Merge pull request #2648 from akohlmey/next_lammps_version

Update version strings for the next patch release

.github/CODEOWNERS

@@ -114,6 +114,7 @@ src/info.*                @akohlmey @rbberger
 src/timer.*               @akohlmey
 src/min*                  @sjplimp @stanmoore1
 src/utils.*               @akohlmey @rbberger
+src/math_eigen_impl.h     @jewettaij
 
 # tools
 tools/msi2lmp/*       @akohlmey
@@ -134,6 +135,9 @@ cmake/presets/*.cmake @junghans @rbberger @akohlmey
 # python
 python/*              @rbberger
 
+# fortran
+fortran/*             @akohlmey
+
 # docs
 doc/utils/*/*         @rbberger
 doc/Makefile          @rbberger

.github/CONTRIBUTING.md

@@ -108,7 +108,7 @@ For bug reports, the next step is that one of the core LAMMPS developers will se
 
 For submitting pull requests, there is a [detailed tutorial](https://lammps.sandia.gov/doc/Howto_github.html) in the LAMMPS manual. Thus only a brief breakdown of the steps is presented here. Please note, that the LAMMPS developers are still reviewing and trying to improve the process. If you are unsure about something, do not hesitate to post a question on the lammps-users mailing list or contact one fo the core LAMMPS developers.
 Immediately after the submission, the LAMMPS continuing integration server at ci.lammps.org will download your submitted branch and perform a simple compilation test, i.e. will test whether your submitted code can be compiled under various conditions. It will also do a check on whether your included documentation translates cleanly. Whether these tests are successful or fail will be recorded. If a test fails, please inspect the corresponding output on the CI server and take the necessary steps, if needed, so that the code can compile cleanly again. The test will be re-run each the pull request is updated with a push to the remote branch on GitHub.
-Next a LAMMPS core developer will self-assign and do an overall technical assessment of the submission. If you are not yet registered as a LAMMPS collaborator, you will receive an invitation for that. As part of the assesment, the pull request will be categorized with labels. There are two special labels: `needs_work` (indicates that work from the submitter of the pull request is needed) and `work_in_progress` (indicates, that the assigned LAMMPS developer will make changes, if not done by the contributor who made the submit). 
+Next a LAMMPS core developer will self-assign and do an overall technical assessment of the submission. If you are not yet registered as a LAMMPS collaborator, you will receive an invitation for that. As part of the assessment, the pull request will be categorized with labels. There are two special labels: `needs_work` (indicates that work from the submitter of the pull request is needed) and `work_in_progress` (indicates, that the assigned LAMMPS developer will make changes, if not done by the contributor who made the submit). 
 You may also receive comments and suggestions on the overall submission or specific details and on occasion specific requests for changes as part of the review. If permitted, also additional changes may be pushed into your pull request branch or a pull request may be filed in your LAMMPS fork on GitHub to include those changes.
 The LAMMPS developer may then decide to assign the pull request to another developer (e.g. when that developer is more knowledgeable about the submitted feature or enhancement or has written the modified code). It may also happen, that additional developers are requested to provide a review and approve the changes. For submissions, that may change the general behavior of LAMMPS, or where a possibility of unwanted side effects exists, additional tests may be requested by the assigned developer.
 If the assigned developer is satisfied and considers the submission ready for inclusion into LAMMPS, the pull request will receive approvals and be merged into the master branch by one of the core LAMMPS developers. After the pull request is merged, you may delete the feature branch used for the pull request in your personal LAMMPS fork.

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,47 @@
+# GitHub action to run static code analysis on C++ and Python code
+name: "CodeQL Code Analysis"
+
+on:
+  push:
+    branches: [master]
+
+jobs:
+  analyze:
+    name: Analyze
+    if: ${{ github.repository == 'lammps/lammps' }}
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: ['cpp', 'python']
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      with:
+        fetch-depth: 2
+
+    - name: Setup Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+
+    - name: Create Build Environment
+      run: cmake -E make_directory ${{github.workspace}}/build
+
+    - name: Building LAMMPS via CMake
+      if: ${{ matrix.language == 'cpp' }}
+      shell: bash
+      working-directory: ${{github.workspace}}/build
+      run: |
+        cmake -C $GITHUB_WORKSPACE/cmake/presets/most.cmake $GITHUB_WORKSPACE/cmake
+        cmake --build . --parallel 2
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/unittest-macos.yml

@@ -0,0 +1,34 @@
+# GitHub action to build LAMMPS on MacOS and run unit tests
+name: "Unittest for MacOS"
+
+on:
+  push:
+    branches: [master]
+
+jobs:
+  build:
+    name: MacOS Unit Test
+    if: ${{ github.repository == 'lammps/lammps' }}
+    runs-on: macos-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      with:
+        fetch-depth: 2
+
+    - name: Create Build Environment
+      run: cmake -E make_directory ${{github.workspace}}/build
+
+    - name: Building LAMMPS via CMake
+      shell: bash
+      working-directory: ${{github.workspace}}/build
+      run: |
+        cmake -C $GITHUB_WORKSPACE/cmake/presets/most.cmake $GITHUB_WORKSPACE/cmake \
+              -DENABLE_TESTING=ON -DBUILD_SHARED_LIBS=ON -DLAMMPS_EXCEPTIONS=ON
+        cmake --build . --parallel 2
+
+    - name: Run Tests
+      working-directory: ${{github.workspace}}/build
+      shell: bash
+      run: ctest -V

.gitignore

@@ -37,6 +37,7 @@ vgcore.*
 ehthumbs.db
 Thumbs.db
 .clang-format
+.lammps_history
 
 #cmake
 /build*

LICENSE

@@ -1,6 +1,6 @@
 GNU GENERAL PUBLIC LICENSE
 
-Version 2, June 1991 
+Version 2, June 1991
 
 Copyright (C) 1989, 1991 Free Software Foundation, Inc.  
 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA
@@ -301,9 +301,8 @@ one line to give the program's name and an idea of what it does.
 Copyright (C) yyyy  name of author
 
 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.
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
 
 This program is distributed in the hope that it will be useful, but
 WITHOUT ANY WARRANTY; without even the implied warranty of

README

@@ -22,28 +22,32 @@ more information about the code and its uses.
 
 The LAMMPS distribution includes the following files and directories:
 
-README			   this file
-LICENSE			   the GNU General Public License (GPL)
-bench			   benchmark problems
-cmake			   CMake build system
-doc			   documentation
-examples		   simple test problems
-lib			   libraries LAMMPS can be linked with
-potentials		   interatomic potential files
-python			   Python wrapper on LAMMPS as a library
-src			   source files
-tools			   pre- and post-processing tools
+README                     this file
+LICENSE                    the GNU General Public License (GPL)
+bench                      benchmark problems
+cmake                      CMake build files
+doc                        documentation
+examples                   simple test problems
+fortran                    Fortran wrapper for LAMMPS
+lib                        additional provided or external libraries
+potentials                 interatomic potential files
+python                     Python wrappers for LAMMPS
+src                        source files
+tools                      pre- and post-processing tools
 
 Point your browser at any of these files to get started:
 
-http://lammps.sandia.gov/doc/Manual.html         the LAMMPS manual
-http://lammps.sandia.gov/doc/Intro.html          hi-level introduction
-http://lammps.sandia.gov/doc/Build.html          how to build LAMMPS
-http://lammps.sandia.gov/doc/Run_head.html       how to run LAMMPS
-http://lammps.sandia.gov/doc/Developer.pdf       LAMMPS developer guide
+https://lammps.sandia.gov/doc/Manual.html         LAMMPS manual
+https://lammps.sandia.gov/doc/Intro.html          hi-level introduction
+https://lammps.sandia.gov/doc/Build.html          how to build LAMMPS
+https://lammps.sandia.gov/doc/Run_head.html       how to run LAMMPS
+https://lammps.sandia.gov/doc/Commands_all.html   Table of available commands
+https://lammps.sandia.gov/doc/Library.html        LAMMPS library interfaces
+https://lammps.sandia.gov/doc/Modify.html         how to modify and extend LAMMPS
+https://lammps.sandia.gov/doc/Developer.html      LAMMPS developer info
 
 You can also create these doc pages locally:
 
 % cd doc
 % make html                # creates HTML pages in doc/html
-% make pdf                 # creates Manual.pdf and Developer.pdf
+% make pdf                 # creates Manual.pdf

bench/KEPLER/Makefile.cpu

@@ -1,108 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.cuda

@@ -1,108 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.gpu

@@ -1,108 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.gpu.double

@@ -1,50 +0,0 @@
-# /* ----------------------------------------------------------------------   
-#  Generic Linux Makefile for CUDA 
-#     - Change CUDA_ARCH for your GPU
-# ------------------------------------------------------------------------- */
-
-# which file will be copied to Makefile.lammps
-
-EXTRAMAKE = Makefile.lammps.standard
-
-CUDA_HOME = /home/projects/cuda/6.0.37
-NVCC = nvcc
-
-# Kepler CUDA
-CUDA_ARCH = -arch=sm_35
-# Tesla CUDA
-#CUDA_ARCH = -arch=sm_21
-# newer CUDA
-#CUDA_ARCH = -arch=sm_13
-# older CUDA
-#CUDA_ARCH = -arch=sm_10 -DCUDA_PRE_THREE
-
-# this setting should match LAMMPS Makefile
-# one of LAMMPS_SMALLBIG (default), LAMMPS_BIGBIG and LAMMPS_SMALLSMALL
-
-LMP_INC = -DLAMMPS_SMALLBIG
-
-# precision for GPU calculations
-# -D_SINGLE_SINGLE  # Single precision for all calculations
-# -D_DOUBLE_DOUBLE  # Double precision for all calculations
-# -D_SINGLE_DOUBLE  # Accumulation of forces, etc. in double
-
-CUDA_PRECISION = -D_DOUBLE_DOUBLE
-
-CUDA_INCLUDE = -I$(CUDA_HOME)/include
-CUDA_LIB = -L$(CUDA_HOME)/lib64
-CUDA_OPTS = -DUNIX -O3 -Xptxas -v --use_fast_math
-
-CUDR_CPP = mpic++ -DMPI_GERYON -DUCL_NO_EXIT -DMPICH_IGNORE_CXX_SEEK
-CUDR_OPTS = -O2 # -xHost -no-prec-div -ansi-alias
-
-BIN_DIR = ./
-OBJ_DIR = ./
-LIB_DIR = ./
-AR = ar
-BSH = /bin/sh
-
-CUDPP_OPT = -DUSE_CUDPP -Icudpp_mini
-
-include Nvidia.makefile
-

bench/KEPLER/Makefile.gpu.mixed

@@ -1,50 +0,0 @@
-# /* ----------------------------------------------------------------------   
-#  Generic Linux Makefile for CUDA 
-#     - Change CUDA_ARCH for your GPU
-# ------------------------------------------------------------------------- */
-
-# which file will be copied to Makefile.lammps
-
-EXTRAMAKE = Makefile.lammps.standard
-
-CUDA_HOME = /home/projects/cuda/6.0.37
-NVCC = nvcc
-
-# Kepler CUDA
-CUDA_ARCH = -arch=sm_35
-# Tesla CUDA
-#CUDA_ARCH = -arch=sm_21
-# newer CUDA
-#CUDA_ARCH = -arch=sm_13
-# older CUDA
-#CUDA_ARCH = -arch=sm_10 -DCUDA_PRE_THREE
-
-# this setting should match LAMMPS Makefile
-# one of LAMMPS_SMALLBIG (default), LAMMPS_BIGBIG and LAMMPS_SMALLSMALL
-
-LMP_INC = -DLAMMPS_SMALLBIG
-
-# precision for GPU calculations
-# -D_SINGLE_SINGLE  # Single precision for all calculations
-# -D_DOUBLE_DOUBLE  # Double precision for all calculations
-# -D_SINGLE_DOUBLE  # Accumulation of forces, etc. in double
-
-CUDA_PRECISION = -D_SINGLE_DOUBLE
-
-CUDA_INCLUDE = -I$(CUDA_HOME)/include
-CUDA_LIB = -L$(CUDA_HOME)/lib64
-CUDA_OPTS = -DUNIX -O3 -Xptxas -v --use_fast_math
-
-CUDR_CPP = mpic++ -DMPI_GERYON -DUCL_NO_EXIT -DMPICH_IGNORE_CXX_SEEK
-CUDR_OPTS = -O2 # -xHost -no-prec-div -ansi-alias
-
-BIN_DIR = ./
-OBJ_DIR = ./
-LIB_DIR = ./
-AR = ar
-BSH = /bin/sh
-
-CUDPP_OPT = -DUSE_CUDPP -Icudpp_mini
-
-include Nvidia.makefile
-

bench/KEPLER/Makefile.gpu.single

@@ -1,50 +0,0 @@
-# /* ----------------------------------------------------------------------   
-#  Generic Linux Makefile for CUDA 
-#     - Change CUDA_ARCH for your GPU
-# ------------------------------------------------------------------------- */
-
-# which file will be copied to Makefile.lammps
-
-EXTRAMAKE = Makefile.lammps.standard
-
-CUDA_HOME = /home/projects/cuda/6.0.37
-NVCC = nvcc
-
-# Kepler CUDA
-CUDA_ARCH = -arch=sm_35
-# Tesla CUDA
-#CUDA_ARCH = -arch=sm_21
-# newer CUDA
-#CUDA_ARCH = -arch=sm_13
-# older CUDA
-#CUDA_ARCH = -arch=sm_10 -DCUDA_PRE_THREE
-
-# this setting should match LAMMPS Makefile
-# one of LAMMPS_SMALLBIG (default), LAMMPS_BIGBIG and LAMMPS_SMALLSMALL
-
-LMP_INC = -DLAMMPS_SMALLBIG
-
-# precision for GPU calculations
-# -D_SINGLE_SINGLE  # Single precision for all calculations
-# -D_DOUBLE_DOUBLE  # Double precision for all calculations
-# -D_SINGLE_DOUBLE  # Accumulation of forces, etc. in double
-
-CUDA_PRECISION = -D_SINGLE_SINGLE
-
-CUDA_INCLUDE = -I$(CUDA_HOME)/include
-CUDA_LIB = -L$(CUDA_HOME)/lib64
-CUDA_OPTS = -DUNIX -O3 -Xptxas -v --use_fast_math
-
-CUDR_CPP = mpic++ -DMPI_GERYON -DUCL_NO_EXIT -DMPICH_IGNORE_CXX_SEEK
-CUDR_OPTS = -O2 # -xHost -no-prec-div -ansi-alias
-
-BIN_DIR = ./
-OBJ_DIR = ./
-LIB_DIR = ./
-AR = ar
-BSH = /bin/sh
-
-CUDPP_OPT = -DUSE_CUDPP -Icudpp_mini
-
-include Nvidia.makefile
-

bench/KEPLER/Makefile.intel.cpu

@@ -1,109 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O3 -openmp -DLAMMPS_MEMALIGN=64 -no-offload \
-                -xHost -fno-alias -ansi-alias -restrict -override-limits
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O -openmp
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =	-DLAMMPS_GZIP -DLAMMPS_JPEG
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.kokkos.cuda

@@ -1,113 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		nvcc
-CCFLAGS =	-O3 -arch=sm_35
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		mpicxx
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-OMP = yes
-CUDA = yes
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-%.o:%.cu
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.kokkos.omp

@@ -1,110 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-OMP = yes
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.omp

@@ -1,108 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O3 -openmp -restrict -ansi-alias
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O -openmp
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/Makefile.opt

@@ -1,108 +0,0 @@
-# linux = Shannon Linux box, Intel icc, OpenMPI, KISS FFTW
-
-SHELL = /bin/sh
-
-# ---------------------------------------------------------------------
-# compiler/linker settings
-# specify flags and libraries needed for your compiler
-
-CC =		icc
-CCFLAGS =	-O -restrict
-SHFLAGS =	-fPIC
-DEPFLAGS =	-M
-
-LINK =		icc
-LINKFLAGS =	-O
-LIB =           -lstdc++
-SIZE =		size
-
-ARCHIVE =	ar
-ARFLAGS =	-rc
-SHLIBFLAGS =	-shared
-
-# ---------------------------------------------------------------------
-# LAMMPS-specific settings
-# specify settings for LAMMPS features you will use
-# if you change any -D setting, do full re-compile after "make clean"
-
-# LAMMPS ifdef settings, OPTIONAL
-# see possible settings in doc/Section_start.html#2_2 (step 4)
-
-LMP_INC =
-
-# MPI library, REQUIRED
-# see discussion in doc/Section_start.html#2_2 (step 5)
-# can point to dummy MPI library in src/STUBS as in Makefile.serial
-# INC = path for mpi.h, MPI compiler settings
-# PATH = path for MPI library
-# LIB = name of MPI library
-
-MPI_INC =       -I/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/include/
-MPI_PATH =      -L/home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37/lib
-MPI_LIB =	-lmpi
-
-# FFT library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 6)
-# can be left blank to use provided KISS FFT library
-# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings
-# PATH = path for FFT library
-# LIB = name of FFT library
-
-FFT_INC =
-FFT_PATH = 
-FFT_LIB =
-
-# JPEG and/or PNG library, OPTIONAL
-# see discussion in doc/Section_start.html#2_2 (step 7)
-# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC
-# INC = path(s) for jpeglib.h and/or png.h
-# PATH = path(s) for JPEG library and/or PNG library
-# LIB = name(s) of JPEG library and/or PNG library
-
-JPG_INC =       
-JPG_PATH = 	
-JPG_LIB =	-ljpeg
-
-# ---------------------------------------------------------------------
-# build rules and dependencies
-# no need to edit this section
-
-include	Makefile.package.settings
-include	Makefile.package
-
-EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC)
-EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH)
-EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB)
-
-# Path to src files
-
-vpath %.cpp ..
-vpath %.h ..
-
-# Link target
-
-$(EXE):	$(OBJ)
-	$(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE)
-	$(SIZE) $(EXE)
-
-# Library targets
-
-lib:	$(OBJ)
-	$(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ)
-
-shlib:	$(OBJ)
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \
-        $(OBJ) $(EXTRA_LIB) $(LIB)
-
-# Compilation rules
-
-%.o:%.cpp
-	$(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $<
-
-%.d:%.cpp
-	$(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@
-
-# Individual dependencies
-
-DEPENDS = $(OBJ:.o=.d)
-sinclude $(DEPENDS)

bench/KEPLER/README

@@ -1,68 +0,0 @@
-These are build and input and run scripts used to run the LJ benchmark
-in the top-level bench directory using all the various accelerator
-packages currently available in LAMMPS.  The results of running these
-benchmarks on a GPU cluster with Kepler GPUs are shown on the "GPU
-(Kepler)" section of the Benchmark page of the LAMMPS WWW site:
-lammps.sandia.gov/bench.
-
-The specifics of the benchmark machine are as follows:
-
-It is a small GPU cluster at Sandia National Labs called "shannon". It
-has 32 nodes, each with two 8-core Sandy Bridge Xeon CPUs (E5-2670,
-2.6GHz, HT deactivated), for a total of 512 cores.  Twenty-four of the
-nodes have two NVIDIA Kepler GPUs (K20x, 2688 732 MHz cores).  LAMMPS
-was compiled with the Intel icc compiler, using module
-openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37.
-
-------------------------------------------------------------------------
-
-You can, of course, build LAMMPS yourself with any of the accelerator
-packages installed for your platform.
-
-The build.py script will build LAMMPS for the various accelerlator
-packages using the Makefile.* files in this dir, which you can edit if
-necessary for your platform.  You must set the "lmpdir" variable at
-the top of build.py to the home directory of LAMMPS as installed on
-your system.  Note that the build.py script hardcodes the arch setting
-for the USER-CUDA package, which should be matched to the GPUs on your
-system, e.g. sm_35 for Kepler GPUs.  For the GPU package, this setting
-is in the Makefile.gpu.* files, as is the CUDA_HOME variable which
-should point to where NVIDIA Cuda software is installed on your
-system.
-
-Once the Makefiles are in place, then typing, for example,
-
-python build.py cpu gpu
-
-will build executables for the CPU (no accelerators), and 3 variants
-(double, mixed, single precision) of the GPU package.  See the list of
-possible targets at the top of the build.py script.
-
-Note that the build.py script will un-install all packages in your
-LAMMPS directory, then only install the ones needed for the benchmark.
-The Makefile.* files in this dir are copied into lammps/src/MAKE, as a
-dummy Makefile.foo, so they will not conflict with makefiles that may
-already be there.  The build.py script also builds the auxiliary GPU
-and USER-CUDA library as needed.
-
-LAMMPS executables that are generated by build.py are copied into this
-directory when the script finishes each build.
-
-------------------------------------------------------------------------
-
-The in.* files can be run with any of the accelerator packages,
-if you specify the appropriate command-line switches.  These
-include switches to set the problem size and number of timesteps
-to run.
-
-The run*.sh scripts have sample mpirun commands for running the input
-scripts on a single node or on multiple nodes for the strong and weak
-scaling results shown on the benchmark web page.  These scripts are
-provided for illustration purposes, to show what command-line
-arguments are used with each accelerator package.
-
-Note that we generate these run scripts, either for interactive or
-batch submission, via Python scripts which often produces a long list
-of runs to exercise a combination of options.  To perform a quick
-benchmark calculation on your platform, you will typically only want
-to run a few commands out of any of the run*.sh scripts.

bench/KEPLER/build.py

@@ -1,187 +0,0 @@
-#!/usr/local/bin/python
-
-# Syntax: build.py target1 target2 ...
-#         targets:
-#         cpu, opt, omp,
-#         gpu/double, gpu/mixed, gpu/single,
-#         cuda/double, cuda/mixed, cuda/single,
-#         intel/cpu, intel/phi,
-#         kokkos/omp, kokkos/phi, kokkos/cuda
-#         gpu = gpu/double + gpu/mixed + gpu/single
-#         cuda = cuda/double + cuda/mixed + cuda/single
-#         intel = intel/cpu + intel/phi
-#         kokkos = kokkos/omp + kokkos/phi + kokkos/cuda
-#         all = cpu + opt + omp + gpu + cuda + intel + kokkos
-
-# create exectuables for different packages
-# MUST set lmpdir to path of LAMMPS home directory
-
-import sys,commands,os
-
-lmpdir = "~/lammps"
-
-# build LAMMPS
-# copy makefile into src/MAKE as Makefile.foo, then remove it
-
-def build_lammps(makefile,pkg):
-  print "Building LAMMPS with %s and %s packages ..." % (makefile,pkg)
-  commands.getoutput("cp %s %s/src/MAKE/Makefile.foo" % (makefile,lmpdir))
-  cwd = os.getcwd()
-  os.chdir(os.path.expanduser(lmpdir + "/src"))
-  str = "make clean-foo"
-  txt = commands.getoutput(str)
-  str = "make no-all"
-  txt = commands.getoutput(str)
-  for package in pkg:
-    str = "make yes-%s" % package
-    txt = commands.getoutput(str)
-    print txt
-  str = "make -j 16 foo"
-  txt = commands.getoutput(str)
-  os.remove("MAKE/Makefile.foo")
-  os.chdir(cwd)
-
-# build GPU library in LAMMPS
-# copy makefile into lib/gpu as Makefile.foo, then remove it
-  
-def build_gpu(makefile):
-  print "Building GPU lib with %s ..." % makefile
-  commands.getoutput("cp %s %s/lib/gpu/Makefile.foo" % (makefile,lmpdir))
-  cwd = os.getcwd()
-  os.chdir(os.path.expanduser(lmpdir + "/lib/gpu"))
-  str = "make -f Makefile.foo clean"
-  txt = commands.getoutput(str)
-  str = "make -j 16 -f Makefile.foo"
-  txt = commands.getoutput(str)
-  os.remove("Makefile.foo")
-  os.chdir(cwd)
-
-# build CUDA library in LAMMPS
-# set precision and arch explicitly as options to make in lib/cuda
-  
-def build_cuda(precision,arch):
-  print "Building USER-CUDA lib with %s and arch sm_%d ..." % (precision,arch)
-  cwd = os.getcwd()
-  os.chdir(os.path.expanduser(lmpdir + "/lib/cuda"))
-  str = "make clean"
-  txt = commands.getoutput(str)
-  if precision == "double": pflag = 2
-  elif precision == "mixed": pflag = 4
-  elif precision == "single": pflag = 1
-  str = "make -j 16 precision=%d arch=%s" % (pflag,arch)
-  txt = commands.getoutput(str)
-
-  os.chdir(cwd)
-
-# main program
-# convert target keywords into target flags
-
-  cpu = opt = omp = 0
-gpu = gpu_double = gpu_mixed = gpu_single = 0
-cuda = cuda_double = cuda_mixed = cuda_single = 0
-intel = intel_cpu = intel_phi = 0
-kokkos = kokkos_omp = kokkos_phi = kokkos_cuda = 0
-  
-targets = sys.argv[1:]
-for target in targets:
-  if target == "cpu": cpu = 1
-  elif target == "opt": opt = 1
-  elif target == "omp": omp = 1
-  elif target == "gpu/double": gpu_double = 1
-  elif target == "gpu/mixed": gpu_mixed = 1
-  elif target == "gpu/single": gpu_single = 1
-  elif target == "gpu": gpu = 1
-  elif target == "cuda/double": cuda_double = 1
-  elif target == "cuda/mixed": cuda_mixed = 1
-  elif target == "cuda/single": cuda_single = 1
-  elif target == "cuda": cuda = 1
-  elif target == "intel/cpu": intel_cpu = 1
-  elif target == "intel/phi": intel_phi = 1
-  elif target == "intel": intel = 1
-  elif target == "kokkos/omp": kokkos_omp = 1
-  elif target == "kokkos/phi": kokkos_phi = 1
-  elif target == "kokkos/cuda": kokkos_cuda = 1
-  elif target == "kokkos": kokkos = 1
-  elif target == "all": cpu = omp = gpu = cuda = intel = kokkos = 1
-  else: print "Target",target,"is unknown"
-
-if gpu: gpu_double = gpu_mixed = gpu_single = 1
-if cuda: cuda_double = cuda_mixed = cuda_single = 1
-if intel: intel_cpu = intel_phi = 1
-if kokkos: kokkos_omp = kokkos_phi = kokkos_cuda = 1
-
-# CPU
-
-if cpu:
-  build_lammps(makefile = "Makefile.cpu", pkg = [])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_cpu" % lmpdir)
-
-# OPT
-
-if opt:
-  build_lammps(makefile = "Makefile.opt", pkg = ["opt"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_opt" % lmpdir)
-
-# OMP
-
-if omp:
-  build_lammps(makefile = "Makefile.omp", pkg = ["user-omp"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_omp" % lmpdir)
-
-# GPU, 3 precisions
-
-if gpu_double:
-  build_gpu(makefile = "Makefile.gpu.double")
-  build_lammps(makefile = "Makefile.gpu", pkg = ["gpu"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_gpu_double" % lmpdir)
-
-if gpu_mixed:
-  build_gpu(makefile = "Makefile.gpu.mixed")
-  build_lammps(makefile = "Makefile.gpu", pkg = ["gpu"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_gpu_mixed" % lmpdir)
-
-if gpu_single:
-  build_gpu(makefile = "Makefile.gpu.single")
-  build_lammps(makefile = "Makefile.gpu", pkg = ["gpu"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_gpu_single" % lmpdir)
-
-# CUDA, 3 precisions
-
-if cuda_double:
-  build_cuda(precision = "double", arch = 35)
-  build_lammps(makefile = "Makefile.cuda", pkg = ["kspace","user-cuda"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_cuda_double" % lmpdir)
-
-if cuda_mixed:
-  build_cuda(precision = "mixed", arch = 35)
-  build_lammps(makefile = "Makefile.cuda", pkg = ["kspace","user-cuda"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_cuda_mixed" % lmpdir)
-
-if cuda_single:
-  build_cuda(precision = "single", arch = 35)
-  build_lammps(makefile = "Makefile.cuda", pkg = ["kspace","user-cuda"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_cuda_single" % lmpdir)
-
-# INTEL, CPU and Phi
-
-if intel_cpu:
-  build_lammps(makefile = "Makefile.intel.cpu", pkg = ["user-intel"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_intel_cpu" % lmpdir)
-
-if intel_phi:
-  build_lammps(makefile = "Makefile.intel.phi", pkg = ["user-intel","user-omp"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_intel_phi" % lmpdir)
-
-# KOKKOS, all variants
-
-if kokkos_omp:
-  build_lammps(makefile = "Makefile.kokkos.omp", pkg = ["kokkos"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_kokkos_omp" % lmpdir)
-
-if kokkos_phi:
-  build_lammps(makefile = "Makefile.kokkos.phi", pkg = ["kokkos"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_kokkos_phi" % lmpdir)
-
-if kokkos_cuda:
-  build_lammps(makefile = "Makefile.kokkos.cuda", pkg = ["kokkos"])
-  print commands.getoutput("mv %s/src/lmp_foo ./lmp_kokkos_cuda" % lmpdir)

bench/KEPLER/in.lj

@@ -1,22 +0,0 @@
-# 3d Lennard-Jones melt
-
-units		lj
-atom_style	atomic
-
-lattice		fcc 0.8442
-region		box block 0 $x 0 $y 0 $z
-create_box	1 box
-create_atoms	1 box
-mass		1 1.0
-
-velocity	all create 1.44 87287 loop geom
-
-pair_style	lj/cut 2.5
-pair_coeff	1 1 1.0 1.0 2.5
-
-neighbor	0.3 bin
-neigh_modify	delay 0 every 20 check no
-
-fix		1 all nve
-
-run		$t

bench/KEPLER/run_cpu.sh

@@ -1,29 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.1
-
-mpirun -np 2 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.2
-
-mpirun -np 4 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.4
-
-mpirun -np 6 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.6
-
-mpirun -np 8 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.8
-
-mpirun -np 10 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.10
-
-mpirun -np 12 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.12
-
-mpirun -np 14 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.14
-
-mpirun -np 16 lmp_cpu -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cpu.128K.16

bench/KEPLER/run_cuda.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -N 1 lmp_cuda_double -c on -sf cuda -pk cuda 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.double.128K.1
-
-mpirun -N 2 lmp_cuda_double -c on -sf cuda -pk cuda 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.double.128K.2
-
-mpirun -N 1 lmp_cuda_mixed -c on -sf cuda -pk cuda 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.mixed.128K.1
-
-mpirun -N 2 lmp_cuda_mixed -c on -sf cuda -pk cuda 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.mixed.128K.2
-
-mpirun -N 1 lmp_cuda_single -c on -sf cuda -pk cuda 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.single.128K.1
-
-mpirun -N 2 lmp_cuda_single -c on -sf cuda -pk cuda 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.cuda.single.128K.2

bench/KEPLER/run_gpu.sh

@@ -1,155 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.1.1
-
-mpirun -np 2 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.2.1
-
-mpirun -np 2 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.2.2
-
-mpirun -np 4 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.4.1
-
-mpirun -np 4 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.4.2
-
-mpirun -np 6 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.6.1
-
-mpirun -np 6 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.6.2
-
-mpirun -np 8 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.8.1
-
-mpirun -np 8 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.8.2
-
-mpirun -np 10 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.10.1
-
-mpirun -np 10 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.10.2
-
-mpirun -np 12 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.12.1
-
-mpirun -np 12 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.12.2
-
-mpirun -np 14 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.14.1
-
-mpirun -np 14 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.14.2
-
-mpirun -np 16 lmp_gpu_single -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.16.1
-
-mpirun -np 16 lmp_gpu_single -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.single.128K.16.2
-
-mpirun -np 1 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.1.1
-
-mpirun -np 2 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.2.1
-
-mpirun -np 2 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.2.2
-
-mpirun -np 4 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.4.1
-
-mpirun -np 4 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.4.2
-
-mpirun -np 6 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.6.1
-
-mpirun -np 6 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.6.2
-
-mpirun -np 8 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.8.1
-
-mpirun -np 8 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.8.2
-
-mpirun -np 10 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.10.1
-
-mpirun -np 10 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.10.2
-
-mpirun -np 12 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.12.1
-
-mpirun -np 12 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.12.2
-
-mpirun -np 14 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.14.1
-
-mpirun -np 14 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.14.2
-
-mpirun -np 16 lmp_gpu_mixed -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.16.1
-
-mpirun -np 16 lmp_gpu_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.mixed.128K.16.2
-
-mpirun -np 1 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.1.1
-
-mpirun -np 2 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.2.1
-
-mpirun -np 2 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.2.2
-
-mpirun -np 4 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.4.1
-
-mpirun -np 4 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.4.2
-
-mpirun -np 6 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.6.1
-
-mpirun -np 6 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.6.2
-
-mpirun -np 8 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.8.1
-
-mpirun -np 8 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.8.2
-
-mpirun -np 10 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.10.1
-
-mpirun -np 10 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.10.2
-
-mpirun -np 12 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.12.1
-
-mpirun -np 12 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.12.2
-
-mpirun -np 14 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.14.1
-
-mpirun -np 14 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.14.2
-
-mpirun -np 16 lmp_gpu_double -sf gpu -pk gpu 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.16.1
-
-mpirun -np 16 lmp_gpu_double -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.gpu.double.128K.16.2

bench/KEPLER/run_intel_cpu.sh

@@ -1,83 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.1
-
-mpirun -np 2 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.2
-
-mpirun -np 4 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.4
-
-mpirun -np 6 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.6
-
-mpirun -np 8 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.8
-
-mpirun -np 10 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.10
-
-mpirun -np 12 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.12
-
-mpirun -np 14 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.14
-
-mpirun -np 16 lmp_intel_cpu -sf intel -pk intel 1 prec single -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.single.128K.16
-
-mpirun -np 1 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.1
-
-mpirun -np 2 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.2
-
-mpirun -np 4 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.4
-
-mpirun -np 6 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.6
-
-mpirun -np 8 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.8
-
-mpirun -np 10 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.10
-
-mpirun -np 12 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.12
-
-mpirun -np 14 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.14
-
-mpirun -np 16 lmp_intel_cpu -sf intel -pk intel 1 prec mixed -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.mixed.128K.16
-
-mpirun -np 1 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.1
-
-mpirun -np 2 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.2
-
-mpirun -np 4 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.4
-
-mpirun -np 6 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.6
-
-mpirun -np 8 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.8
-
-mpirun -np 10 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.10
-
-mpirun -np 12 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.12
-
-mpirun -np 14 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.14
-
-mpirun -np 16 lmp_intel_cpu -sf intel -pk intel 1 prec double -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.intel.cpu.double.128K.16

bench/KEPLER/run_kokkos_cuda.sh

@@ -1,74 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 1 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.1
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 2 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.2
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 3 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.3
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 4 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.4
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 5 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.5
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 6 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.6
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 7 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.7
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 8 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.8
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 9 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.9
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 10 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.10
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 11 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.11
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 12 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.12
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 13 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.13
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 14 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.14
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 15 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.15
-
-mpirun -np 1 lmp_kokkos_cuda -k on g 1 t 16 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.1.16
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 1 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.1
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 2 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.2
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 3 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.3
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 4 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.4
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 5 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.5
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 6 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.6
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 7 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.7
-
-mpirun -np 2 lmp_kokkos_cuda -k on g 2 t 8 -sf kk -pk kokkos binsize 2.8 comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.cuda.128K.2.8

bench/KEPLER/run_kokkos_omp.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np full -bind-to socket -map-by socket -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 16 -sf kk -pk kokkos neigh full newton off comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.omp.128K.1.16
-
-mpirun -np full -bind-to socket -map-by socket -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 8 -sf kk -pk kokkos neigh full newton off comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.omp.128K.2.8
-
-mpirun -np full -bind-to socket -map-by socket -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 4 -sf kk -pk kokkos neigh full newton off comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.omp.128K.4.4
-
-mpirun -np full -bind-to socket -map-by socket -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 2 -sf kk -pk kokkos neigh full newton off comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.omp.128K.8.2
-
-mpirun -np half -bind-to socket -map-by socket -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 1 -sf kk -pk kokkos neigh half newton on comm device -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.kokkos.omp.128K.16.1

bench/KEPLER/run_omp.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_omp -sf omp -pk omp 16 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.omp.128K.1.16
-
-mpirun -np 2 lmp_omp -sf omp -pk omp 8 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.omp.128K.2.8
-
-mpirun -np 4 lmp_omp -sf omp -pk omp 4 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.omp.128K.4.4
-
-mpirun -np 8 lmp_omp -sf omp -pk omp 2 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.omp.128K.8.2
-
-mpirun -np 16 lmp_omp -sf omp -pk omp 1 -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.omp.128K.16.1

bench/KEPLER/run_opt.sh

@@ -1,29 +0,0 @@
-#!/bin/bash
-#SBATCH -N 1 --time=12:00:00
-
-mpirun -np 1 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.1
-
-mpirun -np 2 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.2
-
-mpirun -np 4 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.4
-
-mpirun -np 6 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.6
-
-mpirun -np 8 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.8
-
-mpirun -np 10 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.10
-
-mpirun -np 12 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.12
-
-mpirun -np 14 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.14
-
-mpirun -np 16 lmp_opt -sf opt -v x 32 -v y 32 -v z 32 -v t 100 < in.lj
-mv log.lammps log.10Sep14.lj.opt.128K.16

bench/KEPLER/run_strong.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-#SBATCH -N 16 --time=12:00:00
-
-mpirun -npernode 16 lmp_cpu -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.cpu.2048K.16.16
-
-mpirun -npernode 16 lmp_omp -sf omp -pk omp 1 -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.omp.2048K.16.1.16
-
-mpirun -npernode 2 lmp_cuda -c on -sf cuda -pk cuda 2 -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.cuda.2048K.2.16
-
-mpirun -npernode 14 lmp_gpu -sf gpu -pk gpu 2 -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.gpu.2048K.2.14.16
-
-mpirun -npernode 2 lmp_kokkos_cuda -k on g 2 t 1 -sf kk -pk kokkos comm device -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.kokkos.cuda.2048K.2.1.16
-
-mpirun -np 256 -bind-to core -map-by core -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 1 -sf kk -pk kokkos comm device -v x 64 -v y 64 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.kokkos.omp.2048K.16.1.16

bench/KEPLER/run_weak.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-#SBATCH -N 16 --time=12:00:00
-
-mpirun -npernode 16 lmp_cpu -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.cpu.512K.16.16
-
-mpirun -npernode 16 lmp_omp -sf omp -pk omp 1 -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.omp.512K.16.1.16
-
-mpirun -npernode 2 lmp_cuda -c on -sf cuda -pk cuda 2 -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.cuda.512K.2.16
-
-mpirun -npernode 14 lmp_gpu -sf gpu -pk gpu 2 -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.gpu.512K.2.14.16
-
-mpirun -npernode 2 lmp_kokkos_cuda -k on g 2 t 1 -sf kk -pk kokkos comm device -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.kokkos.cuda.512K.2.1.16
-
-mpirun -np 256 -bind-to core -map-by core -x KMP_AFFINITY=scatter lmp_kokkos_omp -k on t 1 -sf kk -pk kokkos comm device -v x 128 -v y 128 -v z 128 -v t 100 < in.lj
-mv log.lammps log.28Jun14.lj.kokkos.omp.512K.16.1.16

bench/POTENTIALS/CH.rebo

@@ -0,0 +1 @@
+../../potentials/CH.rebo

bench/POTENTIALS/in.rebo

@@ -11,7 +11,7 @@ neighbor	    0.5 bin
 neigh_modify	    delay 5 every 1
 
 pair_style	    rebo
-pair_coeff	    * * CH.airebo C H
+pair_coeff	    * * CH.rebo C H
 
 velocity	    all create 300.0 761341
 

bench/POTENTIALS/log.16Mar18.airebo.1

@@ -1,87 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# AIREBO polyethelene benchmark
-
-units		    metal
-atom_style	    atomic
-
-read_data	    data.airebo
-  orthogonal box = (-2.1 -2.1 0) to (2.1 2.1 25.579)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  60 atoms
-
-replicate	    17 16 2
-  orthogonal box = (-2.1 -2.1 0) to (69.3 65.1 51.158)
-  1 by 1 by 1 MPI processor grid
-  32640 atoms
-  Time spent = 0.00154901 secs
-
-neighbor	    0.5 bin
-neigh_modify	    delay 5 every 1
-
-pair_style	    airebo 3.0 1 1
-pair_coeff	    * * CH.airebo C H
-
-velocity	    all create 300.0 761341
-
-fix		    1 all nve
-timestep	    0.0005
-
-thermo		    10
-run		    100
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 10.7
-  ghost atom cutoff = 10.7
-  binsize = 5.35, bins = 14 13 10
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair airebo, perpetual
-      attributes: full, newton on, ghost
-      pair build: full/bin/ghost
-      stencil: full/ghost/bin/3d
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 106.4 | 106.4 | 106.4 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300    -139299.7            0   -138034.03    7998.7287 
-      10    161.33916   -138711.85            0   -138031.17    33242.273 
-      20    208.59505   -138911.77            0   -138031.73   -3199.2371 
-      30    139.73485   -138617.76            0   -138028.23    10890.529 
-      40    142.15332   -138628.03            0    -138028.3    14614.022 
-      50    114.21945   -138509.87            0   -138027.98    24700.885 
-      60     164.9432   -138725.08            0   -138029.19    35135.722 
-      70    162.14928   -138714.86            0   -138030.77    5666.4609 
-      80    157.17575   -138694.81            0    -138031.7    19838.161 
-      90    196.16354   -138859.65            0   -138032.05   -7942.9718 
-     100    178.30378    -138783.8            0   -138031.55     31012.15 
-Loop time of 60.9424 on 1 procs for 100 steps with 32640 atoms
-
-Performance: 0.071 ns/day, 338.569 hours/ns, 1.641 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    | 55.299     | 55.299     | 55.299     |   0.0 | 90.74
-Neigh   | 5.5777     | 5.5777     | 5.5777     |   0.0 |  9.15
-Comm    | 0.027658   | 0.027658   | 0.027658   |   0.0 |  0.05
-Output  | 0.0011463  | 0.0011463  | 0.0011463  |   0.0 |  0.00
-Modify  | 0.024684   | 0.024684   | 0.024684   |   0.0 |  0.04
-Other   |            | 0.012      |            |       |  0.02
-
-Nlocal:    32640 ave 32640 max 32640 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    48190 ave 48190 max 48190 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:  2.22179e+07 ave 2.22179e+07 max 2.22179e+07 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 22217870
-Ave neighs/atom = 680.695
-Neighbor list builds = 8
-Dangerous builds = 0
-Total wall time: 0:01:02

bench/POTENTIALS/log.16Mar18.airebo.4

@@ -1,87 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# AIREBO polyethelene benchmark
-
-units		    metal
-atom_style	    atomic
-
-read_data	    data.airebo
-  orthogonal box = (-2.1 -2.1 0) to (2.1 2.1 25.579)
-  1 by 1 by 4 MPI processor grid
-  reading atoms ...
-  60 atoms
-
-replicate	    17 16 2
-  orthogonal box = (-2.1 -2.1 0) to (69.3 65.1 51.158)
-  2 by 2 by 1 MPI processor grid
-  32640 atoms
-  Time spent = 0.00070262 secs
-
-neighbor	    0.5 bin
-neigh_modify	    delay 5 every 1
-
-pair_style	    airebo 3.0 1 1
-pair_coeff	    * * CH.airebo C H
-
-velocity	    all create 300.0 761341
-
-fix		    1 all nve
-timestep	    0.0005
-
-thermo		    10
-run		    100
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 10.7
-  ghost atom cutoff = 10.7
-  binsize = 5.35, bins = 14 13 10
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair airebo, perpetual
-      attributes: full, newton on, ghost
-      pair build: full/bin/ghost
-      stencil: full/ghost/bin/3d
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 29.37 | 29.75 | 30.13 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300    -139299.7            0   -138034.03    7998.7287 
-      10    161.33916   -138711.85            0   -138031.17    33242.273 
-      20    208.59505   -138911.77            0   -138031.73   -3199.2371 
-      30    139.73485   -138617.76            0   -138028.23    10890.529 
-      40    142.15332   -138628.03            0    -138028.3    14614.022 
-      50    114.21945   -138509.87            0   -138027.98    24700.885 
-      60     164.9432   -138725.08            0   -138029.19    35135.722 
-      70    162.14928   -138714.86            0   -138030.77    5666.4609 
-      80    157.17575   -138694.81            0    -138031.7    19838.161 
-      90    196.16354   -138859.65            0   -138032.05   -7942.9718 
-     100    178.30378    -138783.8            0   -138031.55     31012.15 
-Loop time of 16.768 on 4 procs for 100 steps with 32640 atoms
-
-Performance: 0.258 ns/day, 93.156 hours/ns, 5.964 timesteps/s
-99.2% CPU use with 4 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 14.538     | 14.589     | 14.654     |   1.3 | 87.00
-Neigh   | 1.8853     | 1.8992     | 1.9159     |   0.8 | 11.33
-Comm    | 0.18073    | 0.25896    | 0.31361    |  10.6 |  1.54
-Output  | 0.00050807 | 0.0040419  | 0.0077746  |   5.6 |  0.02
-Modify  | 0.0094635  | 0.0096973  | 0.0099616  |   0.2 |  0.06
-Other   |            | 0.007481   |            |       |  0.04
-
-Nlocal:    8160 ave 8174 max 8146 min
-Histogram: 1 0 1 0 0 0 0 1 0 1
-Nghost:    22614.5 ave 22629 max 22601 min
-Histogram: 1 1 0 0 0 0 0 1 0 1
-Neighs:    0 ave 0 max 0 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-FullNghs:  5.55447e+06 ave 5.56557e+06 max 5.54193e+06 min
-Histogram: 1 0 0 1 0 0 0 1 0 1
-
-Total # of neighbors = 22217870
-Ave neighs/atom = 680.695
-Neighbor list builds = 8
-Dangerous builds = 0
-Total wall time: 0:00:17

bench/POTENTIALS/log.16Mar18.reaxc.1

@@ -1,93 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# ReaxFF benchmark: simulation of PETN crystal, replicated unit cell
-
-units		real
-atom_style	charge
-
-read_data	data.reax
-  orthogonal box = (0 0 0) to (9.49107 9.49107 6.99123)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  58 atoms
-
-replicate	7 8 10
-  orthogonal box = (0 0 0) to (66.4375 75.9285 69.9123)
-  1 by 1 by 1 MPI processor grid
-  32480 atoms
-  Time spent = 0.00162625 secs
-
-velocity	all create 300.0 9999
-
-pair_style	reax/c NULL
-pair_coeff      * * ffield.reax C H O N
-
-timestep	0.1
-fix		1 all nve
-fix             2 all qeq/reax 1 0.0 10.0 1.0e-6 reax/c
-
-thermo		10
-thermo_style	custom step temp ke pe pxx pyy pzz etotal
-
-run		100
-Neighbor list info ...
-  update every 1 steps, delay 10 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 12
-  ghost atom cutoff = 12
-  binsize = 6, bins = 12 13 12
-  2 neighbor lists, perpetual/occasional/extra = 2 0 0
-  (1) pair reax/c, perpetual
-      attributes: half, newton off, ghost
-      pair build: half/bin/newtoff/ghost
-      stencil: half/ghost/bin/3d/newtoff
-      bin: standard
-  (2) fix qeq/reax, perpetual, copy from (1)
-      attributes: half, newton off, ghost
-      pair build: copy
-      stencil: none
-      bin: none
-Per MPI rank memory allocation (min/avg/max) = 1727 | 1727 | 1727 Mbytes
-Step Temp KinEng PotEng Pxx Pyy Pzz TotEng 
-       0          300    29044.119   -3232140.8    22804.879   -29365.593    6302.5637   -3203096.6 
-      10    299.37479     28983.59   -3232075.2    21746.778    -23987.41    7610.2967   -3203091.6 
-      20     295.5855    28616.735   -3231710.1    18178.568   -10871.882    10603.247   -3203093.3 
-      30    289.48845    28026.457   -3231123.2    12146.362    4985.5572    13364.455   -3203096.8 
-      40    282.66404     27365.76   -3230467.5    4284.2794    18132.771    14133.719   -3203101.7 
-      50    274.97005    26620.876   -3229730.4     -3719.11    25519.692    12551.708   -3203109.5 
-      60    266.11301    25763.393   -3228883.8   -9271.4049    27307.216    9753.2509   -3203120.4 
-      70     259.3263    25106.346   -3228237.2   -11150.726    24238.382    6578.5306   -3203130.8 
-      80    260.33956    25204.444   -3228344.2   -9576.6006     16737.65    3454.5747   -3203139.7 
-      90    269.90199    26130.219   -3229275.5    -5906.376    5246.1572    467.31789   -3203145.3 
-     100    280.76717    27182.117   -3230330.6   -1363.8281   -8133.2509   -1689.7711   -3203148.5 
-Loop time of 437.886 on 1 procs for 100 steps with 32480 atoms
-
-Performance: 0.002 ns/day, 12163.512 hours/ns, 0.228 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    | 350.29     | 350.29     | 350.29     |   0.0 | 80.00
-Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 0.026264   | 0.026264   | 0.026264   |   0.0 |  0.01
-Output  | 0.0024614  | 0.0024614  | 0.0024614  |   0.0 |  0.00
-Modify  | 87.55      | 87.55      | 87.55      |   0.0 | 19.99
-Other   |            | 0.01296    |            |       |  0.00
-
-Nlocal:    32480 ave 32480 max 32480 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    45128 ave 45128 max 45128 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    1.27781e+07 ave 1.27781e+07 max 1.27781e+07 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 12778082
-Ave neighs/atom = 393.414
-Neighbor list builds = 0
-Dangerous builds = 0
-
-Please see the log.cite file for references relevant to this simulation
-
-Total wall time: 0:07:24

bench/POTENTIALS/log.16Mar18.reaxc.4

@@ -1,93 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# ReaxFF benchmark: simulation of PETN crystal, replicated unit cell
-
-units		real
-atom_style	charge
-
-read_data	data.reax
-  orthogonal box = (0 0 0) to (9.49107 9.49107 6.99123)
-  2 by 2 by 1 MPI processor grid
-  reading atoms ...
-  58 atoms
-
-replicate	7 8 10
-  orthogonal box = (0 0 0) to (66.4375 75.9285 69.9123)
-  1 by 2 by 2 MPI processor grid
-  32480 atoms
-  Time spent = 0.000803709 secs
-
-velocity	all create 300.0 9999
-
-pair_style	reax/c NULL
-pair_coeff      * * ffield.reax C H O N
-
-timestep	0.1
-fix		1 all nve
-fix             2 all qeq/reax 1 0.0 10.0 1.0e-6 reax/c
-
-thermo		10
-thermo_style	custom step temp ke pe pxx pyy pzz etotal
-
-run		100
-Neighbor list info ...
-  update every 1 steps, delay 10 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 12
-  ghost atom cutoff = 12
-  binsize = 6, bins = 12 13 12
-  2 neighbor lists, perpetual/occasional/extra = 2 0 0
-  (1) pair reax/c, perpetual
-      attributes: half, newton off, ghost
-      pair build: half/bin/newtoff/ghost
-      stencil: half/ghost/bin/3d/newtoff
-      bin: standard
-  (2) fix qeq/reax, perpetual, copy from (1)
-      attributes: half, newton off, ghost
-      pair build: copy
-      stencil: none
-      bin: none
-Per MPI rank memory allocation (min/avg/max) = 647 | 647 | 647 Mbytes
-Step Temp KinEng PotEng Pxx Pyy Pzz TotEng 
-       0          300    29044.119   -3232140.8    22804.879   -29365.593    6302.5638   -3203096.6 
-      10    299.37479     28983.59   -3232075.2    21746.773   -23987.409    7610.2911   -3203091.6 
-      20    295.58552    28616.737   -3231710.1    18178.576   -10871.874    10603.421   -3203093.3 
-      30    289.48843    28026.455   -3231123.3    12146.158    4985.3436    13364.461   -3203096.8 
-      40    282.66409    27365.764   -3230467.5    4284.5077    18133.151    14133.949   -3203101.7 
-      50    274.97008    26620.879   -3229730.3    -3718.536    25520.328    12552.195   -3203109.5 
-      60    266.11301    25763.393   -3228883.7   -9271.0381    27307.591    9753.5339   -3203120.4 
-      70    259.32631    25106.348   -3228237.1   -11150.314    24238.962    6578.8636   -3203130.8 
-      80    260.33966    25204.453   -3228344.1   -9575.5709    16738.467    3455.2525   -3203139.7 
-      90    269.90213    26130.231   -3229275.5   -5906.0456    5246.2122    467.43473   -3203145.2 
-     100    280.76727    27182.127   -3230330.6   -1363.1733   -8132.8726   -1689.3275   -3203148.4 
-Loop time of 128.275 on 4 procs for 100 steps with 32480 atoms
-
-Performance: 0.007 ns/day, 3563.196 hours/ns, 0.780 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    | 92.314     | 97.932     | 103.53     |  44.1 | 76.34
-Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 0.039458   | 5.6409     | 11.263     | 184.0 |  4.40
-Output  | 0.00086117 | 0.0010868  | 0.0016167  |   0.9 |  0.00
-Modify  | 24.687     | 24.688     | 24.69      |   0.0 | 19.25
-Other   |            | 0.01323    |            |       |  0.01
-
-Nlocal:    8120 ave 8120 max 8120 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Nghost:    21992 ave 21992 max 21992 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Neighs:    3.48274e+06 ave 3.48274e+06 max 3.48274e+06 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 13930976
-Ave neighs/atom = 428.909
-Neighbor list builds = 0
-Dangerous builds = 0
-
-Please see the log.cite file for references relevant to this simulation
-
-Total wall time: 0:02:10

bench/POTENTIALS/log.16Mar18.rebo.1

@@ -1,87 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# REBO polyethelene benchmark
-
-units		    metal
-atom_style	    atomic
-
-read_data	    data.rebo
-  orthogonal box = (-2.1 -2.1 0) to (2.1 2.1 25.579)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  60 atoms
-
-replicate	    17 16 2
-  orthogonal box = (-2.1 -2.1 0) to (69.3 65.1 51.158)
-  1 by 1 by 1 MPI processor grid
-  32640 atoms
-  Time spent = 0.00151849 secs
-
-neighbor	    0.5 bin
-neigh_modify	    delay 5 every 1
-
-pair_style	    rebo
-pair_coeff	    * * CH.airebo C H
-
-velocity	    all create 300.0 761341
-
-fix		    1 all nve
-timestep	    0.0005
-
-thermo		    10
-run		    100
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.5
-  ghost atom cutoff = 6.5
-  binsize = 3.25, bins = 22 21 16
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair rebo, perpetual
-      attributes: full, newton on, ghost
-      pair build: full/bin/ghost
-      stencil: full/ghost/bin/3d
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 34.21 | 34.21 | 34.21 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300   -138442.48            0    -137176.8    2464.5258 
-      10    179.38052   -137930.92            0   -137174.12     15656.95 
-      20    206.87725   -138046.63            0   -137173.83   -24042.005 
-      30    150.80048   -137807.07            0   -137170.86   -16524.069 
-      40    173.25027      -137902            0   -137171.07   -5716.7297 
-      50    151.80552   -137812.01            0   -137171.55    3481.1096 
-      60    199.08762   -138013.46            0   -137173.53    17882.906 
-      70     217.8592   -138093.51            0   -137174.38   -12269.648 
-      80    202.37612   -138029.05            0   -137175.24   -7622.1573 
-      90      194.905   -137996.68            0    -137174.4   -32267.297 
-     100    185.17966   -137954.16            0    -137172.9   -6902.1493 
-Loop time of 5.17257 on 1 procs for 100 steps with 32640 atoms
-
-Performance: 0.835 ns/day, 28.737 hours/ns, 19.333 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    | 3.3427     | 3.3427     | 3.3427     |   0.0 | 64.62
-Neigh   | 1.7764     | 1.7764     | 1.7764     |   0.0 | 34.34
-Comm    | 0.017914   | 0.017914   | 0.017914   |   0.0 |  0.35
-Output  | 0.0011199  | 0.0011199  | 0.0011199  |   0.0 |  0.02
-Modify  | 0.024357   | 0.024357   | 0.024357   |   0.0 |  0.47
-Other   |            | 0.01004    |            |       |  0.19
-
-Nlocal:    32640 ave 32640 max 32640 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    26460 ave 26460 max 26460 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:  4.90213e+06 ave 4.90213e+06 max 4.90213e+06 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 4902132
-Ave neighs/atom = 150.188
-Neighbor list builds = 9
-Dangerous builds = 0
-Total wall time: 0:00:05

bench/POTENTIALS/log.16Mar18.rebo.4

@@ -1,87 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# REBO polyethelene benchmark
-
-units		    metal
-atom_style	    atomic
-
-read_data	    data.rebo
-  orthogonal box = (-2.1 -2.1 0) to (2.1 2.1 25.579)
-  1 by 1 by 4 MPI processor grid
-  reading atoms ...
-  60 atoms
-
-replicate	    17 16 2
-  orthogonal box = (-2.1 -2.1 0) to (69.3 65.1 51.158)
-  2 by 2 by 1 MPI processor grid
-  32640 atoms
-  Time spent = 0.000838995 secs
-
-neighbor	    0.5 bin
-neigh_modify	    delay 5 every 1
-
-pair_style	    rebo
-pair_coeff	    * * CH.airebo C H
-
-velocity	    all create 300.0 761341
-
-fix		    1 all nve
-timestep	    0.0005
-
-thermo		    10
-run		    100
-Neighbor list info ...
-  update every 1 steps, delay 5 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 6.5
-  ghost atom cutoff = 6.5
-  binsize = 3.25, bins = 22 21 16
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair rebo, perpetual
-      attributes: full, newton on, ghost
-      pair build: full/bin/ghost
-      stencil: full/ghost/bin/3d
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 11.75 | 11.94 | 12.13 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300   -138442.48            0    -137176.8    2464.5258 
-      10    179.38052   -137930.92            0   -137174.12     15656.95 
-      20    206.87725   -138046.63            0   -137173.83   -24042.005 
-      30    150.80048   -137807.07            0   -137170.86   -16524.069 
-      40    173.25027      -137902            0   -137171.07   -5716.7297 
-      50    151.80552   -137812.01            0   -137171.55    3481.1096 
-      60    199.08762   -138013.46            0   -137173.53    17882.906 
-      70     217.8592   -138093.51            0   -137174.38   -12269.648 
-      80    202.37612   -138029.05            0   -137175.24   -7622.1573 
-      90      194.905   -137996.68            0    -137174.4   -32267.297 
-     100    185.17966   -137954.16            0    -137172.9   -6902.1493 
-Loop time of 1.52214 on 4 procs for 100 steps with 32640 atoms
-
-Performance: 2.838 ns/day, 8.456 hours/ns, 65.697 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    | 0.88531    | 0.90632    | 0.92546    |   1.6 | 59.54
-Neigh   | 0.53954    | 0.54258    | 0.54621    |   0.3 | 35.65
-Comm    | 0.035654   | 0.058364   | 0.079543   |   7.0 |  3.83
-Output  | 0.00048494 | 0.00065351 | 0.0011017  |   0.0 |  0.04
-Modify  | 0.0090034  | 0.0090633  | 0.0091114  |   0.0 |  0.60
-Other   |            | 0.005168   |            |       |  0.34
-
-Nlocal:    8160 ave 8163 max 8157 min
-Histogram: 1 1 0 0 0 0 0 0 1 1
-Nghost:    11605.8 ave 11615 max 11593 min
-Histogram: 1 0 0 0 0 0 2 0 0 1
-Neighs:    0 ave 0 max 0 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-FullNghs:  1.22553e+06 ave 1.22734e+06 max 1.22455e+06 min
-Histogram: 2 0 0 1 0 0 0 0 0 1
-
-Total # of neighbors = 4902132
-Ave neighs/atom = 150.188
-Neighbor list builds = 9
-Dangerous builds = 0
-Total wall time: 0:00:01

bench/POTENTIALS/log.16Mar18.spce.1

@@ -1,132 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# SPC/E water box benchmark
-
-units		real
-atom_style	full
-
-read_data	data.spce
-  orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  4500 atoms
-  scanning bonds ...
-  2 = max bonds/atom
-  scanning angles ...
-  1 = max angles/atom
-  reading bonds ...
-  3000 bonds
-  reading angles ...
-  1500 angles
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-
-replicate	2 4 1
-  orthogonal box = (0.02645 0.02645 0.02641) to (71.0392 142.052 35.4736)
-  1 by 1 by 1 MPI processor grid
-  36000 atoms
-  24000 bonds
-  12000 angles
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-  Time spent = 0.0105426 secs
-
-pair_style	lj/cut/coul/long 9.8 9.8
-kspace_style	pppm 1.0e-4
-
-pair_coeff	1 1 0.15535 3.166
-pair_coeff	* 2 0.0000 0.0000
-
-bond_style	harmonic
-angle_style	harmonic
-dihedral_style	none
-improper_style	none
-
-bond_coeff	1 1000.00 1.000
-angle_coeff	1 100.0 109.47
-
-special_bonds   lj/coul 0.0 0.0 0.5
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-
-neighbor        2.0 bin
-neigh_modify	every 1 delay 10 check yes
-
-fix		1 all shake 0.0001 20 0 b 1 a 1
-  0 = # of size 2 clusters
-  0 = # of size 3 clusters
-  0 = # of size 4 clusters
-  12000 = # of frozen angles
-fix		2 all nvt temp 300.0 300.0 100.0
-
-velocity	all create 300 432567 dist uniform
-
-timestep	2.0
-
-thermo_style    one
-thermo		50
-
-run		100
-PPPM initialization ...
-  using 12-bit tables for long-range coulomb (../kspace.cpp:321)
-  G vector (1/distance) = 0.268801
-  grid = 36 64 24
-  stencil order = 5
-  estimated absolute RMS force accuracy = 0.0331015
-  estimated relative force accuracy = 9.96841e-05
-  using double precision FFTs
-  3d grid and FFT values/proc = 91977 55296
-Neighbor list info ...
-  update every 1 steps, delay 10 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 11.8
-  ghost atom cutoff = 11.8
-  binsize = 5.9, bins = 13 25 7
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair lj/cut/coul/long, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 105.1 | 105.1 | 105.1 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300   -133281.51            0   -111820.57    516.17807 
-      50    264.98553   -136986.74            0   -118030.61   -440.29256 
-     100    274.45966   -136364.57            0   -116730.69   -128.61949 
-Loop time of 20.172 on 1 procs for 100 steps with 36000 atoms
-
-Performance: 0.857 ns/day, 28.017 hours/ns, 4.957 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    | 15.818     | 15.818     | 15.818     |   0.0 | 78.41
-Bond    | 7.8201e-05 | 7.8201e-05 | 7.8201e-05 |   0.0 |  0.00
-Kspace  | 1.966      | 1.966      | 1.966      |   0.0 |  9.75
-Neigh   | 2.0639     | 2.0639     | 2.0639     |   0.0 | 10.23
-Comm    | 0.043918   | 0.043918   | 0.043918   |   0.0 |  0.22
-Output  | 0.00025153 | 0.00025153 | 0.00025153 |   0.0 |  0.00
-Modify  | 0.27056    | 0.27056    | 0.27056    |   0.0 |  1.34
-Other   |            | 0.009522   |            |       |  0.05
-
-Nlocal:    36000 ave 36000 max 36000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    56963 ave 56963 max 56963 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    1.24625e+07 ave 1.24625e+07 max 1.24625e+07 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 12462451
-Ave neighs/atom = 346.179
-Ave special neighs/atom = 2
-Neighbor list builds = 9
-Dangerous builds = 6
-Total wall time: 0:00:20

bench/POTENTIALS/log.16Mar18.spce.4

@@ -1,132 +0,0 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
-  using 1 OpenMP thread(s) per MPI task
-# SPC/E water box benchmark
-
-units		real
-atom_style	full
-
-read_data	data.spce
-  orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
-  2 by 2 by 1 MPI processor grid
-  reading atoms ...
-  4500 atoms
-  scanning bonds ...
-  2 = max bonds/atom
-  scanning angles ...
-  1 = max angles/atom
-  reading bonds ...
-  3000 bonds
-  reading angles ...
-  1500 angles
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-
-replicate	2 4 1
-  orthogonal box = (0.02645 0.02645 0.02641) to (71.0392 142.052 35.4736)
-  1 by 4 by 1 MPI processor grid
-  36000 atoms
-  24000 bonds
-  12000 angles
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-  Time spent = 0.00535488 secs
-
-pair_style	lj/cut/coul/long 9.8 9.8
-kspace_style	pppm 1.0e-4
-
-pair_coeff	1 1 0.15535 3.166
-pair_coeff	* 2 0.0000 0.0000
-
-bond_style	harmonic
-angle_style	harmonic
-dihedral_style	none
-improper_style	none
-
-bond_coeff	1 1000.00 1.000
-angle_coeff	1 100.0 109.47
-
-special_bonds   lj/coul 0.0 0.0 0.5
-  2 = max # of 1-2 neighbors
-  1 = max # of 1-3 neighbors
-  1 = max # of 1-4 neighbors
-  2 = max # of special neighbors
-
-neighbor        2.0 bin
-neigh_modify	every 1 delay 10 check yes
-
-fix		1 all shake 0.0001 20 0 b 1 a 1
-  0 = # of size 2 clusters
-  0 = # of size 3 clusters
-  0 = # of size 4 clusters
-  12000 = # of frozen angles
-fix		2 all nvt temp 300.0 300.0 100.0
-
-velocity	all create 300 432567 dist uniform
-
-timestep	2.0
-
-thermo_style    one
-thermo		50
-
-run		100
-PPPM initialization ...
-  using 12-bit tables for long-range coulomb (../kspace.cpp:321)
-  G vector (1/distance) = 0.268801
-  grid = 36 64 24
-  stencil order = 5
-  estimated absolute RMS force accuracy = 0.0331015
-  estimated relative force accuracy = 9.96841e-05
-  using double precision FFTs
-  3d grid and FFT values/proc = 27993 13824
-Neighbor list info ...
-  update every 1 steps, delay 10 steps, check yes
-  max neighbors/atom: 2000, page size: 100000
-  master list distance cutoff = 11.8
-  ghost atom cutoff = 11.8
-  binsize = 5.9, bins = 13 25 7
-  1 neighbor lists, perpetual/occasional/extra = 1 0 0
-  (1) pair lj/cut/coul/long, perpetual
-      attributes: half, newton on
-      pair build: half/bin/newton
-      stencil: half/bin/3d/newton
-      bin: standard
-Per MPI rank memory allocation (min/avg/max) = 37.74 | 37.74 | 37.74 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0          300   -133281.51            0   -111820.57    516.17807 
-      50    264.98553   -136986.74            0   -118030.61   -440.29256 
-     100    274.45966   -136364.57            0   -116730.69   -128.61949 
-Loop time of 5.43807 on 4 procs for 100 steps with 36000 atoms
-
-Performance: 3.178 ns/day, 7.553 hours/ns, 18.389 timesteps/s
-99.1% CPU use with 4 MPI tasks x 1 OpenMP threads
-
-MPI task timing breakdown:
-Section |  min time  |  avg time  |  max time  |%varavg| %total
----------------------------------------------------------------
-Pair    | 4.0016     | 4.0968     | 4.1706     |   3.3 | 75.34
-Bond    | 7.1049e-05 | 8.5771e-05 | 0.00010586 |   0.0 |  0.00
-Kspace  | 0.56386    | 0.63614    | 0.73036    |   8.3 | 11.70
-Neigh   | 0.52575    | 0.52587    | 0.52594    |   0.0 |  9.67
-Comm    | 0.045847   | 0.047308   | 0.048331   |   0.4 |  0.87
-Output  | 9.1314e-05 | 0.00012183 | 0.00021172 |   0.0 |  0.00
-Modify  | 0.12561    | 0.1258     | 0.12605    |   0.1 |  2.31
-Other   |            | 0.005944   |            |       |  0.11
-
-Nlocal:    9000 ave 9002 max 8998 min
-Histogram: 2 0 0 0 0 0 0 0 0 2
-Nghost:    24134.2 ave 24184 max 24062 min
-Histogram: 1 0 0 0 0 0 1 1 0 1
-Neighs:    3.11561e+06 ave 3.11676e+06 max 3.11446e+06 min
-Histogram: 1 0 0 1 0 0 1 0 0 1
-
-Total # of neighbors = 12462451
-Ave neighs/atom = 346.179
-Ave special neighs/atom = 2
-Neighbor list builds = 9
-Dangerous builds = 6
-Total wall time: 0:00:05

bench/POTENTIALS/log.9Oct20.adp.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Ni in ADP
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.52
-Lattice spacing in x,y,z = 3.52 3.52 3.52
+Lattice spacing in x,y,z = 3.5200000 3.5200000 3.5200000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (70.4 70.4 70.4)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (70.400000 70.400000 70.400000)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00184107 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	adp
 pair_coeff	* * Ni.adp Ni
+Reading adp potential file Ni.adp with DATE: 2011-06-20
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -41,35 +41,35 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 27.56 | 27.56 | 27.56 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 27.57 | 27.57 | 27.57 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -142400            0   -135782.09    20259.105 
      100    793.05485   -139023.13            0    -135742.9    32175.694 
-Loop time of 11.9854 on 1 procs for 100 steps with 32000 atoms
+Loop time of 11.0841 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 3.604 ns/day, 6.659 hours/ns, 8.344 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 3.897 ns/day, 6.158 hours/ns, 9.022 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 11.447     | 11.447     | 11.447     |   0.0 | 95.51
-Neigh   | 0.48465    | 0.48465    | 0.48465    |   0.0 |  4.04
-Comm    | 0.019317   | 0.019317   | 0.019317   |   0.0 |  0.16
-Output  | 0.00011063 | 0.00011063 | 0.00011063 |   0.0 |  0.00
-Modify  | 0.025319   | 0.025319   | 0.025319   |   0.0 |  0.21
-Other   |            | 0.009125   |            |       |  0.08
+Pair    | 10.597     | 10.597     | 10.597     |   0.0 | 95.60
+Neigh   | 0.43765    | 0.43765    | 0.43765    |   0.0 |  3.95
+Comm    | 0.018561   | 0.018561   | 0.018561   |   0.0 |  0.17
+Output  | 0.0001123  | 0.0001123  | 0.0001123  |   0.0 |  0.00
+Modify  | 0.023261   | 0.023261   | 0.023261   |   0.0 |  0.21
+Other   |            | 0.00792    |            |       |  0.07
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    19911 ave 19911 max 19911 min
+Nghost:        19911.0 ave       19911 max       19911 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    1.33704e+06 ave 1.33704e+06 max 1.33704e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 1337035
-Ave neighs/atom = 41.7823
+Ave neighs/atom = 41.782344
 Neighbor list builds = 13
 Dangerous builds = 0
 
-Total wall time: 0:00:12
+Total wall time: 0:00:11

bench/POTENTIALS/log.9Oct20.adp.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Ni in ADP
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.52
-Lattice spacing in x,y,z = 3.52 3.52 3.52
+Lattice spacing in x,y,z = 3.5200000 3.5200000 3.5200000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (70.4 70.4 70.4)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (70.400000 70.400000 70.400000)
   1 by 2 by 2 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000586033 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	adp
 pair_coeff	* * Ni.adp Ni
+Reading adp potential file Ni.adp with DATE: 2011-06-20
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -45,30 +45,30 @@ Per MPI rank memory allocation (min/avg/max) = 12.45 | 12.45 | 12.45 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -142400            0   -135782.09    20259.105 
      100    793.05485   -139023.13            0    -135742.9    32175.694 
-Loop time of 3.49752 on 4 procs for 100 steps with 32000 atoms
+Loop time of 3.54402 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 12.352 ns/day, 1.943 hours/ns, 28.592 timesteps/s
-99.1% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 12.190 ns/day, 1.969 hours/ns, 28.217 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    | 3.3203     | 3.3261     | 3.3317     |   0.3 | 95.10
-Neigh   | 0.12544    | 0.12594    | 0.12634    |   0.1 |  3.60
-Comm    | 0.024059   | 0.03001    | 0.035574   |   2.9 |  0.86
-Output  | 4.8161e-05 | 6.8128e-05 | 0.00011802 |   0.0 |  0.00
-Modify  | 0.010666   | 0.010841   | 0.011109   |   0.2 |  0.31
-Other   |            | 0.00457    |            |       |  0.13
+Pair    | 3.2768     | 3.3041     | 3.339      |   1.2 | 93.23
+Neigh   | 0.11542    | 0.11601    | 0.11661    |   0.1 |  3.27
+Comm    | 0.068218   | 0.10201    | 0.13103    |   7.0 |  2.88
+Output  | 4.4823e-05 | 8.0943e-05 | 0.000175   |   0.0 |  0.00
+Modify  | 0.010904   | 0.011064   | 0.011172   |   0.1 |  0.31
+Other   |            | 0.01075    |            |       |  0.30
 
-Nlocal:    8000 ave 8044 max 7960 min
+Nlocal:        8000.00 ave        8044 max        7960 min
 Histogram: 1 0 0 1 0 1 0 0 0 1
-Nghost:    9131 ave 9171 max 9087 min
+Nghost:        9131.00 ave        9171 max        9087 min
 Histogram: 1 0 0 0 1 0 1 0 0 1
-Neighs:    334259 ave 336108 max 332347 min
+Neighs:       334259.0 ave      336108 max      332347 min
 Histogram: 1 0 0 1 0 0 1 0 0 1
 
 Total # of neighbors = 1337035
-Ave neighs/atom = 41.7823
+Ave neighs/atom = 41.782344
 Neighbor list builds = 13
 Dangerous builds = 0
 

bench/POTENTIALS/log.9Oct20.airebo.1

@@ -0,0 +1,90 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# AIREBO polyethelene benchmark
+
+units		    metal
+atom_style	    atomic
+
+read_data	    data.airebo
+Reading data file ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (2.1000000 2.1000000 25.579000)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  60 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	    17 16 2
+Replicating atoms ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (69.300000 65.100000 51.158000)
+  1 by 1 by 1 MPI processor grid
+  32640 atoms
+  replicate CPU = 0.002 seconds
+
+neighbor	    0.5 bin
+neigh_modify	    delay 5 every 1
+
+pair_style	    airebo 3.0 1 1
+pair_coeff	    * * CH.airebo C H
+Reading airebo potential file CH.airebo with DATE: 2011-10-25
+
+velocity	    all create 300.0 761341
+
+fix		    1 all nve
+timestep	    0.0005
+
+thermo		    10
+run		    100
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 10.7
+  ghost atom cutoff = 10.7
+  binsize = 5.35, bins = 14 13 10
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair airebo, perpetual
+      attributes: full, newton on, ghost
+      pair build: full/bin/ghost
+      stencil: full/ghost/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 106.4 | 106.4 | 106.4 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -139300.72            0   -138035.04    7988.6646 
+      10    161.34683    -138712.9            0   -138032.19    33228.921 
+      20    208.59504   -138912.79            0   -138032.74   -3211.8806 
+      30     139.7513   -138618.85            0   -138029.25    10878.143 
+      40    142.14562   -138629.02            0   -138029.32    14601.302 
+      50    114.23401   -138510.95            0      -138029    24691.124 
+      60    164.92002      -138726            0   -138030.21    35125.541 
+      70    162.15256    -138715.9            0   -138031.79    5658.7946 
+      80    157.16184   -138695.77            0   -138032.72    19824.698 
+      90    196.15907   -138860.65            0   -138033.07   -7950.8463 
+     100    178.31875   -138784.89            0   -138032.57    30997.671 
+Loop time of 58.0757 on 1 procs for 100 steps with 32640 atoms
+
+Performance: 0.074 ns/day, 322.643 hours/ns, 1.722 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 53.513     | 53.513     | 53.513     |   0.0 | 92.14
+Neigh   | 4.5013     | 4.5013     | 4.5013     |   0.0 |  7.75
+Comm    | 0.026609   | 0.026609   | 0.026609   |   0.0 |  0.05
+Output  | 0.0010192  | 0.0010192  | 0.0010192  |   0.0 |  0.00
+Modify  | 0.02275    | 0.02275    | 0.02275    |   0.0 |  0.04
+Other   |            | 0.01074    |            |       |  0.02
+
+Nlocal:        32640.0 ave       32640 max       32640 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:        48190.0 ave       48190 max       48190 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:        0.00000 ave           0 max           0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+FullNghs:  2.22178e+07 ave 2.22178e+07 max 2.22178e+07 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 22217840
+Ave neighs/atom = 680.69363
+Neighbor list builds = 8
+Dangerous builds = 0
+Total wall time: 0:00:59

bench/POTENTIALS/log.9Oct20.airebo.4

@@ -0,0 +1,90 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# AIREBO polyethelene benchmark
+
+units		    metal
+atom_style	    atomic
+
+read_data	    data.airebo
+Reading data file ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (2.1000000 2.1000000 25.579000)
+  1 by 1 by 4 MPI processor grid
+  reading atoms ...
+  60 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	    17 16 2
+Replicating atoms ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (69.300000 65.100000 51.158000)
+  2 by 2 by 1 MPI processor grid
+  32640 atoms
+  replicate CPU = 0.001 seconds
+
+neighbor	    0.5 bin
+neigh_modify	    delay 5 every 1
+
+pair_style	    airebo 3.0 1 1
+pair_coeff	    * * CH.airebo C H
+Reading airebo potential file CH.airebo with DATE: 2011-10-25
+
+velocity	    all create 300.0 761341
+
+fix		    1 all nve
+timestep	    0.0005
+
+thermo		    10
+run		    100
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 10.7
+  ghost atom cutoff = 10.7
+  binsize = 5.35, bins = 14 13 10
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair airebo, perpetual
+      attributes: full, newton on, ghost
+      pair build: full/bin/ghost
+      stencil: full/ghost/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 29.43 | 29.81 | 30.19 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -139300.72            0   -138035.04    7988.6646 
+      10    161.34683    -138712.9            0   -138032.19    33228.921 
+      20    208.59504   -138912.79            0   -138032.74   -3211.8806 
+      30     139.7513   -138618.85            0   -138029.25    10878.143 
+      40    142.14562   -138629.02            0   -138029.32    14601.302 
+      50    114.23401   -138510.95            0      -138029    24691.124 
+      60    164.92002      -138726            0   -138030.21    35125.541 
+      70    162.15256    -138715.9            0   -138031.79    5658.7946 
+      80    157.16184   -138695.77            0   -138032.72    19824.698 
+      90    196.15907   -138860.65            0   -138033.07   -7950.8463 
+     100    178.31875   -138784.89            0   -138032.57    30997.671 
+Loop time of 17.206 on 4 procs for 100 steps with 32640 atoms
+
+Performance: 0.251 ns/day, 95.589 hours/ns, 5.812 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    | 14.655     | 14.727     | 14.848     |   1.9 | 85.59
+Neigh   | 1.5571     | 1.6135     | 1.6871     |   3.7 |  9.38
+Comm    | 0.7741     | 0.83422    | 0.90385    |   5.8 |  4.85
+Output  | 0.00047541 | 0.0027475  | 0.009517   |   7.5 |  0.02
+Modify  | 0.0091925  | 0.009367   | 0.0096078  |   0.2 |  0.05
+Other   |            | 0.01908    |            |       |  0.11
+
+Nlocal:        8160.00 ave        8174 max        8146 min
+Histogram: 1 0 1 0 0 0 0 1 0 1
+Nghost:        22614.5 ave       22629 max       22601 min
+Histogram: 1 1 0 0 0 0 0 1 0 1
+Neighs:        0.00000 ave           0 max           0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+FullNghs:  5.55446e+06 ave 5.56556e+06 max 5.54192e+06 min
+Histogram: 1 0 0 1 0 0 0 1 0 1
+
+Total # of neighbors = 22217840
+Ave neighs/atom = 680.69363
+Neighbor list builds = 8
+Dangerous builds = 0
+Total wall time: 0:00:17

bench/POTENTIALS/log.9Oct20.bop.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk CdTe via BOP
 
@@ -7,19 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		custom 6.82884 		basis 0.0 0.0 0.0 basis 0.25 0.25 0.25 		basis 0.0 0.5 0.5 basis 0.25 0.75 0.75 		basis 0.5 0.0 0.5 basis 0.75 0.25 0.75 		basis 0.5 0.5 0.0 basis 0.75 0.75 0.25
-Lattice spacing in x,y,z = 6.82884 6.82884 6.82884
+Lattice spacing in x,y,z = 6.8288400 6.8288400 6.8288400
 region		box block 0 20 0 20 0 10
 create_box	2 box
-Created orthogonal box = (0 0 0) to (136.577 136.577 68.2884)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (136.57680 136.57680 68.288400)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box basis 2 2 basis 4 2 basis 6 2 basis 8 2
 Created 32000 atoms
-  Time spent = 0.00191426 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	bop
 pair_coeff	* * CdTe.bop.table Cd Te
-Reading potential file CdTe.bop.table with DATE: 2012-06-25
-Reading potential file CdTe.bop.table with DATE: 2012-06-25
+Reading bop potential file CdTe.bop.table with DATE: 2012-06-25
 mass		1 112.4
 mass		2 127.6
 
@@ -51,32 +49,32 @@ Per MPI rank memory allocation (min/avg/max) = 19.39 | 19.39 | 19.39 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000   -69539.487            0   -65403.292    3473.2595 
      100    572.16481   -67769.936            0    -65403.35    1838.6993 
-Loop time of 24.1696 on 1 procs for 100 steps with 32000 atoms
+Loop time of 36.0284 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 0.357 ns/day, 67.138 hours/ns, 4.137 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 0.240 ns/day, 100.079 hours/ns, 2.776 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 23.355     | 23.355     | 23.355     |   0.0 | 96.63
-Neigh   | 0.7545     | 0.7545     | 0.7545     |   0.0 |  3.12
-Comm    | 0.026978   | 0.026978   | 0.026978   |   0.0 |  0.11
-Output  | 0.0001111  | 0.0001111  | 0.0001111  |   0.0 |  0.00
-Modify  | 0.024145   | 0.024145   | 0.024145   |   0.0 |  0.10
-Other   |            | 0.009326   |            |       |  0.04
+Pair    | 35.306     | 35.306     | 35.306     |   0.0 | 97.99
+Neigh   | 0.66375    | 0.66375    | 0.66375    |   0.0 |  1.84
+Comm    | 0.027954   | 0.027954   | 0.027954   |   0.0 |  0.08
+Output  | 9.9182e-05 | 9.9182e-05 | 9.9182e-05 |   0.0 |  0.00
+Modify  | 0.022574   | 0.022574   | 0.022574   |   0.0 |  0.06
+Other   |            | 0.008374   |            |       |  0.02
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    35071 ave 35071 max 35071 min
+Nghost:        35071.0 ave       35071 max       35071 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-FullNghs:  141288 ave 141288 max 141288 min
+FullNghs:     141288.0 ave      141288 max      141288 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 141288
-Ave neighs/atom = 4.41525
+Ave neighs/atom = 4.4152500
 Neighbor list builds = 14
 Dangerous builds = 0
-Total wall time: 0:00:24
+Total wall time: 0:00:36

bench/POTENTIALS/log.9Oct20.bop.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk CdTe via BOP
 
@@ -7,19 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		custom 6.82884 		basis 0.0 0.0 0.0 basis 0.25 0.25 0.25 		basis 0.0 0.5 0.5 basis 0.25 0.75 0.75 		basis 0.5 0.0 0.5 basis 0.75 0.25 0.75 		basis 0.5 0.5 0.0 basis 0.75 0.75 0.25
-Lattice spacing in x,y,z = 6.82884 6.82884 6.82884
+Lattice spacing in x,y,z = 6.8288400 6.8288400 6.8288400
 region		box block 0 20 0 20 0 10
 create_box	2 box
-Created orthogonal box = (0 0 0) to (136.577 136.577 68.2884)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (136.57680 136.57680 68.288400)
   2 by 2 by 1 MPI processor grid
 create_atoms	1 box basis 2 2 basis 4 2 basis 6 2 basis 8 2
 Created 32000 atoms
-  Time spent = 0.000597477 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	bop
 pair_coeff	* * CdTe.bop.table Cd Te
-Reading potential file CdTe.bop.table with DATE: 2012-06-25
-Reading potential file CdTe.bop.table with DATE: 2012-06-25
+Reading bop potential file CdTe.bop.table with DATE: 2012-06-25
 mass		1 112.4
 mass		2 127.6
 
@@ -47,36 +45,36 @@ Neighbor list info ...
       pair build: full/bin/ghost
       stencil: full/ghost/bin/3d
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 8.497 | 8.497 | 8.497 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 8.495 | 8.495 | 8.495 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000   -69539.487            0   -65403.292    3473.2595 
      100    572.16481   -67769.936            0    -65403.35    1838.6993 
-Loop time of 6.50033 on 4 procs for 100 steps with 32000 atoms
+Loop time of 10.2579 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 1.329 ns/day, 18.056 hours/ns, 15.384 timesteps/s
-99.2% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 0.842 ns/day, 28.494 hours/ns, 9.749 timesteps/s
+97.2% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 5.7879     | 5.975      | 6.1607     |   5.4 | 91.92
-Neigh   | 0.27603    | 0.27621    | 0.27647    |   0.0 |  4.25
-Comm    | 0.049869   | 0.23531    | 0.42241    |  27.2 |  3.62
-Output  | 4.9829e-05 | 5.9724e-05 | 8.5592e-05 |   0.0 |  0.00
-Modify  | 0.0089927  | 0.0090921  | 0.0092406  |   0.1 |  0.14
-Other   |            | 0.004665   |            |       |  0.07
+Pair    | 9.0899     | 9.3839     | 9.6808     |   6.9 | 91.48
+Neigh   | 0.24734    | 0.2533     | 0.25828    |   0.8 |  2.47
+Comm    | 0.30495    | 0.60685    | 0.89832    |  27.5 |  5.92
+Output  | 4.673e-05  | 7.695e-05  | 0.00016189 |   0.0 |  0.00
+Modify  | 0.0092409  | 0.00937    | 0.0094445  |   0.1 |  0.09
+Other   |            | 0.004455   |            |       |  0.04
 
-Nlocal:    8000 ave 8006 max 7994 min
+Nlocal:        8000.00 ave        8006 max        7994 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Nghost:    15171 ave 15177 max 15165 min
+Nghost:        15171.0 ave       15177 max       15165 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-FullNghs:  35322 ave 35412 max 35267 min
+FullNghs:      35322.0 ave       35412 max       35267 min
 Histogram: 1 0 1 1 0 0 0 0 0 1
 
 Total # of neighbors = 141288
-Ave neighs/atom = 4.41525
+Ave neighs/atom = 4.4152500
 Neighbor list builds = 14
 Dangerous builds = 0
-Total wall time: 0:00:06
+Total wall time: 0:00:10

bench/POTENTIALS/log.9Oct20.comb.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # SiO2 for COMB potential
 
@@ -7,10 +6,12 @@ units		metal
 atom_style	charge
 
 read_data  	data.comb
-  triclinic box = (0 0 0) to (74.58 74.58 83.064) with tilt (0 0 0)
+Reading data file ...
+  triclinic box = (0.0000000 0.0000000 0.0000000) to (74.580000 74.580000 83.064000) with tilt (0.0000000 0.0000000 0.0000000)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32400 atoms
+  read_data CPU = 0.022 seconds
 
 mass		1 28.0855
 group    	type1 type 1
@@ -63,32 +64,32 @@ Step Temp TotEng PotEng E_vdwl E_coul c_q1 c_q2 Press Volume
       80    272.98301    -6.803583   -6.8388677    4.6404093   -11.479277    2.8932784   -1.4466392   -9896.1704    462016.62 
       90    305.77651   -6.8036184   -6.8431419    4.6512736   -11.494415    2.8953109   -1.4476554   -15675.983    462016.62 
      100    331.58255   -6.8036753   -6.8465344     4.662727   -11.509261     2.897273   -1.4486365   -21675.515    462016.62 
-Loop time of 517.206 on 1 procs for 100 steps with 32400 atoms
+Loop time of 426.185 on 1 procs for 100 steps with 32400 atoms
 
-Performance: 0.003 ns/day, 7183.417 hours/ns, 0.193 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 0.004 ns/day, 5919.239 hours/ns, 0.235 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 114.18     | 114.18     | 114.18     |   0.0 | 22.08
-Neigh   | 0.47558    | 0.47558    | 0.47558    |   0.0 |  0.09
-Comm    | 0.030611   | 0.030611   | 0.030611   |   0.0 |  0.01
-Output  | 0.0024922  | 0.0024922  | 0.0024922  |   0.0 |  0.00
-Modify  | 402.51     | 402.51     | 402.51     |   0.0 | 77.82
-Other   |            | 0.006137   |            |       |  0.00
+Pair    | 87.4       | 87.4       | 87.4       |   0.0 | 20.51
+Neigh   | 0.3908     | 0.3908     | 0.3908     |   0.0 |  0.09
+Comm    | 0.029936   | 0.029936   | 0.029936   |   0.0 |  0.01
+Output  | 0.0024605  | 0.0024605  | 0.0024605  |   0.0 |  0.00
+Modify  | 338.36     | 338.36     | 338.36     |   0.0 | 79.39
+Other   |            | 0.005751   |            |       |  0.00
 
-Nlocal:    32400 ave 32400 max 32400 min
+Nlocal:        32400.0 ave       32400 max       32400 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    42518 ave 42518 max 42518 min
+Nghost:        42518.0 ave       42518 max       42518 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 FullNghs:  1.85317e+07 ave 1.85317e+07 max 1.85317e+07 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 18531740
-Ave neighs/atom = 571.967
+Ave neighs/atom = 571.96728
 Neighbor list builds = 1
 Dangerous builds = 0
-Total wall time: 0:09:18
+Total wall time: 0:07:40

bench/POTENTIALS/log.9Oct20.comb.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # SiO2 for COMB potential
 
@@ -7,10 +6,12 @@ units		metal
 atom_style	charge
 
 read_data  	data.comb
-  triclinic box = (0 0 0) to (74.58 74.58 83.064) with tilt (0 0 0)
+Reading data file ...
+  triclinic box = (0.0000000 0.0000000 0.0000000) to (74.580000 74.580000 83.064000) with tilt (0.0000000 0.0000000 0.0000000)
   1 by 2 by 2 MPI processor grid
   reading atoms ...
   32400 atoms
+  read_data CPU = 0.031 seconds
 
 mass		1 28.0855
 group    	type1 type 1
@@ -50,7 +51,7 @@ Neighbor list info ...
       pair build: full/bin/atomonly
       stencil: full/bin/3d
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 32.11 | 32.11 | 32.11 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 32.28 | 32.28 | 32.29 Mbytes
 Step Temp TotEng PotEng E_vdwl E_coul c_q1 c_q2 Press Volume 
        0          300   -6.8032038   -6.8419806    4.6274455   -11.469426    2.8875895   -1.4437947    13386.415    462016.62 
       10    273.21913   -6.8032489   -6.8385642    4.6221303   -11.460695    2.8872353   -1.4436176    13076.442    462016.62 
@@ -63,32 +64,32 @@ Step Temp TotEng PotEng E_vdwl E_coul c_q1 c_q2 Press Volume
       80    272.98301    -6.803583   -6.8388677    4.6404093   -11.479277    2.8932784   -1.4466392   -9896.1704    462016.62 
       90    305.77651   -6.8036184   -6.8431419    4.6512736   -11.494415    2.8953109   -1.4476554   -15675.983    462016.62 
      100    331.58255   -6.8036753   -6.8465344     4.662727   -11.509261     2.897273   -1.4486365   -21675.515    462016.62 
-Loop time of 131.437 on 4 procs for 100 steps with 32400 atoms
+Loop time of 116.902 on 4 procs for 100 steps with 32400 atoms
 
-Performance: 0.013 ns/day, 1825.518 hours/ns, 0.761 timesteps/s
-99.2% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 0.015 ns/day, 1623.637 hours/ns, 0.855 timesteps/s
+97.0% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 28.847     | 28.874     | 28.913     |   0.5 | 21.97
-Neigh   | 0.10981    | 0.11084    | 0.11145    |   0.2 |  0.08
-Comm    | 0.28924    | 0.32866    | 0.3556     |   4.5 |  0.25
-Output  | 0.0010426  | 0.0011656  | 0.0015302  |   0.6 |  0.00
-Modify  | 102.12     | 102.12     | 102.12     |   0.0 | 77.69
-Other   |            | 0.003455   |            |       |  0.00
+Pair    | 22.866     | 23.181     | 23.375     |   4.0 | 19.83
+Neigh   | 0.093812   | 0.094818   | 0.095301   |   0.2 |  0.08
+Comm    | 0.94054    | 1.1329     | 1.4505     |  18.1 |  0.97
+Output  | 0.0011141  | 0.001422   | 0.0023448  |   1.4 |  0.00
+Modify  | 92.485     | 92.488     | 92.494     |   0.0 | 79.12
+Other   |            | 0.003673   |            |       |  0.00
 
-Nlocal:    8100 ave 8110 max 8090 min
+Nlocal:        8100.00 ave        8110 max        8090 min
 Histogram: 1 0 0 0 1 1 0 0 0 1
-Nghost:    20725.2 ave 20772 max 20694 min
+Nghost:        20725.2 ave       20772 max       20694 min
 Histogram: 1 1 0 0 1 0 0 0 0 1
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
 FullNghs:  4.63294e+06 ave 4.63866e+06 max 4.62736e+06 min
 Histogram: 1 0 0 0 1 1 0 0 0 1
 
 Total # of neighbors = 18531740
-Ave neighs/atom = 571.967
+Ave neighs/atom = 571.96728
 Neighbor list builds = 1
 Dangerous builds = 0
-Total wall time: 0:02:21
+Total wall time: 0:02:06

bench/POTENTIALS/log.9Oct20.dpd.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # DPD benchmark
 
@@ -8,14 +7,14 @@ atom_style	atomic
 comm_modify     mode single vel yes
 
 lattice		fcc 3.0
-Lattice spacing in x,y,z = 1.10064 1.10064 1.10064
+Lattice spacing in x,y,z = 1.1006424 1.1006424 1.1006424
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (22.0128 22.0128 22.0128)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (22.012848 22.012848 22.012848)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.0018332 secs
+  create_atoms CPU = 0.002 seconds
 mass		1 1.0
 
 velocity	all create 1.0 87287 loop geom
@@ -46,30 +45,30 @@ Per MPI rank memory allocation (min/avg/max) = 11.32 | 11.32 | 11.32 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0            1    3.6872574            0    5.1872105    28.880274 
      100    1.0246036    4.5727353            0    6.1095927    23.859969 
-Loop time of 3.09286 on 1 procs for 100 steps with 32000 atoms
+Loop time of 2.63541 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 111741.340 tau/day, 32.333 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 131137.146 tau/day, 37.945 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 1.5326     | 1.5326     | 1.5326     |   0.0 | 49.55
-Neigh   | 1.4771     | 1.4771     | 1.4771     |   0.0 | 47.76
-Comm    | 0.044292   | 0.044292   | 0.044292   |   0.0 |  1.43
-Output  | 0.00011039 | 0.00011039 | 0.00011039 |   0.0 |  0.00
-Modify  | 0.022322   | 0.022322   | 0.022322   |   0.0 |  0.72
-Other   |            | 0.01648    |            |       |  0.53
+Pair    | 1.1841     | 1.1841     | 1.1841     |   0.0 | 44.93
+Neigh   | 1.3737     | 1.3737     | 1.3737     |   0.0 | 52.12
+Comm    | 0.04266    | 0.04266    | 0.04266    |   0.0 |  1.62
+Output  | 9.5844e-05 | 9.5844e-05 | 9.5844e-05 |   0.0 |  0.00
+Modify  | 0.020128   | 0.020128   | 0.020128   |   0.0 |  0.76
+Other   |            | 0.01468    |            |       |  0.56
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    14981 ave 14981 max 14981 min
+Nghost:        14981.0 ave       14981 max       14981 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    660587 ave 660587 max 660587 min
+Neighs:       660587.0 ave      660587 max      660587 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 660587
-Ave neighs/atom = 20.6433
+Ave neighs/atom = 20.643344
 Neighbor list builds = 50
 Dangerous builds = 0
-Total wall time: 0:00:03
+Total wall time: 0:00:02

bench/POTENTIALS/log.9Oct20.dpd.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # DPD benchmark
 
@@ -8,14 +7,14 @@ atom_style	atomic
 comm_modify     mode single vel yes
 
 lattice		fcc 3.0
-Lattice spacing in x,y,z = 1.10064 1.10064 1.10064
+Lattice spacing in x,y,z = 1.1006424 1.1006424 1.1006424
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (22.0128 22.0128 22.0128)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (22.012848 22.012848 22.012848)
   1 by 2 by 2 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000589132 secs
+  create_atoms CPU = 0.001 seconds
 mass		1 1.0
 
 velocity	all create 1.0 87287 loop geom
@@ -42,34 +41,34 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.874 | 3.874 | 3.874 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 3.875 | 3.875 | 3.875 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0            1    3.6872574            0    5.1872105    28.911346 
      100    1.0219182    4.5817845            0    6.1146139    23.803115 
-Loop time of 0.83904 on 4 procs for 100 steps with 32000 atoms
+Loop time of 0.882096 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 411899.440 tau/day, 119.184 timesteps/s
-99.3% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 391793.935 tau/day, 113.366 timesteps/s
+93.4% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.39605    | 0.40101    | 0.40702    |   0.6 | 47.79
-Neigh   | 0.38186    | 0.38494    | 0.38738    |   0.4 | 45.88
-Comm    | 0.032073   | 0.039688   | 0.045953   |   2.9 |  4.73
-Output  | 4.4823e-05 | 5.4002e-05 | 7.844e-05  |   0.0 |  0.01
-Modify  | 0.0056572  | 0.0056887  | 0.0057547  |   0.1 |  0.68
-Other   |            | 0.007655   |            |       |  0.91
+Pair    | 0.31428    | 0.33654    | 0.37754    |   4.4 | 38.15
+Neigh   | 0.36308    | 0.3849     | 0.41542    |   3.1 | 43.63
+Comm    | 0.07276    | 0.14322    | 0.1842     |  11.3 | 16.24
+Output  | 4.22e-05   | 5.2989e-05 | 8.2493e-05 |   0.0 |  0.01
+Modify  | 0.0057678  | 0.0060433  | 0.0065472  |   0.4 |  0.69
+Other   |            | 0.01134    |            |       |  1.29
 
-Nlocal:    8000 ave 8014 max 7986 min
+Nlocal:        8000.00 ave        8014 max        7986 min
 Histogram: 1 1 0 0 0 0 0 0 1 1
-Nghost:    6744 ave 6764 max 6726 min
+Nghost:        6744.00 ave        6764 max        6726 min
 Histogram: 1 0 0 1 0 1 0 0 0 1
-Neighs:    165107 ave 166433 max 163419 min
+Neighs:       165107.0 ave      166433 max      163419 min
 Histogram: 1 0 1 0 0 0 0 0 0 2
 
 Total # of neighbors = 660428
-Ave neighs/atom = 20.6384
+Ave neighs/atom = 20.638375
 Neighbor list builds = 50
 Dangerous builds = 0
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.eam.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Cu in EAM
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.615
-Lattice spacing in x,y,z = 3.615 3.615 3.615
+Lattice spacing in x,y,z = 3.6150000 3.6150000 3.6150000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (72.3 72.3 72.3)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (72.300000 72.300000 72.300000)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00185037 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	eam
 pair_coeff	1 1 Cu_u3.eam
+Reading eam potential file Cu_u3.eam with DATE: 2007-06-11
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -45,30 +45,30 @@ Per MPI rank memory allocation (min/avg/max) = 16.83 | 16.83 | 16.83 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -113280            0   -106662.09    18703.573 
      100      801.832    -109957.3            0   -106640.77    51322.821 
-Loop time of 3.92295 on 1 procs for 100 steps with 32000 atoms
+Loop time of 3.70399 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 11.012 ns/day, 2.179 hours/ns, 25.491 timesteps/s
-99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 11.663 ns/day, 2.058 hours/ns, 26.998 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 3.3913     | 3.3913     | 3.3913     |   0.0 | 86.45
-Neigh   | 0.48107    | 0.48107    | 0.48107    |   0.0 | 12.26
-Comm    | 0.01729    | 0.01729    | 0.01729    |   0.0 |  0.44
-Output  | 0.00011253 | 0.00011253 | 0.00011253 |   0.0 |  0.00
-Modify  | 0.024349   | 0.024349   | 0.024349   |   0.0 |  0.62
-Other   |            | 0.008847   |            |       |  0.23
+Pair    | 3.2216     | 3.2216     | 3.2216     |   0.0 | 86.98
+Neigh   | 0.43766    | 0.43766    | 0.43766    |   0.0 | 11.82
+Comm    | 0.015404   | 0.015404   | 0.015404   |   0.0 |  0.42
+Output  | 0.000103   | 0.000103   | 0.000103   |   0.0 |  0.00
+Modify  | 0.021604   | 0.021604   | 0.021604   |   0.0 |  0.58
+Other   |            | 0.007627   |            |       |  0.21
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    19909 ave 19909 max 19909 min
+Nghost:        19909.0 ave       19909 max       19909 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    1.20778e+06 ave 1.20778e+06 max 1.20778e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 1207784
-Ave neighs/atom = 37.7433
+Ave neighs/atom = 37.743250
 Neighbor list builds = 13
 Dangerous builds = 0
 Total wall time: 0:00:03

bench/POTENTIALS/log.9Oct20.eam.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Cu in EAM
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.615
-Lattice spacing in x,y,z = 3.615 3.615 3.615
+Lattice spacing in x,y,z = 3.6150000 3.6150000 3.6150000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (72.3 72.3 72.3)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (72.300000 72.300000 72.300000)
   1 by 2 by 2 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000595331 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	eam
 pair_coeff	1 1 Cu_u3.eam
+Reading eam potential file Cu_u3.eam with DATE: 2007-06-11
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -41,34 +41,34 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 7.381 | 7.381 | 7.381 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 7.382 | 7.382 | 7.382 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -113280            0   -106662.09    18703.573 
      100      801.832    -109957.3            0   -106640.77    51322.821 
-Loop time of 1.04497 on 4 procs for 100 steps with 32000 atoms
+Loop time of 1.01466 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 41.341 ns/day, 0.581 hours/ns, 95.697 timesteps/s
-99.4% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 42.576 ns/day, 0.564 hours/ns, 98.555 timesteps/s
+99.3% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.88513    | 0.88724    | 0.89191    |   0.3 | 84.91
-Neigh   | 0.12418    | 0.12458    | 0.12511    |   0.1 | 11.92
-Comm    | 0.015654   | 0.020543   | 0.022984   |   2.0 |  1.97
-Output  | 4.8637e-05 | 5.8711e-05 | 8.6546e-05 |   0.0 |  0.01
-Modify  | 0.0085199  | 0.0085896  | 0.0086446  |   0.1 |  0.82
-Other   |            | 0.003959   |            |       |  0.38
+Pair    | 0.86683    | 0.86797    | 0.86877    |   0.1 | 85.54
+Neigh   | 0.11567    | 0.11681    | 0.11992    |   0.5 | 11.51
+Comm    | 0.015399   | 0.017346   | 0.018526   |   0.9 |  1.71
+Output  | 4.6253e-05 | 8.1241e-05 | 0.00017262 |   0.0 |  0.01
+Modify  | 0.0085337  | 0.0085824  | 0.0086181  |   0.0 |  0.85
+Other   |            | 0.003876   |            |       |  0.38
 
-Nlocal:    8000 ave 8008 max 7993 min
+Nlocal:        8000.00 ave        8008 max        7993 min
 Histogram: 2 0 0 0 0 0 0 0 1 1
-Nghost:    9130.25 ave 9138 max 9122 min
+Nghost:        9130.25 ave        9138 max        9122 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Neighs:    301946 ave 302392 max 301360 min
+Neighs:       301946.0 ave      302392 max      301360 min
 Histogram: 1 0 0 0 1 0 0 0 1 1
 
 Total # of neighbors = 1207784
-Ave neighs/atom = 37.7433
+Ave neighs/atom = 37.743250
 Neighbor list builds = 13
 Dangerous builds = 0
 Total wall time: 0:00:01

bench/POTENTIALS/log.9Oct20.eff.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # eFF benchmark of H plasma
 
@@ -7,12 +6,14 @@ units 		electron
 atom_style	electron
 
 read_data  	data.eff
-  orthogonal box = (0 0 0) to (41.9118 41.9118 41.9118)
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (41.911791 41.911791 41.911791)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.040 seconds
 
 pair_style      eff/cut 12
 pair_coeff	* *
@@ -42,7 +43,7 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 370.9 | 370.9 | 370.9 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 371.5 | 371.5 | 371.5 Mbytes
 Step TotEng PotEng KinEng Temp Press 
        0    4046.5854    796.63785    3249.9475    42763.133 4.4764483e+12 
        5    4046.5854    796.95799    3249.6274     42758.92 4.4728546e+12 
@@ -65,33 +66,33 @@ Step TotEng PotEng KinEng Temp Press
       90    4046.5857    864.14162    3182.4441    41874.916 4.3868277e+12 
       95    4046.5857    871.30234    3175.2834    41780.695 4.3805068e+12 
      100    4046.5858    878.76023    3167.8255    41682.563 4.3740731e+12 
-Loop time of 323.031 on 1 procs for 100 steps with 32000 atoms
+Loop time of 344.943 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 26.747 fs/day, 0.897 hours/fs, 0.310 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 25.048 fs/day, 0.958 hours/fs, 0.290 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 322.78     | 322.78     | 322.78     |   0.0 | 99.92
+Pair    | 344.71     | 344.71     | 344.71     |   0.0 | 99.93
 Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 0.1876     | 0.1876     | 0.1876     |   0.0 |  0.06
-Output  | 0.0027025  | 0.0027025  | 0.0027025  |   0.0 |  0.00
-Modify  | 0.032475   | 0.032475   | 0.032475   |   0.0 |  0.01
-Other   |            | 0.02538    |            |       |  0.01
+Comm    | 0.1763     | 0.1763     | 0.1763     |   0.0 |  0.05
+Output  | 0.0024362  | 0.0024362  | 0.0024362  |   0.0 |  0.00
+Modify  | 0.030869   | 0.030869   | 0.030869   |   0.0 |  0.01
+Other   |            | 0.02272    |            |       |  0.01
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    114349 ave 114349 max 114349 min
+Nghost:       114349.0 ave      114349 max      114349 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    8.10572e+07 ave 8.10572e+07 max 8.10572e+07 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 81057159
-Ave neighs/atom = 2533.04
+Ave neighs/atom = 2533.0362
 Neighbor list builds = 0
 Dangerous builds = 0
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:05:27
+Total wall time: 0:05:49

bench/POTENTIALS/log.9Oct20.eff.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # eFF benchmark of H plasma
 
@@ -7,12 +6,14 @@ units 		electron
 atom_style	electron
 
 read_data  	data.eff
-  orthogonal box = (0 0 0) to (41.9118 41.9118 41.9118)
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (41.911791 41.911791 41.911791)
   1 by 2 by 2 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.064 seconds
 
 pair_style      eff/cut 12
 pair_coeff	* *
@@ -42,7 +43,7 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 101.4 | 104.8 | 108.3 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 102.1 | 105.5 | 109.0 Mbytes
 Step TotEng PotEng KinEng Temp Press 
        0    4046.5854    796.63785    3249.9475    42763.133 4.4764483e+12 
        5    4046.5854    796.95799    3249.6274     42758.92 4.4728546e+12 
@@ -65,33 +66,33 @@ Step TotEng PotEng KinEng Temp Press
       90    4046.5857    864.14162    3182.4441    41874.916 4.3868277e+12 
       95    4046.5857    871.30234    3175.2834    41780.695 4.3805068e+12 
      100    4046.5858    878.76023    3167.8255    41682.563 4.3740731e+12 
-Loop time of 90.1636 on 4 procs for 100 steps with 32000 atoms
+Loop time of 100.431 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 95.826 fs/day, 0.250 hours/fs, 1.109 timesteps/s
-99.1% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 86.029 fs/day, 0.279 hours/fs, 0.996 timesteps/s
+95.8% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 83.772     | 86.516     | 89.593     |  29.5 | 95.95
+Pair    | 89.149     | 93.787     | 97.971     |  41.9 | 93.38
 Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 0.51677    | 3.5934     | 6.3368     | 144.6 |  3.99
-Output  | 0.0012872  | 0.0018208  | 0.0024981  |   1.0 |  0.00
-Modify  | 0.017231   | 0.018405   | 0.01983    |   0.8 |  0.02
-Other   |            | 0.03431    |            |       |  0.04
+Comm    | 2.4073     | 6.5821     | 11.21      | 157.8 |  6.55
+Output  | 0.0014203  | 0.0094504  | 0.019111   |   8.3 |  0.01
+Modify  | 0.016678   | 0.016999   | 0.017425   |   0.2 |  0.02
+Other   |            | 0.03524    |            |       |  0.04
 
-Nlocal:    8000 ave 8112 max 7875 min
+Nlocal:        8000.00 ave        8112 max        7875 min
 Histogram: 1 1 0 0 0 0 0 0 0 2
-Nghost:    65589 ave 66004 max 65177 min
+Nghost:        65589.0 ave       66004 max       65177 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
 Neighs:    2.02643e+07 ave 2.11126e+07 max 1.94058e+07 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
 
 Total # of neighbors = 81057159
-Ave neighs/atom = 2533.04
+Ave neighs/atom = 2533.0362
 Neighbor list builds = 0
 Dangerous builds = 0
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:01:31
+Total wall time: 0:01:42

bench/POTENTIALS/log.9Oct20.eim.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # EIM benchmark
 # if run long enough (e.g. 1M steps), the unstable CsCl form of a NaCl single
@@ -9,12 +8,14 @@ units		metal
 atom_style      atomic
 
 read_data       data.eim
-  orthogonal box = (-0.5 -0.5 -0.5) to (71.58 143.66 71.58)
+Reading data file ...
+  orthogonal box = (-0.5 -0.5 -0.5) to (71.580002 143.66000 71.580002)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.024 seconds
 
 pair_style      eim
 pair_coeff      * * Na Cl ffield.eim Na Cl
@@ -44,34 +45,34 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 17.72 | 17.72 | 17.72 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 17.74 | 17.74 | 17.74 Mbytes
 Step PotEng Pxx Pyy Pzz Temp 
        0    -90567.58    -117883.6   -118039.81   -117894.07         1400 
-     100   -91997.012   -4104.7052    -4138.276   -4145.8936    944.10136 
-Loop time of 11.4536 on 1 procs for 100 steps with 32000 atoms
+     100    -91997.39    -4127.237   -4160.9799   -4169.0581    944.09785 
+Loop time of 10.3731 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 0.377 ns/day, 63.631 hours/ns, 8.731 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 0.416 ns/day, 57.628 hours/ns, 9.640 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 9.8277     | 9.8277     | 9.8277     |   0.0 | 85.80
-Neigh   | 1.484      | 1.484      | 1.484      |   0.0 | 12.96
-Comm    | 0.028584   | 0.028584   | 0.028584   |   0.0 |  0.25
-Output  | 0.00023127 | 0.00023127 | 0.00023127 |   0.0 |  0.00
-Modify  | 0.09791    | 0.09791    | 0.09791    |   0.0 |  0.85
-Other   |            | 0.0152     |            |       |  0.13
+Pair    | 8.8937     | 8.8937     | 8.8937     |   0.0 | 85.74
+Neigh   | 1.344      | 1.344      | 1.344      |   0.0 | 12.96
+Comm    | 0.028207   | 0.028207   | 0.028207   |   0.0 |  0.27
+Output  | 0.00020099 | 0.00020099 | 0.00020099 |   0.0 |  0.00
+Modify  | 0.093584   | 0.093584   | 0.093584   |   0.0 |  0.90
+Other   |            | 0.0134     |            |       |  0.13
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    21505 ave 21505 max 21505 min
+Nghost:        21505.0 ave       21505 max       21505 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    1.5839e+06 ave 1.5839e+06 max 1.5839e+06 min
+Neighs:    1.58387e+06 ave 1.58387e+06 max 1.58387e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
-Total # of neighbors = 1583901
-Ave neighs/atom = 49.4969
+Total # of neighbors = 1583871
+Ave neighs/atom = 49.495969
 Neighbor list builds = 37
 Dangerous builds = 12
-Total wall time: 0:00:11
+Total wall time: 0:00:10

bench/POTENTIALS/log.9Oct20.eim.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # EIM benchmark
 # if run long enough (e.g. 1M steps), the unstable CsCl form of a NaCl single
@@ -9,12 +8,14 @@ units		metal
 atom_style      atomic
 
 read_data       data.eim
-  orthogonal box = (-0.5 -0.5 -0.5) to (71.58 143.66 71.58)
+Reading data file ...
+  orthogonal box = (-0.5 -0.5 -0.5) to (71.580002 143.66000 71.580002)
   1 by 4 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.023 seconds
 
 pair_style      eim
 pair_coeff      * * Na Cl ffield.eim Na Cl
@@ -44,34 +45,34 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 7.285 | 7.285 | 7.285 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 7.460 | 7.460 | 7.460 Mbytes
 Step PotEng Pxx Pyy Pzz Temp 
        0    -90567.58    -117883.6   -118039.81   -117894.07         1400 
-     100   -91997.012   -4104.7052    -4138.276   -4145.8936    944.10136 
-Loop time of 3.12061 on 4 procs for 100 steps with 32000 atoms
+     100    -91997.39    -4127.237   -4160.9799   -4169.0581    944.09785 
+Loop time of 3.14457 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 1.384 ns/day, 17.337 hours/ns, 32.045 timesteps/s
-98.8% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 1.374 ns/day, 17.470 hours/ns, 31.801 timesteps/s
+95.8% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 2.6504     | 2.6583     | 2.6685     |   0.5 | 85.18
-Neigh   | 0.36996    | 0.37847    | 0.39396    |   1.5 | 12.13
-Comm    | 0.037041   | 0.040586   | 0.04504    |   1.4 |  1.30
-Output  | 7.081e-05  | 8.75e-05   | 0.00012994 |   0.0 |  0.00
-Modify  | 0.029286   | 0.035978   | 0.047942   |   3.9 |  1.15
-Other   |            | 0.007206   |            |       |  0.23
+Pair    | 2.6017     | 2.6264     | 2.6758     |   1.8 | 83.52
+Neigh   | 0.34384    | 0.35308    | 0.36784    |   1.6 | 11.23
+Comm    | 0.039635   | 0.099661   | 0.15326    |  15.0 |  3.17
+Output  | 6.485e-05  | 9.656e-05  | 0.0001905  |   0.0 |  0.00
+Modify  | 0.035666   | 0.055446   | 0.098401   |  10.6 |  1.76
+Other   |            | 0.009939   |            |       |  0.32
 
-Nlocal:    8000 ave 8000 max 8000 min
+Nlocal:        8000.00 ave        8000 max        8000 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-Nghost:    9460.25 ave 9469 max 9449 min
+Nghost:        9460.25 ave        9469 max        9449 min
 Histogram: 1 0 0 0 0 1 0 1 0 1
-Neighs:    395975 ave 397239 max 394616 min
+Neighs:       395968.0 ave      397233 max      394606 min
 Histogram: 1 0 0 1 0 0 0 1 0 1
 
-Total # of neighbors = 1583901
-Ave neighs/atom = 49.4969
+Total # of neighbors = 1583871
+Ave neighs/atom = 49.495969
 Neighbor list builds = 37
 Dangerous builds = 12
 Total wall time: 0:00:03

bench/POTENTIALS/log.9Oct20.fene.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # FENE beadspring benchmark
 
@@ -8,7 +7,8 @@ atom_style	bond
 special_bonds   fene
 
 read_data	data.fene
-  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+Reading data file ...
+  orthogonal box = (-16.796000 -16.796000 -16.796000) to (16.796000 16.796000 16.796000)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
@@ -18,8 +18,13 @@ read_data	data.fene
   1 = max bonds/atom
   reading bonds ...
   31680 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      1.0      1.0     
+  special bond factors coul:  0.0      1.0      1.0     
+     2 = max # of 1-2 neighbors
+     2 = max # of special neighbors
+  special bonds CPU = 0.003 seconds
+  read_data CPU = 0.054 seconds
 
 neighbor	0.4 bin
 neigh_modify    delay 5 every 1
@@ -49,36 +54,37 @@ Neighbor list info ...
       pair build: half/bin/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 13.18 | 13.18 | 13.18 Mbytes
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:667)
+Per MPI rank memory allocation (min/avg/max) = 13.20 | 13.20 | 13.20 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0   0.97029772   0.44484087    20.494523    22.394765    4.6721833 
      100    0.9729966    0.4361122    20.507698     22.40326    4.6548819 
-Loop time of 0.66285 on 1 procs for 100 steps with 32000 atoms
+Loop time of 0.648089 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 156415.445 tau/day, 150.864 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 159978.044 tau/day, 154.300 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.13075    | 0.13075    | 0.13075    |   0.0 | 19.73
-Bond    | 0.046363   | 0.046363   | 0.046363   |   0.0 |  6.99
-Neigh   | 0.3172     | 0.3172     | 0.3172     |   0.0 | 47.85
-Comm    | 0.016553   | 0.016553   | 0.016553   |   0.0 |  2.50
-Output  | 0.00010395 | 0.00010395 | 0.00010395 |   0.0 |  0.02
-Modify  | 0.14515    | 0.14515    | 0.14515    |   0.0 | 21.90
-Other   |            | 0.006728   |            |       |  1.02
+Pair    | 0.12174    | 0.12174    | 0.12174    |   0.0 | 18.78
+Bond    | 0.050688   | 0.050688   | 0.050688   |   0.0 |  7.82
+Neigh   | 0.33136    | 0.33136    | 0.33136    |   0.0 | 51.13
+Comm    | 0.014753   | 0.014753   | 0.014753   |   0.0 |  2.28
+Output  | 9.8467e-05 | 9.8467e-05 | 9.8467e-05 |   0.0 |  0.02
+Modify  | 0.12378    | 0.12378    | 0.12378    |   0.0 | 19.10
+Other   |            | 0.005668   |            |       |  0.87
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    9493 ave 9493 max 9493 min
+Nghost:        9493.00 ave        9493 max        9493 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    155873 ave 155873 max 155873 min
+Neighs:       155873.0 ave      155873 max      155873 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 155873
-Ave neighs/atom = 4.87103
-Ave special neighs/atom = 1.98
+Ave neighs/atom = 4.8710312
+Ave special neighs/atom = 1.9800000
 Neighbor list builds = 20
 Dangerous builds = 20
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.fene.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # FENE beadspring benchmark
 
@@ -8,7 +7,8 @@ atom_style	bond
 special_bonds   fene
 
 read_data	data.fene
-  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+Reading data file ...
+  orthogonal box = (-16.796000 -16.796000 -16.796000) to (16.796000 16.796000 16.796000)
   1 by 2 by 2 MPI processor grid
   reading atoms ...
   32000 atoms
@@ -18,8 +18,13 @@ read_data	data.fene
   1 = max bonds/atom
   reading bonds ...
   31680 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      1.0      1.0     
+  special bond factors coul:  0.0      1.0      1.0     
+     2 = max # of 1-2 neighbors
+     2 = max # of special neighbors
+  special bonds CPU = 0.001 seconds
+  read_data CPU = 0.048 seconds
 
 neighbor	0.4 bin
 neigh_modify    delay 5 every 1
@@ -49,36 +54,37 @@ Neighbor list info ...
       pair build: half/bin/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 4.605 | 4.605 | 4.606 Mbytes
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:667)
+Per MPI rank memory allocation (min/avg/max) = 4.779 | 4.780 | 4.780 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0   0.97029772   0.44484087    20.494523    22.394765    4.6721833 
      100    0.9736748   0.44378481    20.502389     22.40664    4.7809557 
-Loop time of 0.184782 on 4 procs for 100 steps with 32000 atoms
+Loop time of 0.179123 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 561093.346 tau/day, 541.178 timesteps/s
-98.4% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 578819.228 tau/day, 558.275 timesteps/s
+99.2% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.033747   | 0.034391   | 0.035036   |   0.3 | 18.61
-Bond    | 0.012475   | 0.012579   | 0.012812   |   0.1 |  6.81
-Neigh   | 0.083916   | 0.083953   | 0.084022   |   0.0 | 45.43
-Comm    | 0.012409   | 0.01363    | 0.014534   |   0.7 |  7.38
-Output  | 4.1246e-05 | 5.9545e-05 | 0.00010443 |   0.0 |  0.03
-Modify  | 0.036675   | 0.037876   | 0.038357   |   0.4 | 20.50
-Other   |            | 0.002294   |            |       |  1.24
+Pair    | 0.031898   | 0.032311   | 0.032864   |   0.2 | 18.04
+Bond    | 0.01335    | 0.013471   | 0.013588   |   0.1 |  7.52
+Neigh   | 0.087105   | 0.087195   | 0.087282   |   0.0 | 48.68
+Comm    | 0.010541   | 0.011533   | 0.012463   |   0.7 |  6.44
+Output  | 3.8624e-05 | 5.6028e-05 | 0.00010157 |   0.0 |  0.03
+Modify  | 0.031766   | 0.03233    | 0.033015   |   0.3 | 18.05
+Other   |            | 0.002227   |            |       |  1.24
 
-Nlocal:    8000 ave 8023 max 7978 min
+Nlocal:        8000.00 ave        8023 max        7978 min
 Histogram: 1 0 0 0 1 1 0 0 0 1
-Nghost:    4158.75 ave 4175 max 4145 min
+Nghost:        4158.75 ave        4175 max        4145 min
 Histogram: 1 0 1 0 0 0 1 0 0 1
-Neighs:    38940 ave 39184 max 38640 min
+Neighs:        38940.0 ave       39184 max       38640 min
 Histogram: 1 0 0 0 0 1 1 0 0 1
 
 Total # of neighbors = 155760
-Ave neighs/atom = 4.8675
-Ave special neighs/atom = 1.98
+Ave neighs/atom = 4.8675000
+Ave special neighs/atom = 1.9800000
 Neighbor list builds = 20
 Dangerous builds = 20
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.gb.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Gay-Berne benchmark
 # biaxial ellipsoid mesogens in isotropic phase
@@ -18,13 +17,15 @@ atom_style    ellipsoid
 #set	      group all quat/random 982381
 
 read_data     data.gb
-  orthogonal box = (2.19575 2.19575 2.19575) to (50.8124 50.8124 50.8124)
+Reading data file ...
+  orthogonal box = (2.1957493 2.1957493 2.1957493) to (50.812373 50.812373 50.812373)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32768 atoms
   reading velocities ...
   32768 velocities
   32768 ellipsoids
+  read_data CPU = 0.097 seconds
 
 compute	      rot all temp/asphere
 group	      spheroid type 1
@@ -63,41 +64,41 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 28.91 | 28.91 | 28.91 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 28.98 | 28.98 | 28.98 Mbytes
 Step Temp E_pair E_mol TotEng Press Volume 
        0          2.4   0.50438568            0    4.1042758    6.7818168    114909.09 
-      20    2.7357818   0.26045557            0     4.364003    6.8299368    111715.16 
-      40    2.9201296   0.22570735            0     4.605768    7.0767907    109473.23 
-      60    2.9820039   0.19733812            0    4.6702075    7.1507065    108393.77 
-      80    3.0148529   0.15114819            0    4.6732895    7.1699502    107672.24 
-     100    3.0206703   0.10567623            0    4.6365433     7.154345    107184.83 
-Loop time of 43.7894 on 1 procs for 100 steps with 32768 atoms
+      20    2.7357797   0.26044978            0     4.363994    6.8299173     111715.2 
+      40    2.9201268    0.2257049            0    4.6057615    7.0767796    109473.26 
+      60    2.9820022   0.19733756            0    4.6702044    7.1507023    108393.79 
+      80     3.014852   0.15114765            0    4.6732876    7.1699472    107672.25 
+     100    3.0206698     0.105676            0    4.6365424    7.1543436    107184.84 
+Loop time of 57.1053 on 1 procs for 100 steps with 32768 atoms
 
-Performance: 394.616 tau/day, 2.284 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 302.599 tau/day, 1.751 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 42.881     | 42.881     | 42.881     |   0.0 | 97.93
-Neigh   | 0.35071    | 0.35071    | 0.35071    |   0.0 |  0.80
-Comm    | 0.065153   | 0.065153   | 0.065153   |   0.0 |  0.15
-Output  | 0.00054383 | 0.00054383 | 0.00054383 |   0.0 |  0.00
-Modify  | 0.47852    | 0.47852    | 0.47852    |   0.0 |  1.09
-Other   |            | 0.01337    |            |       |  0.03
+Pair    | 56.246     | 56.246     | 56.246     |   0.0 | 98.50
+Neigh   | 0.31058    | 0.31058    | 0.31058    |   0.0 |  0.54
+Comm    | 0.066039   | 0.066039   | 0.066039   |   0.0 |  0.12
+Output  | 0.00048757 | 0.00048757 | 0.00048757 |   0.0 |  0.00
+Modify  | 0.46972    | 0.46972    | 0.46972    |   0.0 |  0.82
+Other   |            | 0.01198    |            |       |  0.02
 
-Nlocal:    32768 ave 32768 max 32768 min
+Nlocal:        32768.0 ave       32768 max       32768 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    25669 ave 25669 max 25669 min
+Nghost:        25669.0 ave       25669 max       25669 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    2.30433e+06 ave 2.30433e+06 max 2.30433e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
-Total # of neighbors = 2304332
-Ave neighs/atom = 70.3226
+Total # of neighbors = 2304331
+Ave neighs/atom = 70.322601
 Neighbor list builds = 6
 Dangerous builds = 3
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:00:44
+Total wall time: 0:00:57

bench/POTENTIALS/log.9Oct20.gb.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Gay-Berne benchmark
 # biaxial ellipsoid mesogens in isotropic phase
@@ -18,13 +17,15 @@ atom_style    ellipsoid
 #set	      group all quat/random 982381
 
 read_data     data.gb
-  orthogonal box = (2.19575 2.19575 2.19575) to (50.8124 50.8124 50.8124)
+Reading data file ...
+  orthogonal box = (2.1957493 2.1957493 2.1957493) to (50.812373 50.812373 50.812373)
   1 by 2 by 2 MPI processor grid
   reading atoms ...
   32768 atoms
   reading velocities ...
   32768 velocities
   32768 ellipsoids
+  read_data CPU = 0.079 seconds
 
 compute	      rot all temp/asphere
 group	      spheroid type 1
@@ -63,41 +64,41 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 11.78 | 11.78 | 11.78 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 11.99 | 11.99 | 12.00 Mbytes
 Step Temp E_pair E_mol TotEng Press Volume 
        0          2.4   0.50438568            0    4.1042758    6.7818168    114909.09 
-      20    2.7357818   0.26045557            0     4.364003    6.8299368    111715.16 
-      40    2.9201296   0.22570735            0     4.605768    7.0767907    109473.23 
-      60    2.9820039   0.19733812            0    4.6702075    7.1507065    108393.77 
-      80    3.0148529   0.15114819            0    4.6732895    7.1699502    107672.24 
-     100    3.0206703   0.10567623            0    4.6365433     7.154345    107184.83 
-Loop time of 11.3124 on 4 procs for 100 steps with 32768 atoms
+      20    2.7357797   0.26044978            0     4.363994    6.8299173     111715.2 
+      40    2.9201268    0.2257049            0    4.6057615    7.0767796    109473.26 
+      60    2.9820022   0.19733756            0    4.6702044    7.1507023    108393.79 
+      80     3.014852   0.15114765            0    4.6732876    7.1699472    107672.25 
+     100    3.0206698     0.105676            0    4.6365424    7.1543436    107184.84 
+Loop time of 14.9338 on 4 procs for 100 steps with 32768 atoms
 
-Performance: 1527.522 tau/day, 8.840 timesteps/s
-99.2% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 1157.109 tau/day, 6.696 timesteps/s
+99.5% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 10.778     | 10.849     | 10.934     |   2.0 | 95.90
-Neigh   | 0.088265   | 0.08871    | 0.089238   |   0.1 |  0.78
-Comm    | 0.1384     | 0.22518    | 0.29662    |  14.1 |  1.99
-Output  | 0.00020599 | 0.00024837 | 0.00036836 |   0.0 |  0.00
-Modify  | 0.13828    | 0.13899    | 0.13984    |   0.2 |  1.23
-Other   |            | 0.01053    |            |       |  0.09
+Pair    | 14.317     | 14.457     | 14.545     |   2.5 | 96.81
+Neigh   | 0.080048   | 0.080928   | 0.082009   |   0.3 |  0.54
+Comm    | 0.15948    | 0.24734    | 0.38914    |  18.9 |  1.66
+Output  | 0.00018859 | 0.00034791 | 0.00082254 |   0.0 |  0.00
+Modify  | 0.137      | 0.13804    | 0.13981    |   0.3 |  0.92
+Other   |            | 0.01041    |            |       |  0.07
 
-Nlocal:    8192 ave 8215 max 8166 min
+Nlocal:        8192.00 ave        8215 max        8166 min
 Histogram: 1 1 0 0 0 0 0 0 0 2
-Nghost:    11972.5 ave 11984 max 11959 min
+Nghost:        11972.5 ave       11984 max       11959 min
 Histogram: 1 0 0 0 1 0 1 0 0 1
-Neighs:    576083 ave 579616 max 572161 min
+Neighs:       576083.0 ave      579616 max      572161 min
 Histogram: 1 1 0 0 0 0 0 0 0 2
 
-Total # of neighbors = 2304332
-Ave neighs/atom = 70.3226
+Total # of neighbors = 2304331
+Ave neighs/atom = 70.322601
 Neighbor list builds = 6
 Dangerous builds = 3
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:00:11
+Total wall time: 0:00:15

bench/POTENTIALS/log.9Oct20.granular.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # granular chute flow
 
@@ -10,12 +9,14 @@ newton		off
 comm_modify	vel yes
 
 read_data	data.granular
-  orthogonal box = (0 0 0) to (40 20 37.2886)
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (40.000000 20.000000 37.288600)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.050 seconds
 
 pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
 pair_coeff	* *
@@ -52,34 +53,34 @@ Neighbor list info ...
       pair build: half/size/bin/newtoff
       stencil: half/bin/3d/newtoff
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 23.36 | 23.36 | 23.36 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 23.37 | 23.37 | 23.37 Mbytes
 Step Atoms KinEng c_1 Volume 
        0    32000    784139.13    1601.1263    29833.783 
      100    32000    784292.08    1571.0968    29834.707 
-Loop time of 0.292816 on 1 procs for 100 steps with 32000 atoms
+Loop time of 0.274779 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 2950.657 tau/day, 341.511 timesteps/s
-99.3% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 3144.341 tau/day, 363.928 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    | 0.17449    | 0.17449    | 0.17449    |   0.0 | 59.59
-Neigh   | 0.031927   | 0.031927   | 0.031927   |   0.0 | 10.90
-Comm    | 0.010195   | 0.010195   | 0.010195   |   0.0 |  3.48
-Output  | 0.00019121 | 0.00019121 | 0.00019121 |   0.0 |  0.07
-Modify  | 0.064463   | 0.064463   | 0.064463   |   0.0 | 22.01
-Other   |            | 0.01155    |            |       |  3.94
+Pair    | 0.16956    | 0.16956    | 0.16956    |   0.0 | 61.71
+Neigh   | 0.027646   | 0.027646   | 0.027646   |   0.0 | 10.06
+Comm    | 0.010068   | 0.010068   | 0.010068   |   0.0 |  3.66
+Output  | 0.00017285 | 0.00017285 | 0.00017285 |   0.0 |  0.06
+Modify  | 0.056372   | 0.056372   | 0.056372   |   0.0 | 20.52
+Other   |            | 0.01096    |            |       |  3.99
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    5463 ave 5463 max 5463 min
+Nghost:        5463.00 ave        5463 max        5463 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    115133 ave 115133 max 115133 min
+Neighs:       115133.0 ave      115133 max      115133 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 115133
-Ave neighs/atom = 3.59791
+Ave neighs/atom = 3.5979062
 Neighbor list builds = 2
 Dangerous builds = 0
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.granular.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # granular chute flow
 
@@ -10,12 +9,14 @@ newton		off
 comm_modify	vel yes
 
 read_data	data.granular
-  orthogonal box = (0 0 0) to (40 20 37.2886)
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (40.000000 20.000000 37.288600)
   2 by 1 by 2 MPI processor grid
   reading atoms ...
   32000 atoms
   reading velocities ...
   32000 velocities
+  read_data CPU = 0.052 seconds
 
 pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
 pair_coeff	* *
@@ -52,34 +53,34 @@ Neighbor list info ...
       pair build: half/size/bin/newtoff
       stencil: half/bin/3d/newtoff
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 10.41 | 10.42 | 10.42 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 10.59 | 10.59 | 10.60 Mbytes
 Step Atoms KinEng c_1 Volume 
        0    32000    784139.13    1601.1263    29833.783 
      100    32000    784292.08    1571.0968    29834.707 
-Loop time of 0.0903978 on 4 procs for 100 steps with 32000 atoms
+Loop time of 0.0952788 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 9557.751 tau/day, 1106.221 timesteps/s
-98.3% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 9068.124 tau/day, 1049.551 timesteps/s
+95.4% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.046331   | 0.049088   | 0.052195   |   1.2 | 54.30
-Neigh   | 0.0090401  | 0.0091327  | 0.0091863  |   0.1 | 10.10
-Comm    | 0.0073855  | 0.0080023  | 0.0086699  |   0.6 |  8.85
-Output  | 7.1049e-05 | 0.00010067 | 0.00012088 |   0.0 |  0.11
-Modify  | 0.017226   | 0.017449   | 0.01803    |   0.3 | 19.30
-Other   |            | 0.006625   |            |       |  7.33
+Pair    | 0.044316   | 0.047274   | 0.049681   |   1.0 | 49.62
+Neigh   | 0.0079038  | 0.0079354  | 0.0079608  |   0.0 |  8.33
+Comm    | 0.0082569  | 0.0089372  | 0.0094819  |   0.5 |  9.38
+Output  | 6.9857e-05 | 9.3222e-05 | 0.00010514 |   0.0 |  0.10
+Modify  | 0.015689   | 0.016034   | 0.016789   |   0.4 | 16.83
+Other   |            | 0.015      |            |       | 15.75
 
-Nlocal:    8000 ave 8008 max 7992 min
+Nlocal:        8000.00 ave        8008 max        7992 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Nghost:    2439 ave 2450 max 2428 min
+Nghost:        2439.00 ave        2450 max        2428 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Neighs:    29500.5 ave 30488 max 28513 min
+Neighs:        29500.5 ave       30488 max       28513 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
 
 Total # of neighbors = 118002
-Ave neighs/atom = 3.68756
+Ave neighs/atom = 3.6875625
 Neighbor list builds = 2
 Dangerous builds = 0
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.lj.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # 3d Lennard-Jones melt
 
@@ -7,14 +6,14 @@ units		lj
 atom_style	atomic
 
 lattice		fcc 0.8442
-Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+Lattice spacing in x,y,z = 1.6795962 1.6795962 1.6795962
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (33.591924 33.591924 33.591924)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00183916 secs
+  create_atoms CPU = 0.002 seconds
 mass		1 1.0
 
 velocity	all create 1.44 87287 loop geom
@@ -44,30 +43,30 @@ Per MPI rank memory allocation (min/avg/max) = 15.82 | 15.82 | 15.82 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
      100   0.75745998   -5.7584998            0   -4.6223453   0.20729996 
-Loop time of 1.721 on 1 procs for 100 steps with 32000 atoms
+Loop time of 1.59245 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 25101.720 tau/day, 58.106 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 27127.959 tau/day, 62.796 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 1.2551     | 1.2551     | 1.2551     |   0.0 | 72.93
-Neigh   | 0.41825    | 0.41825    | 0.41825    |   0.0 | 24.30
-Comm    | 0.015347   | 0.015347   | 0.015347   |   0.0 |  0.89
-Output  | 0.00010729 | 0.00010729 | 0.00010729 |   0.0 |  0.01
-Modify  | 0.023436   | 0.023436   | 0.023436   |   0.0 |  1.36
-Other   |            | 0.008766   |            |       |  0.51
+Pair    | 1.1654     | 1.1654     | 1.1654     |   0.0 | 73.18
+Neigh   | 0.38321    | 0.38321    | 0.38321    |   0.0 | 24.06
+Comm    | 0.014476   | 0.014476   | 0.014476   |   0.0 |  0.91
+Output  | 9.5844e-05 | 9.5844e-05 | 9.5844e-05 |   0.0 |  0.01
+Modify  | 0.021453   | 0.021453   | 0.021453   |   0.0 |  1.35
+Other   |            | 0.007799   |            |       |  0.49
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    19669 ave 19669 max 19669 min
+Nghost:        19669.0 ave       19669 max       19669 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    1.20318e+06 ave 1.20318e+06 max 1.20318e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 1203176
-Ave neighs/atom = 37.5992
+Ave neighs/atom = 37.599250
 Neighbor list builds = 11
 Dangerous builds = 0
 Total wall time: 0:00:01

bench/POTENTIALS/log.9Oct20.lj.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # 3d Lennard-Jones melt
 
@@ -7,14 +6,14 @@ units		lj
 atom_style	atomic
 
 lattice		fcc 0.8442
-Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+Lattice spacing in x,y,z = 1.6795962 1.6795962 1.6795962
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (33.591924 33.591924 33.591924)
   1 by 2 by 2 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000587225 secs
+  create_atoms CPU = 0.001 seconds
 mass		1 1.0
 
 velocity	all create 1.44 87287 loop geom
@@ -40,34 +39,34 @@ Neighbor list info ...
       pair build: half/bin/atomonly/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 6.88 | 6.88 | 6.88 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 6.881 | 6.881 | 6.881 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
      100   0.75745998   -5.7584998            0   -4.6223453   0.20729996 
-Loop time of 0.469936 on 4 procs for 100 steps with 32000 atoms
+Loop time of 0.452443 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 91927.316 tau/day, 212.795 timesteps/s
-99.1% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 95481.741 tau/day, 221.023 timesteps/s
+98.4% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 0.32713    | 0.32917    | 0.33317    |   0.4 | 70.05
-Neigh   | 0.10836    | 0.10931    | 0.11007    |   0.2 | 23.26
-Comm    | 0.015526   | 0.020355   | 0.022399   |   2.0 |  4.33
-Output  | 4.2439e-05 | 5.8353e-05 | 0.00010061 |   0.0 |  0.01
-Modify  | 0.0071156  | 0.0072448  | 0.007309   |   0.1 |  1.54
-Other   |            | 0.003793   |            |       |  0.81
+Pair    | 0.31149    | 0.3132     | 0.31493    |   0.2 | 69.22
+Neigh   | 0.1006     | 0.10164    | 0.10385    |   0.4 | 22.47
+Comm    | 0.02195    | 0.025904   | 0.028603   |   1.6 |  5.73
+Output  | 4.3631e-05 | 7.534e-05  | 0.00015879 |   0.0 |  0.02
+Modify  | 0.0067751  | 0.0073788  | 0.0088398  |   1.0 |  1.63
+Other   |            | 0.004243   |            |       |  0.94
 
-Nlocal:    8000 ave 8041 max 7958 min
+Nlocal:        8000.00 ave        8041 max        7958 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
-Nghost:    9011 ave 9065 max 8961 min
+Nghost:        9011.00 ave        9065 max        8961 min
 Histogram: 1 1 0 0 0 0 0 1 0 1
-Neighs:    300794 ave 304843 max 297317 min
+Neighs:       300794.0 ave      304843 max      297317 min
 Histogram: 1 0 0 1 1 0 0 0 0 1
 
 Total # of neighbors = 1203176
-Ave neighs/atom = 37.5992
+Ave neighs/atom = 37.599250
 Neighbor list builds = 11
 Dangerous builds = 0
 Total wall time: 0:00:00

bench/POTENTIALS/log.9Oct20.meamc.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Ni in MEAM
 
@@ -7,17 +6,19 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.52
-Lattice spacing in x,y,z = 3.52 3.52 3.52
+Lattice spacing in x,y,z = 3.5200000 3.5200000 3.5200000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (70.4 70.4 70.4)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (70.400000 70.400000 70.400000)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00184226 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	meam/c
 pair_coeff	* * library.meam Ni4 Ni.meam Ni4
+Reading potential file library.meam with DATE: 2012-06-29
+Reading potential file Ni.meam with DATE: 2007-06-11
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -47,37 +48,37 @@ Neighbor list info ...
       pair build: halffull/newton
       stencil: none
       bin: none
-Per MPI rank memory allocation (min/avg/max) = 55.91 | 55.91 | 55.91 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 55.92 | 55.92 | 55.92 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -142400            0   -135782.09     20259.18 
       50    885.10702   -139411.51            0   -135750.54    32425.431 
      100    895.50973    -139454.3            0    -135750.3    31804.185 
-Loop time of 22.9343 on 1 procs for 100 steps with 32000 atoms
+Loop time of 21.655 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 1.884 ns/day, 12.741 hours/ns, 4.360 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 1.995 ns/day, 12.031 hours/ns, 4.618 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 22.397     | 22.397     | 22.397     |   0.0 | 97.66
-Neigh   | 0.48781    | 0.48781    | 0.48781    |   0.0 |  2.13
-Comm    | 0.013967   | 0.013967   | 0.013967   |   0.0 |  0.06
-Output  | 0.00022793 | 0.00022793 | 0.00022793 |   0.0 |  0.00
-Modify  | 0.025412   | 0.025412   | 0.025412   |   0.0 |  0.11
-Other   |            | 0.009448   |            |       |  0.04
+Pair    | 21.181     | 21.181     | 21.181     |   0.0 | 97.81
+Neigh   | 0.42787    | 0.42787    | 0.42787    |   0.0 |  1.98
+Comm    | 0.013557   | 0.013557   | 0.013557   |   0.0 |  0.06
+Output  | 0.00020766 | 0.00020766 | 0.00020766 |   0.0 |  0.00
+Modify  | 0.023456   | 0.023456   | 0.023456   |   0.0 |  0.11
+Other   |            | 0.008504   |            |       |  0.04
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    13576 ave 13576 max 13576 min
+Nghost:        13576.0 ave       13576 max       13576 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    780360 ave 780360 max 780360 min
+Neighs:       780360.0 ave      780360 max      780360 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 FullNghs:  1.56072e+06 ave 1.56072e+06 max 1.56072e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 1560720
-Ave neighs/atom = 48.7725
+Ave neighs/atom = 48.772500
 Neighbor list builds = 8
 Dangerous builds = 0
-Total wall time: 0:00:23
+Total wall time: 0:00:21

bench/POTENTIALS/log.9Oct20.meamc.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Ni in MEAM
 
@@ -7,17 +6,19 @@ units		metal
 atom_style	atomic
 
 lattice		fcc 3.52
-Lattice spacing in x,y,z = 3.52 3.52 3.52
+Lattice spacing in x,y,z = 3.5200000 3.5200000 3.5200000
 region		box block 0 20 0 20 0 20
 create_box	1 box
-Created orthogonal box = (0 0 0) to (70.4 70.4 70.4)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (70.400000 70.400000 70.400000)
   1 by 2 by 2 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00058651 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	meam/c
 pair_coeff	* * library.meam Ni4 Ni.meam Ni4
+Reading potential file library.meam with DATE: 2012-06-29
+Reading potential file Ni.meam with DATE: 2007-06-11
 
 velocity	all create 1600.0 376847 loop geom
 
@@ -47,37 +48,37 @@ Neighbor list info ...
       pair build: halffull/newton
       stencil: none
       bin: none
-Per MPI rank memory allocation (min/avg/max) = 17.41 | 17.41 | 17.41 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 17.42 | 17.42 | 17.42 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1600      -142400            0   -135782.09     20259.18 
       50    885.10702   -139411.51            0   -135750.54    32425.431 
      100    895.50973    -139454.3            0    -135750.3    31804.185 
-Loop time of 6.45947 on 4 procs for 100 steps with 32000 atoms
+Loop time of 6.34746 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 6.688 ns/day, 3.589 hours/ns, 15.481 timesteps/s
+Performance: 6.806 ns/day, 3.526 hours/ns, 15.754 timesteps/s
 98.0% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 6.22       | 6.2385     | 6.265      |   0.7 | 96.58
-Neigh   | 0.12657    | 0.12691    | 0.12721    |   0.1 |  1.96
-Comm    | 0.052339   | 0.07915    | 0.097897   |   5.9 |  1.23
-Output  | 9.7752e-05 | 0.0001151  | 0.00016594 |   0.0 |  0.00
-Modify  | 0.010194   | 0.010291   | 0.010442   |   0.1 |  0.16
-Other   |            | 0.004529   |            |       |  0.07
+Pair    | 6.0585     | 6.1109     | 6.1535     |   1.4 | 96.27
+Neigh   | 0.11286    | 0.11651    | 0.12455    |   1.4 |  1.84
+Comm    | 0.058046   | 0.099641   | 0.15569    |  11.7 |  1.57
+Output  | 9.0122e-05 | 0.00016046 | 0.0003624  |   0.0 |  0.00
+Modify  | 0.010822   | 0.011674   | 0.014224   |   1.4 |  0.18
+Other   |            | 0.008601   |            |       |  0.14
 
-Nlocal:    8000 ave 8045 max 7947 min
+Nlocal:        8000.00 ave        8045 max        7947 min
 Histogram: 1 0 0 1 0 0 0 1 0 1
-Nghost:    6066.75 ave 6120 max 6021 min
+Nghost:        6066.75 ave        6120 max        6021 min
 Histogram: 1 0 1 0 0 0 1 0 0 1
-Neighs:    195090 ave 196403 max 193697 min
+Neighs:       195090.0 ave      196403 max      193697 min
 Histogram: 1 0 0 1 0 0 0 1 0 1
-FullNghs:  390180 ave 392616 max 387490 min
+FullNghs:     390180.0 ave      392616 max      387490 min
 Histogram: 1 0 0 1 0 0 0 1 0 1
 
 Total # of neighbors = 1560720
-Ave neighs/atom = 48.7725
+Ave neighs/atom = 48.772500
 Neighbor list builds = 8
 Dangerous builds = 0
 Total wall time: 0:00:06

bench/POTENTIALS/log.9Oct20.peri.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Crack growth in notched 3D Peridynamic block
 
@@ -58,11 +57,11 @@ region          plate block 		0 0.01975 0 0.01575 ${myzmin} ${myzmax} 		units bo
 region          plate block 		0 0.01975 0 0.01575 0 ${myzmax} 		units box
 region          plate block 		0 0.01975 0 0.01575 0 0.01225 		units box
 create_box      3 plate
-Created orthogonal box = (0 0 0) to (0.01975 0.01575 0.01225)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (0.01975 0.01575 0.01225)
   1 by 1 by 1 MPI processor grid
 create_atoms    1 region plate
 Created 32000 atoms
-  Time spent = 0.00362897 secs
+  create_atoms CPU = 0.004 seconds
 
 
 pair_style      peri/pmb
@@ -101,8 +100,10 @@ region		topright block 		0.009875 0.01975 0.01075 0.01575 ${myzmin} ${myzmax}
 region		topright block 		0.009875 0.01975 0.01075 0.01575 0 ${myzmax} 		units box
 region		topright block 		0.009875 0.01975 0.01075 0.01575 0 0.01225 		units box
 set 		region topleft  type 2
+Setting atom values ...
   5000 settings made for type
 set 		region topright type 3
+Setting atom values ...
   5000 settings made for type
 pair_coeff      1 1 ${myc} ${mydelta} ${mys0} 0.0
 pair_coeff      1 1 5.43248872420337e+22 ${mydelta} ${mys0} 0.0
@@ -129,11 +130,13 @@ pair_coeff      1 3 5.43248872420337e+22 0.001515 ${mys0} 0.0
 pair_coeff      1 3 5.43248872420337e+22 0.001515 0.00102062072615966 0.0
 set             group all density ${mydensity}
 set             group all density 2440
+Setting atom values ...
   32000 settings made for density
 variable	myvolume equal ($h)^3
 variable	myvolume equal (0.0005)^3
 set             group all volume ${myvolume}
 set             group all volume 1.25e-10
+Setting atom values ...
   32000 settings made for volume
 
 velocity        all set 0.0 0.0 0.0 sum no units box
@@ -184,23 +187,23 @@ Step Temp E_pair E_mol TotEng Press Volume
       60 9.8975313e+26 5.7284448e+08            0 1.2287455e+09 1.2048543e+14 3.6292128e-06 
       80 9.3888573e+26 4.0928092e+08            0 1.0314725e+09 1.1429321e+14 3.6292128e-06 
      100 8.3930314e+26 3.8522361e+08            0 9.4142265e+08 1.0217075e+14 3.6292128e-06 
-Loop time of 11.0398 on 1 procs for 100 steps with 32000 atoms
+Loop time of 10.1036 on 1 procs for 100 steps with 32000 atoms
 
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 11.005     | 11.005     | 11.005     |   0.0 | 99.68
+Pair    | 10.07      | 10.07      | 10.07      |   0.0 | 99.67
 Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 6.6042e-05 | 6.6042e-05 | 6.6042e-05 |   0.0 |  0.00
-Output  | 0.00057292 | 0.00057292 | 0.00057292 |   0.0 |  0.01
-Modify  | 0.0256     | 0.0256     | 0.0256     |   0.0 |  0.23
-Other   |            | 0.008592   |            |       |  0.08
+Comm    | 6.6519e-05 | 6.6519e-05 | 6.6519e-05 |   0.0 |  0.00
+Output  | 0.00051737 | 0.00051737 | 0.00051737 |   0.0 |  0.01
+Modify  | 0.024288   | 0.024288   | 0.024288   |   0.0 |  0.24
+Other   |            | 0.008486   |            |       |  0.08
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    0 ave 0 max 0 min
+Nghost:        0.00000 ave           0 max           0 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    6.74442e+06 ave 6.74442e+06 max 6.74442e+06 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
@@ -208,10 +211,10 @@ FullNghs:  1.34888e+07 ave 1.34888e+07 max 1.34888e+07 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 13488836
-Ave neighs/atom = 421.526
+Ave neighs/atom = 421.52612
 Neighbor list builds = 0
 Dangerous builds = 0
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:00:11
+Total wall time: 0:00:10

bench/POTENTIALS/log.9Oct20.peri.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Crack growth in notched 3D Peridynamic block
 
@@ -58,11 +57,11 @@ region          plate block 		0 0.01975 0 0.01575 ${myzmin} ${myzmax} 		units bo
 region          plate block 		0 0.01975 0 0.01575 0 ${myzmax} 		units box
 region          plate block 		0 0.01975 0 0.01575 0 0.01225 		units box
 create_box      3 plate
-Created orthogonal box = (0 0 0) to (0.01975 0.01575 0.01225)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (0.01975 0.01575 0.01225)
   2 by 2 by 1 MPI processor grid
 create_atoms    1 region plate
 Created 32000 atoms
-  Time spent = 0.0011344 secs
+  create_atoms CPU = 0.001 seconds
 
 
 pair_style      peri/pmb
@@ -101,8 +100,10 @@ region		topright block 		0.009875 0.01975 0.01075 0.01575 ${myzmin} ${myzmax}
 region		topright block 		0.009875 0.01975 0.01075 0.01575 0 ${myzmax} 		units box
 region		topright block 		0.009875 0.01975 0.01075 0.01575 0 0.01225 		units box
 set 		region topleft  type 2
+Setting atom values ...
   5000 settings made for type
 set 		region topright type 3
+Setting atom values ...
   5000 settings made for type
 pair_coeff      1 1 ${myc} ${mydelta} ${mys0} 0.0
 pair_coeff      1 1 5.43248872420337e+22 ${mydelta} ${mys0} 0.0
@@ -129,11 +130,13 @@ pair_coeff      1 3 5.43248872420337e+22 0.001515 ${mys0} 0.0
 pair_coeff      1 3 5.43248872420337e+22 0.001515 0.00102062072615966 0.0
 set             group all density ${mydensity}
 set             group all density 2440
+Setting atom values ...
   32000 settings made for density
 variable	myvolume equal ($h)^3
 variable	myvolume equal (0.0005)^3
 set             group all volume ${myvolume}
 set             group all volume 1.25e-10
+Setting atom values ...
   32000 settings made for volume
 
 velocity        all set 0.0 0.0 0.0 sum no units box
@@ -176,7 +179,7 @@ Neighbor list info ...
 Peridynamic bonds:
   total # of bonds = 3457032
   bonds/atom = 108.032
-Per MPI rank memory allocation (min/avg/max) = 47.63 | 48.11 | 48.78 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 47.70 | 48.18 | 48.85 Mbytes
 Step Temp E_pair E_mol TotEng Press Volume 
        0 2.0134233e+27            0            0 1.3342785e+09 2.4509971e+14 3.6292128e-06 
       20 1.7695805e+27 1.6163291e+08            0 1.3343188e+09 2.1541601e+14 3.6292128e-06 
@@ -184,34 +187,34 @@ Step Temp E_pair E_mol TotEng Press Volume
       60 9.8975313e+26 5.7284448e+08            0 1.2287455e+09 1.2048543e+14 3.6292128e-06 
       80 9.3888573e+26 4.0928092e+08            0 1.0314725e+09 1.1429321e+14 3.6292128e-06 
      100 8.3930314e+26 3.8522361e+08            0 9.4142265e+08 1.0217075e+14 3.6292128e-06 
-Loop time of 2.8928 on 4 procs for 100 steps with 32000 atoms
+Loop time of 2.82804 on 4 procs for 100 steps with 32000 atoms
 
-99.0% CPU use with 4 MPI tasks x 1 OpenMP threads
+97.9% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 2.7472     | 2.7951     | 2.8585     |   2.9 | 96.62
+Pair    | 2.6021     | 2.6599     | 2.7081     |   2.4 | 94.05
 Neigh   | 0          | 0          | 0          |   0.0 |  0.00
-Comm    | 0.019592   | 0.083156   | 0.13278    |  17.0 |  2.87
-Output  | 0.00022125 | 0.00034326 | 0.00058961 |   0.0 |  0.01
-Modify  | 0.0083542  | 0.0089623  | 0.0095983  |   0.5 |  0.31
-Other   |            | 0.005276   |            |       |  0.18
+Comm    | 0.10341    | 0.15313    | 0.21057    |  10.3 |  5.41
+Output  | 0.00020409 | 0.00041658 | 0.00093699 |   0.0 |  0.01
+Modify  | 0.008944   | 0.0092288  | 0.0095088  |   0.3 |  0.33
+Other   |            | 0.005395   |            |       |  0.19
 
-Nlocal:    8000 ave 8000 max 8000 min
+Nlocal:        8000.00 ave        8000 max        8000 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-Nghost:    5125 ave 5125 max 5125 min
+Nghost:        5125.00 ave        5125 max        5125 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-Neighs:    1.6861e+06 ave 1.77502e+06 max 1.60625e+06 min
+Neighs:    1.68610e+06 ave 1.77502e+06 max 1.60625e+06 min
 Histogram: 2 0 0 0 0 0 0 0 1 1
-FullNghs:  3.37221e+06 ave 3.41832e+06 max 3.3261e+06 min
+FullNghs:  3.37221e+06 ave 3.41832e+06 max  3.3261e+06 min
 Histogram: 2 0 0 0 0 0 0 0 0 2
 
 Total # of neighbors = 13488836
-Ave neighs/atom = 421.526
+Ave neighs/atom = 421.52612
 Neighbor list builds = 0
 Dangerous builds = 0
 
 Please see the log.cite file for references relevant to this simulation
 
-Total wall time: 0:00:03
+Total wall time: 0:00:02

bench/POTENTIALS/log.9Oct20.protein.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Rhodopsin model
 
@@ -17,7 +16,8 @@ pair_modify     mix arithmetic
 kspace_style    pppm 1e-4
 
 read_data       data.protein
-  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+Reading data file ...
+  orthogonal box = (-27.500000 -38.500000 -36.364600) to (27.500000 38.500000 36.361500)
   1 by 1 by 1 MPI processor grid
   reading atoms ...
   32000 atoms
@@ -39,16 +39,22 @@ read_data       data.protein
   56829 dihedrals
   reading impropers ...
   1034 impropers
-  4 = max # of 1-2 neighbors
-  12 = max # of 1-3 neighbors
-  24 = max # of 1-4 neighbors
-  26 = max # of special neighbors
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     4 = max # of 1-2 neighbors
+    12 = max # of 1-3 neighbors
+    24 = max # of 1-4 neighbors
+    26 = max # of special neighbors
+  special bonds CPU = 0.011 seconds
+  read_data CPU = 0.125 seconds
 
 fix             1 all shake 0.0001 5 0 m 1.0 a 232
-  1617 = # of size 2 clusters
-  3633 = # of size 3 clusters
-  747 = # of size 4 clusters
-  4233 = # of frozen angles
+    1617 = # of size 2 clusters
+    3633 = # of size 3 clusters
+     747 = # of size 4 clusters
+    4233 = # of frozen angles
+  find clusters CPU = 0.006 seconds
 fix             2 all npt temp 300.0 300.0 100.0 		z 0.0 0.0 1000.0 mtk no pchain 0 tchain 1
 
 special_bonds   charmm
@@ -58,13 +64,13 @@ timestep        2.0
 
 run		100
 PPPM initialization ...
-  using 12-bit tables for long-range coulomb (../kspace.cpp:321)
-  G vector (1/distance) = 0.248835
+  using 12-bit tables for long-range coulomb (src/kspace.cpp:328)
+  G vector (1/distance) = 0.24883488
   grid = 25 32 32
   stencil order = 5
-  estimated absolute RMS force accuracy = 0.0355478
-  estimated relative force accuracy = 0.000107051
-  using double precision FFTs
+  estimated absolute RMS force accuracy = 0.035547797
+  estimated relative force accuracy = 0.00010705113
+  using double precision KISS FFT
   3d grid and FFT values/proc = 41070 25600
 Neighbor list info ...
   update every 1 steps, delay 5 steps, check yes
@@ -78,46 +84,46 @@ Neighbor list info ...
       pair build: half/bin/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 140 | 140 | 140 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 140.0 | 140.0 | 140.0 Mbytes
 ---------------- Step        0 ----- CPU =      0.0000 (sec) ----------------
 TotEng   =    -25356.2064 KinEng   =     21444.8313 Temp     =       299.0397 
 PotEng   =    -46801.0377 E_bond   =      2537.9940 E_angle  =     10921.3742 
 E_dihed  =      5211.7865 E_impro  =       213.5116 E_vdwl   =     -2307.8634 
 E_coul   =    207025.8927 E_long   =   -270403.7333 Press    =      -149.3301 
 Volume   =    307995.0335 
----------------- Step      100 ----- CPU =     23.7567 (sec) ----------------
-TotEng   =    -25290.7386 KinEng   =     21591.9096 Temp     =       301.0906 
-PotEng   =    -46882.6482 E_bond   =      2567.9789 E_angle  =     10781.9556 
-E_dihed  =      5198.7493 E_impro  =       216.7863 E_vdwl   =     -1902.6458 
-E_coul   =    206659.5007 E_long   =   -270404.9733 Press    =         6.7898 
-Volume   =    308133.9933 
-Loop time of 23.7568 on 1 procs for 100 steps with 32000 atoms
+---------------- Step      100 ----- CPU =     20.0022 (sec) ----------------
+TotEng   =    -25290.7304 KinEng   =     21591.9084 Temp     =       301.0906 
+PotEng   =    -46882.6388 E_bond   =      2567.9807 E_angle  =     10781.9571 
+E_dihed  =      5198.7492 E_impro  =       216.7864 E_vdwl   =     -1902.6618 
+E_coul   =    206659.5226 E_long   =   -270404.9730 Press    =         6.7406 
+Volume   =    308134.2285 
+Loop time of 20.0022 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 0.727 ns/day, 32.995 hours/ns, 4.209 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 0.864 ns/day, 27.781 hours/ns, 4.999 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 17.905     | 17.905     | 17.905     |   0.0 | 75.37
-Bond    | 0.73417    | 0.73417    | 0.73417    |   0.0 |  3.09
-Kspace  | 1.4676     | 1.4676     | 1.4676     |   0.0 |  6.18
-Neigh   | 2.9907     | 2.9907     | 2.9907     |   0.0 | 12.59
-Comm    | 0.037427   | 0.037427   | 0.037427   |   0.0 |  0.16
-Output  | 0.00011754 | 0.00011754 | 0.00011754 |   0.0 |  0.00
-Modify  | 0.60985    | 0.60985    | 0.60985    |   0.0 |  2.57
-Other   |            | 0.01201    |            |       |  0.05
+Pair    | 15         | 15         | 15         |   0.0 | 74.99
+Bond    | 0.65091    | 0.65091    | 0.65091    |   0.0 |  3.25
+Kspace  | 1.2144     | 1.2144     | 1.2144     |   0.0 |  6.07
+Neigh   | 2.6096     | 2.6096     | 2.6096     |   0.0 | 13.05
+Comm    | 0.035203   | 0.035203   | 0.035203   |   0.0 |  0.18
+Output  | 0.00010848 | 0.00010848 | 0.00010848 |   0.0 |  0.00
+Modify  | 0.48116    | 0.48116    | 0.48116    |   0.0 |  2.41
+Other   |            | 0.01032    |            |       |  0.05
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    47958 ave 47958 max 47958 min
+Nghost:        47958.0 ave       47958 max       47958 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 Neighs:    1.20281e+07 ave 1.20281e+07 max 1.20281e+07 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
-Total # of neighbors = 12028098
-Ave neighs/atom = 375.878
-Ave special neighs/atom = 7.43187
+Total # of neighbors = 12028093
+Ave neighs/atom = 375.87791
+Ave special neighs/atom = 7.4318750
 Neighbor list builds = 11
 Dangerous builds = 0
-Total wall time: 0:00:24
+Total wall time: 0:00:20

bench/POTENTIALS/log.9Oct20.protein.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # Rhodopsin model
 
@@ -17,7 +16,8 @@ pair_modify     mix arithmetic
 kspace_style    pppm 1e-4
 
 read_data       data.protein
-  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+Reading data file ...
+  orthogonal box = (-27.500000 -38.500000 -36.364600) to (27.500000 38.500000 36.361500)
   1 by 2 by 2 MPI processor grid
   reading atoms ...
   32000 atoms
@@ -39,16 +39,22 @@ read_data       data.protein
   56829 dihedrals
   reading impropers ...
   1034 impropers
-  4 = max # of 1-2 neighbors
-  12 = max # of 1-3 neighbors
-  24 = max # of 1-4 neighbors
-  26 = max # of special neighbors
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     4 = max # of 1-2 neighbors
+    12 = max # of 1-3 neighbors
+    24 = max # of 1-4 neighbors
+    26 = max # of special neighbors
+  special bonds CPU = 0.005 seconds
+  read_data CPU = 0.210 seconds
 
 fix             1 all shake 0.0001 5 0 m 1.0 a 232
-  1617 = # of size 2 clusters
-  3633 = # of size 3 clusters
-  747 = # of size 4 clusters
-  4233 = # of frozen angles
+    1617 = # of size 2 clusters
+    3633 = # of size 3 clusters
+     747 = # of size 4 clusters
+    4233 = # of frozen angles
+  find clusters CPU = 0.003 seconds
 fix             2 all npt temp 300.0 300.0 100.0 		z 0.0 0.0 1000.0 mtk no pchain 0 tchain 1
 
 special_bonds   charmm
@@ -58,13 +64,13 @@ timestep        2.0
 
 run		100
 PPPM initialization ...
-  using 12-bit tables for long-range coulomb (../kspace.cpp:321)
-  G vector (1/distance) = 0.248835
+  using 12-bit tables for long-range coulomb (src/kspace.cpp:328)
+  G vector (1/distance) = 0.24883488
   grid = 25 32 32
   stencil order = 5
-  estimated absolute RMS force accuracy = 0.0355478
-  estimated relative force accuracy = 0.000107051
-  using double precision FFTs
+  estimated absolute RMS force accuracy = 0.035547797
+  estimated relative force accuracy = 0.00010705113
+  using double precision KISS FFT
   3d grid and FFT values/proc = 13230 6400
 Neighbor list info ...
   update every 1 steps, delay 5 steps, check yes
@@ -78,46 +84,46 @@ Neighbor list info ...
       pair build: half/bin/newton
       stencil: half/bin/3d/newton
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 49.07 | 49.17 | 49.46 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 49.25 | 49.35 | 49.64 Mbytes
 ---------------- Step        0 ----- CPU =      0.0000 (sec) ----------------
 TotEng   =    -25356.2064 KinEng   =     21444.8313 Temp     =       299.0397 
 PotEng   =    -46801.0377 E_bond   =      2537.9940 E_angle  =     10921.3742 
 E_dihed  =      5211.7865 E_impro  =       213.5116 E_vdwl   =     -2307.8634 
 E_coul   =    207025.8927 E_long   =   -270403.7333 Press    =      -149.3301 
 Volume   =    307995.0335 
----------------- Step      100 ----- CPU =      6.3997 (sec) ----------------
-TotEng   =    -25290.7386 KinEng   =     21591.9096 Temp     =       301.0906 
-PotEng   =    -46882.6483 E_bond   =      2567.9789 E_angle  =     10781.9556 
-E_dihed  =      5198.7493 E_impro  =       216.7863 E_vdwl   =     -1902.6458 
-E_coul   =    206659.5007 E_long   =   -270404.9733 Press    =         6.7898 
-Volume   =    308133.9933 
-Loop time of 6.39977 on 4 procs for 100 steps with 32000 atoms
+---------------- Step      100 ----- CPU =      5.5375 (sec) ----------------
+TotEng   =    -25290.7303 KinEng   =     21591.9085 Temp     =       301.0906 
+PotEng   =    -46882.6388 E_bond   =      2567.9807 E_angle  =     10781.9571 
+E_dihed  =      5198.7492 E_impro  =       216.7864 E_vdwl   =     -1902.6618 
+E_coul   =    206659.5225 E_long   =   -270404.9730 Press    =         6.7406 
+Volume   =    308134.2285 
+Loop time of 5.53765 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 2.700 ns/day, 8.889 hours/ns, 15.626 timesteps/s
-98.8% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 3.120 ns/day, 7.691 hours/ns, 18.058 timesteps/s
+99.4% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 4.4434     | 4.5321     | 4.6846     |   4.3 | 70.82
-Bond    | 0.17894    | 0.18568    | 0.19951    |   1.9 |  2.90
-Kspace  | 0.4651     | 0.61064    | 0.69123    |  11.1 |  9.54
-Neigh   | 0.7739     | 0.77394    | 0.774      |   0.0 | 12.09
-Comm    | 0.057676   | 0.069183   | 0.07901    |   3.0 |  1.08
-Output  | 5.6505e-05 | 6.6578e-05 | 9.4414e-05 |   0.0 |  0.00
-Modify  | 0.21444    | 0.21866    | 0.22524    |   0.9 |  3.42
-Other   |            | 0.009451   |            |       |  0.15
+Pair    | 3.8921     | 3.9427     | 4.0762     |   3.9 | 71.20
+Bond    | 0.16218    | 0.16829    | 0.17972    |   1.7 |  3.04
+Kspace  | 0.35196    | 0.48475    | 0.53996    |  11.1 |  8.75
+Neigh   | 0.69975    | 0.69981    | 0.69988    |   0.0 | 12.64
+Comm    | 0.04908    | 0.049445   | 0.049767   |   0.1 |  0.89
+Output  | 5.1737e-05 | 8.5056e-05 | 0.00018382 |   0.0 |  0.00
+Modify  | 0.18393    | 0.18474    | 0.18528    |   0.1 |  3.34
+Other   |            | 0.007858   |            |       |  0.14
 
-Nlocal:    8000 ave 8143 max 7933 min
+Nlocal:        8000.00 ave        8143 max        7933 min
 Histogram: 1 2 0 0 0 0 0 0 0 1
-Nghost:    22733.5 ave 22769 max 22693 min
+Nghost:        22733.5 ave       22769 max       22693 min
 Histogram: 1 0 0 0 0 2 0 0 0 1
-Neighs:    3.00702e+06 ave 3.0975e+06 max 2.96492e+06 min
+Neighs:    3.00702e+06 ave  3.0975e+06 max 2.96492e+06 min
 Histogram: 1 2 0 0 0 0 0 0 0 1
 
-Total # of neighbors = 12028098
-Ave neighs/atom = 375.878
-Ave special neighs/atom = 7.43187
+Total # of neighbors = 12028093
+Ave neighs/atom = 375.87791
+Ave special neighs/atom = 7.4318750
 Neighbor list builds = 11
 Dangerous builds = 0
-Total wall time: 0:00:06
+Total wall time: 0:00:05

bench/POTENTIALS/log.9Oct20.reaxc.1

@@ -0,0 +1,96 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# ReaxFF benchmark: simulation of PETN crystal, replicated unit cell
+
+units		real
+atom_style	charge
+
+read_data	data.reax
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (9.4910650 9.4910650 6.9912300)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  58 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	7 8 10
+Replicating atoms ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (66.437455 75.928520 69.912300)
+  1 by 1 by 1 MPI processor grid
+  32480 atoms
+  replicate CPU = 0.002 seconds
+
+velocity	all create 300.0 9999
+
+pair_style	reax/c NULL
+pair_coeff      * * ffield.reax C H O N
+WARNING: Changed valency_val to valency_boc for X (src/USER-REAXC/reaxc_ffield.cpp:315)
+
+timestep	0.1
+fix		1 all nve
+fix             2 all qeq/reax 1 0.0 10.0 1.0e-6 reax/c
+
+thermo		10
+thermo_style	custom step temp ke pe pxx pyy pzz etotal
+
+run		100
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 12
+  ghost atom cutoff = 12
+  binsize = 6, bins = 12 13 12
+  2 neighbor lists, perpetual/occasional/extra = 2 0 0
+  (1) pair reax/c, perpetual
+      attributes: half, newton off, ghost
+      pair build: half/bin/newtoff/ghost
+      stencil: half/ghost/bin/3d/newtoff
+      bin: standard
+  (2) fix qeq/reax, perpetual, copy from (1)
+      attributes: half, newton off, ghost
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 1727.0 | 1727.0 | 1727.0 Mbytes
+Step Temp KinEng PotEng Pxx Pyy Pzz TotEng 
+       0          300    29044.119   -3232140.8    22804.879   -29365.593    6302.5638   -3203096.6 
+      10    299.37479     28983.59   -3232075.2    21746.783   -23987.396    7610.3039   -3203091.6 
+      20    295.58549    28616.733   -3231710.1    18178.443   -10872.027     10603.19   -3203093.3 
+      30    289.48845    28026.456   -3231123.3    12146.101    4985.2572    13364.258   -3203096.8 
+      40    282.66408    27365.763   -3230467.5    4284.1187    18132.512     14133.51   -3203101.7 
+      50    274.97007    26620.878   -3229730.4    -3718.933    25520.016    12551.903   -3203109.5 
+      60    266.11301    25763.393   -3228883.8   -9271.3498    27307.451    9753.2362   -3203120.4 
+      70    259.32635    25106.351   -3228237.2   -11150.623    24238.509     6578.531   -3203130.8 
+      80    260.33969    25204.456   -3228344.2   -9576.4144    16737.758    3454.6426   -3203139.7 
+      90     269.9021    26130.229   -3229275.5   -5905.8652    5246.3236    467.53439   -3203145.2 
+     100    280.76723    27182.123   -3230330.6   -1363.6002   -8133.2093   -1689.6535   -3203148.5 
+Loop time of 213.234 on 1 procs for 100 steps with 32480 atoms
+
+Performance: 0.004 ns/day, 5923.154 hours/ns, 0.469 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 157        | 157        | 157        |   0.0 | 73.63
+Neigh   | 0          | 0          | 0          |   0.0 |  0.00
+Comm    | 0.024997   | 0.024997   | 0.024997   |   0.0 |  0.01
+Output  | 0.0022025  | 0.0022025  | 0.0022025  |   0.0 |  0.00
+Modify  | 56.19      | 56.19      | 56.19      |   0.0 | 26.35
+Other   |            | 0.01211    |            |       |  0.01
+
+Nlocal:        32480.0 ave       32480 max       32480 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:        45128.0 ave       45128 max       45128 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    1.27781e+07 ave 1.27781e+07 max 1.27781e+07 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 12778082
+Ave neighs/atom = 393.41385
+Neighbor list builds = 0
+Dangerous builds = 0
+
+Please see the log.cite file for references relevant to this simulation
+
+Total wall time: 0:03:37

bench/POTENTIALS/log.9Oct20.reaxc.4

@@ -0,0 +1,96 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# ReaxFF benchmark: simulation of PETN crystal, replicated unit cell
+
+units		real
+atom_style	charge
+
+read_data	data.reax
+Reading data file ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (9.4910650 9.4910650 6.9912300)
+  2 by 2 by 1 MPI processor grid
+  reading atoms ...
+  58 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	7 8 10
+Replicating atoms ...
+  orthogonal box = (0.0000000 0.0000000 0.0000000) to (66.437455 75.928520 69.912300)
+  1 by 2 by 2 MPI processor grid
+  32480 atoms
+  replicate CPU = 0.001 seconds
+
+velocity	all create 300.0 9999
+
+pair_style	reax/c NULL
+pair_coeff      * * ffield.reax C H O N
+WARNING: Changed valency_val to valency_boc for X (src/USER-REAXC/reaxc_ffield.cpp:315)
+
+timestep	0.1
+fix		1 all nve
+fix             2 all qeq/reax 1 0.0 10.0 1.0e-6 reax/c
+
+thermo		10
+thermo_style	custom step temp ke pe pxx pyy pzz etotal
+
+run		100
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 12
+  ghost atom cutoff = 12
+  binsize = 6, bins = 12 13 12
+  2 neighbor lists, perpetual/occasional/extra = 2 0 0
+  (1) pair reax/c, perpetual
+      attributes: half, newton off, ghost
+      pair build: half/bin/newtoff/ghost
+      stencil: half/ghost/bin/3d/newtoff
+      bin: standard
+  (2) fix qeq/reax, perpetual, copy from (1)
+      attributes: half, newton off, ghost
+      pair build: copy
+      stencil: none
+      bin: none
+Per MPI rank memory allocation (min/avg/max) = 647.0 | 647.0 | 647.0 Mbytes
+Step Temp KinEng PotEng Pxx Pyy Pzz TotEng 
+       0          300    29044.119   -3232140.8    22804.879   -29365.593    6302.5638   -3203096.6 
+      10    299.37479     28983.59   -3232075.2    21746.771   -23987.411    7610.2901   -3203091.6 
+      20    295.58551    28616.736   -3231710.1    18178.439   -10871.954    10603.303   -3203093.3 
+      30    289.48844    28026.456   -3231123.2    12146.289    4985.5678    13364.519   -3203096.8 
+      40    282.66406    27365.762   -3230467.4    4284.8179    18133.406    14134.156   -3203101.7 
+      50    274.97009     26620.88   -3229730.3   -3718.6796    25520.338    12552.205   -3203109.5 
+      60    266.11302    25763.394   -3228883.8   -9271.5644    27307.146    9753.1034   -3203120.4 
+      70    259.32636    25106.352   -3228237.1    -11150.66    24238.705    6578.7141   -3203130.8 
+      80    260.33966    25204.454   -3228344.1   -9576.2474    16737.753    3454.7607   -3203139.7 
+      90    269.90207    26130.226   -3229275.5   -5905.8809    5246.1687    467.42114   -3203145.2 
+     100    280.76722    27182.122   -3230330.6   -1363.4752   -8133.2096   -1689.5922   -3203148.5 
+Loop time of 69.1187 on 4 procs for 100 steps with 32480 atoms
+
+Performance: 0.013 ns/day, 1919.965 hours/ns, 1.447 timesteps/s
+97.5% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 45.964     | 48.533     | 51.423     |  29.3 | 70.22
+Neigh   | 0          | 0          | 0          |   0.0 |  0.00
+Comm    | 0.19604    | 3.0913     | 5.6647     | 116.3 |  4.47
+Output  | 0.00074649 | 0.0011722  | 0.0023553  |   2.0 |  0.00
+Modify  | 17.48      | 17.485     | 17.489     |   0.1 | 25.30
+Other   |            | 0.008528   |            |       |  0.01
+
+Nlocal:        8120.00 ave        8120 max        8120 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Nghost:        21992.0 ave       21992 max       21992 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs:    3.48274e+06 ave 3.48274e+06 max 3.48274e+06 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 13930976
+Ave neighs/atom = 428.90936
+Neighbor list builds = 0
+Dangerous builds = 0
+
+Please see the log.cite file for references relevant to this simulation
+
+Total wall time: 0:01:10

bench/POTENTIALS/log.9Oct20.rebo.1

@@ -0,0 +1,90 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# REBO polyethelene benchmark
+
+units		    metal
+atom_style	    atomic
+
+read_data	    data.rebo
+Reading data file ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (2.1000000 2.1000000 25.579000)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  60 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	    17 16 2
+Replicating atoms ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (69.300000 65.100000 51.158000)
+  1 by 1 by 1 MPI processor grid
+  32640 atoms
+  replicate CPU = 0.002 seconds
+
+neighbor	    0.5 bin
+neigh_modify	    delay 5 every 1
+
+pair_style	    rebo
+pair_coeff	    * * CH.rebo C H
+Reading rebo potential file CH.rebo with DATE: 2018-7-3
+
+velocity	    all create 300.0 761341
+
+fix		    1 all nve
+timestep	    0.0005
+
+thermo		    10
+run		    100
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.5
+  ghost atom cutoff = 6.5
+  binsize = 3.25, bins = 22 21 16
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair rebo, perpetual
+      attributes: full, newton on, ghost
+      pair build: full/bin/ghost
+      stencil: full/ghost/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 34.21 | 34.21 | 34.21 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -138442.83            0   -137177.16    2463.0748 
+      10    179.37985   -137931.27            0   -137174.48    15655.936 
+      20    206.87654   -138046.99            0   -137174.19   -24042.627 
+      30    150.80122   -137807.43            0   -137171.21   -16524.118 
+      40    173.24945   -137902.35            0   -137171.42   -5716.9119 
+      50    151.80455   -137812.36            0   -137171.91    3480.4584 
+      60    199.08777   -138013.82            0   -137173.88    17881.372 
+      70    217.85748   -138093.86            0   -137174.73   -12270.999 
+      80    202.37482   -138029.39            0   -137175.59   -7622.7319 
+      90    194.90628   -137997.05            0   -137174.75   -32267.471 
+     100    185.17818   -137954.51            0   -137173.26   -6901.7499 
+Loop time of 4.83649 on 1 procs for 100 steps with 32640 atoms
+
+Performance: 0.893 ns/day, 26.869 hours/ns, 20.676 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 3.3248     | 3.3248     | 3.3248     |   0.0 | 68.74
+Neigh   | 1.4583     | 1.4583     | 1.4583     |   0.0 | 30.15
+Comm    | 0.01934    | 0.01934    | 0.01934    |   0.0 |  0.40
+Output  | 0.0011871  | 0.0011871  | 0.0011871  |   0.0 |  0.02
+Modify  | 0.023516   | 0.023516   | 0.023516   |   0.0 |  0.49
+Other   |            | 0.009316   |            |       |  0.19
+
+Nlocal:        32640.0 ave       32640 max       32640 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:        26460.0 ave       26460 max       26460 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:        0.00000 ave           0 max           0 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+FullNghs:  4.90213e+06 ave 4.90213e+06 max 4.90213e+06 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 4902134
+Ave neighs/atom = 150.18793
+Neighbor list builds = 9
+Dangerous builds = 0
+Total wall time: 0:00:05

bench/POTENTIALS/log.9Oct20.rebo.4

@@ -0,0 +1,90 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# REBO polyethelene benchmark
+
+units		    metal
+atom_style	    atomic
+
+read_data	    data.rebo
+Reading data file ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (2.1000000 2.1000000 25.579000)
+  1 by 1 by 4 MPI processor grid
+  reading atoms ...
+  60 atoms
+  read_data CPU = 0.000 seconds
+
+replicate	    17 16 2
+Replicating atoms ...
+  orthogonal box = (-2.1000000 -2.1000000 0.0000000) to (69.300000 65.100000 51.158000)
+  2 by 2 by 1 MPI processor grid
+  32640 atoms
+  replicate CPU = 0.001 seconds
+
+neighbor	    0.5 bin
+neigh_modify	    delay 5 every 1
+
+pair_style	    rebo
+pair_coeff	    * * CH.rebo C H
+Reading rebo potential file CH.rebo with DATE: 2018-7-3
+
+velocity	    all create 300.0 761341
+
+fix		    1 all nve
+timestep	    0.0005
+
+thermo		    10
+run		    100
+Neighbor list info ...
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 6.5
+  ghost atom cutoff = 6.5
+  binsize = 3.25, bins = 22 21 16
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair rebo, perpetual
+      attributes: full, newton on, ghost
+      pair build: full/bin/ghost
+      stencil: full/ghost/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 11.80 | 12.00 | 12.19 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -138442.83            0   -137177.16    2463.0748 
+      10    179.37985   -137931.27            0   -137174.48    15655.936 
+      20    206.87654   -138046.99            0   -137174.19   -24042.627 
+      30    150.80122   -137807.43            0   -137171.21   -16524.118 
+      40    173.24945   -137902.35            0   -137171.42   -5716.9119 
+      50    151.80455   -137812.36            0   -137171.91    3480.4584 
+      60    199.08777   -138013.82            0   -137173.88    17881.372 
+      70    217.85748   -138093.86            0   -137174.73   -12270.999 
+      80    202.37482   -138029.39            0   -137175.59   -7622.7319 
+      90    194.90628   -137997.05            0   -137174.75   -32267.471 
+     100    185.17818   -137954.51            0   -137173.26   -6901.7499 
+Loop time of 1.74701 on 4 procs for 100 steps with 32640 atoms
+
+Performance: 2.473 ns/day, 9.706 hours/ns, 57.241 timesteps/s
+94.1% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.89836    | 0.96998    | 1.054      |   6.0 | 55.52
+Neigh   | 0.453      | 0.47091    | 0.50316    |   2.8 | 26.96
+Comm    | 0.15706    | 0.27291    | 0.36547    |  14.5 | 15.62
+Output  | 0.00047016 | 0.00073808 | 0.0015287  |   0.0 |  0.04
+Modify  | 0.0093558  | 0.010209   | 0.011958   |   1.0 |  0.58
+Other   |            | 0.02227    |            |       |  1.27
+
+Nlocal:        8160.00 ave        8163 max        8157 min
+Histogram: 1 1 0 0 0 0 0 0 1 1
+Nghost:        11605.8 ave       11615 max       11593 min
+Histogram: 1 0 0 0 0 0 2 0 0 1
+Neighs:        0.00000 ave           0 max           0 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+FullNghs:  1.22553e+06 ave 1.22735e+06 max 1.22455e+06 min
+Histogram: 2 0 0 1 0 0 0 0 0 1
+
+Total # of neighbors = 4902134
+Ave neighs/atom = 150.18793
+Neighbor list builds = 9
+Dangerous builds = 0
+Total wall time: 0:00:01

bench/POTENTIALS/log.9Oct20.spce.1

@@ -0,0 +1,147 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# SPC/E water box benchmark
+
+units		real
+atom_style	full
+
+read_data	data.spce
+Reading data file ...
+  orthogonal box = (0.02645 0.02645 0.02641) to (35.532800 35.532800 35.473600)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  4500 atoms
+  scanning bonds ...
+  2 = max bonds/atom
+  scanning angles ...
+  1 = max angles/atom
+  reading bonds ...
+  3000 bonds
+  reading angles ...
+  1500 angles
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     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 = 0.001 seconds
+  read_data CPU = 0.009 seconds
+
+replicate	2 4 1
+Replicating atoms ...
+  orthogonal box = (0.02645 0.02645 0.02641) to (71.039150 142.05185 35.473600)
+  1 by 1 by 1 MPI processor grid
+  36000 atoms
+  24000 bonds
+  12000 angles
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     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 = 0.005 seconds
+  replicate CPU = 0.012 seconds
+
+pair_style	lj/cut/coul/long 9.8 9.8
+kspace_style	pppm 1.0e-4
+
+pair_coeff	1 1 0.15535 3.166
+pair_coeff	* 2 0.0000 0.0000
+
+bond_style	harmonic
+angle_style	harmonic
+dihedral_style	none
+improper_style	none
+
+bond_coeff	1 1000.00 1.000
+angle_coeff	1 100.0 109.47
+
+special_bonds   lj/coul 0.0 0.0 0.5
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.5     
+  special bond factors coul:  0.0      0.0      0.5     
+     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 = 0.005 seconds
+
+neighbor        2.0 bin
+neigh_modify	every 1 delay 10 check yes
+
+fix		1 all shake 0.0001 20 0 b 1 a 1
+       0 = # of size 2 clusters
+       0 = # of size 3 clusters
+       0 = # of size 4 clusters
+   12000 = # of frozen angles
+  find clusters CPU = 0.005 seconds
+fix		2 all nvt temp 300.0 300.0 100.0
+
+velocity	all create 300 432567 dist uniform
+
+timestep	2.0
+
+thermo_style    one
+thermo		50
+
+run		100
+PPPM initialization ...
+  using 12-bit tables for long-range coulomb (src/kspace.cpp:328)
+  G vector (1/distance) = 0.2688011
+  grid = 36 64 24
+  stencil order = 5
+  estimated absolute RMS force accuracy = 0.033101471
+  estimated relative force accuracy = 9.9684097e-05
+  using double precision KISS FFT
+  3d grid and FFT values/proc = 91977 55296
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 11.8
+  ghost atom cutoff = 11.8
+  binsize = 5.9, bins = 13 25 7
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut/coul/long, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 105.4 | 105.4 | 105.4 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -133281.51            0   -111820.57    516.17807 
+      50    264.98553   -136986.74            0   -118030.61   -440.29256 
+     100    274.45966   -136364.57            0   -116730.69   -128.61948 
+Loop time of 18.5133 on 1 procs for 100 steps with 36000 atoms
+
+Performance: 0.933 ns/day, 25.713 hours/ns, 5.402 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 14.557     | 14.557     | 14.557     |   0.0 | 78.63
+Bond    | 7.1764e-05 | 7.1764e-05 | 7.1764e-05 |   0.0 |  0.00
+Kspace  | 1.7651     | 1.7651     | 1.7651     |   0.0 |  9.53
+Neigh   | 1.8703     | 1.8703     | 1.8703     |   0.0 | 10.10
+Comm    | 0.042219   | 0.042219   | 0.042219   |   0.0 |  0.23
+Output  | 0.00021219 | 0.00021219 | 0.00021219 |   0.0 |  0.00
+Modify  | 0.26983    | 0.26983    | 0.26983    |   0.0 |  1.46
+Other   |            | 0.008397   |            |       |  0.05
+
+Nlocal:        36000.0 ave       36000 max       36000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:        56963.0 ave       56963 max       56963 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    1.24625e+07 ave 1.24625e+07 max 1.24625e+07 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 12462451
+Ave neighs/atom = 346.17919
+Ave special neighs/atom = 2.0000000
+Neighbor list builds = 9
+Dangerous builds = 6
+Total wall time: 0:00:19

bench/POTENTIALS/log.9Oct20.spce.4

@@ -0,0 +1,147 @@
+LAMMPS (9 Oct 2020)
+  using 1 OpenMP thread(s) per MPI task
+# SPC/E water box benchmark
+
+units		real
+atom_style	full
+
+read_data	data.spce
+Reading data file ...
+  orthogonal box = (0.02645 0.02645 0.02641) to (35.532800 35.532800 35.473600)
+  2 by 2 by 1 MPI processor grid
+  reading atoms ...
+  4500 atoms
+  scanning bonds ...
+  2 = max bonds/atom
+  scanning angles ...
+  1 = max angles/atom
+  reading bonds ...
+  3000 bonds
+  reading angles ...
+  1500 angles
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     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 = 0.001 seconds
+  read_data CPU = 0.008 seconds
+
+replicate	2 4 1
+Replicating atoms ...
+  orthogonal box = (0.02645 0.02645 0.02641) to (71.039150 142.05185 35.473600)
+  1 by 4 by 1 MPI processor grid
+  36000 atoms
+  24000 bonds
+  12000 angles
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.0     
+  special bond factors coul:  0.0      0.0      0.0     
+     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 = 0.002 seconds
+  replicate CPU = 0.005 seconds
+
+pair_style	lj/cut/coul/long 9.8 9.8
+kspace_style	pppm 1.0e-4
+
+pair_coeff	1 1 0.15535 3.166
+pair_coeff	* 2 0.0000 0.0000
+
+bond_style	harmonic
+angle_style	harmonic
+dihedral_style	none
+improper_style	none
+
+bond_coeff	1 1000.00 1.000
+angle_coeff	1 100.0 109.47
+
+special_bonds   lj/coul 0.0 0.0 0.5
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0.0      0.0      0.5     
+  special bond factors coul:  0.0      0.0      0.5     
+     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 = 0.004 seconds
+
+neighbor        2.0 bin
+neigh_modify	every 1 delay 10 check yes
+
+fix		1 all shake 0.0001 20 0 b 1 a 1
+       0 = # of size 2 clusters
+       0 = # of size 3 clusters
+       0 = # of size 4 clusters
+   12000 = # of frozen angles
+  find clusters CPU = 0.003 seconds
+fix		2 all nvt temp 300.0 300.0 100.0
+
+velocity	all create 300 432567 dist uniform
+
+timestep	2.0
+
+thermo_style    one
+thermo		50
+
+run		100
+PPPM initialization ...
+  using 12-bit tables for long-range coulomb (src/kspace.cpp:328)
+  G vector (1/distance) = 0.2688011
+  grid = 36 64 24
+  stencil order = 5
+  estimated absolute RMS force accuracy = 0.033101471
+  estimated relative force accuracy = 9.9684097e-05
+  using double precision KISS FFT
+  3d grid and FFT values/proc = 27993 13824
+Neighbor list info ...
+  update every 1 steps, delay 10 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 11.8
+  ghost atom cutoff = 11.8
+  binsize = 5.9, bins = 13 25 7
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut/coul/long, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/3d/newton
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 37.90 | 37.90 | 37.90 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0          300   -133281.51            0   -111820.57    516.17807 
+      50    264.98553   -136986.74            0   -118030.61   -440.29255 
+     100    274.45966   -136364.57            0   -116730.69   -128.61954 
+Loop time of 5.44355 on 4 procs for 100 steps with 36000 atoms
+
+Performance: 3.174 ns/day, 7.560 hours/ns, 18.370 timesteps/s
+95.4% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 3.82       | 3.8744     | 3.9155     |   1.8 | 71.17
+Bond    | 7.8917e-05 | 8.6784e-05 | 9.4891e-05 |   0.0 |  0.00
+Kspace  | 0.79192    | 0.83671    | 0.88328    |   3.5 | 15.37
+Neigh   | 0.51754    | 0.5178     | 0.51789    |   0.0 |  9.51
+Comm    | 0.069774   | 0.078783   | 0.088247   |   2.3 |  1.45
+Output  | 9.0361e-05 | 0.00015712 | 0.00035048 |   0.0 |  0.00
+Modify  | 0.12822    | 0.13016    | 0.13486    |   0.8 |  2.39
+Other   |            | 0.005435   |            |       |  0.10
+
+Nlocal:        9000.00 ave        9002 max        8998 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+Nghost:        24134.2 ave       24184 max       24062 min
+Histogram: 1 0 0 0 0 0 1 1 0 1
+Neighs:    3.11561e+06 ave 3.11676e+06 max 3.11446e+06 min
+Histogram: 1 0 0 1 0 0 1 0 0 1
+
+Total # of neighbors = 12462451
+Ave neighs/atom = 346.17919
+Ave special neighs/atom = 2.0000000
+Neighbor list builds = 9
+Dangerous builds = 6
+Total wall time: 0:00:05

bench/POTENTIALS/log.9Oct20.sw.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Si via Stillinger-Weber
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		diamond 5.431
-Lattice spacing in x,y,z = 5.431 5.431 5.431
+Lattice spacing in x,y,z = 5.4310000 5.4310000 5.4310000
 region		box block 0 20 0 20 0 10
 create_box	1 box
-Created orthogonal box = (0 0 0) to (108.62 108.62 54.31)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (108.62000 108.62000 54.310000)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.00191712 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	sw
 pair_coeff	* * Si.sw Si
+Reading sw potential file Si.sw with DATE: 2007-06-11
 mass            1 28.06
 
 velocity	all create 1000.0 376847 loop geom
@@ -46,32 +46,32 @@ Per MPI rank memory allocation (min/avg/max) = 12.52 | 12.52 | 12.52 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000    -138771.2            0      -134635    6866.6499 
      100    508.80533   -136736.12            0    -134631.6    6361.7858 
-Loop time of 5.66634 on 1 procs for 100 steps with 32000 atoms
+Loop time of 3.9309 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 1.525 ns/day, 15.740 hours/ns, 17.648 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 2.198 ns/day, 10.919 hours/ns, 25.439 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 5.5464     | 5.5464     | 5.5464     |   0.0 | 97.88
-Neigh   | 0.075834   | 0.075834   | 0.075834   |   0.0 |  1.34
-Comm    | 0.0092049  | 0.0092049  | 0.0092049  |   0.0 |  0.16
-Output  | 0.00010991 | 0.00010991 | 0.00010991 |   0.0 |  0.00
-Modify  | 0.024666   | 0.024666   | 0.024666   |   0.0 |  0.44
-Other   |            | 0.01014    |            |       |  0.18
+Pair    | 3.8206     | 3.8206     | 3.8206     |   0.0 | 97.19
+Neigh   | 0.067368   | 0.067368   | 0.067368   |   0.0 |  1.71
+Comm    | 0.0091503  | 0.0091503  | 0.0091503  |   0.0 |  0.23
+Output  | 0.0001049  | 0.0001049  | 0.0001049  |   0.0 |  0.00
+Modify  | 0.023839   | 0.023839   | 0.023839   |   0.0 |  0.61
+Other   |            | 0.009882   |            |       |  0.25
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    12495 ave 12495 max 12495 min
+Nghost:        12495.0 ave       12495 max       12495 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-FullNghs:  894818 ave 894818 max 894818 min
+FullNghs:     894818.0 ave      894818 max      894818 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 894818
-Ave neighs/atom = 27.9631
+Ave neighs/atom = 27.963062
 Neighbor list builds = 2
 Dangerous builds = 0
-Total wall time: 0:00:05
+Total wall time: 0:00:03

bench/POTENTIALS/log.9Oct20.sw.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Si via Stillinger-Weber
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		diamond 5.431
-Lattice spacing in x,y,z = 5.431 5.431 5.431
+Lattice spacing in x,y,z = 5.4310000 5.4310000 5.4310000
 region		box block 0 20 0 20 0 10
 create_box	1 box
-Created orthogonal box = (0 0 0) to (108.62 108.62 54.31)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (108.62000 108.62000 54.310000)
   2 by 2 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000604153 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	sw
 pair_coeff	* * Si.sw Si
+Reading sw potential file Si.sw with DATE: 2007-06-11
 mass            1 28.06
 
 velocity	all create 1000.0 376847 loop geom
@@ -46,32 +46,32 @@ Per MPI rank memory allocation (min/avg/max) = 4.104 | 4.104 | 4.104 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000    -138771.2            0      -134635    6866.6499 
      100    508.80533   -136736.12            0    -134631.6    6361.7858 
-Loop time of 1.47105 on 4 procs for 100 steps with 32000 atoms
+Loop time of 1.04386 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 5.873 ns/day, 4.086 hours/ns, 67.978 timesteps/s
-98.8% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 8.277 ns/day, 2.900 hours/ns, 95.798 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    | 1.3788     | 1.3929     | 1.4053     |   0.8 | 94.69
-Neigh   | 0.019134   | 0.019502   | 0.019816   |   0.2 |  1.33
-Comm    | 0.024183   | 0.035734   | 0.049122   |   4.7 |  2.43
-Output  | 5.1975e-05 | 6.6102e-05 | 0.00010204 |   0.0 |  0.00
-Modify  | 0.0063825  | 0.0064374  | 0.0064764  |   0.0 |  0.44
-Other   |            | 0.01638    |            |       |  1.11
+Pair    | 0.96496    | 0.97632    | 0.9978     |   1.3 | 93.53
+Neigh   | 0.01732    | 0.017998   | 0.019718   |   0.7 |  1.72
+Comm    | 0.012035   | 0.036398   | 0.049588   |   7.7 |  3.49
+Output  | 4.5061e-05 | 5.5015e-05 | 7.7248e-05 |   0.0 |  0.01
+Modify  | 0.0070148  | 0.0070775  | 0.0071096  |   0.0 |  0.68
+Other   |            | 0.006012   |            |       |  0.58
 
-Nlocal:    8000 ave 8015 max 7978 min
+Nlocal:        8000.00 ave        8015 max        7978 min
 Histogram: 1 0 0 0 0 0 1 1 0 1
-Nghost:    4995 ave 5017 max 4980 min
+Nghost:        4995.00 ave        5017 max        4980 min
 Histogram: 1 0 1 1 0 0 0 0 0 1
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-FullNghs:  223704 ave 224108 max 223131 min
+FullNghs:     223704.0 ave      224108 max      223131 min
 Histogram: 1 0 0 0 0 0 1 1 0 1
 
 Total # of neighbors = 894818
-Ave neighs/atom = 27.9631
+Ave neighs/atom = 27.963062
 Neighbor list builds = 2
 Dangerous builds = 0
 Total wall time: 0:00:01

bench/POTENTIALS/log.9Oct20.tersoff.1

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Si via Tersoff
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		diamond 5.431
-Lattice spacing in x,y,z = 5.431 5.431 5.431
+Lattice spacing in x,y,z = 5.4310000 5.4310000 5.4310000
 region		box block 0 20 0 20 0 10
 create_box	1 box
-Created orthogonal box = (0 0 0) to (108.62 108.62 54.31)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (108.62000 108.62000 54.310000)
   1 by 1 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.0019412 secs
+  create_atoms CPU = 0.002 seconds
 
 pair_style	tersoff
 pair_coeff	* * Si.tersoff Si
+Reading tersoff potential file Si.tersoff with DATE: 2007-10-25
 mass            1 28.06
 
 velocity	all create 1000.0 376847 loop geom
@@ -42,36 +42,36 @@ Neighbor list info ...
       pair build: full/bin/atomonly
       stencil: full/bin/3d
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 11.1 | 11.1 | 11.1 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 11.11 | 11.11 | 11.11 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000   -148173.19            0   -144036.99    7019.4434 
      100    430.57813   -145815.61            0   -144034.65   -14550.734 
-Loop time of 8.53088 on 1 procs for 100 steps with 32000 atoms
+Loop time of 4.71424 on 1 procs for 100 steps with 32000 atoms
 
-Performance: 1.013 ns/day, 23.697 hours/ns, 11.722 timesteps/s
-99.8% CPU use with 1 MPI tasks x 1 OpenMP threads
+Performance: 1.833 ns/day, 13.095 hours/ns, 21.212 timesteps/s
+99.9% CPU use with 1 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 8.4236     | 8.4236     | 8.4236     |   0.0 | 98.74
-Neigh   | 0.065852   | 0.065852   | 0.065852   |   0.0 |  0.77
-Comm    | 0.0078607  | 0.0078607  | 0.0078607  |   0.0 |  0.09
-Output  | 0.00010872 | 0.00010872 | 0.00010872 |   0.0 |  0.00
-Modify  | 0.023968   | 0.023968   | 0.023968   |   0.0 |  0.28
-Other   |            | 0.009521   |            |       |  0.11
+Pair    | 4.612      | 4.612      | 4.612      |   0.0 | 97.83
+Neigh   | 0.060618   | 0.060618   | 0.060618   |   0.0 |  1.29
+Comm    | 0.008847   | 0.008847   | 0.008847   |   0.0 |  0.19
+Output  | 9.9659e-05 | 9.9659e-05 | 9.9659e-05 |   0.0 |  0.00
+Modify  | 0.023234   | 0.023234   | 0.023234   |   0.0 |  0.49
+Other   |            | 0.00941    |            |       |  0.20
 
-Nlocal:    32000 ave 32000 max 32000 min
+Nlocal:        32000.0 ave       32000 max       32000 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    11537 ave 11537 max 11537 min
+Nghost:        11537.0 ave       11537 max       11537 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
-FullNghs:  530500 ave 530500 max 530500 min
+FullNghs:     530500.0 ave      530500 max      530500 min
 Histogram: 1 0 0 0 0 0 0 0 0 0
 
 Total # of neighbors = 530500
-Ave neighs/atom = 16.5781
+Ave neighs/atom = 16.578125
 Neighbor list builds = 2
 Dangerous builds = 0
-Total wall time: 0:00:08
+Total wall time: 0:00:04

bench/POTENTIALS/log.9Oct20.tersoff.4

@@ -1,5 +1,4 @@
-LAMMPS (16 Mar 2018)
-OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
+LAMMPS (9 Oct 2020)
   using 1 OpenMP thread(s) per MPI task
 # bulk Si via Tersoff
 
@@ -7,17 +6,18 @@ units		metal
 atom_style	atomic
 
 lattice		diamond 5.431
-Lattice spacing in x,y,z = 5.431 5.431 5.431
+Lattice spacing in x,y,z = 5.4310000 5.4310000 5.4310000
 region		box block 0 20 0 20 0 10
 create_box	1 box
-Created orthogonal box = (0 0 0) to (108.62 108.62 54.31)
+Created orthogonal box = (0.0000000 0.0000000 0.0000000) to (108.62000 108.62000 54.310000)
   2 by 2 by 1 MPI processor grid
 create_atoms	1 box
 Created 32000 atoms
-  Time spent = 0.000605822 secs
+  create_atoms CPU = 0.001 seconds
 
 pair_style	tersoff
 pair_coeff	* * Si.tersoff Si
+Reading tersoff potential file Si.tersoff with DATE: 2007-10-25
 mass            1 28.06
 
 velocity	all create 1000.0 376847 loop geom
@@ -42,36 +42,36 @@ Neighbor list info ...
       pair build: full/bin/atomonly
       stencil: full/bin/3d
       bin: standard
-Per MPI rank memory allocation (min/avg/max) = 3.753 | 3.753 | 3.753 Mbytes
+Per MPI rank memory allocation (min/avg/max) = 3.754 | 3.754 | 3.754 Mbytes
 Step Temp E_pair E_mol TotEng Press 
        0         1000   -148173.19            0   -144036.99    7019.4434 
      100    430.57813   -145815.61            0   -144034.65   -14550.734 
-Loop time of 2.16161 on 4 procs for 100 steps with 32000 atoms
+Loop time of 1.32053 on 4 procs for 100 steps with 32000 atoms
 
-Performance: 3.997 ns/day, 6.004 hours/ns, 46.262 timesteps/s
-99.4% CPU use with 4 MPI tasks x 1 OpenMP threads
+Performance: 6.543 ns/day, 3.668 hours/ns, 75.727 timesteps/s
+97.5% CPU use with 4 MPI tasks x 1 OpenMP threads
 
 MPI task timing breakdown:
 Section |  min time  |  avg time  |  max time  |%varavg| %total
 ---------------------------------------------------------------
-Pair    | 2.1122     | 2.1165     | 2.122      |   0.2 | 97.91
-Neigh   | 0.016894   | 0.016915   | 0.016955   |   0.0 |  0.78
-Comm    | 0.012348   | 0.017858   | 0.022105   |   2.7 |  0.83
-Output  | 4.7684e-05 | 6.2048e-05 | 9.9421e-05 |   0.0 |  0.00
-Modify  | 0.0064063  | 0.0064579  | 0.0065169  |   0.0 |  0.30
-Other   |            | 0.003793   |            |       |  0.18
+Pair    | 1.1729     | 1.2118     | 1.2453     |   2.3 | 91.77
+Neigh   | 0.015989   | 0.016319   | 0.016708   |   0.3 |  1.24
+Comm    | 0.046884   | 0.078767   | 0.11602    |   8.9 |  5.96
+Output  | 3.9816e-05 | 7.0453e-05 | 0.00015831 |   0.0 |  0.01
+Modify  | 0.0070612  | 0.0071967  | 0.0073555  |   0.1 |  0.54
+Other   |            | 0.006331   |            |       |  0.48
 
-Nlocal:    8000 ave 8005 max 7993 min
+Nlocal:        8000.00 ave        8005 max        7993 min
 Histogram: 1 0 0 0 0 1 0 1 0 1
-Nghost:    4580.25 ave 4593 max 4567 min
+Nghost:        4580.25 ave        4593 max        4567 min
 Histogram: 1 0 0 1 0 0 0 1 0 1
-Neighs:    0 ave 0 max 0 min
+Neighs:        0.00000 ave           0 max           0 min
 Histogram: 4 0 0 0 0 0 0 0 0 0
-FullNghs:  132625 ave 132785 max 132562 min
+FullNghs:     132625.0 ave      132785 max      132562 min
 Histogram: 2 1 0 0 0 0 0 0 0 1
 
 Total # of neighbors = 530500
-Ave neighs/atom = 16.5781
+Ave neighs/atom = 16.578125
 Neighbor list builds = 2
 Dangerous builds = 0
-Total wall time: 0:00:02
+Total wall time: 0:00:01

cmake/CMakeLists.txt

@@ -25,15 +25,22 @@ set(LAMMPS_POTENTIALS_DIR ${LAMMPS_DIR}/potentials)
 find_package(Git)
 
 # by default, install into $HOME/.local (not /usr/local), so that no root access (and sudo!!) is needed
-if (CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
-  set(CMAKE_INSTALL_PREFIX "$ENV{HOME}/.local" CACHE PATH "default install path" FORCE )
+if(CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
+  set(CMAKE_INSTALL_PREFIX "$ENV{HOME}/.local" CACHE PATH "Default install path" FORCE)
+endif()
+
+# If enabled, no need to use LD_LIBRARY_PATH / DYLD_LIBRARY_PATH when installed
+option(LAMMPS_INSTALL_RPATH "Set runtime path for shared libraries linked to LAMMPS binaries" OFF)
+if (LAMMPS_INSTALL_RPATH)
+  set(CMAKE_INSTALL_RPATH ${CMAKE_INSTALL_FULL_LIBDIR})
+  set(CMAKE_INSTALL_RPATH_USE_LINK_PATH ON)
 endif()
 
 # Cmake modules/macros are in a subdirectory to keep this file cleaner
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/Modules)
 
 # make sure LIBRARY_PATH is set if environment variable is set
-if (DEFINED ENV{LIBRARY_PATH})
+if(DEFINED ENV{LIBRARY_PATH})
   list(APPEND CMAKE_LIBRARY_PATH "$ENV{LIBRARY_PATH}")
   message(STATUS "Appending $ENV{LIBRARY_PATH} to CMAKE_LIBRARY_PATH: ${CMAKE_LIBRARY_PATH}")
 endif()
@@ -90,6 +97,7 @@ if(BUILD_SHARED_LIBS) # for all pkg libs, mpi_stubs and linalg
 endif()
 
 option(BUILD_TOOLS "Build and install LAMMPS tools (msi2lmp, binary2txt, chain)" OFF)
+option(BUILD_LAMMPS_SHELL "Build and install the LAMMPS shell" OFF)
 
 include(GNUInstallDirs)
 file(GLOB ALL_SOURCES ${LAMMPS_SOURCE_DIR}/[^.]*.cpp)
@@ -106,13 +114,15 @@ option(CMAKE_VERBOSE_MAKEFILE "Generate verbose Makefiles" OFF)
 set(STANDARD_PACKAGES ASPHERE BODY CLASS2 COLLOID COMPRESS DIPOLE
   GRANULAR KSPACE LATTE MANYBODY MC MESSAGE MISC MLIAP MOLECULE PERI POEMS
   QEQ REPLICA RIGID SHOCK SPIN SNAP SRD KIM PYTHON MSCG MPIIO VORONOI
-  USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-MESODPD USER-CGSDK USER-COLVARS
-  USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD USER-LB
-  USER-MANIFOLD USER-MEAMC USER-MESONT USER-MGPT USER-MISC USER-MOFFF USER-MOLFILE
-  USER-NETCDF USER-PHONON USER-PLUMED USER-PTM USER-QTB USER-REACTION
-  USER-REAXC USER-SCAFACOS USER-SDPD USER-SMD USER-SMTBQ USER-SPH USER-TALLY
-  USER-UEF USER-VTK USER-QUIP USER-QMMM USER-YAFF USER-ADIOS)
-set(SUFFIX_PACKAGES CORESHELL USER-OMP KOKKOS OPT USER-INTEL GPU)
+  USER-ADIOS USER-ATC USER-AWPMD USER-BOCS USER-CGDNA USER-MESODPD USER-CGSDK
+  USER-COLVARS USER-DIFFRACTION USER-DPD USER-DRUDE USER-EFF USER-FEP USER-H5MD
+  USER-LB USER-MANIFOLD USER-MEAMC USER-MESONT USER-MGPT USER-MISC USER-MOFFF
+  USER-MOLFILE USER-NETCDF USER-PHONON USER-PLUMED USER-PTM USER-QTB
+  USER-REACTION USER-REAXC USER-SCAFACOS USER-SDPD USER-SMD USER-SMTBQ USER-SPH
+  USER-TALLY USER-UEF USER-VTK USER-QUIP USER-QMMM USER-YAFF)
+
+set(SUFFIX_PACKAGES CORESHELL GPU KOKKOS OPT USER-INTEL USER-OMP)
+
 foreach(PKG ${STANDARD_PACKAGES} ${SUFFIX_PACKAGES})
   option(PKG_${PKG} "Build ${PKG} Package" OFF)
 endforeach()
@@ -153,15 +163,14 @@ if(BUILD_MPI)
     endif()
   endif()
 else()
-  enable_language(C)
-  file(GLOB MPI_SOURCES ${LAMMPS_SOURCE_DIR}/STUBS/mpi.c)
+  file(GLOB MPI_SOURCES ${LAMMPS_SOURCE_DIR}/STUBS/mpi.cpp)
   add_library(mpi_stubs STATIC ${MPI_SOURCES})
   set_target_properties(mpi_stubs PROPERTIES OUTPUT_NAME lammps_mpi_stubs${LAMMPS_MACHINE})
-  target_include_directories(mpi_stubs PUBLIC $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS> $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/lammps/mpi>)
-  install(FILES ${LAMMPS_SOURCE_DIR}/STUBS/mpi.h DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/lammps/mpi)
+  target_include_directories(mpi_stubs PUBLIC $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
   if(BUILD_SHARED_LIBS)
     target_link_libraries(lammps PRIVATE mpi_stubs)
-    target_include_directories(lammps INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS> $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/lammps/mpi>)
+    target_include_directories(lammps INTERFACE $<BUILD_INTERFACE:${LAMMPS_SOURCE_DIR}/STUBS>)
+    target_compile_definitions(lammps INTERFACE $<INSTALL_INTERFACE:LAMMPS_LIB_NO_MPI>)
   else()
     target_link_libraries(lammps PUBLIC mpi_stubs)
   endif()
@@ -219,6 +228,7 @@ if(BUILD_OMP)
   endif()
 
   if (((CMAKE_CXX_COMPILER_ID STREQUAL "GNU") AND (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 9.0)) OR
+      (CMAKE_CXX_COMPILER_ID STREQUAL "PGI") OR
       ((CMAKE_CXX_COMPILER_ID STREQUAL "Clang") AND (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 10.0)) OR
       ((CMAKE_CXX_COMPILER_ID STREQUAL "Intel") AND (CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 19.0)))
     # GCC 9.x and later plus Clang 10.x and later implement strict OpenMP 4.0 semantics for consts.
@@ -343,20 +353,22 @@ find_program(GZIP_EXECUTABLE gzip)
 find_package_handle_standard_args(GZIP REQUIRED_VARS GZIP_EXECUTABLE)
 option(WITH_GZIP "Enable GZIP support" ${GZIP_FOUND})
 if(WITH_GZIP)
-  if(NOT GZIP_FOUND)
+  if(GZIP_FOUND OR ((CMAKE_SYSTEM_NAME STREQUAL Windows) AND CMAKE_CROSSCOMPILING))
+    target_compile_definitions(lammps PRIVATE -DLAMMPS_GZIP)
+  else()
     message(FATAL_ERROR "gzip executable not found")
   endif()
-  target_compile_definitions(lammps PRIVATE -DLAMMPS_GZIP)
 endif()
 
 find_program(FFMPEG_EXECUTABLE ffmpeg)
 find_package_handle_standard_args(FFMPEG REQUIRED_VARS FFMPEG_EXECUTABLE)
 option(WITH_FFMPEG "Enable FFMPEG support" ${FFMPEG_FOUND})
 if(WITH_FFMPEG)
-  if(NOT FFMPEG_FOUND)
+  if(FFMPEG_FOUND OR ((CMAKE_SYSTEM_NAME STREQUAL Windows) AND CMAKE_CROSSCOMPILING))
+    target_compile_definitions(lammps PRIVATE -DLAMMPS_FFMPEG)
+  else()
     message(FATAL_ERROR "ffmpeg executable not found")
   endif()
-  target_compile_definitions(lammps PRIVATE -DLAMMPS_FFMPEG)
 endif()
 
 if(BUILD_SHARED_LIBS)
@@ -369,13 +381,20 @@ else()
   set(CUDA_REQUEST_PIC)
 endif()
 
-foreach(PKG_WITH_INCL KSPACE PYTHON VORONOI USER-COLVARS USER-MOLFILE USER-NETCDF USER-PLUMED USER-QMMM
+foreach(PKG_WITH_INCL KSPACE PYTHON MLIAP VORONOI USER-COLVARS USER-MOLFILE USER-NETCDF USER-PLUMED USER-QMMM
         USER-QUIP USER-SCAFACOS USER-SMD USER-VTK KIM LATTE MESSAGE MSCG COMPRESS)
   if(PKG_${PKG_WITH_INCL})
     include(Packages/${PKG_WITH_INCL})
   endif()
 endforeach()
 
+# optionally enable building script wrappers using swig
+option(WITH_SWIG "Build scripting language wrappers with SWIG" OFF)
+if(WITH_SWIG)
+  get_filename_component(LAMMPS_SWIG_DIR ${LAMMPS_SOURCE_DIR}/../tools/swig ABSOLUTE)
+  add_subdirectory(${LAMMPS_SWIG_DIR} swig)
+endif()
+
 set(CMAKE_TUNE_FLAGS "${CMAKE_TUNE_DEFAULT}" CACHE STRING "Compiler and machine specific optimization flags (compilation only)")
 separate_arguments(CMAKE_TUNE_FLAGS)
 foreach(_FLAG ${CMAKE_TUNE_FLAGS})
@@ -569,19 +588,19 @@ add_dependencies(lammps gitversion)
 ############################################
 get_property(LANGUAGES GLOBAL PROPERTY ENABLED_LANGUAGES)
 list (FIND LANGUAGES "Fortran" _index)
-if (${_index} GREATER -1)
+if(${_index} GREATER -1)
   target_link_libraries(lammps PRIVATE ${CMAKE_Fortran_IMPLICIT_LINK_LIBRARIES})
 endif()
 set(LAMMPS_CXX_HEADERS angle.h atom.h bond.h citeme.h comm.h compute.h dihedral.h domain.h error.h fix.h force.h group.h improper.h
   input.h info.h kspace.h lammps.h lattice.h library.h lmppython.h lmptype.h memory.h modify.h neighbor.h neigh_list.h output.h
-  pair.h pointers.h region.h timer.h universe.h update.h variable.h)
+  pair.h pointers.h region.h timer.h universe.h update.h utils.h variable.h)
 if(LAMMPS_EXCEPTIONS)
   list(APPEND LAMMPS_CXX_HEADERS exceptions.h)
 endif()
 
 set_target_properties(lammps PROPERTIES OUTPUT_NAME lammps${LAMMPS_MACHINE})
 set_target_properties(lammps PROPERTIES SOVERSION ${SOVERSION})
-target_include_directories(lammps PUBLIC $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
+target_include_directories(lammps PUBLIC $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/lammps>)
 file(MAKE_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/includes/lammps)
 foreach(_HEADER ${LAMMPS_CXX_HEADERS})
   add_custom_command(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/includes/lammps/${_HEADER} COMMAND ${CMAKE_COMMAND} -E copy_if_different ${LAMMPS_SOURCE_DIR}/${_HEADER} ${CMAKE_CURRENT_BINARY_DIR}/includes/lammps/${_HEADER} DEPENDS ${LAMMPS_SOURCE_DIR}/${_HEADER})
@@ -610,36 +629,7 @@ if(BUILD_SHARED_LIBS)
 endif()
 install(FILES ${LAMMPS_DOC_DIR}/lammps.1 DESTINATION ${CMAKE_INSTALL_MANDIR}/man1 RENAME ${LAMMPS_BINARY}.1)
 
-if(BUILD_TOOLS)
-  add_executable(binary2txt ${LAMMPS_TOOLS_DIR}/binary2txt.cpp)
-  target_compile_definitions(binary2txt PRIVATE -DLAMMPS_${LAMMPS_SIZES})
-  install(TARGETS binary2txt DESTINATION ${CMAKE_INSTALL_BINDIR})
-
-  include(CheckGeneratorSupport)
-  if(CMAKE_GENERATOR_SUPPORT_FORTRAN)
-    include(CheckLanguage)
-    check_language(Fortran)
-    if(CMAKE_Fortran_COMPILER)
-      enable_language(Fortran)
-      add_executable(chain.x ${LAMMPS_TOOLS_DIR}/chain.f)
-      target_link_libraries(chain.x PRIVATE ${CMAKE_Fortran_IMPLICIT_LINK_LIBRARIES})
-      install(TARGETS chain.x DESTINATION ${CMAKE_INSTALL_BINDIR})
-    else()
-      message(WARNING "No suitable Fortran compiler found, skipping building 'chain.x'")
-    endif()
-  else()
-    message(WARNING "CMake build doesn't support fortran, skipping building 'chain.x'")
-  endif()
-
-  enable_language(C)
-  get_filename_component(MSI2LMP_SOURCE_DIR ${LAMMPS_TOOLS_DIR}/msi2lmp/src ABSOLUTE)
-  file(GLOB MSI2LMP_SOURCES ${MSI2LMP_SOURCE_DIR}/[^.]*.c)
-  add_executable(msi2lmp ${MSI2LMP_SOURCES})
-  target_link_libraries(msi2lmp PRIVATE ${MATH_LIBRARIES})
-  install(TARGETS msi2lmp DESTINATION ${CMAKE_INSTALL_BINDIR})
-  install(FILES ${LAMMPS_DOC_DIR}/msi2lmp.1 DESTINATION ${CMAKE_INSTALL_MANDIR}/man1)
-endif()
-
+include(Tools)
 include(Documentation)
 
 ###############################################################################
@@ -668,7 +658,7 @@ install(
 if(BUILD_SHARED_LIBS)
   if(CMAKE_VERSION VERSION_LESS 3.12)
     # adjust so we find Python 3 versions before Python 2 on old systems with old CMake
-    set(Python_ADDITIONAL_VERSIONS 3.8 3.7 3.6 3.5)
+    set(Python_ADDITIONAL_VERSIONS 3.9 3.8 3.7 3.6 3.5)
     find_package(PythonInterp) # Deprecated since version 3.12
     if(PYTHONINTERP_FOUND)
         set(Python_EXECUTABLE ${PYTHON_EXECUTABLE})
@@ -678,10 +668,10 @@ if(BUILD_SHARED_LIBS)
   endif()
   if (Python_EXECUTABLE)
     add_custom_target(
-      install-python
-      ${Python_EXECUTABLE} install.py -v ${LAMMPS_SOURCE_DIR}/version.h
-      -m ${LAMMPS_PYTHON_DIR}/lammps.py
-      -l ${CMAKE_BINARY_DIR}/liblammps${CMAKE_SHARED_LIBRARY_SUFFIX}
+      install-python ${CMAKE_COMMAND} -E remove_directory build
+      COMMAND ${Python_EXECUTABLE} install.py -v ${LAMMPS_SOURCE_DIR}/version.h
+      -p ${LAMMPS_PYTHON_DIR}/lammps
+      -l ${CMAKE_BINARY_DIR}/liblammps${LAMMPS_MACHINE}${CMAKE_SHARED_LIBRARY_SUFFIX}
       WORKING_DIRECTORY  ${LAMMPS_PYTHON_DIR}
       COMMENT "Installing LAMMPS Python module")
   else()
@@ -710,11 +700,8 @@ if(BUILD_SHARED_LIBS OR PKG_PYTHON)
     find_package(Python COMPONENTS Interpreter)
   endif()
   if (Python_EXECUTABLE)
-    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 ${LAMMPS_PYTHON_DIR}/lammps.py DESTINATION ${PYTHON_INSTDIR})
+    file(MAKE_DIRECTORY ${CMAKE_BINARY_DIR}/python)
+    install(CODE "execute_process(COMMAND ${Python_EXECUTABLE} setup.py build -b ${CMAKE_BINARY_DIR}/python install --prefix=${CMAKE_INSTALL_PREFIX} --root=\$ENV{DESTDIR}/ WORKING_DIRECTORY ${LAMMPS_PYTHON_DIR})")
   endif()
 endif()
 
@@ -722,23 +709,31 @@ include(Testing)
 include(CodeCoverage)
 include(CodingStandard)
 
-###############################################################################
-# Print package summary
-###############################################################################
-foreach(PKG ${STANDARD_PACKAGES} ${SUFFIX_PACKAGES})
-  if(PKG_${PKG})
-    message(STATUS "Building package: ${PKG}")
-  endif()
-endforeach()
-
 get_target_property(DEFINES lammps COMPILE_DEFINITIONS)
 include(FeatureSummary)
 feature_summary(DESCRIPTION "The following tools and libraries have been found and configured:" WHAT PACKAGES_FOUND)
 message(STATUS "<<< Build configuration >>>
+   Operating System: ${CMAKE_SYSTEM_NAME}
    Build type:       ${CMAKE_BUILD_TYPE}
    Install path:     ${CMAKE_INSTALL_PREFIX}
-   Generator:        ${CMAKE_GENERATOR} using ${CMAKE_MAKE_PROGRAM}
--- <<< Compilers and Flags: >>>
+   Generator:        ${CMAKE_GENERATOR} using ${CMAKE_MAKE_PROGRAM}")
+###############################################################################
+# Print package summary
+###############################################################################
+set(ENABLED_PACKAGES)
+foreach(PKG ${STANDARD_PACKAGES} ${SUFFIX_PACKAGES})
+  if(PKG_${PKG})
+    list(APPEND ENABLED_PACKAGES ${PKG})
+  endif()
+endforeach()
+if(ENABLED_PACKAGES)
+  list(SORT ENABLED_PACKAGES)
+else()
+  set(ENABLED_PACKAGES "<None>")
+endif()
+message(STATUS "Enabled packages: ${ENABLED_PACKAGES}")
+
+message(STATUS "<<< Compilers and Flags: >>>
 -- C++ Compiler:     ${CMAKE_CXX_COMPILER}
       Type:          ${CMAKE_CXX_COMPILER_ID}
       Version:       ${CMAKE_CXX_COMPILER_VERSION}
@@ -750,14 +745,14 @@ if(OPTIONS)
 endif()
 get_property(LANGUAGES GLOBAL PROPERTY ENABLED_LANGUAGES)
 list (FIND LANGUAGES "Fortran" _index)
-if (${_index} GREATER -1)
+if(${_index} GREATER -1)
   message(STATUS "Fortran Compiler: ${CMAKE_Fortran_COMPILER}
       Type:          ${CMAKE_Fortran_COMPILER_ID}
       Version:       ${CMAKE_Fortran_COMPILER_VERSION}
       Fortran Flags:${CMAKE_Fortran_FLAGS} ${CMAKE_Fortran_FLAGS_${BTYPE}}")
 endif()
 list (FIND LANGUAGES "C" _index)
-if (${_index} GREATER -1)
+if(${_index} GREATER -1)
   message(STATUS "C compiler:       ${CMAKE_C_COMPILER}
       Type:          ${CMAKE_C_COMPILER_ID}
       Version:       ${CMAKE_C_COMPILER_VERSION}
@@ -789,9 +784,7 @@ if(PKG_GPU)
   message(STATUS "<<< GPU package settings >>>
 -- GPU API:          ${GPU_API}")
   if(GPU_API STREQUAL "CUDA")
-    message(STATUS "GPU architecture: ${GPU_ARCH}")
-  elseif(GPU_API STREQUAL "OPENCL")
-    message(STATUS "OpenCL tuning:    ${OCL_TUNE}")
+    message(STATUS "GPU default architecture: ${GPU_ARCH}")
   elseif(GPU_API STREQUAL "HIP")
     message(STATUS "HIP platform:     ${HIP_PLATFORM}")
     message(STATUS "HIP architecture: ${HIP_ARCH}")
@@ -834,3 +827,15 @@ endif()
 if(BUILD_DOC)
   message(STATUS "<<< Building HTML Manual >>>")
 endif()
+if(BUILD_TOOLS)
+  message(STATUS "<<< Building Tools >>>")
+endif()
+if(BUILD_LAMMPS_SHELL)
+  message(STATUS "<<< Building LAMMPS Shell >>>")
+endif()
+if(ENABLE_TESTING)
+  message(STATUS "<<< Building Unit Tests >>>")
+  if(ENABLE_COVERAGE)
+    message(STATUS "Collecting code coverage data")
+  endif()
+endif()

cmake/Modules/CodingStandard.cmake

@@ -8,7 +8,7 @@ else()
     find_package(Python3 COMPONENTS Interpreter QUIET)
 endif()
 
-if (Python3_EXECUTABLE)
+if(Python3_EXECUTABLE)
     if(Python3_VERSION VERSION_GREATER_EQUAL 3.5)
         add_custom_target(
           check-whitespace

cmake/Modules/Documentation.cmake

@@ -50,27 +50,21 @@ if(BUILD_DOC)
     OUTPUT ${DOC_BUILD_DIR}/requirements.txt
     DEPENDS docenv ${DOCENV_REQUIREMENTS_FILE}
     COMMAND ${CMAKE_COMMAND} -E copy ${DOCENV_REQUIREMENTS_FILE} ${DOC_BUILD_DIR}/requirements.txt
-    COMMAND ${DOCENV_BINARY_DIR}/pip install --upgrade pip
-    COMMAND ${DOCENV_BINARY_DIR}/pip install --upgrade ${LAMMPS_DOC_DIR}/utils/converters
-    COMMAND ${DOCENV_BINARY_DIR}/pip install --use-feature=2020-resolver -r ${DOC_BUILD_DIR}/requirements.txt --upgrade
+    COMMAND ${DOCENV_BINARY_DIR}/pip $ENV{PIP_OPTIONS} install --upgrade pip
+    COMMAND ${DOCENV_BINARY_DIR}/pip $ENV{PIP_OPTIONS} install --upgrade ${LAMMPS_DOC_DIR}/utils/converters
+    COMMAND ${DOCENV_BINARY_DIR}/pip $ENV{PIP_OPTIONS} install -r ${DOC_BUILD_DIR}/requirements.txt --upgrade
   )
 
   # download mathjax distribution and unpack to folder "mathjax"
   if(NOT EXISTS ${DOC_BUILD_STATIC_DIR}/mathjax/es5)
-    file(DOWNLOAD "https://github.com/mathjax/MathJax/archive/3.0.5.tar.gz"
+    file(DOWNLOAD "https://github.com/mathjax/MathJax/archive/3.1.2.tar.gz"
       "${CMAKE_CURRENT_BINARY_DIR}/mathjax.tar.gz"
-      EXPECTED_MD5 5d9d3799cce77a1a95eee6be04eb68e7)
+      EXPECTED_MD5 a4a6a093a89bc2ccab1452d766b98e53)
     execute_process(COMMAND ${CMAKE_COMMAND} -E tar xzf mathjax.tar.gz WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
     file(GLOB MATHJAX_VERSION_DIR ${CMAKE_CURRENT_BINARY_DIR}/MathJax-*)
     execute_process(COMMAND ${CMAKE_COMMAND} -E rename ${MATHJAX_VERSION_DIR} ${DOC_BUILD_STATIC_DIR}/mathjax)
   endif()
 
-  # for increased browser compatibility
-  if(NOT EXISTS ${DOC_BUILD_STATIC_DIR}/polyfill.js)
-    file(DOWNLOAD "https://polyfill.io/v3/polyfill.min.js?features=es6"
-      "${DOC_BUILD_STATIC_DIR}/polyfill.js")
-  endif()
-
   # set up doxygen and add targets to run it
   file(MAKE_DIRECTORY ${DOXYGEN_BUILD_DIR})
   file(COPY ${LAMMPS_DOC_DIR}/doxygen/lammps-logo.png DESTINATION ${DOXYGEN_BUILD_DIR}/lammps-logo.png)

cmake/Modules/FindCythonize.cmake

@@ -0,0 +1,30 @@
+# Find the Cythonize tool.
+#
+# This code sets the following variables:
+#
+#  Cythonize_EXECUTABLE
+#
+# adapted from https://github.com/cmarshall108/cython-cmake-example/blob/master/cmake/FindCython.cmake
+#=============================================================================
+
+if(CMAKE_VERSION VERSION_LESS 3.12)
+    find_package(PythonInterp 3.6 QUIET) # Deprecated since version 3.12
+    if(PYTHONINTERP_FOUND)
+        set(Python3_EXECUTABLE ${PYTHON_EXECUTABLE})
+    endif()
+else()
+    find_package(Python3 3.6 COMPONENTS Interpreter QUIET)
+endif()
+
+# Use the Cython executable that lives next to the Python executable
+# if it is a local installation.
+if(Python3_EXECUTABLE)
+  get_filename_component(_python_path ${Python3_EXECUTABLE} PATH)
+  find_program(Cythonize_EXECUTABLE
+    NAMES cythonize3 cythonize cythonize.bat
+    HINTS ${_python_path})
+endif()
+
+include(FindPackageHandleStandardArgs)
+FIND_PACKAGE_HANDLE_STANDARD_ARGS(Cythonize REQUIRED_VARS Cythonize_EXECUTABLE)
+mark_as_advanced(Cythonize_EXECUTABLE)

cmake/Modules/GTest.cmake

@@ -20,10 +20,10 @@ ExternalProject_Add(googletest
                                     -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
                                     -DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}
                                     -DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}
-                    BUILD_BYPRODUCTS <BINARY_DIR>/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gtest${GTEST_LIB_POSTFIX}.a
-                                     <BINARY_DIR>/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gmock${GTEST_LIB_POSTFIX}.a
-                                     <BINARY_DIR>/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gtest_main${GTEST_LIB_POSTFIX}.a
-                                     <BINARY_DIR>/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gmock_main${GTEST_LIB_POSTFIX}.a
+                    BUILD_BYPRODUCTS <BINARY_DIR>/lib/libgtest${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
+                                     <BINARY_DIR>/lib/libgmock${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
+                                     <BINARY_DIR>/lib/libgtest_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
+                                     <BINARY_DIR>/lib/libgmock_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX}
                     LOG_DOWNLOAD ON
                     LOG_CONFIGURE ON
                     LOG_BUILD ON
@@ -39,10 +39,10 @@ file(MAKE_DIRECTORY ${GTEST_INCLUDE_DIR})
 file(MAKE_DIRECTORY ${GMOCK_INCLUDE_DIR})
 
 ExternalProject_Get_Property(googletest BINARY_DIR)
-set(GTEST_LIBRARY_PATH ${BINARY_DIR}/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gtest${GTEST_LIB_POSTFIX}.a)
-set(GMOCK_LIBRARY_PATH ${BINARY_DIR}/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gmock${GTEST_LIB_POSTFIX}.a)
-set(GTEST_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gtest_main${GTEST_LIB_POSTFIX}.a)
-set(GMOCK_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/${CMAKE_FIND_LIBRARY_PREFIXES}gmock_main${GTEST_LIB_POSTFIX}.a)
+set(GTEST_LIBRARY_PATH ${BINARY_DIR}/lib/libgtest${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
+set(GMOCK_LIBRARY_PATH ${BINARY_DIR}/lib/libgmock${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
+set(GTEST_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/libgtest_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
+set(GMOCK_MAIN_LIBRARY_PATH ${BINARY_DIR}/lib/libgmock_main${GTEST_LIB_POSTFIX}${CMAKE_STATIC_LIBRARY_SUFFIX})
 
 # Prevent GoogleTest from overriding our compiler/linker options
 # when building with Visual Studio

cmake/Modules/GenerateBinaryHeader.cmake

@@ -1,3 +1,3 @@
 # utility script to call GenerateBinaryHeader function
 include(${SOURCE_DIR}/Modules/LAMMPSUtils.cmake)
-GenerateBinaryHeader(${VARNAME} ${HEADER_FILE} ${SOURCE_FILES})
+GenerateBinaryHeader(${VARNAME} ${HEADER_FILE} ${SOURCE_FILE})

cmake/Modules/LAMMPSUtils.cmake

@@ -50,6 +50,7 @@ function(check_for_autogen_files source_dir)
     file(GLOB SRC_AUTOGEN_FILES ${source_dir}/style_*.h)
     file(GLOB SRC_AUTOGEN_PACKAGES ${source_dir}/packages_*.h)
     list(APPEND SRC_AUTOGEN_FILES ${SRC_AUTOGEN_PACKAGES} ${source_dir}/lmpinstalledpkgs.h ${source_dir}/lmpgitversion.h)
+    list(APPEND SRC_AUTOGEN_FILES ${SRC_AUTOGEN_PACKAGES} ${source_dir}/mliap_model_python_couple.h ${source_dir}/mliap_model_python_couple.cpp)
     foreach(_SRC ${SRC_AUTOGEN_FILES})
       get_filename_component(FILENAME "${_SRC}" NAME)
       if(EXISTS ${source_dir}/${FILENAME})
@@ -71,19 +72,15 @@ macro(pkg_depends PKG1 PKG2)
 endmacro()
 
 # CMake-only replacement for bin2c and xxd
-function(GenerateBinaryHeader varname outfile files)
+function(GenerateBinaryHeader varname outfile infile)
     message("Creating ${outfile}...")
     file(WRITE ${outfile} "// CMake generated file\n")
-    math(EXPR ARG_END   "${ARGC}-1")
 
-    foreach(IDX RANGE 2 ${ARG_END})
-        list(GET ARGV ${IDX} filename)
-        file(READ ${filename} content HEX)
-        string(REGEX REPLACE "([0-9a-f][0-9a-f])" "0x\\1," content "${content}")
-        string(REGEX REPLACE ",$" "" content "${content}")
-        file(APPEND ${outfile} "const unsigned char ${varname}[] = { ${content} };\n")
-        file(APPEND ${outfile} "const unsigned int ${varname}_size = sizeof(${varname});\n")
-    endforeach()
+    file(READ ${infile} content HEX)
+    string(REGEX REPLACE "([0-9a-f][0-9a-f])" "0x\\1," content "${content}")
+    string(REGEX REPLACE ",$" "" content "${content}")
+    file(APPEND ${outfile} "const unsigned char ${varname}[] = { ${content} };\n")
+    file(APPEND ${outfile} "const unsigned int ${varname}_size = sizeof(${varname});\n")
 endfunction(GenerateBinaryHeader)
 
 # fetch missing potential files

cmake/Modules/MPI4WIN.cmake

@@ -1,7 +1,7 @@
 # Download and configure custom MPICH files for Windows
 message(STATUS "Downloading and configuring MPICH-1.4.1 for Windows")
 include(ExternalProject)
-if (CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64")
+if(CMAKE_SYSTEM_PROCESSOR STREQUAL "x86_64")
   ExternalProject_Add(mpi4win_build
     URL https://download.lammps.org/thirdparty/mpich2-win64-devel.tar.gz
     URL_MD5 4939fdb59d13182fd5dd65211e469f14

cmake/Modules/OpenCLLoader.cmake

@@ -0,0 +1,48 @@
+message(STATUS "Downloading and building OpenCL loader library")
+
+include(ExternalProject)
+set(OPENCL_LOADER_URL "https://download.lammps.org/thirdparty/opencl-loader-2020.12.18.tar.gz" CACHE STRING "URL for OpenCL loader tarball")
+mark_as_advanced(OPENCL_LOADER_URL)
+ExternalProject_Add(opencl_loader
+                    URL ${OPENCL_LOADER_URL}
+                    URL_MD5         011cdcbd41030be94f3fced6d763a52a
+                    SOURCE_DIR      "${CMAKE_BINARY_DIR}/opencl_loader-src"
+                    BINARY_DIR      "${CMAKE_BINARY_DIR}/opencl_loader-build"
+                    CMAKE_ARGS      ${CMAKE_REQUEST_PIC} ${CMAKE_EXTRA_OPENCL_LOADER_OPTS}
+                                    -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
+                                    -DCMAKE_INSTALL_PREFIX=<INSTALL_DIR>
+                                    -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}
+                                    -DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}
+                                    -DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}
+                    BUILD_BYPRODUCTS <BINARY_DIR>/libOpenCL${CMAKE_STATIC_LIBRARY_SUFFIX}
+                    LOG_DOWNLOAD ON
+                    LOG_CONFIGURE ON
+                    LOG_BUILD ON
+                    INSTALL_COMMAND ""
+                    TEST_COMMAND    "")
+
+ExternalProject_Get_Property(opencl_loader SOURCE_DIR)
+set(OPENCL_LOADER_INCLUDE_DIR ${SOURCE_DIR}/inc)
+
+# workaround for CMake 3.10 on ubuntu 18.04
+file(MAKE_DIRECTORY ${OPENCL_LOADER_INCLUDE_DIR})
+
+ExternalProject_Get_Property(opencl_loader BINARY_DIR)
+set(OPENCL_LOADER_LIBRARY_PATH "${BINARY_DIR}/libOpenCL${CMAKE_STATIC_LIBRARY_SUFFIX}")
+
+find_package(Threads QUIET)
+if(NOT WIN32)
+  set(OPENCL_LOADER_DEP_LIBS "Threads::Threads;${CMAKE_DL_LIBS}")
+else()
+  set(OPENCL_LOADER_DEP_LIBS "cfgmgr32;runtimeobject")
+endif()
+
+add_library(OpenCL::OpenCL UNKNOWN IMPORTED)
+add_dependencies(OpenCL::OpenCL opencl_loader)
+
+set_target_properties(OpenCL::OpenCL PROPERTIES
+  IMPORTED_LOCATION ${OPENCL_LOADER_LIBRARY_PATH}
+  INTERFACE_INCLUDE_DIRECTORIES ${OPENCL_LOADER_INCLUDE_DIR}
+  INTERFACE_LINK_LIBRARIES "${OPENCL_LOADER_DEP_LIBS}")
+
+

cmake/Modules/Packages/GPU.cmake

@@ -1,7 +1,10 @@
 set(GPU_SOURCES_DIR ${LAMMPS_SOURCE_DIR}/GPU)
 set(GPU_SOURCES ${GPU_SOURCES_DIR}/gpu_extra.h
                 ${GPU_SOURCES_DIR}/fix_gpu.h
-                ${GPU_SOURCES_DIR}/fix_gpu.cpp)
+                ${GPU_SOURCES_DIR}/fix_gpu.cpp
+                ${GPU_SOURCES_DIR}/fix_nh_gpu.h
+                ${GPU_SOURCES_DIR}/fix_nh_gpu.cpp)
+target_compile_definitions(lammps PRIVATE -DLMP_GPU)
 
 set(GPU_API "opencl" CACHE STRING "API used by GPU package")
 set(GPU_API_VALUES opencl cuda hip)
@@ -35,6 +38,9 @@ if(GPU_API STREQUAL "CUDA")
   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)
+    if(CUDPP_OPT)
+      message(FATAL_ERROR "Must use -DCUDPP_OPT=OFF with -DGPU_CUDA_MPS_SUPPORT=ON")
+    endif()
     set(GPU_CUDA_MPS_FLAGS "-DCUDA_PROXY")
   endif()
 
@@ -97,6 +103,10 @@ if(GPU_API STREQUAL "CUDA")
   if(CUDA_VERSION VERSION_GREATER_EQUAL "11.0")
     string(APPEND GPU_CUDA_GENCODE " -gencode arch=compute_80,code=[sm_80,compute_80]")
   endif()
+  # Ampere (GPU Arch 8.6) is supported by CUDA 11.1 and later
+  if(CUDA_VERSION VERSION_GREATER_EQUAL "11.1")
+    string(APPEND GPU_CUDA_GENCODE " -gencode arch=compute_86,code=[sm_86,compute_86]")
+  endif()
   if(CUDA_VERSION VERSION_GREATER_EQUAL "12.0")
     message(WARNING "Unsupported CUDA version. Use at your own risk.")
   endif()
@@ -135,27 +145,13 @@ if(GPU_API STREQUAL "CUDA")
   target_include_directories(nvc_get_devices PRIVATE ${CUDA_INCLUDE_DIRS})
 
 elseif(GPU_API STREQUAL "OPENCL")
-  if(${CMAKE_SYSTEM_NAME} STREQUAL "Windows")
-    # download and unpack support binaries for compilation of windows binaries.
-    set(LAMMPS_THIRDPARTY_URL "https://download.lammps.org/thirdparty")
-    file(DOWNLOAD "${LAMMPS_THIRDPARTY_URL}/opencl-win-devel.tar.gz" "${CMAKE_CURRENT_BINARY_DIR}/opencl-win-devel.tar.gz"
-            EXPECTED_MD5 2c00364888d5671195598b44c2e0d44d)
-    execute_process(COMMAND ${CMAKE_COMMAND} -E tar xzf opencl-win-devel.tar.gz WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR})
-    add_library(OpenCL::OpenCL UNKNOWN IMPORTED)
-    if(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "x86")
-      set_target_properties(OpenCL::OpenCL PROPERTIES IMPORTED_LOCATION "${CMAKE_CURRENT_BINARY_DIR}/OpenCL/lib_win32/libOpenCL.dll")
-    elseif(${CMAKE_SYSTEM_PROCESSOR} STREQUAL "x86_64")
-      set_target_properties(OpenCL::OpenCL PROPERTIES IMPORTED_LOCATION "${CMAKE_CURRENT_BINARY_DIR}/OpenCL/lib_win64/libOpenCL.dll")
-    endif()
-    set_target_properties(OpenCL::OpenCL PROPERTIES INTERFACE_INCLUDE_DIRECTORIES "${CMAKE_CURRENT_BINARY_DIR}/OpenCL/include")
+  option(USE_STATIC_OPENCL_LOADER "Download and include a static OpenCL ICD loader" ON)
+  mark_as_advanced(USE_STATIC_OPENCL_LOADER)
+  if (USE_STATIC_OPENCL_LOADER)
+    include(OpenCLLoader)
   else()
     find_package(OpenCL REQUIRED)
   endif()
-  set(OCL_TUNE "generic" CACHE STRING "OpenCL Device Tuning")
-  set(OCL_TUNE_VALUES intel fermi kepler cypress generic)
-  set_property(CACHE OCL_TUNE PROPERTY STRINGS ${OCL_TUNE_VALUES})
-  validate_option(OCL_TUNE OCL_TUNE_VALUES)
-  string(TOUPPER ${OCL_TUNE} OCL_TUNE)
 
   include(OpenCLUtils)
   set(OCL_COMMON_HEADERS ${LAMMPS_LIB_SOURCE_DIR}/gpu/lal_preprocessor.h ${LAMMPS_LIB_SOURCE_DIR}/gpu/lal_aux_fun1.h)
@@ -199,7 +195,7 @@ elseif(GPU_API STREQUAL "OPENCL")
   add_library(gpu STATIC ${GPU_LIB_SOURCES})
   target_link_libraries(gpu PRIVATE OpenCL::OpenCL)
   target_include_directories(gpu PRIVATE ${CMAKE_CURRENT_BINARY_DIR}/gpu)
-  target_compile_definitions(gpu PRIVATE -D_${GPU_PREC_SETTING} -D${OCL_TUNE}_OCL -DMPI_GERYON -DUCL_NO_EXIT)
+  target_compile_definitions(gpu PRIVATE -D_${GPU_PREC_SETTING} -DMPI_GERYON -DGERYON_NUMA_FISSION -DUCL_NO_EXIT)
   target_compile_definitions(gpu PRIVATE -DUSE_OPENCL)
 
   target_link_libraries(lammps PRIVATE gpu)
@@ -207,6 +203,7 @@ elseif(GPU_API STREQUAL "OPENCL")
   add_executable(ocl_get_devices ${LAMMPS_LIB_SOURCE_DIR}/gpu/geryon/ucl_get_devices.cpp)
   target_compile_definitions(ocl_get_devices PRIVATE -DUCL_OPENCL)
   target_link_libraries(ocl_get_devices PRIVATE OpenCL::OpenCL)
+  add_dependencies(ocl_get_devices OpenCL::OpenCL)
 elseif(GPU_API STREQUAL "HIP")
   if(NOT DEFINED HIP_PATH)
       if(NOT DEFINED ENV{HIP_PATH})
@@ -309,7 +306,7 @@ elseif(GPU_API STREQUAL "HIP")
     endif()
 
     add_custom_command(OUTPUT ${CUBIN_H_FILE}
-      COMMAND ${CMAKE_COMMAND} -D SOURCE_DIR=${CMAKE_CURRENT_SOURCE_DIR} -D VARNAME=${CU_NAME} -D HEADER_FILE=${CUBIN_H_FILE} -D SOURCE_FILES=${CUBIN_FILE} -P ${CMAKE_CURRENT_SOURCE_DIR}/Modules/GenerateBinaryHeader.cmake
+      COMMAND ${CMAKE_COMMAND} -D SOURCE_DIR=${CMAKE_CURRENT_SOURCE_DIR} -D VARNAME=${CU_NAME} -D HEADER_FILE=${CUBIN_H_FILE} -D SOURCE_FILE=${CUBIN_FILE} -P ${CMAKE_CURRENT_SOURCE_DIR}/Modules/GenerateBinaryHeader.cmake
       DEPENDS ${CUBIN_FILE}
       COMMENT "Generating ${CU_NAME}_cubin.h")
 
@@ -389,13 +386,10 @@ elseif(GPU_API STREQUAL "HIP")
   target_link_libraries(lammps PRIVATE gpu)
 endif()
 
-# GPU package
-FindStyleHeaders(${GPU_SOURCES_DIR} FIX_CLASS fix_ FIX)
-
 set_property(GLOBAL PROPERTY "GPU_SOURCES" "${GPU_SOURCES}")
-
-# detects styles which have GPU version
+# detect styles which have a GPU version
 RegisterStylesExt(${GPU_SOURCES_DIR} gpu GPU_SOURCES)
+RegisterFixStyle(${GPU_SOURCES_DIR}/fix_gpu.h)
 
 get_property(GPU_SOURCES GLOBAL PROPERTY GPU_SOURCES)
 

cmake/Modules/Packages/KIM.cmake

@@ -19,6 +19,8 @@ if(CURL_FOUND)
     target_compile_definitions(lammps PRIVATE -DLMP_NO_SSL_CHECK)
   endif()
 endif()
+set(KIM_EXTRA_UNITTESTS OFF CACHE STRING "Set extra unit tests verbose mode on/off. If on, extra tests are included.")
+mark_as_advanced(KIM_EXTRA_UNITTESTS)
 find_package(PkgConfig QUIET)
 set(DOWNLOAD_KIM_DEFAULT ON)
 if(PKG_CONFIG_FOUND)
@@ -34,8 +36,8 @@ if(DOWNLOAD_KIM)
   enable_language(C)
   enable_language(Fortran)
   ExternalProject_Add(kim_build
-    URL https://s3.openkim.org/kim-api/kim-api-2.1.3.txz
-    URL_MD5 6ee829a1bbba5f8b9874c88c4c4ebff8
+    URL https://s3.openkim.org/kim-api/kim-api-2.2.1.txz
+    URL_MD5 ae1ddda2ef7017ea07934e519d023dca
     BINARY_DIR build
     CMAKE_ARGS ${CMAKE_REQUEST_PIC}
                -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
@@ -53,11 +55,28 @@ if(DOWNLOAD_KIM)
   add_library(LAMMPS::KIM UNKNOWN IMPORTED)
   set_target_properties(LAMMPS::KIM PROPERTIES
     IMPORTED_LOCATION "${INSTALL_DIR}/lib/libkim-api${CMAKE_SHARED_LIBRARY_SUFFIX}"
-    INTERFACE_INCLUDE_DIRECTORIES "${INSTALL_DIR}/include/kim-api")
-  target_link_libraries(lammps PRIVATE LAMMPS::KIM)
+    INTERFACE_INCLUDE_DIRECTORIES "${INSTALL_DIR}/include/kim-api"
+    )
   add_dependencies(LAMMPS::KIM kim_build)
+  target_link_libraries(lammps PRIVATE LAMMPS::KIM)
+  # Set rpath so lammps build directory is relocatable
+  if("${CMAKE_SYSTEM_NAME}" STREQUAL "Darwin")
+    set(_rpath_prefix "@loader_path")
+  else()
+    set(_rpath_prefix "$ORIGIN")
+  endif()
+  set_target_properties(lmp PROPERTIES
+    BUILD_RPATH "${_rpath_prefix}/kim_build-prefix/lib"
+    )
 else()
-  find_package(PkgConfig REQUIRED)
-  pkg_check_modules(KIM-API REQUIRED IMPORTED_TARGET libkim-api>=${KIM-API_MIN_VERSION})
-  target_link_libraries(lammps PRIVATE PkgConfig::KIM-API)
+  if(KIM-API_FOUND AND KIM-API_VERSION VERSION_GREATER_EQUAL 2.2.0)
+    # For kim-api >= 2.2.0
+    find_package(KIM-API 2.2.0 CONFIG REQUIRED)
+    target_link_libraries(lammps PRIVATE KIM-API::kim-api)
+  else()
+    # For kim-api 2.1.3 (consistent with previous version of this file)
+    find_package(PkgConfig REQUIRED)
+    pkg_check_modules(KIM-API REQUIRED IMPORTED_TARGET libkim-api>=${KIM-API_MIN_VERSION})
+    target_link_libraries(lammps PRIVATE PkgConfig::KIM-API)
+  endif()
 endif()

cmake/Modules/Packages/KOKKOS.cmake

@@ -1,4 +1,7 @@
 ########################################################################
+# As of version 3.3.0 Kokkos requires C++14
+set(CMAKE_CXX_STANDARD 14)
+########################################################################
 # consistency checks and Kokkos options/settings required by LAMMPS
 if(Kokkos_ENABLE_CUDA)
   message(STATUS "KOKKOS: Enabling CUDA LAMBDA function support")
@@ -35,8 +38,8 @@ if(DOWNLOAD_KOKKOS)
   list(APPEND KOKKOS_LIB_BUILD_ARGS "-DCMAKE_TOOLCHAIN_FILE=${CMAKE_TOOLCHAIN_FILE}")
   include(ExternalProject)
   ExternalProject_Add(kokkos_build
-    URL https://github.com/kokkos/kokkos/archive/3.2.00.tar.gz
-    URL_MD5 81569170fe232e5e64ab074f7cca5e50
+    URL https://github.com/kokkos/kokkos/archive/3.3.01.tar.gz
+    URL_MD5 08201d1c7cf5bc458ce0f5b44a629d5a
     CMAKE_ARGS ${KOKKOS_LIB_BUILD_ARGS}
     BUILD_BYPRODUCTS <INSTALL_DIR>/lib/libkokkoscore.a
   )
@@ -50,7 +53,7 @@ if(DOWNLOAD_KOKKOS)
   target_link_libraries(lammps PRIVATE LAMMPS::KOKKOS)
   add_dependencies(LAMMPS::KOKKOS kokkos_build)
 elseif(EXTERNAL_KOKKOS)
-  find_package(Kokkos 3.2.00 REQUIRED CONFIG)
+  find_package(Kokkos 3.3.01 REQUIRED CONFIG)
   target_link_libraries(lammps PRIVATE Kokkos::kokkos)
 else()
   set(LAMMPS_LIB_KOKKOS_SRC_DIR ${LAMMPS_LIB_SOURCE_DIR}/kokkos)

cmake/Modules/Packages/MESSAGE.cmake

@@ -2,9 +2,8 @@ if(LAMMPS_SIZES STREQUAL BIGBIG)
   message(FATAL_ERROR "The MESSAGE Package is not compatible with -DLAMMPS_BIGBIG")
 endif()
 option(MESSAGE_ZMQ "Use ZeroMQ in MESSAGE package" OFF)
-file(GLOB_RECURSE cslib_SOURCES ${LAMMPS_LIB_SOURCE_DIR}/message/cslib/[^.]*.F
-    ${LAMMPS_LIB_SOURCE_DIR}/message/cslib/[^.]*.c
-    ${LAMMPS_LIB_SOURCE_DIR}/message/cslib/[^.]*.cpp)
+file(GLOB_RECURSE cslib_SOURCES
+        ${LAMMPS_LIB_SOURCE_DIR}/message/cslib/[^.]*.cpp)
 
 add_library(cslib STATIC ${cslib_SOURCES})
 target_compile_definitions(cslib PRIVATE -DLAMMPS_${LAMMPS_SIZES})

cmake/Modules/Packages/MLIAP.cmake

@@ -0,0 +1,40 @@
+# if PYTHON package is included we may also include Python support in MLIAP
+set(MLIAP_ENABLE_PYTHON_DEFAULT OFF)
+if(PKG_PYTHON)
+  find_package(Cythonize QUIET)
+  if(Cythonize_FOUND)
+    set(MLIAP_ENABLE_PYTHON_DEFAULT ON)
+  endif()
+endif()
+
+option(MLIAP_ENABLE_PYTHON "Build MLIAP package with Python support" ${MLIAP_ENABLE_PYTHON_DEFAULT})
+
+if(MLIAP_ENABLE_PYTHON)
+  find_package(Cythonize REQUIRED)
+  if(NOT PKG_PYTHON)
+    message(FATAL_ERROR "Must enable PYTHON package for including Python support in MLIAP")
+  endif()
+  if(CMAKE_VERSION VERSION_LESS 3.12)
+    if(PYTHONLIBS_VERSION_STRING VERSION_LESS 3.6)
+      message(FATAL_ERROR "Python support in MLIAP requires Python 3.6 or later")
+    endif()
+  else()
+    if(Python_VERSION VERSION_LESS 3.6)
+      message(FATAL_ERROR "Python support in MLIAP requires Python 3.6 or later")
+    endif()
+  endif()
+
+  set(MLIAP_BINARY_DIR ${CMAKE_BINARY_DIR}/cython)
+  set(MLIAP_CYTHON_SRC ${LAMMPS_SOURCE_DIR}/MLIAP/mliap_model_python_couple.pyx)
+  get_filename_component(MLIAP_CYTHON_BASE ${MLIAP_CYTHON_SRC} NAME_WE)
+  file(MAKE_DIRECTORY ${MLIAP_BINARY_DIR})
+  add_custom_command(OUTPUT  ${MLIAP_BINARY_DIR}/${MLIAP_CYTHON_BASE}.cpp ${MLIAP_BINARY_DIR}/${MLIAP_CYTHON_BASE}.h
+          COMMAND            ${CMAKE_COMMAND} -E copy_if_different ${MLIAP_CYTHON_SRC} ${MLIAP_BINARY_DIR}/${MLIAP_CYTHON_BASE}.pyx
+          COMMAND            ${Cythonize_EXECUTABLE} -3 ${MLIAP_BINARY_DIR}/${MLIAP_CYTHON_BASE}.pyx
+          WORKING_DIRECTORY  ${MLIAP_BINARY_DIR}
+          MAIN_DEPENDENCY    ${MLIAP_CYTHON_SRC}
+          COMMENT "Generating C++ sources with cythonize...")
+  target_compile_definitions(lammps PRIVATE -DMLIAP_PYTHON)
+  target_sources(lammps PRIVATE ${MLIAP_BINARY_DIR}/${MLIAP_CYTHON_BASE}.cpp)
+  target_include_directories(lammps PRIVATE ${MLIAP_BINARY_DIR})
+endif()

cmake/Modules/Packages/USER-PLUMED.cmake

@@ -55,8 +55,8 @@ if(DOWNLOAD_PLUMED)
   endif()
   include(ExternalProject)
   ExternalProject_Add(plumed_build
-    URL https://github.com/plumed/plumed2/releases/download/v2.6.1/plumed-src-2.6.1.tgz
-    URL_MD5 89a9a450fc6025299fe16af235957163
+    URL https://github.com/plumed/plumed2/releases/download/v2.7.0/plumed-src-2.7.0.tgz
+    URL_MD5 95f29dd0c067577f11972ff90dfc7d12
     BUILD_IN_SOURCE 1
     CONFIGURE_COMMAND <SOURCE_DIR>/configure --prefix=<INSTALL_DIR>
                                              ${CONFIGURE_REQUEST_PIC}

cmake/Modules/StyleHeaderUtils.cmake

@@ -59,7 +59,6 @@ function(CreateStyleHeader path filename)
             set(temp "${temp}#include \"${FNAME}\"\n")
         endforeach()
     endif()
-    message(STATUS "Generating ${filename}...")
     file(WRITE "${path}/${filename}.tmp" "${temp}" )
     execute_process(COMMAND ${CMAKE_COMMAND} -E copy_if_different "${path}/${filename}.tmp" "${path}/${filename}")
     set_property(DIRECTORY APPEND PROPERTY CMAKE_CONFIGURE_DEPENDS "${path}/${filename}")
@@ -142,6 +141,7 @@ function(RegisterStylesExt search_path extension sources)
 endfunction(RegisterStylesExt)
 
 function(GenerateStyleHeaders output_path)
+    message(STATUS "Generating style headers...")
     GenerateStyleHeader(${output_path} ANGLE      angle     ) # force
     GenerateStyleHeader(${output_path} ATOM_VEC   atom      ) # atom      atom_vec_hybrid
     GenerateStyleHeader(${output_path} BODY       body      ) # atom_vec_body
@@ -232,7 +232,6 @@ function(CreatePackagesHeader path filename)
       set(temp "${temp}#include \"${DNAME}/${FNAME}\"\n")
     endforeach()
   endif()
-  message(STATUS "Generating ${filename}...")
   file(WRITE "${path}/${filename}.tmp" "${temp}" )
   execute_process(COMMAND ${CMAKE_COMMAND} -E copy_if_different "${path}/${filename}.tmp" "${path}/${filename}")
   set_property(DIRECTORY APPEND PROPERTY CMAKE_CONFIGURE_DEPENDS "${path}/${filename}")
@@ -244,6 +243,7 @@ function(GeneratePackagesHeader path property style)
 endfunction(GeneratePackagesHeader)
 
 function(GeneratePackagesHeaders output_path)
+    message(STATUS "Generating package headers...")
     GeneratePackagesHeader(${output_path} PKGANGLE      angle     ) # force
     GeneratePackagesHeader(${output_path} PKGATOM_VEC   atom      ) # atom      atom_vec_hybrid
     GeneratePackagesHeader(${output_path} PKGBODY       body      ) # atom_vec_body

cmake/Modules/Tools.cmake

@@ -0,0 +1,57 @@
+if(BUILD_TOOLS)
+  add_executable(binary2txt ${LAMMPS_TOOLS_DIR}/binary2txt.cpp)
+  target_compile_definitions(binary2txt PRIVATE -DLAMMPS_${LAMMPS_SIZES})
+  install(TARGETS binary2txt DESTINATION ${CMAKE_INSTALL_BINDIR})
+
+  include(CheckGeneratorSupport)
+  if(CMAKE_GENERATOR_SUPPORT_FORTRAN)
+    include(CheckLanguage)
+    check_language(Fortran)
+    if(CMAKE_Fortran_COMPILER)
+      enable_language(Fortran)
+      add_executable(chain.x ${LAMMPS_TOOLS_DIR}/chain.f)
+      target_link_libraries(chain.x PRIVATE ${CMAKE_Fortran_IMPLICIT_LINK_LIBRARIES})
+      install(TARGETS chain.x DESTINATION ${CMAKE_INSTALL_BINDIR})
+    else()
+      message(WARNING "No suitable Fortran compiler found, skipping build of 'chain.x'")
+    endif()
+  else()
+    message(WARNING "CMake build doesn't support fortran, skipping build of 'chain.x'")
+  endif()
+
+  enable_language(C)
+  get_filename_component(MSI2LMP_SOURCE_DIR ${LAMMPS_TOOLS_DIR}/msi2lmp/src ABSOLUTE)
+  file(GLOB MSI2LMP_SOURCES ${MSI2LMP_SOURCE_DIR}/[^.]*.c)
+  add_executable(msi2lmp ${MSI2LMP_SOURCES})
+  target_link_libraries(msi2lmp PRIVATE ${MATH_LIBRARIES})
+  install(TARGETS msi2lmp DESTINATION ${CMAKE_INSTALL_BINDIR})
+  install(FILES ${LAMMPS_DOC_DIR}/msi2lmp.1 DESTINATION ${CMAKE_INSTALL_MANDIR}/man1)
+endif()
+
+if(BUILD_LAMMPS_SHELL)
+  find_package(PkgConfig REQUIRED)
+  pkg_check_modules(READLINE IMPORTED_TARGET REQUIRED readline)
+  if(NOT LAMMPS_EXCEPTIONS)
+    message(WARNING "The LAMMPS shell needs LAMMPS_EXCEPTIONS enabled for full functionality")
+  endif()
+
+  # include resource compiler to embed icons into the executable on Windows
+  if(CMAKE_SYSTEM_NAME STREQUAL "Windows")
+    enable_language(RC)
+    set(ICON_RC_FILE ${LAMMPS_TOOLS_DIR}/lammps-shell/lmpicons.rc)
+  endif()
+
+  add_executable(lammps-shell ${LAMMPS_TOOLS_DIR}/lammps-shell/lammps-shell.cpp ${ICON_RC_FILE})
+  target_include_directories(lammps-shell PRIVATE ${LAMMPS_TOOLS_DIR}/lammps-shell)
+
+  # workaround for broken readline pkg-config file on FreeBSD
+  if(CMAKE_SYSTEM_NAME STREQUAL FreeBSD)
+    target_include_directories(lammps-shell PRIVATE /usr/local/include)
+  endif()
+  target_link_libraries(lammps-shell PRIVATE lammps PkgConfig::READLINE)
+  install(TARGETS lammps-shell EXPORT LAMMPS_Targets DESTINATION ${CMAKE_INSTALL_BINDIR})
+  install(DIRECTORY ${LAMMPS_TOOLS_DIR}/lammps-shell/icons DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/)
+  install(FILES ${LAMMPS_TOOLS_DIR}/lammps-shell/lammps-shell.desktop DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/applications/)
+endif()
+
+

cmake/Modules/YAML.cmake

@@ -0,0 +1,32 @@
+message(STATUS "Downloading and building YAML library")
+
+include(ExternalProject)
+set(YAML_URL "https://pyyaml.org/download/libyaml/yaml-0.2.5.tar.gz" CACHE STRING "URL for libyaml tarball")
+mark_as_advanced(YAML_URL)
+ExternalProject_Add(libyaml
+                    URL               ${YAML_URL}
+                    URL_MD5           bb15429d8fb787e7d3f1c83ae129a999
+                    SOURCE_DIR        "${CMAKE_BINARY_DIR}/yaml-src"
+                    BINARY_DIR        "${CMAKE_BINARY_DIR}/yaml-build"
+                    CONFIGURE_COMMAND <SOURCE_DIR>/configure ${CONFIGURE_REQUEST_PIC}
+                                      CXX=${CMAKE_CXX_COMPILER}
+                                      CC=${CMAKE_C_COMPILER}
+                                      --prefix=<INSTALL_DIR> --disable-shared
+                    BUILD_BYPRODUCTS  <INSTALL_DIR>/lib/libyaml${CMAKE_STATIC_LIBRARY_SUFFIX}
+                    TEST_COMMAND      "")
+
+ExternalProject_Get_Property(libyaml INSTALL_DIR)
+set(YAML_INCLUDE_DIR ${INSTALL_DIR}/include)
+set(YAML_LIBRARY_DIR ${INSTALL_DIR}/lib)
+
+# workaround for CMake 3.10 on ubuntu 18.04
+file(MAKE_DIRECTORY ${YAML_INCLUDE_DIR})
+file(MAKE_DIRECTORY ${YAML_LIBRARY_DIR})
+
+set(YAML_LIBRARY_PATH ${INSTALL_DIR}/lib/libyaml${CMAKE_STATIC_LIBRARY_SUFFIX})
+
+add_library(Yaml::Yaml UNKNOWN IMPORTED)
+set_target_properties(Yaml::Yaml PROPERTIES
+        IMPORTED_LOCATION ${YAML_LIBRARY_PATH}
+        INTERFACE_INCLUDE_DIRECTORIES ${YAML_INCLUDE_DIR})
+add_dependencies(Yaml::Yaml libyaml)