +36,7 @@ PairTersoffMODCOMP::PairTersoffMODCOMP(LAMMPS *lmp) :
 
 void PairTersoffMODCOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_tersoff_mod_omp.cpp b/src/USER-OMP/pair_tersoff_mod_omp.cpp
index 04e54c6e69..da22110c1c 100644
--- a/src/USER-OMP/pair_tersoff_mod_omp.cpp
+++ b/src/USER-OMP/pair_tersoff_mod_omp.cpp
@@ -36,9 +36,7 @@ PairTersoffMODOMP::PairTersoffMODOMP(LAMMPS *lmp) :
 
 void PairTersoffMODOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_tersoff_omp.cpp b/src/USER-OMP/pair_tersoff_omp.cpp
index a5afdc7509..661f15d64d 100644
--- a/src/USER-OMP/pair_tersoff_omp.cpp
+++ b/src/USER-OMP/pair_tersoff_omp.cpp
@@ -37,9 +37,7 @@ PairTersoffOMP::PairTersoffOMP(LAMMPS *lmp) :
 
 void PairTersoffOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_tersoff_table_omp.cpp b/src/USER-OMP/pair_tersoff_table_omp.cpp
index de045f9c62..7e83814f95 100644
--- a/src/USER-OMP/pair_tersoff_table_omp.cpp
+++ b/src/USER-OMP/pair_tersoff_table_omp.cpp
@@ -61,9 +61,7 @@ PairTersoffTableOMP::~PairTersoffTableOMP()
 
 void PairTersoffTableOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_tip4p_cut_omp.cpp b/src/USER-OMP/pair_tip4p_cut_omp.cpp
index 85589cf043..1900ed4394 100644
--- a/src/USER-OMP/pair_tip4p_cut_omp.cpp
+++ b/src/USER-OMP/pair_tip4p_cut_omp.cpp
@@ -62,8 +62,7 @@ PairTIP4PCutOMP::~PairTIP4PCutOMP()
 
 void PairTIP4PCutOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
 
diff --git a/src/USER-OMP/pair_tip4p_long_omp.cpp b/src/USER-OMP/pair_tip4p_long_omp.cpp
index c6c4bfe5fc..ee65937c46 100644
--- a/src/USER-OMP/pair_tip4p_long_omp.cpp
+++ b/src/USER-OMP/pair_tip4p_long_omp.cpp
@@ -62,8 +62,7 @@ PairTIP4PLongOMP::~PairTIP4PLongOMP()
 
 void PairTIP4PLongOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_tip4p_long_soft_omp.cpp b/src/USER-OMP/pair_tip4p_long_soft_omp.cpp
index 7e9d3b6dff..adb984a2cd 100644
--- a/src/USER-OMP/pair_tip4p_long_soft_omp.cpp
+++ b/src/USER-OMP/pair_tip4p_long_soft_omp.cpp
@@ -62,8 +62,7 @@ PairTIP4PLongSoftOMP::~PairTIP4PLongSoftOMP()
 
 void PairTIP4PLongSoftOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nlocal = atom->nlocal;
   const int nall = nlocal + atom->nghost;
diff --git a/src/USER-OMP/pair_ufm_omp.cpp b/src/USER-OMP/pair_ufm_omp.cpp
index ff258b5b3b..08d8cc15f9 100644
--- a/src/USER-OMP/pair_ufm_omp.cpp
+++ b/src/USER-OMP/pair_ufm_omp.cpp
@@ -38,9 +38,7 @@ PairUFMOMP::PairUFMOMP(LAMMPS *lmp) :
 
 void PairUFMOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_vashishta_omp.cpp b/src/USER-OMP/pair_vashishta_omp.cpp
index 194a3e2d86..28104013f0 100644
--- a/src/USER-OMP/pair_vashishta_omp.cpp
+++ b/src/USER-OMP/pair_vashishta_omp.cpp
@@ -37,9 +37,7 @@ PairVashishtaOMP::PairVashishtaOMP(LAMMPS *lmp) :
 
 void PairVashishtaOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_vashishta_table_omp.cpp b/src/USER-OMP/pair_vashishta_table_omp.cpp
index e0d96d8bb6..b044902ebe 100644
--- a/src/USER-OMP/pair_vashishta_table_omp.cpp
+++ b/src/USER-OMP/pair_vashishta_table_omp.cpp
@@ -37,9 +37,7 @@ PairVashishtaTableOMP::PairVashishtaTableOMP(LAMMPS *lmp) :
 
 void PairVashishtaTableOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_yukawa_colloid_omp.cpp b/src/USER-OMP/pair_yukawa_colloid_omp.cpp
index c1d2133a1c..86314ce7b8 100644
--- a/src/USER-OMP/pair_yukawa_colloid_omp.cpp
+++ b/src/USER-OMP/pair_yukawa_colloid_omp.cpp
@@ -36,9 +36,7 @@ PairYukawaColloidOMP::PairYukawaColloidOMP(LAMMPS *lmp) :
 
 void PairYukawaColloidOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_yukawa_omp.cpp b/src/USER-OMP/pair_yukawa_omp.cpp
index cbfd627f97..add81e9b04 100644
--- a/src/USER-OMP/pair_yukawa_omp.cpp
+++ b/src/USER-OMP/pair_yukawa_omp.cpp
@@ -36,9 +36,7 @@ PairYukawaOMP::PairYukawaOMP(LAMMPS *lmp) :
 
 void PairYukawaOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/pair_zbl_omp.cpp b/src/USER-OMP/pair_zbl_omp.cpp
index 788679434b..f6856c4fa0 100644
--- a/src/USER-OMP/pair_zbl_omp.cpp
+++ b/src/USER-OMP/pair_zbl_omp.cpp
@@ -37,9 +37,7 @@ PairZBLOMP::PairZBLOMP(LAMMPS *lmp) :
 
 void PairZBLOMP::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) {
-    ev_setup(eflag,vflag);
-  } else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   const int nall = atom->nlocal + atom->nghost;
   const int nthreads = comm->nthreads;
diff --git a/src/USER-OMP/reaxc_forces_omp.cpp b/src/USER-OMP/reaxc_forces_omp.cpp
index 80741a46a8..0a08bd6a46 100644
--- a/src/USER-OMP/reaxc_forces_omp.cpp
+++ b/src/USER-OMP/reaxc_forces_omp.cpp
@@ -262,8 +262,8 @@ void Compute_Total_ForceOMP( reax_system *system, control_params *control,
 
 /* ---------------------------------------------------------------------- */
 
-void Validate_ListsOMP( reax_system *system, storage * /*workspace */, reax_list **lists,
-                     int step, int n, int N, int numH, MPI_Comm comm )
+void Validate_ListsOMP(reax_system *system, storage * /*workspace*/, reax_list **lists,
+                       int step, int n, int N, int numH, MPI_Comm /*comm*/)
 {
   int i, comp, Hindex;
   reax_list *bonds, *hbonds;
@@ -289,9 +289,10 @@ void Validate_ListsOMP( reax_system *system, storage * /*workspace */, reax_list
       else comp = bonds->num_intrs;
 
       if (End_Index(i, bonds) > comp) {
-        fprintf( stderr, "step%d-bondchk failed: i=%d end(i)=%d str(i+1)=%d\n",
-                 step, i, End_Index(i,bonds), comp );
-        MPI_Abort( comm, INSUFFICIENT_MEMORY );
+        char errmsg[256];
+        snprintf(errmsg, 256, "step%d-bondchk failed: i=%d end(i)=%d str(i+1)=%d\n",
+                  step, i, End_Index(i,bonds), comp );
+        system->error_ptr->one(FLERR,errmsg);
       }
     }
   }
@@ -315,9 +316,10 @@ void Validate_ListsOMP( reax_system *system, storage * /*workspace */, reax_list
         else comp = hbonds->num_intrs;
 
         if (End_Index(Hindex, hbonds) > comp) {
-          fprintf(stderr,"step%d-hbondchk failed: H=%d end(H)=%d str(H+1)=%d\n",
+          char errmsg[256];
+          snprintf(errmsg, 256, "step%d-hbondchk failed: H=%d end(H)=%d str(H+1)=%d\n",
                   step, Hindex, End_Index(Hindex,hbonds), comp );
-          MPI_Abort( comm, INSUFFICIENT_MEMORY );
+          system->error_ptr->one(FLERR, errmsg);
         }
       }
     }
diff --git a/src/USER-OMP/reaxc_init_md_omp.cpp b/src/USER-OMP/reaxc_init_md_omp.cpp
index bd15b3b9df..fe7682d035 100644
--- a/src/USER-OMP/reaxc_init_md_omp.cpp
+++ b/src/USER-OMP/reaxc_init_md_omp.cpp
@@ -43,7 +43,7 @@
 extern int Init_MPI_Datatypes(reax_system*, storage*, mpi_datatypes*, MPI_Comm, char*);
 extern int Init_System(reax_system*, control_params*, char*);
 extern int Init_Simulation_Data(reax_system*, control_params*, simulation_data*, char*);
-extern int Init_Workspace(reax_system*, control_params*, storage*, MPI_Comm, char*);
+extern int Init_Workspace(reax_system*, control_params*, storage*, char*);
 
 /* ---------------------------------------------------------------------- */
 
@@ -63,7 +63,7 @@ int Init_ListsOMP( reax_system *system, control_params *control,
   bond_top = (int*) calloc( system->total_cap, sizeof(int) );
   hb_top = (int*) calloc( system->local_cap, sizeof(int) );
   Estimate_Storages( system, control, lists,
-                     &Htop, hb_top, bond_top, &num_3body, comm );
+                     &Htop, hb_top, bond_top, &num_3body );
 
   if (control->hbond_cut > 0) {
     /* init H indexes */
@@ -75,9 +75,8 @@ int Init_ListsOMP( reax_system *system, control_params *control,
     total_hbonds = (int)(MAX( total_hbonds*saferzone, mincap*MIN_HBONDS ));
 
     if( !Make_List( system->Hcap, total_hbonds, TYP_HBOND,
-                    *lists+HBONDS, comm ) ) {
-      fprintf( stderr, "not enough space for hbonds list. terminating!\n" );
-      MPI_Abort( comm, INSUFFICIENT_MEMORY );
+                    *lists+HBONDS ) ) {
+      system->error_ptr->one( FLERR, "Not enough space for hbonds list. Terminating!" );
     }
   }
 
@@ -89,9 +88,8 @@ int Init_ListsOMP( reax_system *system, control_params *control,
   bond_cap = (int)(MAX( total_bonds*safezone, mincap*MIN_BONDS ));
 
   if( !Make_List( system->total_cap, bond_cap, TYP_BOND,
-                  *lists+BONDS, comm ) ) {
-    fprintf( stderr, "not enough space for bonds list. terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+                  *lists+BONDS ) ) {
+    system->error_ptr->one( FLERR, "Not enough space for bonds list. Terminating!\n" );
   }
 
   int nthreads = control->nthreads;
@@ -99,15 +97,14 @@ int Init_ListsOMP( reax_system *system, control_params *control,
 
   for (i = 0; i < bonds->num_intrs; ++i)
     bonds->select.bond_list[i].bo_data.CdboReduction =
-      (double*) smalloc(sizeof(double)*nthreads, "CdboReduction", comm);
+      (double*) smalloc(system->error_ptr, sizeof(double)*nthreads, "CdboReduction");
 
   /* 3bodies list */
   cap_3body = (int)(MAX( num_3body*safezone, MIN_3BODIES ));
   if( !Make_List( bond_cap, cap_3body, TYP_THREE_BODY,
-                  *lists+THREE_BODIES, comm ) ){
+                  *lists+THREE_BODIES ) ){
 
-    fprintf( stderr, "Problem in initializing angles list. Terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+    system->error_ptr->one( FLERR, "Problem in initializing angles list. Terminating!" );
   }
 
   free( hb_top );
@@ -125,60 +122,50 @@ void InitializeOMP( reax_system *system, control_params *control,
                  mpi_datatypes *mpi_data, MPI_Comm comm )
 {
   char msg[MAX_STR];
+  char errmsg[512];
 
 
   if (Init_MPI_Datatypes(system, workspace, mpi_data, comm, msg) == FAILURE) {
-    fprintf( stderr, "p%d: init_mpi_datatypes: could not create datatypes\n",
-             system->my_rank );
-    fprintf( stderr, "p%d: mpi_data couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    system->error_ptr->one( FLERR, "init_mpi_datatypes: could not create datatypes. "
+    "Mpi_data couldn't be initialized! Terminating.");
   }
 
   if (Init_System(system, control, msg) == FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: system could not be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    snprintf( errmsg, 512, "Error on: %s. "
+    "System could not be initialized! Terminating.", msg );
+    system->error_ptr->one(FLERR, errmsg);
   }
 
   if (Init_Simulation_Data( system, control, data, msg ) == FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: sim_data couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    snprintf( errmsg, 512, "Error on: %s. "
+    "Sim_data couldn't be initialized! Terminating.", msg );
+    system->error_ptr->one(FLERR, errmsg);
   }
 
-  if (Init_Workspace( system, control, workspace, mpi_data->world, msg ) ==
+  if (Init_Workspace( system, control, workspace, msg ) ==
       FAILURE) {
-    fprintf( stderr, "p%d:init_workspace: not enough memory\n",
-             system->my_rank );
-    fprintf( stderr, "p%d:workspace couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    system->error_ptr->one(FLERR, "init_workspace: not enough memory. "
+    "Workspace couldn't be initialized! Terminating.");
   }
 
   if (Init_ListsOMP( system, control, data, workspace, lists, mpi_data, msg ) ==
       FAILURE) {
-      fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-      fprintf( stderr, "p%d: system could not be initialized! terminating.\n",
-               system->my_rank );
-      MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+      snprintf( errmsg, 512, "Error on: %s. "
+      "System could not be initialized! Terminating.", msg );
+      system->error_ptr->one(FLERR, errmsg);
     }
 
   if (Init_Output_Files(system,control,out_control,mpi_data,msg)== FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: could not open output files! terminating...\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    snprintf( errmsg, 512, "Error on: %s"
+    "Could not open output files! Terminating.", msg );
+    system->error_ptr->one(FLERR, errmsg);
   }
 
   if (control->tabulate) {
     if (Init_Lookup_Tables( system, control, workspace, mpi_data, msg ) == FAILURE) {
-      fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-      fprintf( stderr, "p%d: couldn't create lookup table! terminating.\n",
-               system->my_rank );
-      MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+      snprintf( errmsg, 512, "Error on: %s."
+      " Couldn't create lookup table! Terminating.", msg );
+      system->error_ptr->one(FLERR, errmsg);
     }
   }
 
diff --git a/src/USER-OMP/reaxc_nonbonded_omp.cpp b/src/USER-OMP/reaxc_nonbonded_omp.cpp
index 41b1474791..a93cd54931 100644
--- a/src/USER-OMP/reaxc_nonbonded_omp.cpp
+++ b/src/USER-OMP/reaxc_nonbonded_omp.cpp
@@ -213,9 +213,9 @@ void vdW_Coulomb_Energy_OMP( reax_system *system, control_params *control,
           rvec_ScaledSum( delij, 1., system->my_atoms[i].x,
                           -1., system->my_atoms[j].x );
           f_tmp = -(CEvd + CEclmb);
-          pair_reax_ptr->ev_tally_thr_proxy( system->pair_ptr, i, j, natoms,
-                                             1, pe_vdw, e_ele, f_tmp,
-                                             delij[0], delij[1], delij[2], thr);
+          pair_reax_ptr->ev_tally_thr_proxy(system->pair_ptr, i, j, natoms,
+                                            1, pe_vdw, e_ele, f_tmp,
+                                            delij[0], delij[1], delij[2], thr);
         }
 
         if (control->virial == 0) {
diff --git a/src/USER-OMP/reaxc_valence_angles_omp.cpp b/src/USER-OMP/reaxc_valence_angles_omp.cpp
index 4164d39cab..195f16a75d 100644
--- a/src/USER-OMP/reaxc_valence_angles_omp.cpp
+++ b/src/USER-OMP/reaxc_valence_angles_omp.cpp
@@ -237,12 +237,12 @@ void Valence_AnglesOMP( reax_system *system, control_params *control,
 
       // Confirm that thb_intrs->num_intrs / nthreads is enough to hold all angles from a single atom
       if(my_offset >= (tid+1)*per_thread) {
-        int me;
-        MPI_Comm_rank(MPI_COMM_WORLD,&me);
-        fprintf( stderr, "step%d-ran out of space on angle_list on proc %i for atom %i:", data->step, me, j);
-        fprintf( stderr, " nthreads= %d, tid=%d, my_offset=%d, per_thread=%d\n", nthreads, tid, my_offset, per_thread);
-        fprintf( stderr, " num_intrs= %i  N= %i\n",thb_intrs->num_intrs , system->N);
-        MPI_Abort( MPI_COMM_WORLD, INSUFFICIENT_MEMORY );
+        char errmsg[512];
+        snprintf( errmsg, 512, "step%d-ran out of space on angle_list for atom %i:\n"
+        " nthreads= %d, tid=%d, my_offset=%d, per_thread=%d\n"
+        " num_intrs= %i  N= %i\n"
+        , data->step, j, nthreads, tid, my_offset, per_thread,thb_intrs->num_intrs , system->N);
+        control->error_ptr->one(FLERR, errmsg);
       }
 
       // Number of angles owned by this atom
@@ -601,9 +601,10 @@ void Valence_AnglesOMP( reax_system *system, control_params *control,
   if (num_thb_intrs >= thb_intrs->num_intrs * DANGER_ZONE) {
     workspace->realloc.num_3body = num_thb_intrs * TWICE;
     if (num_thb_intrs > thb_intrs->num_intrs) {
-      fprintf( stderr, "step%d-ran out of space on angle_list: top=%d, max=%d",
-               data->step, num_thb_intrs, thb_intrs->num_intrs );
-      MPI_Abort( MPI_COMM_WORLD, INSUFFICIENT_MEMORY );
+      char errmsg[128];
+      snprintf(errmsg, 128, "step%d-ran out of space on angle_list: top=%d, max=%d",
+               data->step, num_thb_intrs, thb_intrs->num_intrs);
+      control->error_ptr->one(FLERR, errmsg);
     }
   }
 
diff --git a/src/USER-PHONON/dynamical_matrix.cpp b/src/USER-PHONON/dynamical_matrix.cpp
index 372f4e4e31..d94bd11a80 100644
--- a/src/USER-PHONON/dynamical_matrix.cpp
+++ b/src/USER-PHONON/dynamical_matrix.cpp
@@ -138,6 +138,9 @@ void DynamicalMatrix::command(int narg, char **arg)
     else if (style == ESKM) options(narg-3,&arg[3]); //COME BACK
     else if (comm->me == 0 && screen) fprintf(screen,"Illegal Dynamical Matrix command\n");
 
+    if (atom->map_style == 0)
+      error->all(FLERR,"Dynamical_matrix command requires an atom map, see atom_modify");
+
     // move atoms by 3-vector or specified variable(s)
 
     if (style == REGULAR) {
@@ -240,7 +243,7 @@ void DynamicalMatrix::calculateMatrix()
     int nlocal = atom->nlocal;
     bigint natoms = atom->natoms;
     int *type = atom->type;
-    int *gm = groupmap;
+    bigint *gm = groupmap;
     double imass; // dynamical matrix element
     double *m = atom->mass;
     double **f = atom->f;
@@ -256,20 +259,30 @@ void DynamicalMatrix::calculateMatrix()
     //initialize dynmat to all zeros
     dynmat_clear(dynmat);
 
-    if (comm->me == 0 && screen) fprintf(screen,"Calculating Dynamical Matrix...\n");
+    if (comm->me == 0 && screen) {
+        fprintf(screen,"Calculating Dynamical Matrix ...\n");
+        fprintf(screen,"  Total # of atoms = " BIGINT_FORMAT "\n", natoms);
+        fprintf(screen,"  Atoms in group = " BIGINT_FORMAT "\n", gcount);
+        fprintf(screen,"  Total dynamical matrix elements = " BIGINT_FORMAT "\n", (dynlen*dynlen) );
+    }
+    
+    // emit dynlen rows of dimalpha*dynlen*dimbeta elements
 
     update->nsteps = 0;
+    int prog = 0;
     for (bigint i=1; i<=natoms; i++){
         local_idx = atom->map(i);
+        if (gm[i-1] < 0)
+            continue;
         for (bigint alpha=0; alpha<3; alpha++){
             displace_atom(local_idx, alpha, 1);
             update_force();
             for (bigint j=1; j<=natoms; j++){
                 local_jdx = atom->map(j);
                 if (local_idx >= 0 && local_jdx >= 0 && local_jdx < nlocal
-                    && gm[i-1] >= 0 && gm[j-1] >= 0){
+                    && gm[j-1] >= 0){
                     for (int beta=0; beta<3; beta++){
-                        dynmat[alpha][(gm[j-1])*3+beta] -= f[local_jdx][beta];
+                        dynmat[alpha][gm[j-1]*3+beta] -= f[local_jdx][beta];
                     }
                 }
             }
@@ -278,15 +291,15 @@ void DynamicalMatrix::calculateMatrix()
             for (bigint j=1; j<=natoms; j++){
                 local_jdx = atom->map(j);
                 if (local_idx >= 0 && local_jdx >= 0 && local_jdx < nlocal
-                    && gm[i-1] >= 0 && gm[j-1] >= 0){
+                    && gm[j-1] >= 0){
                     for (bigint beta=0; beta<3; beta++){
                         if (atom->rmass_flag == 1)
                             imass = sqrt(m[local_idx] * m[local_jdx]);
                         else
                             imass = sqrt(m[type[local_idx]] * m[type[local_jdx]]);
-                        dynmat[alpha][(gm[j-1])*3+beta] -= -f[local_jdx][beta];
-                        dynmat[alpha][(gm[j-1])*3+beta] /= (2 * del * imass);
-                        dynmat[alpha][(gm[j-1])*3+beta] *= conversion;
+                        dynmat[alpha][gm[j-1]*3+beta] -= -f[local_jdx][beta];
+                        dynmat[alpha][gm[j-1]*3+beta] /= (2 * del * imass);
+                        dynmat[alpha][gm[j-1]*3+beta] *= conversion;
                     }
                 }
             }
@@ -297,7 +310,16 @@ void DynamicalMatrix::calculateMatrix()
         if (me == 0)
             writeMatrix(fdynmat);
         dynmat_clear(dynmat);
+        if (comm->me == 0 && screen) {
+            int p = 10 * gm[i-1] / gcount;
+            if (p > prog) {
+              prog = p;
+              fprintf(screen," %d%%",p*10);
+              fflush(screen);
+            }
+        }
     }
+    if (comm->me == 0 && screen) fprintf(screen,"\n");
 
     for (int i=0; i < 3; i++)
         delete [] dynmat[i];
@@ -316,27 +338,24 @@ void DynamicalMatrix::calculateMatrix()
 
 void DynamicalMatrix::writeMatrix(double **dynmat)
 {
-    if (me != 0 || fp == NULL) return;
+    if (me != 0 || !fp)
+        return;
 
-    // print file comment lines
-
-    if (!binaryflag && fp) {
-        clearerr(fp);
+    clearerr(fp);
+    if (binaryflag) {
+        for (int i=0; i<3; i++)
+            fwrite(dynmat[i], sizeof(double), dynlen, fp);
+        if (ferror(fp))
+            error->one(FLERR, "Error writing to binary file");
+    } else {
         for (int i = 0; i < 3; i++) {
             for (bigint j = 0; j < dynlen; j++) {
                 if ((j+1)%3==0) fprintf(fp, "%4.8f\n", dynmat[i][j]);
                 else fprintf(fp, "%4.8f ",dynmat[i][j]);
             }
         }
-    }
-    if (ferror(fp))
-        error->one(FLERR,"Error writing to file");
-
-    if (binaryflag && fp) {
-        clearerr(fp);
-        fwrite(&dynmat[0], sizeof(double), 3 * dynlen, fp);
         if (ferror(fp))
-            error->one(FLERR, "Error writing to binary file");
+            error->one(FLERR,"Error writing to file");
     }
 }
 
@@ -490,6 +509,7 @@ void DynamicalMatrix::convert_units(const char *style)
 void DynamicalMatrix::create_groupmap()
 {
     //Create a group map which maps atom order onto group
+    // groupmap[global atom index-1] = output column/row
 
     int local_idx; // local index
     int gid = 0; //group index
@@ -498,7 +518,7 @@ void DynamicalMatrix::create_groupmap()
     bigint natoms = atom->natoms;
     int *recv = new int[comm->nprocs];
     int *displs = new int[comm->nprocs];
-    int *temp_groupmap = new int[natoms];
+    bigint *temp_groupmap = new bigint[natoms];
 
     //find number of local atoms in the group (final_gid)
     for (bigint i=1; i<=natoms; i++){
@@ -507,7 +527,7 @@ void DynamicalMatrix::create_groupmap()
             gid += 1; // gid at the end of loop is final_Gid
     }
     //create an array of length final_gid
-    int *sub_groupmap = new int[gid];
+    bigint *sub_groupmap = new bigint[gid];
 
     gid = 0;
     //create a map between global atom id and group atom id for each proc
@@ -524,7 +544,7 @@ void DynamicalMatrix::create_groupmap()
         recv[i] = 0;
     }
     recv[comm->me] = gid;
-    MPI_Allreduce(recv,displs,4,MPI_INT,MPI_SUM,world);
+    MPI_Allreduce(recv,displs,comm->nprocs,MPI_INT,MPI_SUM,world);
     for (int i=0; i<comm->nprocs; i++){
         recv[i]=displs[i];
         if (i>0) displs[i] = displs[i-1]+recv[i-1];
@@ -532,15 +552,17 @@ void DynamicalMatrix::create_groupmap()
     }
 
     //combine subgroup maps into total temporary groupmap
-    MPI_Allgatherv(sub_groupmap,gid,MPI_INT,temp_groupmap,recv,displs,MPI_INT,world);
+    MPI_Allgatherv(sub_groupmap,gid,MPI_LMP_BIGINT,temp_groupmap,recv,displs,MPI_LMP_BIGINT,world);
     std::sort(temp_groupmap,temp_groupmap+gcount);
 
     //populate member groupmap based on temp groupmap
-    for (bigint i=0; i<natoms; i++){
-        if (i==temp_groupmap[i]-1)
-            groupmap[i] = temp_groupmap[i]-1;
+    bigint j = 0;
+    for (bigint i=1; i<=natoms; i++){
+        // flag groupmap contents that are in temp_groupmap
+        if (j < gcount && i == temp_groupmap[j])
+            groupmap[i-1] = j++;
         else
-            groupmap[i] = -1;
+            groupmap[i-1] = -1;
     }
 
     //free that memory!
diff --git a/src/USER-PHONON/dynamical_matrix.h b/src/USER-PHONON/dynamical_matrix.h
index 56de814e97..8ff11044ea 100644
--- a/src/USER-PHONON/dynamical_matrix.h
+++ b/src/USER-PHONON/dynamical_matrix.h
@@ -58,7 +58,7 @@ namespace LAMMPS_NS {
         bigint dynlen;             // rank of dynamical matrix
         int scaleflag;
         int me;
-        int *groupmap;
+        bigint *groupmap;
 
         int compressed;            // 1 if dump file is written compressed, 0 no
         int binaryflag;            // 1 if dump file is written binary, 0 no
diff --git a/src/USER-PTM/ptm_polar.cpp b/src/USER-PTM/ptm_polar.cpp
index 7a2695b504..5e234127a9 100644
--- a/src/USER-PTM/ptm_polar.cpp
+++ b/src/USER-PTM/ptm_polar.cpp
@@ -88,6 +88,7 @@
 #include <cmath>
 #include <algorithm>
 #include <cstring>
+#include "ptm_polar.h"
 #include "ptm_quat.h"
 
 
diff --git a/src/USER-QUIP/pair_quip.cpp b/src/USER-QUIP/pair_quip.cpp
index fce6313754..c3b03bc5e0 100644
--- a/src/USER-QUIP/pair_quip.cpp
+++ b/src/USER-QUIP/pair_quip.cpp
@@ -75,8 +75,7 @@ void PairQUIP::compute(int eflag, int vflag)
 
   double *quip_local_e, *quip_force, *quip_local_virial, *quip_virial, quip_energy, *lattice;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else ev_unset();
+  ev_init(eflag,vflag);
 
   inum = list->inum;
   ilist = list->ilist;
diff --git a/src/USER-REAXC/fix_reaxc.cpp b/src/USER-REAXC/fix_reaxc.cpp
index 361733f3ca..dc67ad6ffb 100644
--- a/src/USER-REAXC/fix_reaxc.cpp
+++ b/src/USER-REAXC/fix_reaxc.cpp
@@ -41,7 +41,7 @@ FixReaxC::FixReaxC(LAMMPS *lmp,int narg, char **arg) :
 {
   // perform initial allocation of atom-based arrays
   // register with atom class
-  
+
   oldnmax = 0;
   num_bonds = NULL;
   num_hbonds = NULL;
diff --git a/src/USER-REAXC/pair_reaxc.cpp b/src/USER-REAXC/pair_reaxc.cpp
index b68e0d0779..3f80f2101d 100644
--- a/src/USER-REAXC/pair_reaxc.cpp
+++ b/src/USER-REAXC/pair_reaxc.cpp
@@ -76,8 +76,10 @@ PairReaxC::PairReaxC(LAMMPS *lmp) : Pair(lmp)
 
   system = (reax_system *)
     memory->smalloc(sizeof(reax_system),"reax:system");
+  memset(system,0,sizeof(reax_system));
   control = (control_params *)
     memory->smalloc(sizeof(control_params),"reax:control");
+  memset(control,0,sizeof(control_params));
   data = (simulation_data *)
     memory->smalloc(sizeof(simulation_data),"reax:data");
   workspace = (storage *)
@@ -87,10 +89,11 @@ PairReaxC::PairReaxC(LAMMPS *lmp) : Pair(lmp)
   memset(lists,0,LIST_N * sizeof(reax_list));
   out_control = (output_controls *)
     memory->smalloc(sizeof(output_controls),"reax:out_control");
+  memset(out_control,0,sizeof(output_controls));
   mpi_data = (mpi_datatypes *)
     memory->smalloc(sizeof(mpi_datatypes),"reax:mpi");
 
-  MPI_Comm_rank(world,&system->my_rank);
+  control->me = system->my_rank = comm->me;
 
   system->my_coords[0] = 0;
   system->my_coords[1] = 0;
@@ -108,6 +111,8 @@ PairReaxC::PairReaxC(LAMMPS *lmp) : Pair(lmp)
   system->bndry_cuts.ghost_cutoff = 0;
   system->my_atoms = NULL;
   system->pair_ptr = this;
+  system->error_ptr = error;
+  control->error_ptr = error;
 
   system->omp_active = 0;
 
@@ -139,10 +144,10 @@ PairReaxC::~PairReaxC()
 
     if (control->tabulate ) Deallocate_Lookup_Tables( system);
 
-    if (control->hbond_cut > 0 )  Delete_List( lists+HBONDS, world);
-    Delete_List( lists+BONDS, world );
-    Delete_List( lists+THREE_BODIES, world );
-    Delete_List( lists+FAR_NBRS, world );
+    if (control->hbond_cut > 0 )  Delete_List( lists+HBONDS );
+    Delete_List( lists+BONDS );
+    Delete_List( lists+THREE_BODIES );
+    Delete_List( lists+FAR_NBRS );
 
     DeAllocate_Workspace( control, workspace );
     DeAllocate_System( system );
@@ -380,6 +385,14 @@ void PairReaxC::init_style( )
     error->all(FLERR,"Pair style reax/c requires atom IDs");
   if (force->newton_pair == 0)
     error->all(FLERR,"Pair style reax/c requires newton pair on");
+  if ((atom->map_tag_max > 99999999) && (comm->me == 0))
+    error->warning(FLERR,"Some Atom-IDs are too large. Pair style reax/c "
+                   "native output files may get misformatted or corrupted");
+
+  // because system->bigN is an int, we cannot have more atoms than MAXSMALLINT
+
+  if (atom->natoms > MAXSMALLINT)
+    error->all(FLERR,"Too many atoms for pair style reax/c");
 
   // need a half neighbor list w/ Newton off and ghost neighbors
   // built whenever re-neighboring occurs
@@ -394,7 +407,8 @@ void PairReaxC::init_style( )
                    "increased neighbor list skin.");
 
   for( int i = 0; i < LIST_N; ++i )
-    lists[i].allocated = 0;
+    if (lists[i].allocated != 1)
+      lists[i].allocated = 0;
 
   if (fix_reax == NULL) {
     char **fixarg = new char*[3];
@@ -436,13 +450,14 @@ void PairReaxC::setup( )
 
     // initialize my data structures
 
-    PreAllocate_Space( system, control, workspace, world );
+    PreAllocate_Space( system, control, workspace );
     write_reax_atoms();
 
     int num_nbrs = estimate_reax_lists();
     if(!Make_List(system->total_cap, num_nbrs, TYP_FAR_NEIGHBOR,
-                  lists+FAR_NBRS, world))
-      error->all(FLERR,"Pair reax/c problem in far neighbor list");
+                  lists+FAR_NBRS))
+      error->one(FLERR,"Pair reax/c problem in far neighbor list");
+    (lists+FAR_NBRS)->error_ptr=error;
 
     write_reax_lists();
     Initialize( system, control, data, workspace, &lists, out_control,
@@ -465,7 +480,7 @@ void PairReaxC::setup( )
 
     // check if I need to shrink/extend my data-structs
 
-    ReAllocate( system, control, data, workspace, &lists, mpi_data );
+    ReAllocate( system, control, data, workspace, &lists );
   }
 
   bigint local_ngroup = list->inum;
@@ -497,8 +512,7 @@ void PairReaxC::compute(int eflag, int vflag)
   int *num_hbonds = fix_reax->num_hbonds;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else ev_unset();
+  ev_init(eflag,vflag);
 
   if (vflag_global) control->virial = 1;
   else control->virial = 0;
@@ -517,7 +531,7 @@ void PairReaxC::compute(int eflag, int vflag)
 
   setup();
 
-  Reset( system, control, data, workspace, &lists, world );
+  Reset( system, control, data, workspace, &lists );
   workspace->realloc.num_far = write_reax_lists();
   // timing for filling in the reax lists
   if (comm->me == 0) {
diff --git a/src/USER-REAXC/reaxc_allocate.cpp b/src/USER-REAXC/reaxc_allocate.cpp
index 700e68514c..460f8aeb6a 100644
--- a/src/USER-REAXC/reaxc_allocate.cpp
+++ b/src/USER-REAXC/reaxc_allocate.cpp
@@ -35,12 +35,14 @@
 #include <omp.h>
 #endif
 
+#include "error.h"
+
 /* allocate space for my_atoms
    important: we cannot know the exact number of atoms that will fall into a
    process's box throughout the whole simulation. therefore
    we need to make upper bound estimates for various data structures */
 int PreAllocate_Space( reax_system *system, control_params * /*control*/,
-                       storage * workspace, MPI_Comm comm )
+                       storage * workspace )
 {
   int mincap = system->mincap;
   double safezone = system->safezone;
@@ -51,7 +53,7 @@ int PreAllocate_Space( reax_system *system, control_params * /*control*/,
   system->total_cap = MAX( (int)(system->N * safezone), mincap );
 
   system->my_atoms = (reax_atom*)
-    scalloc( system->total_cap, sizeof(reax_atom), "my_atoms", comm );
+    scalloc(system->error_ptr,  system->total_cap, sizeof(reax_atom), "my_atoms");
 
   // Nullify some arrays only used in omp styles
   // Should be safe to do here since called in pair->setup();
@@ -86,39 +88,39 @@ void DeAllocate_System( reax_system *system )
   int ntypes;
   reax_interaction *ff_params;
 
-  // dealloocate the atom list
-  sfree( system->my_atoms, "system->my_atoms" );
+  // deallocate the atom list
+  sfree(system->error_ptr,  system->my_atoms, "system->my_atoms" );
 
   // deallocate the ffield parameters storage
   ff_params = &(system->reax_param);
   ntypes = ff_params->num_atom_types;
 
-  sfree( ff_params->gp.l, "ff:globals" );
+  sfree(system->error_ptr,  ff_params->gp.l, "ff:globals" );
 
   for( i = 0; i < ntypes; ++i ) {
     for( j = 0; j < ntypes; ++j ) {
       for( k = 0; k < ntypes; ++k ) {
-        sfree( ff_params->fbp[i][j][k], "ff:fbp[i,j,k]" );
+        sfree(system->error_ptr,  ff_params->fbp[i][j][k], "ff:fbp[i,j,k]" );
       }
-      sfree( ff_params->fbp[i][j], "ff:fbp[i,j]" );
-      sfree( ff_params->thbp[i][j], "ff:thbp[i,j]" );
-      sfree( ff_params->hbp[i][j], "ff:hbp[i,j]" );
+      sfree(system->error_ptr,  ff_params->fbp[i][j], "ff:fbp[i,j]" );
+      sfree(system->error_ptr,  ff_params->thbp[i][j], "ff:thbp[i,j]" );
+      sfree(system->error_ptr,  ff_params->hbp[i][j], "ff:hbp[i,j]" );
     }
-    sfree( ff_params->fbp[i], "ff:fbp[i]" );
-    sfree( ff_params->thbp[i], "ff:thbp[i]" );
-    sfree( ff_params->hbp[i], "ff:hbp[i]" );
-    sfree( ff_params->tbp[i], "ff:tbp[i]" );
+    sfree(system->error_ptr,  ff_params->fbp[i], "ff:fbp[i]" );
+    sfree(system->error_ptr,  ff_params->thbp[i], "ff:thbp[i]" );
+    sfree(system->error_ptr,  ff_params->hbp[i], "ff:hbp[i]" );
+    sfree(system->error_ptr,  ff_params->tbp[i], "ff:tbp[i]" );
   }
-  sfree( ff_params->fbp, "ff:fbp" );
-  sfree( ff_params->thbp, "ff:thbp" );
-  sfree( ff_params->hbp, "ff:hbp" );
-  sfree( ff_params->tbp, "ff:tbp" );
-  sfree( ff_params->sbp, "ff:sbp" );
+  sfree(system->error_ptr,  ff_params->fbp, "ff:fbp" );
+  sfree(system->error_ptr,  ff_params->thbp, "ff:thbp" );
+  sfree(system->error_ptr,  ff_params->hbp, "ff:hbp" );
+  sfree(system->error_ptr,  ff_params->tbp, "ff:tbp" );
+  sfree(system->error_ptr,  ff_params->sbp, "ff:sbp" );
 }
 
 
 /*************       workspace        *************/
-void DeAllocate_Workspace( control_params * /*control*/, storage *workspace )
+void DeAllocate_Workspace( control_params * control, storage *workspace )
 {
   int i;
 
@@ -129,86 +131,86 @@ void DeAllocate_Workspace( control_params * /*control*/, storage *workspace )
 
   /* communication storage */
   for( i = 0; i < MAX_NBRS; ++i ) {
-    sfree( workspace->tmp_dbl[i], "tmp_dbl[i]" );
-    sfree( workspace->tmp_rvec[i], "tmp_rvec[i]" );
-    sfree( workspace->tmp_rvec2[i], "tmp_rvec2[i]" );
+    sfree(control->error_ptr,  workspace->tmp_dbl[i], "tmp_dbl[i]" );
+    sfree(control->error_ptr,  workspace->tmp_rvec[i], "tmp_rvec[i]" );
+    sfree(control->error_ptr,  workspace->tmp_rvec2[i], "tmp_rvec2[i]" );
   }
 
   /* bond order storage */
-  sfree( workspace->within_bond_box, "skin" );
-  sfree( workspace->total_bond_order, "total_bo" );
-  sfree( workspace->Deltap, "Deltap" );
-  sfree( workspace->Deltap_boc, "Deltap_boc" );
-  sfree( workspace->dDeltap_self, "dDeltap_self" );
-  sfree( workspace->Delta, "Delta" );
-  sfree( workspace->Delta_lp, "Delta_lp" );
-  sfree( workspace->Delta_lp_temp, "Delta_lp_temp" );
-  sfree( workspace->dDelta_lp, "dDelta_lp" );
-  sfree( workspace->dDelta_lp_temp, "dDelta_lp_temp" );
-  sfree( workspace->Delta_e, "Delta_e" );
-  sfree( workspace->Delta_boc, "Delta_boc" );
-  sfree( workspace->Delta_val, "Delta_val" );
-  sfree( workspace->nlp, "nlp" );
-  sfree( workspace->nlp_temp, "nlp_temp" );
-  sfree( workspace->Clp, "Clp" );
-  sfree( workspace->vlpex, "vlpex" );
-  sfree( workspace->bond_mark, "bond_mark" );
-  sfree( workspace->done_after, "done_after" );
+  sfree(control->error_ptr,  workspace->within_bond_box, "skin" );
+  sfree(control->error_ptr,  workspace->total_bond_order, "total_bo" );
+  sfree(control->error_ptr,  workspace->Deltap, "Deltap" );
+  sfree(control->error_ptr,  workspace->Deltap_boc, "Deltap_boc" );
+  sfree(control->error_ptr,  workspace->dDeltap_self, "dDeltap_self" );
+  sfree(control->error_ptr,  workspace->Delta, "Delta" );
+  sfree(control->error_ptr,  workspace->Delta_lp, "Delta_lp" );
+  sfree(control->error_ptr,  workspace->Delta_lp_temp, "Delta_lp_temp" );
+  sfree(control->error_ptr,  workspace->dDelta_lp, "dDelta_lp" );
+  sfree(control->error_ptr,  workspace->dDelta_lp_temp, "dDelta_lp_temp" );
+  sfree(control->error_ptr,  workspace->Delta_e, "Delta_e" );
+  sfree(control->error_ptr,  workspace->Delta_boc, "Delta_boc" );
+  sfree(control->error_ptr,  workspace->Delta_val, "Delta_val" );
+  sfree(control->error_ptr,  workspace->nlp, "nlp" );
+  sfree(control->error_ptr,  workspace->nlp_temp, "nlp_temp" );
+  sfree(control->error_ptr,  workspace->Clp, "Clp" );
+  sfree(control->error_ptr,  workspace->vlpex, "vlpex" );
+  sfree(control->error_ptr,  workspace->bond_mark, "bond_mark" );
+  sfree(control->error_ptr,  workspace->done_after, "done_after" );
 
   /* QEq storage */
-  sfree( workspace->Hdia_inv, "Hdia_inv" );
-  sfree( workspace->b_s, "b_s" );
-  sfree( workspace->b_t, "b_t" );
-  sfree( workspace->b_prc, "b_prc" );
-  sfree( workspace->b_prm, "b_prm" );
-  sfree( workspace->s, "s" );
-  sfree( workspace->t, "t" );
-  sfree( workspace->droptol, "droptol" );
-  sfree( workspace->b, "b" );
-  sfree( workspace->x, "x" );
+  sfree(control->error_ptr,  workspace->Hdia_inv, "Hdia_inv" );
+  sfree(control->error_ptr,  workspace->b_s, "b_s" );
+  sfree(control->error_ptr,  workspace->b_t, "b_t" );
+  sfree(control->error_ptr,  workspace->b_prc, "b_prc" );
+  sfree(control->error_ptr,  workspace->b_prm, "b_prm" );
+  sfree(control->error_ptr,  workspace->s, "s" );
+  sfree(control->error_ptr,  workspace->t, "t" );
+  sfree(control->error_ptr,  workspace->droptol, "droptol" );
+  sfree(control->error_ptr,  workspace->b, "b" );
+  sfree(control->error_ptr,  workspace->x, "x" );
 
   /* GMRES storage */
   for( i = 0; i < RESTART+1; ++i ) {
-    sfree( workspace->h[i], "h[i]" );
-    sfree( workspace->v[i], "v[i]" );
+    sfree(control->error_ptr,  workspace->h[i], "h[i]" );
+    sfree(control->error_ptr,  workspace->v[i], "v[i]" );
   }
-  sfree( workspace->h, "h" );
-  sfree( workspace->v, "v" );
-  sfree( workspace->y, "y" );
-  sfree( workspace->z, "z" );
-  sfree( workspace->g, "g" );
-  sfree( workspace->hs, "hs" );
-  sfree( workspace->hc, "hc" );
+  sfree(control->error_ptr,  workspace->h, "h" );
+  sfree(control->error_ptr,  workspace->v, "v" );
+  sfree(control->error_ptr,  workspace->y, "y" );
+  sfree(control->error_ptr,  workspace->z, "z" );
+  sfree(control->error_ptr,  workspace->g, "g" );
+  sfree(control->error_ptr,  workspace->hs, "hs" );
+  sfree(control->error_ptr,  workspace->hc, "hc" );
   /* CG storage */
-  sfree( workspace->r, "r" );
-  sfree( workspace->d, "d" );
-  sfree( workspace->q, "q" );
-  sfree( workspace->p, "p" );
-  sfree( workspace->r2, "r2" );
-  sfree( workspace->d2, "d2" );
-  sfree( workspace->q2, "q2" );
-  sfree( workspace->p2, "p2" );
+  sfree(control->error_ptr,  workspace->r, "r" );
+  sfree(control->error_ptr,  workspace->d, "d" );
+  sfree(control->error_ptr,  workspace->q, "q" );
+  sfree(control->error_ptr,  workspace->p, "p" );
+  sfree(control->error_ptr,  workspace->r2, "r2" );
+  sfree(control->error_ptr,  workspace->d2, "d2" );
+  sfree(control->error_ptr,  workspace->q2, "q2" );
+  sfree(control->error_ptr,  workspace->p2, "p2" );
 
   /* integrator storage */
-  sfree( workspace->v_const, "v_const" );
+  sfree(control->error_ptr,  workspace->v_const, "v_const" );
 
   /* force related storage */
-  sfree( workspace->f, "f" );
-  sfree( workspace->CdDelta, "CdDelta" );
+  sfree(control->error_ptr,  workspace->f, "f" );
+  sfree(control->error_ptr,  workspace->CdDelta, "CdDelta" );
 
   /* reductions */
 #ifdef LMP_USER_OMP
-  if (workspace->CdDeltaReduction) sfree( workspace->CdDeltaReduction, "cddelta_reduce" );
-  if (workspace->forceReduction) sfree( workspace->forceReduction, "f_reduce" );
-  if (workspace->valence_angle_atom_myoffset) sfree( workspace->valence_angle_atom_myoffset, "valence_angle_atom_myoffset");
-  if (workspace->my_ext_pressReduction) sfree( workspace->my_ext_pressReduction, "ext_press_reduce");
+  if (workspace->CdDeltaReduction) sfree(control->error_ptr,  workspace->CdDeltaReduction, "cddelta_reduce" );
+  if (workspace->forceReduction) sfree(control->error_ptr,  workspace->forceReduction, "f_reduce" );
+  if (workspace->valence_angle_atom_myoffset) sfree(control->error_ptr,  workspace->valence_angle_atom_myoffset, "valence_angle_atom_myoffset");
+  if (workspace->my_ext_pressReduction) sfree(control->error_ptr,  workspace->my_ext_pressReduction, "ext_press_reduce");
 #endif
 }
 
 
 int Allocate_Workspace( reax_system * /*system*/, control_params * control,
                         storage *workspace, int local_cap, int total_cap,
-                        MPI_Comm comm, char * /*msg*/ )
+                        char * /*msg*/ )
 {
   int i, total_real, total_rvec, local_rvec;
 
@@ -220,94 +222,94 @@ int Allocate_Workspace( reax_system * /*system*/, control_params * control,
   /* communication storage */
   for( i = 0; i < MAX_NBRS; ++i ) {
     workspace->tmp_dbl[i] = (double*)
-      scalloc( total_cap, sizeof(double), "tmp_dbl", comm );
+      scalloc(control->error_ptr,  total_cap, sizeof(double), "tmp_dbl");
     workspace->tmp_rvec[i] = (rvec*)
-      scalloc( total_cap, sizeof(rvec), "tmp_rvec", comm );
+      scalloc(control->error_ptr,  total_cap, sizeof(rvec), "tmp_rvec");
     workspace->tmp_rvec2[i] = (rvec2*)
-      scalloc( total_cap, sizeof(rvec2), "tmp_rvec2", comm );
+      scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "tmp_rvec2");
   }
 
   /* bond order related storage  */
   workspace->within_bond_box = (int*)
-    scalloc( total_cap, sizeof(int), "skin", comm );
-  workspace->total_bond_order = (double*) smalloc( total_real, "total_bo", comm );
-  workspace->Deltap = (double*) smalloc( total_real, "Deltap", comm );
-  workspace->Deltap_boc = (double*) smalloc( total_real, "Deltap_boc", comm );
-  workspace->dDeltap_self = (rvec*) smalloc( total_rvec, "dDeltap_self", comm );
-  workspace->Delta = (double*) smalloc( total_real, "Delta", comm );
-  workspace->Delta_lp = (double*) smalloc( total_real, "Delta_lp", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(int), "skin");
+  workspace->total_bond_order = (double*) smalloc(control->error_ptr,  total_real, "total_bo");
+  workspace->Deltap = (double*) smalloc(control->error_ptr,  total_real, "Deltap");
+  workspace->Deltap_boc = (double*) smalloc(control->error_ptr,  total_real, "Deltap_boc");
+  workspace->dDeltap_self = (rvec*) smalloc(control->error_ptr,  total_rvec, "dDeltap_self");
+  workspace->Delta = (double*) smalloc(control->error_ptr,  total_real, "Delta");
+  workspace->Delta_lp = (double*) smalloc(control->error_ptr,  total_real, "Delta_lp");
   workspace->Delta_lp_temp = (double*)
-    smalloc( total_real, "Delta_lp_temp", comm );
-  workspace->dDelta_lp = (double*) smalloc( total_real, "dDelta_lp", comm );
+    smalloc(control->error_ptr,  total_real, "Delta_lp_temp");
+  workspace->dDelta_lp = (double*) smalloc(control->error_ptr,  total_real, "dDelta_lp");
   workspace->dDelta_lp_temp = (double*)
-    smalloc( total_real, "dDelta_lp_temp", comm );
-  workspace->Delta_e = (double*) smalloc( total_real, "Delta_e", comm );
-  workspace->Delta_boc = (double*) smalloc( total_real, "Delta_boc", comm );
-  workspace->Delta_val = (double*) smalloc( total_real, "Delta_val", comm );
-  workspace->nlp = (double*) smalloc( total_real, "nlp", comm );
-  workspace->nlp_temp = (double*) smalloc( total_real, "nlp_temp", comm );
-  workspace->Clp = (double*) smalloc( total_real, "Clp", comm );
-  workspace->vlpex = (double*) smalloc( total_real, "vlpex", comm );
+    smalloc(control->error_ptr,  total_real, "dDelta_lp_temp");
+  workspace->Delta_e = (double*) smalloc(control->error_ptr,  total_real, "Delta_e");
+  workspace->Delta_boc = (double*) smalloc(control->error_ptr,  total_real, "Delta_boc");
+  workspace->Delta_val = (double*) smalloc(control->error_ptr,  total_real, "Delta_val");
+  workspace->nlp = (double*) smalloc(control->error_ptr,  total_real, "nlp");
+  workspace->nlp_temp = (double*) smalloc(control->error_ptr,  total_real, "nlp_temp");
+  workspace->Clp = (double*) smalloc(control->error_ptr,  total_real, "Clp");
+  workspace->vlpex = (double*) smalloc(control->error_ptr,  total_real, "vlpex");
   workspace->bond_mark = (int*)
-    scalloc( total_cap, sizeof(int), "bond_mark", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(int), "bond_mark");
   workspace->done_after = (int*)
-    scalloc( total_cap, sizeof(int), "done_after", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(int), "done_after");
 
   /* QEq storage */
   workspace->Hdia_inv = (double*)
-    scalloc( total_cap, sizeof(double), "Hdia_inv", comm );
-  workspace->b_s = (double*) scalloc( total_cap, sizeof(double), "b_s", comm );
-  workspace->b_t = (double*) scalloc( total_cap, sizeof(double), "b_t", comm );
-  workspace->b_prc = (double*) scalloc( total_cap, sizeof(double), "b_prc", comm );
-  workspace->b_prm = (double*) scalloc( total_cap, sizeof(double), "b_prm", comm );
-  workspace->s = (double*) scalloc( total_cap, sizeof(double), "s", comm );
-  workspace->t = (double*) scalloc( total_cap, sizeof(double), "t", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(double), "Hdia_inv");
+  workspace->b_s = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "b_s");
+  workspace->b_t = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "b_t");
+  workspace->b_prc = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "b_prc");
+  workspace->b_prm = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "b_prm");
+  workspace->s = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "s");
+  workspace->t = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "t");
   workspace->droptol = (double*)
-    scalloc( total_cap, sizeof(double), "droptol", comm );
-  workspace->b = (rvec2*) scalloc( total_cap, sizeof(rvec2), "b", comm );
-  workspace->x = (rvec2*) scalloc( total_cap, sizeof(rvec2), "x", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(double), "droptol");
+  workspace->b = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "b");
+  workspace->x = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "x");
 
   /* GMRES storage */
-  workspace->y = (double*) scalloc( RESTART+1, sizeof(double), "y", comm );
-  workspace->z = (double*) scalloc( RESTART+1, sizeof(double), "z", comm );
-  workspace->g = (double*) scalloc( RESTART+1, sizeof(double), "g", comm );
-  workspace->h = (double**) scalloc( RESTART+1, sizeof(double*), "h", comm );
-  workspace->hs = (double*) scalloc( RESTART+1, sizeof(double), "hs", comm );
-  workspace->hc = (double*) scalloc( RESTART+1, sizeof(double), "hc", comm );
-  workspace->v = (double**) scalloc( RESTART+1, sizeof(double*), "v", comm );
+  workspace->y = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "y");
+  workspace->z = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "z");
+  workspace->g = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "g");
+  workspace->h = (double**) scalloc(control->error_ptr,  RESTART+1, sizeof(double*), "h");
+  workspace->hs = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "hs");
+  workspace->hc = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "hc");
+  workspace->v = (double**) scalloc(control->error_ptr,  RESTART+1, sizeof(double*), "v");
 
   for( i = 0; i < RESTART+1; ++i ) {
-    workspace->h[i] = (double*) scalloc( RESTART+1, sizeof(double), "h[i]", comm );
-    workspace->v[i] = (double*) scalloc( total_cap, sizeof(double), "v[i]", comm );
+    workspace->h[i] = (double*) scalloc(control->error_ptr,  RESTART+1, sizeof(double), "h[i]");
+    workspace->v[i] = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "v[i]");
   }
 
   /* CG storage */
-  workspace->r = (double*) scalloc( total_cap, sizeof(double), "r", comm );
-  workspace->d = (double*) scalloc( total_cap, sizeof(double), "d", comm );
-  workspace->q = (double*) scalloc( total_cap, sizeof(double), "q", comm );
-  workspace->p = (double*) scalloc( total_cap, sizeof(double), "p", comm );
-  workspace->r2 = (rvec2*) scalloc( total_cap, sizeof(rvec2), "r2", comm );
-  workspace->d2 = (rvec2*) scalloc( total_cap, sizeof(rvec2), "d2", comm );
-  workspace->q2 = (rvec2*) scalloc( total_cap, sizeof(rvec2), "q2", comm );
-  workspace->p2 = (rvec2*) scalloc( total_cap, sizeof(rvec2), "p2", comm );
+  workspace->r = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "r");
+  workspace->d = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "d");
+  workspace->q = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "q");
+  workspace->p = (double*) scalloc(control->error_ptr,  total_cap, sizeof(double), "p");
+  workspace->r2 = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "r2");
+  workspace->d2 = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "d2");
+  workspace->q2 = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "q2");
+  workspace->p2 = (rvec2*) scalloc(control->error_ptr,  total_cap, sizeof(rvec2), "p2");
 
   /* integrator storage */
-  workspace->v_const = (rvec*) smalloc( local_rvec, "v_const", comm );
+  workspace->v_const = (rvec*) smalloc(control->error_ptr,  local_rvec, "v_const");
 
   /* force related storage */
-  workspace->f = (rvec*) scalloc( total_cap, sizeof(rvec), "f", comm );
+  workspace->f = (rvec*) scalloc(control->error_ptr,  total_cap, sizeof(rvec), "f");
   workspace->CdDelta = (double*)
-    scalloc( total_cap, sizeof(double), "CdDelta", comm );
+    scalloc(control->error_ptr,  total_cap, sizeof(double), "CdDelta");
 
   // storage for reductions with multiple threads
 #ifdef LMP_USER_OMP
-  workspace->CdDeltaReduction = (double *) scalloc(sizeof(double), total_cap*control->nthreads,
-                                                 "cddelta_reduce", comm);
+  workspace->CdDeltaReduction = (double *) scalloc(control->error_ptr, sizeof(double), total_cap*control->nthreads,
+                                                 "cddelta_reduce");
 
-  workspace->forceReduction = (rvec *) scalloc(sizeof(rvec), total_cap*control->nthreads,
-                                               "forceReduction", comm);
+  workspace->forceReduction = (rvec *) scalloc(control->error_ptr, sizeof(rvec), total_cap*control->nthreads,
+                                               "forceReduction");
 
-  workspace->valence_angle_atom_myoffset = (int *) scalloc(sizeof(int), total_cap, "valence_angle_atom_myoffset", comm);
+  workspace->valence_angle_atom_myoffset = (int *) scalloc(control->error_ptr, sizeof(int), total_cap, "valence_angle_atom_myoffset");
   workspace->my_ext_pressReduction = (rvec *) calloc(sizeof(rvec), control->nthreads);
 #else
   LMP_UNUSED_PARAM(control);
@@ -318,18 +320,16 @@ int Allocate_Workspace( reax_system * /*system*/, control_params * control,
 
 
 static void Reallocate_Neighbor_List( reax_list *far_nbrs, int n,
-                                      int num_intrs, MPI_Comm comm )
+                                      int num_intrs )
 {
-  Delete_List( far_nbrs, comm );
-  if(!Make_List( n, num_intrs, TYP_FAR_NEIGHBOR, far_nbrs, comm )){
-    fprintf(stderr, "Problem in initializing far nbrs list. Terminating!\n");
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+  Delete_List( far_nbrs);
+  if(!Make_List( n, num_intrs, TYP_FAR_NEIGHBOR, far_nbrs )){
+    far_nbrs->error_ptr->one(FLERR,"Problem in initializing far neighbors list");
   }
 }
 
 
-static int Reallocate_HBonds_List( reax_system *system, reax_list *hbonds,
-                                   MPI_Comm comm )
+static int Reallocate_HBonds_List( reax_system *system, reax_list *hbonds )
 {
   int i, total_hbonds;
 
@@ -343,10 +343,9 @@ static int Reallocate_HBonds_List( reax_system *system, reax_list *hbonds,
     }
   total_hbonds = (int)(MAX( total_hbonds*saferzone, mincap*MIN_HBONDS ));
 
-  Delete_List( hbonds, comm );
-  if (!Make_List( system->Hcap, total_hbonds, TYP_HBOND, hbonds, comm )) {
-    fprintf( stderr, "not enough space for hbonds list. terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+  Delete_List( hbonds);
+  if (!Make_List( system->Hcap, total_hbonds, TYP_HBOND, hbonds )) {
+    hbonds->error_ptr->one(FLERR, "Not enough space for hydrogen bonds list");
   }
 
   return total_hbonds;
@@ -354,8 +353,7 @@ static int Reallocate_HBonds_List( reax_system *system, reax_list *hbonds,
 
 
 static int Reallocate_Bonds_List( reax_system *system, reax_list *bonds,
-                                  int *total_bonds, int *est_3body,
-                                  MPI_Comm comm )
+                                  int *total_bonds, int *est_3body )
 {
   int i;
 
@@ -373,13 +371,12 @@ static int Reallocate_Bonds_List( reax_system *system, reax_list *bonds,
 #ifdef LMP_USER_OMP
   if (system->omp_active)
     for (i = 0; i < bonds->num_intrs; ++i)
-      sfree(bonds->select.bond_list[i].bo_data.CdboReduction, "CdboReduction");
+      sfree(system->error_ptr, bonds->select.bond_list[i].bo_data.CdboReduction, "CdboReduction");
 #endif
 
-  Delete_List( bonds, comm );
-  if(!Make_List(system->total_cap, *total_bonds, TYP_BOND, bonds, comm)) {
-    fprintf( stderr, "not enough space for bonds list. terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+  Delete_List( bonds);
+  if(!Make_List(system->total_cap, *total_bonds, TYP_BOND, bonds)) {
+    bonds->error_ptr->one(FLERR, "Not enough space for bonds list");
   }
 
 #ifdef LMP_USER_OMP
@@ -392,7 +389,7 @@ static int Reallocate_Bonds_List( reax_system *system, reax_list *bonds,
   if (system->omp_active)
     for (i = 0; i < bonds->num_intrs; ++i)
       bonds->select.bond_list[i].bo_data.CdboReduction =
-        (double*) smalloc(sizeof(double)*nthreads, "CdboReduction", comm);
+        (double*) smalloc(system->error_ptr, sizeof(double)*nthreads, "CdboReduction");
 #endif
 
   return SUCCESS;
@@ -400,14 +397,12 @@ static int Reallocate_Bonds_List( reax_system *system, reax_list *bonds,
 
 
 void ReAllocate( reax_system *system, control_params *control,
-                 simulation_data *data, storage *workspace, reax_list **lists,
-                 mpi_datatypes *mpi_data )
+                 simulation_data *data, storage *workspace, reax_list **lists )
 {
   int num_bonds, est_3body, Hflag, ret;
   int renbr, newsize;
   reallocate_data *realloc;
   reax_list *far_nbrs;
-  MPI_Comm comm;
   char msg[200];
 
   int mincap = system->mincap;
@@ -415,7 +410,6 @@ void ReAllocate( reax_system *system, control_params *control,
   double saferzone = system->saferzone;
 
   realloc = &(workspace->realloc);
-  comm = mpi_data->world;
 
   if( system->n >= DANGER_ZONE * system->local_cap ||
       (0 && system->n <= LOOSE_ZONE * system->local_cap) ) {
@@ -433,21 +427,19 @@ void ReAllocate( reax_system *system, control_params *control,
     /* system */
     ret = Allocate_System( system, system->local_cap, system->total_cap, msg );
     if (ret != SUCCESS) {
-      fprintf( stderr, "not enough space for atom_list: total_cap=%d",
-               system->total_cap );
-      fprintf( stderr, "terminating...\n" );
-      MPI_Abort( comm, INSUFFICIENT_MEMORY );
+      char errmsg[256];
+      snprintf(errmsg, 256, "Not enough space for atom_list: total_cap=%d", system->total_cap);
+      system->error_ptr->one(FLERR, errmsg);
     }
 
     /* workspace */
     DeAllocate_Workspace( control, workspace );
     ret = Allocate_Workspace( system, control, workspace, system->local_cap,
-                              system->total_cap, comm, msg );
+                              system->total_cap, msg );
     if (ret != SUCCESS) {
-      fprintf( stderr, "no space for workspace: local_cap=%d total_cap=%d",
-               system->local_cap, system->total_cap );
-      fprintf( stderr, "terminating...\n" );
-      MPI_Abort( comm, INSUFFICIENT_MEMORY );
+      char errmsg[256];
+      snprintf(errmsg, 256, "Not enough space for workspace: local_cap=%d total_cap=%d", system->local_cap, system->total_cap);
+      system->error_ptr->one(FLERR, errmsg);
     }
   }
 
@@ -459,15 +451,15 @@ void ReAllocate( reax_system *system, control_params *control,
 
     if (Nflag || realloc->num_far >= far_nbrs->num_intrs * DANGER_ZONE) {
       if (realloc->num_far > far_nbrs->num_intrs) {
-        fprintf( stderr, "step%d-ran out of space on far_nbrs: top=%d, max=%d",
-                 data->step, realloc->num_far, far_nbrs->num_intrs );
-        MPI_Abort( comm, INSUFFICIENT_MEMORY );
+        char errmsg[256];
+        snprintf(errmsg, 256, "step%d-ran out of space on far_nbrs: top=%d, max=%d", data->step, realloc->num_far, far_nbrs->num_intrs);
+        system->error_ptr->one(FLERR, errmsg);
       }
 
       newsize = static_cast<int>
         (MAX( realloc->num_far*safezone, mincap*MIN_NBRS ));
 
-      Reallocate_Neighbor_List( far_nbrs, system->total_cap, newsize, comm );
+      Reallocate_Neighbor_List( far_nbrs, system->total_cap, newsize);
       realloc->num_far = 0;
     }
   }
@@ -482,7 +474,7 @@ void ReAllocate( reax_system *system, control_params *control,
     }
 
     if (Hflag || realloc->hbonds) {
-      ret = Reallocate_HBonds_List( system, (*lists)+HBONDS, comm );
+      ret = Reallocate_HBonds_List( system, (*lists)+HBONDS);
       realloc->hbonds = 0;
     }
   }
@@ -491,14 +483,14 @@ void ReAllocate( reax_system *system, control_params *control,
   num_bonds = est_3body = -1;
   if (Nflag || realloc->bonds) {
     Reallocate_Bonds_List( system, (*lists)+BONDS, &num_bonds,
-                           &est_3body, comm );
+                           &est_3body);
     realloc->bonds = 0;
     realloc->num_3body = MAX( realloc->num_3body, est_3body ) * 2;
   }
 
   /* 3-body list */
   if (realloc->num_3body > 0) {
-    Delete_List( (*lists)+THREE_BODIES, comm );
+    Delete_List( (*lists)+THREE_BODIES);
 
     if (num_bonds == -1)
       num_bonds = ((*lists)+BONDS)->num_intrs;
@@ -506,9 +498,8 @@ void ReAllocate( reax_system *system, control_params *control,
     realloc->num_3body = (int)(MAX(realloc->num_3body*safezone, MIN_3BODIES));
 
     if( !Make_List( num_bonds, realloc->num_3body, TYP_THREE_BODY,
-                    (*lists)+THREE_BODIES, comm ) ) {
-      fprintf( stderr, "Problem in initializing angles list. Terminating!\n" );
-      MPI_Abort( comm, CANNOT_INITIALIZE );
+                    (*lists)+THREE_BODIES ) ) {
+      system->error_ptr->one(FLERR, "Problem in initializing angles list");
     }
     realloc->num_3body = -1;
   }
diff --git a/src/USER-REAXC/reaxc_allocate.h b/src/USER-REAXC/reaxc_allocate.h
index f8814859af..be203340f6 100644
--- a/src/USER-REAXC/reaxc_allocate.h
+++ b/src/USER-REAXC/reaxc_allocate.h
@@ -28,15 +28,15 @@
 #define __ALLOCATE_H_
 
 #include "reaxc_types.h"
-int  PreAllocate_Space( reax_system*, control_params*, storage*, MPI_Comm );
+int  PreAllocate_Space( reax_system*, control_params*, storage* );
 
 int  Allocate_System( reax_system*, int, int, char* );
 void DeAllocate_System( reax_system* );
 
 int  Allocate_Workspace( reax_system*, control_params*, storage*,
-                         int, int, MPI_Comm, char* );
+                         int, int, char* );
 void DeAllocate_Workspace( control_params*, storage* );
 
 void ReAllocate( reax_system*, control_params*, simulation_data*, storage*,
-                 reax_list**, mpi_datatypes* );
+                 reax_list** );
 #endif
diff --git a/src/USER-REAXC/reaxc_control.cpp b/src/USER-REAXC/reaxc_control.cpp
index dd2b5a32ad..535226fff8 100644
--- a/src/USER-REAXC/reaxc_control.cpp
+++ b/src/USER-REAXC/reaxc_control.cpp
@@ -28,6 +28,8 @@
 #include "reaxc_control.h"
 #include "reaxc_tool_box.h"
 
+#include "error.h"
+
 char Read_Control_File( char *control_file, control_params* control,
                         output_controls *out_control )
 {
@@ -38,8 +40,7 @@ char Read_Control_File( char *control_file, control_params* control,
 
   /* open control file */
   if ( (fp = fopen( control_file, "r" ) ) == NULL ) {
-    fprintf( stderr, "error opening the control file! terminating...\n" );
-    MPI_Abort( MPI_COMM_WORLD,  FILE_NOT_FOUND );
+    control->error_ptr->all(FLERR, "The control file cannot be opened");
   }
 
   /* assign default values */
@@ -364,8 +365,9 @@ char Read_Control_File( char *control_file, control_params* control,
       control->restrict_type = ival;
     }
     else {
-      fprintf( stderr, "WARNING: unknown parameter %s\n", tmp[0] );
-      MPI_Abort( MPI_COMM_WORLD, 15 );
+      char errmsg[128];
+      snprintf(errmsg,128,"Unknown parameter %s in the control file", tmp[0]);
+      control->error_ptr->all(FLERR, errmsg);
     }
   }
 
diff --git a/src/USER-REAXC/reaxc_ffield.cpp b/src/USER-REAXC/reaxc_ffield.cpp
index dd8f12f9d2..9534637645 100644
--- a/src/USER-REAXC/reaxc_ffield.cpp
+++ b/src/USER-REAXC/reaxc_ffield.cpp
@@ -29,6 +29,7 @@
 #include "reaxc_ffield.h"
 #include "reaxc_tool_box.h"
 
+
 char Read_Force_Field( FILE *fp, reax_interaction *reax,
                        control_params *control )
 {
@@ -41,7 +42,6 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
   double     val;
   MPI_Comm comm;
   int me;
-
   comm = MPI_COMM_WORLD;
   MPI_Comm_rank(comm, &me);
 
@@ -61,7 +61,7 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
   n = atoi(tmp[0]);
   if (n < 1) {
     if (me == 0)
-      fprintf( stderr, "WARNING: number of globals in ffield file is 0!\n" );
+      control->error_ptr->warning( FLERR, "Number of globals in ffield file is 0. The file will not be read." );
     fclose(fp);
     free(s);
     free(tmp);
@@ -96,61 +96,52 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
 
   /* Allocating structures in reax_interaction */
   reax->sbp = (single_body_parameters*)
-    scalloc( reax->num_atom_types, sizeof(single_body_parameters), "sbp",
-             comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(single_body_parameters), "sbp");
   reax->tbp = (two_body_parameters**)
-    scalloc( reax->num_atom_types, sizeof(two_body_parameters*), "tbp", comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(two_body_parameters*), "tbp");
   reax->thbp= (three_body_header***)
-    scalloc( reax->num_atom_types, sizeof(three_body_header**), "thbp", comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(three_body_header**), "thbp");
   reax->hbp = (hbond_parameters***)
-    scalloc( reax->num_atom_types, sizeof(hbond_parameters**), "hbp", comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(hbond_parameters**), "hbp");
   reax->fbp = (four_body_header****)
-    scalloc( reax->num_atom_types, sizeof(four_body_header***), "fbp", comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(four_body_header***), "fbp");
   tor_flag  = (char****)
-    scalloc( reax->num_atom_types, sizeof(char***), "tor_flag", comm );
+    scalloc(control->error_ptr,  reax->num_atom_types, sizeof(char***), "tor_flag");
 
   for( i = 0; i < reax->num_atom_types; i++ ) {
     reax->tbp[i] = (two_body_parameters*)
-      scalloc( reax->num_atom_types, sizeof(two_body_parameters), "tbp[i]",
-               comm );
+      scalloc(control->error_ptr,  reax->num_atom_types, sizeof(two_body_parameters), "tbp[i]");
     reax->thbp[i]= (three_body_header**)
-      scalloc( reax->num_atom_types, sizeof(three_body_header*), "thbp[i]",
-               comm );
+      scalloc(control->error_ptr,  reax->num_atom_types, sizeof(three_body_header*), "thbp[i]");
     reax->hbp[i] = (hbond_parameters**)
-      scalloc( reax->num_atom_types, sizeof(hbond_parameters*), "hbp[i]",
-               comm );
+      scalloc(control->error_ptr,  reax->num_atom_types, sizeof(hbond_parameters*), "hbp[i]");
     reax->fbp[i] = (four_body_header***)
-      scalloc( reax->num_atom_types, sizeof(four_body_header**), "fbp[i]",
-               comm );
+      scalloc(control->error_ptr,  reax->num_atom_types, sizeof(four_body_header**), "fbp[i]");
     tor_flag[i]  = (char***)
-      scalloc( reax->num_atom_types, sizeof(char**), "tor_flag[i]", comm );
+      scalloc(control->error_ptr,  reax->num_atom_types, sizeof(char**), "tor_flag[i]");
 
     for( j = 0; j < reax->num_atom_types; j++ ) {
       reax->thbp[i][j]= (three_body_header*)
-        scalloc( reax->num_atom_types, sizeof(three_body_header), "thbp[i,j]",
-                 comm );
+        scalloc(control->error_ptr,  reax->num_atom_types, sizeof(three_body_header), "thbp[i,j]");
       reax->hbp[i][j] = (hbond_parameters*)
-        scalloc( reax->num_atom_types, sizeof(hbond_parameters), "hbp[i,j]",
-                 comm );
+        scalloc(control->error_ptr,  reax->num_atom_types, sizeof(hbond_parameters), "hbp[i,j]");
       reax->fbp[i][j] = (four_body_header**)
-        scalloc( reax->num_atom_types, sizeof(four_body_header*), "fbp[i,j]",
-                 comm );
+        scalloc(control->error_ptr,  reax->num_atom_types, sizeof(four_body_header*), "fbp[i,j]");
       tor_flag[i][j]  = (char**)
-        scalloc( reax->num_atom_types, sizeof(char*), "tor_flag[i,j]", comm );
+        scalloc(control->error_ptr,  reax->num_atom_types, sizeof(char*), "tor_flag[i,j]");
 
       for (k=0; k < reax->num_atom_types; k++) {
         reax->fbp[i][j][k] = (four_body_header*)
-          scalloc( reax->num_atom_types, sizeof(four_body_header), "fbp[i,j,k]",
-                   comm );
+          scalloc(control->error_ptr,  reax->num_atom_types, sizeof(four_body_header), "fbp[i,j,k]");
         tor_flag[i][j][k]  = (char*)
-          scalloc( reax->num_atom_types, sizeof(char), "tor_flag[i,j,k]",
-                   comm );
+          scalloc(control->error_ptr,  reax->num_atom_types, sizeof(char), "tor_flag[i,j,k]");
       }
     }
   }
 
   reax->gp.vdw_type = 0;
 
+  char errmsg[1024];
 
   for( i = 0; i < reax->num_atom_types; i++ ) {
     /* line one */
@@ -158,15 +149,12 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
     c = Tokenize( s, &tmp );
 
     /* Sanity checks */
-    if (c == 2 && !lgflag) {
-      if (me == 0)
-        fprintf(stderr, "Force field file requires using 'lgvdw yes'\n");
-      MPI_Abort( comm, FILE_NOT_FOUND );
-    }
+    if (c == 2 && !lgflag)
+        control->error_ptr->all(FLERR, "Force field file requires using 'lgvdw yes'");	
+
     if (c < 9) {
-      if (me == 0)
-        fprintf(stderr, "Inconsistent ffield file (reaxc_ffield.cpp) \n");
-      MPI_Abort( comm, FILE_NOT_FOUND );
+      snprintf (errmsg, 1024, "Missing parameter(s) in line %s", s);
+      control->error_ptr->all(FLERR, errmsg);
     }
 
     for( j = 0; j < (int)(strlen(tmp[0])); ++j )
@@ -188,9 +176,8 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
 
     /* Sanity check */
     if (c < 8) {
-      if (me == 0)
-        fprintf(stderr, "Inconsistent ffield file (reaxc_ffield.cpp) \n");
-      MPI_Abort( comm, FILE_NOT_FOUND );
+      snprintf (errmsg, 1024, "Missing parameter(s) in line %s", s);
+      control->error_ptr->all(FLERR, errmsg);
     }
 
     val = atof(tmp[0]); reax->sbp[i].alpha      = val;
@@ -208,9 +195,8 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
 
     /* Sanity check */
     if (c < 8) {
-      if (me == 0)
-        fprintf(stderr, "Inconsistent ffield file (reaxc_ffield.cpp) \n");
-      MPI_Abort( comm, FILE_NOT_FOUND );
+      snprintf (errmsg, 1024, "Missing parameter(s) in line %s", s);
+      control->error_ptr->all(FLERR, errmsg);
     }
 
     val = atof(tmp[0]); reax->sbp[i].r_pi_pi    = val;
@@ -228,9 +214,8 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
 
     /* Sanity check */
     if (c < 8) {
-      if (me == 0)
-        fprintf(stderr, "Inconsistent ffield file (reaxc_ffield.cpp) \n");
-      MPI_Abort( comm, FILE_NOT_FOUND );
+      snprintf (errmsg, 1024, "Missing parameter(s) in line %s", s);
+      control->error_ptr->all(FLERR, errmsg);
     }
 
     val = atof(tmp[0]); reax->sbp[i].p_ovun2    = val;
@@ -249,9 +234,7 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
 
       /* Sanity check */
       if (c > 2) {
-        if (me == 0)
-          fprintf(stderr, "Force field file incompatible with 'lgvdw yes'\n");
-        MPI_Abort( comm, FILE_NOT_FOUND );
+        control->error_ptr->all(FLERR,"Force field file incompatible with 'lgvdw yes'");
       }
 
       val = atof(tmp[0]); reax->sbp[i].lgcij           = val;
@@ -261,28 +244,32 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
     if (reax->sbp[i].rcore2>0.01 && reax->sbp[i].acore2>0.01) { // Inner-wall
       if (reax->sbp[i].gamma_w>0.5) { // Shielding vdWaals
         if (reax->gp.vdw_type != 0 && reax->gp.vdw_type != 3) {
-          if (errorflag && (me == 0))
-            fprintf( stderr, "Warning: inconsistent vdWaals-parameters\n" \
-                   "Force field parameters for element %s\n"              \
-                   "indicate inner wall+shielding, but earlier\n"         \
-                   "atoms indicate different vdWaals-method.\n"           \
-                   "This may cause division-by-zero errors.\n"            \
-                   "Keeping vdWaals-setting for earlier atoms.\n",
-                   reax->sbp[i].name );
+          if (errorflag && (me == 0)) {
+            char errmsg[512];
+            snprintf(errmsg, 512, "VdWaals-parameters for element %s "
+                   "indicate inner wall+shielding, but earlier "
+                   "atoms indicate different vdWaals-method. "
+                   "This may cause division-by-zero errors. "
+                   "Keeping vdWaals-setting for earlier atoms.",
+                   reax->sbp[i].name);
+            control->error_ptr->warning(FLERR,errmsg);
+          }
           errorflag = 0;
         } else {
           reax->gp.vdw_type = 3;
         }
       } else {  // No shielding vdWaals parameters present
         if (reax->gp.vdw_type != 0 && reax->gp.vdw_type != 2) {
-          if (me == 0)
-            fprintf( stderr, "Warning: inconsistent vdWaals-parameters\n" \
-                   "Force field parameters for element %s\n"              \
-                   "indicate inner wall without shielding, but earlier\n" \
-                   "atoms indicate different vdWaals-method.\n"           \
-                   "This may cause division-by-zero errors.\n"            \
-                   "Keeping vdWaals-setting for earlier atoms.\n",
-                   reax->sbp[i].name );
+          if (me == 0) {
+            char errmsg[512];
+            snprintf(errmsg, 512, "VdWaals-parameters for element %s "
+                   "indicate inner wall without shielding, but earlier "
+                   "atoms indicate different vdWaals-method. "
+                   "This may cause division-by-zero errors. "
+                   "Keeping vdWaals-setting for earlier atoms.",
+                   reax->sbp[i].name);
+            control->error_ptr->warning(FLERR,errmsg);
+          }
         } else {
           reax->gp.vdw_type = 2;
         }
@@ -290,23 +277,25 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
     } else { // No Inner wall parameters present
       if (reax->sbp[i].gamma_w>0.5) { // Shielding vdWaals
         if (reax->gp.vdw_type != 0 && reax->gp.vdw_type != 1) {
-          if (me == 0)
-            fprintf( stderr, "Warning: inconsistent vdWaals-parameters\n"  \
-                   "Force field parameters for element %s\n"               \
-                   "indicate  shielding without inner wall, but earlier\n" \
-                   "atoms indicate different vdWaals-method.\n"            \
-                   "This may cause division-by-zero errors.\n"             \
-                   "Keeping vdWaals-setting for earlier atoms.\n",
-                   reax->sbp[i].name );
+          if (me == 0) {
+            char errmsg[512];
+            snprintf(errmsg, 512, "VdWaals parameters for element %s "
+                   "indicate shielding without inner wall, but earlier "
+                   "elements indicate different vdWaals-method. "
+                   "This may cause division-by-zero errors. "
+                   "Keeping vdWaals-setting for earlier atoms.",
+                   reax->sbp[i].name);
+            control->error_ptr->warning(FLERR,errmsg);
+          }
         } else {
           reax->gp.vdw_type = 1;
         }
       } else {
-        if (me == 0)
-          fprintf( stderr, "Error: inconsistent vdWaals-parameters\n"  \
-                 "No shielding or inner-wall set for element %s\n",
-                 reax->sbp[i].name );
-        MPI_Abort( comm, INVALID_INPUT );
+        char errmsg[256];
+        snprintf(errmsg, 256, "Inconsistent vdWaals-parameters: "
+                 "No shielding or inner-wall set for element %s",
+                 reax->sbp[i].name);
+        control->error_ptr->all(FLERR, errmsg);
       }
     }
   }
@@ -315,15 +304,23 @@ char Read_Force_Field( FILE *fp, reax_interaction *reax,
   for( i = 0; i < reax->num_atom_types; i++ )
     if( reax->sbp[i].mass < 21 &&
         reax->sbp[i].valency_val != reax->sbp[i].valency_boc ) {
-      if (me == 0)
-        fprintf(stderr,"Warning: changed valency_val to valency_boc for %s\n",
-               reax->sbp[i].name );
+      if (me == 0) {
+        char errmsg[256];
+        snprintf(errmsg, 256, "Changed valency_val to valency_boc for %s",
+               reax->sbp[i].name);
+        control->error_ptr->warning(FLERR,errmsg);
+      }
       reax->sbp[i].valency_val = reax->sbp[i].valency_boc;
     }
 
   /* next line is number of two body combination and some comments */
   fgets(s,MAX_LINE,fp);
   c=Tokenize(s,&tmp);
+
+  if (c == 2 && !lgflag) {
+      control->error_ptr->all(FLERR, "Force field file requires using 'lgvdw yes'");
+    }
+
   l = atoi(tmp[0]);
 
   /* a line of comments */
diff --git a/src/USER-REAXC/reaxc_forces.cpp b/src/USER-REAXC/reaxc_forces.cpp
index 19b3cc4975..186cde681a 100644
--- a/src/USER-REAXC/reaxc_forces.cpp
+++ b/src/USER-REAXC/reaxc_forces.cpp
@@ -39,11 +39,14 @@
 #include "reaxc_valence_angles.h"
 #include "reaxc_vector.h"
 
+#include "error.h"
+
+
 interaction_function Interaction_Functions[NUM_INTRS];
 
 void Dummy_Interaction( reax_system * /*system*/, control_params * /*control*/,
                         simulation_data * /*data*/, storage * /*workspace*/,
-                        reax_list **/*lists*/, output_controls * /*out_control*/ )
+                        reax_list ** /*lists*/, output_controls * /*out_control*/ )
 {
 }
 
@@ -115,7 +118,7 @@ void Compute_Total_Force( reax_system *system, control_params *control,
 }
 
 void Validate_Lists( reax_system *system, storage * /*workspace*/, reax_list **lists,
-                     int step, int /*n*/, int N, int numH, MPI_Comm comm )
+                     int step, int /*n*/, int N, int numH )
 {
   int i, comp, Hindex;
   reax_list *bonds, *hbonds;
@@ -134,9 +137,10 @@ void Validate_Lists( reax_system *system, storage * /*workspace*/, reax_list **l
       else comp = bonds->num_intrs;
 
       if (End_Index(i, bonds) > comp) {
-        fprintf( stderr, "step%d-bondchk failed: i=%d end(i)=%d str(i+1)=%d\n",
+        char errmsg[256];
+        snprintf(errmsg, 256, "step%d-bondchk failed: i=%d end(i)=%d str(i+1)=%d\n",
                  step, i, End_Index(i,bonds), comp );
-        MPI_Abort( comm, INSUFFICIENT_MEMORY );
+        system->error_ptr->one(FLERR,errmsg);
       }
     }
   }
@@ -161,9 +165,10 @@ void Validate_Lists( reax_system *system, storage * /*workspace*/, reax_list **l
         else comp = hbonds->num_intrs;
 
         if (End_Index(Hindex, hbonds) > comp) {
-          fprintf(stderr,"step%d-hbondchk failed: H=%d end(H)=%d str(H+1)=%d\n",
+          char errmsg[256];
+          snprintf(errmsg, 256, "step%d-hbondchk failed: H=%d end(H)=%d str(H+1)=%d\n",
                   step, Hindex, End_Index(Hindex,hbonds), comp );
-          MPI_Abort( comm, INSUFFICIENT_MEMORY );
+          system->error_ptr->one(FLERR, errmsg);
         }
       }
     }
@@ -173,8 +178,7 @@ void Validate_Lists( reax_system *system, storage * /*workspace*/, reax_list **l
 
 void Init_Forces_noQEq( reax_system *system, control_params *control,
                         simulation_data *data, storage *workspace,
-                        reax_list **lists, output_controls * /*out_control*/,
-                        MPI_Comm comm ) {
+                        reax_list **lists, output_controls * /*out_control*/ ) {
   int i, j, pj;
   int start_i, end_i;
   int type_i, type_j;
@@ -308,13 +312,13 @@ void Init_Forces_noQEq( reax_system *system, control_params *control,
   workspace->realloc.num_hbonds = num_hbonds;
 
   Validate_Lists( system, workspace, lists, data->step,
-                  system->n, system->N, system->numH, comm );
+                  system->n, system->N, system->numH);
 }
 
 
 void Estimate_Storages( reax_system *system, control_params *control,
                         reax_list **lists, int *Htop, int *hb_top,
-                        int *bond_top, int *num_3body, MPI_Comm /*comm*/ )
+                        int *bond_top, int *num_3body )
 {
   int i, j, pj;
   int start_i, end_i;
@@ -436,10 +440,9 @@ void Compute_Forces( reax_system *system, control_params *control,
                      reax_list **lists, output_controls *out_control,
                      mpi_datatypes *mpi_data )
 {
-  MPI_Comm comm = mpi_data->world;
 
   Init_Forces_noQEq( system, control, data, workspace,
-                       lists, out_control, comm );
+                       lists, out_control);
 
   /********* bonded interactions ************/
   Compute_Bonded_Forces( system, control, data, workspace,
diff --git a/src/USER-REAXC/reaxc_forces.h b/src/USER-REAXC/reaxc_forces.h
index 6c839a7023..bfad2e9b71 100644
--- a/src/USER-REAXC/reaxc_forces.h
+++ b/src/USER-REAXC/reaxc_forces.h
@@ -36,5 +36,5 @@ void Init_Force_Functions( control_params* );
 void Compute_Forces( reax_system*, control_params*, simulation_data*,
                      storage*, reax_list**, output_controls*, mpi_datatypes* );
 void Estimate_Storages( reax_system*, control_params*, reax_list**,
-                        int*, int*, int*, int*, MPI_Comm );
+                        int*, int*, int*, int* );
 #endif
diff --git a/src/USER-REAXC/reaxc_init_md.cpp b/src/USER-REAXC/reaxc_init_md.cpp
index 5901b76326..df5de49034 100644
--- a/src/USER-REAXC/reaxc_init_md.cpp
+++ b/src/USER-REAXC/reaxc_init_md.cpp
@@ -36,6 +36,8 @@
 #include "reaxc_tool_box.h"
 #include "reaxc_vector.h"
 
+#include "error.h"
+
 int Init_System( reax_system *system, control_params *control, char * /*msg*/ )
 {
   int i;
@@ -80,7 +82,7 @@ int Init_Simulation_Data( reax_system *system, control_params *control,
   return SUCCESS;
 }
 
-void Init_Taper( control_params *control,  storage *workspace, MPI_Comm comm )
+void Init_Taper( control_params *control,  storage *workspace )
 {
   double d1, d7;
   double swa, swa2, swa3;
@@ -89,15 +91,17 @@ void Init_Taper( control_params *control,  storage *workspace, MPI_Comm comm )
   swa = control->nonb_low;
   swb = control->nonb_cut;
 
-  if (fabs( swa ) > 0.01)
-    fprintf( stderr, "Warning: non-zero lower Taper-radius cutoff\n" );
+  if (fabs( swa ) > 0.01 && control->me == 0)
+    control->error_ptr->warning( FLERR, "Non-zero lower Taper-radius cutoff" );
 
   if (swb < 0) {
-    fprintf( stderr, "Negative upper Taper-radius cutoff\n" );
-    MPI_Abort( comm,  INVALID_INPUT );
+    control->error_ptr->all(FLERR,"Negative upper Taper-radius cutoff");
+  }
+  else if( swb < 5 && control->me == 0) {
+    char errmsg[256];
+    snprintf(errmsg, 256, "Very low Taper-radius cutoff: %f", swb );
+    control->error_ptr->warning( FLERR, errmsg );
   }
-  else if( swb < 5 )
-    fprintf( stderr, "Warning: very low Taper-radius cutoff: %f\n", swb );
 
   d1 = swb - swa;
   d7 = pow( d1, 7.0 );
@@ -119,12 +123,12 @@ void Init_Taper( control_params *control,  storage *workspace, MPI_Comm comm )
 
 
 int Init_Workspace( reax_system *system, control_params *control,
-                    storage *workspace, MPI_Comm comm, char *msg )
+                    storage *workspace, char *msg )
 {
   int ret;
 
   ret = Allocate_Workspace( system, control, workspace,
-                            system->local_cap, system->total_cap, comm, msg );
+                            system->local_cap, system->total_cap, msg );
   if (ret != SUCCESS)
     return ret;
 
@@ -132,7 +136,7 @@ int Init_Workspace( reax_system *system, control_params *control,
   Reset_Workspace( system, workspace );
 
   /* Initialize the Taper function */
-  Init_Taper( control, workspace, comm );
+  Init_Taper( control, workspace);
 
   return SUCCESS;
 }
@@ -152,21 +156,19 @@ int Init_MPI_Datatypes( reax_system *system, storage * /*workspace*/,
 
 int  Init_Lists( reax_system *system, control_params *control,
                  simulation_data * /*data*/, storage * /*workspace*/, reax_list **lists,
-                 mpi_datatypes *mpi_data, char * /*msg*/ )
+                 mpi_datatypes * /*mpi_data*/, char * /*msg*/ )
 {
   int i, total_hbonds, total_bonds, bond_cap, num_3body, cap_3body, Htop;
   int *hb_top, *bond_top;
-  MPI_Comm comm;
 
   int mincap = system->mincap;
   double safezone = system->safezone;
   double saferzone = system->saferzone;
 
-  comm = mpi_data->world;
   bond_top = (int*) calloc( system->total_cap, sizeof(int) );
   hb_top = (int*) calloc( system->local_cap, sizeof(int) );
   Estimate_Storages( system, control, lists,
-                     &Htop, hb_top, bond_top, &num_3body, comm );
+                     &Htop, hb_top, bond_top, &num_3body);
 
   if (control->hbond_cut > 0) {
     /* init H indexes */
@@ -178,10 +180,10 @@ int  Init_Lists( reax_system *system, control_params *control,
     total_hbonds = (int)(MAX( total_hbonds*saferzone, mincap*MIN_HBONDS ));
 
     if( !Make_List( system->Hcap, total_hbonds, TYP_HBOND,
-                    *lists+HBONDS, comm ) ) {
-      fprintf( stderr, "not enough space for hbonds list. terminating!\n" );
-      MPI_Abort( comm, INSUFFICIENT_MEMORY );
+                    *lists+HBONDS ) ) {
+      control->error_ptr->one(FLERR, "Not enough space for hbonds list.");
     }
+    (*lists+HBONDS)->error_ptr = system->error_ptr;
   }
 
   total_bonds = 0;
@@ -192,18 +194,18 @@ int  Init_Lists( reax_system *system, control_params *control,
   bond_cap = (int)(MAX( total_bonds*safezone, mincap*MIN_BONDS ));
 
   if( !Make_List( system->total_cap, bond_cap, TYP_BOND,
-                  *lists+BONDS, comm ) ) {
-    fprintf( stderr, "not enough space for bonds list. terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+                  *lists+BONDS ) ) {
+    control->error_ptr->one(FLERR, "Not enough space for bonds list.");
   }
+  (*lists+BONDS)->error_ptr = system->error_ptr;
 
   /* 3bodies list */
   cap_3body = (int)(MAX( num_3body*safezone, MIN_3BODIES ));
   if( !Make_List( bond_cap, cap_3body, TYP_THREE_BODY,
-                  *lists+THREE_BODIES, comm ) ){
-    fprintf( stderr, "Problem in initializing angles list. Terminating!\n" );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+                  *lists+THREE_BODIES ) ){
+    control->error_ptr->one(FLERR,"Problem in initializing angles list.");
   }
+  (*lists+THREE_BODIES)->error_ptr = system->error_ptr;
 
   free( hb_top );
   free( bond_top );
@@ -218,59 +220,35 @@ void Initialize( reax_system *system, control_params *control,
 {
   char msg[MAX_STR];
 
-
   if (Init_MPI_Datatypes(system, workspace, mpi_data, comm, msg) == FAILURE) {
-    fprintf( stderr, "p%d: init_mpi_datatypes: could not create datatypes\n",
-             system->my_rank );
-    fprintf( stderr, "p%d: mpi_data couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Could not create datatypes");
   }
 
   if (Init_System(system, control, msg) == FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: system could not be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"System could not be initialized");
   }
 
   if (Init_Simulation_Data( system, control, data, msg ) == FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: sim_data couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Sim_data could not be initialized");
   }
 
-  if (Init_Workspace( system, control, workspace, mpi_data->world, msg ) ==
+  if (Init_Workspace( system, control, workspace, msg ) ==
       FAILURE) {
-    fprintf( stderr, "p%d:init_workspace: not enough memory\n",
-             system->my_rank );
-    fprintf( stderr, "p%d:workspace couldn't be initialized! terminating.\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Workspace could not be initialized");
   }
 
   if (Init_Lists( system, control, data, workspace, lists, mpi_data, msg ) ==
       FAILURE) {
-      fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-      fprintf( stderr, "p%d: system could not be initialized! terminating.\n",
-               system->my_rank );
-      MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Lists could not be initialized");
     }
 
   if (Init_Output_Files(system,control,out_control,mpi_data,msg)== FAILURE) {
-    fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-    fprintf( stderr, "p%d: could not open output files! terminating...\n",
-             system->my_rank );
-    MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Could not open output files");
   }
 
   if (control->tabulate) {
     if (Init_Lookup_Tables( system, control, workspace, mpi_data, msg ) == FAILURE) {
-      fprintf( stderr, "p%d: %s\n", system->my_rank, msg );
-      fprintf( stderr, "p%d: couldn't create lookup table! terminating.\n",
-               system->my_rank );
-      MPI_Abort( mpi_data->world, CANNOT_INITIALIZE );
+    control->error_ptr->one(FLERR,"Lookup table could not be created");
     }
   }
 
diff --git a/src/USER-REAXC/reaxc_init_md.h b/src/USER-REAXC/reaxc_init_md.h
index 25333c744f..ab519a4c72 100644
--- a/src/USER-REAXC/reaxc_init_md.h
+++ b/src/USER-REAXC/reaxc_init_md.h
@@ -29,6 +29,7 @@
 
 #include "reaxc_types.h"
 
+
 void Initialize( reax_system*, control_params*, simulation_data*, storage*,
                  reax_list**, output_controls*, mpi_datatypes*, MPI_Comm );
 #endif
diff --git a/src/USER-REAXC/reaxc_io_tools.cpp b/src/USER-REAXC/reaxc_io_tools.cpp
index f71fcbec8e..51aa8bca0f 100644
--- a/src/USER-REAXC/reaxc_io_tools.cpp
+++ b/src/USER-REAXC/reaxc_io_tools.cpp
@@ -55,8 +55,7 @@ int Init_Output_Files( reax_system *system, control_params *control,
       sprintf( temp, "%s.pot", control->sim_name );
       if ((out_control->pot = fopen( temp, "w" )) != NULL) {
         fflush( out_control->pot );
-      }
-      else {
+      } else {
         strcpy( msg, "init_out_controls: .pot file could not be opened\n" );
         return FAILURE;
       }
@@ -74,8 +73,7 @@ int Init_Output_Files( reax_system *system, control_params *control,
                 "step", "Pint/norm[x]", "Pint/norm[y]", "Pint/norm[z]",
                 "Pext/Ptot[x]", "Pext/Ptot[y]", "Pext/Ptot[z]", "Pkin/V" );
         fflush( out_control->prs );
-      }
-      else {
+      } else {
         strcpy(msg,"init_out_controls: .prs file couldn't be opened\n");
         return FAILURE;
       }
@@ -94,13 +92,15 @@ int Close_Output_Files( reax_system *system, control_params *control,
     End_Traj( system->my_rank, out_control );
 
   if (system->my_rank == MASTER_NODE) {
-    if (out_control->energy_update_freq > 0) {
+    if (out_control->pot) {
       fclose( out_control->pot );
+      out_control->pot = NULL;
     }
 
-    if( control->ensemble == NPT || control->ensemble == iNPT ||
-        control->ensemble == sNPT )
-      fclose( out_control->prs );
+    if (out_control->prs) {
+      fclose(out_control->prs);
+      out_control->prs = NULL;
+    }
   }
 
   return SUCCESS;
@@ -124,7 +124,7 @@ void Output_Results( reax_system *system, control_params *control,
         out_control->energy_update_freq > 0 &&
         data->step % out_control->energy_update_freq == 0 ) {
 
-      if (control->virial) {
+      if (control->virial && out_control->prs) {
         fprintf( out_control->prs,
                  "%8d%13.6f%13.6f%13.6f%13.6f%13.6f%13.6f%13.6f\n",
                  data->step,
diff --git a/src/USER-REAXC/reaxc_list.cpp b/src/USER-REAXC/reaxc_list.cpp
index 8a3bb9d322..cd4f815286 100644
--- a/src/USER-REAXC/reaxc_list.cpp
+++ b/src/USER-REAXC/reaxc_list.cpp
@@ -28,117 +28,121 @@
 #include "reaxc_list.h"
 #include "reaxc_tool_box.h"
 
+#include "error.h"
+
 /************* allocate list space ******************/
-int Make_List(int n, int num_intrs, int type, reax_list *l, MPI_Comm comm)
+int Make_List(int n, int num_intrs, int type, reax_list *l )
 {
   l->allocated = 1;
 
   l->n = n;
   l->num_intrs = num_intrs;
 
-  if (l->index) sfree(l->index, "list:index");
-  if (l->end_index) sfree(l->end_index, "list:end_index");
-  l->index = (int*) smalloc( n * sizeof(int), "list:index", comm );
-  l->end_index = (int*) smalloc( n * sizeof(int), "list:end_index", comm );
+  if (l->index) sfree(l->error_ptr, l->index, "list:index");
+  if (l->end_index) sfree(l->error_ptr, l->end_index, "list:end_index");
+  l->index = (int*) smalloc(l->error_ptr,  n * sizeof(int), "list:index");
+  l->end_index = (int*) smalloc(l->error_ptr,  n * sizeof(int), "list:end_index");
 
   l->type = type;
 
   switch(l->type) {
   case TYP_VOID:
-    if (l->select.v) sfree(l->select.v, "list:v");
-    l->select.v = (void*) smalloc(l->num_intrs * sizeof(void*), "list:v", comm);
+    if (l->select.v) sfree(l->error_ptr, l->select.v, "list:v");
+    l->select.v = (void*) smalloc(l->error_ptr, l->num_intrs * sizeof(void*), "list:v");
     break;
 
   case TYP_THREE_BODY:
-    if (l->select.three_body_list) sfree(l->select.three_body_list,"list:three_bodies");
+    if (l->select.three_body_list) sfree(l->error_ptr, l->select.three_body_list,"list:three_bodies");
     l->select.three_body_list = (three_body_interaction_data*)
-      smalloc( l->num_intrs * sizeof(three_body_interaction_data),
-               "list:three_bodies", comm );
+      smalloc(l->error_ptr,  l->num_intrs * sizeof(three_body_interaction_data),
+               "list:three_bodies");
     break;
 
   case TYP_BOND:
-    if (l->select.bond_list) sfree(l->select.bond_list,"list:bonds");
+    if (l->select.bond_list) sfree(l->error_ptr, l->select.bond_list,"list:bonds");
     l->select.bond_list = (bond_data*)
-      smalloc( l->num_intrs * sizeof(bond_data), "list:bonds", comm );
+      smalloc(l->error_ptr,  l->num_intrs * sizeof(bond_data), "list:bonds");
     break;
 
   case TYP_DBO:
-    if (l->select.dbo_list) sfree(l->select.dbo_list,"list:dbonds");
+    if (l->select.dbo_list) sfree(l->error_ptr, l->select.dbo_list,"list:dbonds");
     l->select.dbo_list = (dbond_data*)
-      smalloc( l->num_intrs * sizeof(dbond_data), "list:dbonds", comm );
+      smalloc(l->error_ptr,  l->num_intrs * sizeof(dbond_data), "list:dbonds");
     break;
 
   case TYP_DDELTA:
-    if (l->select.dDelta_list) sfree(l->select.dDelta_list,"list:dDeltas");
+    if (l->select.dDelta_list) sfree(l->error_ptr, l->select.dDelta_list,"list:dDeltas");
     l->select.dDelta_list = (dDelta_data*)
-      smalloc( l->num_intrs * sizeof(dDelta_data), "list:dDeltas", comm );
+      smalloc(l->error_ptr,  l->num_intrs * sizeof(dDelta_data), "list:dDeltas");
     break;
 
   case TYP_FAR_NEIGHBOR:
-    if (l->select.far_nbr_list) sfree(l->select.far_nbr_list,"list:far_nbrs");
+    if (l->select.far_nbr_list) sfree(l->error_ptr, l->select.far_nbr_list,"list:far_nbrs");
     l->select.far_nbr_list = (far_neighbor_data*)
-      smalloc(l->num_intrs * sizeof(far_neighbor_data), "list:far_nbrs", comm);
+      smalloc(l->error_ptr, l->num_intrs * sizeof(far_neighbor_data), "list:far_nbrs");
     break;
 
   case TYP_HBOND:
-    if (l->select.hbond_list) sfree(l->select.hbond_list,"list:hbonds");
+    if (l->select.hbond_list) sfree(l->error_ptr, l->select.hbond_list,"list:hbonds");
     l->select.hbond_list = (hbond_data*)
-      smalloc( l->num_intrs * sizeof(hbond_data), "list:hbonds", comm );
+      smalloc(l->error_ptr,  l->num_intrs * sizeof(hbond_data), "list:hbonds");
     break;
 
   default:
-    fprintf( stderr, "ERROR: no %d list type defined!\n", l->type );
-    MPI_Abort( comm, INVALID_INPUT );
+    char errmsg[128];
+    snprintf(errmsg, 128, "No %d list type defined", l->type);
+    l->error_ptr->one(FLERR,errmsg);
   }
 
   return SUCCESS;
 }
 
 
-void Delete_List( reax_list *l, MPI_Comm comm )
+void Delete_List( reax_list *l )
 {
   if (l->allocated == 0)
     return;
   l->allocated = 0;
 
-  sfree( l->index, "list:index" );
-  sfree( l->end_index, "list:end_index" );
+  sfree(l->error_ptr,  l->index, "list:index" );
+  sfree(l->error_ptr,  l->end_index, "list:end_index" );
   l->index = NULL;
   l->end_index = NULL;
 
   switch(l->type) {
   case TYP_VOID:
-    sfree( l->select.v, "list:v" );
+    sfree(l->error_ptr,  l->select.v, "list:v" );
     l->select.v = NULL;
     break;
   case TYP_HBOND:
-    sfree( l->select.hbond_list, "list:hbonds" );
+    sfree(l->error_ptr,  l->select.hbond_list, "list:hbonds" );
     l->select.hbond_list = NULL;
     break;
   case TYP_FAR_NEIGHBOR:
-    sfree( l->select.far_nbr_list, "list:far_nbrs" );
+    sfree(l->error_ptr,  l->select.far_nbr_list, "list:far_nbrs" );
     l->select.far_nbr_list = NULL;
     break;
   case TYP_BOND:
-    sfree( l->select.bond_list, "list:bonds" );
+    sfree(l->error_ptr,  l->select.bond_list, "list:bonds" );
     l->select.bond_list = NULL;
     break;
   case TYP_DBO:
-    sfree( l->select.dbo_list, "list:dbos" );
+    sfree(l->error_ptr,  l->select.dbo_list, "list:dbos" );
     l->select.dbo_list = NULL;
     break;
   case TYP_DDELTA:
-    sfree( l->select.dDelta_list, "list:dDeltas" );
+    sfree(l->error_ptr,  l->select.dDelta_list, "list:dDeltas" );
     l->select.dDelta_list = NULL;
     break;
   case TYP_THREE_BODY:
-    sfree( l->select.three_body_list, "list:three_bodies" );
+    sfree(l->error_ptr,  l->select.three_body_list, "list:three_bodies" );
     l->select.three_body_list = NULL;
     break;
 
   default:
-    fprintf( stderr, "ERROR: no %d list type defined!\n", l->type );
-    MPI_Abort( comm, INVALID_INPUT );
+    char errmsg[128];
+    snprintf(errmsg, 128, "No %d list type defined", l->type);
+    l->error_ptr->all(FLERR,errmsg);
   }
 }
 
diff --git a/src/USER-REAXC/reaxc_list.h b/src/USER-REAXC/reaxc_list.h
index ab7fbce19c..28567252da 100644
--- a/src/USER-REAXC/reaxc_list.h
+++ b/src/USER-REAXC/reaxc_list.h
@@ -29,8 +29,8 @@
 
 #include "reaxc_types.h"
 
-int  Make_List( int, int, int, reax_list*, MPI_Comm );
-void Delete_List( reax_list*, MPI_Comm );
+int  Make_List( int, int, int, reax_list* );
+void Delete_List( reax_list* );
 
 inline int  Num_Entries(int,reax_list*);
 inline int  Start_Index( int, reax_list* );
diff --git a/src/USER-REAXC/reaxc_lookup.cpp b/src/USER-REAXC/reaxc_lookup.cpp
index 92945ebdb5..74d8176522 100644
--- a/src/USER-REAXC/reaxc_lookup.cpp
+++ b/src/USER-REAXC/reaxc_lookup.cpp
@@ -50,19 +50,18 @@ void Tridiagonal_Solve( const double *a, const double *b,
 }
 
 
-void Natural_Cubic_Spline( const double *h, const double *f,
-                           cubic_spline_coef *coef, unsigned int n,
-                           MPI_Comm comm )
+void Natural_Cubic_Spline( LAMMPS_NS::Error* error_ptr, const double *h, const double *f,
+                           cubic_spline_coef *coef, unsigned int n )
 {
   int i;
   double *a, *b, *c, *d, *v;
 
   /* allocate space for the linear system */
-  a = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  b = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  c = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  d = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  v = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
+  a = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  b = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  c = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  d = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  v = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
 
   /* build the linear system */
   a[0] = a[1] = a[n-1] = 0;
@@ -92,28 +91,27 @@ void Natural_Cubic_Spline( const double *h, const double *f,
     coef[i-1].a = f[i];
   }
 
-  sfree( a, "cubic_spline:a" );
-  sfree( b, "cubic_spline:b" );
-  sfree( c, "cubic_spline:c" );
-  sfree( d, "cubic_spline:d" );
-  sfree( v, "cubic_spline:v" );
+  sfree(error_ptr,  a, "cubic_spline:a" );
+  sfree(error_ptr,  b, "cubic_spline:b" );
+  sfree(error_ptr,  c, "cubic_spline:c" );
+  sfree(error_ptr,  d, "cubic_spline:d" );
+  sfree(error_ptr,  v, "cubic_spline:v" );
 }
 
 
 
-void Complete_Cubic_Spline( const double *h, const double *f, double v0, double vlast,
-                            cubic_spline_coef *coef, unsigned int n,
-                            MPI_Comm comm )
+void Complete_Cubic_Spline( LAMMPS_NS::Error* error_ptr, const double *h, const double *f, double v0, double vlast,
+                            cubic_spline_coef *coef, unsigned int n )
 {
   int i;
   double *a, *b, *c, *d, *v;
 
   /* allocate space for the linear system */
-  a = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  b = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  c = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  d = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
-  v = (double*) smalloc( n * sizeof(double), "cubic_spline:a", comm );
+  a = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  b = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  c = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  d = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
+  v = (double*) smalloc(error_ptr,  n * sizeof(double), "cubic_spline:a");
 
   /* build the linear system */
   a[0] = 0;
@@ -142,11 +140,11 @@ void Complete_Cubic_Spline( const double *h, const double *f, double v0, double
     coef[i-1].a = f[i];
   }
 
-  sfree( a, "cubic_spline:a" );
-  sfree( b, "cubic_spline:b" );
-  sfree( c, "cubic_spline:c" );
-  sfree( d, "cubic_spline:d" );
-  sfree( v, "cubic_spline:v" );
+  sfree(error_ptr,  a, "cubic_spline:a" );
+  sfree(error_ptr,  b, "cubic_spline:b" );
+  sfree(error_ptr,  c, "cubic_spline:c" );
+  sfree(error_ptr,  d, "cubic_spline:d" );
+  sfree(error_ptr,  v, "cubic_spline:v" );
 }
 
 
@@ -159,35 +157,33 @@ int Init_Lookup_Tables( reax_system *system, control_params *control,
   double dr;
   double *h, *fh, *fvdw, *fele, *fCEvd, *fCEclmb;
   double v0_vdw, v0_ele, vlast_vdw, vlast_ele;
-  MPI_Comm comm;
 
   /* initializations */
   v0_vdw = 0;
   v0_ele = 0;
   vlast_vdw = 0;
   vlast_ele = 0;
-  comm = mpi_data->world;
 
   num_atom_types = system->reax_param.num_atom_types;
   dr = control->nonb_cut / control->tabulate;
   h = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:h", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:h");
   fh = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fh", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:fh");
   fvdw = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fvdw", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:fvdw");
   fCEvd = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fCEvd", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:fCEvd");
   fele = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fele", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:fele");
   fCEclmb = (double*)
-    smalloc( (control->tabulate+2) * sizeof(double), "lookup:fCEclmb", comm );
+    smalloc(system->error_ptr,  (control->tabulate+2) * sizeof(double), "lookup:fCEclmb");
 
   LR = (LR_lookup_table**)
-    scalloc( num_atom_types, sizeof(LR_lookup_table*), "lookup:LR", comm );
+    scalloc(system->error_ptr,  num_atom_types, sizeof(LR_lookup_table*), "lookup:LR");
   for( i = 0; i < num_atom_types; ++i )
     LR[i] = (LR_lookup_table*)
-      scalloc( num_atom_types, sizeof(LR_lookup_table), "lookup:LR[i]", comm );
+      scalloc(system->error_ptr,  num_atom_types, sizeof(LR_lookup_table), "lookup:LR[i]");
 
   for( i = 0; i < MAX_ATOM_TYPES; ++i )
     existing_types[i] = 0;
@@ -207,22 +203,18 @@ int Init_Lookup_Tables( reax_system *system, control_params *control,
           LR[i][j].dx = dr;
           LR[i][j].inv_dx = control->tabulate / control->nonb_cut;
           LR[i][j].y = (LR_data*)
-            smalloc( LR[i][j].n * sizeof(LR_data), "lookup:LR[i,j].y", comm );
+            smalloc(system->error_ptr,  LR[i][j].n * sizeof(LR_data), "lookup:LR[i,j].y");
           LR[i][j].H = (cubic_spline_coef*)
-            smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].H" ,
-                     comm );
+            smalloc(system->error_ptr,  LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].H");
           LR[i][j].vdW = (cubic_spline_coef*)
-            smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].vdW",
-                     comm);
+            smalloc(system->error_ptr,  LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].vdW");
           LR[i][j].CEvd = (cubic_spline_coef*)
-            smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].CEvd",
-                     comm);
+            smalloc(system->error_ptr,  LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].CEvd");
           LR[i][j].ele = (cubic_spline_coef*)
-            smalloc( LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].ele",
-                     comm );
+            smalloc(system->error_ptr,  LR[i][j].n*sizeof(cubic_spline_coef),"lookup:LR[i,j].ele");
           LR[i][j].CEclmb = (cubic_spline_coef*)
-            smalloc( LR[i][j].n*sizeof(cubic_spline_coef),
-                     "lookup:LR[i,j].CEclmb", comm );
+            smalloc(system->error_ptr,  LR[i][j].n*sizeof(cubic_spline_coef),
+                     "lookup:LR[i,j].CEclmb");
 
           for( r = 1; r <= control->tabulate; ++r ) {
             LR_vdW_Coulomb( system, workspace, control, i, j, r * dr, &(LR[i][j].y[r]) );
@@ -246,24 +238,20 @@ int Init_Lookup_Tables( reax_system *system, control_params *control,
           vlast_vdw = fCEvd[r-1];
           vlast_ele = fele[r-1];
 
-          Natural_Cubic_Spline( &h[1], &fh[1],
-                                &(LR[i][j].H[1]), control->tabulate+1, comm );
+          Natural_Cubic_Spline( control->error_ptr, &h[1], &fh[1],
+                                &(LR[i][j].H[1]), control->tabulate+1);
 
-          Complete_Cubic_Spline( &h[1], &fvdw[1], v0_vdw, vlast_vdw,
-                                 &(LR[i][j].vdW[1]), control->tabulate+1,
-                                 comm );
+          Complete_Cubic_Spline( control->error_ptr, &h[1], &fvdw[1], v0_vdw, vlast_vdw,
+                                 &(LR[i][j].vdW[1]), control->tabulate+1);
 
-          Natural_Cubic_Spline( &h[1], &fCEvd[1],
-                                &(LR[i][j].CEvd[1]), control->tabulate+1,
-                                comm );
+          Natural_Cubic_Spline( control->error_ptr, &h[1], &fCEvd[1],
+                                &(LR[i][j].CEvd[1]), control->tabulate+1);
 
-          Complete_Cubic_Spline( &h[1], &fele[1], v0_ele, vlast_ele,
-                                 &(LR[i][j].ele[1]), control->tabulate+1,
-                                 comm );
+          Complete_Cubic_Spline( control->error_ptr, &h[1], &fele[1], v0_ele, vlast_ele,
+                                 &(LR[i][j].ele[1]), control->tabulate+1);
 
-          Natural_Cubic_Spline( &h[1], &fCEclmb[1],
-                                &(LR[i][j].CEclmb[1]), control->tabulate+1,
-                                comm );
+          Natural_Cubic_Spline( control->error_ptr, &h[1], &fCEclmb[1],
+                                &(LR[i][j].CEclmb[1]), control->tabulate+1);
         } else {
           LR[i][j].n = 0;
         }
@@ -291,14 +279,14 @@ void Deallocate_Lookup_Tables( reax_system *system )
   for( i = 0; i < ntypes; ++i ) {
     for( j = i; j < ntypes; ++j )
       if (LR[i][j].n) {
-        sfree( LR[i][j].y, "LR[i,j].y" );
-        sfree( LR[i][j].H, "LR[i,j].H" );
-        sfree( LR[i][j].vdW, "LR[i,j].vdW" );
-        sfree( LR[i][j].CEvd, "LR[i,j].CEvd" );
-        sfree( LR[i][j].ele, "LR[i,j].ele" );
-        sfree( LR[i][j].CEclmb, "LR[i,j].CEclmb" );
+        sfree(system->error_ptr,  LR[i][j].y, "LR[i,j].y" );
+        sfree(system->error_ptr,  LR[i][j].H, "LR[i,j].H" );
+        sfree(system->error_ptr,  LR[i][j].vdW, "LR[i,j].vdW" );
+        sfree(system->error_ptr,  LR[i][j].CEvd, "LR[i,j].CEvd" );
+        sfree(system->error_ptr,  LR[i][j].ele, "LR[i,j].ele" );
+        sfree(system->error_ptr,  LR[i][j].CEclmb, "LR[i,j].CEclmb" );
       }
-    sfree( LR[i], "LR[i]" );
+    sfree(system->error_ptr,  LR[i], "LR[i]" );
   }
-  sfree( LR, "LR" );
+  sfree(system->error_ptr,  LR, "LR" );
 }
diff --git a/src/USER-REAXC/reaxc_lookup.h b/src/USER-REAXC/reaxc_lookup.h
index 66fa3c407c..3fd0c2581a 100644
--- a/src/USER-REAXC/reaxc_lookup.h
+++ b/src/USER-REAXC/reaxc_lookup.h
@@ -32,13 +32,11 @@
 void Tridiagonal_Solve( const double *a, const double *b,
                         double *c, double *d, double *x, unsigned int n);
 
-void Natural_Cubic_Spline( const double *h, const double *f,
-                           cubic_spline_coef *coef, unsigned int n,
-                           MPI_Comm comm );
+void Natural_Cubic_Spline( LAMMPS_NS::Error*, const double *h, const double *f,
+                           cubic_spline_coef *coef, unsigned int n );
 
-void Complete_Cubic_Spline( const double *h, const double *f, double v0, double vlast,
-                            cubic_spline_coef *coef, unsigned int n,
-                            MPI_Comm comm );
+void Complete_Cubic_Spline( LAMMPS_NS::Error*, const double *h, const double *f, double v0, double vlast,
+                            cubic_spline_coef *coef, unsigned int n );
 
 int Init_Lookup_Tables( reax_system*, control_params*, storage*,
                         mpi_datatypes*, char* );
diff --git a/src/USER-REAXC/reaxc_reset_tools.cpp b/src/USER-REAXC/reaxc_reset_tools.cpp
index 80faed1e9f..e00656694c 100644
--- a/src/USER-REAXC/reaxc_reset_tools.cpp
+++ b/src/USER-REAXC/reaxc_reset_tools.cpp
@@ -30,6 +30,9 @@
 #include "reaxc_tool_box.h"
 #include "reaxc_vector.h"
 
+#include "error.h"
+
+
 void Reset_Atoms( reax_system* system, control_params *control )
 {
   int i;
@@ -120,8 +123,7 @@ void Reset_Workspace( reax_system *system, storage *workspace )
 
 
 void Reset_Neighbor_Lists( reax_system *system, control_params *control,
-                           storage *workspace, reax_list **lists,
-                           MPI_Comm comm )
+                           storage *workspace, reax_list **lists )
 {
   int i, total_bonds, Hindex, total_hbonds;
   reax_list *bonds, *hbonds;
@@ -142,10 +144,10 @@ void Reset_Neighbor_Lists( reax_system *system, control_params *control,
     if (total_bonds >= bonds->num_intrs * DANGER_ZONE) {
       workspace->realloc.bonds = 1;
       if (total_bonds >= bonds->num_intrs) {
-        fprintf(stderr,
-                "p%d: not enough space for bonds! total=%d allocated=%d\n",
-                system->my_rank, total_bonds, bonds->num_intrs );
-        MPI_Abort( comm, INSUFFICIENT_MEMORY );
+        char errmsg[256];
+        snprintf(errmsg, 256, "Not enough space for bonds! total=%d allocated=%d\n",
+                total_bonds, bonds->num_intrs);
+        control->error_ptr->one(FLERR, errmsg);
       }
     }
   }
@@ -168,10 +170,10 @@ void Reset_Neighbor_Lists( reax_system *system, control_params *control,
     if (total_hbonds >= hbonds->num_intrs * 0.90/*DANGER_ZONE*/) {
       workspace->realloc.hbonds = 1;
       if (total_hbonds >= hbonds->num_intrs) {
-        fprintf(stderr,
-                "p%d: not enough space for hbonds! total=%d allocated=%d\n",
-                system->my_rank, total_hbonds, hbonds->num_intrs );
-        MPI_Abort( comm, INSUFFICIENT_MEMORY );
+        char errmsg[256];
+        snprintf(errmsg, 256, "Not enough space for hbonds! total=%d allocated=%d\n",
+                total_hbonds, hbonds->num_intrs);
+        control->error_ptr->one(FLERR, errmsg);
       }
     }
   }
@@ -179,7 +181,7 @@ void Reset_Neighbor_Lists( reax_system *system, control_params *control,
 
 
 void Reset( reax_system *system, control_params *control, simulation_data *data,
-            storage *workspace, reax_list **lists, MPI_Comm comm )
+            storage *workspace, reax_list **lists )
 {
   Reset_Atoms( system, control );
 
@@ -187,6 +189,6 @@ void Reset( reax_system *system, control_params *control, simulation_data *data,
 
   Reset_Workspace( system, workspace );
 
-  Reset_Neighbor_Lists( system, control, workspace, lists, comm );
+  Reset_Neighbor_Lists( system, control, workspace, lists );
 
 }
diff --git a/src/USER-REAXC/reaxc_reset_tools.h b/src/USER-REAXC/reaxc_reset_tools.h
index c2a90072d5..20d1ab6964 100644
--- a/src/USER-REAXC/reaxc_reset_tools.h
+++ b/src/USER-REAXC/reaxc_reset_tools.h
@@ -34,7 +34,7 @@ void Reset_Simulation_Data( simulation_data*, int );
 void Reset_Timing( reax_timing* );
 void Reset_Workspace( reax_system*, storage* );
 void Reset_Neighbor_Lists( reax_system*, control_params*, storage*,
-                           reax_list**, MPI_Comm );
+                           reax_list** );
 void Reset( reax_system*, control_params*, simulation_data*, storage*,
-            reax_list**, MPI_Comm );
+            reax_list** );
 #endif
diff --git a/src/USER-REAXC/reaxc_tool_box.cpp b/src/USER-REAXC/reaxc_tool_box.cpp
index 9e662e7a45..b6058b2516 100644
--- a/src/USER-REAXC/reaxc_tool_box.cpp
+++ b/src/USER-REAXC/reaxc_tool_box.cpp
@@ -27,6 +27,8 @@
 #include "pair_reaxc.h"
 #include "reaxc_tool_box.h"
 
+#include "error.h"
+
 struct timeval tim;
 double t_end;
 
@@ -53,23 +55,25 @@ int Tokenize( char* s, char*** tok )
   return count;
 }
 
+
+
 /* safe malloc */
-void *smalloc( rc_bigint n, const char *name, MPI_Comm comm )
+void *smalloc( LAMMPS_NS::Error *error_ptr, rc_bigint n, const char *name )
 {
   void *ptr;
+  char errmsg[256];
 
   if (n <= 0) {
-    fprintf( stderr, "WARNING: trying to allocate %ld bytes for array %s. ",
-             n, name );
-    fprintf( stderr, "returning NULL.\n" );
+    snprintf(errmsg, 256, "Trying to allocate %ld bytes for array %s. "
+              "returning NULL.", n, name);
+    error_ptr->one(FLERR,errmsg);
     return NULL;
   }
 
   ptr = malloc( n );
   if (ptr == NULL) {
-    fprintf( stderr, "ERROR: failed to allocate %ld bytes for array %s",
-             n, name );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+    snprintf(errmsg, 256, "Failed to allocate %ld bytes for array %s", n, name);
+    error_ptr->one(FLERR,errmsg);
   }
 
   return ptr;
@@ -77,29 +81,30 @@ void *smalloc( rc_bigint n, const char *name, MPI_Comm comm )
 
 
 /* safe calloc */
-void *scalloc( rc_bigint n, rc_bigint size, const char *name, MPI_Comm comm )
+void *scalloc( LAMMPS_NS::Error *error_ptr, rc_bigint n, rc_bigint size, const char *name )
 {
   void *ptr;
+  char errmsg[256];
 
   if (n <= 0) {
-    fprintf( stderr, "WARNING: trying to allocate %ld elements for array %s. ",
-             n, name );
-    fprintf( stderr, "returning NULL.\n" );
+    snprintf(errmsg, 256, "Trying to allocate %ld elements for array %s. "
+            "returning NULL.\n", n, name );
+    error_ptr->one(FLERR,errmsg);
     return NULL;
   }
 
   if (size <= 0) {
-    fprintf( stderr, "WARNING: elements size for array %s is %ld. ",
-             name, size );
-    fprintf( stderr, "returning NULL.\n" );
+    snprintf(errmsg, 256, "Elements size for array %s is %ld. "
+             "returning NULL", name, size );
+             error_ptr->one(FLERR,errmsg);
     return NULL;
   }
 
   ptr = calloc( n, size );
   if (ptr == NULL) {
-    fprintf( stderr, "ERROR: failed to allocate %ld bytes for array %s",
-             n*size, name );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+    char errmsg[256];
+    snprintf(errmsg, 256, "Failed to allocate %ld bytes for array %s", n*size, name);
+    error_ptr->one(FLERR,errmsg);
   }
 
   return ptr;
@@ -107,11 +112,12 @@ void *scalloc( rc_bigint n, rc_bigint size, const char *name, MPI_Comm comm )
 
 
 /* safe free */
-void sfree( void *ptr, const char *name )
+void sfree( LAMMPS_NS::Error* error_ptr, void *ptr, const char *name )
 {
   if (ptr == NULL) {
-    fprintf( stderr, "WARNING: trying to free the already NULL pointer %s!\n",
-             name );
+    char errmsg[256];
+    snprintf(errmsg, 256, "Trying to free the already NULL pointer %s", name );
+    error_ptr->one(FLERR,errmsg);
     return;
   }
 
diff --git a/src/USER-REAXC/reaxc_tool_box.h b/src/USER-REAXC/reaxc_tool_box.h
index 7f8dd455ca..0465376dba 100644
--- a/src/USER-REAXC/reaxc_tool_box.h
+++ b/src/USER-REAXC/reaxc_tool_box.h
@@ -37,7 +37,7 @@ double Get_Time( );
 int   Tokenize( char*, char*** );
 
 /* from lammps */
-void *smalloc( rc_bigint, const char*, MPI_Comm );
-void *scalloc( rc_bigint, rc_bigint, const char*, MPI_Comm );
-void sfree( void*, const char* );
+void *smalloc( LAMMPS_NS::Error*, rc_bigint, const char* );
+void *scalloc( LAMMPS_NS::Error*, rc_bigint, rc_bigint, const char* );
+void sfree( LAMMPS_NS::Error*, void*, const char* );
 #endif
diff --git a/src/USER-REAXC/reaxc_traj.cpp b/src/USER-REAXC/reaxc_traj.cpp
index 54d8b3219c..356d7b6eeb 100644
--- a/src/USER-REAXC/reaxc_traj.cpp
+++ b/src/USER-REAXC/reaxc_traj.cpp
@@ -29,8 +29,9 @@
 #include "reaxc_list.h"
 #include "reaxc_tool_box.h"
 
-int Reallocate_Output_Buffer( output_controls *out_control, int req_space,
-                              MPI_Comm comm )
+#include "error.h"
+
+int Reallocate_Output_Buffer( LAMMPS_NS::Error *error_ptr, output_controls *out_control, int req_space )
 {
   if (out_control->buffer_len > 0)
     free( out_control->buffer );
@@ -38,10 +39,9 @@ int Reallocate_Output_Buffer( output_controls *out_control, int req_space,
   out_control->buffer_len = (int)(req_space*SAFE_ZONE);
   out_control->buffer = (char*) malloc(out_control->buffer_len*sizeof(char));
   if (out_control->buffer == NULL) {
-    fprintf( stderr,
-             "insufficient memory for required buffer size %d. terminating!\n",
-             (int) (req_space*SAFE_ZONE) );
-    MPI_Abort( comm, INSUFFICIENT_MEMORY );
+    char errmsg[256];
+    snprintf(errmsg, 256, "Insufficient memory for required buffer size %d", (int) (req_space*SAFE_ZONE));
+    error_ptr->one(FLERR,errmsg);
   }
 
   return SUCCESS;
@@ -58,7 +58,7 @@ void Write_Skip_Line( output_controls *out_control, mpi_datatypes * /*mpi_data*/
 
 
 int Write_Header( reax_system *system, control_params *control,
-                  output_controls *out_control, mpi_datatypes *mpi_data )
+                  output_controls *out_control, mpi_datatypes * /*mpi_data*/ )
 {
   int  num_hdr_lines, my_hdr_lines, buffer_req;
   char ensembles[ens_N][25] =  { "NVE", "NVT", "fully flexible NPT",
@@ -83,7 +83,7 @@ int Write_Header( reax_system *system, control_params *control,
   my_hdr_lines = num_hdr_lines * ( system->my_rank == MASTER_NODE );
   buffer_req = my_hdr_lines * HEADER_LINE_LEN;
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( control->error_ptr, out_control, buffer_req );
 
   /* only the master node writes into trajectory header */
   if (system->my_rank == MASTER_NODE) {
@@ -278,7 +278,7 @@ int Write_Init_Desc( reax_system *system, control_params * /*control*/,
   else buffer_req = system->n * INIT_DESC_LEN + 1;
 
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( system->error_ptr, out_control, buffer_req );
 
   out_control->line[0] = 0;
   out_control->buffer[0] = 0;
@@ -357,7 +357,7 @@ int Init_Traj( reax_system *system, control_params *control,
 
 int Write_Frame_Header( reax_system *system, control_params *control,
                         simulation_data *data, output_controls *out_control,
-                        mpi_datatypes *mpi_data )
+                        mpi_datatypes * /*mpi_data*/ )
 {
   int me, num_frm_hdr_lines, my_frm_hdr_lines, buffer_req;
 
@@ -367,7 +367,7 @@ int Write_Frame_Header( reax_system *system, control_params *control,
   my_frm_hdr_lines = num_frm_hdr_lines * ( me == MASTER_NODE );
   buffer_req = my_frm_hdr_lines * HEADER_LINE_LEN;
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( control->error_ptr, out_control, buffer_req );
 
   /* only the master node writes into trajectory header */
   if (me == MASTER_NODE) {
@@ -500,7 +500,7 @@ int Write_Atoms( reax_system *system, control_params * /*control*/,
   else buffer_req = system->n * line_len + 1;
 
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( system->error_ptr, out_control, buffer_req );
 
   /* fill in buffer */
   out_control->line[0] = 0;
@@ -531,9 +531,7 @@ int Write_Atoms( reax_system *system, control_params * /*control*/,
                p_atom->f[0], p_atom->f[1], p_atom->f[2], p_atom->q );
       break;
     default:
-      fprintf( stderr,
-               "write_traj_atoms: unknown atom trajectroy format!\n");
-      MPI_Abort( mpi_data->world, UNKNOWN_OPTION );
+      system->error_ptr->one(FLERR,"Write_traj_atoms: unknown atom trajectory format");
     }
 
     strncpy( out_control->buffer + i*line_len, out_control->line, line_len+1 );
@@ -592,7 +590,7 @@ int Write_Bonds(reax_system *system, control_params *control, reax_list *bonds,
   else buffer_req = my_bonds * line_len + 1;
 
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( system->error_ptr, out_control, buffer_req );
 
   /* fill in the buffer */
   out_control->line[0] = 0;
@@ -619,8 +617,7 @@ int Write_Bonds(reax_system *system, control_params *control, reax_list *bonds,
                    bo_ij->bo_data.BO_pi, bo_ij->bo_data.BO_pi2 );
           break;
         default:
-          fprintf(stderr, "write_traj_bonds: FATAL! invalid bond_info option");
-          MPI_Abort( mpi_data->world, UNKNOWN_OPTION );
+          system->error_ptr->one(FLERR, "Write_traj_bonds: FATAL! invalid bond_info option");
         }
         strncpy( out_control->buffer + my_bonds*line_len,
                  out_control->line, line_len+1 );
@@ -693,7 +690,7 @@ int Write_Angles( reax_system *system, control_params *control,
   else buffer_req = my_angles * line_len + 1;
 
   if (buffer_req > out_control->buffer_len * DANGER_ZONE)
-    Reallocate_Output_Buffer( out_control, buffer_req, mpi_data->world );
+    Reallocate_Output_Buffer( system->error_ptr, out_control, buffer_req );
 
   /* fill in the buffer */
   my_angles = 0;
diff --git a/src/USER-REAXC/reaxc_traj.h b/src/USER-REAXC/reaxc_traj.h
index 72c56637eb..4966bf11d8 100644
--- a/src/USER-REAXC/reaxc_traj.h
+++ b/src/USER-REAXC/reaxc_traj.h
@@ -42,7 +42,11 @@
 #define SCI_LINE  "%-37s%-24g\n"
 #define REAL3_LINE "%-32s%9.3f,%9.3f,%9.3f\n"
 
+#if defined(LAMMPS_BIGBIG)
+#define INIT_DESC "%9ld%3d%9s%10.3f\n" //AtomID - AtomType, AtomName, AtomMass
+#else
 #define INIT_DESC "%9d%3d%9s%10.3f\n" //AtomID - AtomType, AtomName, AtomMass
+#endif
 #define INIT_DESC_LEN 32
 
 #define SIZE_INFO_LINE2 "%-10d%-10d\n"
@@ -51,21 +55,33 @@
 #define SIZE_INFO_LINE3 "%-10d%-10d%-10d\n"
 #define SIZE_INFO_LEN3 31
 
+#if defined(LAMMPS_BIGBIG)
+#define ATOM_BASIC "%9ld%10.3f%10.3f%10.3f%10.3f\n" //AtomID AtomType (X Y Z) Charge
+#define ATOM_wV    "%9ld%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Vx Vy Vz) Charge
+#define ATOM_wF    "%9ld%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Fx Fy Fz) Charge
+#define ATOM_FULL  "%9ld%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Vx Vy Vz) (Fx Fy Fz) Charge
+#else
 #define ATOM_BASIC "%9d%10.3f%10.3f%10.3f%10.3f\n" //AtomID AtomType (X Y Z) Charge
-#define ATOM_BASIC_LEN 50
 #define ATOM_wV    "%9d%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Vx Vy Vz) Charge
-#define ATOM_wV_LEN 80
 #define ATOM_wF    "%9d%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Fx Fy Fz) Charge
-#define ATOM_wF_LEN 80
 #define ATOM_FULL  "%9d%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f%10.3f\n" //AtomID (X Y Z) (Vx Vy Vz) (Fx Fy Fz) Charge
+#endif
+#define ATOM_BASIC_LEN 50
+#define ATOM_wV_LEN 80
+#define ATOM_wF_LEN 80
 #define ATOM_FULL_LEN 110
 
+#if defined(LAMMPS_BIGBIG)
+#define BOND_BASIC "%9ld%9ld%10.3f%10.3f\n" // Atom1 Atom2 Dist Total_BO
+#define BOND_FULL  "%9ld%9ld%10.3f%10.3f%10.3f%10.3f%10.3f\n" // Atom1 Atom2 Dist Total_BO BOs BOpi BOpi2
+#define ANGLE_BASIC "%9ld%9ld%9ld%10.3f\n" // Atom1 Atom2 Atom3 Theta
+#else
 #define BOND_BASIC "%9d%9d%10.3f%10.3f\n" // Atom1 Atom2 Dist Total_BO
-#define BOND_BASIC_LEN 39
 #define BOND_FULL  "%9d%9d%10.3f%10.3f%10.3f%10.3f%10.3f\n" // Atom1 Atom2 Dist Total_BO BOs BOpi BOpi2
-#define BOND_FULL_LEN 69
-
 #define ANGLE_BASIC "%9d%9d%9d%10.3f\n" // Atom1 Atom2 Atom3 Theta
+#endif
+#define BOND_BASIC_LEN 39
+#define BOND_FULL_LEN 69
 #define ANGLE_BASIC_LEN 38
 
 enum ATOM_LINE_OPTS  { OPT_NOATOM = 0, OPT_ATOM_BASIC = 4, OPT_ATOM_wF = 5, OPT_ATOM_wV = 6, OPT_ATOM_FULL = 7, NR_OPT_ATOM = 8 };
diff --git a/src/USER-REAXC/reaxc_types.h b/src/USER-REAXC/reaxc_types.h
index 2666fcf85c..b05f655040 100644
--- a/src/USER-REAXC/reaxc_types.h
+++ b/src/USER-REAXC/reaxc_types.h
@@ -39,6 +39,9 @@
 #include <sys/time.h>
 #include "accelerator_kokkos.h"
 
+
+namespace LAMMPS_NS { class Error;}
+
 #if defined LMP_USER_OMP
 #define OMP_TIMING 0
 
@@ -392,8 +395,6 @@ typedef struct
   double ghost_cutoff;
 } boundary_cutoff;
 
-using LAMMPS_NS::Pair;
-
 struct _reax_system
 {
   reax_interaction reax_param;
@@ -411,7 +412,8 @@ struct _reax_system
   boundary_cutoff  bndry_cuts;
   reax_atom       *my_atoms;
 
-  class Pair *pair_ptr;
+  class LAMMPS_NS::Error *error_ptr;
+  class LAMMPS_NS::Pair *pair_ptr;
   int my_bonds;
   int mincap;
   double safezone, saferzone;
@@ -488,6 +490,8 @@ typedef struct
 
   int lgflag;
   int enobondsflag;
+  class LAMMPS_NS::Error *error_ptr;
+  int me;
 
 } control_params;
 
@@ -774,6 +778,7 @@ struct _reax_list
 
   int type;
   list_type select;
+  class LAMMPS_NS::Error     *error_ptr;
 };
 typedef _reax_list  reax_list;
 
diff --git a/src/USER-REAXC/reaxc_valence_angles.cpp b/src/USER-REAXC/reaxc_valence_angles.cpp
index af1f1f8003..4ba870b6d9 100644
--- a/src/USER-REAXC/reaxc_valence_angles.cpp
+++ b/src/USER-REAXC/reaxc_valence_angles.cpp
@@ -30,6 +30,8 @@
 #include "reaxc_list.h"
 #include "reaxc_vector.h"
 
+#include "error.h"
+
 static double Dot( double* v1, double* v2, int k )
 {
   double ret = 0.0;
@@ -405,9 +407,10 @@ void Valence_Angles( reax_system *system, control_params *control,
   if (num_thb_intrs >= thb_intrs->num_intrs * DANGER_ZONE) {
     workspace->realloc.num_3body = num_thb_intrs;
     if (num_thb_intrs > thb_intrs->num_intrs) {
-      fprintf( stderr, "step%d-ran out of space on angle_list: top=%d, max=%d",
-               data->step, num_thb_intrs, thb_intrs->num_intrs );
-      MPI_Abort( MPI_COMM_WORLD, INSUFFICIENT_MEMORY );
+      char errmsg[128];
+      snprintf(errmsg, 128, "step%d-ran out of space on angle_list: top=%d, max=%d",
+               data->step, num_thb_intrs, thb_intrs->num_intrs);
+      control->error_ptr->one(FLERR, errmsg);
     }
   }
 
diff --git a/src/USER-SCAFACOS/scafacos.cpp b/src/USER-SCAFACOS/scafacos.cpp
index 4b8e10123c..497442fbe8 100644
--- a/src/USER-SCAFACOS/scafacos.cpp
+++ b/src/USER-SCAFACOS/scafacos.cpp
@@ -197,12 +197,7 @@ void Scafacos::compute(int eflag, int vflag)
       fcs_set_redistribute((FCS)fcs,0);
   }
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else
-  {
-    eflag_atom = 0;
-    vflag_global = 0;
-  }
+  ev_init(eflag,vflag);
 
   // grow xpbc, epot, efield if necessary
 
diff --git a/src/USER-SDPD/pair_sdpd_taitwater_isothermal.cpp b/src/USER-SDPD/pair_sdpd_taitwater_isothermal.cpp
index 7cfc950eff..db80debe51 100644
--- a/src/USER-SDPD/pair_sdpd_taitwater_isothermal.cpp
+++ b/src/USER-SDPD/pair_sdpd_taitwater_isothermal.cpp
@@ -71,8 +71,7 @@ void PairSDPDTaitwaterIsothermal::compute (int eflag, int vflag) {
   double rsq, tmp, wfd, delVdotDelR;
   double prefactor, wiener[3][3], f_random[3];
 
-  if (eflag || vflag) ev_setup (eflag, vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **v = atom->vest;
   double **x = atom->x;
diff --git a/src/USER-SMD/pair_smd_hertz.cpp b/src/USER-SMD/pair_smd_hertz.cpp
index 13f48e995e..541be9f05c 100644
--- a/src/USER-SMD/pair_smd_hertz.cpp
+++ b/src/USER-SMD/pair_smd_hertz.cpp
@@ -87,10 +87,7 @@ void PairHertz::compute(int eflag, int vflag) {
         double *rmass = atom->rmass;
 
         evdwl = 0.0;
-        if (eflag || vflag)
-                ev_setup(eflag, vflag);
-        else
-                evflag = vflag_fdotr = 0;
+        ev_init(eflag, vflag);
 
         double **f = atom->f;
         double **x = atom->x;
diff --git a/src/USER-SMD/pair_smd_tlsph.cpp b/src/USER-SMD/pair_smd_tlsph.cpp
index ab6b7d2785..1d7bbca780 100644
--- a/src/USER-SMD/pair_smd_tlsph.cpp
+++ b/src/USER-SMD/pair_smd_tlsph.cpp
@@ -308,7 +308,7 @@ void PairTlsph::PreCompute() {
                          */
 
                         if ((detF[i] < DETF_MIN) || (detF[i] > DETF_MAX) || (numNeighsRefConfig[i] == 0)) {
-                                printf("deleting particle [%d] because det(F)=%f is outside stable range %f -- %f \n", tag[i],
+                                printf("deleting particle [" TAGINT_FORMAT "] because det(F)=%f is outside stable range %f -- %f \n", tag[i],
                                                 Fincr[i].determinant(),
                                                 DETF_MIN, DETF_MAX);
                                 printf("nn = %d, damage=%f\n", numNeighsRefConfig[i], damage[i]);
@@ -448,10 +448,7 @@ void PairTlsph::ComputeForces(int eflag, int vflag) {
         Matrix3d eye;
         eye.setIdentity();
 
-        if (eflag || vflag)
-                ev_setup(eflag, vflag);
-        else
-                evflag = vflag_fdotr = 0;
+        ev_init(eflag, vflag);
 
         /*
          * iterate over pairs of particles i, j and assign forces using PK1 stress tensor
diff --git a/src/USER-SMD/pair_smd_triangulated_surface.cpp b/src/USER-SMD/pair_smd_triangulated_surface.cpp
index e40c876ec3..d3a4983379 100644
--- a/src/USER-SMD/pair_smd_triangulated_surface.cpp
+++ b/src/USER-SMD/pair_smd_triangulated_surface.cpp
@@ -96,10 +96,7 @@ void PairTriSurf::compute(int eflag, int vflag) {
         Vector2d w2d, rhs;
 
         evdwl = 0.0;
-        if (eflag || vflag)
-                ev_setup(eflag, vflag);
-        else
-                evflag = vflag_fdotr = 0;
+        ev_init(eflag, vflag);
 
         tagint *mol = atom->molecule;
         double **f = atom->f;
diff --git a/src/USER-SMD/pair_smd_ulsph.cpp b/src/USER-SMD/pair_smd_ulsph.cpp
index 50af6e2356..2c4a2de989 100644
--- a/src/USER-SMD/pair_smd_ulsph.cpp
+++ b/src/USER-SMD/pair_smd_ulsph.cpp
@@ -386,10 +386,7 @@ void PairULSPH::compute(int eflag, int vflag) {
         int k;
         SelfAdjointEigenSolver < Matrix3d > es;
 
-        if (eflag || vflag)
-                ev_setup(eflag, vflag);
-        else
-                evflag = vflag_fdotr = 0;
+        ev_init(eflag, vflag);
 
         if (atom->nmax > nmax) {
 //printf("... allocating in compute with nmax = %d\n", atom->nmax);
diff --git a/src/USER-SMD/smd_material_models.h b/src/USER-SMD/smd_material_models.h
index acb498c04d..557612bdf5 100644
--- a/src/USER-SMD/smd_material_models.h
+++ b/src/USER-SMD/smd_material_models.h
@@ -22,10 +22,10 @@
  See the README file in the top-level LAMMPS directory.
  ------------------------------------------------------------------------- */
 
-#ifndef SMD_MATERIAL_MODELS_H_
-#define SMD_MATERIAL_MODELS_H_
+#ifndef SMD_MATERIAL_MODELS_H
+#define SMD_MATERIAL_MODELS_H
 
-using namespace Eigen;
+#include <Eigen/Eigen>
 
 /*
  * EOS models
@@ -42,22 +42,22 @@ void PerfectGasEOS(const double gamma, const double vol, const double mass, cons
 /*
  * Material strength models
  */
-void LinearStrength(const double mu, const Matrix3d sigmaInitial_dev, const Matrix3d d_dev, const double dt,
-                Matrix3d &sigmaFinal_dev__, Matrix3d &sigma_dev_rate__);
-void LinearPlasticStrength(const double G, const double yieldStress, const Matrix3d sigmaInitial_dev, const Matrix3d d_dev,
-                const double dt, Matrix3d &sigmaFinal_dev__, Matrix3d &sigma_dev_rate__, double &plastic_strain_increment);
+void LinearStrength(const double mu, const Eigen::Matrix3d sigmaInitial_dev, const Eigen::Matrix3d d_dev, const double dt,
+                Eigen::Matrix3d &sigmaFinal_dev__, Eigen::Matrix3d &sigma_dev_rate__);
+void LinearPlasticStrength(const double G, const double yieldStress, const Eigen::Matrix3d sigmaInitial_dev, const Eigen::Matrix3d d_dev,
+                const double dt, Eigen::Matrix3d &sigmaFinal_dev__, Eigen::Matrix3d &sigma_dev_rate__, double &plastic_strain_increment);
 void JohnsonCookStrength(const double G, const double cp, const double espec, const double A, const double B, const double a,
                 const double C, const double epdot0, const double T0, const double Tmelt, const double M, const double dt, const double ep,
-                const double epdot, const Matrix3d sigmaInitial_dev, const Matrix3d d_dev, Matrix3d &sigmaFinal_dev__,
-                Matrix3d &sigma_dev_rate__, double &plastic_strain_increment);
+                const double epdot, const Eigen::Matrix3d sigmaInitial_dev, const Eigen::Matrix3d d_dev, Eigen::Matrix3d &sigmaFinal_dev__,
+                Eigen::Matrix3d &sigma_dev_rate__, double &plastic_strain_increment);
 
 /*
  * Damage models
  */
 
-bool IsotropicMaxStrainDamage(const Matrix3d E, const double maxStrain);
-bool IsotropicMaxStressDamage(const Matrix3d E, const double maxStrain);
-double JohnsonCookFailureStrain(const double p, const Matrix3d Sdev, const double d1, const double d2, const double d3,
+bool IsotropicMaxStrainDamage(const Eigen::Matrix3d E, const double maxStrain);
+bool IsotropicMaxStressDamage(const Eigen::Matrix3d E, const double maxStrain);
+double JohnsonCookFailureStrain(const double p, const Eigen::Matrix3d Sdev, const double d1, const double d2, const double d3,
                 const double d4, const double epdot0, const double epdot);
 
 
diff --git a/src/USER-SMD/smd_math.h b/src/USER-SMD/smd_math.h
index cea9e9dbc7..52e7c983d5 100644
--- a/src/USER-SMD/smd_math.h
+++ b/src/USER-SMD/smd_math.h
@@ -9,14 +9,11 @@
  *
  * ----------------------------------------------------------------------- */
 
-//test
-#ifndef SMD_MATH_H_
-#define SMD_MATH_H_
+#ifndef SMD_MATH_H
+#define SMD_MATH_H
 
 #include <Eigen/Eigen>
 #include <iostream>
-using namespace Eigen;
-using namespace std;
 
 namespace SMD_Math {
 static inline void LimitDoubleMagnitude(double &x, const double limit) {
@@ -31,8 +28,8 @@ static inline void LimitDoubleMagnitude(double &x, const double limit) {
 /*
  * deviator of a tensor
  */
-static inline Matrix3d Deviator(const Matrix3d M) {
-        Matrix3d eye;
+static inline Eigen::Matrix3d Deviator(const Eigen::Matrix3d M) {
+        Eigen::Matrix3d eye;
         eye.setIdentity();
         eye *= M.trace() / 3.0;
         return M - eye;
@@ -53,14 +50,14 @@ static inline Matrix3d Deviator(const Matrix3d M) {
  * obtained again from an SVD. The rotation should proper now, i.e., det(R) = +1.
  */
 
-static inline bool PolDec(Matrix3d M, Matrix3d &R, Matrix3d &T, bool scaleF) {
+static inline bool PolDec(Eigen::Matrix3d M, Eigen::Matrix3d &R, Eigen::Matrix3d &T, bool scaleF) {
 
-        JacobiSVD<Matrix3d> svd(M, ComputeFullU | ComputeFullV); // SVD(A) = U S V*
-        Vector3d S_eigenvalues = svd.singularValues();
-        Matrix3d S = svd.singularValues().asDiagonal();
-        Matrix3d U = svd.matrixU();
-        Matrix3d V = svd.matrixV();
-        Matrix3d eye;
+        Eigen::JacobiSVD<Eigen::Matrix3d> svd(M, Eigen::ComputeFullU | Eigen::ComputeFullV); // SVD(A) = U S V*
+        Eigen::Vector3d S_eigenvalues = svd.singularValues();
+        Eigen::Matrix3d S = svd.singularValues().asDiagonal();
+        Eigen::Matrix3d U = svd.matrixU();
+        Eigen::Matrix3d V = svd.matrixV();
+        Eigen::Matrix3d eye;
         eye.setIdentity();
 
         // now do polar decomposition into M = R * T, where R is rotation
@@ -105,16 +102,12 @@ static inline bool PolDec(Matrix3d M, Matrix3d &R, Matrix3d &T, bool scaleF) {
  * Pseudo-inverse via SVD
  */
 
-static inline void pseudo_inverse_SVD(Matrix3d &M) {
+static inline void pseudo_inverse_SVD(Eigen::Matrix3d &M) {
 
-        //JacobiSVD < Matrix3d > svd(M, ComputeFullU | ComputeFullV);
-        JacobiSVD<Matrix3d> svd(M, ComputeFullU); // one Eigevector base is sufficient because matrix is square and symmetric
+        Eigen::JacobiSVD<Eigen::Matrix3d> svd(M, Eigen::ComputeFullU); // one Eigevector base is sufficient because matrix is square and symmetric
 
-        Vector3d singularValuesInv;
-        Vector3d singularValues = svd.singularValues();
-
-//cout << "Here is the matrix V:" << endl << V * singularValues.asDiagonal() * U << endl;
-//cout << "Its singular values are:" << endl << singularValues << endl;
+        Eigen::Vector3d singularValuesInv;
+        Eigen::Vector3d singularValues = svd.singularValues();
 
         double pinvtoler = 1.0e-16; // 2d machining example goes unstable if this value is increased (1.0e-16).
         for (int row = 0; row < 3; row++) {
@@ -126,39 +119,19 @@ static inline void pseudo_inverse_SVD(Matrix3d &M) {
         }
 
         M = svd.matrixU() * singularValuesInv.asDiagonal() * svd.matrixU().transpose();
-
-//      JacobiSVD < Matrix3d > svd(M, ComputeFullU | ComputeFullV);
-//
-//      Vector3d singularValuesInv;
-//      Vector3d singularValues = svd.singularValues();
-//
-//      //cout << "Here is the matrix V:" << endl << V * singularValues.asDiagonal() * U << endl;
-//      //cout << "Its singular values are:" << endl << singularValues << endl;
-//
-//      double pinvtoler = 1.0e-16; // 2d machining example goes unstable if this value is increased (1.0e-16).
-//      for (int row = 0; row < 3; row++) {
-//              if (singularValues(row) > pinvtoler) {
-//                      singularValuesInv(row) = 1.0 / singularValues(row);
-//              } else {
-//                      singularValuesInv(row) = 0.0;
-//              }
-//      }
-//
-//      M = svd.matrixU() * singularValuesInv.asDiagonal() * svd.matrixV().transpose();
-
 }
 
 /*
  * test if two matrices are equal
  */
-static inline double TestMatricesEqual(Matrix3d A, Matrix3d B, double eps) {
-        Matrix3d diff;
+static inline double TestMatricesEqual(Eigen::Matrix3d A, Eigen::Matrix3d B, double eps) {
+        Eigen::Matrix3d diff;
         diff = A - B;
         double norm = diff.norm();
         if (norm > eps) {
-                printf("Matrices A and B are not equal! The L2-norm difference is: %g\n", norm);
-                cout << "Here is matrix A:" << endl << A << endl;
-                cout << "Here is matrix B:" << endl << B << endl;
+                std::cout << "Matrices A and B are not equal! The L2-norm difference is: " << norm << "\n"
+                          << "Here is matrix A:\n" << A << "\n"
+                          << "Here is matrix B:\n" << B << std::endl;
         }
         return norm;
 }
@@ -167,12 +140,12 @@ static inline double TestMatricesEqual(Matrix3d A, Matrix3d B, double eps) {
  Limit eigenvalues of a matrix to upper and lower bounds.
  ------------------------------------------------------------------------- */
 
-static inline Matrix3d LimitEigenvalues(Matrix3d S, double limitEigenvalue) {
+static inline Eigen::Matrix3d LimitEigenvalues(Eigen::Matrix3d S, double limitEigenvalue) {
 
         /*
          * compute Eigenvalues of matrix S
          */
-        SelfAdjointEigenSolver < Matrix3d > es;
+        Eigen::SelfAdjointEigenSolver < Eigen::Matrix3d > es;
         es.compute(S);
 
         double max_eigenvalue = es.eigenvalues().maxCoeff();
@@ -183,17 +156,17 @@ static inline Matrix3d LimitEigenvalues(Matrix3d S, double limitEigenvalue) {
         if ((amax_eigenvalue > limitEigenvalue) || (amin_eigenvalue > limitEigenvalue)) {
                 if (amax_eigenvalue > amin_eigenvalue) { // need to scale with max_eigenvalue
                         double scale = amax_eigenvalue / limitEigenvalue;
-                        Matrix3d V = es.eigenvectors();
-                        Matrix3d S_diag = V.inverse() * S * V; // diagonalized input matrix
+                        Eigen::Matrix3d V = es.eigenvectors();
+                        Eigen::Matrix3d S_diag = V.inverse() * S * V; // diagonalized input matrix
                         S_diag /= scale;
-                        Matrix3d S_scaled = V * S_diag * V.inverse(); // undiagonalize matrix
+                        Eigen::Matrix3d S_scaled = V * S_diag * V.inverse(); // undiagonalize matrix
                         return S_scaled;
                 } else { // need to scale using min_eigenvalue
                         double scale = amin_eigenvalue / limitEigenvalue;
-                        Matrix3d V = es.eigenvectors();
-                        Matrix3d S_diag = V.inverse() * S * V; // diagonalized input matrix
+                        Eigen::Matrix3d V = es.eigenvectors();
+                        Eigen::Matrix3d S_diag = V.inverse() * S * V; // diagonalized input matrix
                         S_diag /= scale;
-                        Matrix3d S_scaled = V * S_diag * V.inverse(); // undiagonalize matrix
+                        Eigen::Matrix3d S_scaled = V * S_diag * V.inverse(); // undiagonalize matrix
                         return S_scaled;
                 }
         } else { // limiting does not apply
@@ -201,17 +174,17 @@ static inline Matrix3d LimitEigenvalues(Matrix3d S, double limitEigenvalue) {
         }
 }
 
-static inline bool LimitMinMaxEigenvalues(Matrix3d &S, double min, double max) {
+static inline bool LimitMinMaxEigenvalues(Eigen::Matrix3d &S, double min, double max) {
 
         /*
          * compute Eigenvalues of matrix S
          */
-        SelfAdjointEigenSolver < Matrix3d > es;
+        Eigen::SelfAdjointEigenSolver < Eigen::Matrix3d > es;
         es.compute(S);
 
         if ((es.eigenvalues().maxCoeff() > max) || (es.eigenvalues().minCoeff() < min)) {
-                Matrix3d S_diag = es.eigenvalues().asDiagonal();
-                Matrix3d V = es.eigenvectors();
+                Eigen::Matrix3d S_diag = es.eigenvalues().asDiagonal();
+                Eigen::Matrix3d V = es.eigenvectors();
                 for (int i = 0; i < 3; i++) {
                         if (S_diag(i, i) < min) {
                                 //printf("limiting eigenvalue %f --> %f\n", S_diag(i, i), min);
@@ -229,10 +202,10 @@ static inline bool LimitMinMaxEigenvalues(Matrix3d &S, double min, double max) {
         }
 }
 
-static inline void reconstruct_rank_deficient_shape_matrix(Matrix3d &K) {
+static inline void reconstruct_rank_deficient_shape_matrix(Eigen::Matrix3d &K) {
 
-        JacobiSVD<Matrix3d> svd(K, ComputeFullU | ComputeFullV);
-        Vector3d singularValues = svd.singularValues();
+        Eigen::JacobiSVD<Eigen::Matrix3d> svd(K, Eigen::ComputeFullU | Eigen::ComputeFullV);
+        Eigen::Vector3d singularValues = svd.singularValues();
 
         for (int i = 0; i < 3; i++) {
                 if (singularValues(i) < 1.0e-8) {
diff --git a/src/USER-SMTBQ/README b/src/USER-SMTBQ/README
index 74b621eef1..e778c65be2 100644
--- a/src/USER-SMTBQ/README
+++ b/src/USER-SMTBQ/README
@@ -2,9 +2,11 @@ This package implements the Second Moment Tight Binding - QEq (SMTB-Q)
 potential for the description of ionocovalent bonds in oxides.
 
 Authors: Nicolas Salles, Emile Maras, Olivier Politano, Robert Tetot
-at LAAS-CNRS in France.
+at ICB, Universite de Bourgogne and ICMMO, Universite Paris-Sud.
 
-Contact emails:  lammps@u-bourgogne.fr, nsalles@laas.fr
+Contact emails:  lammps@u-bourgogne.fr, nsalles33@gmail.com
+
+This package is occasionally maintained.
 
 See the doc page for the pair_style smtbq command to get started.
 
diff --git a/src/USER-SMTBQ/pair_smtbq.cpp b/src/USER-SMTBQ/pair_smtbq.cpp
index 5c3189fc31..ba7f8eb88c 100644
--- a/src/USER-SMTBQ/pair_smtbq.cpp
+++ b/src/USER-SMTBQ/pair_smtbq.cpp
@@ -899,8 +899,7 @@ void PairSMTBQ::compute(int eflag, int vflag)
   evdwl = ecoul = ecovtot = ErepOO = ErepMO = Eion = 0.0;
   Eself = 0.0;
 
-  if (eflag || vflag) { ev_setup(eflag,vflag); }
-  else { evflag = vflag_fdotr = vflag_atom = 0; }
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-SPH/pair_sph_heatconduction.cpp b/src/USER-SPH/pair_sph_heatconduction.cpp
index c93e8040b2..bafa26be89 100644
--- a/src/USER-SPH/pair_sph_heatconduction.cpp
+++ b/src/USER-SPH/pair_sph_heatconduction.cpp
@@ -52,10 +52,7 @@ void PairSPHHeatConduction::compute(int eflag, int vflag) {
   double imass, jmass, h, ih, ihsq;
   double rsq, wfd, D, deltaE;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **x = atom->x;
   double *e = atom->e;
diff --git a/src/USER-SPH/pair_sph_idealgas.cpp b/src/USER-SPH/pair_sph_idealgas.cpp
index d12ee06736..db5ec964bc 100644
--- a/src/USER-SPH/pair_sph_idealgas.cpp
+++ b/src/USER-SPH/pair_sph_idealgas.cpp
@@ -53,10 +53,7 @@ void PairSPHIdealGas::compute(int eflag, int vflag) {
   double vxtmp, vytmp, vztmp, imass, jmass, fi, fj, fvisc, h, ih, ihsq;
   double rsq, wfd, delVdotDelR, mu, deltaE, ci, cj;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **v = atom->vest;
   double **x = atom->x;
diff --git a/src/USER-SPH/pair_sph_lj.cpp b/src/USER-SPH/pair_sph_lj.cpp
index 3a30ecb5fa..7d315c975c 100644
--- a/src/USER-SPH/pair_sph_lj.cpp
+++ b/src/USER-SPH/pair_sph_lj.cpp
@@ -53,10 +53,7 @@ void PairSPHLJ::compute(int eflag, int vflag) {
   double vxtmp, vytmp, vztmp, imass, jmass, fi, fj, fvisc, h, ih, ihsq, ihcub;
   double rsq, wfd, delVdotDelR, mu, deltaE, ci, cj, lrc;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **v = atom->vest;
   double **x = atom->x;
diff --git a/src/USER-SPH/pair_sph_rhosum.cpp b/src/USER-SPH/pair_sph_rhosum.cpp
index 896a422782..842dddc744 100644
--- a/src/USER-SPH/pair_sph_rhosum.cpp
+++ b/src/USER-SPH/pair_sph_rhosum.cpp
@@ -72,10 +72,7 @@ void PairSPHRhoSum::compute(int eflag, int vflag) {
   // neighbor list variables
   int inum, *ilist, *numneigh, **firstneigh;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **x = atom->x;
   double *rho = atom->rho;
diff --git a/src/USER-SPH/pair_sph_taitwater.cpp b/src/USER-SPH/pair_sph_taitwater.cpp
index 9d5a417e5b..cf3c0e914b 100644
--- a/src/USER-SPH/pair_sph_taitwater.cpp
+++ b/src/USER-SPH/pair_sph_taitwater.cpp
@@ -58,10 +58,7 @@ void PairSPHTaitwater::compute(int eflag, int vflag) {
   double vxtmp, vytmp, vztmp, imass, jmass, fi, fj, fvisc, h, ih, ihsq;
   double rsq, tmp, wfd, delVdotDelR, mu, deltaE;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **v = atom->vest;
   double **x = atom->x;
diff --git a/src/USER-SPH/pair_sph_taitwater_morris.cpp b/src/USER-SPH/pair_sph_taitwater_morris.cpp
index fb745ac7da..5cbaa5959f 100644
--- a/src/USER-SPH/pair_sph_taitwater_morris.cpp
+++ b/src/USER-SPH/pair_sph_taitwater_morris.cpp
@@ -58,10 +58,7 @@ void PairSPHTaitwaterMorris::compute(int eflag, int vflag) {
   double vxtmp, vytmp, vztmp, imass, jmass, fi, fj, fvisc, h, ih, ihsq, velx, vely, velz;
   double rsq, tmp, wfd, delVdotDelR, deltaE;
 
-  if (eflag || vflag)
-    ev_setup(eflag, vflag);
-  else
-    evflag = vflag_fdotr = 0;
+  ev_init(eflag, vflag);
 
   double **v = atom->vest;
   double **x = atom->x;
diff --git a/src/USER-YAFF/angle_cross.cpp b/src/USER-YAFF/angle_cross.cpp
index 6333c2f035..2e6731f494 100644
--- a/src/USER-YAFF/angle_cross.cpp
+++ b/src/USER-YAFF/angle_cross.cpp
@@ -67,8 +67,7 @@ void AngleCross::compute(int eflag, int vflag)
   double vx11,vx12,vy11,vy12,vz11,vz12,vx21,vx22,vy21,vy22,vz21,vz22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/angle_mm3.cpp b/src/USER-YAFF/angle_mm3.cpp
index 4e44f10408..53cb11b5df 100644
--- a/src/USER-YAFF/angle_mm3.cpp
+++ b/src/USER-YAFF/angle_mm3.cpp
@@ -61,8 +61,7 @@ void AngleMM3::compute(int eflag, int vflag)
   double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
 
   eangle = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/bond_mm3.cpp b/src/USER-YAFF/bond_mm3.cpp
index 1c464ff895..ee1ebcdd61 100644
--- a/src/USER-YAFF/bond_mm3.cpp
+++ b/src/USER-YAFF/bond_mm3.cpp
@@ -54,8 +54,7 @@ void BondMM3::compute(int eflag, int vflag)
   double rsq,r,dr,dr2,de_bond,K3,K4;
 
   ebond = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/improper_distharm.cpp b/src/USER-YAFF/improper_distharm.cpp
index 9a54afed9a..b45087a9ab 100644
--- a/src/USER-YAFF/improper_distharm.cpp
+++ b/src/USER-YAFF/improper_distharm.cpp
@@ -67,8 +67,7 @@ void ImproperDistHarm::compute(int eflag, int vflag)
   double domega,a;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/improper_sqdistharm.cpp b/src/USER-YAFF/improper_sqdistharm.cpp
index 763d82f1c5..ae702820cb 100644
--- a/src/USER-YAFF/improper_sqdistharm.cpp
+++ b/src/USER-YAFF/improper_sqdistharm.cpp
@@ -67,8 +67,7 @@ void ImproperSQDistHarm::compute(int eflag, int vflag)
   double domega,a;
 
   eimproper = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/pair_lj_switch3_coulgauss_long.cpp b/src/USER-YAFF/pair_lj_switch3_coulgauss_long.cpp
index 91c75d6945..f37dcc3ed1 100644
--- a/src/USER-YAFF/pair_lj_switch3_coulgauss_long.cpp
+++ b/src/USER-YAFF/pair_lj_switch3_coulgauss_long.cpp
@@ -91,8 +91,7 @@ void PairLJSwitch3CoulGaussLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/USER-YAFF/pair_mm3_switch3_coulgauss_long.cpp b/src/USER-YAFF/pair_mm3_switch3_coulgauss_long.cpp
index aa656e5b2d..931ed1d116 100644
--- a/src/USER-YAFF/pair_mm3_switch3_coulgauss_long.cpp
+++ b/src/USER-YAFF/pair_mm3_switch3_coulgauss_long.cpp
@@ -91,8 +91,7 @@ void PairMM3Switch3CoulGaussLong::compute(int eflag, int vflag)
   double rsq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/VORONOI/compute_voronoi_atom.cpp b/src/VORONOI/compute_voronoi_atom.cpp
index f884530fd9..860126fa77 100644
--- a/src/VORONOI/compute_voronoi_atom.cpp
+++ b/src/VORONOI/compute_voronoi_atom.cpp
@@ -642,7 +642,7 @@ void ComputeVoronoi::compute_local()
 /* ---------------------------------------------------------------------- */
 
 int ComputeVoronoi::pack_forward_comm(int n, int *list, double *buf,
-                                  int pbc_flag, int *pbc)
+                                  int /* pbc_flag */, int * /* pbc */)
 {
   int i,m=0;
   for (i = 0; i < n; ++i) buf[m++] = rfield[list[i]];
diff --git a/src/angle.h b/src/angle.h
index 0247fa0ff8..3d8371242e 100644
--- a/src/angle.h
+++ b/src/angle.h
@@ -58,6 +58,10 @@ class Angle : protected Pointers {
   int vflag_either,vflag_global,vflag_atom;
   int maxeatom,maxvatom;
 
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int, int alloc = 1);
   void ev_tally(int, int, int, int, int, double, double *, double *,
                 double, double, double, double, double, double);
diff --git a/src/angle_hybrid.cpp b/src/angle_hybrid.cpp
index c29eaac2ae..6afa7413b2 100644
--- a/src/angle_hybrid.cpp
+++ b/src/angle_hybrid.cpp
@@ -103,8 +103,7 @@ void AngleHybrid::compute(int eflag, int vflag)
   // set neighbor->anglelist to sub-style anglelist before call
   // accumulate sub-style global/peratom energy/virial in hybrid
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   for (m = 0; m < nstyles; m++) {
     neighbor->nanglelist = nanglelist[m];
diff --git a/src/angle_zero.cpp b/src/angle_zero.cpp
index d7b7c9cdb5..6eb127fa58 100644
--- a/src/angle_zero.cpp
+++ b/src/angle_zero.cpp
@@ -47,8 +47,7 @@ AngleZero::~AngleZero()
 
 void AngleZero::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/balance.cpp b/src/balance.cpp
index 2a953caf47..61ac895467 100644
--- a/src/balance.cpp
+++ b/src/balance.cpp
@@ -1255,14 +1255,14 @@ void Balance::dumpout(bigint tstep)
       int m = 0;
       for (int i = 0; i < nprocs; i++) {
         domain->lamda_box_corners(&boxall[i][0],&boxall[i][3]);
-        fprintf(fp,"%d %d %g %g %g\n",m+1,1,bc[0][0],bc[0][1],bc[0][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+2,1,bc[1][0],bc[1][1],bc[1][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+3,1,bc[2][0],bc[2][1],bc[2][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+4,1,bc[3][0],bc[3][1],bc[3][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+5,1,bc[4][0],bc[4][1],bc[4][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+6,1,bc[5][0],bc[5][1],bc[5][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+7,1,bc[6][0],bc[6][1],bc[6][1]);
-        fprintf(fp,"%d %d %g %g %g\n",m+8,1,bc[7][0],bc[7][1],bc[7][1]);
+        fprintf(fp,"%d %d %g %g %g\n",m+1,1,bc[0][0],bc[0][1],bc[0][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+2,1,bc[1][0],bc[1][1],bc[1][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+3,1,bc[2][0],bc[2][1],bc[2][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+4,1,bc[3][0],bc[3][1],bc[3][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+5,1,bc[4][0],bc[4][1],bc[4][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+6,1,bc[5][0],bc[5][1],bc[5][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+7,1,bc[6][0],bc[6][1],bc[6][2]);
+        fprintf(fp,"%d %d %g %g %g\n",m+8,1,bc[7][0],bc[7][1],bc[7][2]);
         m += 8;
       }
     }
diff --git a/src/bond.h b/src/bond.h
index 9c353a1a6d..8fb7040832 100644
--- a/src/bond.h
+++ b/src/bond.h
@@ -64,6 +64,10 @@ class Bond : protected Pointers {
   int vflag_either,vflag_global,vflag_atom;
   int maxeatom,maxvatom;
 
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int, int alloc = 1);
   void ev_tally(int, int, int, int, double, double, double, double, double);
 };
diff --git a/src/bond_hybrid.cpp b/src/bond_hybrid.cpp
index 4e5a26f731..65609b4b6e 100644
--- a/src/bond_hybrid.cpp
+++ b/src/bond_hybrid.cpp
@@ -103,8 +103,7 @@ void BondHybrid::compute(int eflag, int vflag)
   // set neighbor->bondlist to sub-style bondlist before call
   // accumulate sub-style global/peratom energy/virial in hybrid
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   for (m = 0; m < nstyles; m++) {
     neighbor->nbondlist = nbondlist[m];
diff --git a/src/bond_zero.cpp b/src/bond_zero.cpp
index 9fcf300b21..0847cf9e6b 100644
--- a/src/bond_zero.cpp
+++ b/src/bond_zero.cpp
@@ -45,8 +45,7 @@ BondZero::~BondZero()
 
 void BondZero::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/comm.cpp b/src/comm.cpp
index f355a562fc..30fd7c243e 100644
--- a/src/comm.cpp
+++ b/src/comm.cpp
@@ -28,6 +28,7 @@
 #include "dump.h"
 #include "group.h"
 #include "procmap.h"
+#include "irregular.h"
 #include "accelerator_kokkos.h"
 #include "memory.h"
 #include "error.h"
@@ -725,6 +726,429 @@ void Comm::ring(int n, int nper, void *inbuf, int messtag,
   memory->destroy(bufcopy);
 }
 
+/* ----------------------------------------------------------------------
+   rendezvous communication operation
+   three stages:
+     first comm sends inbuf from caller decomp to rvous decomp
+     callback operates on data in rendevous decomp
+     second comm sends outbuf from rvous decomp back to caller decomp
+   inputs:
+     which = perform (0) irregular or (1) MPI_All2allv communication
+     n = # of datums in inbuf
+     inbuf = vector of input datums
+     insize = byte size of each input datum
+     inorder = 0 for inbuf in random proc order, 1 for datums ordered by proc
+     procs: inorder 0 = proc to send each datum to, 1 = # of datums/proc,
+     callback = caller function to invoke in rendezvous decomposition
+                takes input datums, returns output datums
+     outorder = same as inorder, but for datums returned by callback()
+     ptr = pointer to caller class, passed to callback()
+   outputs:
+     nout = # of output datums (function return)
+     outbuf = vector of output datums
+     outsize = byte size of each output datum
+   callback inputs:
+     nrvous = # of rvous decomp datums in inbuf_rvous
+     inbuf_rvous = vector of rvous decomp input datums
+     ptr = pointer to caller class
+   callback outputs:
+     nrvous_out = # of rvous decomp output datums (function return)
+     flag = 0 for no second comm, 1 for outbuf_rvous = inbuf_rvous,
+            2 for second comm with new outbuf_rvous
+     procs_rvous = outorder 0 = proc to send each datum to, 1 = # of datums/proc
+                   allocated
+     outbuf_rvous = vector of rvous decomp output datums
+   NOTE: could use MPI_INT or MPI_DOUBLE insead of MPI_CHAR
+         to avoid checked-for overflow in MPI_Alltoallv?
+------------------------------------------------------------------------- */
+
+int Comm::
+rendezvous(int which, int n, char *inbuf, int insize,
+           int inorder, int *procs,
+           int (*callback)(int, char *, int &, int *&, char *&, void *),
+           int outorder, char *&outbuf, int outsize, void *ptr, int statflag)
+{
+  if (which == 0)
+    return rendezvous_irregular(n,inbuf,insize,inorder,procs,callback,
+                                outorder,outbuf,outsize,ptr,statflag);
+  else
+    return rendezvous_all2all(n,inbuf,insize,inorder,procs,callback,
+                              outorder,outbuf,outsize,ptr,statflag);
+}
+
+/* ---------------------------------------------------------------------- */
+
+int Comm::
+rendezvous_irregular(int n, char *inbuf, int insize, int inorder, int *procs,
+                     int (*callback)(int, char *, int &, int *&, char *&, void *),
+                     int outorder, char *&outbuf,
+                     int outsize, void *ptr, int statflag)
+{
+  // irregular comm of inbuf from caller decomp to rendezvous decomp
+
+  Irregular *irregular = new Irregular(lmp);
+
+  int nrvous;
+  if (inorder) nrvous = irregular->create_data_grouped(n,procs);
+  else nrvous = irregular->create_data(n,procs);
+
+  char *inbuf_rvous = (char *) memory->smalloc((bigint) nrvous*insize,
+                                               "rendezvous:inbuf");
+  irregular->exchange_data(inbuf,insize,inbuf_rvous);
+
+  bigint irregular1_bytes = irregular->memory_usage();
+  irregular->destroy_data();
+  delete irregular;
+
+  // peform rendezvous computation via callback()
+  // callback() allocates/populates proclist_rvous and outbuf_rvous
+
+  int flag;
+  int *procs_rvous;
+  char *outbuf_rvous;
+  int nrvous_out = callback(nrvous,inbuf_rvous,flag,
+                            procs_rvous,outbuf_rvous,ptr);
+
+  if (flag != 1) memory->sfree(inbuf_rvous);  // outbuf_rvous = inbuf_vous
+  if (flag == 0) {
+    if (statflag) rendezvous_stats(n,0,nrvous,nrvous_out,insize,outsize,
+                                   (bigint) nrvous_out*sizeof(int) +
+                                   irregular1_bytes);
+    return 0;    // all nout_rvous are 0, no 2nd comm stage
+  }
+
+  // irregular comm of outbuf from rendezvous decomp back to caller decomp
+  // caller will free outbuf
+
+  irregular = new Irregular(lmp);
+
+  int nout;
+  if (outorder)
+    nout = irregular->create_data_grouped(nrvous_out,procs_rvous);
+  else nout = irregular->create_data(nrvous_out,procs_rvous);
+
+  outbuf = (char *) memory->smalloc((bigint) nout*outsize,
+                                    "rendezvous:outbuf");
+  irregular->exchange_data(outbuf_rvous,outsize,outbuf);
+
+  bigint irregular2_bytes = irregular->memory_usage();
+  irregular->destroy_data();
+  delete irregular;
+
+  memory->destroy(procs_rvous);
+  memory->sfree(outbuf_rvous);
+
+  // return number of output datums
+  // last arg to stats() = memory for procs_rvous + irregular comm
+
+  if (statflag) rendezvous_stats(n,nout,nrvous,nrvous_out,insize,outsize,
+                                 (bigint) nrvous_out*sizeof(int) +
+                                 MAX(irregular1_bytes,irregular2_bytes));
+  return nout;
+}
+
+/* ---------------------------------------------------------------------- */
+
+int Comm::
+rendezvous_all2all(int n, char *inbuf, int insize, int inorder, int *procs,
+                   int (*callback)(int, char *, int &, int *&, char *&, void *),
+                   int outorder, char *&outbuf, int outsize, void *ptr,
+                   int statflag)
+{
+  int iproc;
+  bigint all2all1_bytes,all2all2_bytes;
+  int *sendcount,*sdispls,*recvcount,*rdispls;
+  int *procs_a2a;
+  bigint *offsets;
+  char *inbuf_a2a,*outbuf_a2a;
+
+  // create procs and inbuf for All2all if necesary
+
+  if (!inorder) {
+    memory->create(procs_a2a,nprocs,"rendezvous:procs");
+    inbuf_a2a = (char *) memory->smalloc((bigint) n*insize,
+                                         "rendezvous:inbuf");
+    memory->create(offsets,nprocs,"rendezvous:offsets");
+
+    for (int i = 0; i < nprocs; i++) procs_a2a[i] = 0;
+    for (int i = 0; i < n; i++) procs_a2a[procs[i]]++;
+
+    offsets[0] = 0;
+    for (int i = 1; i < nprocs; i++)
+      offsets[i] = offsets[i-1] + insize*procs_a2a[i-1];
+
+    bigint offset = 0;
+    for (int i = 0; i < n; i++) {
+      iproc = procs[i];
+      memcpy(&inbuf_a2a[offsets[iproc]],&inbuf[offset],insize);
+      offsets[iproc] += insize;
+      offset += insize;
+    }
+
+    all2all1_bytes = nprocs*sizeof(int) + nprocs*sizeof(bigint) + n*insize;
+
+  } else {
+    procs_a2a = procs;
+    inbuf_a2a = inbuf;
+    all2all1_bytes = 0;
+  }
+
+  // create args for MPI_Alltoallv() on input data
+
+  memory->create(sendcount,nprocs,"rendezvous:sendcount");
+  memcpy(sendcount,procs_a2a,nprocs*sizeof(int));
+
+  memory->create(recvcount,nprocs,"rendezvous:recvcount");
+  MPI_Alltoall(sendcount,1,MPI_INT,recvcount,1,MPI_INT,world);
+
+  memory->create(sdispls,nprocs,"rendezvous:sdispls");
+  memory->create(rdispls,nprocs,"rendezvous:rdispls");
+  sdispls[0] = rdispls[0] = 0;
+  for (int i = 1; i < nprocs; i++) {
+    sdispls[i] = sdispls[i-1] + sendcount[i-1];
+    rdispls[i] = rdispls[i-1] + recvcount[i-1];
+  }
+  int nrvous = rdispls[nprocs-1] + recvcount[nprocs-1];
+
+  // test for overflow of input data due to imbalance or insize
+  // means that individual sdispls or rdispls values overflow
+
+  int overflow = 0;
+  if ((bigint) n*insize > MAXSMALLINT) overflow = 1;
+  if ((bigint) nrvous*insize > MAXSMALLINT) overflow = 1;
+  int overflowall;
+  MPI_Allreduce(&overflow,&overflowall,1,MPI_INT,MPI_MAX,world);
+  if (overflowall) error->all(FLERR,"Overflow input size in rendezvous_a2a");
+
+  for (int i = 0; i < nprocs; i++) {
+    sendcount[i] *= insize;
+    sdispls[i] *= insize;
+    recvcount[i] *= insize;
+    rdispls[i] *= insize;
+  }
+
+  // all2all comm of inbuf from caller decomp to rendezvous decomp
+
+  char *inbuf_rvous = (char *) memory->smalloc((bigint) nrvous*insize,
+                                               "rendezvous:inbuf");
+
+  MPI_Alltoallv(inbuf_a2a,sendcount,sdispls,MPI_CHAR,
+                inbuf_rvous,recvcount,rdispls,MPI_CHAR,world);
+
+  if (!inorder) {
+    memory->destroy(procs_a2a);
+    memory->sfree(inbuf_a2a);
+    memory->destroy(offsets);
+  }
+
+  // peform rendezvous computation via callback()
+  // callback() allocates/populates proclist_rvous and outbuf_rvous
+
+  int flag;
+  int *procs_rvous;
+  char *outbuf_rvous;
+
+  int nrvous_out = callback(nrvous,inbuf_rvous,flag,
+                            procs_rvous,outbuf_rvous,ptr);
+
+  if (flag != 1) memory->sfree(inbuf_rvous);  // outbuf_rvous = inbuf_vous
+  if (flag == 0) {
+    memory->destroy(sendcount);
+    memory->destroy(recvcount);
+    memory->destroy(sdispls);
+    memory->destroy(rdispls);
+    if (statflag) rendezvous_stats(n,0,nrvous,nrvous_out,insize,outsize,
+                                   (bigint) nrvous_out*sizeof(int) +
+                                   4*nprocs*sizeof(int) + all2all1_bytes);
+    return 0;    // all nout_rvous are 0, no 2nd irregular
+  }
+
+
+
+
+
+
+  // create procs and outbuf for All2all if necesary
+
+  if (!outorder) {
+    memory->create(procs_a2a,nprocs,"rendezvous_a2a:procs");
+
+    outbuf_a2a = (char *) memory->smalloc((bigint) nrvous_out*outsize,
+                                          "rendezvous:outbuf");
+    memory->create(offsets,nprocs,"rendezvous:offsets");
+
+    for (int i = 0; i < nprocs; i++) procs_a2a[i] = 0;
+    for (int i = 0; i < nrvous_out; i++) procs_a2a[procs_rvous[i]]++;
+
+    offsets[0] = 0;
+    for (int i = 1; i < nprocs; i++)
+      offsets[i] = offsets[i-1] + outsize*procs_a2a[i-1];
+
+    bigint offset = 0;
+    for (int i = 0; i < nrvous_out; i++) {
+      iproc = procs_rvous[i];
+      memcpy(&outbuf_a2a[offsets[iproc]],&outbuf_rvous[offset],outsize);
+      offsets[iproc] += outsize;
+      offset += outsize;
+    }
+
+    all2all2_bytes = nprocs*sizeof(int) + nprocs*sizeof(bigint) +
+      nrvous_out*outsize;
+
+  } else {
+    procs_a2a = procs_rvous;
+    outbuf_a2a = outbuf_rvous;
+    all2all2_bytes = 0;
+  }
+
+  // comm outbuf from rendezvous decomposition back to caller
+
+  memcpy(sendcount,procs_a2a,nprocs*sizeof(int));
+
+  MPI_Alltoall(sendcount,1,MPI_INT,recvcount,1,MPI_INT,world);
+
+  sdispls[0] = rdispls[0] = 0;
+  for (int i = 1; i < nprocs; i++) {
+    sdispls[i] = sdispls[i-1] + sendcount[i-1];
+    rdispls[i] = rdispls[i-1] + recvcount[i-1];
+  }
+  int nout = rdispls[nprocs-1] + recvcount[nprocs-1];
+
+  // test for overflow of outbuf due to imbalance or outsize
+  // means that individual sdispls or rdispls values overflow
+
+  overflow = 0;
+  if ((bigint) nrvous*outsize > MAXSMALLINT) overflow = 1;
+  if ((bigint) nout*outsize > MAXSMALLINT) overflow = 1;
+  MPI_Allreduce(&overflow,&overflowall,1,MPI_INT,MPI_MAX,world);
+  if (overflowall) error->all(FLERR,"Overflow output in rendezvous_a2a");
+
+  for (int i = 0; i < nprocs; i++) {
+    sendcount[i] *= outsize;
+    sdispls[i] *= outsize;
+    recvcount[i] *= outsize;
+    rdispls[i] *= outsize;
+  }
+
+  // all2all comm of outbuf from rendezvous decomp back to caller decomp
+  // caller will free outbuf
+
+  outbuf = (char *) memory->smalloc((bigint) nout*outsize,"rendezvous:outbuf");
+
+  MPI_Alltoallv(outbuf_a2a,sendcount,sdispls,MPI_CHAR,
+                outbuf,recvcount,rdispls,MPI_CHAR,world);
+
+  memory->destroy(procs_rvous);
+  memory->sfree(outbuf_rvous);
+
+  if (!outorder) {
+    memory->destroy(procs_a2a);
+    memory->sfree(outbuf_a2a);
+    memory->destroy(offsets);
+  }
+
+  // clean up
+
+  memory->destroy(sendcount);
+  memory->destroy(recvcount);
+  memory->destroy(sdispls);
+  memory->destroy(rdispls);
+
+  // return number of output datums
+  // last arg to stats() = mem for procs_rvous + per-proc vecs + reordering ops
+
+  if (statflag) rendezvous_stats(n,nout,nrvous,nrvous_out,insize,outsize,
+                                 (bigint) nrvous_out*sizeof(int) +
+                                 4*nprocs*sizeof(int) +
+                                 MAX(all2all1_bytes,all2all2_bytes));
+  return nout;
+}
+
+/* ----------------------------------------------------------------------
+   print balance and memory info for rendezvous operation
+   useful for debugging
+------------------------------------------------------------------------- */
+
+void Comm::rendezvous_stats(int n, int nout, int nrvous, int nrvous_out,
+                            int insize, int outsize, bigint commsize)
+{
+  bigint size_in_all,size_in_max,size_in_min;
+  bigint size_out_all,size_out_max,size_out_min;
+  bigint size_inrvous_all,size_inrvous_max,size_inrvous_min;
+  bigint size_outrvous_all,size_outrvous_max,size_outrvous_min;
+  bigint size_comm_all,size_comm_max,size_comm_min;
+
+  bigint size = (bigint) n*insize;
+  MPI_Allreduce(&size,&size_in_all,1,MPI_LMP_BIGINT,MPI_SUM,world);
+  MPI_Allreduce(&size,&size_in_max,1,MPI_LMP_BIGINT,MPI_MAX,world);
+  MPI_Allreduce(&size,&size_in_min,1,MPI_LMP_BIGINT,MPI_MIN,world);
+
+  size = (bigint) nout*outsize;
+  MPI_Allreduce(&size,&size_out_all,1,MPI_LMP_BIGINT,MPI_SUM,world);
+  MPI_Allreduce(&size,&size_out_max,1,MPI_LMP_BIGINT,MPI_MAX,world);
+  MPI_Allreduce(&size,&size_out_min,1,MPI_LMP_BIGINT,MPI_MIN,world);
+
+  size = (bigint) nrvous*insize;
+  MPI_Allreduce(&size,&size_inrvous_all,1,MPI_LMP_BIGINT,MPI_SUM,world);
+  MPI_Allreduce(&size,&size_inrvous_max,1,MPI_LMP_BIGINT,MPI_MAX,world);
+  MPI_Allreduce(&size,&size_inrvous_min,1,MPI_LMP_BIGINT,MPI_MIN,world);
+
+  size = (bigint) nrvous_out*insize;
+  MPI_Allreduce(&size,&size_outrvous_all,1,MPI_LMP_BIGINT,MPI_SUM,world);
+  MPI_Allreduce(&size,&size_outrvous_max,1,MPI_LMP_BIGINT,MPI_MAX,world);
+  MPI_Allreduce(&size,&size_outrvous_min,1,MPI_LMP_BIGINT,MPI_MIN,world);
+
+  size = commsize;
+  MPI_Allreduce(&size,&size_comm_all,1,MPI_LMP_BIGINT,MPI_SUM,world);
+  MPI_Allreduce(&size,&size_comm_max,1,MPI_LMP_BIGINT,MPI_MAX,world);
+  MPI_Allreduce(&size,&size_comm_min,1,MPI_LMP_BIGINT,MPI_MIN,world);
+
+  int mbytes = 1024*1024;
+
+  if (me == 0) {
+    if (screen) {
+      fprintf(screen,"Rendezvous balance and memory info: (tot,ave,max,min) \n");
+      fprintf(screen,"  input datum count: "
+              BIGINT_FORMAT " %g " BIGINT_FORMAT " " BIGINT_FORMAT "\n",
+              size_in_all/insize,1.0*size_in_all/nprocs/insize,
+              size_in_max/insize,size_in_min/insize);
+      fprintf(screen,"  input data (MB): %g %g %g %g\n",
+              1.0*size_in_all/mbytes,1.0*size_in_all/nprocs/mbytes,
+              1.0*size_in_max/mbytes,1.0*size_in_min/mbytes);
+      if (outsize)
+        fprintf(screen,"  output datum count: "
+                BIGINT_FORMAT " %g " BIGINT_FORMAT " " BIGINT_FORMAT "\n",
+                size_out_all/outsize,1.0*size_out_all/nprocs/outsize,
+                size_out_max/outsize,size_out_min/outsize);
+      else
+        fprintf(screen,"  output datum count: %d %g %d %d\n",0,0.0,0,0);
+      fprintf(screen,"  output data (MB): %g %g %g %g\n",
+              1.0*size_out_all/mbytes,1.0*size_out_all/nprocs/mbytes,
+              1.0*size_out_max/mbytes,1.0*size_out_min/mbytes);
+      fprintf(screen,"  input rvous datum count: "
+              BIGINT_FORMAT " %g " BIGINT_FORMAT " " BIGINT_FORMAT "\n",
+              size_inrvous_all/insize,1.0*size_inrvous_all/nprocs/insize,
+              size_inrvous_max/insize,size_inrvous_min/insize);
+      fprintf(screen,"  input rvous data (MB): %g %g %g %g\n",
+              1.0*size_inrvous_all/mbytes,1.0*size_inrvous_all/nprocs/mbytes,
+              1.0*size_inrvous_max/mbytes,1.0*size_inrvous_min/mbytes);
+      if (outsize)
+        fprintf(screen,"  output rvous datum count: "
+                BIGINT_FORMAT " %g " BIGINT_FORMAT " " BIGINT_FORMAT "\n",
+                size_outrvous_all/outsize,1.0*size_outrvous_all/nprocs/outsize,
+                size_outrvous_max/outsize,size_outrvous_min/outsize);
+      else
+        fprintf(screen,"  output rvous datum count: %d %g %d %d\n",0,0.0,0,0);
+      fprintf(screen,"  output rvous data (MB): %g %g %g %g\n",
+              1.0*size_outrvous_all/mbytes,1.0*size_outrvous_all/nprocs/mbytes,
+              1.0*size_outrvous_max/mbytes,1.0*size_outrvous_min/mbytes);
+      fprintf(screen,"  rvous comm (MB): %g %g %g %g\n",
+              1.0*size_comm_all/mbytes,1.0*size_comm_all/nprocs/mbytes,
+              1.0*size_comm_max/mbytes,1.0*size_comm_min/mbytes);
+    }
+  }
+}
+
 /* ----------------------------------------------------------------------
    proc 0 reads Nlines from file into buf and bcasts buf to all procs
    caller allocates buf to max size needed
diff --git a/src/comm.h b/src/comm.h
index 2579f9b283..30360b1059 100644
--- a/src/comm.h
+++ b/src/comm.h
@@ -109,6 +109,10 @@ class Comm : protected Pointers {
 
   void ring(int, int, void *, int, void (*)(int, char *, void *),
             void *, void *, int self = 1);
+  int rendezvous(int, int, char *, int, int, int *,
+                 int (*)(int, char *, int &, int *&, char *&, void *),
+                 int, char *&, int, void *, int statflag=0);
+
   int read_lines_from_file(FILE *, int, int, char *);
   int read_lines_from_file_universe(FILE *, int, int, char *);
 
@@ -142,6 +146,15 @@ class Comm : protected Pointers {
   int ncores;                       // # of cores per node
   int coregrid[3];                  // 3d grid of cores within a node
   int user_coregrid[3];             // user request for cores in each dim
+
+  int rendezvous_irregular(int, char *, int, int, int *,
+                           int (*)(int, char *, int &, int *&, char *&, void *),
+                           int, char *&, int, void *, int);
+  int rendezvous_all2all(int, char *, int, int, int *,
+                         int (*)(int, char *, int &, int *&, char *&, void *),
+                         int, char *&, int, void *, int);
+  void rendezvous_stats(int, int, int, int, int, int, bigint);
+
  public:
   enum{MULTIPLE};
 };
diff --git a/src/comm_brick.cpp b/src/comm_brick.cpp
index bf7f3e2f8f..330551aaed 100644
--- a/src/comm_brick.cpp
+++ b/src/comm_brick.cpp
@@ -1069,6 +1069,7 @@ void CommBrick::reverse_comm_fix_variable(Fix *fix)
       MPI_Sendrecv(&nsend,1,MPI_INT,recvproc[iswap],0,
                    &nrecv,1,MPI_INT,sendproc[iswap],0,world,
                    MPI_STATUS_IGNORE);
+
       if (sendnum[iswap]) {
         if (nrecv > maxrecv) grow_recv(nrecv);
         MPI_Irecv(buf_recv,maxrecv,MPI_DOUBLE,sendproc[iswap],0,
diff --git a/src/comm_tiled.cpp b/src/comm_tiled.cpp
index d7d2e4725d..d1d625445a 100644
--- a/src/comm_tiled.cpp
+++ b/src/comm_tiled.cpp
@@ -512,7 +512,7 @@ void CommTiled::forward_comm(int /*dummy*/)
                     MPI_DOUBLE,recvproc[iswap][i],0,world,&requests[i]);
       }
       if (sendother[iswap]) {
-        for (i = 0; i < nsendproc[iswap]; i++) {
+        for (i = 0; i < nsend; i++) {
           n = avec->pack_comm(sendnum[iswap][i],sendlist[iswap][i],
                               buf_send,pbc_flag[iswap][i],pbc[iswap][i]);
           MPI_Send(buf_send,n,MPI_DOUBLE,sendproc[iswap][i],0,world);
diff --git a/src/compute_angle_local.cpp b/src/compute_angle_local.cpp
index 641784fe03..1196211665 100644
--- a/src/compute_angle_local.cpp
+++ b/src/compute_angle_local.cpp
@@ -88,7 +88,7 @@ ComputeAngleLocal::ComputeAngleLocal(LAMMPS *lmp, int narg, char **arg) :
         int n = strlen(arg[iarg+2]) + 1;
         tstr = new char[n];
         strcpy(tstr,arg[iarg+2]);
-	tflag = 1;
+        tflag = 1;
       } else error->all(FLERR,"Illegal compute angle/local command");
       iarg += 3;
     } else error->all(FLERR,"Illegal compute angle/local command");
@@ -102,9 +102,9 @@ ComputeAngleLocal::ComputeAngleLocal(LAMMPS *lmp, int narg, char **arg) :
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,"Variable name for copute angle/local does not exist");
+        error->all(FLERR,"Variable name for copute angle/local does not exist");
       if (!input->variable->equalstyle(vvar[i]))
-	error->all(FLERR,"Variable for compute angle/local is invalid style");
+        error->all(FLERR,"Variable for compute angle/local is invalid style");
     }
 
     if (tstr) {
@@ -153,7 +153,7 @@ void ComputeAngleLocal::init()
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,"Variable name for compute angle/local does not exist");
+        error->all(FLERR,"Variable name for compute angle/local does not exist");
     }
 
     if (tstr) {
@@ -261,53 +261,53 @@ int ComputeAngleLocal::compute_angles(int flag)
       // theta needed by one or more outputs
 
       if (tflag) {
-	delx1 = x[atom1][0] - x[atom2][0];
-	dely1 = x[atom1][1] - x[atom2][1];
-	delz1 = x[atom1][2] - x[atom2][2];
-	domain->minimum_image(delx1,dely1,delz1);
+        delx1 = x[atom1][0] - x[atom2][0];
+        dely1 = x[atom1][1] - x[atom2][1];
+        delz1 = x[atom1][2] - x[atom2][2];
+        domain->minimum_image(delx1,dely1,delz1);
 
-	rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
-	r1 = sqrt(rsq1);
-	
-	delx2 = x[atom3][0] - x[atom2][0];
-	dely2 = x[atom3][1] - x[atom2][1];
-	delz2 = x[atom3][2] - x[atom2][2];
-	domain->minimum_image(delx2,dely2,delz2);
+        rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
+        r1 = sqrt(rsq1);
 
-	rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
-	r2 = sqrt(rsq2);
+        delx2 = x[atom3][0] - x[atom2][0];
+        dely2 = x[atom3][1] - x[atom2][1];
+        delz2 = x[atom3][2] - x[atom2][2];
+        domain->minimum_image(delx2,dely2,delz2);
 
-	// c = cosine of angle
-	// theta = angle in radians
+        rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
+        r2 = sqrt(rsq2);
 
-	c = delx1*delx2 + dely1*dely2 + delz1*delz2;
-	c /= r1*r2;
-	if (c > 1.0) c = 1.0;
-	if (c < -1.0) c = -1.0;
-	theta = acos(c);
+        // c = cosine of angle
+        // theta = angle in radians
+
+        c = delx1*delx2 + dely1*dely2 + delz1*delz2;
+        c /= r1*r2;
+        if (c > 1.0) c = 1.0;
+        if (c < -1.0) c = -1.0;
+        theta = acos(c);
       }
 
       if (nvalues == 1) ptr = &vlocal[m];
       else ptr = alocal[m];
 
       if (nvar) {
-	ivar = 0;
-	if (tstr) input->variable->internal_set(tvar,theta);
+        ivar = 0;
+        if (tstr) input->variable->internal_set(tvar,theta);
       }
 
       for (n = 0; n < nvalues; n++) {
-	switch (bstyle[n]) {
-	case THETA:
-	  ptr[n] = 180.0*theta/MY_PI;
-	  break;
-	case ENG:
-	  if (atype > 0) ptr[n] = angle->single(atype,atom1,atom2,atom3);
-	  else ptr[n] = 0.0;
-	  break;
-	case VARIABLE:
-	  ptr[n] = input->variable->compute_equal(vvar[ivar]);
-	  ivar++;
-	  break;
+        switch (bstyle[n]) {
+        case THETA:
+          ptr[n] = 180.0*theta/MY_PI;
+          break;
+        case ENG:
+          if (atype > 0) ptr[n] = angle->single(atype,atom1,atom2,atom3);
+          else ptr[n] = 0.0;
+          break;
+        case VARIABLE:
+          ptr[n] = input->variable->compute_equal(vvar[ivar]);
+          ivar++;
+          break;
         }
       }
 
diff --git a/src/compute_bond_local.cpp b/src/compute_bond_local.cpp
index adbbde1a0c..ccdd3ee77c 100644
--- a/src/compute_bond_local.cpp
+++ b/src/compute_bond_local.cpp
@@ -105,9 +105,9 @@ ComputeBondLocal::ComputeBondLocal(LAMMPS *lmp, int narg, char **arg) :
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,"Variable name for copute bond/local does not exist");
+        error->all(FLERR,"Variable name for copute bond/local does not exist");
       if (!input->variable->equalstyle(vvar[i]))
-	error->all(FLERR,"Variable for compute bond/local is invalid style");
+        error->all(FLERR,"Variable for compute bond/local is invalid style");
     }
 
     if (dstr) {
@@ -168,7 +168,7 @@ void ComputeBondLocal::init()
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,"Variable name for compute bond/local does not exist");
+        error->all(FLERR,"Variable name for compute bond/local does not exist");
     }
 
     if (dstr) {
@@ -377,10 +377,10 @@ int ComputeBondLocal::compute_bonds(int flag)
         if (nvalues == 1) ptr = &vlocal[m];
         else ptr = alocal[m];
 
-	if (nvar) {
-	  ivar = 0;
-	  if (dstr) input->variable->internal_set(dvar,sqrt(rsq));
-	}
+        if (nvar) {
+          ivar = 0;
+          if (dstr) input->variable->internal_set(dvar,sqrt(rsq));
+        }
 
         for (n = 0; n < nvalues; n++) {
           switch (bstyle[n]) {
@@ -408,10 +408,10 @@ int ComputeBondLocal::compute_bonds(int flag)
           case VELVIB:
             ptr[n] = vvib;
             break;
-	  case VARIABLE:
-	    ptr[n] = input->variable->compute_equal(vvar[ivar]);
-	    ivar++;
-	    break;
+          case VARIABLE:
+            ptr[n] = input->variable->compute_equal(vvar[ivar]);
+            ivar++;
+            break;
           }
         }
       }
diff --git a/src/compute_chunk_spread_atom.cpp b/src/compute_chunk_spread_atom.cpp
index 36fad5cca1..3d0cea1add 100644
--- a/src/compute_chunk_spread_atom.cpp
+++ b/src/compute_chunk_spread_atom.cpp
@@ -71,7 +71,7 @@ ComputeChunkSpreadAtom(LAMMPS *lmp, int narg, char **arg) :
     ids[nvalues] = NULL;
 
     if (strncmp(arg[iarg],"c_",2) == 0 ||
-	strncmp(arg[iarg],"f_",2) == 0) {
+        strncmp(arg[iarg],"f_",2) == 0) {
       if (arg[iarg][0] == 'c') which[nvalues] = COMPUTE;
       else if (arg[iarg][0] == 'f') which[nvalues] = FIX;
 
@@ -123,15 +123,15 @@ ComputeChunkSpreadAtom(LAMMPS *lmp, int narg, char **arg) :
                    "does not calculate per-chunk values");
 
       if (argindex[i] == 0) {
-	if (!modify->compute[icompute]->vector_flag)
-	  error->all(FLERR,"Compute chunk/spread/atom compute "
+        if (!modify->compute[icompute]->vector_flag)
+          error->all(FLERR,"Compute chunk/spread/atom compute "
                      "does not calculate global vector");
       } else {
-	if (!modify->compute[icompute]->array_flag)
-	  error->all(FLERR,"Compute chunk/spread/atom compute "
+        if (!modify->compute[icompute]->array_flag)
+          error->all(FLERR,"Compute chunk/spread/atom compute "
                      "does not calculate global array");
-	if (argindex[i] > modify->compute[icompute]->size_array_cols)
-	  error->all(FLERR,"Compute chunk/spread/atom compute array "
+        if (argindex[i] > modify->compute[icompute]->size_array_cols)
+          error->all(FLERR,"Compute chunk/spread/atom compute array "
                      "is accessed out-of-range");
       }
 
@@ -140,15 +140,15 @@ ComputeChunkSpreadAtom(LAMMPS *lmp, int narg, char **arg) :
       if (ifix < 0)
         error->all(FLERR,"Fix ID for compute chunk/spread/atom does not exist");
       if (argindex[i] == 0) {
-	if (!modify->fix[ifix]->vector_flag)
-	  error->all(FLERR,"Compute chunk/spread/atom fix "
+        if (!modify->fix[ifix]->vector_flag)
+          error->all(FLERR,"Compute chunk/spread/atom fix "
                      "does not calculate global vector");
       } else {
-	if (!modify->fix[ifix]->array_flag)
-	  error->all(FLERR,"Compute chunk/spread/atom fix "
+        if (!modify->fix[ifix]->array_flag)
+          error->all(FLERR,"Compute chunk/spread/atom fix "
                      "does not calculate global array");
-	if (argindex[i] > modify->fix[ifix]->size_array_cols)
-	  error->all(FLERR,"Compute chunk/spread/atom fix array "
+        if (argindex[i] > modify->fix[ifix]->size_array_cols)
+          error->all(FLERR,"Compute chunk/spread/atom fix array "
                      "is accessed out-of-range");
       }
     }
@@ -281,14 +281,14 @@ void ComputeChunkSpreadAtom::compute_peratom()
           compute->compute_vector();
           compute->invoked_flag |= INVOKED_VECTOR;
         }
-	double *cvector = compute->vector;
-	for (i = 0; i < nlocal; i++, ptr += nstride) {
-	  *ptr = 0.0;
-	  if (!(mask[i] & groupbit)) continue;
-	  index = ichunk[i]-1;
-	  if (index < 0 || index >= nchunk) continue;
-	  *ptr = cvector[index];
-	}
+        double *cvector = compute->vector;
+        for (i = 0; i < nlocal; i++, ptr += nstride) {
+          *ptr = 0.0;
+          if (!(mask[i] & groupbit)) continue;
+          index = ichunk[i]-1;
+          if (index < 0 || index >= nchunk) continue;
+          *ptr = cvector[index];
+        }
 
       } else {
         if (!(compute->invoked_flag & INVOKED_ARRAY)) {
@@ -297,13 +297,13 @@ void ComputeChunkSpreadAtom::compute_peratom()
         }
         int icol = argindex[m]-1;
         double **carray = compute->array;
-	for (i = 0; i < nlocal; i++, ptr += nstride) {
-	  *ptr = 0.0;
-	  if (!(mask[i] & groupbit)) continue;
-	  index = ichunk[i]-1;
-	  if (index < 0 || index >= nchunk) continue;
-	  *ptr = carray[index][icol];
-	}
+        for (i = 0; i < nlocal; i++, ptr += nstride) {
+          *ptr = 0.0;
+          if (!(mask[i] & groupbit)) continue;
+          index = ichunk[i]-1;
+          if (index < 0 || index >= nchunk) continue;
+          *ptr = carray[index][icol];
+        }
       }
 
     // access fix data, check if fix frequency is a match
diff --git a/src/compute_dihedral_local.cpp b/src/compute_dihedral_local.cpp
index 9e18d03f9f..9efdd61cb8 100644
--- a/src/compute_dihedral_local.cpp
+++ b/src/compute_dihedral_local.cpp
@@ -101,10 +101,10 @@ ComputeDihedralLocal::ComputeDihedralLocal(LAMMPS *lmp, int narg, char **arg) :
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,
+        error->all(FLERR,
                    "Variable name for copute dihedral/local does not exist");
       if (!input->variable->equalstyle(vvar[i]))
-	error->all(FLERR,"Variable for compute dihedral/local is invalid style");
+        error->all(FLERR,"Variable for compute dihedral/local is invalid style");
     }
 
     if (pstr) {
@@ -154,7 +154,7 @@ void ComputeDihedralLocal::init()
     for (int i = 0; i < nvar; i++) {
       vvar[i] = input->variable->find(vstr[i]);
       if (vvar[i] < 0)
-	error->all(FLERR,
+        error->all(FLERR,
                    "Variable name for compute dihedral/local does not exist");
     }
 
@@ -307,19 +307,19 @@ int ComputeDihedralLocal::compute_dihedrals(int flag)
       else ptr = alocal[m];
 
       if (nvar) {
-	ivar = 0;
-	if (pstr) input->variable->internal_set(pvar,phi);
+        ivar = 0;
+        if (pstr) input->variable->internal_set(pvar,phi);
       }
 
       for (n = 0; n < nvalues; n++) {
-	switch (bstyle[n]) {
-	case PHI:
-	  ptr[n] = 180.0*phi/MY_PI;
-	  break;
-	case VARIABLE:
-	  ptr[n] = input->variable->compute_equal(vvar[ivar]);
-	  ivar++;
-	  break;
+        switch (bstyle[n]) {
+        case PHI:
+          ptr[n] = 180.0*phi/MY_PI;
+          break;
+        case VARIABLE:
+          ptr[n] = input->variable->compute_equal(vvar[ivar]);
+          ivar++;
+          break;
         }
       }
 
diff --git a/src/compute_improper_local.cpp b/src/compute_improper_local.cpp
index f54cb67535..2861850c79 100644
--- a/src/compute_improper_local.cpp
+++ b/src/compute_improper_local.cpp
@@ -46,9 +46,6 @@ ComputeImproperLocal::ComputeImproperLocal(LAMMPS *lmp, int narg, char **arg) :
 
   local_flag = 1;
   nvalues = narg - 3;
-  if (nvalues == 1) size_local_cols = 0;
-  else size_local_cols = nvalues;
-
   cflag = -1;
   nvalues = 0;
 
@@ -57,6 +54,9 @@ ComputeImproperLocal::ComputeImproperLocal(LAMMPS *lmp, int narg, char **arg) :
     else error->all(FLERR,"Invalid keyword in compute improper/local command");
   }
 
+  if (nvalues == 1) size_local_cols = 0;
+  else size_local_cols = nvalues;
+
   nmax = 0;
   vlocal = NULL;
   alocal = NULL;
diff --git a/src/compute_pair_local.cpp b/src/compute_pair_local.cpp
index e4cbabfd3d..c356a08be9 100644
--- a/src/compute_pair_local.cpp
+++ b/src/compute_pair_local.cpp
@@ -43,9 +43,6 @@ ComputePairLocal::ComputePairLocal(LAMMPS *lmp, int narg, char **arg) :
 
   local_flag = 1;
   nvalues = narg - 3;
-  if (nvalues == 1) size_local_cols = 0;
-  else size_local_cols = nvalues;
-
   pstyle = new int[nvalues];
   pindex = new int[nvalues];
 
@@ -96,6 +93,9 @@ ComputePairLocal::ComputePairLocal(LAMMPS *lmp, int narg, char **arg) :
   for (int i = 0; i < nvalues; i++)
     if (pstyle[i] != DIST) singleflag = 1;
 
+  if (nvalues == 1) size_local_cols = 0;
+  else size_local_cols = nvalues;
+
   nmax = 0;
   vlocal = NULL;
   alocal = NULL;
diff --git a/src/compute_property_atom.cpp b/src/compute_property_atom.cpp
index 862a66e3f9..0b57840696 100644
--- a/src/compute_property_atom.cpp
+++ b/src/compute_property_atom.cpp
@@ -141,7 +141,7 @@ ComputePropertyAtom::ComputePropertyAtom(LAMMPS *lmp, int narg, char **arg) :
         error->all(FLERR,"Compute property/atom for "
                    "atom property that isn't allocated");
       pack_choice[i] = &ComputePropertyAtom::pack_mu;
-    } else if (strcmp(arg[iarg],"spx") == 0) { 		// pack magnetic variables
+    } else if (strcmp(arg[iarg],"spx") == 0) {          // pack magnetic variables
       if (!atom->sp_flag)
         error->all(FLERR,"Compute property/atom for "
                    "atom property that isn't allocated");
diff --git a/src/compute_property_atom.h b/src/compute_property_atom.h
index 0c1ed7e305..eb002457fb 100644
--- a/src/compute_property_atom.h
+++ b/src/compute_property_atom.h
@@ -84,7 +84,9 @@ class ComputePropertyAtom : public Compute {
   void pack_radius(int);
   void pack_diameter(int);
 
-  void pack_spx(int);		// pack magnetic variables
+  // pack magnetic variables
+
+  void pack_spx(int);
   void pack_spy(int);
   void pack_spz(int);
   void pack_sp(int);
diff --git a/src/create_atoms.cpp b/src/create_atoms.cpp
index cb0da42970..52e4256fca 100644
--- a/src/create_atoms.cpp
+++ b/src/create_atoms.cpp
@@ -514,9 +514,6 @@ void CreateAtoms::command(int narg, char **arg)
     if (domain->triclinic) domain->lamda2x(atom->nlocal);
   }
 
-  MPI_Barrier(world);
-  double time2 = MPI_Wtime();
-
   // clean up
 
   delete ranmol;
@@ -526,21 +523,6 @@ void CreateAtoms::command(int narg, char **arg)
   delete [] ystr;
   delete [] zstr;
 
-  // print status
-
-  if (comm->me == 0) {
-    if (screen) {
-      fprintf(screen,"Created " BIGINT_FORMAT " atoms\n",
-              atom->natoms-natoms_previous);
-      fprintf(screen,"  Time spent = %g secs\n",time2-time1);
-    }
-    if (logfile) {
-      fprintf(logfile,"Created " BIGINT_FORMAT " atoms\n",
-              atom->natoms-natoms_previous);
-      fprintf(logfile,"  Time spent = %g secs\n",time2-time1);
-    }
-  }
-
   // for MOLECULE mode:
   // create special bond lists for molecular systems,
   //   but not for atom style template
@@ -550,6 +532,25 @@ void CreateAtoms::command(int narg, char **arg)
     if (atom->molecular == 1 && onemol->bondflag && !onemol->specialflag) {
       Special special(lmp);
       special.build();
+
+    }
+  }
+
+  // print status
+
+  MPI_Barrier(world);
+  double time2 = MPI_Wtime();
+
+  if (comm->me == 0) {
+    if (screen) {
+      fprintf(screen,"Created " BIGINT_FORMAT " atoms\n",
+              atom->natoms-natoms_previous);
+      fprintf(screen,"  create_atoms CPU = %g secs\n",time2-time1);
+    }
+    if (logfile) {
+      fprintf(logfile,"Created " BIGINT_FORMAT " atoms\n",
+              atom->natoms-natoms_previous);
+      fprintf(logfile,"  create_atoms CPU = %g secs\n",time2-time1);
     }
   }
 }
diff --git a/src/dihedral.h b/src/dihedral.h
index 627104871b..f1b42008bf 100644
--- a/src/dihedral.h
+++ b/src/dihedral.h
@@ -56,6 +56,10 @@ class Dihedral : protected Pointers {
   int vflag_either,vflag_global,vflag_atom;
   int maxeatom,maxvatom;
 
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int, int alloc = 1);
   void ev_tally(int, int, int, int, int, int, double,
                 double *, double *, double *, double, double, double,
diff --git a/src/dihedral_hybrid.cpp b/src/dihedral_hybrid.cpp
index b9107ac874..f3e4823d53 100644
--- a/src/dihedral_hybrid.cpp
+++ b/src/dihedral_hybrid.cpp
@@ -104,8 +104,7 @@ void DihedralHybrid::compute(int eflag, int vflag)
   // set neighbor->dihedrallist to sub-style dihedrallist before call
   // accumulate sub-style global/peratom energy/virial in hybrid
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   for (m = 0; m < nstyles; m++) {
     neighbor->ndihedrallist = ndihedrallist[m];
diff --git a/src/dihedral_zero.cpp b/src/dihedral_zero.cpp
index 46facdb6db..8145d5f32d 100644
--- a/src/dihedral_zero.cpp
+++ b/src/dihedral_zero.cpp
@@ -44,8 +44,7 @@ DihedralZero::~DihedralZero()
 
 void DihedralZero::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/domain.cpp b/src/domain.cpp
index beaf5fc08e..86c4eb2c02 100644
--- a/src/domain.cpp
+++ b/src/domain.cpp
@@ -763,9 +763,9 @@ void Domain::image_check()
         continue;
       }
 
-      delx = unwrap[i][0] - unwrap[k][0];
-      dely = unwrap[i][1] - unwrap[k][1];
-      delz = unwrap[i][2] - unwrap[k][2];
+      delx = fabs(unwrap[i][0] - unwrap[k][0]);
+      dely = fabs(unwrap[i][1] - unwrap[k][1]);
+      delz = fabs(unwrap[i][2] - unwrap[k][2]);
 
       if (xperiodic && delx > xprd_half) flag = 1;
       if (yperiodic && dely > yprd_half) flag = 1;
diff --git a/src/dump.cpp b/src/dump.cpp
index 7cd80dcf71..8fa07a9cb2 100644
--- a/src/dump.cpp
+++ b/src/dump.cpp
@@ -423,7 +423,12 @@ void Dump::write()
     atom->x = xpbc;
     atom->v = vpbc;
     atom->image = imagepbc;
+
+    // for triclinic, PBC is applied in lamda coordinates
+
+    if (domain->triclinic) domain->x2lamda(nlocal);
     domain->pbc();
+    if (domain->triclinic) domain->lamda2x(nlocal);
   }
 
   // pack my data into buf
diff --git a/src/error.cpp b/src/error.cpp
index 913239ac49..7c2d3c5409 100644
--- a/src/error.cpp
+++ b/src/error.cpp
@@ -72,7 +72,9 @@ void Error::universe_all(const char *file, int line, const char *str)
 #ifdef LAMMPS_EXCEPTIONS
 
   // allow commands if an exception was caught in a run
-  update->whichflag = 0;
+  // update may be NULL when catching command line errors
+
+  if (update) update->whichflag = 0;
 
   char msg[100];
   snprintf(msg, 100, "ERROR: %s (%s:%d)\n", str, truncpath(file), line);
@@ -97,7 +99,9 @@ void Error::universe_one(const char *file, int line, const char *str)
 #ifdef LAMMPS_EXCEPTIONS
 
   // allow commands if an exception was caught in a run
-  update->whichflag = 0;
+  // update may be NULL when catching command line errors
+
+  if (update) update->whichflag = 0;
 
   char msg[100];
   snprintf(msg, 100, "ERROR: %s (%s:%d)\n", str, truncpath(file), line);
@@ -148,7 +152,9 @@ void Error::all(const char *file, int line, const char *str)
 #ifdef LAMMPS_EXCEPTIONS
 
   // allow commands if an exception was caught in a run
-  update->whichflag = 0;
+  // update may be NULL when catching command line errors
+
+  if (update) update->whichflag = 0;
 
   char msg[100];
   snprintf(msg, 100, "ERROR: %s (%s:%d)\n", str, truncpath(file), line);
@@ -198,7 +204,9 @@ void Error::one(const char *file, int line, const char *str)
 #ifdef LAMMPS_EXCEPTIONS
 
   // allow commands if an exception was caught in a run
-  update->whichflag = 0;
+  // update may be NULL when catching command line errors
+
+  if (update) update->whichflag = 0;
 
   char msg[100];
   snprintf(msg, 100, "ERROR on proc %d: %s (%s:%d)\n", me, str, truncpath(file), line);
diff --git a/src/fix.h b/src/fix.h
index 21dfc955a8..7eaff38bd3 100644
--- a/src/fix.h
+++ b/src/fix.h
@@ -223,6 +223,10 @@ class Fix : protected Pointers {
 
   int dynamic;    // recount atoms for temperature computes
 
+  void ev_init(int eflag, int vflag) {
+    if (eflag||vflag) ev_setup(eflag, vflag);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int);
   void ev_tally(int, int *, double, double, double *);
   void v_setup(int);
diff --git a/src/fix_ave_histo.cpp b/src/fix_ave_histo.cpp
index a5bf8db557..87da5222f0 100644
--- a/src/fix_ave_histo.cpp
+++ b/src/fix_ave_histo.cpp
@@ -32,7 +32,7 @@ using namespace FixConst;
 enum{X,V,F,COMPUTE,FIX,VARIABLE};
 enum{ONE,RUNNING};
 enum{SCALAR,VECTOR,WINDOW};
-enum{GLOBAL,PERATOM,LOCAL};
+enum{DEFAULT,GLOBAL,PERATOM,LOCAL};
 enum{IGNORE,END,EXTRA};
 
 #define INVOKED_SCALAR 1
@@ -46,8 +46,10 @@ enum{IGNORE,END,EXTRA};
 
 FixAveHisto::FixAveHisto(LAMMPS *lmp, int narg, char **arg) :
   Fix(lmp, narg, arg),
-  nvalues(0), which(NULL), argindex(NULL), value2index(NULL), ids(NULL), fp(NULL), stats_list(NULL),
-  bin(NULL), bin_total(NULL), bin_all(NULL), bin_list(NULL), coord(NULL), vector(NULL)
+  nvalues(0), which(NULL), argindex(NULL), value2index(NULL),
+  ids(NULL), fp(NULL), stats_list(NULL),
+  bin(NULL), bin_total(NULL), bin_all(NULL), bin_list(NULL),
+  coord(NULL), vector(NULL)
 {
   if (narg < 10) error->all(FLERR,"Illegal fix ave/histo command");
 
@@ -188,9 +190,8 @@ FixAveHisto::FixAveHisto(LAMMPS *lmp, int narg, char **arg) :
     memory->sfree(earg);
   }
 
-  // setup and error check
-  // kind = inputs are all global, or all per-atom, or all local
-  // for fix inputs, check that fix frequency is acceptable
+  // check input args for kind consistency
+  // all inputs must all be global, per-atom, or local
 
   if (nevery <= 0 || nrepeat <= 0 || nfreq <= 0)
     error->all(FLERR,"Illegal fix ave/histo command");
@@ -201,40 +202,65 @@ FixAveHisto::FixAveHisto(LAMMPS *lmp, int narg, char **arg) :
   if (ave != RUNNING && overwrite)
     error->all(FLERR,"Illegal fix ave/histo command");
 
-  int kindflag;
+  int kindglobal,kindperatom,kindlocal;
+
   for (int i = 0; i < nvalues; i++) {
-    if (which[i] == X || which[i] == V || which[i] == F) kindflag = PERATOM;
-    else if (which[i] == COMPUTE) {
+    kindglobal = kindperatom = kindlocal = 0;
+
+    if (which[i] == X || which[i] == V || which[i] == F) {
+      kindperatom = 1;
+
+    } else if (which[i] == COMPUTE) {
       int c_id = modify->find_compute(ids[i]);
       if (c_id < 0) error->all(FLERR,"Fix ave/histo input is invalid compute");
       Compute *compute = modify->compute[c_id];
+      // computes can produce multiple kinds of output
       if (compute->scalar_flag || compute->vector_flag || compute->array_flag)
-        kindflag = GLOBAL;
-      else if (compute->peratom_flag) kindflag = PERATOM;
-      else if (compute->local_flag) kindflag = LOCAL;
-      else error->all(FLERR,"Fix ave/histo input is invalid compute");
+        kindglobal = 1;
+      if (compute->peratom_flag) kindperatom = 1;
+      if (compute->local_flag) kindlocal = 1;
+
     } else if (which[i] == FIX) {
       int f_id = modify->find_fix(ids[i]);
       if (f_id < 0) error->all(FLERR,"Fix ave/histo input is invalid fix");
       Fix *fix = modify->fix[f_id];
+      // fixes can produce multiple kinds of output
       if (fix->scalar_flag || fix->vector_flag || fix->array_flag)
-        kindflag = GLOBAL;
-      else if (fix->peratom_flag) kindflag = PERATOM;
-      else if (fix->local_flag) kindflag = LOCAL;
-      else error->all(FLERR,"Fix ave/histo input is invalid fix");
+        kindglobal = 1;
+      if (fix->peratom_flag) kindperatom = 1;
+      if (fix->local_flag) kindlocal = 1;
+
     } else if (which[i] == VARIABLE) {
       int ivariable = input->variable->find(ids[i]);
-      if (ivariable < 0) error->all(FLERR,"Fix ave/histo input is invalid variable");
-      if (input->variable->equalstyle(ivariable)) kindflag = GLOBAL;
-      else if (input->variable->atomstyle(ivariable)) kindflag = PERATOM;
-      else error->all(FLERR,"Fix ave/histo input is invalid variable");
+      if (ivariable < 0)
+        error->all(FLERR,"Fix ave/histo input is invalid variable");
+      // variables only produce one kind of output
+      if (input->variable->equalstyle(ivariable)) kindglobal = 1;
+      else if (input->variable->atomstyle(ivariable)) kindperatom = 1;
+      else error->all(FLERR,"Fix ave/histo input is invalid kind of variable");
+    }
+
+    if (kind == DEFAULT) {
+      if (kindglobal + kindperatom + kindlocal > 1)
+        error->all(FLERR,"Fix ave/histo input kind is ambiguous");
+      if (kindglobal) kind = GLOBAL;
+      if (kindperatom) kind = PERATOM;
+      if (kindlocal) kind = LOCAL;
+    } else if (kind == GLOBAL) {
+      if (!kindglobal)
+        error->all(FLERR,"Fix ave/histo input kind is invalid");
+    } else if (kind == PERATOM) {
+      if (!kindperatom)
+        error->all(FLERR,"Fix ave/histo input kind is invalid");
+    } else if (kind == LOCAL) {
+      if (!kindlocal)
+        error->all(FLERR,"Fix ave/histo input kind is invalid");
     }
-    if (i == 0) kind = kindflag;
-    else if (kindflag != kind)
-      error->all(FLERR,
-                 "Fix ave/histo inputs are not all global, peratom, or local");
   }
 
+  // more error checks
+  // for fix inputs, check that fix frequency is acceptable
+
   if (kind == PERATOM && mode == SCALAR)
     error->all(FLERR,
                "Fix ave/histo cannot input per-atom values in scalar mode");
@@ -919,6 +945,7 @@ void FixAveHisto::options(int iarg, int narg, char **arg)
   // option defaults
 
   fp = NULL;
+  kind = DEFAULT;
   ave = ONE;
   startstep = 0;
   mode = SCALAR;
@@ -942,6 +969,13 @@ void FixAveHisto::options(int iarg, int narg, char **arg)
         }
       }
       iarg += 2;
+    } else if (strcmp(arg[iarg],"kind") == 0) {
+      if (iarg+2 > narg) error->all(FLERR,"Illegal fix ave/histo command");
+      if (strcmp(arg[iarg+1],"global") == 0) kind = GLOBAL;
+      else if (strcmp(arg[iarg+1],"peratom") == 0) kind = PERATOM;
+      else if (strcmp(arg[iarg+1],"local") == 0) kind = LOCAL;
+      else error->all(FLERR,"Illegal fix ave/histo command");
+      iarg += 2;
     } else if (strcmp(arg[iarg],"ave") == 0) {
       if (iarg+2 > narg) error->all(FLERR,"Illegal fix ave/histo command");
       if (strcmp(arg[iarg+1],"one") == 0) ave = ONE;
diff --git a/src/fix_balance.cpp b/src/fix_balance.cpp
index 8995a57afe..ddaf42b49d 100644
--- a/src/fix_balance.cpp
+++ b/src/fix_balance.cpp
@@ -274,10 +274,6 @@ void FixBalance::rebalance()
     comm->layout = Comm::LAYOUT_TILED;
   }
 
-  // output of new decomposition
-
-  if (balance->outflag) balance->dumpout(update->ntimestep);
-
   // reset proc sub-domains
   // check and warn if any proc's subbox is smaller than neigh skin
   //   since may lead to lost atoms in comm->exchange()
@@ -286,12 +282,17 @@ void FixBalance::rebalance()
   domain->set_local_box();
   domain->subbox_too_small_check(neighbor->skin);
 
+  // output of new decomposition
+
+  if (balance->outflag) balance->dumpout(update->ntimestep);
+
   // move atoms to new processors via irregular()
   // for non-RCB only needed if migrate_check() says an atom moves too far
   // else allow caller's comm->exchange() to do it
   // set disable = 0, so weights migrate with atoms
   //   important to delay disable = 1 until after pre_neighbor imbfinal calc
   //   b/c atoms may migrate again in comm->exchange()
+  // NOTE: for reproducible debug runs, set 1st arg of migrate_atoms() to 1
 
   if (domain->triclinic) domain->x2lamda(atom->nlocal);
   if (wtflag) balance->fixstore->disable = 0;
diff --git a/src/fix_external.cpp b/src/fix_external.cpp
index 5ac9206e7f..b1ffa65e49 100644
--- a/src/fix_external.cpp
+++ b/src/fix_external.cpp
@@ -141,8 +141,7 @@ void FixExternal::post_force(int vflag)
   bigint ntimestep = update->ntimestep;
 
   int eflag = eflag_caller;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   // invoke the callback in driver program
   // it will fill fexternal with forces
diff --git a/src/fix_neigh_history.cpp b/src/fix_neigh_history.cpp
index c21b494aa4..207c409596 100644
--- a/src/fix_neigh_history.cpp
+++ b/src/fix_neigh_history.cpp
@@ -408,7 +408,9 @@ void FixNeighHistory::pre_exchange_newton()
         m = npartner[j]++;
         partner[j][m] = tag[i];
         jvalues = &valuepartner[j][dnum*m];
-        for (n = 0; n < dnum; n++) jvalues[n] = -onevalues[n];
+        if (pair->nondefault_history_transfer) 
+          pair->transfer_history(onevalues,jvalues);
+        else for (n = 0; n < dnum; n++) jvalues[n] = -onevalues[n];
       }
     }
   }
@@ -520,7 +522,9 @@ void FixNeighHistory::pre_exchange_no_newton()
           m = npartner[j]++;
           partner[j][m] = tag[i];
           jvalues = &valuepartner[j][dnum*m];
-          for (n = 0; n < dnum; n++) jvalues[n] = -onevalues[n];
+          if (pair->nondefault_history_transfer) 
+            pair->transfer_history(onevalues, jvalues);
+          else for (n = 0; n < dnum; n++) jvalues[n] = -onevalues[n];
         }
       }
     }
@@ -604,7 +608,7 @@ void FixNeighHistory::post_neighbor()
 
     for (jj = 0; jj < jnum; jj++) {
       j = jlist[jj];
-      rflag = sbmask(j);
+      rflag = sbmask(j) | pair->beyond_contact;
       j &= NEIGHMASK;
       jlist[jj] = j;
 
diff --git a/src/group.cpp b/src/group.cpp
index 6c19af8bc6..256bab7778 100644
--- a/src/group.cpp
+++ b/src/group.cpp
@@ -40,7 +40,7 @@ using namespace LAMMPS_NS;
 #define MAX_GROUP 32
 #define EPSILON 1.0e-6
 
-enum{TYPE,MOLECULE,ID};
+enum{NONE,TYPE,MOLECULE,ID};
 enum{LT,LE,GT,GE,EQ,NEQ,BETWEEN};
 
 #define BIG 1.0e20
@@ -202,7 +202,7 @@ void Group::assign(int narg, char **arg)
 
     if (narg < 3) error->all(FLERR,"Illegal group command");
 
-    int category;
+    int category=NONE;
     if (strcmp(arg[1],"type") == 0) category = TYPE;
     else if (strcmp(arg[1],"molecule") == 0) category = MOLECULE;
     else if (strcmp(arg[1],"id") == 0) category = ID;
diff --git a/src/hashlittle.cpp b/src/hashlittle.cpp
new file mode 100644
index 0000000000..f612be9eeb
--- /dev/null
+++ b/src/hashlittle.cpp
@@ -0,0 +1,348 @@
+// Hash function hashlittle()
+// from lookup3.c, by Bob Jenkins, May 2006, Public Domain
+// bob_jenkins@burtleburtle.net
+
+#include <cmath>
+#include <stddef.h>
+#include <stdint.h>
+
+// if the system defines the __BYTE_ORDER__ define,
+// we use it instead of guessing the platform
+
+#if defined(__BYTE_ORDER__)
+# if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#  define HASH_LITTLE_ENDIAN 1
+# else
+#  define HASH_LITTLE_ENDIAN 0
+# endif
+#else   // heuristic platform guess
+# if defined(__bg__)
+#  define HASH_LITTLE_ENDIAN 0       // IBM BlueGene is big endian
+# else
+#  define HASH_LITTLE_ENDIAN 1       // Intel and AMD x86 are little endian
+# endif
+#endif
+
+#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k))))
+
+/*
+-------------------------------------------------------------------------------
+mix -- mix 3 32-bit values reversibly.
+
+This is reversible, so any information in (a,b,c) before mix() is
+still in (a,b,c) after mix().
+
+If four pairs of (a,b,c) inputs are run through mix(), or through
+mix() in reverse, there are at least 32 bits of the output that
+are sometimes the same for one pair and different for another pair.
+This was tested for:
+* pairs that differed by one bit, by two bits, in any combination
+  of top bits of (a,b,c), or in any combination of bottom bits of
+  (a,b,c).
+* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
+  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
+  is commonly produced by subtraction) look like a single 1-bit
+  difference.
+* the base values were pseudorandom, all zero but one bit set, or
+  all zero plus a counter that starts at zero.
+
+Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that
+satisfy this are
+    4  6  8 16 19  4
+    9 15  3 18 27 15
+   14  9  3  7 17  3
+Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing
+for "differ" defined as + with a one-bit base and a two-bit delta.  I
+used http://burtleburtle.net/bob/hash/avalanche.html to choose
+the operations, constants, and arrangements of the variables.
+
+This does not achieve avalanche.  There are input bits of (a,b,c)
+that fail to affect some output bits of (a,b,c), especially of a.  The
+most thoroughly mixed value is c, but it doesn't really even achieve
+avalanche in c.
+
+This allows some parallelism.  Read-after-writes are good at doubling
+the number of bits affected, so the goal of mixing pulls in the opposite
+direction as the goal of parallelism.  I did what I could.  Rotates
+seem to cost as much as shifts on every machine I could lay my hands
+on, and rotates are much kinder to the top and bottom bits, so I used
+rotates.
+-------------------------------------------------------------------------------
+*/
+#define mix(a,b,c) \
+{ \
+  a -= c;  a ^= rot(c, 4);  c += b; \
+  b -= a;  b ^= rot(a, 6);  a += c; \
+  c -= b;  c ^= rot(b, 8);  b += a; \
+  a -= c;  a ^= rot(c,16);  c += b; \
+  b -= a;  b ^= rot(a,19);  a += c; \
+  c -= b;  c ^= rot(b, 4);  b += a; \
+}
+
+/*
+-------------------------------------------------------------------------------
+final -- final mixing of 3 32-bit values (a,b,c) into c
+
+Pairs of (a,b,c) values differing in only a few bits will usually
+produce values of c that look totally different.  This was tested for
+* pairs that differed by one bit, by two bits, in any combination
+  of top bits of (a,b,c), or in any combination of bottom bits of
+  (a,b,c).
+* "differ" is defined as +, -, ^, or ~^.  For + and -, I transformed
+  the output delta to a Gray code (a^(a>>1)) so a string of 1's (as
+  is commonly produced by subtraction) look like a single 1-bit
+  difference.
+* the base values were pseudorandom, all zero but one bit set, or
+  all zero plus a counter that starts at zero.
+
+These constants passed:
+ 14 11 25 16 4 14 24
+ 12 14 25 16 4 14 24
+and these came close:
+  4  8 15 26 3 22 24
+ 10  8 15 26 3 22 24
+ 11  8 15 26 3 22 24
+-------------------------------------------------------------------------------
+*/
+#define final(a,b,c) \
+{ \
+  c ^= b; c -= rot(b,14); \
+  a ^= c; a -= rot(c,11); \
+  b ^= a; b -= rot(a,25); \
+  c ^= b; c -= rot(b,16); \
+  a ^= c; a -= rot(c,4);  \
+  b ^= a; b -= rot(a,14); \
+  c ^= b; c -= rot(b,24); \
+}
+
+/*
+-------------------------------------------------------------------------------
+hashlittle() -- hash a variable-length key into a 32-bit value
+  k       : the key (the unaligned variable-length array of bytes)
+  length  : the length of the key, counting by bytes
+  initval : can be any 4-byte value
+Returns a 32-bit value.  Every bit of the key affects every bit of
+the return value.  Two keys differing by one or two bits will have
+totally different hash values.
+
+The best hash table sizes are powers of 2.  There is no need to do
+mod a prime (mod is sooo slow!).  If you need less than 32 bits,
+use a bitmask.  For example, if you need only 10 bits, do
+  h = (h & hashmask(10));
+In which case, the hash table should have hashsize(10) elements.
+
+If you are hashing n strings (uint8_t **)k, do it like this:
+  for (i=0, h=0; i<n; ++i) h = hashlittle( k[i], len[i], h);
+
+By Bob Jenkins, 2006.  bob_jenkins@burtleburtle.net.  You may use this
+code any way you wish, private, educational, or commercial.  It's free.
+
+Use for hash table lookup, or anything where one collision in 2^^32 is
+acceptable.  Do NOT use for cryptographic purposes.
+-------------------------------------------------------------------------------
+*/
+
+uint32_t hashlittle( const void *key, size_t length, uint32_t initval)
+{
+#ifndef PURIFY_HATES_HASHLITTLE
+
+  uint32_t a,b,c;                                          /* internal state */
+  union { const void *ptr; size_t i; } u;     /* needed for Mac Powerbook G4 */
+
+  /* Set up the internal state */
+  a = b = c = 0xdeadbeef + ((uint32_t)length) + initval;
+
+  u.ptr = key;
+  if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) {
+    const uint32_t *k = (const uint32_t *)key;         /* read 32-bit chunks */
+
+    /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += k[0];
+      b += k[1];
+      c += k[2];
+      mix(a,b,c);
+      length -= 12;
+      k += 3;
+    }
+
+    /*----------------------------- handle the last (probably partial) block */
+    /*
+     * "k[2]&0xffffff" actually reads beyond the end of the string, but
+     * then masks off the part it's not allowed to read.  Because the
+     * string is aligned, the masked-off tail is in the same word as the
+     * rest of the string.  Every machine with memory protection I've seen
+     * does it on word boundaries, so is OK with this.  But VALGRIND will
+     * still catch it and complain.  The masking trick does make the hash
+     * noticably faster for short strings (like English words).
+     */
+#ifndef VALGRIND
+
+    switch(length)
+    {
+    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
+    case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break;
+    case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break;
+    case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break;
+    case 8 : b+=k[1]; a+=k[0]; break;
+    case 7 : b+=k[1]&0xffffff; a+=k[0]; break;
+    case 6 : b+=k[1]&0xffff; a+=k[0]; break;
+    case 5 : b+=k[1]&0xff; a+=k[0]; break;
+    case 4 : a+=k[0]; break;
+    case 3 : a+=k[0]&0xffffff; break;
+    case 2 : a+=k[0]&0xffff; break;
+    case 1 : a+=k[0]&0xff; break;
+    case 0 : return c;              /* zero length strings require no mixing */
+    }
+
+#else /* make valgrind happy */
+
+    const uint8_t  *k8 = (const uint8_t *)k;
+    switch(length)
+    {
+    case 12: c+=k[2]; b+=k[1]; a+=k[0]; break;
+    case 11: c+=((uint32_t)k8[10])<<16;  /* fall through */
+    case 10: c+=((uint32_t)k8[9])<<8;    /* fall through */
+    case 9 : c+=k8[8];                   /* fall through */
+    case 8 : b+=k[1]; a+=k[0]; break;
+    case 7 : b+=((uint32_t)k8[6])<<16;   /* fall through */
+    case 6 : b+=((uint32_t)k8[5])<<8;    /* fall through */
+    case 5 : b+=k8[4];                   /* fall through */
+    case 4 : a+=k[0]; break;
+    case 3 : a+=((uint32_t)k8[2])<<16;   /* fall through */
+    case 2 : a+=((uint32_t)k8[1])<<8;    /* fall through */
+    case 1 : a+=k8[0]; break;
+    case 0 : return c;
+    }
+
+#endif /* !valgrind */
+
+  } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) {
+    const uint16_t *k = (const uint16_t *)key;         /* read 16-bit chunks */
+    const uint8_t  *k8;
+
+    /*--------------- all but last block: aligned reads and different mixing */
+    while (length > 12)
+    {
+      a += k[0] + (((uint32_t)k[1])<<16);
+      b += k[2] + (((uint32_t)k[3])<<16);
+      c += k[4] + (((uint32_t)k[5])<<16);
+      mix(a,b,c);
+      length -= 12;
+      k += 6;
+    }
+
+    /*----------------------------- handle the last (probably partial) block */
+    k8 = (const uint8_t *)k;
+    switch(length)
+    {
+    case 12: c+=k[4]+(((uint32_t)k[5])<<16);
+             b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 11: c+=((uint32_t)k8[10])<<16;     /* fall through */
+    case 10: c+=k[4];
+             b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 9 : c+=k8[8];                      /* fall through */
+    case 8 : b+=k[2]+(((uint32_t)k[3])<<16);
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 7 : b+=((uint32_t)k8[6])<<16;      /* fall through */
+    case 6 : b+=k[2];
+             a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 5 : b+=k8[4];                      /* fall through */
+    case 4 : a+=k[0]+(((uint32_t)k[1])<<16);
+             break;
+    case 3 : a+=((uint32_t)k8[2])<<16;      /* fall through */
+    case 2 : a+=k[0];
+             break;
+    case 1 : a+=k8[0];
+             break;
+    case 0 : return c;                     /* zero length requires no mixing */
+    }
+
+  } else {                        /* need to read the key one byte at a time */
+    const uint8_t *k = (const uint8_t *)key;
+
+    /*--------------- all but the last block: affect some 32 bits of (a,b,c) */
+    while (length > 12)
+    {
+      a += k[0];
+      a += ((uint32_t)k[1])<<8;
+      a += ((uint32_t)k[2])<<16;
+      a += ((uint32_t)k[3])<<24;
+      b += k[4];
+      b += ((uint32_t)k[5])<<8;
+      b += ((uint32_t)k[6])<<16;
+      b += ((uint32_t)k[7])<<24;
+      c += k[8];
+      c += ((uint32_t)k[9])<<8;
+      c += ((uint32_t)k[10])<<16;
+      c += ((uint32_t)k[11])<<24;
+      mix(a,b,c);
+      length -= 12;
+      k += 12;
+    }
+
+    /*-------------------------------- last block: affect all 32 bits of (c) */
+    switch(length)                   /* all the case statements fall through */
+    {
+    case 12: c+=((uint32_t)k[11])<<24; /* fall through */
+    case 11: c+=((uint32_t)k[10])<<16; /* fall through */
+    case 10: c+=((uint32_t)k[9])<<8;   /* fall through */
+    case 9 : c+=k[8];                  /* fall through */
+    case 8 : b+=((uint32_t)k[7])<<24;  /* fall through */
+    case 7 : b+=((uint32_t)k[6])<<16;  /* fall through */
+    case 6 : b+=((uint32_t)k[5])<<8;   /* fall through */
+    case 5 : b+=k[4];                  /* fall through */
+    case 4 : a+=((uint32_t)k[3])<<24;  /* fall through */
+    case 3 : a+=((uint32_t)k[2])<<16;  /* fall through */
+    case 2 : a+=((uint32_t)k[1])<<8;   /* fall through */
+    case 1 : a+=k[0];
+             break;
+    case 0 : return c;
+    }
+  }
+
+  final(a,b,c);
+  return c;
+
+#else  /* PURIFY_HATES_HASHLITTLE */
+/* I don't know what it is about Jenkins' hashlittle function, but
+ * it drives purify insane, even with VALGRIND defined.  It makes
+ * purify unusable!!  The code execution doesn't even make sense.
+ * Below is a (probably) weaker hash function that at least allows
+ * testing with purify.
+ */
+#define MAXINT_DIV_PHI  11400714819323198485U
+
+  uint32_t h, rest, *p, bytes, num_bytes;
+  char *byteptr;
+
+  num_bytes = length;
+
+  /* First hash the uint32_t-sized portions of the key */
+  h = 0;
+  for (p = (uint32_t *)key, bytes=num_bytes;
+       bytes >= (uint32_t) sizeof(uint32_t);
+       bytes-=sizeof(uint32_t), p++){
+    h = (h^(*p))*MAXINT_DIV_PHI;
+  }
+
+  /* Then take care of the remaining bytes, if any */
+  rest = 0;
+  for (byteptr = (char *)p; bytes > 0; bytes--, byteptr++){
+    rest = (rest<<8) | (*byteptr);
+  }
+
+  /* If extra bytes, merge the two parts */
+  if (rest)
+    h = (h^rest)*MAXINT_DIV_PHI;
+
+  return h;
+#endif /* PURIFY_HATES_HASHLITTLE */
+}
diff --git a/src/hashlittle.h b/src/hashlittle.h
new file mode 100644
index 0000000000..7b57a35c80
--- /dev/null
+++ b/src/hashlittle.h
@@ -0,0 +1,5 @@
+// Hash function hashlittle()
+// from lookup3.c, by Bob Jenkins, May 2006, Public Domain
+// bob_jenkins@burtleburtle.net
+
+uint32_t hashlittle(const void *key, size_t length, uint32_t);
diff --git a/src/improper.h b/src/improper.h
index adcf6d29c8..d940b43a13 100644
--- a/src/improper.h
+++ b/src/improper.h
@@ -56,6 +56,10 @@ class Improper : protected Pointers {
   int vflag_either,vflag_global,vflag_atom;
   int maxeatom,maxvatom;
 
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int, int alloc = 1);
   void ev_tally(int, int, int, int, int, int, double,
                 double *, double *, double *, double, double, double,
diff --git a/src/improper_hybrid.cpp b/src/improper_hybrid.cpp
index 3c17e42eaf..5fdcb42a96 100644
--- a/src/improper_hybrid.cpp
+++ b/src/improper_hybrid.cpp
@@ -104,8 +104,7 @@ void ImproperHybrid::compute(int eflag, int vflag)
   // set neighbor->improperlist to sub-style improperlist before call
   // accumulate sub-style global/peratom energy/virial in hybrid
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = eflag_global = vflag_global = eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   for (m = 0; m < nstyles; m++) {
     neighbor->nimproperlist = nimproperlist[m];
diff --git a/src/improper_zero.cpp b/src/improper_zero.cpp
index 8a1fa529c6..747dd57919 100644
--- a/src/improper_zero.cpp
+++ b/src/improper_zero.cpp
@@ -44,8 +44,7 @@ ImproperZero::~ImproperZero()
 
 void ImproperZero::compute(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/info.cpp b/src/info.cpp
index 3d8a8d7b9e..ac2ee4a96d 100644
--- a/src/info.cpp
+++ b/src/info.cpp
@@ -42,6 +42,7 @@
 #include "variable.h"
 #include "update.h"
 #include "error.h"
+#include "utils.h"
 
 #include <ctime>
 #include <map>
@@ -397,7 +398,7 @@ void Info::command(int narg, char **arg)
     fprintf(out,"Atoms = " BIGINT_FORMAT ",  types = %d,  style = %s\n",
             atom->natoms, atom->ntypes, force->pair_style);
 
-    if (force->pair && strstr(force->pair_style,"hybrid")) {
+    if (force->pair && utils::strmatch(force->pair_style,"^hybrid")) {
       PairHybrid *hybrid = (PairHybrid *)force->pair;
       fprintf(out,"Hybrid sub-styles:");
       for (int i=0; i < hybrid->nstyles; ++i)
diff --git a/src/irregular.cpp b/src/irregular.cpp
index 9c15f135d0..1865f9cbf6 100644
--- a/src/irregular.cpp
+++ b/src/irregular.cpp
@@ -501,7 +501,8 @@ int compare_standalone(const int i, const int j, void *ptr)
 
 void Irregular::exchange_atom(double *sendbuf, int *sizes, double *recvbuf)
 {
-  int i,m,n,offset,count;
+  int i,m,n,count;
+  bigint offset;
 
   // post all receives
 
@@ -621,6 +622,7 @@ int Irregular::create_data(int n, int *proclist, int sortflag)
   num_send = new int[nsend_proc];
   index_send = new int[n-work1[me]];
   index_self = new int[work1[me]];
+  maxindex = n;
 
   // proc_send = procs I send to
   // num_send = # of datums I send to each proc
@@ -678,8 +680,182 @@ int Irregular::create_data(int n, int *proclist, int sortflag)
 
   // receive incoming messages
   // proc_recv = procs I recv from
-  // num_recv = total size of message each proc sends me
-  // nrecvdatum = total size of data I recv
+  // num_recv = # of datums each proc sends me
+  // nrecvdatum = total # of datums I recv
+
+  int nrecvdatum = 0;
+  for (i = 0; i < nrecv_proc; i++) {
+    MPI_Recv(&num_recv[i],1,MPI_INT,MPI_ANY_SOURCE,0,world,status);
+    proc_recv[i] = status->MPI_SOURCE;
+    nrecvdatum += num_recv[i];
+  }
+  nrecvdatum += num_self;
+
+  // sort proc_recv and num_recv by proc ID if requested
+  // useful for debugging to insure reproducible ordering of received datums
+
+  if (sortflag) {
+    int *order = new int[nrecv_proc];
+    int *proc_recv_ordered = new int[nrecv_proc];
+    int *num_recv_ordered = new int[nrecv_proc];
+
+    for (i = 0; i < nrecv_proc; i++) order[i] = i;
+
+#if defined(LMP_QSORT)
+    proc_recv_copy = proc_recv;
+    qsort(order,nrecv_proc,sizeof(int),compare_standalone);
+#else
+    merge_sort(order,nrecv_proc,(void *)proc_recv,compare_standalone);
+#endif
+
+    int j;
+    for (i = 0; i < nrecv_proc; i++) {
+      j = order[i];
+      proc_recv_ordered[i] = proc_recv[j];
+      num_recv_ordered[i] = num_recv[j];
+    }
+
+    memcpy(proc_recv,proc_recv_ordered,nrecv_proc*sizeof(int));
+    memcpy(num_recv,num_recv_ordered,nrecv_proc*sizeof(int));
+    delete [] order;
+    delete [] proc_recv_ordered;
+    delete [] num_recv_ordered;
+  }
+
+  // barrier to insure all MPI_ANY_SOURCE messages are received
+  // else another proc could proceed to exchange_data() and send to me
+
+  MPI_Barrier(world);
+
+  // return # of datums I will receive
+
+  return nrecvdatum;
+}
+
+/* ----------------------------------------------------------------------
+   create communication plan based on list of datums of uniform size
+   n = # of datums to send
+   procs = how many datums to send to each proc, must include self
+   sort = flag for sorting order of received messages by proc ID
+   return total # of datums I will recv, including any to self
+------------------------------------------------------------------------- */
+
+int Irregular::create_data_grouped(int n, int *procs, int sortflag)
+{
+  int i,j,k,m;
+
+  // setup for collective comm
+  // work1 = # of datums I send to each proc, set self to 0
+  // work2 = 1 for all procs, used for ReduceScatter
+
+  for (i = 0; i < nprocs; i++) {
+    work1[i] = procs[i];
+    work2[i] = 1;
+  }
+  work1[me] = 0;
+
+  // nrecv_proc = # of procs I receive messages from, not including self
+  // options for performing ReduceScatter operation
+  // some are more efficient on some machines at big sizes
+
+#ifdef LAMMPS_RS_ALLREDUCE_INPLACE
+  MPI_Allreduce(MPI_IN_PLACE,work1,nprocs,MPI_INT,MPI_SUM,world);
+  nrecv_proc = work1[me];
+#else
+#ifdef LAMMPS_RS_ALLREDUCE
+  MPI_Allreduce(work1,work2,nprocs,MPI_INT,MPI_SUM,world);
+  nrecv_proc = work2[me];
+#else
+  MPI_Reduce_scatter(work1,&nrecv_proc,work2,MPI_INT,MPI_SUM,world);
+#endif
+#endif
+
+  // allocate receive arrays
+
+  proc_recv = new int[nrecv_proc];
+  num_recv = new int[nrecv_proc];
+  request = new MPI_Request[nrecv_proc];
+  status = new MPI_Status[nrecv_proc];
+
+  // work1 = # of datums I send to each proc, including self
+  // nsend_proc = # of procs I send messages to, not including self
+
+  for (i = 0; i < nprocs; i++) work1[i] = procs[i];
+
+  nsend_proc = 0;
+  for (i = 0; i < nprocs; i++)
+    if (work1[i]) nsend_proc++;
+  if (work1[me]) nsend_proc--;
+
+  // allocate send and self arrays
+
+  proc_send = new int[nsend_proc];
+  num_send = new int[nsend_proc];
+  index_send = new int[n-work1[me]];
+  index_self = new int[work1[me]];
+  maxindex = n;
+
+  // proc_send = procs I send to
+  // num_send = # of datums I send to each proc
+  // num_self = # of datums I copy to self
+  // to balance pattern of send messages:
+  //   each proc begins with iproc > me, continues until iproc = me
+  // reset work1 to store which send message each proc corresponds to
+
+  int iproc = me;
+  int isend = 0;
+  for (i = 0; i < nprocs; i++) {
+    iproc++;
+    if (iproc == nprocs) iproc = 0;
+    if (iproc == me) {
+      num_self = work1[iproc];
+      work1[iproc] = 0;
+    } else if (work1[iproc] > 0) {
+      proc_send[isend] = iproc;
+      num_send[isend] = work1[iproc];
+      work1[iproc] = isend;
+      isend++;
+    }
+  }
+
+  // work2 = offsets into index_send for each proc I send to
+  // m = ptr into index_self
+  // index_send = list of which datums to send to each proc
+  //   1st N1 values are datum indices for 1st proc,
+  //   next N2 values are datum indices for 2nd proc, etc
+  // index_self = list of which datums to copy to self
+
+  work2[0] = 0;
+  for (i = 1; i < nsend_proc; i++) work2[i] = work2[i-1] + num_send[i-1];
+
+  m = 0;
+  i = 0;
+  for (iproc = 0; iproc < nprocs; iproc++) {
+    k = procs[iproc];
+    for (j = 0; j < k; j++) {
+      if (iproc == me) index_self[m++] = i++;
+      else {
+        isend = work1[iproc];
+        index_send[work2[isend]++] = i++;
+      }
+    }
+  }
+
+  // tell receivers how much data I send
+  // sendmax_proc = largest # of datums I send in a single message
+
+  sendmax_proc = 0;
+  for (i = 0; i < nsend_proc; i++) {
+    MPI_Request tmpReq; // Use non-blocking send to avoid possible deadlock
+    MPI_Isend(&num_send[i],1,MPI_INT,proc_send[i],0,world,&tmpReq);
+    MPI_Request_free(&tmpReq); // the MPI_Barrier below marks completion
+    sendmax_proc = MAX(sendmax_proc,num_send[i]);
+  }
+
+  // receive incoming messages
+  // proc_recv = procs I recv from
+  // num_recv = # of datums each proc sends me
+  // nrecvdatum = total # of datums I recv
 
   int nrecvdatum = 0;
   for (i = 0; i < nrecv_proc; i++) {
@@ -739,11 +915,13 @@ int Irregular::create_data(int n, int *proclist, int sortflag)
 
 void Irregular::exchange_data(char *sendbuf, int nbytes, char *recvbuf)
 {
-  int i,m,n,offset,count;
+  int i,n,count;
+  bigint m;       // these 2 lines enable send/recv buf to be larger than 2 GB
+  char *dest;
 
   // post all receives, starting after self copies
 
-  offset = num_self*nbytes;
+  bigint offset = num_self*(bigint)nbytes;
   for (int irecv = 0; irecv < nrecv_proc; irecv++) {
     MPI_Irecv(&recvbuf[offset],num_recv[irecv]*nbytes,MPI_CHAR,
               proc_recv[irecv],0,world,&request[irecv]);
@@ -765,18 +943,22 @@ void Irregular::exchange_data(char *sendbuf, int nbytes, char *recvbuf)
   n = 0;
   for (int isend = 0; isend < nsend_proc; isend++) {
     count = num_send[isend];
+    dest = buf;
     for (i = 0; i < count; i++) {
       m = index_send[n++];
-      memcpy(&buf[i*nbytes],&sendbuf[m*nbytes],nbytes);
+      memcpy(dest,&sendbuf[m*nbytes],nbytes);
+      dest += nbytes;
     }
     MPI_Send(buf,count*nbytes,MPI_CHAR,proc_send[isend],0,world);
   }
 
   // copy datums to self, put at beginning of recvbuf
 
+  dest = recvbuf;
   for (i = 0; i < num_self; i++) {
     m = index_self[i];
-    memcpy(&recvbuf[i*nbytes],&sendbuf[m*nbytes],nbytes);
+    memcpy(dest,&sendbuf[m*nbytes],nbytes);
+    dest += nbytes;
   }
 
   // wait on all incoming messages
diff --git a/src/irregular.h b/src/irregular.h
index 1f74fe801b..d56bcb253d 100644
--- a/src/irregular.h
+++ b/src/irregular.h
@@ -33,6 +33,7 @@ class Irregular : protected Pointers {
                      int *procassign = NULL);
   int migrate_check();
   int create_data(int, int *, int sortflag = 0);
+  int create_data_grouped(int, int *, int sortflag = 0);
   void exchange_data(char *, int, char *);
   void destroy_data();
   bigint memory_usage();
@@ -48,6 +49,7 @@ class Irregular : protected Pointers {
   double *dbuf;                     // double buf for largest single atom send
   int maxbuf;                       // size of char buf in bytes
   char *buf;                        // char buf for largest single data send
+  int maxindex;                     // combined size of index_send + index_self
 
   int *mproclist,*msizes;           // persistent vectors in migrate_atoms
   int maxlocal;                     // allocated size of mproclist and msizes
diff --git a/src/kspace.cpp b/src/kspace.cpp
index 25491cd964..0144ea59a3 100644
--- a/src/kspace.cpp
+++ b/src/kspace.cpp
@@ -168,9 +168,7 @@ void KSpace::triclinic_check()
 
 void KSpace::compute_dummy(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = evflag_atom = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/kspace.h b/src/kspace.h
index f29659d0e8..2345cebf24 100644
--- a/src/kspace.h
+++ b/src/kspace.h
@@ -194,6 +194,10 @@ class KSpace : protected Pointers {
   int kx_ewald,ky_ewald,kz_ewald;   // kspace settings for Ewald sum
 
   void pair_check();
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else evflag = eflag_either = eflag_global = eflag_atom = vflag_either = vflag_global = vflag_atom = 0;
+  }
   void ev_setup(int, int, int alloc = 1);
   double estimate_table_accuracy(double, double);
 };
diff --git a/src/library.cpp b/src/library.cpp
index d8c55159a2..a653b83adb 100644
--- a/src/library.cpp
+++ b/src/library.cpp
@@ -801,6 +801,17 @@ void lammps_reset_box(void *ptr, double *boxlo, double *boxhi,
      Allreduce to sum vector into data across all procs
 ------------------------------------------------------------------------- */
 
+#if defined(LAMMPS_BIGBIG)
+void lammps_gather_atoms(void *ptr, char * /*name */,
+                         int /*type*/, int /*count*/, void * /*data*/)
+{
+  LAMMPS *lmp = (LAMMPS *) ptr;
+
+  BEGIN_CAPTURE
+  lmp->error->all(FLERR,"Library function lammps_gather_atoms() not compatible with -DLAMMPS_BIGBIG");
+  END_CAPTURE
+}
+#else
 void lammps_gather_atoms(void *ptr, char *name,
                          int type, int count, void *data)
 {
@@ -905,6 +916,7 @@ void lammps_gather_atoms(void *ptr, char *name,
   }
   END_CAPTURE
 }
+#endif
 
 /* ----------------------------------------------------------------------
    gather the named atom-based entity for all atoms
@@ -927,6 +939,17 @@ void lammps_gather_atoms(void *ptr, char *name,
      Allgather Nlocal atoms from each proc into data
 ------------------------------------------------------------------------- */
 
+#if defined(LAMMPS_BIGBIG)
+void lammps_gather_atoms_concat(void *ptr, char * /*name */,
+                                int /*type*/, int /*count*/, void * /*data*/)
+{
+  LAMMPS *lmp = (LAMMPS *) ptr;
+
+  BEGIN_CAPTURE
+  lmp->error->all(FLERR,"Library function lammps_gather_atoms_concat() not compatible with -DLAMMPS_BIGBIG");
+  END_CAPTURE
+}
+#else
 void lammps_gather_atoms_concat(void *ptr, char *name,
                                 int type, int count, void *data)
 {
@@ -1047,6 +1070,7 @@ void lammps_gather_atoms_concat(void *ptr, char *name,
   }
   END_CAPTURE
 }
+#endif
 
 /* ----------------------------------------------------------------------
    gather the named atom-based entity for a subset of atoms
@@ -1071,6 +1095,18 @@ void lammps_gather_atoms_concat(void *ptr, char *name,
      Allreduce to sum vector into data across all procs
 ------------------------------------------------------------------------- */
 
+#if defined(LAMMPS_BIGBIG)
+void lammps_gather_atoms_subset(void *ptr, char * /*name */,
+                                int /*type*/, int /*count*/,
+                                int /*ndata*/, int * /*ids*/, void * /*data*/)
+{
+  LAMMPS *lmp = (LAMMPS *) ptr;
+
+  BEGIN_CAPTURE
+  lmp->error->all(FLERR,"Library function lammps_gather_atoms_subset() not compatible with -DLAMMPS_BIGBIG");
+  END_CAPTURE
+}
+#else
 void lammps_gather_atoms_subset(void *ptr, char *name,
                                 int type, int count,
                                 int ndata, int *ids, void *data)
@@ -1188,6 +1224,7 @@ void lammps_gather_atoms_subset(void *ptr, char *name,
   }
   END_CAPTURE
 }
+#endif
 
 /* ----------------------------------------------------------------------
    scatter the named atom-based entity in data to all atoms
@@ -1205,6 +1242,17 @@ void lammps_gather_atoms_subset(void *ptr, char *name,
      loop over Natoms, if I own atom ID, set its values from data
 ------------------------------------------------------------------------- */
 
+#if defined(LAMMPS_BIGBIG)
+void lammps_scatter_atoms(void *ptr, char * /*name */,
+                          int /*type*/, int /*count*/, void * /*data*/)
+{
+  LAMMPS *lmp = (LAMMPS *) ptr;
+
+  BEGIN_CAPTURE
+  lmp->error->all(FLERR,"Library function lammps_scatter_atoms() not compatible with -DLAMMPS_BIGBIG");
+  END_CAPTURE
+}
+#else
 void lammps_scatter_atoms(void *ptr, char *name,
                           int type, int count, void *data)
 {
@@ -1299,6 +1347,7 @@ void lammps_scatter_atoms(void *ptr, char *name,
   }
   END_CAPTURE
 }
+#endif
 
 /* ----------------------------------------------------------------------
    scatter the named atom-based entity in data to a subset of atoms
@@ -1318,6 +1367,18 @@ void lammps_scatter_atoms(void *ptr, char *name,
      loop over Ndata, if I own atom ID, set its values from data
 ------------------------------------------------------------------------- */
 
+#if defined(LAMMPS_BIGBIG)
+void lammps_scatter_atoms_subset(void *ptr, char * /*name */,
+                                int /*type*/, int /*count*/,
+                                int /*ndata*/, int * /*ids*/, void * /*data*/)
+{
+  LAMMPS *lmp = (LAMMPS *) ptr;
+
+  BEGIN_CAPTURE
+  lmp->error->all(FLERR,"Library function lammps_scatter_atoms_subset() not compatible with -DLAMMPS_BIGBIG");
+  END_CAPTURE
+}
+#else
 void lammps_scatter_atoms_subset(void *ptr, char *name,
                                  int type, int count,
                                  int ndata, int *ids, void *data)
@@ -1420,6 +1481,7 @@ void lammps_scatter_atoms_subset(void *ptr, char *name,
   }
   END_CAPTURE
 }
+#endif
 
 /* ----------------------------------------------------------------------
    create N atoms and assign them to procs based on coords
diff --git a/src/lmpwindows.h b/src/lmpwindows.h
index 546fa62535..92a248a05e 100644
--- a/src/lmpwindows.h
+++ b/src/lmpwindows.h
@@ -24,14 +24,13 @@
 inline double pow(int i, int j){
   return pow((double)i,j);
 }
-#endif
-inline double sqrt(int i){
-  return sqrt((double) i);
-}
-
 inline double fabs(int i){
   return fabs((double) i);
 }
+inline double sqrt(int i){
+  return sqrt((double) i);
+}
+#endif
 
 inline double trunc(double x) {
   return x > 0 ? floor(x) : ceil(x);
diff --git a/src/memory.cpp b/src/memory.cpp
index 971de3dce6..b2f8a95b17 100644
--- a/src/memory.cpp
+++ b/src/memory.cpp
@@ -26,7 +26,7 @@
 #endif
 #endif
 
-#if defined(LMP_USER_INTEL) && !defined(LAMMPS_MEMALIGN)
+#if defined(LMP_USER_INTEL) && !defined(LAMMPS_MEMALIGN) && !defined(_WIN32)
 #define LAMMPS_MEMALIGN 64
 #endif
 
diff --git a/src/memory.h b/src/memory.h
index df942387fa..c5eddc7fe7 100644
--- a/src/memory.h
+++ b/src/memory.h
@@ -443,44 +443,44 @@ class Memory : protected Pointers {
 
   template <typename TYPE>
   TYPE ****grow(TYPE ****&array, int n1, int n2, int n3, int n4,
-	  const char *name)
+          const char *name)
   {
-	  if (array == NULL) return create(array, n1, n2, n3, n4, name);
+          if (array == NULL) return create(array, n1, n2, n3, n4, name);
 
-	  bigint nbytes = ((bigint) sizeof(TYPE)) * n1*n2*n3*n4;
-	  TYPE *data = (TYPE *)srealloc(array[0][0][0], nbytes, name);
-	  nbytes = ((bigint) sizeof(TYPE *)) * n1*n2*n3;
-	  TYPE **cube = (TYPE **)srealloc(array[0][0], nbytes, name);
-	  nbytes = ((bigint) sizeof(TYPE **)) * n1*n2;
-	  TYPE ***plane = (TYPE ***)srealloc(array[0], nbytes, name);
-	  nbytes = ((bigint) sizeof(TYPE ***)) * n1;
-	  array = (TYPE ****)srealloc(array, nbytes, name);
+          bigint nbytes = ((bigint) sizeof(TYPE)) * n1*n2*n3*n4;
+          TYPE *data = (TYPE *)srealloc(array[0][0][0], nbytes, name);
+          nbytes = ((bigint) sizeof(TYPE *)) * n1*n2*n3;
+          TYPE **cube = (TYPE **)srealloc(array[0][0], nbytes, name);
+          nbytes = ((bigint) sizeof(TYPE **)) * n1*n2;
+          TYPE ***plane = (TYPE ***)srealloc(array[0], nbytes, name);
+          nbytes = ((bigint) sizeof(TYPE ***)) * n1;
+          array = (TYPE ****)srealloc(array, nbytes, name);
 
-	  int i, j, k;
-	  bigint m1, m2;
-	  bigint n = 0;
-	  for (i = 0; i < n1; i++) {
-		  m2 = ((bigint)i) * n2;
-		  array[i] = &plane[m2];
-		  for (j = 0; j < n2; j++) {
-			  m1 = ((bigint)i) * n2 + j;
-			  m2 = ((bigint)i) * n2*n3 + j*n3;
-			  plane[m1] = &cube[m2];
-			  for (k = 0; k < n3; k++) {
-				  m1 = ((bigint)i) * n2*n3 + j*n3 + k;
-				  cube[m1] = &data[n];
-				  n += n4;
-			  }
-		  }
-	  }
-	  return array;
+          int i, j, k;
+          bigint m1, m2;
+          bigint n = 0;
+          for (i = 0; i < n1; i++) {
+                  m2 = ((bigint)i) * n2;
+                  array[i] = &plane[m2];
+                  for (j = 0; j < n2; j++) {
+                          m1 = ((bigint)i) * n2 + j;
+                          m2 = ((bigint)i) * n2*n3 + j*n3;
+                          plane[m1] = &cube[m2];
+                          for (k = 0; k < n3; k++) {
+                                  m1 = ((bigint)i) * n2*n3 + j*n3 + k;
+                                  cube[m1] = &data[n];
+                                  n += n4;
+                          }
+                  }
+          }
+          return array;
   }
 
   template <typename TYPE>
-  TYPE *****grow(TYPE *****&array, int n1, int n2, int n3, int n4,
-	  const char *name)
+  TYPE *****grow(TYPE *****& /*array*/, int /*n1*/, int /*n2*/, int /*n3*/, int /*n4*/,
+          const char *name)
   {
-	  fail(name); return NULL;
+          fail(name); return NULL;
   }
 
 /* ----------------------------------------------------------------------
diff --git a/src/min.cpp b/src/min.cpp
index cd9253f8d3..2a42a444a0 100644
--- a/src/min.cpp
+++ b/src/min.cpp
@@ -655,7 +655,11 @@ void Min::modify_params(int narg, char **arg)
       else if (strcmp(arg[iarg+1],"forcezero") == 0) linestyle = 2;
       else error->all(FLERR,"Illegal min_modify command");
       iarg += 2;
-    } else error->all(FLERR,"Illegal min_modify command");
+    } else {
+      int n = modify_param(narg-iarg,&arg[iarg]);
+      if (n == 0) error->all(FLERR,"Illegal fix_modify command");
+      iarg += n;
+    }
   }
 }
 
diff --git a/src/min.h b/src/min.h
index 92da97c664..a63254231c 100644
--- a/src/min.h
+++ b/src/min.h
@@ -38,6 +38,7 @@ class Min : protected Pointers {
   int request(class Pair *, int, double);
   virtual bigint memory_usage() {return 0;}
   void modify_params(int, char **);
+  virtual int modify_param(int, char **) {return 0;}
   double fnorm_sqr();
   double fnorm_inf();
 
diff --git a/src/modify.cpp b/src/modify.cpp
index 0a03bb6804..7f43f035d2 100644
--- a/src/modify.cpp
+++ b/src/modify.cpp
@@ -28,6 +28,7 @@
 #include "variable.h"
 #include "memory.h"
 #include "error.h"
+#include "utils.h"
 
 using namespace LAMMPS_NS;
 using namespace FixConst;
@@ -1058,7 +1059,7 @@ int Modify::check_rigid_group_overlap(int groupbit)
 
   int n = 0;
   for (int ifix = 0; ifix < nfix; ifix++) {
-    if (strncmp("rigid",fix[ifix]->style,5) == 0) {
+    if (utils::strmatch(fix[ifix]->style,"^rigid")) {
       const int * const body = (const int *)fix[ifix]->extract("body",dim);
       if ((body == NULL) || (dim != 1)) break;
 
diff --git a/src/my_page.h b/src/my_page.h
index 5cd7098d8c..01542a9174 100644
--- a/src/my_page.h
+++ b/src/my_page.h
@@ -48,7 +48,7 @@ methods:
 #ifndef LAMMPS_MY_PAGE_H
 #define LAMMPS_MY_PAGE_H
 
-#if defined(LMP_USER_INTEL) && !defined(LAMMPS_MEMALIGN)
+#if defined(LMP_USER_INTEL) && !defined(LAMMPS_MEMALIGN) && !defined(_WIN32)
 #define LAMMPS_MEMALIGN 64
 #endif
 
diff --git a/src/pair.cpp b/src/pair.cpp
index 44cf3a43ea..20bc35fb01 100644
--- a/src/pair.cpp
+++ b/src/pair.cpp
@@ -72,6 +72,9 @@ Pair::Pair(LAMMPS *lmp) : Pointers(lmp)
   single_extra = 0;
   svector = NULL;
 
+  setflag = NULL;
+  cutsq = NULL;
+
   ewaldflag = pppmflag = msmflag = dispersionflag = tip4pflag = dipoleflag = 0;
   reinitflag = 1;
 
@@ -100,6 +103,9 @@ Pair::Pair(LAMMPS *lmp) : Pointers(lmp)
   num_tally_compute = 0;
   list_tally_compute = NULL;
 
+  nondefault_history_transfer = 0;
+  beyond_contact = 0;
+
   // KOKKOS per-fix data masks
 
   execution_space = Host;
@@ -688,8 +694,7 @@ double Pair::mix_distance(double sig1, double sig2)
 
 void Pair::compute_dummy(int eflag, int vflag)
 {
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 }
 
 /* ---------------------------------------------------------------------- */
diff --git a/src/pair.h b/src/pair.h
index 27b6d41eef..d766a20ef4 100644
--- a/src/pair.h
+++ b/src/pair.h
@@ -98,6 +98,8 @@ class Pair : protected Pointers {
 
   enum{GEOMETRIC,ARITHMETIC,SIXTHPOWER};   // mixing options
 
+  int beyond_contact, nondefault_history_transfer;   // for granular styles
+
   // KOKKOS host/device flag and data masks
 
   ExecutionSpace execution_space;
@@ -180,6 +182,7 @@ class Pair : protected Pointers {
   virtual void min_xf_pointers(int, double **, double **) {}
   virtual void min_xf_get(int) {}
   virtual void min_x_set(int) {}
+  virtual void transfer_history(double *, double*) {}
 
   // management of callbacks to be run from ev_tally()
 
@@ -202,6 +205,7 @@ class Pair : protected Pointers {
   double tabinner;                     // inner cutoff for Coulomb table
   double tabinner_disp;                 // inner cutoff for dispersion table
 
+
  public:
   // custom data type for accessing Coulomb tables
 
@@ -218,6 +222,10 @@ class Pair : protected Pointers {
   int copymode;   // if set, do not deallocate during destruction
                   // required when classes are used as functors by Kokkos
 
+  void ev_init(int eflag, int vflag, int alloc = 1) {
+    if (eflag||vflag) ev_setup(eflag, vflag, alloc);
+    else ev_unset();
+  }
   virtual void ev_setup(int, int, int alloc = 1);
   void ev_unset();
   void ev_tally_full(int, double, double, double, double, double, double);
diff --git a/src/pair_beck.cpp b/src/pair_beck.cpp
index d9c0fb902c..17731ebf0b 100644
--- a/src/pair_beck.cpp
+++ b/src/pair_beck.cpp
@@ -63,8 +63,7 @@ void PairBeck::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_born.cpp b/src/pair_born.cpp
index 1a1db9dd90..78434c91f8 100644
--- a/src/pair_born.cpp
+++ b/src/pair_born.cpp
@@ -71,8 +71,7 @@ void PairBorn::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_born_coul_dsf.cpp b/src/pair_born_coul_dsf.cpp
index be7f41ca2b..2e565897b5 100644
--- a/src/pair_born_coul_dsf.cpp
+++ b/src/pair_born_coul_dsf.cpp
@@ -77,8 +77,7 @@ void PairBornCoulDSF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_born_coul_wolf.cpp b/src/pair_born_coul_wolf.cpp
index 22dcfa9f2d..3bb0e39e57 100644
--- a/src/pair_born_coul_wolf.cpp
+++ b/src/pair_born_coul_wolf.cpp
@@ -76,8 +76,7 @@ void PairBornCoulWolf::compute(int eflag, int vflag)
   double erfcc,erfcd,v_sh,dvdrr,e_self,e_shift,f_shift,qisq;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_buck.cpp b/src/pair_buck.cpp
index 8b6d79234b..a3cf1a38d6 100644
--- a/src/pair_buck.cpp
+++ b/src/pair_buck.cpp
@@ -66,8 +66,7 @@ void PairBuck::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_buck_coul_cut.cpp b/src/pair_buck_coul_cut.cpp
index 7eecb62121..094797694c 100644
--- a/src/pair_buck_coul_cut.cpp
+++ b/src/pair_buck_coul_cut.cpp
@@ -42,7 +42,9 @@ PairBuckCoulCut::PairBuckCoulCut(LAMMPS *lmp) : Pair(lmp)
 
 PairBuckCoulCut::~PairBuckCoulCut()
 {
-  if (!copymode) {
+  if (copymode) return;
+
+  if (allocated) {
     memory->destroy(setflag);
     memory->destroy(cutsq);
 
@@ -71,8 +73,7 @@ void PairBuckCoulCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_coul_cut.cpp b/src/pair_coul_cut.cpp
index 8741abdb89..e7c0e0aabb 100644
--- a/src/pair_coul_cut.cpp
+++ b/src/pair_coul_cut.cpp
@@ -53,8 +53,7 @@ void PairCoulCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_coul_debye.cpp b/src/pair_coul_debye.cpp
index 432a015598..c8afdabb93 100644
--- a/src/pair_coul_debye.cpp
+++ b/src/pair_coul_debye.cpp
@@ -40,8 +40,7 @@ void PairCoulDebye::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_coul_dsf.cpp b/src/pair_coul_dsf.cpp
index 8cd5f7fece..e487ff171c 100644
--- a/src/pair_coul_dsf.cpp
+++ b/src/pair_coul_dsf.cpp
@@ -68,8 +68,7 @@ void PairCoulDSF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_coul_streitz.cpp b/src/pair_coul_streitz.cpp
index 920770ed7f..244dccda12 100644
--- a/src/pair_coul_streitz.cpp
+++ b/src/pair_coul_streitz.cpp
@@ -412,8 +412,7 @@ void PairCoulStreitz::compute(int eflag, int vflag)
   ci_jfi = ci_fifj = dci_jfi = dci_fifj = 0.0;
   forcecoul = 0.0;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   inum = list->inum;
   ilist = list->ilist;
diff --git a/src/pair_coul_wolf.cpp b/src/pair_coul_wolf.cpp
index 762491166e..dbf21b8bee 100644
--- a/src/pair_coul_wolf.cpp
+++ b/src/pair_coul_wolf.cpp
@@ -64,8 +64,7 @@ void PairCoulWolf::compute(int eflag, int vflag)
   double erfcc,erfcd,v_sh,dvdrr,e_self,e_shift,f_shift,qisq;
 
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_dpd.cpp b/src/pair_dpd.cpp
index 5c5fc4254b..914b4aee17 100644
--- a/src/pair_dpd.cpp
+++ b/src/pair_dpd.cpp
@@ -70,8 +70,7 @@ void PairDPD::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **v = atom->v;
diff --git a/src/pair_dpd_tstat.cpp b/src/pair_dpd_tstat.cpp
index f2c0b157ea..1207c954eb 100644
--- a/src/pair_dpd_tstat.cpp
+++ b/src/pair_dpd_tstat.cpp
@@ -43,8 +43,7 @@ void PairDPDTstat::compute(int eflag, int vflag)
   double rsq,r,rinv,dot,wd,randnum,factor_dpd;
   int *ilist,*jlist,*numneigh,**firstneigh;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   // adjust sigma if target T is changing
 
diff --git a/src/pair_gauss.cpp b/src/pair_gauss.cpp
index 426389753b..2d157d6cac 100644
--- a/src/pair_gauss.cpp
+++ b/src/pair_gauss.cpp
@@ -68,8 +68,7 @@ void PairGauss::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
   int occ = 0;
 
   double **x = atom->x;
diff --git a/src/pair_hybrid.cpp b/src/pair_hybrid.cpp
index 2b2304718c..a1a6c81195 100644
--- a/src/pair_hybrid.cpp
+++ b/src/pair_hybrid.cpp
@@ -1,3 +1,4 @@
+
 /* ----------------------------------------------------------------------
    LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
    http://lammps.sandia.gov, Sandia National Laboratories
@@ -45,7 +46,7 @@ PairHybrid::PairHybrid(LAMMPS *lmp) : Pair(lmp),
 
 PairHybrid::~PairHybrid()
 {
-  if (nstyles) {
+  if (nstyles > 0) {
     for (int m = 0; m < nstyles; m++) {
       delete styles[m];
       delete [] keywords[m];
@@ -95,9 +96,7 @@ void PairHybrid::compute(int eflag, int vflag)
 
   if (no_virial_fdotr_compute && vflag % 4 == 2) vflag = 1 + vflag/4 * 4;
 
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = eflag_global = vflag_global =
-         eflag_atom = vflag_atom = 0;
+  ev_init(eflag,vflag);
 
   // check if global component of incoming vflag = 2
   // if so, reset vflag passed to substyle as if it were 0
@@ -243,11 +242,18 @@ void PairHybrid::settings(int narg, char **arg)
 
   // delete old lists, since cannot just change settings
 
-  if (nstyles) {
-    for (int m = 0; m < nstyles; m++) delete styles[m];
-    delete [] styles;
-    for (int m = 0; m < nstyles; m++) delete [] keywords[m];
-    delete [] keywords;
+  if (nstyles > 0) {
+    for (int m = 0; m < nstyles; m++) {
+      delete styles[m];
+      delete [] keywords[m];
+      if (special_lj[m])   delete [] special_lj[m];
+      if (special_coul[m]) delete [] special_coul[m];
+    }
+    delete[] styles;
+    delete[] keywords;
+    delete[] multiple;
+    delete[] special_lj;
+    delete[] special_coul;
   }
 
   if (allocated) {
@@ -670,6 +676,12 @@ void PairHybrid::read_restart(FILE *fp)
 
   // allocate list of sub-styles
 
+  delete[] styles;
+  delete[] keywords;
+  delete[] multiple;
+  delete[] special_lj;
+  delete[] special_coul;
+
   styles = new Pair*[nstyles];
   keywords = new char*[nstyles];
   multiple = new int[nstyles];
diff --git a/src/pair_lj96_cut.cpp b/src/pair_lj96_cut.cpp
index 457eba0e79..cefe9b87e0 100644
--- a/src/pair_lj96_cut.cpp
+++ b/src/pair_lj96_cut.cpp
@@ -73,8 +73,7 @@ void PairLJ96Cut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -308,8 +307,7 @@ void PairLJ96Cut::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cubic.cpp b/src/pair_lj_cubic.cpp
index 770caa6359..fdbfca608f 100644
--- a/src/pair_lj_cubic.cpp
+++ b/src/pair_lj_cubic.cpp
@@ -67,8 +67,7 @@ void PairLJCubic::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cut.cpp b/src/pair_lj_cut.cpp
index 13a546f5a5..2a0fcde3a5 100644
--- a/src/pair_lj_cut.cpp
+++ b/src/pair_lj_cut.cpp
@@ -73,8 +73,7 @@ void PairLJCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -305,8 +304,7 @@ void PairLJCut::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cut_coul_cut.cpp b/src/pair_lj_cut_coul_cut.cpp
index 15c06ab36a..6f2ba75309 100644
--- a/src/pair_lj_cut_coul_cut.cpp
+++ b/src/pair_lj_cut_coul_cut.cpp
@@ -67,8 +67,7 @@ void PairLJCutCoulCut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cut_coul_debye.cpp b/src/pair_lj_cut_coul_debye.cpp
index dfd866ca7a..cc6e92b2e3 100644
--- a/src/pair_lj_cut_coul_debye.cpp
+++ b/src/pair_lj_cut_coul_debye.cpp
@@ -37,8 +37,7 @@ void PairLJCutCoulDebye::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cut_coul_dsf.cpp b/src/pair_lj_cut_coul_dsf.cpp
index a49af13fb2..f114a5851f 100644
--- a/src/pair_lj_cut_coul_dsf.cpp
+++ b/src/pair_lj_cut_coul_dsf.cpp
@@ -52,21 +52,21 @@ PairLJCutCoulDSF::PairLJCutCoulDSF(LAMMPS *lmp) : Pair(lmp)
 
 PairLJCutCoulDSF::~PairLJCutCoulDSF()
 {
-  if (!copymode) {
-    if (allocated) {
-      memory->destroy(setflag);
-      memory->destroy(cutsq);
+  if (copymode) return;
 
-      memory->destroy(cut_lj);
-      memory->destroy(cut_ljsq);
-      memory->destroy(epsilon);
-      memory->destroy(sigma);
-      memory->destroy(lj1);
-      memory->destroy(lj2);
-      memory->destroy(lj3);
-      memory->destroy(lj4);
-      memory->destroy(offset);
-    }
+  if (allocated) {
+    memory->destroy(setflag);
+    memory->destroy(cutsq);
+
+    memory->destroy(cut_lj);
+    memory->destroy(cut_ljsq);
+    memory->destroy(epsilon);
+    memory->destroy(sigma);
+    memory->destroy(lj1);
+    memory->destroy(lj2);
+    memory->destroy(lj3);
+    memory->destroy(lj4);
+    memory->destroy(offset);
   }
 }
 
@@ -81,8 +81,7 @@ void PairLJCutCoulDSF::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_cut_coul_wolf.cpp b/src/pair_lj_cut_coul_wolf.cpp
index fc8a858ce1..55aff0d7c5 100644
--- a/src/pair_lj_cut_coul_wolf.cpp
+++ b/src/pair_lj_cut_coul_wolf.cpp
@@ -77,8 +77,7 @@ void PairLJCutCoulWolf::compute(int eflag, int vflag)
 
   evdwl = 0.0;
   ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -218,7 +217,8 @@ void PairLJCutCoulWolf::settings(int narg, char **arg)
 
   alf = force->numeric(FLERR,arg[0]);
   cut_lj_global = force->numeric(FLERR,arg[1]);
-  if (narg == 2) cut_coul = cut_lj_global;
+  if (narg == 3) cut_coul = force->numeric(FLERR,arg[2]);
+  else           cut_coul = cut_lj_global;
 
   if (allocated) {
     int i,j;
diff --git a/src/pair_lj_expand.cpp b/src/pair_lj_expand.cpp
index 9aa58b3b88..d5c0a40f2d 100644
--- a/src/pair_lj_expand.cpp
+++ b/src/pair_lj_expand.cpp
@@ -38,8 +38,9 @@ PairLJExpand::PairLJExpand(LAMMPS *lmp) : Pair(lmp)
 
 PairLJExpand::~PairLJExpand()
 {
-  if (!copymode) {
-   if (allocated) {
+  if (copymode) return;
+
+  if (allocated) {
     memory->destroy(setflag);
     memory->destroy(cutsq);
 
@@ -52,7 +53,6 @@ PairLJExpand::~PairLJExpand()
     memory->destroy(lj3);
     memory->destroy(lj4);
     memory->destroy(offset);
-   }
   }
 }
 
@@ -67,8 +67,7 @@ void PairLJExpand::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_gromacs.cpp b/src/pair_lj_gromacs.cpp
index 495e96c368..1fdaefebe9 100644
--- a/src/pair_lj_gromacs.cpp
+++ b/src/pair_lj_gromacs.cpp
@@ -41,8 +41,9 @@ PairLJGromacs::PairLJGromacs(LAMMPS *lmp) : Pair(lmp)
 
 PairLJGromacs::~PairLJGromacs()
 {
-  if (!copymode) {
-   if (allocated) {
+  if (copymode) return;
+
+  if (allocated) {
     memory->destroy(setflag);
     memory->destroy(cutsq);
 
@@ -60,7 +61,6 @@ PairLJGromacs::~PairLJGromacs()
     memory->destroy(ljsw3);
     memory->destroy(ljsw4);
     memory->destroy(ljsw5);
-   }
   }
 }
 
@@ -75,8 +75,7 @@ void PairLJGromacs::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_gromacs_coul_gromacs.cpp b/src/pair_lj_gromacs_coul_gromacs.cpp
index 414bfea92a..28dc8ec79b 100644
--- a/src/pair_lj_gromacs_coul_gromacs.cpp
+++ b/src/pair_lj_gromacs_coul_gromacs.cpp
@@ -41,8 +41,9 @@ PairLJGromacsCoulGromacs::PairLJGromacsCoulGromacs(LAMMPS *lmp) : Pair(lmp)
 
 PairLJGromacsCoulGromacs::~PairLJGromacsCoulGromacs()
 {
-  if (!copymode) {
-   if (allocated) {
+  if (copymode) return;
+
+  if (allocated) {
     memory->destroy(setflag);
     memory->destroy(cutsq);
 
@@ -57,7 +58,6 @@ PairLJGromacsCoulGromacs::~PairLJGromacsCoulGromacs()
     memory->destroy(ljsw3);
     memory->destroy(ljsw4);
     memory->destroy(ljsw5);
-   }
   }
 }
 
@@ -72,8 +72,7 @@ void PairLJGromacsCoulGromacs::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = ecoul = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_smooth.cpp b/src/pair_lj_smooth.cpp
index a12046bb3b..ecacadbffa 100644
--- a/src/pair_lj_smooth.cpp
+++ b/src/pair_lj_smooth.cpp
@@ -72,8 +72,7 @@ void PairLJSmooth::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_lj_smooth_linear.cpp b/src/pair_lj_smooth_linear.cpp
index 17c789bcee..265828c4cf 100644
--- a/src/pair_lj_smooth_linear.cpp
+++ b/src/pair_lj_smooth_linear.cpp
@@ -62,8 +62,7 @@ void PairLJSmoothLinear::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_mie_cut.cpp b/src/pair_mie_cut.cpp
index c1e1c1ff50..231832dc48 100644
--- a/src/pair_mie_cut.cpp
+++ b/src/pair_mie_cut.cpp
@@ -75,8 +75,7 @@ void PairMIECut::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -310,8 +309,7 @@ void PairMIECut::compute_outer(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_morse.cpp b/src/pair_morse.cpp
index c1031343e1..dca1834c14 100644
--- a/src/pair_morse.cpp
+++ b/src/pair_morse.cpp
@@ -59,8 +59,7 @@ void PairMorse::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_soft.cpp b/src/pair_soft.cpp
index d1c51ac600..7602f7b925 100644
--- a/src/pair_soft.cpp
+++ b/src/pair_soft.cpp
@@ -58,8 +58,7 @@ void PairSoft::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_table.cpp b/src/pair_table.cpp
index 04b1e4ceee..b1b6f45eda 100644
--- a/src/pair_table.cpp
+++ b/src/pair_table.cpp
@@ -74,8 +74,7 @@ void PairTable::compute(int eflag, int vflag)
   int tlm1 = tablength - 1;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
@@ -379,7 +378,7 @@ void PairTable::read_table(Table *tb, char *file, char *keyword)
     utils::sfgets(FLERR,line,MAXLINE,fp,file,error); // no match, skip section
     param_extract(tb,line);
     utils::sfgets(FLERR,line,MAXLINE,fp,file,error);
-    for (int i = 0; i < tb->ninput; i++) 
+    for (int i = 0; i < tb->ninput; i++)
       utils::sfgets(FLERR,line,MAXLINE,fp,file,error);
   }
 
diff --git a/src/pair_ufm.cpp b/src/pair_ufm.cpp
index a9f076f504..226fb6e7d9 100644
--- a/src/pair_ufm.cpp
+++ b/src/pair_ufm.cpp
@@ -74,8 +74,7 @@ void PairUFM::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_yukawa.cpp b/src/pair_yukawa.cpp
index af520fd3da..913afbd5a1 100644
--- a/src/pair_yukawa.cpp
+++ b/src/pair_yukawa.cpp
@@ -55,8 +55,7 @@ void PairYukawa::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_zbl.cpp b/src/pair_zbl.cpp
index f23a1e5d56..254a82ea64 100644
--- a/src/pair_zbl.cpp
+++ b/src/pair_zbl.cpp
@@ -78,8 +78,7 @@ void PairZBL::compute(int eflag, int vflag)
   int *ilist,*jlist,*numneigh,**firstneigh;
 
   evdwl = 0.0;
-  if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+  ev_init(eflag,vflag);
 
   double **x = atom->x;
   double **f = atom->f;
diff --git a/src/pair_zero.cpp b/src/pair_zero.cpp
index d423e196af..143808f598 100644
--- a/src/pair_zero.cpp
+++ b/src/pair_zero.cpp
@@ -50,8 +50,7 @@ PairZero::~PairZero()
 
 void PairZero::compute(int eflag, int vflag)
 {
- if (eflag || vflag) ev_setup(eflag,vflag);
-  else evflag = vflag_fdotr = 0;
+ ev_init(eflag,vflag);
 
  if (vflag_fdotr) virial_fdotr_compute();
 }
diff --git a/src/read_data.cpp b/src/read_data.cpp
index 2f4484010b..e2efbaaefa 100644
--- a/src/read_data.cpp
+++ b/src/read_data.cpp
@@ -120,6 +120,9 @@ void ReadData::command(int narg, char **arg)
 {
   if (narg < 1) error->all(FLERR,"Illegal read_data command");
 
+  MPI_Barrier(world);
+  double time1 = MPI_Wtime();
+
   // optional args
 
   addflag = NONE;
@@ -906,6 +909,18 @@ void ReadData::command(int narg, char **arg)
 
     force->kspace = saved_kspace;
   }
+
+  // total time
+
+  MPI_Barrier(world);
+  double time2 = MPI_Wtime();
+
+  if (comm->me == 0) {
+    if (screen)
+      fprintf(screen,"  read_data CPU = %g secs\n",time2-time1);
+    if (logfile)
+      fprintf(logfile,"  read_data CPU = %g secs\n",time2-time1);
+  }
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/read_dump.cpp b/src/read_dump.cpp
index 551cc63c9e..7a05f4b1b5 100644
--- a/src/read_dump.cpp
+++ b/src/read_dump.cpp
@@ -94,7 +94,7 @@ ReadDump::~ReadDump()
 
   memory->destroy(fields);
   memory->destroy(buf);
-  
+
   for (int i = 0; i < nreader; i++) delete readers[i];
   delete [] readers;
   delete [] nsnapatoms;
@@ -359,7 +359,7 @@ bigint ReadDump::seek(bigint nrequest, int exact)
         readers[i]->skip();
       }
 
-      if (eofflag) 
+      if (eofflag)
         error->one(FLERR,"Read dump parallel files "
                    "do not all have same timestep");
     }
@@ -466,7 +466,7 @@ bigint ReadDump::next(bigint ncurrent, bigint nlast, int nevery, int nskip)
         readers[i]->skip();
       }
 
-      if (eofflag) 
+      if (eofflag)
         error->one(FLERR,"Read dump parallel files "
                    "do not all have same timestep");
     }
@@ -724,7 +724,7 @@ void ReadDump::read_atoms()
       otherproc = 0;
       ofirst = (bigint) otherproc * nsnap/nprocs_cluster;
       olast = (bigint) (otherproc+1) * nsnap/nprocs_cluster;
-      if (olast-ofirst > MAXSMALLINT) 
+      if (olast-ofirst > MAXSMALLINT)
         error->one(FLERR,"Read dump snapshot is too large for a proc");
       nnew = static_cast<int> (olast - ofirst);
 
@@ -765,7 +765,7 @@ void ReadDump::read_atoms()
     } else {
       ofirst = (bigint) me_cluster * nsnap/nprocs_cluster;
       olast = (bigint) (me_cluster+1) * nsnap/nprocs_cluster;
-      if (olast-ofirst > MAXSMALLINT) 
+      if (olast-ofirst > MAXSMALLINT)
         error->one(FLERR,"Read dump snapshot is too large for a proc");
       nnew = static_cast<int> (olast - ofirst);
       if (nnew > maxnew || maxnew == 0) {
@@ -791,7 +791,7 @@ void ReadDump::read_atoms()
     bigint sum = 0;
     for (int i = 0; i < nreader; i++)
       sum += nsnapatoms[i];
-    if (sum > MAXSMALLINT) 
+    if (sum > MAXSMALLINT)
       error->one(FLERR,"Read dump snapshot is too large for a proc");
     nnew = static_cast<int> (sum);
     if (nnew > maxnew || maxnew == 0) {
@@ -811,7 +811,7 @@ void ReadDump::read_atoms()
       }
       nnew += nsnap;
     }
-  }  
+  }
 }
 
 /* ----------------------------------------------------------------------
@@ -943,7 +943,7 @@ void ReadDump::process_atoms()
         ntrim++;
       } else i++;
     }
-    
+
     atom->nlocal = nlocal;
     bigint nblocal = atom->nlocal;
     MPI_Allreduce(&nblocal,&atom->natoms,1,MPI_LMP_BIGINT,MPI_SUM,world);
diff --git a/src/read_dump.h b/src/read_dump.h
index 73cb0a8995..de174c3df6 100644
--- a/src/read_dump.h
+++ b/src/read_dump.h
@@ -86,7 +86,7 @@ private:
   double xlo,xhi,ylo,yhi,zlo,zhi,xy,xz,yz;  // dump snapshot box params
   double xprd,yprd,zprd;
 
-  bigint *nsnapatoms;       // # of atoms in one snapshot from 
+  bigint *nsnapatoms;       // # of atoms in one snapshot from
                             //   one (parallel) dump file
                             // nreader-length vector b/c a reader proc
                             //   may read from multiple parallel dump files
diff --git a/src/read_restart.cpp b/src/read_restart.cpp
index 73dc37f4cb..5aa4622a67 100644
--- a/src/read_restart.cpp
+++ b/src/read_restart.cpp
@@ -81,6 +81,9 @@ void ReadRestart::command(int narg, char **arg)
   if (domain->box_exist)
     error->all(FLERR,"Cannot read_restart after simulation box is defined");
 
+  MPI_Barrier(world);
+  double time1 = MPI_Wtime();
+
   MPI_Comm_rank(world,&me);
   MPI_Comm_size(world,&nprocs);
 
@@ -562,6 +565,18 @@ void ReadRestart::command(int narg, char **arg)
     Special special(lmp);
     special.build();
   }
+
+  // total time
+
+  MPI_Barrier(world);
+  double time2 = MPI_Wtime();
+
+  if (comm->me == 0) {
+    if (screen)
+      fprintf(screen,"  read_restart CPU = %g secs\n",time2-time1);
+    if (logfile)
+      fprintf(logfile,"  read_restart CPU = %g secs\n",time2-time1);
+  }
 }
 
 /* ----------------------------------------------------------------------
diff --git a/src/replicate.cpp b/src/replicate.cpp
index cdadf1fd1f..3c8f4a8aee 100644
--- a/src/replicate.cpp
+++ b/src/replicate.cpp
@@ -76,7 +76,7 @@ void Replicate::command(int narg, char **arg)
   if (atom->nextra_grow || atom->nextra_restart || atom->nextra_store)
     error->all(FLERR,"Cannot replicate with fixes that store atom quantities");
 
-  // Record wall time for atom replication
+  // record wall time for atom replication
 
   MPI_Barrier(world);
   double time1 = MPI_Wtime();
@@ -762,15 +762,15 @@ void Replicate::command(int narg, char **arg)
     special.build();
   }
 
-  // Wall time
+  // total time
 
   MPI_Barrier(world);
   double time2 = MPI_Wtime();
 
   if (me == 0) {
     if (screen)
-      fprintf(screen,"  Time spent = %g secs\n",time2-time1);
+      fprintf(screen,"  replicate CPU = %g secs\n",time2-time1);
     if (logfile)
-      fprintf(logfile,"  Time spent = %g secs\n",time2-time1);
+      fprintf(logfile,"  replicate CPU = %g secs\n",time2-time1);
   }
 }
diff --git a/src/respa.cpp b/src/respa.cpp
index 26bae5a1cb..6fa9959d78 100644
--- a/src/respa.cpp
+++ b/src/respa.cpp
@@ -38,6 +38,7 @@
 #include "timer.h"
 #include "memory.h"
 #include "error.h"
+#include "utils.h"
 #include "pair_hybrid.h"
 
 using namespace LAMMPS_NS;
@@ -120,7 +121,7 @@ Respa::Respa(LAMMPS *lmp, int narg, char **arg) :
       iarg += 2;
     } else if (strcmp(arg[iarg],"hybrid") == 0) {
       // the hybrid keyword requires a hybrid pair style
-      if (!strstr(force->pair_style,"hybrid"))
+      if (!utils::strmatch(force->pair_style,"^hybrid"))
         error->all(FLERR,"Illegal run_style respa command");
       PairHybrid *hybrid = (PairHybrid *) force->pair;
       nhybrid_styles = hybrid->nstyles;
diff --git a/src/special.cpp b/src/special.cpp
index fccc930353..903794c0f6 100644
--- a/src/special.cpp
+++ b/src/special.cpp
@@ -21,12 +21,14 @@
 #include "modify.h"
 #include "fix.h"
 #include "accelerator_kokkos.h"
+#include "atom_masks.h"
 #include "memory.h"
 #include "error.h"
-#include "atom_masks.h"
 
 using namespace LAMMPS_NS;
 
+#define RVOUS 1   // 0 for irregular, 1 for all2all
+
 /* ---------------------------------------------------------------------- */
 
 Special::Special(LAMMPS *lmp) : Pointers(lmp)
@@ -54,18 +56,8 @@ Special::~Special()
 
 void Special::build()
 {
-  int i,j,k,size;
-  int max,maxall,nbuf;
-  tagint *buf;
-
   MPI_Barrier(world);
-
-  int nlocal = atom->nlocal;
-
-  tagint *tag = atom->tag;
-  int *num_bond = atom->num_bond;
-  tagint **bond_atom = atom->bond_atom;
-  int **nspecial = atom->nspecial;
+  double time1 = MPI_Wtime();
 
   if (me == 0 && screen) {
     const double * const special_lj   = force->special_lj;
@@ -79,224 +71,57 @@ void Special::build()
 
   // initialize nspecial counters to 0
 
-  for (i = 0; i < nlocal; i++) {
+  int **nspecial = atom->nspecial;
+  int nlocal = atom->nlocal;
+
+  for (int i = 0; i < nlocal; i++) {
     nspecial[i][0] = 0;
     nspecial[i][1] = 0;
     nspecial[i][2] = 0;
   }
 
-  // -----------------------------------------------------
-  // compute nspecial[i][0] = # of 1-2 neighbors of atom i
-  // -----------------------------------------------------
+  // setup atomIDs and procowner vectors in rendezvous decomposition
 
-  // bond partners stored by atom itself
+  atom_owners();
 
-  for (i = 0; i < nlocal; i++) nspecial[i][0] = num_bond[i];
-
-  // if newton_bond off, then done
-  // else only counted 1/2 of all bonds, so count other half
-
-  if (force->newton_bond) {
-
-    // nbufmax = largest buffer needed to hold info from any proc
-    // info for each atom = global tag of 2nd atom in each bond
-
-    nbuf = 0;
-    for (i = 0; i < nlocal; i++) nbuf += num_bond[i];
-    memory->create(buf,nbuf,"special:buf");
-
-    // fill buffer with global tags of bond partners of my atoms
-
-    size = 0;
-    for (i = 0; i < nlocal; i++)
-      for (j = 0; j < num_bond[i]; j++)
-        buf[size++] = bond_atom[i][j];
-
-    // cycle buffer around ring of procs back to self
-    // when receive buffer, scan tags for atoms I own
-    // when find one, increment nspecial count for that atom
-
-    comm->ring(size,sizeof(tagint),buf,1,ring_one,NULL,(void *)this);
-
-    memory->destroy(buf);
-  }
-
-  // ----------------------------------------------------
+  // tally nspecial[i][0] = # of 1-2 neighbors of atom i
   // create onetwo[i] = list of 1-2 neighbors for atom i
-  // ----------------------------------------------------
 
-  max = 0;
-  for (i = 0; i < nlocal; i++) max = MAX(max,nspecial[i][0]);
+  if (force->newton_bond) onetwo_build_newton();
+  else onetwo_build_newton_off();
 
-  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  // print max # of 1-2 neighbors
 
   if (me == 0) {
     if (screen) fprintf(screen,"  %d = max # of 1-2 neighbors\n",maxall);
     if (logfile) fprintf(logfile,"  %d = max # of 1-2 neighbors\n",maxall);
   }
 
-  memory->create(onetwo,nlocal,maxall,"special:onetwo");
-
-  // count = accumulating counter
-
-  memory->create(count,nlocal,"special:count");
-  for (i = 0; i < nlocal; i++) count[i] = 0;
-
-  // add bond partners stored by atom to onetwo list
-
-  for (i = 0; i < nlocal; i++)
-    for (j = 0; j < num_bond[i]; j++)
-      onetwo[i][count[i]++] = bond_atom[i][j];
-
-  // if newton_bond off, then done
-  // else only stored 1/2 of all bonds, so store other half
-
-  if (force->newton_bond) {
-
-    // nbufmax = largest buffer needed to hold info from any proc
-    // info for each atom = 2 global tags in each bond
-
-    nbuf = 0;
-    for (i = 0; i < nlocal; i++) nbuf += 2*num_bond[i];
-    memory->create(buf,nbuf,"special:buf");
-
-    // fill buffer with global tags of both atoms in bond
-
-    size = 0;
-    for (i = 0; i < nlocal; i++)
-      for (j = 0; j < num_bond[i]; j++) {
-        buf[size++] = tag[i];
-        buf[size++] = bond_atom[i][j];
-      }
-
-    // cycle buffer around ring of procs back to self
-    // when receive buffer, scan 2nd-atom tags for atoms I own
-    // when find one, add 1st-atom tag to onetwo list for 2nd atom
-
-    comm->ring(size,sizeof(tagint),buf,2,ring_two,NULL,(void *)this);
-
-    memory->destroy(buf);
-  }
-
-  memory->destroy(count);
-
-  // -----------------------------------------------------
   // done if special_bond weights for 1-3, 1-4 are set to 1.0
-  // -----------------------------------------------------
 
   if (force->special_lj[2] == 1.0 && force->special_coul[2] == 1.0 &&
       force->special_lj[3] == 1.0 && force->special_coul[3] == 1.0) {
     dedup();
     combine();
     fix_alteration();
+    memory->destroy(procowner);
+    memory->destroy(atomIDs);
+    timer_output(time1);
     return;
   }
 
-  // -----------------------------------------------------
-  // compute nspecial[i][1] = # of 1-3 neighbors of atom i
-  // -----------------------------------------------------
-
-  // nbufmax = largest buffer needed to hold info from any proc
-  // info for each atom = 2 scalars + list of 1-2 neighbors
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) nbuf += 2 + nspecial[i][0];
-  memory->create(buf,nbuf,"special:buf");
-
-  // fill buffer with:
-  // (1) = counter for 1-3 neighbors, initialized to 0
-  // (2) = # of 1-2 neighbors
-  // (3:N) = list of 1-2 neighbors
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    buf[size++] = 0;
-    buf[size++] = nspecial[i][0];
-    for (j = 0; j < nspecial[i][0]; j++) buf[size++] = onetwo[i][j];
-  }
-
-  // cycle buffer around ring of procs back to self
-  // when receive buffer, scan list of 1-2 neighbors for atoms I own
-  // when find one, increment 1-3 count by # of 1-2 neighbors of my atom,
-  //   subtracting one since my list will contain original atom
-
-  comm->ring(size,sizeof(tagint),buf,3,ring_three,buf,(void *)this);
-
-  // extract count from buffer that has cycled back to me
-  // nspecial[i][1] = # of 1-3 neighbors of atom i
-
-  j = 0;
-  for (i = 0; i < nlocal; i++) {
-    nspecial[i][1] = buf[j];
-    j += 2 + nspecial[i][0];
-  }
-
-  memory->destroy(buf);
-
-  // ----------------------------------------------------
+  // tally nspecial[i][1] = # of 1-3 neighbors of atom i
   // create onethree[i] = list of 1-3 neighbors for atom i
-  // ----------------------------------------------------
 
-  max = 0;
-  for (i = 0; i < nlocal; i++) max = MAX(max,nspecial[i][1]);
-  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  onethree_build();
+
+  // print max # of 1-3 neighbors
 
   if (me == 0) {
     if (screen) fprintf(screen,"  %d = max # of 1-3 neighbors\n",maxall);
     if (logfile) fprintf(logfile,"  %d = max # of 1-3 neighbors\n",maxall);
   }
 
-  memory->create(onethree,nlocal,maxall,"special:onethree");
-
-  // nbufmax = largest buffer needed to hold info from any proc
-  // info for each atom = 4 scalars + list of 1-2 neighs + list of 1-3 neighs
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) nbuf += 4 + nspecial[i][0] + nspecial[i][1];
-  memory->create(buf,nbuf,"special:buf");
-
-  // fill buffer with:
-  // (1) = global tag of original atom
-  // (2) = # of 1-2 neighbors
-  // (3) = # of 1-3 neighbors
-  // (4) = counter for 1-3 neighbors, initialized to 0
-  // (5:N) = list of 1-2 neighbors
-  // (N+1:2N) space for list of 1-3 neighbors
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    buf[size++] = tag[i];
-    buf[size++] = nspecial[i][0];
-    buf[size++] = nspecial[i][1];
-    buf[size++] = 0;
-    for (j = 0; j < nspecial[i][0]; j++) buf[size++] = onetwo[i][j];
-    size += nspecial[i][1];
-  }
-
-  // cycle buffer around ring of procs back to self
-  // when receive buffer, scan list of 1-2 neighbors for atoms I own
-  // when find one, add its neighbors to 1-3 list
-  //   increment the count in buf(i+4)
-  //   exclude the atom whose tag = original
-  //   this process may include duplicates but they will be culled later
-
-  comm->ring(size,sizeof(tagint),buf,4,ring_four,buf,(void *)this);
-
-  // fill onethree with buffer values that have been returned to me
-  // sanity check: accumulated buf[i+3] count should equal
-  //   nspecial[i][1] for each atom
-
-  j = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (buf[j+3] != nspecial[i][1])
-      error->one(FLERR,"1-3 bond count is inconsistent");
-    j += 4 + nspecial[i][0];
-    for (k = 0; k < nspecial[i][1]; k++)
-      onethree[i][k] = buf[j++];
-  }
-
-  memory->destroy(buf);
-
   // done if special_bond weights for 1-4 are set to 1.0
 
   if (force->special_lj[3] == 1.0 && force->special_coul[3] == 1.0) {
@@ -304,117 +129,408 @@ void Special::build()
     if (force->special_angle) angle_trim();
     combine();
     fix_alteration();
+    memory->destroy(procowner);
+    memory->destroy(atomIDs);
+    timer_output(time1);
     return;
   }
 
-  // -----------------------------------------------------
-  // compute nspecial[i][2] = # of 1-4 neighbors of atom i
-  // -----------------------------------------------------
-
-  // nbufmax = largest buffer needed to hold info from any proc
-  // info for each atom = 2 scalars + list of 1-3 neighbors
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++) nbuf += 2 + nspecial[i][1];
-  memory->create(buf,nbuf,"special:buf");
-
-  // fill buffer with:
-  // (1) = counter for 1-4 neighbors, initialized to 0
-  // (2) = # of 1-3 neighbors
-  // (3:N) = list of 1-3 neighbors
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    buf[size++] = 0;
-    buf[size++] = nspecial[i][1];
-    for (j = 0; j < nspecial[i][1]; j++) buf[size++] = onethree[i][j];
-  }
-
-  // cycle buffer around ring of procs back to self
-  // when receive buffer, scan list of 1-3 neighbors for atoms I own
-  // when find one, increment 1-4 count by # of 1-2 neighbors of my atom
-  //   may include duplicates and original atom but they will be culled later
-
-  comm->ring(size,sizeof(tagint),buf,5,ring_five,buf,(void *)this);
-
-  // extract count from buffer that has cycled back to me
-  // nspecial[i][2] = # of 1-4 neighbors of atom i
-
-  j = 0;
-  for (i = 0; i < nlocal; i++) {
-    nspecial[i][2] = buf[j];
-    j += 2 + nspecial[i][1];
-  }
-
-  memory->destroy(buf);
-
-  // ----------------------------------------------------
+  // tally nspecial[i][2] = # of 1-4 neighbors of atom i
   // create onefour[i] = list of 1-4 neighbors for atom i
-  // ----------------------------------------------------
 
-  max = 0;
-  for (i = 0; i < nlocal; i++) max = MAX(max,nspecial[i][2]);
-  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  onefour_build();
+
+  // print max # of 1-4 neighbors
 
   if (me == 0) {
     if (screen) fprintf(screen,"  %d = max # of 1-4 neighbors\n",maxall);
     if (logfile) fprintf(logfile,"  %d = max # of 1-4 neighbors\n",maxall);
   }
 
-  memory->create(onefour,nlocal,maxall,"special:onefour");
-
-  // nbufmax = largest buffer needed to hold info from any proc
-  // info for each atom = 3 scalars + list of 1-3 neighs + list of 1-4 neighs
-
-  nbuf = 0;
-  for (i = 0; i < nlocal; i++)
-    nbuf += 3 + nspecial[i][1] + nspecial[i][2];
-  memory->create(buf,nbuf,"special:buf");
-
-  // fill buffer with:
-  // (1) = # of 1-3 neighbors
-  // (2) = # of 1-4 neighbors
-  // (3) = counter for 1-4 neighbors, initialized to 0
-  // (4:N) = list of 1-3 neighbors
-  // (N+1:2N) space for list of 1-4 neighbors
-
-  size = 0;
-  for (i = 0; i < nlocal; i++) {
-    buf[size++] = nspecial[i][1];
-    buf[size++] = nspecial[i][2];
-    buf[size++] = 0;
-    for (j = 0; j < nspecial[i][1]; j++) buf[size++] = onethree[i][j];
-    size += nspecial[i][2];
-  }
-
-  // cycle buffer around ring of procs back to self
-  // when receive buffer, scan list of 1-3 neighbors for atoms I own
-  // when find one, add its neighbors to 1-4 list
-  //   incrementing the count in buf(i+4)
-  //   this process may include duplicates but they will be culled later
-
-  comm->ring(size,sizeof(tagint),buf,6,ring_six,buf,(void *)this);
-
-  // fill onefour with buffer values that have been returned to me
-  // sanity check: accumulated buf[i+2] count should equal
-  //  nspecial[i][2] for each atom
-
-  j = 0;
-  for (i = 0; i < nlocal; i++) {
-    if (buf[j+2] != nspecial[i][2])
-      error->one(FLERR,"1-4 bond count is inconsistent");
-    j += 3 + nspecial[i][1];
-    for (k = 0; k < nspecial[i][2]; k++)
-      onefour[i][k] = buf[j++];
-  }
-
-  memory->destroy(buf);
+  // finish processing the onetwo, onethree, onefour lists
 
   dedup();
   if (force->special_angle) angle_trim();
   if (force->special_dihedral) dihedral_trim();
   combine();
   fix_alteration();
+  memory->destroy(procowner);
+  memory->destroy(atomIDs);
+
+  timer_output(time1);
+}
+
+/* ----------------------------------------------------------------------
+   setup atomIDs and procowner
+------------------------------------------------------------------------- */
+
+void Special::atom_owners()
+{
+  tagint *tag = atom->tag;
+  int nlocal = atom->nlocal;
+
+  int *proclist;
+  memory->create(proclist,nlocal,"special:proclist");
+  IDRvous *idbuf = (IDRvous *)
+    memory->smalloc((bigint) nlocal*sizeof(IDRvous),"special:idbuf");
+
+  // setup input buf for rendezvous comm
+  // one datum for each owned atom: datum = owning proc, atomID
+  // each proc assigned every 1/Pth atom
+
+  for (int i = 0; i < nlocal; i++) {
+    proclist[i] = tag[i] % nprocs;
+    idbuf[i].me = me;
+    idbuf[i].atomID = tag[i];
+  }
+
+  // perform rendezvous operation
+
+  char *buf;
+  comm->rendezvous(RVOUS,nlocal,(char *) idbuf,sizeof(IDRvous),0,proclist,
+                   rendezvous_ids,0,buf,0,(void *) this);
+
+  memory->destroy(proclist);
+  memory->sfree(idbuf);
+}
+
+/* ----------------------------------------------------------------------
+   onetwo build when newton_bond flag on
+   uses rendezvous comm
+------------------------------------------------------------------------- */
+
+void Special::onetwo_build_newton()
+{
+  int i,j,m;
+
+  tagint *tag = atom->tag;
+  int *num_bond = atom->num_bond;
+  tagint **bond_atom = atom->bond_atom;
+  int **nspecial = atom->nspecial;
+  int nlocal = atom->nlocal;
+
+  // nsend = # of my datums to send
+
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < num_bond[i]; j++) {
+      m = atom->map(bond_atom[i][j]);
+      if (m < 0 || m >= nlocal) nsend++;
+    }
+  }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  PairRvous *inbuf = (PairRvous *)
+    memory->smalloc((bigint) nsend*sizeof(PairRvous),"special:inbuf");
+
+  // setup input buf to rendezvous comm
+  // one datum for each unowned bond partner: bond partner ID, atomID
+  // owning proc for each datum = bond partner ID % nprocs
+
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < num_bond[i]; j++) {
+      m = atom->map(bond_atom[i][j]);
+      if (m >= 0 && m < nlocal) continue;
+      proclist[nsend] = bond_atom[i][j] % nprocs;
+      inbuf[nsend].atomID = bond_atom[i][j];
+      inbuf[nsend].partnerID = tag[i];
+      nsend++;
+    }
+  }
+
+  // perform rendezvous operation
+
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PairRvous),
+                                 0,proclist,
+                                 rendezvous_pairs,0,buf,sizeof(PairRvous),
+                                 (void *) this);
+  PairRvous *outbuf = (PairRvous *) buf;
+
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
+
+  // set nspecial[0] and onetwo for all owned atoms
+  // based on owned info plus rendezvous output info
+  // output datums = pairs of atoms that are 1-2 neighbors
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < num_bond[i]; j++) {
+      nspecial[i][0]++;
+      m = atom->map(bond_atom[i][j]);
+      if (m >= 0 && m < nlocal) nspecial[m][0]++;
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    nspecial[i][0]++;
+  }
+
+  int max = 0;
+  for (i = 0; i < nlocal; i++)
+    max = MAX(max,nspecial[i][0]);
+
+  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  memory->create(onetwo,nlocal,maxall,"special:onetwo");
+
+  for (i = 0; i < nlocal; i++) nspecial[i][0] = 0;
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < num_bond[i]; j++) {
+      onetwo[i][nspecial[i][0]++] = bond_atom[i][j];
+      m = atom->map(bond_atom[i][j]);
+      if (m >= 0 && m < nlocal) onetwo[m][nspecial[m][0]++] = tag[i];
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    onetwo[i][nspecial[i][0]++] = outbuf[m].partnerID;
+  }
+
+  memory->sfree(outbuf);
+}
+
+/* ----------------------------------------------------------------------
+   onetwo build with newton_bond flag off
+   no need for rendezvous comm
+------------------------------------------------------------------------- */
+
+void Special::onetwo_build_newton_off()
+{
+  int i,j;
+
+  int *num_bond = atom->num_bond;
+  tagint **bond_atom = atom->bond_atom;
+  int **nspecial = atom->nspecial;
+  int nlocal = atom->nlocal;
+
+  int max = 0;
+  for (i = 0; i < nlocal; i++)
+    max = MAX(max,num_bond[i]);
+
+  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  memory->create(onetwo,nlocal,maxall,"special:onetwo");
+
+  // nsend = # of my datums to send
+  // include nlocal datums with owner of each atom
+
+  for (i = 0; i < nlocal; i++) {
+    nspecial[i][0] = num_bond[i];
+    for (j = 0; j < num_bond[i]; j++)
+      onetwo[i][j] = bond_atom[i][j];
+  }
+}
+
+/* ----------------------------------------------------------------------
+   onethree build
+   uses rendezvous comm
+------------------------------------------------------------------------- */
+
+void Special::onethree_build()
+{
+  int i,j,k,m,proc;
+
+  int **nspecial = atom->nspecial;
+  int nlocal = atom->nlocal;
+
+  // nsend = # of my datums to send
+
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][0]; j++) {
+      m = atom->map(onetwo[i][j]);
+      if (m < 0 || m >= nlocal) nsend += nspecial[i][0]-1;
+    }
+  }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  PairRvous *inbuf = (PairRvous *)
+    memory->smalloc((bigint) nsend*sizeof(PairRvous),"special:inbuf");
+
+  // setup input buf to rendezvous comm
+  // datums = pairs of onetwo partners where either is unknown
+  //          these pairs are onethree neighbors
+  //          datum = onetwo ID, onetwo ID
+  // owning proc for each datum = onetwo ID % nprocs
+
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][0]; j++) {
+      m = atom->map(onetwo[i][j]);
+      if (m >= 0 && m < nlocal) continue;
+      proc = onetwo[i][j] % nprocs;
+      for (k = 0; k < nspecial[i][0]; k++) {
+        if (j == k) continue;
+        proclist[nsend] = proc;
+        inbuf[nsend].atomID = onetwo[i][j];
+        inbuf[nsend].partnerID = onetwo[i][k];
+        nsend++;
+      }
+    }
+  }
+
+  // perform rendezvous operation
+
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PairRvous),
+                                 0,proclist,
+                                 rendezvous_pairs,0,buf,sizeof(PairRvous),
+                                 (void *) this);
+  PairRvous *outbuf = (PairRvous *) buf;
+
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
+
+  // set nspecial[1] and onethree for all owned atoms
+  // based on owned info plus rendezvous output info
+  // output datums = pairs of atoms that are 1-3 neighbors
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][0]; j++) {
+      m = atom->map(onetwo[i][j]);
+      if (m >= 0 && m < nlocal) nspecial[m][1] += nspecial[i][0]-1;
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    nspecial[i][1]++;
+  }
+
+  int max = 0;
+  for (i = 0; i < nlocal; i++)
+    max = MAX(max,nspecial[i][1]);
+
+  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  memory->create(onethree,nlocal,maxall,"special:onethree");
+
+  for (i = 0; i < nlocal; i++) nspecial[i][1] = 0;
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][0]; j++) {
+      m = atom->map(onetwo[i][j]);
+      if (m < 0 || m >= nlocal) continue;
+      for (k = 0; k < nspecial[i][0]; k++) {
+        if (j == k) continue;
+        onethree[m][nspecial[m][1]++] = onetwo[i][k];
+      }
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    onethree[i][nspecial[i][1]++] = outbuf[m].partnerID;
+  }
+
+  memory->sfree(outbuf);
+}
+
+/* ----------------------------------------------------------------------
+   onefour build
+   uses rendezvous comm
+------------------------------------------------------------------------- */
+
+void Special::onefour_build()
+{
+  int i,j,k,m,proc;
+
+  int **nspecial = atom->nspecial;
+  int nlocal = atom->nlocal;
+
+  // nsend = # of my datums to send
+
+  int nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][1]; j++) {
+      m = atom->map(onethree[i][j]);
+      if (m < 0 || m >= nlocal) nsend += nspecial[i][0];
+    }
+  }
+
+  int *proclist;
+  memory->create(proclist,nsend,"special:proclist");
+  PairRvous *inbuf = (PairRvous *)
+    memory->smalloc((bigint) nsend*sizeof(PairRvous),"special:inbuf");
+
+  // setup input buf to rendezvous comm
+  // datums = pairs of onethree and onetwo partners where onethree is unknown
+  //          these pairs are onefour neighbors
+  //          datum = onetwo ID, onetwo ID
+  // owning proc for each datum = onethree ID % nprocs
+
+  nsend = 0;
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][1]; j++) {
+      m = atom->map(onethree[i][j]);
+      if (m >= 0 && m < nlocal) continue;
+      proc = onethree[i][j] % nprocs;
+      for (k = 0; k < nspecial[i][0]; k++) {
+        proclist[nsend] = proc;
+        inbuf[nsend].atomID = onethree[i][j];
+        inbuf[nsend].partnerID = onetwo[i][k];
+        nsend++;
+      }
+    }
+  }
+
+  // perform rendezvous operation
+
+  char *buf;
+  int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PairRvous),
+                                 0,proclist,
+                                 rendezvous_pairs,0,buf,sizeof(PairRvous),
+                                 (void *) this);
+  PairRvous *outbuf = (PairRvous *) buf;
+
+  memory->destroy(proclist);
+  memory->sfree(inbuf);
+
+  // set nspecial[2] and onefour for all owned atoms
+  // based on owned info plus rendezvous output info
+  // output datums = pairs of atoms that are 1-4 neighbors
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][1]; j++) {
+      m = atom->map(onethree[i][j]);
+      if (m >= 0 && m < nlocal) nspecial[m][2] += nspecial[i][0];
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    nspecial[i][2]++;
+  }
+
+  int max = 0;
+  for (i = 0; i < nlocal; i++)
+    max = MAX(max,nspecial[i][2]);
+
+  MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+  memory->create(onefour,nlocal,maxall,"special:onefour");
+
+  for (i = 0; i < nlocal; i++) nspecial[i][2] = 0;
+
+  for (i = 0; i < nlocal; i++) {
+    for (j = 0; j < nspecial[i][1]; j++) {
+      m = atom->map(onethree[i][j]);
+      if (m < 0 || m >= nlocal) continue;
+      for (k = 0; k < nspecial[i][0]; k++) {
+        onefour[m][nspecial[m][2]++] = onetwo[i][k];
+      }
+    }
+  }
+
+  for (m = 0; m < nreturn; m++) {
+    i = atom->map(outbuf[m].atomID);
+    onefour[i][nspecial[i][2]++] = outbuf[m].partnerID;
+  }
+
+  memory->sfree(outbuf);
 }
 
 /* ----------------------------------------------------------------------
@@ -659,21 +775,24 @@ void Special::combine()
    trim list of 1-3 neighbors by checking defined angles
    delete a 1-3 neigh if they are not end atoms of a defined angle
      and if they are not 1,3 or 2,4 atoms of a defined dihedral
+   uses rendezvous comm
 ------------------------------------------------------------------------- */
 
 void Special::angle_trim()
 {
-  int i,j,m,n;
+  int i,j,k,m;;
 
   int *num_angle = atom->num_angle;
   int *num_dihedral = atom->num_dihedral;
   tagint **angle_atom1 = atom->angle_atom1;
+  tagint **angle_atom2 = atom->angle_atom2;
   tagint **angle_atom3 = atom->angle_atom3;
   tagint **dihedral_atom1 = atom->dihedral_atom1;
   tagint **dihedral_atom2 = atom->dihedral_atom2;
   tagint **dihedral_atom3 = atom->dihedral_atom3;
   tagint **dihedral_atom4 = atom->dihedral_atom4;
   int **nspecial = atom->nspecial;
+  tagint *tag = atom->tag;
   int nlocal = atom->nlocal;
 
   // stats on old 1-3 neighbor counts
@@ -692,75 +811,221 @@ void Special::angle_trim()
               "  %g = # of 1-3 neighbors before angle trim\n",allcount);
   }
 
-  // if angles or dihedrals are defined,
-  // flag each 1-3 neigh if it appears in an angle or dihedral
+  // if angles or dihedrals are defined
+  // rendezvous angle 1-3 and dihedral 1-3,2-4 pairs
 
   if ((num_angle && atom->nangles) || (num_dihedral && atom->ndihedrals)) {
 
-    // dflag = flag for 1-3 neighs of all owned atoms
-
-    int maxcount = 0;
-    for (i = 0; i < nlocal; i++) maxcount = MAX(maxcount,nspecial[i][1]);
-    memory->create(dflag,nlocal,maxcount,"special::dflag");
+    // nsend = # of my datums to send
+    // latter is only for angles or dihedrlas where I own atom2 (newton bond off)
 
+    int nsend = 0;
     for (i = 0; i < nlocal; i++) {
-      n = nspecial[i][1];
-      for (j = 0; j < n; j++) dflag[i][j] = 0;
-    }
-
-    // nbufmax = largest buffer needed to hold info from any proc
-    // info for each atom = list of 1,3 atoms in each angle stored by atom
-    //   and list of 1,3 and 2,4 atoms in each dihedral stored by atom
-
-    int nbuf = 0;
-    for (i = 0; i < nlocal; i++) {
-      if (num_angle && atom->nangles) nbuf += 2*num_angle[i];
-      if (num_dihedral && atom->ndihedrals) nbuf += 2*2*num_dihedral[i];
-    }
-    int *buf;
-    memory->create(buf,nbuf,"special:buf");
-
-    // fill buffer with list of 1,3 atoms in each angle
-    // and with list of 1,3 and 2,4 atoms in each dihedral
-
-    int size = 0;
-    if (num_angle && atom->nangles)
-      for (i = 0; i < nlocal; i++)
+      if (num_angle) {
         for (j = 0; j < num_angle[i]; j++) {
-          buf[size++] = angle_atom1[i][j];
-          buf[size++] = angle_atom3[i][j];
+          if (tag[i] != angle_atom2[i][j]) continue;
+          m = atom->map(angle_atom1[i][j]);
+          if (m < 0 || m >= nlocal) nsend++;
+          m = atom->map(angle_atom3[i][j]);
+          if (m < 0 || m >= nlocal) nsend++;
         }
+      }
 
-    if (num_dihedral && atom->ndihedrals)
-      for (i = 0; i < nlocal; i++)
+      if (num_dihedral) {
         for (j = 0; j < num_dihedral[i]; j++) {
-          buf[size++] = dihedral_atom1[i][j];
-          buf[size++] = dihedral_atom3[i][j];
-          buf[size++] = dihedral_atom2[i][j];
-          buf[size++] = dihedral_atom4[i][j];
+          if (tag[i] != dihedral_atom2[i][j]) continue;
+          m = atom->map(dihedral_atom1[i][j]);
+          if (m < 0 || m >= nlocal) nsend++;
+          m = atom->map(dihedral_atom3[i][j]);
+          if (m < 0 || m >= nlocal) nsend++;
+          m = atom->map(dihedral_atom4[i][j]);
+          if (m < 0 || m >= nlocal) nsend++;
         }
-
-    // cycle buffer around ring of procs back to self
-    // when receive buffer, scan list of 1,3 atoms looking for atoms I own
-    // when find one, scan its 1-3 neigh list and mark I,J as in an angle
-
-    comm->ring(size,sizeof(tagint),buf,7,ring_seven,NULL,(void *)this);
-
-    // delete 1-3 neighbors if they are not flagged in dflag
-
-    for (i = 0; i < nlocal; i++) {
-      m = 0;
-      for (j = 0; j < nspecial[i][1]; j++)
-        if (dflag[i][j]) onethree[i][m++] = onethree[i][j];
-      nspecial[i][1] = m;
+      }
     }
 
-    // clean up
+    int *proclist;
+    memory->create(proclist,nsend,"special:proclist");
+    PairRvous *inbuf = (PairRvous *)
+      memory->smalloc((bigint) nsend*sizeof(PairRvous),"special:inbuf");
 
-    memory->destroy(dflag);
-    memory->destroy(buf);
+    // setup input buf to rendezvous comm
+    // datums = pairs of onetwo partners where either is unknown
+    //          these pairs are onethree neighbors
+    //          datum = onetwo ID, onetwo ID
+    // owning proc for each datum = onetwo ID % nprocs
 
-  // if no angles or dihedrals are defined, delete all 1-3 neighs
+    nsend = 0;
+    for (i = 0; i < nlocal; i++) {
+      if (num_angle) {
+        for (j = 0; j < num_angle[i]; j++) {
+          if (tag[i] != angle_atom2[i][j]) continue;
+
+          m = atom->map(angle_atom1[i][j]);
+          if (m < 0 || m >= nlocal) {
+            proclist[nsend] = angle_atom1[i][j] % nprocs;
+            inbuf[nsend].atomID = angle_atom1[i][j];
+            inbuf[nsend].partnerID = angle_atom3[i][j];
+            nsend++;
+          }
+
+          m = atom->map(angle_atom3[i][j]);
+          if (m < 0 || m >= nlocal) {
+            proclist[nsend] = angle_atom3[i][j] % nprocs;
+            inbuf[nsend].atomID = angle_atom3[i][j];
+            inbuf[nsend].partnerID = angle_atom1[i][j];
+            nsend++;
+          }
+        }
+      }
+
+      if (num_dihedral) {
+        for (j = 0; j < num_dihedral[i]; j++) {
+          if (tag[i] != dihedral_atom2[i][j]) continue;
+
+          m = atom->map(dihedral_atom1[i][j]);
+          if (m < 0 || m >= nlocal) {
+            proclist[nsend] = dihedral_atom1[i][j] % nprocs;
+            inbuf[nsend].atomID = dihedral_atom1[i][j];
+            inbuf[nsend].partnerID = dihedral_atom3[i][j];
+            nsend++;
+          }
+
+          m = atom->map(dihedral_atom3[i][j]);
+          if (m < 0 || m >= nlocal) {
+            proclist[nsend] = dihedral_atom3[i][j] % nprocs;
+            inbuf[nsend].atomID = dihedral_atom3[i][j];
+            inbuf[nsend].partnerID = dihedral_atom1[i][j];
+            nsend++;
+          }
+
+          m = atom->map(dihedral_atom4[i][j]);
+          if (m < 0 || m >= nlocal) {
+            proclist[nsend] = dihedral_atom4[i][j] % nprocs;
+            inbuf[nsend].atomID = dihedral_atom4[i][j];
+            inbuf[nsend].partnerID = dihedral_atom2[i][j];
+            nsend++;
+          }
+        }
+      }
+    }
+
+    // perform rendezvous operation
+
+    char *buf;
+    int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PairRvous),
+                                   0,proclist,
+                                   rendezvous_pairs,0,buf,sizeof(PairRvous),
+                                   (void *) this);
+    PairRvous *outbuf = (PairRvous *) buf;
+
+    memory->destroy(proclist);
+    memory->sfree(inbuf);
+
+    // flag all onethree atoms to keep
+
+    int max = 0;
+    for (i = 0; i < nlocal; i++)
+      max = MAX(max,nspecial[i][1]);
+    MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+
+    int **flag;
+    memory->create(flag,nlocal,maxall,"special:flag");
+
+    for (i = 0; i < nlocal; i++)
+      for (j = 0; j < nspecial[i][1]; j++)
+        flag[i][j] = 0;
+
+    // reset nspecial[1] and onethree for all owned atoms based on output info
+    // based on owned info plus rendezvous output info
+    // output datums = pairs of atoms that are 1-3 neighbors
+
+    for (i = 0; i < nlocal; i++) {
+      if (num_angle) {
+        for (j = 0; j < num_angle[i]; j++) {
+          if (tag[i] != angle_atom2[i][j]) continue;
+
+          m = atom->map(angle_atom1[i][j]);
+          if (m >= 0 && m < nlocal) {
+            for (k = 0; k < nspecial[m][1]; k++)
+              if (onethree[m][k] == angle_atom3[i][j]) {
+                flag[m][k] = 1;
+                break;
+              }
+          }
+
+          m = atom->map(angle_atom3[i][j]);
+          if (m >= 0 && m < nlocal) {
+            for (k = 0; k < nspecial[m][1]; k++)
+              if (onethree[m][k] == angle_atom1[i][j]) {
+                flag[m][k] = 1;
+                break;
+              }
+          }
+        }
+      }
+
+      if (num_dihedral) {
+        for (j = 0; j < num_dihedral[i]; j++) {
+          if (tag[i] != dihedral_atom2[i][j]) continue;
+
+          m = atom->map(dihedral_atom1[i][j]);
+          if (m >= 0 && m < nlocal) {
+            for (k = 0; k < nspecial[m][1]; k++)
+              if (onethree[m][k] == dihedral_atom3[i][j]) {
+                flag[m][k] = 1;
+                break;
+              }
+          }
+
+          m = atom->map(dihedral_atom3[i][j]);
+          if (m >= 0 && m < nlocal) {
+            for (k = 0; k < nspecial[m][1]; k++)
+              if (onethree[m][k] == dihedral_atom1[i][j]) {
+                flag[m][k] = 1;
+                break;
+              }
+          }
+
+          m = atom->map(dihedral_atom4[i][j]);
+          if (m >= 0 && m < nlocal) {
+            for (k = 0; k < nspecial[m][1]; k++)
+              if (onethree[m][k] == dihedral_atom2[i][j]) {
+                flag[m][k] = 1;
+                break;
+              }
+          }
+        }
+      }
+    }
+
+    for (m = 0; m < nreturn; m++) {
+      i = atom->map(outbuf[m].atomID);
+      for (k = 0; k < nspecial[i][1]; k++)
+        if (onethree[i][k] == outbuf[m].partnerID) {
+          flag[i][k] = 1;
+          break;
+        }
+    }
+
+    memory->destroy(outbuf);
+
+    // use flag values to compress onefour list for each atom
+
+    for (i = 0; i < nlocal; i++) {
+      j = 0;
+      while (j < nspecial[i][1]) {
+        if (flag[i][j] == 0) {
+          onethree[i][j] = onethree[i][nspecial[i][1]-1];
+          flag[i][j] = flag[i][nspecial[i][1]-1];
+          nspecial[i][1]--;
+        } else j++;
+      }
+    }
+
+    memory->destroy(flag);
+
+    // if no angles or dihedrals are defined, delete all 1-3 neighs
 
   } else {
     for (i = 0; i < nlocal; i++) nspecial[i][1] = 0;
@@ -783,18 +1048,21 @@ void Special::angle_trim()
 }
 
 /* ----------------------------------------------------------------------
-   trim list of 1-4 neighbors by checking defined dihedrals
+   trim list of 1-4 neighbors by checking all defined dihedrals
    delete a 1-4 neigh if they are not end atoms of a defined dihedral
+   uses rendezvous comm
 ------------------------------------------------------------------------- */
 
 void Special::dihedral_trim()
 {
-  int i,j,m,n;
+  int i,j,k,m;
 
   int *num_dihedral = atom->num_dihedral;
   tagint **dihedral_atom1 = atom->dihedral_atom1;
+  tagint **dihedral_atom2 = atom->dihedral_atom2;
   tagint **dihedral_atom4 = atom->dihedral_atom4;
   int **nspecial = atom->nspecial;
+  tagint *tag = atom->tag;
   int nlocal = atom->nlocal;
 
   // stats on old 1-4 neighbor counts
@@ -813,57 +1081,133 @@ void Special::dihedral_trim()
               "  %g = # of 1-4 neighbors before dihedral trim\n",allcount);
   }
 
-  // if dihedrals are defined, flag each 1-4 neigh if it appears in a dihedral
+  // if dihedrals are defined, rendezvous the dihedral 1-4 pairs
 
   if (num_dihedral && atom->ndihedrals) {
 
-    // dflag = flag for 1-4 neighs of all owned atoms
-
-    int maxcount = 0;
-    for (i = 0; i < nlocal; i++) maxcount = MAX(maxcount,nspecial[i][2]);
-    memory->create(dflag,nlocal,maxcount,"special::dflag");
+    // nsend = # of my datums to send
 
+    int nsend = 0;
     for (i = 0; i < nlocal; i++) {
-      n = nspecial[i][2];
-      for (j = 0; j < n; j++) dflag[i][j] = 0;
-    }
-
-    // nbufmax = largest buffer needed to hold info from any proc
-    // info for each atom = list of 1,4 atoms in each dihedral stored by atom
-
-    int nbuf = 0;
-    for (i = 0; i < nlocal; i++) nbuf += 2*num_dihedral[i];
-    int *buf;
-    memory->create(buf,nbuf,"special:buf");
-
-    // fill buffer with list of 1,4 atoms in each dihedral
-
-    int size = 0;
-    for (i = 0; i < nlocal; i++)
       for (j = 0; j < num_dihedral[i]; j++) {
-        buf[size++] = dihedral_atom1[i][j];
-        buf[size++] = dihedral_atom4[i][j];
+        if (tag[i] != dihedral_atom2[i][j]) continue;
+        m = atom->map(dihedral_atom1[i][j]);
+        if (m < 0 || m >= nlocal) nsend++;
+        m = atom->map(dihedral_atom4[i][j]);
+        if (m < 0 || m >= nlocal) nsend++;
       }
-
-    // cycle buffer around ring of procs back to self
-    // when receive buffer, scan list of 1,4 atoms looking for atoms I own
-    // when find one, scan its 1-4 neigh list and mark I,J as in a dihedral
-
-    comm->ring(size,sizeof(tagint),buf,8,ring_eight,NULL,(void *)this);
-
-    // delete 1-4 neighbors if they are not flagged in dflag
-
-    for (i = 0; i < nlocal; i++) {
-      m = 0;
-      for (j = 0; j < nspecial[i][2]; j++)
-        if (dflag[i][j]) onefour[i][m++] = onefour[i][j];
-      nspecial[i][2] = m;
     }
 
-    // clean up
+    int *proclist;
+    memory->create(proclist,nsend,"special:proclist");
+    PairRvous *inbuf = (PairRvous *)
+      memory->smalloc((bigint) nsend*sizeof(PairRvous),"special:inbuf");
 
-    memory->destroy(dflag);
-    memory->destroy(buf);
+    // setup input buf to rendezvous comm
+    // datums = pairs of onefour atom IDs in a dihedral defined for my atoms
+    //          only dihedrals where I own atom2 (in case newton_bond off)
+    //          datum = atom1 ID and atom4 ID
+    //          send the datum twice, to owner of atom1 ID and atom4 ID
+    // owning procs for each datum = atom1 or atom4 ID % nprocs
+
+    nsend = 0;
+    for (i = 0; i < nlocal; i++) {
+      for (j = 0; j < num_dihedral[i]; j++) {
+        if (tag[i] != dihedral_atom2[i][j]) continue;
+
+        m = atom->map(dihedral_atom1[i][j]);
+        if (m < 0 || m >= nlocal) {
+          proclist[nsend] = dihedral_atom1[i][j] % nprocs;
+          inbuf[nsend].atomID = dihedral_atom1[i][j];
+          inbuf[nsend].partnerID = dihedral_atom4[i][j];
+          nsend++;
+        }
+
+        m = atom->map(dihedral_atom4[i][j]);
+        if (m < 0 || m >= nlocal) {
+          proclist[nsend] = dihedral_atom4[i][j] % nprocs;
+          inbuf[nsend].atomID = dihedral_atom4[i][j];
+          inbuf[nsend].partnerID = dihedral_atom1[i][j];
+          nsend++;
+        }
+      }
+    }
+
+    // perform rendezvous operation
+
+    char *buf;
+    int nreturn = comm->rendezvous(RVOUS,nsend,(char *) inbuf,sizeof(PairRvous),
+                                   0,proclist,
+                                   rendezvous_pairs,0,buf,sizeof(PairRvous),
+                                   (void *) this);
+    PairRvous *outbuf = (PairRvous *) buf;
+
+    memory->destroy(proclist);
+    memory->sfree(inbuf);
+
+    // flag all of my onefour IDs to keep
+
+    int max = 0;
+    for (i = 0; i < nlocal; i++)
+      max = MAX(max,nspecial[i][2]);
+    MPI_Allreduce(&max,&maxall,1,MPI_INT,MPI_MAX,world);
+
+    int **flag;
+    memory->create(flag,nlocal,maxall,"special:flag");
+
+    for (i = 0; i < nlocal; i++)
+      for (j = 0; j < nspecial[i][2]; j++)
+        flag[i][j] = 0;
+
+    for (i = 0; i < nlocal; i++) {
+      for (j = 0; j < num_dihedral[i]; j++) {
+        if (tag[i] != dihedral_atom2[i][j]) continue;
+
+        m = atom->map(dihedral_atom1[i][j]);
+        if (m >= 0 && m < nlocal) {
+          for (k = 0; k < nspecial[m][2]; k++)
+            if (onefour[m][k] == dihedral_atom4[i][j]) {
+              flag[m][k] = 1;
+              break;
+            }
+        }
+
+        m = atom->map(dihedral_atom4[i][j]);
+        if (m >= 0 && m < nlocal) {
+          for (k = 0; k < nspecial[m][2]; k++)
+            if (onefour[m][k] == dihedral_atom1[i][j]) {
+              flag[m][k] = 1;
+              break;
+            }
+        }
+      }
+    }
+
+    for (m = 0; m < nreturn; m++) {
+      i = atom->map(outbuf[m].atomID);
+      for (k = 0; k < nspecial[i][2]; k++)
+        if (onefour[i][k] == outbuf[m].partnerID) {
+          flag[i][k] = 1;
+          break;
+        }
+    }
+
+    memory->destroy(outbuf);
+
+    // use flag values to compress onefour list for each atom
+
+    for (i = 0; i < nlocal; i++) {
+      j = 0;
+      while (j < nspecial[i][2]) {
+        if (flag[i][j] == 0) {
+          onefour[i][j] = onefour[i][nspecial[i][2]-1];
+          flag[i][j] = flag[i][nspecial[i][2]-1];
+          nspecial[i][2]--;
+        } else j++;
+      }
+    }
+
+    memory->destroy(flag);
 
   // if no dihedrals are defined, delete all 1-4 neighs
 
@@ -888,262 +1232,95 @@ void Special::dihedral_trim()
 }
 
 /* ----------------------------------------------------------------------
-   when receive buffer, scan tags for atoms I own
-   when find one, increment nspecial count for that atom
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N IDRvous datums
+   no outbuf
 ------------------------------------------------------------------------- */
 
-void Special::ring_one(int ndatum, char *cbuf, void *ptr)
+int Special::rendezvous_ids(int n, char *inbuf,
+                            int &flag, int *& /*proclist*/, char *& /*outbuf*/,
+                            void *ptr)
+{
+  Special *sptr = (Special *) ptr;
+  Memory *memory = sptr->memory;
+
+  int *procowner;
+  tagint *atomIDs;
+
+  memory->create(procowner,n,"special:procowner");
+  memory->create(atomIDs,n,"special:atomIDs");
+
+  IDRvous *in = (IDRvous *) inbuf;
+
+  for (int i = 0; i < n; i++) {
+    procowner[i] = in[i].me;
+    atomIDs[i] = in[i].atomID;
+  }
+
+  // store rendezvous data in Special class
+
+  sptr->nrvous = n;
+  sptr->procowner = procowner;
+  sptr->atomIDs = atomIDs;
+
+  // flag = 0: no second comm needed in rendezvous
+
+  flag = 0;
+  return 0;
+}
+
+
+/* ----------------------------------------------------------------------
+   process data for atoms assigned to me in rendezvous decomposition
+   inbuf = list of N PairRvous datums
+   outbuf = same list of N PairRvous datums, routed to different procs
+------------------------------------------------------------------------- */
+
+int Special::rendezvous_pairs(int n, char *inbuf,
+                             int &flag, int *&proclist, char *&outbuf,
+                             void *ptr)
 {
   Special *sptr = (Special *) ptr;
   Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
+  Memory *memory = sptr->memory;
+
+  // clear atom map so it can be used here as a hash table
+  // faster than an STL map for large atom counts
+
+  atom->map_clear();
+
+  // hash atom IDs stored in rendezvous decomposition
+
+  int nrvous = sptr->nrvous;
+  tagint *atomIDs = sptr->atomIDs;
+
+  for (int i = 0; i < nrvous; i++)
+    atom->map_one(atomIDs[i],i);
+
+  // proclist = owner of atomID in caller decomposition
+
+  PairRvous *in = (PairRvous *) inbuf;
+  int *procowner = sptr->procowner;
+  memory->create(proclist,n,"special:proclist");
 
-  tagint *buf = (tagint *) cbuf;
   int m;
-
-  for (int i = 0; i < ndatum; i++) {
-    m = atom->map(buf[i]);
-    if (m >= 0 && m < nlocal) nspecial[m][0]++;
+  for (int i = 0; i < n; i++) {
+    m = atom->map(in[i].atomID);
+    proclist[i] = procowner[m];
   }
-}
 
-/* ----------------------------------------------------------------------
-   when receive buffer, scan 2nd-atom tags for atoms I own
-   when find one, add 1st-atom tag to onetwo list for 2nd atom
-------------------------------------------------------------------------- */
+  outbuf = inbuf;
 
-void Special::ring_two(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int nlocal = atom->nlocal;
+  // re-create atom map
 
-  tagint **onetwo = sptr->onetwo;
-  int *count = sptr->count;
+  atom->map_init(0);
+  atom->nghost = 0;
+  atom->map_set();
 
-  tagint *buf = (tagint *) cbuf;
-  int m;
+  // flag = 1: outbuf = inbuf
 
-  for (int i = 1; i < ndatum; i += 2) {
-    m = atom->map(buf[i]);
-    if (m >= 0 && m < nlocal) onetwo[m][count[m]++] = buf[i-1];
-  }
-}
-
-/* ----------------------------------------------------------------------
-   when receive buffer, scan list of 1-2 neighbors for atoms I own
-   when find one, increment 1-3 count by # of 1-2 neighbors of my atom,
-     subtracting one since my list will contain original atom
-------------------------------------------------------------------------- */
-
-void Special::ring_three(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint *buf = (tagint *) cbuf;
-  int i,j,m,n,num12;
-
-  i = 0;
-  while (i < ndatum) {
-    n = buf[i];
-    num12 = buf[i+1];
-    for (j = 0; j < num12; j++) {
-      m = atom->map(buf[i+2+j]);
-      if (m >= 0 && m < nlocal)
-        n += nspecial[m][0] - 1;
-    }
-    buf[i] = n;
-    i += 2 + num12;
-  }
-}
-
-/* ----------------------------------------------------------------------
-  when receive buffer, scan list of 1-2 neighbors for atoms I own
-  when find one, add its neighbors to 1-3 list
-    increment the count in buf(i+4)
-    exclude the atom whose tag = original
-    this process may include duplicates but they will be culled later
-------------------------------------------------------------------------- */
-
-void Special::ring_four(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint **onetwo = sptr->onetwo;
-
-  tagint *buf = (tagint *) cbuf;
-  tagint original;
-  int i,j,k,m,n,num12,num13;
-
-  i = 0;
-  while (i < ndatum) {
-    original = buf[i];
-    num12 = buf[i+1];
-    num13 = buf[i+2];
-    n = buf[i+3];
-    for (j = 0; j < num12; j++) {
-      m = atom->map(buf[i+4+j]);
-      if (m >= 0 && m < nlocal)
-        for (k = 0; k < nspecial[m][0]; k++)
-          if (onetwo[m][k] != original)
-            buf[i+4+num12+(n++)] = onetwo[m][k];
-    }
-    buf[i+3] = n;
-    i += 4 + num12 + num13;
-  }
-}
-
-/* ----------------------------------------------------------------------
-   when receive buffer, scan list of 1-3 neighbors for atoms I own
-   when find one, increment 1-4 count by # of 1-2 neighbors of my atom
-     may include duplicates and original atom but they will be culled later
-------------------------------------------------------------------------- */
-
-void Special::ring_five(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint *buf = (tagint *) cbuf;
-  int i,j,m,n,num13;
-
-  i = 0;
-  while (i < ndatum) {
-    n = buf[i];
-    num13 = buf[i+1];
-    for (j = 0; j < num13; j++) {
-      m = atom->map(buf[i+2+j]);
-      if (m >= 0 && m < nlocal) n += nspecial[m][0];
-    }
-      buf[i] = n;
-      i += 2 + num13;
-  }
-}
-
-/* ----------------------------------------------------------------------
-   when receive buffer, scan list of 1-3 neighbors for atoms I own
-   when find one, add its neighbors to 1-4 list
-     incrementing the count in buf(i+4)
-     this process may include duplicates but they will be culled later
-------------------------------------------------------------------------- */
-
-void Special::ring_six(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint **onetwo = sptr->onetwo;
-
-  tagint *buf = (tagint *) cbuf;
-  int i,j,k,m,n,num13,num14;
-
-  i = 0;
-  while (i < ndatum) {
-    num13 = buf[i];
-    num14 = buf[i+1];
-    n = buf[i+2];
-    for (j = 0; j < num13; j++) {
-      m = atom->map(buf[i+3+j]);
-      if (m >= 0 && m < nlocal)
-        for (k = 0; k < nspecial[m][0]; k++)
-          buf[i+3+num13+(n++)] = onetwo[m][k];
-    }
-    buf[i+2] = n;
-    i += 3 + num13 + num14;
-  }
-}
-
-/* ----------------------------------------------------------------------
-   when receive buffer, scan list of 1,3 atoms looking for atoms I own
-   when find one, scan its 1-3 neigh list and mark I,J as in an angle
-------------------------------------------------------------------------- */
-
-void Special::ring_seven(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint **onethree = sptr->onethree;
-  int **dflag = sptr->dflag;
-
-  tagint *buf = (tagint *) cbuf;
-  tagint iglobal,jglobal;
-  int i,m,ilocal,jlocal;
-
-  i = 0;
-  while (i < ndatum) {
-    iglobal = buf[i];
-    jglobal = buf[i+1];
-    ilocal = atom->map(iglobal);
-    jlocal = atom->map(jglobal);
-    if (ilocal >= 0 && ilocal < nlocal)
-      for (m = 0; m < nspecial[ilocal][1]; m++)
-        if (jglobal == onethree[ilocal][m]) {
-          dflag[ilocal][m] = 1;
-          break;
-        }
-    if (jlocal >= 0 && jlocal < nlocal)
-      for (m = 0; m < nspecial[jlocal][1]; m++)
-        if (iglobal == onethree[jlocal][m]) {
-          dflag[jlocal][m] = 1;
-          break;
-        }
-    i += 2;
-  }
-}
-
-/* ----------------------------------------------------------------------
-   when receive buffer, scan list of 1,4 atoms looking for atoms I own
-   when find one, scan its 1-4 neigh list and mark I,J as in a dihedral
-------------------------------------------------------------------------- */
-
-void Special::ring_eight(int ndatum, char *cbuf, void *ptr)
-{
-  Special *sptr = (Special *) ptr;
-  Atom *atom = sptr->atom;
-  int **nspecial = atom->nspecial;
-  int nlocal = atom->nlocal;
-
-  tagint **onefour = sptr->onefour;
-  int **dflag = sptr->dflag;
-
-  tagint *buf = (tagint *) cbuf;
-  tagint iglobal,jglobal;
-  int i,m,ilocal,jlocal;
-
-  i = 0;
-  while (i < ndatum) {
-    iglobal = buf[i];
-    jglobal = buf[i+1];
-    ilocal = atom->map(iglobal);
-    jlocal = atom->map(jglobal);
-    if (ilocal >= 0 && ilocal < nlocal)
-      for (m = 0; m < nspecial[ilocal][2]; m++)
-        if (jglobal == onefour[ilocal][m]) {
-          dflag[ilocal][m] = 1;
-          break;
-        }
-    if (jlocal >= 0 && jlocal < nlocal)
-      for (m = 0; m < nspecial[jlocal][2]; m++)
-        if (iglobal == onefour[jlocal][m]) {
-          dflag[jlocal][m] = 1;
-          break;
-        }
-    i += 2;
-  }
+  flag = 1;
+  return n;
 }
 
 /* ----------------------------------------------------------------------
@@ -1159,3 +1336,15 @@ void Special::fix_alteration()
       modify->fix[ifix]->rebuild_special();
 }
 
+/* ----------------------------------------------------------------------
+   print timing output
+------------------------------------------------------------------------- */
+
+void Special::timer_output(double time1)
+{
+  double time2 = MPI_Wtime();
+  if (comm->me == 0) {
+    if (screen) fprintf(screen,"  special bonds CPU = %g secs\n",time2-time1);
+    if (logfile) fprintf(logfile,"  special bonds CPU = %g secs\n",time2-time1);
+  }
+}
diff --git a/src/special.h b/src/special.h
index 9f25200336..10d2609536 100644
--- a/src/special.h
+++ b/src/special.h
@@ -26,29 +26,43 @@ class Special : protected Pointers {
 
  private:
   int me,nprocs;
+  int maxall;
   tagint **onetwo,**onethree,**onefour;
 
-  // data used by ring callback methods
+  // data used by rendezvous callback methods
 
-  int *count;
-  int **dflag;
+  int nrvous;
+  tagint *atomIDs;
+  int *procowner;
+
+  struct IDRvous {
+    int me;
+    tagint atomID;
+  };
+
+  struct PairRvous {
+    tagint atomID,partnerID;
+  };
+
+  // private methods
+
+  void atom_owners();
+  void onetwo_build_newton();
+  void onetwo_build_newton_off();
+  void onethree_build();
+  void onefour_build();
 
   void dedup();
   void angle_trim();
   void dihedral_trim();
   void combine();
   void fix_alteration();
+  void timer_output(double);
 
-  // callback functions for ring communication
+  // callback functions for rendezvous communication
 
-  static void ring_one(int, char *, void *);
-  static void ring_two(int, char *, void *);
-  static void ring_three(int, char *, void *);
-  static void ring_four(int, char *, void *);
-  static void ring_five(int, char *, void *);
-  static void ring_six(int, char *, void *);
-  static void ring_seven(int, char *, void *);
-  static void ring_eight(int, char *, void *);
+  static int rendezvous_ids(int, char *, int &, int *&, char *&, void *);
+  static int rendezvous_pairs(int, char *, int &, int *&, char *&, void *);
 };
 
 }
diff --git a/src/thermo.cpp b/src/thermo.cpp
index ddbbd0f496..3e777edf82 100644
--- a/src/thermo.cpp
+++ b/src/thermo.cpp
@@ -380,9 +380,8 @@ void Thermo::compute(int flag)
       loc += sprintf(&line[loc],format[ifield],dvalue);
     else if (vtype[ifield] == INT)
       loc += sprintf(&line[loc],format[ifield],ivalue);
-    else if (vtype[ifield] == BIGINT) {
+    else if (vtype[ifield] == BIGINT)
       loc += sprintf(&line[loc],format[ifield],bivalue);
-    }
   }
 
   // print line to screen and logfile
diff --git a/src/variable.cpp b/src/variable.cpp
index c0e4dae7d0..56b66cad0d 100644
--- a/src/variable.cpp
+++ b/src/variable.cpp
@@ -1578,6 +1578,8 @@ double Variable::evaluate(char *str, Tree **tree, int ivar)
           newtree->nextra = 0;
           treestack[ntreestack++] = newtree;
 
+        } else if (nbracket == 1 && compute->local_flag) {
+          print_var_error(FLERR,"Cannot access local data via indexing",ivar);
         } else print_var_error(FLERR,
                                "Mismatched compute in variable formula",ivar);
 
@@ -2179,7 +2181,7 @@ double Variable::evaluate(char *str, Tree **tree, int ivar)
         if (tree) {
           Tree *newtree = new Tree();
           newtree->type = opprevious;
-          if (opprevious == UNARY) {
+          if ((opprevious == UNARY) || (opprevious == NOT)) {
             newtree->first = treestack[--ntreestack];
             newtree->second = NULL;
             newtree->nextra = 0;
diff --git a/src/velocity.cpp b/src/velocity.cpp
index 6d6027cc3c..32b08708cf 100644
--- a/src/velocity.cpp
+++ b/src/velocity.cpp
@@ -33,6 +33,7 @@
 #include "comm.h"
 #include "memory.h"
 #include "error.h"
+#include "utils.h"
 
 using namespace LAMMPS_NS;
 
@@ -709,19 +710,19 @@ void Velocity::zero(int /*narg*/, char **arg)
 {
   if (strcmp(arg[0],"linear") == 0) {
     if (rfix < 0) zero_momentum();
-    else if (strcmp(modify->fix[rfix]->style,"rigid/small") == 0) {
+    else if (utils::strmatch(modify->fix[rfix]->style,"^rigid/small")) {
       modify->fix[rfix]->setup_pre_neighbor();
       modify->fix[rfix]->zero_momentum();
-    } else if (strstr(modify->fix[rfix]->style,"rigid")) {
+    } else if (utils::strmatch(modify->fix[rfix]->style,"^rigid")) {
       modify->fix[rfix]->zero_momentum();
     } else error->all(FLERR,"Velocity rigid used with non-rigid fix-ID");
 
   } else if (strcmp(arg[0],"angular") == 0) {
     if (rfix < 0) zero_rotation();
-    else if (strcmp(modify->fix[rfix]->style,"rigid/small") == 0) {
+    else if (utils::strmatch(modify->fix[rfix]->style,"^rigid/small")) {
       modify->fix[rfix]->setup_pre_neighbor();
       modify->fix[rfix]->zero_rotation();
-    } else if (strstr(modify->fix[rfix]->style,"rigid")) {
+    } else if (utils::strmatch(modify->fix[rfix]->style,"^rigid")) {
       modify->fix[rfix]->zero_rotation();
     } else error->all(FLERR,"Velocity rigid used with non-rigid fix-ID");
 
diff --git a/src/version.h b/src/version.h
index 0539f757c9..94fee893cb 100644
--- a/src/version.h
+++ b/src/version.h
@@ -1 +1 @@
-#define LAMMPS_VERSION "28 Feb 2019"
+#define LAMMPS_VERSION "29 Mar 2019"
diff --git a/tools/msi2lmp/README b/tools/msi2lmp/README
index 9ac7af5607..bd658d897e 100644
--- a/tools/msi2lmp/README
+++ b/tools/msi2lmp/README
@@ -49,8 +49,12 @@ This program uses the .car and .mdf files from MSI/Biosyms's INSIGHT
 
  1. Building msi2lmp
 
-    Use the Makefile in the src directory. It is
-    currently set up for gcc. You will have to modify
+    If you are using CMake to compile LAMMPS, the building
+    (and installation) of msi2lmp is included in the normal
+    build process.
+
+    Otherwise you can use the Makefile in the src directory.
+    It is currently set up for gcc. You will have to modify
     it to use a different compiler.
 
  2. Testing the program