sync with SVN for creation of stable release

remove the misleading "(which it is by default)" from several doc files

.gitignore

@@ -0,0 +1,34 @@
+*~
+*.o
+*.so
+*.cu_o
+*.ptx
+*_ptx.h
+*.a
+*.d
+*.x
+*.exe
+*.dll
+*.pyc
+__pycache__
+
+Obj_*
+log.lammps
+log.cite
+*.bz2
+*.gz
+*.tar
+.*.swp
+*.orig
+*.rej
+.vagrant
+\#*#
+.#*
+
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db

bench/Cu_u3.eam

@@ -1,4 +1,4 @@
-Cu functions (universal 3)
+DATE: 2007-06-11 CONTRIBUTOR: Stephen Foiles, foiles@sandia.gov CITATION: Foiles et al, Phys Rev B, 33, 7983 (1986) COMMENT: Cu functions (universal 3), SM Foiles et al, PRB, 33, 7983 (1986)
    29     63.550         3.6150    FCC
   500  5.0100200400801306e-04  500  1.0000000000000009e-02  4.9499999999999886e+00
   0.                     -3.1561636903424350e-01 -5.2324876182494506e-01 -6.9740831416804383e-01 -8.5202525457518519e-01

bench/FERMI/README

@@ -0,0 +1,103 @@
+These are input scripts used to run versions of several of the
+benchmarks in the top-level bench directory using the GPU and
+USER-CUDA accelerator packages.  The results of running these scripts
+on two different machines (a desktop with 2 Tesla GPUs and the ORNL
+Titan supercomputer) are shown on the "GPU (Fermi)" section of the
+Benchmark page of the LAMMPS WWW site: lammps.sandia.gov/bench.
+
+Examples are shown below of how to run these scripts.  This assumes
+you have built 3 executables with both the GPU and USER-CUDA packages
+installed, e.g.
+
+lmp_linux_single
+lmp_linux_mixed
+lmp_linux_double
+
+The precision (single, mixed, double) refers to the GPU and USER-CUDA
+pacakge precision.  See the README files in the lib/gpu and lib/cuda
+directories for instructions on how to build the packages with
+different precisions.  The GPU and USER-CUDA sub-sections of the
+doc/Section_accelerate.html file also describes this process.
+
+Make.py -d ~/lammps -j 16 -p #all orig -m linux -o cpu -a exe
+Make.py -d ~/lammps -j 16 -p #all opt orig -m linux -o opt -a exe
+Make.py -d ~/lammps -j 16 -p #all omp orig -m linux -o omp -a exe
+Make.py -d ~/lammps -j 16 -p #all gpu orig -m linux \
+        -gpu mode=double arch=20 -o gpu_double -a libs exe
+Make.py -d ~/lammps -j 16 -p #all gpu orig -m linux \
+        -gpu mode=mixed arch=20 -o gpu_mixed -a libs exe
+Make.py -d ~/lammps -j 16 -p #all gpu orig -m linux \
+        -gpu mode=single arch=20 -o gpu_single -a libs exe
+Make.py -d ~/lammps -j 16 -p #all cuda orig -m linux \
+        -cuda mode=double arch=20 -o cuda_double -a libs exe
+Make.py -d ~/lammps -j 16 -p #all cuda orig -m linux \
+        -cuda mode=mixed arch=20 -o cuda_mixed -a libs exe
+Make.py -d ~/lammps -j 16 -p #all cuda orig -m linux \
+        -cuda mode=single arch=20 -o cuda_single -a libs exe
+Make.py -d ~/lammps -j 16 -p #all intel orig -m linux -o intel_cpu -a exe
+Make.py -d ~/lammps -j 16 -p #all kokkos orig -m linux -o kokkos_omp -a exe
+Make.py -d ~/lammps -j 16 -p #all kokkos orig -kokkos cuda arch=20 \
+        -m cuda -o kokkos_cuda -a exe
+
+Make.py -d ~/lammps -j 16 -p #all opt omp gpu cuda intel kokkos orig \
+        -gpu mode=double arch=20 -cuda mode=double arch=20 -m linux \
+        -o all -a libs exe
+
+Make.py -d ~/lammps -j 16 -p #all opt omp gpu cuda intel kokkos orig \
+        -kokkos cuda arch=20 -gpu mode=double arch=20 \
+        -cuda mode=double arch=20 -m cuda -o all_cuda -a libs exe
+
+------------------------------------------------------------------------
+
+To run on just CPUs (without using the GPU or USER-CUDA styles),
+do something like the following:
+
+mpirun -np 1 lmp_linux_double -v x 8 -v y 8 -v z 8 -v t 100 < in.lj
+mpirun -np 12 lmp_linux_double -v x 16 -v y 16 -v z 16 -v t 100 < in.eam
+
+The "xyz" settings determine the problem size.  The "t" setting
+determines the number of timesteps.
+
+These mpirun commands run on a single node.  To run on multiple
+nodes, scale up the "-np" setting.
+
+------------------------------------------------------------------------
+
+To run with the GPU package, do something like the following:
+
+mpirun -np 12 lmp_linux_single -sf gpu -v x 32 -v y 32 -v z 64 -v t 100 < in.lj
+mpirun -np 8 lmp_linux_mixed -sf gpu -pk gpu 2 -v x 32 -v y 32 -v z 64 -v t 100 < in.eam
+
+The "xyz" settings determine the problem size.  The "t" setting
+determines the number of timesteps.  The "np" setting determines how
+many MPI tasks (per node) the problem will run on.  The numeric
+argument to the "-pk" setting is the number of GPUs (per node); 1 GPU
+is the default.  Note that you can use more MPI tasks than GPUs (per
+node) with the GPU package.
+
+These mpirun commands run on a single node.  To run on multiple nodes,
+scale up the "-np" setting, and control the number of MPI tasks per
+node via a "-ppn" setting.
+
+------------------------------------------------------------------------
+
+To run with the USER-CUDA package, do something like the following:
+
+mpirun -np 1 lmp_linux_single -c on -sf cuda -v x 16 -v y 16 -v z 16 -v t 100 < in.lj
+mpirun -np 2 lmp_linux_double -c on -sf cuda -pk cuda 2 -v x 32 -v y 64 -v z 64 -v t 100 < in.eam
+
+The "xyz" settings determine the problem size.  The "t" setting
+determines the number of timesteps.  The "np" setting determines how
+many MPI tasks (per node) the problem will run on.  The numeric
+argument to the "-pk" setting is the number of GPUs (per node); 1 GPU
+is the default.  Note that the number of MPI tasks must equal the
+number of GPUs (both per node) with the USER-CUDA package.
+
+These mpirun commands run on a single node.  To run on multiple nodes,
+scale up the "-np" setting, and control the number of MPI tasks per
+node via a "-ppn" setting.
+
+------------------------------------------------------------------------
+
+If the script has "titan" in its name, it was run on the Titan
+supercomputer at ORNL.

bench/FERMI/in.eam.titan

@@ -0,0 +1,37 @@
+# bulk Cu lattice
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	yy equal 20*$y
+variable	zz equal 20*$z
+
+units		metal
+atom_style	atomic
+
+lattice		fcc 3.615
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+create_box	1 box
+create_atoms	1 box
+
+pair_style	eam/gpu
+pair_coeff	1 1 Cu_u3.eam
+
+velocity	all create 1600.0 376847 loop geom
+
+neighbor	1.0 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 all nve
+
+timestep	0.005
+thermo		50
+
+run             15
+run		100

bench/FERMI/in.lj.titan

@@ -0,0 +1,35 @@
+# 3d Lennard-Jones melt
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	yy equal 20*$y
+variable	zz equal 20*$z
+
+units		lj
+atom_style	atomic
+
+lattice		fcc 0.8442
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+create_box	1 box
+create_atoms	1 box
+mass		1 1.0
+
+velocity	all create 1.44 87287 loop geom
+
+pair_style	lj/cut/gpu 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             15
+run		100

bench/FERMI/in.rhodo.scaled.titan

@@ -0,0 +1,39 @@
+# Rhodopsin model
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+units           real  
+neigh_modify    delay 5 every 1   
+
+atom_style      full  
+atom_modify	map hash
+bond_style      harmonic 
+angle_style     charmm 
+dihedral_style  charmm 
+improper_style  harmonic 
+pair_style      lj/charmm/coul/long/gpu 8.0 ${cutoff}
+pair_modify     mix arithmetic 
+kspace_style    pppm/gpu 1e-4 
+
+read_data       data.rhodo
+
+replicate	$x $y $z
+
+fix             1 all shake 0.0001 5 0 m 1.0 a 232
+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
+ 
+thermo          50
+# thermo_style    multi 
+timestep        2.0
+
+run             15
+run		100

bench/FERMI/in.rhodo.split.titan

@@ -0,0 +1,42 @@
+# Rhodopsin model
+
+newton          off
+package         gpu force/neigh 0 0 1
+partition	yes 1 processors * * * grid twolevel ${grid} * * * &
+		part 1 2 multiple
+partition	yes 2 processors * * * part 1 2 multiple
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+units           real  
+neigh_modify    delay 5 every 1   
+
+atom_style      full  
+atom_modify	map hash
+bond_style      harmonic 
+angle_style     charmm 
+dihedral_style  charmm 
+improper_style  harmonic 
+pair_style      lj/charmm/coul/long/gpu 8.0 ${cutoff}
+pair_modify     mix arithmetic 
+kspace_style    pppm/gpu 1e-4 
+
+read_data       data.rhodo
+
+replicate	$x $y $z
+
+fix             1 all shake 0.0001 5 0 m 1.0 a 232
+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
+ 
+thermo          50
+# thermo_style    multi 
+timestep        2.0
+
+run_style       verlet/split
+run             15
+run		100

bench/GPU/README

@@ -1,60 +0,0 @@
-These are input scripts used to run GPU versions of several of the
-benchmarks in the top-level bench directory.  The results of running
-these scripts on different machines are shown on the GPU section of
-the Benchmark page of the LAMMPS WWW site (lammps.sandia.gov/bench).
-
-Examples are shown below of how to run these scripts.  This assumes
-you have built 3 executables with both the GPU and USER-CUDA packages
-installed, e.g.
-
-lmp_linux_single
-lmp_linux_mixed
-lmp_linux_double
-
-The precision (single, mixed, double) refers to the GPU and USER-CUDA
-pacakge precision.  See the README files in the lib/gpu and lib/cuda
-directories for instructions on how to build the packages with
-different precisions.  The doc/Section_accelerate.html file also has a
-summary description.
-
-------------------------------------------------------------------------
-
-If the script has "cpu" in its name, it is meant to be run in CPU-only
-mode.  For example:
-
-mpirun -np 1 ../lmp_linux_double -c off -v x 8 -v y 8 -v z 8 -v t 100 < in.lj.cpu
-mpirun -np 12 ../lmp_linux_double -c off -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cpu
-
-The "xyz" settings determine the problem size.  The "t" setting
-determines the number of timesteps.
-
-------------------------------------------------------------------------
-
-If the script has "gpu" in its name, it is meant to be run using
-the GPU package.  For example:
-
-mpirun -np 12 ../lmp_linux_single -sf gpu -c off -v g 1 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj.gpu
-
-mpirun -np 8 ../lmp_linux_mixed -sf gpu -c off -v g 2 -v x 32 -v y 32 -v z 64 -v t 100 < in.lj.gpu
-
-The "xyz" settings determine the problem size.  The "t" setting
-determines the number of timesteps.  The "np" setting determines how
-many CPUs the problem will be run on, and the "g" settings determines
-how many GPUs the problem will run on, i.e. 1 or 2 in this case.  You
-can use more CPUs than GPUs with the GPU package.
-
-------------------------------------------------------------------------
-
-If the script has "cuda" in its name, it is meant to be run using
-the USER-CUDA package.  For example:
-
-mpirun -np 1 ../lmp_linux_single -sf cuda -v g 1 -v x 16 -v y 16 -v z 16 -v t 100 < in.lj.cuda
-
-mpirun -np 2 ../lmp_linux_double -sf cuda -v g 2 -v x 32 -v y 64 -v z 64 -v t 100 < in.eam.cuda
-
-The "xyz" settings determine the problem size.  The "t" setting
-determines the number of timesteps.  The "np" setting determines how
-many CPUs the problem will be run on, and the "g" setting determines
-how many GPUs the problem will run on, i.e. 1 or 2 in this case.  You
-should make the number of CPUs and number of GPUs equal for the
-USER-CUDA package.

bench/GPU/in.eam.cuda

@@ -1,29 +0,0 @@
-# bulk Cu lattice
-
-# set variable g = 1/2 for 1/2 GPUs
-
-if "$g == 1" then "package cuda gpu/node 1"
-if "$g == 2" then "package cuda gpu/node 2"
-
-units		metal
-atom_style	atomic
-
-lattice		fcc 3.615
-region		box block 0 $x 0 $y 0 $z
-create_box	1 box
-create_atoms	1 box
-
-pair_style	eam
-pair_coeff	1 1 Cu_u3.eam
-
-velocity	all create 1600.0 376847 loop geom
-
-neighbor	1.0 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 all nve
-
-timestep	0.005
-thermo		50
-
-run		$t

bench/GPU/in.eam.gpu

@@ -1,31 +0,0 @@
-# bulk Cu lattice
-
-# newton off is required for GPU package
-# set variable g = 1/2 for 1/2 GPUs
-
-newton          off
-if "$g == 1" then "package gpu force/neigh 0 0 1"
-if "$g == 2" then "package gpu force/neigh 0 1 1"
-
-units		metal
-atom_style	atomic
-
-lattice		fcc 3.615
-region		box block 0 $x 0 $y 0 $z
-create_box	1 box
-create_atoms	1 box
-
-pair_style	eam
-pair_coeff	1 1 Cu_u3.eam
-
-velocity	all create 1600.0 376847 loop geom
-
-neighbor	1.0 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 all nve
-
-timestep	0.005
-thermo		50
-
-run		$t

bench/GPU/in.lj.cuda

@@ -1,27 +0,0 @@
-# 3d Lennard-Jones melt
-
-# set variable g = 1/2 for 1/2 GPUs
-
-if "$g == 1" then "package cuda gpu/node 1"
-if "$g == 2" then "package cuda gpu/node 2"
-
-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/GPU/in.lj.gpu

@@ -1,29 +0,0 @@
-# 3d Lennard-Jones melt
-
-# newton off is required for GPU package
-# set variable g = 1/2 for 1/2 GPUs
-
-newton          off
-if "$g == 1" then "package gpu force/neigh 0 0 1"
-if "$g == 2" then "package gpu force/neigh 0 1 1"
-
-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/GPU/in.rhodo.cuda

@@ -1,35 +0,0 @@
-# Rhodopsin model
-
-# set variable g = 1/2 for 1/2 GPUs
-
-if "$g == 1" then "package cuda gpu/node 1"
-if "$g == 2" then "package cuda gpu/node 2"
-
-units           real  
-neigh_modify    delay 5 every 1   
-
-atom_style      full  
-#atom_modify	map hash
-bond_style      harmonic 
-angle_style     charmm 
-dihedral_style  charmm 
-improper_style  harmonic 
-pair_style      lj/charmm/coul/long 8.0 10.0 
-pair_modify     mix arithmetic 
-kspace_style    pppm 1e-4 
-
-read_data       data.rhodo
-
-replicate	$x $y $z
-
-fix             1 all shake 0.0001 5 0 m 1.0 a 232
-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
- 
-thermo          50
-thermo_style    multi 
-timestep        2.0
-
-run		$t

bench/GPU/in.rhodo.gpu

@@ -1,37 +0,0 @@
-# Rhodopsin model
-
-# newton off is required for GPU package
-# set variable g = 1/2 for 1/2 GPUs
-
-newton          off
-if "$g == 1" then "package gpu force/neigh 0 0 1"
-if "$g == 2" then "package gpu force/neigh 0 1 1"
-
-units           real  
-neigh_modify    delay 5 every 1   
-
-atom_style      full  
-atom_modify	map hash
-bond_style      harmonic 
-angle_style     charmm 
-dihedral_style  charmm 
-improper_style  harmonic 
-pair_style      lj/charmm/coul/long 8.0 10.0 
-pair_modify     mix arithmetic 
-kspace_style    pppm 1e-4 
-
-read_data       data.rhodo
-
-replicate	$x $y $z
-
-fix             1 all shake 0.0001 5 0 m 1.0 a 232
-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
- 
-thermo          50
-thermo_style    multi 
-timestep        2.0
-
-run		$t

bench/KEPLER/Makefile.cpu

@@ -0,0 +1,108 @@
+# 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

@@ -0,0 +1,108 @@
+# 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

@@ -0,0 +1,108 @@
+# 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

@@ -0,0 +1,50 @@
+# /* ----------------------------------------------------------------------   
+#  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

@@ -0,0 +1,50 @@
+# /* ----------------------------------------------------------------------   
+#  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

@@ -0,0 +1,50 @@
+# /* ----------------------------------------------------------------------   
+#  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

@@ -0,0 +1,109 @@
+# 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

@@ -0,0 +1,113 @@
+# 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

@@ -0,0 +1,110 @@
+# 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

@@ -0,0 +1,108 @@
+# 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

@@ -0,0 +1,108 @@
+# 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

@@ -0,0 +1,68 @@
+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

@@ -0,0 +1,187 @@
+#!/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

@@ -0,0 +1,22 @@
+# 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

@@ -0,0 +1,29 @@
+#!/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

@@ -0,0 +1,20 @@
+#!/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

@@ -0,0 +1,155 @@
+#!/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

@@ -0,0 +1,83 @@
+#!/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

@@ -0,0 +1,74 @@
+#!/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

@@ -0,0 +1,17 @@
+#!/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

@@ -0,0 +1,17 @@
+#!/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

@@ -0,0 +1,29 @@
+#!/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

@@ -0,0 +1,20 @@
+#!/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

@@ -0,0 +1,20 @@
+#!/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/in.dpd

@@ -2,7 +2,7 @@
 
 units		lj
 atom_style	atomic
-communicate	single vel yes
+comm_modify     mode single vel yes
 
 lattice		fcc 3.0
 region		box block 0 20 0 20 0 20

bench/README

@@ -4,19 +4,19 @@ This directory contains 5 benchmark problems which are discussed in
 the Benchmark section of the LAMMPS documentation, and on the
 Benchmark page of the LAMMPS WWW site (lammps.sandia.gov/bench).
 
-This directory also has 2 sub-directories:
+This directory also has several sub-directories:
 
-GPU                 GPU versions of 3 of these benchmarks
-POTENTIALS          benchmarks scripts for various potentials in LAMMPS
+FERMI           benchmark scripts for desktop machine with Fermi GPUs (Tesla)
+KEPLER          benchmark scripts for GPU cluster with Kepler GPUs
+POTENTIALS      benchmarks scripts for various potentials in LAMMPS
 
-The scripts and results in both of these directories are discussed on
-the Benchmark page of the LAMMPS WWW site (lammps.sandia.gov/bench) as
-well.  The two directories have their own README files which you
-should refer to before running the scripts.
+The results for all of these benchmarks are displayed and discussed on
+the Benchmark page of the LAMMPS WWW site: lammps.sandia.gov/bench.
 
-The remainer of this file refers to the 5 problems in the top-level
-of this directory and how to run them on CPUs, either in serial
-or parallel.
+The remainder of this file refers to the 5 problems in the top-level
+of this directory and how to run them on CPUs, either in serial or
+parallel.  The sub-directories have their own README files which you
+should refer to before running those scripts.
 
 ----------------------------------------------------------------------
 
@@ -71,33 +71,49 @@ integration
 
 ----------------------------------------------------------------------
 
+Here is a src/Make.py command which will perform a parallel build of a
+LAMMPS executable "lmp_mpi" with all the packages needed by all the
+examples.  This assumes you have an MPI installed on your machine so
+that "mpicxx" can be used as the wrapper compiler.  It also assumes
+you have an Intel compiler to use as the base compiler.  You can leave
+off the "-cc mpi wrap=icc" switch if that is not the case.  You can
+also leave off the "-fft fftw3" switch if you do not have the FFTW
+(v3) installed as an FFT package, in which case the default KISS FFT
+library will be used.
+
+cd src
+Make.py -j 16 -p none molecule manybody kspace granular rigid orig \
+  -cc mpi wrap=icc -fft fftw3 -a file mpi
+
+----------------------------------------------------------------------
+
 Here is how to run each problem, assuming the LAMMPS executable is
-named lmp_foo, and you are using the mpirun command to launch parallel
+named lmp_mpi, and you are using the mpirun command to launch parallel
 runs:
 
 Serial (one processor runs):
 
-lmp_foo < in.lj
-lmp_foo < in.chain
-lmp_foo < in.eam
-lmp_foo < in.chute
-lmp_foo < in.rhodo
+lmp_mpi < in.lj
+lmp_mpi < in.chain
+lmp_mpi < in.eam
+lmp_mpi < in.chute
+lmp_mpi < in.rhodo
 
 Parallel fixed-size runs (on 8 procs in this case):
 
-mpirun -np 8 lmp_foo < in.lj
-mpirun -np 8 lmp_foo < in.chain
-mpirun -np 8 lmp_foo < in.eam
-mpirun -np 8 lmp_foo < in.chute
-mpirun -np 8 lmp_foo < in.rhodo
+mpirun -np 8 lmp_mpi < in.lj
+mpirun -np 8 lmp_mpi < in.chain
+mpirun -np 8 lmp_mpi < in.eam
+mpirun -np 8 lmp_mpi < in.chute
+mpirun -np 8 lmp_mpi < in.rhodo
 
 Parallel scaled-size runs (on 16 procs in this case):
 
-mpirun -np 16 lmp_foo -var x 2 -var y 2 -var z 4 < in.lj
-mpirun -np 16 lmp_foo -var x 2 -var y 2 -var z 4 < in.chain.scaled
-mpirun -np 16 lmp_foo -var x 2 -var y 2 -var z 4 < in.eam
-mpirun -np 16 lmp_foo -var x 4 -var y 4 < in.chute.scaled
-mpirun -np 16 lmp_foo -var x 2 -var y 2 -var z 4 < in.rhodo.scaled
+mpirun -np 16 lmp_mpi -var x 2 -var y 2 -var z 4 < in.lj
+mpirun -np 16 lmp_mpi -var x 2 -var y 2 -var z 4 < in.chain.scaled
+mpirun -np 16 lmp_mpi -var x 2 -var y 2 -var z 4 < in.eam
+mpirun -np 16 lmp_mpi -var x 4 -var y 4 < in.chute.scaled
+mpirun -np 16 lmp_mpi -var x 2 -var y 2 -var z 4 < in.rhodo.scaled
 
 For each of the scaled-size runs you must set 3 variables as -var
 command line switches.  The variables x,y,z are used in the input

bench/in.chute

@@ -5,7 +5,7 @@ units		lj
 atom_style	sphere
 boundary	p p fs
 newton		off
-communicate	single vel yes
+comm_modify	vel yes
 
 read_data	data.chute
 

bench/in.chute.scaled

@@ -8,7 +8,7 @@ units		lj
 atom_style	sphere
 boundary	p p fs
 newton		off
-communicate	single vel yes
+comm_modify	vel yes
 
 read_data	data.chute
 

bench/log.1Feb14.chain.fixed.linux.1

@@ -1,63 +0,0 @@
-LAMMPS (1 Feb 2014)
-# FENE beadspring benchmark
-
-units		lj
-atom_style	bond
-special_bonds   fene
-
-read_data	data.chain
-  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  1 = max bonds/atom
-  reading bonds ...
-  31680 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-neighbor	0.4 bin
-neigh_modify	every 1 delay 1
-
-bond_style      fene
-bond_coeff	1 30.0 1.5 1.0 1.0
-
-pair_style	lj/cut 1.12
-pair_modify	shift yes
-pair_coeff	1 1 1.0 1.0 1.12
-
-fix		1 all nve
-fix		2 all langevin 1.0 1.0 10.0 904297
-
-thermo          100
-timestep	0.012
-
-run		100
-Memory usage per processor = 11.5156 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 1.00129 on 1 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 0.201344 (20.1083)
-Bond  time (%) = 0.0870376 (8.69251)
-Neigh time (%) = 0.45714 (45.6549)
-Comm  time (%) = 0.0338521 (3.38083)
-Outpt time (%) = 0.000102043 (0.0101911)
-Other time (%) = 0.221819 (22.1532)
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    9493 ave 9493 max 9493 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    155873 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
-Neighbor list builds = 25
-Dangerous builds = 0

bench/log.1Feb14.chain.fixed.linux.4

@@ -1,63 +0,0 @@
-LAMMPS (1 Feb 2014)
-# FENE beadspring benchmark
-
-units		lj
-atom_style	bond
-special_bonds   fene
-
-read_data	data.chain
-  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
-  1 by 2 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  1 = max bonds/atom
-  reading bonds ...
-  31680 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-neighbor	0.4 bin
-neigh_modify	every 1 delay 1
-
-bond_style      fene
-bond_coeff	1 30.0 1.5 1.0 1.0
-
-pair_style	lj/cut 1.12
-pair_modify	shift yes
-pair_coeff	1 1 1.0 1.0 1.12
-
-fix		1 all nve
-fix		2 all langevin 1.0 1.0 10.0 904297
-
-thermo          100
-timestep	0.012
-
-run		100
-Memory usage per processor = 4.85536 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0   0.97029772   0.44484087    20.494523    22.394765    4.6721833 
-     100   0.97145835   0.43803883    20.502691    22.397872     4.626988 
-Loop time of 0.274804 on 4 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 0.0507675 (18.4741)
-Bond  time (%) = 0.0225385 (8.20169)
-Neigh time (%) = 0.121537 (44.2269)
-Comm  time (%) = 0.0207262 (7.54219)
-Outpt time (%) = 8.74996e-05 (0.0318408)
-Other time (%) = 0.0591468 (21.5233)
-
-Nlocal:    8000 ave 8030 max 7974 min
-Histogram: 1 0 0 1 0 1 0 0 0 1
-Nghost:    4177 ave 4191 max 4160 min
-Histogram: 1 0 0 0 1 0 0 1 0 1
-Neighs:    38995.8 ave 39169 max 38852 min
-Histogram: 1 0 0 1 1 0 0 0 0 1
-
-Total # of neighbors = 155983
-Ave neighs/atom = 4.87447
-Ave special neighs/atom = 1.98
-Neighbor list builds = 25
-Dangerous builds = 0

bench/log.1Feb14.chain.scaled.linux.4

@@ -1,79 +0,0 @@
-LAMMPS (1 Feb 2014)
-# FENE beadspring benchmark
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-units		lj
-atom_style	bond
-atom_modify	map hash
-special_bonds   fene
-
-read_data	data.chain
-  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
-  1 by 2 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  1 = max bonds/atom
-  reading bonds ...
-  31680 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-replicate	$x $y $z
-replicate	2 $y $z
-replicate	2 2 $z
-replicate	2 2 1
-  orthogonal box = (-16.796 -16.796 -16.796) to (50.388 50.388 16.796)
-  2 by 2 by 1 MPI processor grid
-  128000 atoms
-  126720 bonds
-  2 = max # of 1-2 neighbors
-  2 = max # of special neighbors
-
-neighbor	0.4 bin
-neigh_modify	every 1 delay 1
-
-bond_style      fene
-bond_coeff	1 30.0 1.5 1.0 1.0
-
-pair_style	lj/cut 1.12
-pair_modify	shift yes
-pair_coeff	1 1 1.0 1.0 1.12
-
-fix		1 all nve
-fix		2 all langevin 1.0 1.0 10.0 904297
-
-thermo          100
-timestep	0.012
-
-run		100
-Memory usage per processor = 13.4806 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0   0.97027498   0.44484087    20.494523    22.394765    4.6721833 
-     100   0.97682955   0.44239968    20.500229    22.407862    4.6527025 
-Loop time of 1.16627 on 4 procs for 100 steps with 128000 atoms
-
-Pair  time (%) = 0.224354 (19.2369)
-Bond  time (%) = 0.0961447 (8.24378)
-Neigh time (%) = 0.510646 (43.7846)
-Comm  time (%) = 0.0876382 (7.5144)
-Outpt time (%) = 0.000156462 (0.0134156)
-Other time (%) = 0.24733 (21.207)
-
-Nlocal:    32000 ave 32015 max 31983 min
-Histogram: 1 0 1 0 0 0 0 0 1 1
-Nghost:    9492 ave 9522 max 9432 min
-Histogram: 1 0 0 0 0 0 1 0 0 2
-Neighs:    155837 ave 156079 max 155506 min
-Histogram: 1 0 0 0 0 1 0 0 1 1
-
-Total # of neighbors = 623349
-Ave neighs/atom = 4.86991
-Ave special neighs/atom = 1.98
-Neighbor list builds = 25
-Dangerous builds = 0

bench/log.1Feb14.chute.fixed.linux.1

@@ -1,65 +0,0 @@
-LAMMPS (1 Feb 2014)
-# LAMMPS benchmark of granular flow
-# chute flow of 32000 atoms with frozen base at 26 degrees
-
-units		lj
-atom_style	sphere
-boundary	p p fs
-newton		off
-communicate	single vel yes
-
-read_data	data.chute
-  orthogonal box = (0 0 0) to (40 20 37.2886)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-
-pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
-pair_coeff	* *
-
-neighbor	0.1 bin
-neigh_modify	every 1 delay 0
-
-timestep	0.0001
-
-group		bottom type 2
-912 atoms in group bottom
-group		active subtract all bottom
-31088 atoms in group active
-neigh_modify	exclude group bottom bottom
-
-fix		1 all gravity 1.0 chute 26.0
-fix		2 bottom freeze
-fix		3 active nve/sphere
-
-compute		1 all erotate/sphere
-thermo_style	custom step atoms ke c_1 vol
-thermo_modify	norm no
-thermo		100
-
-run		100
-Memory usage per processor = 21.4184 Mbytes
-Step Atoms KinEng 1 Volume 
-       0    32000    784139.13    1601.1263    29833.783 
-     100    32000    784292.08    1571.0968    29834.707 
-Loop time of 0.540977 on 1 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 0.330571 (61.1064)
-Neigh time (%) = 0.0416589 (7.70067)
-Comm  time (%) = 0.018239 (3.3715)
-Outpt time (%) = 0.000189066 (0.034949)
-Other time (%) = 0.150319 (27.7865)
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    5463 ave 5463 max 5463 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    115133 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
-Neighbor list builds = 2
-Dangerous builds = 0

bench/log.1Feb14.chute.fixed.linux.4

@@ -1,65 +0,0 @@
-LAMMPS (1 Feb 2014)
-# LAMMPS benchmark of granular flow
-# chute flow of 32000 atoms with frozen base at 26 degrees
-
-units		lj
-atom_style	sphere
-boundary	p p fs
-newton		off
-communicate	single vel yes
-
-read_data	data.chute
-  orthogonal box = (0 0 0) to (40 20 37.2886)
-  2 by 1 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-
-pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
-pair_coeff	* *
-
-neighbor	0.1 bin
-neigh_modify	every 1 delay 0
-
-timestep	0.0001
-
-group		bottom type 2
-912 atoms in group bottom
-group		active subtract all bottom
-31088 atoms in group active
-neigh_modify	exclude group bottom bottom
-
-fix		1 all gravity 1.0 chute 26.0
-fix		2 bottom freeze
-fix		3 active nve/sphere
-
-compute		1 all erotate/sphere
-thermo_style	custom step atoms ke c_1 vol
-thermo_modify	norm no
-thermo		100
-
-run		100
-Memory usage per processor = 10.7034 Mbytes
-Step Atoms KinEng 1 Volume 
-       0    32000    784139.13    1601.1263    29833.783 
-     100    32000    784292.08    1571.0968    29834.707 
-Loop time of 0.133553 on 4 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 0.0669281 (50.1135)
-Neigh time (%) = 0.01061 (7.9444)
-Comm  time (%) = 0.0142241 (10.6505)
-Outpt time (%) = 9.28044e-05 (0.0694888)
-Other time (%) = 0.041698 (31.2221)
-
-Nlocal:    8000 ave 8008 max 7992 min
-Histogram: 2 0 0 0 0 0 0 0 0 2
-Nghost:    2439 ave 2450 max 2428 min
-Histogram: 2 0 0 0 0 0 0 0 0 2
-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
-Neighbor list builds = 2
-Dangerous builds = 0

bench/log.1Feb14.chute.scaled.linux.4

@@ -1,75 +0,0 @@
-LAMMPS (1 Feb 2014)
-# LAMMPS benchmark of granular flow
-# chute flow of 32000 atoms with frozen base at 26 degrees
-
-variable	x index 1
-variable	y index 1
-
-units		lj
-atom_style	sphere
-boundary	p p fs
-newton		off
-communicate	single vel yes
-
-read_data	data.chute
-  orthogonal box = (0 0 0) to (40 20 37.2886)
-  2 by 1 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-
-replicate	$x $y 1
-replicate	2 $y 1
-replicate	2 2 1
-  orthogonal box = (0 0 0) to (80 40 37.2923)
-  2 by 2 by 1 MPI processor grid
-  128000 atoms
-
-pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
-pair_coeff	* *
-
-neighbor	0.1 bin
-neigh_modify	every 1 delay 0
-
-timestep	0.0001
-
-group		bottom type 2
-3648 atoms in group bottom
-group		active subtract all bottom
-124352 atoms in group active
-neigh_modify	exclude group bottom bottom
-
-fix		1 all gravity 1.0 chute 26.0
-fix		2 bottom freeze
-fix		3 active nve/sphere
-
-compute		1 all erotate/sphere
-thermo_style	custom step atoms ke c_1 vol
-thermo_modify	norm no
-thermo		100
-
-run		100
-Memory usage per processor = 22.3334 Mbytes
-Step Atoms KinEng 1 Volume 
-       0   128000    3136556.5    6404.5051    119335.13 
-     100   128000    3137168.3    6284.3873    119338.83 
-Loop time of 0.862817 on 4 procs for 100 steps with 128000 atoms
-
-Pair  time (%) = 0.518524 (60.0966)
-Neigh time (%) = 0.0441293 (5.11455)
-Comm  time (%) = 0.057479 (6.66178)
-Outpt time (%) = 0.000286222 (0.0331729)
-Other time (%) = 0.242399 (28.0939)
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Nghost:    5463 ave 5463 max 5463 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Neighs:    115133 ave 115133 max 115133 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 460532
-Ave neighs/atom = 3.59791
-Neighbor list builds = 2
-Dangerous builds = 0

bench/log.1Feb14.eam.fixed.linux.1

@@ -1,67 +0,0 @@
-LAMMPS (1 Feb 2014)
-# bulk Cu lattice
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*1
-variable	yy equal 20*$y
-variable	yy equal 20*1
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		metal
-atom_style	atomic
-
-lattice		fcc 3.615
-Lattice spacing in x,y,z = 3.615 3.615 3.615
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 20 0 ${yy} 0 ${zz}
-region		box block 0 20 0 20 0 ${zz}
-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)
-  1 by 1 by 1 MPI processor grid
-create_atoms	1 box
-Created 32000 atoms
-
-pair_style	eam
-pair_coeff	1 1 Cu_u3.eam
-
-velocity	all create 1600.0 376847 loop geom
-
-neighbor	1.0 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 all nve
-
-timestep	0.005
-thermo		50
-
-run		100
-Memory usage per processor = 15.3727 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1600      -113280            0   -106662.09    18703.573 
-      50    781.69049   -109873.35            0   -106640.13    52273.088 
-     100      801.832    -109957.3            0   -106640.77    51322.821 
-Loop time of 5.93175 on 1 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 5.20741 (87.7887)
-Neigh time (%) = 0.618579 (10.4283)
-Comm  time (%) = 0.0310862 (0.524064)
-Outpt time (%) = 0.000214815 (0.00362144)
-Other time (%) = 0.0744634 (1.25533)
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    19909 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
-Neighbor list builds = 13
-Dangerous builds = 0

bench/log.1Feb14.eam.fixed.linux.4

@@ -1,67 +0,0 @@
-LAMMPS (1 Feb 2014)
-# bulk Cu lattice
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*1
-variable	yy equal 20*$y
-variable	yy equal 20*1
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		metal
-atom_style	atomic
-
-lattice		fcc 3.615
-Lattice spacing in x,y,z = 3.615 3.615 3.615
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 20 0 ${yy} 0 ${zz}
-region		box block 0 20 0 20 0 ${zz}
-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)
-  1 by 2 by 2 MPI processor grid
-create_atoms	1 box
-Created 32000 atoms
-
-pair_style	eam
-pair_coeff	1 1 Cu_u3.eam
-
-velocity	all create 1600.0 376847 loop geom
-
-neighbor	1.0 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 all nve
-
-timestep	0.005
-thermo		50
-
-run		100
-Memory usage per processor = 4.92441 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1600      -113280            0   -106662.09    18703.573 
-      50    781.69049   -109873.35            0   -106640.13    52273.088 
-     100      801.832    -109957.3            0   -106640.77    51322.821 
-Loop time of 1.57335 on 4 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 1.35199 (85.9304)
-Neigh time (%) = 0.160176 (10.1806)
-Comm  time (%) = 0.0413526 (2.62832)
-Outpt time (%) = 0.000119448 (0.00759193)
-Other time (%) = 0.0197157 (1.2531)
-
-Nlocal:    8000 ave 8008 max 7993 min
-Histogram: 2 0 0 0 0 0 0 0 1 1
-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
-Histogram: 1 0 0 0 1 0 0 0 1 1
-
-Total # of neighbors = 1207784
-Ave neighs/atom = 37.7433
-Neighbor list builds = 13
-Dangerous builds = 0

bench/log.1Feb14.eam.scaled.linux.4

@@ -1,67 +0,0 @@
-LAMMPS (1 Feb 2014)
-# bulk Cu lattice
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*2
-variable	yy equal 20*$y
-variable	yy equal 20*2
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		metal
-atom_style	atomic
-
-lattice		fcc 3.615
-Lattice spacing in x,y,z = 3.615 3.615 3.615
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 40 0 ${yy} 0 ${zz}
-region		box block 0 40 0 40 0 ${zz}
-region		box block 0 40 0 40 0 20
-create_box	1 box
-Created orthogonal box = (0 0 0) to (144.6 144.6 72.3)
-  2 by 2 by 1 MPI processor grid
-create_atoms	1 box
-Created 128000 atoms
-
-pair_style	eam
-pair_coeff	1 1 Cu_u3.eam
-
-velocity	all create 1600.0 376847 loop geom
-
-neighbor	1.0 bin
-neigh_modify    every 1 delay 5 check yes
-
-fix		1 all nve
-
-timestep	0.005
-thermo		50
-
-run		100
-Memory usage per processor = 15.2891 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1600      -453120            0   -426647.73    18704.012 
-      50    779.50001   -439457.02            0   -426560.06    52355.276 
-     100    797.97828   -439764.76            0   -426562.07     51474.74 
-Loop time of 6.55459 on 4 procs for 100 steps with 128000 atoms
-
-Pair  time (%) = 5.63064 (85.9037)
-Neigh time (%) = 0.698691 (10.6596)
-Comm  time (%) = 0.123277 (1.88077)
-Outpt time (%) = 0.000314116 (0.00479231)
-Other time (%) = 0.101672 (1.55115)
-
-Nlocal:    32000 ave 32092 max 31914 min
-Histogram: 1 0 0 1 0 1 0 0 0 1
-Nghost:    19910 ave 19997 max 19818 min
-Histogram: 1 0 0 0 1 0 1 0 0 1
-Neighs:    1.20728e+06 ave 1.21142e+06 max 1.2036e+06 min
-Histogram: 1 0 0 1 1 0 0 0 0 1
-
-Total # of neighbors = 4829126
-Ave neighs/atom = 37.7275
-Neighbor list builds = 14
-Dangerous builds = 0

bench/log.1Feb14.lj.fixed.linux.1

@@ -1,64 +0,0 @@
-LAMMPS (1 Feb 2014)
-# 3d Lennard-Jones melt
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*1
-variable	yy equal 20*$y
-variable	yy equal 20*1
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		lj
-atom_style	atomic
-
-lattice		fcc 0.8442
-Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 20 0 ${yy} 0 ${zz}
-region		box block 0 20 0 20 0 ${zz}
-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)
-  1 by 1 by 1 MPI processor grid
-create_atoms	1 box
-Created 32000 atoms
-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		100
-Memory usage per processor = 13.2266 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
-     100    0.7574531   -5.7585055            0   -4.6223613   0.20726105 
-Loop time of 2.26599 on 1 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 1.92891 (85.1244)
-Neigh time (%) = 0.252641 (11.1493)
-Comm  time (%) = 0.0243704 (1.07549)
-Outpt time (%) = 0.000110865 (0.00489256)
-Other time (%) = 0.059957 (2.64596)
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    19657 ave 19657 max 19657 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Neighs:    1.20283e+06 ave 1.20283e+06 max 1.20283e+06 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-
-Total # of neighbors = 1202833
-Ave neighs/atom = 37.5885
-Neighbor list builds = 5
-Dangerous builds = 0

bench/log.1Feb14.lj.fixed.linux.4

@@ -1,64 +0,0 @@
-LAMMPS (1 Feb 2014)
-# 3d Lennard-Jones melt
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*1
-variable	yy equal 20*$y
-variable	yy equal 20*1
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		lj
-atom_style	atomic
-
-lattice		fcc 0.8442
-Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 20 0 ${yy} 0 ${zz}
-region		box block 0 20 0 20 0 ${zz}
-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)
-  1 by 2 by 2 MPI processor grid
-create_atoms	1 box
-Created 32000 atoms
-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		100
-Memory usage per processor = 4.31282 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
-     100    0.7574531   -5.7585055            0   -4.6223613   0.20726105 
-Loop time of 0.628341 on 4 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 0.505093 (80.3851)
-Neigh time (%) = 0.0659957 (10.5032)
-Comm  time (%) = 0.0406293 (6.46611)
-Outpt time (%) = 8.43406e-05 (0.0134227)
-Other time (%) = 0.016539 (2.63216)
-
-Nlocal:    8000 ave 8037 max 7964 min
-Histogram: 2 0 0 0 0 0 0 0 1 1
-Nghost:    9007.5 ave 9050 max 8968 min
-Histogram: 1 1 0 0 0 0 0 1 0 1
-Neighs:    300708 ave 305113 max 297203 min
-Histogram: 1 0 0 1 1 0 0 0 0 1
-
-Total # of neighbors = 1202833
-Ave neighs/atom = 37.5885
-Neighbor list builds = 5
-Dangerous builds = 0

bench/log.1Feb14.lj.scaled.linux.4

@@ -1,64 +0,0 @@
-LAMMPS (1 Feb 2014)
-# 3d Lennard-Jones melt
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-variable	xx equal 20*$x
-variable	xx equal 20*2
-variable	yy equal 20*$y
-variable	yy equal 20*2
-variable	zz equal 20*$z
-variable	zz equal 20*1
-
-units		lj
-atom_style	atomic
-
-lattice		fcc 0.8442
-Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
-region		box block 0 ${xx} 0 ${yy} 0 ${zz}
-region		box block 0 40 0 ${yy} 0 ${zz}
-region		box block 0 40 0 40 0 ${zz}
-region		box block 0 40 0 40 0 20
-create_box	1 box
-Created orthogonal box = (0 0 0) to (67.1838 67.1838 33.5919)
-  2 by 2 by 1 MPI processor grid
-create_atoms	1 box
-Created 128000 atoms
-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		100
-Memory usage per processor = 13.1495 Mbytes
-Step Temp E_pair E_mol TotEng Press 
-       0         1.44   -6.7733681            0   -4.6133849   -5.0196788 
-     100   0.75841891    -5.759957            0   -4.6223375   0.20008866 
-Loop time of 2.54147 on 4 procs for 100 steps with 128000 atoms
-
-Pair  time (%) = 2.08305 (81.9623)
-Neigh time (%) = 0.258072 (10.1545)
-Comm  time (%) = 0.116279 (4.57528)
-Outpt time (%) = 0.000139415 (0.00548562)
-Other time (%) = 0.0839326 (3.30252)
-
-Nlocal:    32000 ave 32060 max 31939 min
-Histogram: 1 0 1 0 0 0 0 1 0 1
-Nghost:    19630.8 ave 19681 max 19562 min
-Histogram: 1 0 0 0 1 0 0 0 1 1
-Neighs:    1.20195e+06 ave 1.20354e+06 max 1.19931e+06 min
-Histogram: 1 0 0 0 0 0 0 2 0 1
-
-Total # of neighbors = 4807797
-Ave neighs/atom = 37.5609
-Neighbor list builds = 5
-Dangerous builds = 0

bench/log.1Feb14.rhodo.fixed.linux.1

@@ -1,109 +0,0 @@
-LAMMPS (1 Feb 2014)
-# Rhodopsin model
-
-units           real
-neigh_modify    delay 5 every 1
-
-atom_style      full
-bond_style      harmonic
-angle_style     charmm
-dihedral_style  charmm
-improper_style  harmonic
-pair_style      lj/charmm/coul/long 8.0 10.0
-pair_modify     mix arithmetic
-kspace_style    pppm 1e-4
-
-read_data       data.rhodo
-  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
-  1 by 1 by 1 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  4 = max bonds/atom
-  scanning angles ...
-  8 = max angles/atom
-  scanning dihedrals ...
-  18 = max dihedrals/atom
-  scanning impropers ...
-  2 = max impropers/atom
-  reading bonds ...
-  27723 bonds
-  reading angles ...
-  40467 angles
-  reading dihedrals ...
-  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
-
-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
-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
-
-thermo          50
-thermo_style    multi
-timestep        2.0
-
-run		100
-PPPM initialization ...
-  G vector (1/distance) = 0.248835
-  grid = 25 32 32
-  stencil order = 5
-  estimated absolute RMS force accuracy = 0.0355478
-  estimated relative force accuracy = 0.000107051
-  using double precision FFTs
-  3d grid and FFT values/proc = 41070 25600
-Memory usage per processor = 139.238 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    =      -142.6035 
-Volume   =    307995.0335 
----------------- Step       50 ----- CPU =     17.8100 (sec) ----------------
-TotEng   =    -25330.0828 KinEng   =     21501.0029 Temp     =       299.8230 
-PotEng   =    -46831.0857 E_bond   =      2471.7004 E_angle  =     10836.4975 
-E_dihed  =      5239.6299 E_impro  =       227.1218 E_vdwl   =     -1993.2754 
-E_coul   =    206797.6331 E_long   =   -270410.3930 Press    =       237.6701 
-Volume   =    308031.5639 
----------------- Step      100 ----- CPU =     36.2348 (sec) ----------------
-TotEng   =    -25290.7592 KinEng   =     21592.0117 Temp     =       301.0920 
-PotEng   =    -46882.7709 E_bond   =      2567.9807 E_angle  =     10781.9408 
-E_dihed  =      5198.7432 E_impro  =       216.7834 E_vdwl   =     -1902.4783 
-E_coul   =    206659.2327 E_long   =   -270404.9733 Press    =         6.9960 
-Volume   =    308133.9888 
-Loop time of 36.2348 on 1 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 26.0418 (71.8696)
-Bond  time (%) = 1.26644 (3.4951)
-Kspce time (%) = 3.24933 (8.96742)
-Neigh time (%) = 4.47968 (12.3629)
-Comm  time (%) = 0.0700378 (0.193289)
-Outpt time (%) = 0.000230074 (0.000634953)
-Other time (%) = 1.12729 (3.11108)
-
-FFT time (% of Kspce) = 0.276809 (8.51896)
-FFT Gflps 3d (1d only) = 1.87746 3.23903
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 1 0 0 0 0 0 0 0 0 0
-Nghost:    47958 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 = 12028107
-Ave neighs/atom = 375.878
-Ave special neighs/atom = 7.43187
-Neighbor list builds = 11
-Dangerous builds = 0

bench/log.1Feb14.rhodo.fixed.linux.4

@@ -1,109 +0,0 @@
-LAMMPS (1 Feb 2014)
-# Rhodopsin model
-
-units           real
-neigh_modify    delay 5 every 1
-
-atom_style      full
-bond_style      harmonic
-angle_style     charmm
-dihedral_style  charmm
-improper_style  harmonic
-pair_style      lj/charmm/coul/long 8.0 10.0
-pair_modify     mix arithmetic
-kspace_style    pppm 1e-4
-
-read_data       data.rhodo
-  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
-  1 by 2 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  4 = max bonds/atom
-  scanning angles ...
-  8 = max angles/atom
-  scanning dihedrals ...
-  18 = max dihedrals/atom
-  scanning impropers ...
-  2 = max impropers/atom
-  reading bonds ...
-  27723 bonds
-  reading angles ...
-  40467 angles
-  reading dihedrals ...
-  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
-
-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
-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
-
-thermo          50
-thermo_style    multi
-timestep        2.0
-
-run		100
-PPPM initialization ...
-  G vector (1/distance) = 0.248835
-  grid = 25 32 32
-  stencil order = 5
-  estimated absolute RMS force accuracy = 0.0355478
-  estimated relative force accuracy = 0.000107051
-  using double precision FFTs
-  3d grid and FFT values/proc = 13230 6400
-Memory usage per processor = 54.595 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    =      -142.6035 
-Volume   =    307995.0335 
----------------- Step       50 ----- CPU =      4.7061 (sec) ----------------
-TotEng   =    -25330.0829 KinEng   =     21501.0029 Temp     =       299.8230 
-PotEng   =    -46831.0857 E_bond   =      2471.7004 E_angle  =     10836.4975 
-E_dihed  =      5239.6299 E_impro  =       227.1218 E_vdwl   =     -1993.2754 
-E_coul   =    206797.6331 E_long   =   -270410.3930 Press    =       237.6701 
-Volume   =    308031.5639 
----------------- Step      100 ----- CPU =      9.5889 (sec) ----------------
-TotEng   =    -25290.7592 KinEng   =     21592.0117 Temp     =       301.0920 
-PotEng   =    -46882.7709 E_bond   =      2567.9807 E_angle  =     10781.9408 
-E_dihed  =      5198.7432 E_impro  =       216.7834 E_vdwl   =     -1902.4783 
-E_coul   =    206659.2327 E_long   =   -270404.9733 Press    =         6.9960 
-Volume   =    308133.9888 
-Loop time of 9.58898 on 4 procs for 100 steps with 32000 atoms
-
-Pair  time (%) = 6.62576 (69.0976)
-Bond  time (%) = 0.317414 (3.31019)
-Kspce time (%) = 1.04771 (10.9262)
-Neigh time (%) = 1.15891 (12.0859)
-Comm  time (%) = 0.0844751 (0.88096)
-Outpt time (%) = 0.00015074 (0.00157201)
-Other time (%) = 0.354558 (3.69756)
-
-FFT time (% of Kspce) = 0.0967343 (9.23289)
-FFT Gflps 3d (1d only) = 5.37243 12.7459
-
-Nlocal:    8000 ave 8143 max 7933 min
-Histogram: 1 2 0 0 0 0 0 0 0 1
-Nghost:    22733.5 ave 22769 max 22693 min
-Histogram: 1 0 0 0 0 2 0 0 0 1
-Neighs:    3.00703e+06 ave 3.0975e+06 max 2.96493e+06 min
-Histogram: 1 2 0 0 0 0 0 0 0 1
-
-Total # of neighbors = 12028107
-Ave neighs/atom = 375.878
-Ave special neighs/atom = 7.43187
-Neighbor list builds = 11
-Dangerous builds = 0

bench/log.1Feb14.rhodo.scaled.linux.4

@@ -1,130 +0,0 @@
-LAMMPS (1 Feb 2014)
-# Rhodopsin model
-
-variable	x index 1
-variable	y index 1
-variable	z index 1
-
-units           real
-neigh_modify    delay 5 every 1
-
-atom_style      full
-atom_modify	map hash
-bond_style      harmonic
-angle_style     charmm
-dihedral_style  charmm
-improper_style  harmonic
-pair_style      lj/charmm/coul/long 8.0 10.0
-pair_modify     mix arithmetic
-kspace_style    pppm 1e-4
-
-read_data       data.rhodo
-  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
-  1 by 2 by 2 MPI processor grid
-  reading atoms ...
-  32000 atoms
-  reading velocities ...
-  32000 velocities
-  scanning bonds ...
-  4 = max bonds/atom
-  scanning angles ...
-  8 = max angles/atom
-  scanning dihedrals ...
-  18 = max dihedrals/atom
-  scanning impropers ...
-  2 = max impropers/atom
-  reading bonds ...
-  27723 bonds
-  reading angles ...
-  40467 angles
-  reading dihedrals ...
-  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
-
-replicate	$x $y $z
-replicate	2 $y $z
-replicate	2 2 $z
-replicate	2 2 1
-  orthogonal box = (-27.5 -38.5 -36.3646) to (82.5 115.5 36.3615)
-  2 by 2 by 1 MPI processor grid
-  128000 atoms
-  110892 bonds
-  161868 angles
-  227316 dihedrals
-  4136 impropers
-  4 = max # of 1-2 neighbors
-  12 = max # of 1-3 neighbors
-  24 = max # of 1-4 neighbors
-  26 = max # of special neighbors
-
-fix             1 all shake 0.0001 5 0 m 1.0 a 232
-  6468 = # of size 2 clusters
-  14532 = # of size 3 clusters
-  2988 = # of size 4 clusters
-  16932 = # of frozen angles
-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
-
-thermo          50
-thermo_style    multi
-timestep        2.0
-
-run		100
-PPPM initialization ...
-  G vector (1/distance) = 0.248593
-  grid = 48 60 36
-  stencil order = 5
-  estimated absolute RMS force accuracy = 0.0359793
-  estimated relative force accuracy = 0.00010835
-  using double precision FFTs
-  3d grid and FFT values/proc = 41615 25920
-Memory usage per processor = 146.358 Mbytes
----------------- Step        0 ----- CPU =      0.0000 (sec) ----------------
-TotEng   =   -101425.4887 KinEng   =     85779.3251 Temp     =       299.0304 
-PotEng   =   -187204.8138 E_bond   =     10151.9760 E_angle  =     43685.4968 
-E_dihed  =     20847.1460 E_impro  =       854.0463 E_vdwl   =     -9231.4537 
-E_coul   =    827053.5824 E_long   =  -1080565.6077 Press    =      -142.3092 
-Volume   =   1231980.1340 
----------------- Step       50 ----- CPU =     18.9852 (sec) ----------------
-TotEng   =   -101320.2676 KinEng   =     86003.4837 Temp     =       299.8118 
-PotEng   =   -187323.7514 E_bond   =      9887.1072 E_angle  =     43346.7922 
-E_dihed  =     20958.7032 E_impro  =       908.4715 E_vdwl   =     -7973.4457 
-E_coul   =    826141.3831 E_long   =  -1080592.7629 Press    =       238.0161 
-Volume   =   1232126.1855 
----------------- Step      100 ----- CPU =     38.9161 (sec) ----------------
-TotEng   =   -101158.1853 KinEng   =     86355.6148 Temp     =       301.0393 
-PotEng   =   -187513.8001 E_bond   =     10272.0693 E_angle  =     43128.6453 
-E_dihed  =     20793.9759 E_impro  =       867.0826 E_vdwl   =     -7586.7186 
-E_coul   =    825583.7120 E_long   =  -1080572.5667 Press    =        15.2151 
-Volume   =   1232535.8423 
-Loop time of 38.9162 on 4 procs for 100 steps with 128000 atoms
-
-Pair  time (%) = 27.1908 (69.8701)
-Bond  time (%) = 1.30758 (3.35999)
-Kspce time (%) = 3.99359 (10.262)
-Neigh time (%) = 4.65272 (11.9557)
-Comm  time (%) = 0.216829 (0.557168)
-Outpt time (%) = 0.000280738 (0.000721391)
-Other time (%) = 1.55441 (3.99426)
-
-FFT time (% of Kspce) = 0.448314 (11.2258)
-FFT Gflps 3d (1d only) = 5.34183 11.5795
-
-Nlocal:    32000 ave 32000 max 32000 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Nghost:    47957 ave 47957 max 47957 min
-Histogram: 4 0 0 0 0 0 0 0 0 0
-Neighs:    1.20281e+07 ave 1.20572e+07 max 1.1999e+07 min
-Histogram: 2 0 0 0 0 0 0 0 0 2
-
-Total # of neighbors = 48112472
-Ave neighs/atom = 375.879
-Ave special neighs/atom = 7.43187
-Neighbor list builds = 11
-Dangerous builds = 0

bench/log.6Oct16.chain.fixed.icc.1

@@ -0,0 +1,78 @@
+LAMMPS (6 Oct 2016)
+# FENE beadspring benchmark
+
+units		lj
+atom_style	bond
+special_bonds   fene
+
+read_data	data.chain
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  31680 bonds
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+
+neighbor	0.4 bin
+neigh_modify	every 1 delay 1
+
+bond_style      fene
+bond_coeff	1 30.0 1.5 1.0 1.0
+
+pair_style	lj/cut 1.12
+pair_modify	shift yes
+pair_coeff	1 1 1.0 1.0 1.12
+
+fix		1 all nve
+fix		2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep	0.012
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 1 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76 -> bins = 45 45 45
+Memory usage per processor = 12.0423 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 0.977647 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 106050.541 tau/day, 102.286 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.19421    | 0.19421    | 0.19421    |   0.0 | 19.86
+Bond    | 0.08741    | 0.08741    | 0.08741    |   0.0 |  8.94
+Neigh   | 0.45791    | 0.45791    | 0.45791    |   0.0 | 46.84
+Comm    | 0.032649   | 0.032649   | 0.032649   |   0.0 |  3.34
+Output  | 0.00012207 | 0.00012207 | 0.00012207 |   0.0 |  0.01
+Modify  | 0.18071    | 0.18071    | 0.18071    |   0.0 | 18.48
+Other   |            | 0.02464    |            |       |  2.52
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    9493 ave 9493 max 9493 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    155873 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
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:01

bench/log.6Oct16.chain.fixed.icc.4

@@ -0,0 +1,78 @@
+LAMMPS (6 Oct 2016)
+# FENE beadspring benchmark
+
+units		lj
+atom_style	bond
+special_bonds   fene
+
+read_data	data.chain
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  31680 bonds
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+
+neighbor	0.4 bin
+neigh_modify	every 1 delay 1
+
+bond_style      fene
+bond_coeff	1 30.0 1.5 1.0 1.0
+
+pair_style	lj/cut 1.12
+pair_modify	shift yes
+pair_coeff	1 1 1.0 1.0 1.12
+
+fix		1 all nve
+fix		2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep	0.012
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 1 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76 -> bins = 45 45 45
+Memory usage per processor = 4.14663 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0   0.97029772   0.44484087    20.494523    22.394765    4.6721833 
+     100   0.97145835   0.43803883    20.502691    22.397872     4.626988 
+Loop time of 0.269205 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 385133.446 tau/day, 371.464 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.049383   | 0.049756   | 0.049988   |   0.1 | 18.48
+Bond    | 0.022701   | 0.022813   | 0.022872   |   0.0 |  8.47
+Neigh   | 0.11982    | 0.12002    | 0.12018    |   0.0 | 44.58
+Comm    | 0.020274   | 0.021077   | 0.022348   |   0.5 |  7.83
+Output  | 5.3167e-05 | 5.6148e-05 | 6.3181e-05 |   0.1 |  0.02
+Modify  | 0.046276   | 0.046809   | 0.047016   |   0.1 | 17.39
+Other   |            | 0.008669   |            |       |  3.22
+
+Nlocal:    8000 ave 8030 max 7974 min
+Histogram: 1 0 0 1 0 1 0 0 0 1
+Nghost:    4177 ave 4191 max 4160 min
+Histogram: 1 0 0 0 1 0 0 1 0 1
+Neighs:    38995.8 ave 39169 max 38852 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 155983
+Ave neighs/atom = 4.87447
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.6Oct16.chain.scaled.icc.4

@@ -0,0 +1,94 @@
+LAMMPS (6 Oct 2016)
+# FENE beadspring benchmark
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+units		lj
+atom_style	bond
+atom_modify	map hash
+special_bonds   fene
+
+read_data	data.chain
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  reading bonds ...
+  31680 bonds
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+
+replicate	$x $y $z
+replicate	2 $y $z
+replicate	2 2 $z
+replicate	2 2 1
+  orthogonal box = (-16.796 -16.796 -16.796) to (50.388 50.388 16.796)
+  2 by 2 by 1 MPI processor grid
+  128000 atoms
+  126720 bonds
+  2 = max # of 1-2 neighbors
+  2 = max # of special neighbors
+
+neighbor	0.4 bin
+neigh_modify	every 1 delay 1
+
+bond_style      fene
+bond_coeff	1 30.0 1.5 1.0 1.0
+
+pair_style	lj/cut 1.12
+pair_modify	shift yes
+pair_coeff	1 1 1.0 1.0 1.12
+
+fix		1 all nve
+fix		2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep	0.012
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 1 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76 -> bins = 89 89 45
+Memory usage per processor = 13.2993 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0   0.97027498   0.44484087    20.494523    22.394765    4.6721833 
+     100   0.97682955   0.44239968    20.500229    22.407862    4.6527025 
+Loop time of 1.14845 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 90277.919 tau/day, 87.074 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.2203     | 0.22207    | 0.22386    |   0.3 | 19.34
+Bond    | 0.094861   | 0.095302   | 0.095988   |   0.1 |  8.30
+Neigh   | 0.52127    | 0.5216     | 0.52189    |   0.0 | 45.42
+Comm    | 0.079585   | 0.082159   | 0.084366   |   0.7 |  7.15
+Output  | 0.00013304 | 0.00015306 | 0.00018501 |   0.2 |  0.01
+Modify  | 0.18351    | 0.18419    | 0.1856     |   0.2 | 16.04
+Other   |            | 0.04298    |            |       |  3.74
+
+Nlocal:    32000 ave 32015 max 31983 min
+Histogram: 1 0 1 0 0 0 0 0 1 1
+Nghost:    9492 ave 9522 max 9432 min
+Histogram: 1 0 0 0 0 0 1 0 0 2
+Neighs:    155837 ave 156079 max 155506 min
+Histogram: 1 0 0 0 0 1 0 0 1 1
+
+Total # of neighbors = 623349
+Ave neighs/atom = 4.86991
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:01

bench/log.6Oct16.chute.fixed.icc.1

@@ -0,0 +1,80 @@
+LAMMPS (6 Oct 2016)
+# LAMMPS benchmark of granular flow
+# chute flow of 32000 atoms with frozen base at 26 degrees
+
+units		lj
+atom_style	sphere
+boundary	p p fs
+newton		off
+comm_modify	vel yes
+
+read_data	data.chute
+  orthogonal box = (0 0 0) to (40 20 37.2886)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+
+pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
+pair_coeff	* *
+
+neighbor	0.1 bin
+neigh_modify	every 1 delay 0
+
+timestep	0.0001
+
+group		bottom type 2
+912 atoms in group bottom
+group		active subtract all bottom
+31088 atoms in group active
+neigh_modify	exclude group bottom bottom
+
+fix		1 all gravity 1.0 chute 26.0
+fix		2 bottom freeze
+fix		3 active nve/sphere
+
+compute		1 all erotate/sphere
+thermo_style	custom step atoms ke c_1 vol
+thermo_modify	norm no
+thermo		100
+
+run		100
+Neighbor list info ...
+  2 neighbor list requests
+  update every 1 steps, delay 0 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.1
+  ghost atom cutoff = 1.1
+  binsize = 0.55 -> bins = 73 37 68
+Memory usage per processor = 16.0904 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 0.534174 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 1617.451 tau/day, 187.205 timesteps/s
+99.8% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.33346    | 0.33346    | 0.33346    |   0.0 | 62.43
+Neigh   | 0.043902   | 0.043902   | 0.043902   |   0.0 |  8.22
+Comm    | 0.018391   | 0.018391   | 0.018391   |   0.0 |  3.44
+Output  | 0.00022411 | 0.00022411 | 0.00022411 |   0.0 |  0.04
+Modify  | 0.11666    | 0.11666    | 0.11666    |   0.0 | 21.84
+Other   |            | 0.02153    |            |       |  4.03
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    5463 ave 5463 max 5463 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    115133 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
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.6Oct16.chute.fixed.icc.4

@@ -0,0 +1,80 @@
+LAMMPS (6 Oct 2016)
+# LAMMPS benchmark of granular flow
+# chute flow of 32000 atoms with frozen base at 26 degrees
+
+units		lj
+atom_style	sphere
+boundary	p p fs
+newton		off
+comm_modify	vel yes
+
+read_data	data.chute
+  orthogonal box = (0 0 0) to (40 20 37.2886)
+  2 by 1 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+
+pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
+pair_coeff	* *
+
+neighbor	0.1 bin
+neigh_modify	every 1 delay 0
+
+timestep	0.0001
+
+group		bottom type 2
+912 atoms in group bottom
+group		active subtract all bottom
+31088 atoms in group active
+neigh_modify	exclude group bottom bottom
+
+fix		1 all gravity 1.0 chute 26.0
+fix		2 bottom freeze
+fix		3 active nve/sphere
+
+compute		1 all erotate/sphere
+thermo_style	custom step atoms ke c_1 vol
+thermo_modify	norm no
+thermo		100
+
+run		100
+Neighbor list info ...
+  2 neighbor list requests
+  update every 1 steps, delay 0 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.1
+  ghost atom cutoff = 1.1
+  binsize = 0.55 -> bins = 73 37 68
+Memory usage per processor = 7.04927 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 0.171815 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 5028.653 tau/day, 582.020 timesteps/s
+99.7% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.093691   | 0.096898   | 0.10005    |   0.8 | 56.40
+Neigh   | 0.011976   | 0.012059   | 0.012146   |   0.1 |  7.02
+Comm    | 0.016384   | 0.017418   | 0.018465   |   0.8 | 10.14
+Output  | 7.7963e-05 | 0.00010747 | 0.00013304 |   0.2 |  0.06
+Modify  | 0.031744   | 0.031943   | 0.032167   |   0.1 | 18.59
+Other   |            | 0.01339    |            |       |  7.79
+
+Nlocal:    8000 ave 8008 max 7992 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+Nghost:    2439 ave 2450 max 2428 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+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
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.6Oct16.chute.scaled.icc.4

@@ -0,0 +1,90 @@
+LAMMPS (6 Oct 2016)
+# LAMMPS benchmark of granular flow
+# chute flow of 32000 atoms with frozen base at 26 degrees
+
+variable	x index 1
+variable	y index 1
+
+units		lj
+atom_style	sphere
+boundary	p p fs
+newton		off
+comm_modify	vel yes
+
+read_data	data.chute
+  orthogonal box = (0 0 0) to (40 20 37.2886)
+  2 by 1 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+
+replicate	$x $y 1
+replicate	2 $y 1
+replicate	2 2 1
+  orthogonal box = (0 0 0) to (80 40 37.2922)
+  2 by 2 by 1 MPI processor grid
+  128000 atoms
+
+pair_style	gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
+pair_coeff	* *
+
+neighbor	0.1 bin
+neigh_modify	every 1 delay 0
+
+timestep	0.0001
+
+group		bottom type 2
+3648 atoms in group bottom
+group		active subtract all bottom
+124352 atoms in group active
+neigh_modify	exclude group bottom bottom
+
+fix		1 all gravity 1.0 chute 26.0
+fix		2 bottom freeze
+fix		3 active nve/sphere
+
+compute		1 all erotate/sphere
+thermo_style	custom step atoms ke c_1 vol
+thermo_modify	norm no
+thermo		100
+
+run		100
+Neighbor list info ...
+  2 neighbor list requests
+  update every 1 steps, delay 0 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.1
+  ghost atom cutoff = 1.1
+  binsize = 0.55 -> bins = 146 73 68
+Memory usage per processor = 16.1265 Mbytes
+Step Atoms KinEng c_1 Volume 
+       0   128000    3136556.5    6404.5051    119335.13 
+     100   128000    3137168.3    6284.3873    119338.83 
+Loop time of 0.832365 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 1038.006 tau/day, 120.140 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.5178     | 0.52208    | 0.52793    |   0.5 | 62.72
+Neigh   | 0.047003   | 0.047113   | 0.047224   |   0.0 |  5.66
+Comm    | 0.05233    | 0.052988   | 0.053722   |   0.2 |  6.37
+Output  | 0.00024986 | 0.00032717 | 0.00036693 |   0.3 |  0.04
+Modify  | 0.15517    | 0.15627    | 0.15808    |   0.3 | 18.77
+Other   |            | 0.0536     |            |       |  6.44
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Nghost:    5463 ave 5463 max 5463 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs:    115133 ave 115133 max 115133 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 460532
+Ave neighs/atom = 3.59791
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.6Oct16.eam.fixed.icc.1

@@ -0,0 +1,83 @@
+LAMMPS (6 Oct 2016)
+# bulk Cu lattice
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*1
+variable	yy equal 20*$y
+variable	yy equal 20*1
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		metal
+atom_style	atomic
+
+lattice		fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 20 0 ${yy} 0 ${zz}
+region		box block 0 20 0 20 0 ${zz}
+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)
+  1 by 1 by 1 MPI processor grid
+create_atoms	1 box
+Created 32000 atoms
+
+pair_style	eam
+pair_coeff	1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity	all create 1600.0 376847 loop geom
+
+neighbor	1.0 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 all nve
+
+timestep	0.005
+thermo		50
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 5.95
+  ghost atom cutoff = 5.95
+  binsize = 2.975 -> bins = 25 25 25
+Memory usage per processor = 11.2238 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1600      -113280            0   -106662.09    18703.573 
+      50    781.69049   -109873.35            0   -106640.13    52273.088 
+     100      801.832    -109957.3            0   -106640.77    51322.821 
+Loop time of 5.96529 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 7.242 ns/day, 3.314 hours/ns, 16.764 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 5.2743     | 5.2743     | 5.2743     |   0.0 | 88.42
+Neigh   | 0.59212    | 0.59212    | 0.59212    |   0.0 |  9.93
+Comm    | 0.030399   | 0.030399   | 0.030399   |   0.0 |  0.51
+Output  | 0.00026202 | 0.00026202 | 0.00026202 |   0.0 |  0.00
+Modify  | 0.050487   | 0.050487   | 0.050487   |   0.0 |  0.85
+Other   |            | 0.01776    |            |       |  0.30
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    19909 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
+Neighbor list builds = 13
+Dangerous builds = 0
+Total wall time: 0:00:06

bench/log.6Oct16.eam.fixed.icc.4

@@ -0,0 +1,83 @@
+LAMMPS (6 Oct 2016)
+# bulk Cu lattice
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*1
+variable	yy equal 20*$y
+variable	yy equal 20*1
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		metal
+atom_style	atomic
+
+lattice		fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 20 0 ${yy} 0 ${zz}
+region		box block 0 20 0 20 0 ${zz}
+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)
+  1 by 2 by 2 MPI processor grid
+create_atoms	1 box
+Created 32000 atoms
+
+pair_style	eam
+pair_coeff	1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity	all create 1600.0 376847 loop geom
+
+neighbor	1.0 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 all nve
+
+timestep	0.005
+thermo		50
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 5.95
+  ghost atom cutoff = 5.95
+  binsize = 2.975 -> bins = 25 25 25
+Memory usage per processor = 5.59629 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1600      -113280            0   -106662.09    18703.573 
+      50    781.69049   -109873.35            0   -106640.13    52273.088 
+     100      801.832    -109957.3            0   -106640.77    51322.821 
+Loop time of 1.64562 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 26.252 ns/day, 0.914 hours/ns, 60.767 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 1.408      | 1.4175     | 1.4341     |   0.9 | 86.14
+Neigh   | 0.15512    | 0.15722    | 0.16112    |   0.6 |  9.55
+Comm    | 0.029105   | 0.049986   | 0.061822   |   5.8 |  3.04
+Output  | 0.00010991 | 0.00011539 | 0.00012302 |   0.0 |  0.01
+Modify  | 0.013383   | 0.013573   | 0.013883   |   0.2 |  0.82
+Other   |            | 0.007264   |            |       |  0.44
+
+Nlocal:    8000 ave 8008 max 7993 min
+Histogram: 2 0 0 0 0 0 0 0 1 1
+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
+Histogram: 1 0 0 0 1 0 0 0 1 1
+
+Total # of neighbors = 1207784
+Ave neighs/atom = 37.7433
+Neighbor list builds = 13
+Dangerous builds = 0
+Total wall time: 0:00:01

bench/log.6Oct16.eam.scaled.icc.4

@@ -0,0 +1,83 @@
+LAMMPS (6 Oct 2016)
+# bulk Cu lattice
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*2
+variable	yy equal 20*$y
+variable	yy equal 20*2
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		metal
+atom_style	atomic
+
+lattice		fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 40 0 ${yy} 0 ${zz}
+region		box block 0 40 0 40 0 ${zz}
+region		box block 0 40 0 40 0 20
+create_box	1 box
+Created orthogonal box = (0 0 0) to (144.6 144.6 72.3)
+  2 by 2 by 1 MPI processor grid
+create_atoms	1 box
+Created 128000 atoms
+
+pair_style	eam
+pair_coeff	1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity	all create 1600.0 376847 loop geom
+
+neighbor	1.0 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 all nve
+
+timestep	0.005
+thermo		50
+
+run		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 5.95
+  ghost atom cutoff = 5.95
+  binsize = 2.975 -> bins = 49 49 25
+Memory usage per processor = 11.1402 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1600      -453120            0   -426647.73    18704.012 
+      50    779.50001   -439457.02            0   -426560.06    52355.276 
+     100    797.97828   -439764.76            0   -426562.07     51474.74 
+Loop time of 6.60121 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 6.544 ns/day, 3.667 hours/ns, 15.149 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 5.6676     | 5.7011     | 5.7469     |   1.3 | 86.36
+Neigh   | 0.66423    | 0.67119    | 0.68082    |   0.7 | 10.17
+Comm    | 0.079367   | 0.13668    | 0.1791     |  10.5 |  2.07
+Output  | 0.00026989 | 0.00028622 | 0.00031209 |   0.1 |  0.00
+Modify  | 0.060046   | 0.062203   | 0.065009   |   0.9 |  0.94
+Other   |            | 0.02974    |            |       |  0.45
+
+Nlocal:    32000 ave 32092 max 31914 min
+Histogram: 1 0 0 1 0 1 0 0 0 1
+Nghost:    19910 ave 19997 max 19818 min
+Histogram: 1 0 0 0 1 0 1 0 0 1
+Neighs:    1.20728e+06 ave 1.21142e+06 max 1.2036e+06 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 4829126
+Ave neighs/atom = 37.7275
+Neighbor list builds = 14
+Dangerous builds = 0
+Total wall time: 0:00:06

bench/log.6Oct16.lj.fixed.icc.1

@@ -0,0 +1,79 @@
+LAMMPS (6 Oct 2016)
+# 3d Lennard-Jones melt
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*1
+variable	yy equal 20*$y
+variable	yy equal 20*1
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		lj
+atom_style	atomic
+
+lattice		fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 20 0 ${yy} 0 ${zz}
+region		box block 0 20 0 20 0 ${zz}
+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)
+  1 by 1 by 1 MPI processor grid
+create_atoms	1 box
+Created 32000 atoms
+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		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 20 steps, delay 0 steps, check no
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4 -> bins = 24 24 24
+Memory usage per processor = 8.21387 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
+     100    0.7574531   -5.7585055            0   -4.6223613   0.20726105 
+Loop time of 2.26185 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 19099.377 tau/day, 44.212 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 1.9328     | 1.9328     | 1.9328     |   0.0 | 85.45
+Neigh   | 0.2558     | 0.2558     | 0.2558     |   0.0 | 11.31
+Comm    | 0.024061   | 0.024061   | 0.024061   |   0.0 |  1.06
+Output  | 0.00012612 | 0.00012612 | 0.00012612 |   0.0 |  0.01
+Modify  | 0.040887   | 0.040887   | 0.040887   |   0.0 |  1.81
+Other   |            | 0.008214   |            |       |  0.36
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    19657 ave 19657 max 19657 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:    1.20283e+06 ave 1.20283e+06 max 1.20283e+06 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 1202833
+Ave neighs/atom = 37.5885
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:02

bench/log.6Oct16.lj.fixed.icc.4

@@ -0,0 +1,79 @@
+LAMMPS (6 Oct 2016)
+# 3d Lennard-Jones melt
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*1
+variable	yy equal 20*$y
+variable	yy equal 20*1
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		lj
+atom_style	atomic
+
+lattice		fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 20 0 ${yy} 0 ${zz}
+region		box block 0 20 0 20 0 ${zz}
+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)
+  1 by 2 by 2 MPI processor grid
+create_atoms	1 box
+Created 32000 atoms
+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		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 20 steps, delay 0 steps, check no
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4 -> bins = 24 24 24
+Memory usage per processor = 4.09506 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1.44   -6.7733681            0   -4.6134356   -5.0197073 
+     100    0.7574531   -5.7585055            0   -4.6223613   0.20726105 
+Loop time of 0.635957 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 67929.172 tau/day, 157.243 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.51335    | 0.51822    | 0.52569    |   0.7 | 81.49
+Neigh   | 0.063695   | 0.064309   | 0.065397   |   0.3 | 10.11
+Comm    | 0.027525   | 0.03629    | 0.041959   |   3.1 |  5.71
+Output  | 6.3896e-05 | 6.6698e-05 | 7.081e-05  |   0.0 |  0.01
+Modify  | 0.012472   | 0.01254    | 0.012618   |   0.1 |  1.97
+Other   |            | 0.004529   |            |       |  0.71
+
+Nlocal:    8000 ave 8037 max 7964 min
+Histogram: 2 0 0 0 0 0 0 0 1 1
+Nghost:    9007.5 ave 9050 max 8968 min
+Histogram: 1 1 0 0 0 0 0 1 0 1
+Neighs:    300708 ave 305113 max 297203 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 1202833
+Ave neighs/atom = 37.5885
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:00

bench/log.6Oct16.lj.scaled.icc.4

@@ -0,0 +1,79 @@
+LAMMPS (6 Oct 2016)
+# 3d Lennard-Jones melt
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	xx equal 20*2
+variable	yy equal 20*$y
+variable	yy equal 20*2
+variable	zz equal 20*$z
+variable	zz equal 20*1
+
+units		lj
+atom_style	atomic
+
+lattice		fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+region		box block 0 40 0 ${yy} 0 ${zz}
+region		box block 0 40 0 40 0 ${zz}
+region		box block 0 40 0 40 0 20
+create_box	1 box
+Created orthogonal box = (0 0 0) to (67.1838 67.1838 33.5919)
+  2 by 2 by 1 MPI processor grid
+create_atoms	1 box
+Created 128000 atoms
+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		100
+Neighbor list info ...
+  1 neighbor list requests
+  update every 20 steps, delay 0 steps, check no
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 2.8
+  ghost atom cutoff = 2.8
+  binsize = 1.4 -> bins = 48 48 24
+Memory usage per processor = 8.13678 Mbytes
+Step Temp E_pair E_mol TotEng Press 
+       0         1.44   -6.7733681            0   -4.6133849   -5.0196788 
+     100   0.75841891    -5.759957            0   -4.6223375   0.20008866 
+Loop time of 2.55762 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 16890.677 tau/day, 39.099 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 2.0583     | 2.0988     | 2.1594     |   2.6 | 82.06
+Neigh   | 0.24411    | 0.24838    | 0.25585    |   0.9 |  9.71
+Comm    | 0.066397   | 0.13872    | 0.1863     |  11.9 |  5.42
+Output  | 0.00012994 | 0.00021023 | 0.00025702 |   0.3 |  0.01
+Modify  | 0.055533   | 0.058343   | 0.061791   |   1.2 |  2.28
+Other   |            | 0.0132     |            |       |  0.52
+
+Nlocal:    32000 ave 32060 max 31939 min
+Histogram: 1 0 1 0 0 0 0 1 0 1
+Nghost:    19630.8 ave 19681 max 19562 min
+Histogram: 1 0 0 0 1 0 0 0 1 1
+Neighs:    1.20195e+06 ave 1.20354e+06 max 1.19931e+06 min
+Histogram: 1 0 0 0 0 0 0 2 0 1
+
+Total # of neighbors = 4807797
+Ave neighs/atom = 37.5609
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:02

bench/log.6Oct16.rhodo.fixed.icc.1

@@ -0,0 +1,122 @@
+LAMMPS (6 Oct 2016)
+# Rhodopsin model
+
+units           real
+neigh_modify    delay 5 every 1
+
+atom_style      full
+bond_style      harmonic
+angle_style     charmm
+dihedral_style  charmm
+improper_style  harmonic
+pair_style      lj/charmm/coul/long 8.0 10.0
+pair_modify     mix arithmetic
+kspace_style    pppm 1e-4
+
+read_data       data.rhodo
+  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  4 = max bonds/atom
+  scanning angles ...
+  8 = max angles/atom
+  scanning dihedrals ...
+  18 = max dihedrals/atom
+  scanning impropers ...
+  2 = max impropers/atom
+  reading bonds ...
+  27723 bonds
+  reading angles ...
+  40467 angles
+  reading dihedrals ...
+  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
+
+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
+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
+
+thermo          50
+thermo_style    multi
+timestep        2.0
+
+run		100
+PPPM initialization ...
+WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:316)
+  G vector (1/distance) = 0.248835
+  grid = 25 32 32
+  stencil order = 5
+  estimated absolute RMS force accuracy = 0.0355478
+  estimated relative force accuracy = 0.000107051
+  using double precision FFTs
+  3d grid and FFT values/proc = 41070 25600
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 12
+  ghost atom cutoff = 12
+  binsize = 6 -> bins = 10 13 13
+Memory usage per processor = 93.2721 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       50 ----- CPU =     17.2007 (sec) ----------------
+TotEng   =    -25330.0321 KinEng   =     21501.0036 Temp     =       299.8230 
+PotEng   =    -46831.0357 E_bond   =      2471.7033 E_angle  =     10836.5108 
+E_dihed  =      5239.6316 E_impro  =       227.1219 E_vdwl   =     -1993.2763 
+E_coul   =    206797.6655 E_long   =   -270410.3927 Press    =       237.6866 
+Volume   =    308031.5640 
+---------------- Step      100 ----- CPU =     35.0315 (sec) ----------------
+TotEng   =    -25290.7387 KinEng   =     21591.9096 Temp     =       301.0906 
+PotEng   =    -46882.6484 E_bond   =      2567.9789 E_angle  =     10781.9556 
+E_dihed  =      5198.7493 E_impro  =       216.7863 E_vdwl   =     -1902.6458 
+E_coul   =    206659.5006 E_long   =   -270404.9733 Press    =         6.7898 
+Volume   =    308133.9933 
+Loop time of 35.0316 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 0.493 ns/day, 48.655 hours/ns, 2.855 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 25.021     | 25.021     | 25.021     |   0.0 | 71.42
+Bond    | 1.2834     | 1.2834     | 1.2834     |   0.0 |  3.66
+Kspace  | 3.2116     | 3.2116     | 3.2116     |   0.0 |  9.17
+Neigh   | 4.2767     | 4.2767     | 4.2767     |   0.0 | 12.21
+Comm    | 0.069283   | 0.069283   | 0.069283   |   0.0 |  0.20
+Output  | 0.00028205 | 0.00028205 | 0.00028205 |   0.0 |  0.00
+Modify  | 1.14       | 1.14       | 1.14       |   0.0 |  3.25
+Other   |            | 0.02938    |            |       |  0.08
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:    47958 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
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:36

bench/log.6Oct16.rhodo.fixed.icc.4

@@ -0,0 +1,122 @@
+LAMMPS (6 Oct 2016)
+# Rhodopsin model
+
+units           real
+neigh_modify    delay 5 every 1
+
+atom_style      full
+bond_style      harmonic
+angle_style     charmm
+dihedral_style  charmm
+improper_style  harmonic
+pair_style      lj/charmm/coul/long 8.0 10.0
+pair_modify     mix arithmetic
+kspace_style    pppm 1e-4
+
+read_data       data.rhodo
+  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  4 = max bonds/atom
+  scanning angles ...
+  8 = max angles/atom
+  scanning dihedrals ...
+  18 = max dihedrals/atom
+  scanning impropers ...
+  2 = max impropers/atom
+  reading bonds ...
+  27723 bonds
+  reading angles ...
+  40467 angles
+  reading dihedrals ...
+  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
+
+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
+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
+
+thermo          50
+thermo_style    multi
+timestep        2.0
+
+run		100
+PPPM initialization ...
+WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:316)
+  G vector (1/distance) = 0.248835
+  grid = 25 32 32
+  stencil order = 5
+  estimated absolute RMS force accuracy = 0.0355478
+  estimated relative force accuracy = 0.000107051
+  using double precision FFTs
+  3d grid and FFT values/proc = 13230 6400
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 12
+  ghost atom cutoff = 12
+  binsize = 6 -> bins = 10 13 13
+Memory usage per processor = 37.3604 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       50 ----- CPU =      4.6056 (sec) ----------------
+TotEng   =    -25330.0321 KinEng   =     21501.0036 Temp     =       299.8230 
+PotEng   =    -46831.0357 E_bond   =      2471.7033 E_angle  =     10836.5108 
+E_dihed  =      5239.6316 E_impro  =       227.1219 E_vdwl   =     -1993.2763 
+E_coul   =    206797.6655 E_long   =   -270410.3927 Press    =       237.6866 
+Volume   =    308031.5640 
+---------------- Step      100 ----- CPU =      9.3910 (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 9.39107 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 1.840 ns/day, 13.043 hours/ns, 10.648 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 6.2189     | 6.3266     | 6.6072     |   6.5 | 67.37
+Bond    | 0.30793    | 0.32122    | 0.3414     |   2.4 |  3.42
+Kspace  | 0.87994    | 1.1644     | 1.2855     |  15.3 | 12.40
+Neigh   | 1.1358     | 1.136      | 1.1362     |   0.0 | 12.10
+Comm    | 0.08292    | 0.084935   | 0.087077   |   0.5 |  0.90
+Output  | 0.00015712 | 0.00016558 | 0.00018501 |   0.1 |  0.00
+Modify  | 0.33717    | 0.34246    | 0.34794    |   0.7 |  3.65
+Other   |            | 0.01526    |            |       |  0.16
+
+Nlocal:    8000 ave 8143 max 7933 min
+Histogram: 1 2 0 0 0 0 0 0 0 1
+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
+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
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:09

bench/log.6Oct16.rhodo.scaled.icc.4

@@ -0,0 +1,143 @@
+LAMMPS (6 Oct 2016)
+# Rhodopsin model
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+units           real
+neigh_modify    delay 5 every 1
+
+atom_style      full
+atom_modify	map hash
+bond_style      harmonic
+angle_style     charmm
+dihedral_style  charmm
+improper_style  harmonic
+pair_style      lj/charmm/coul/long 8.0 10.0
+pair_modify     mix arithmetic
+kspace_style    pppm 1e-4
+
+read_data       data.rhodo
+  orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  4 = max bonds/atom
+  scanning angles ...
+  8 = max angles/atom
+  scanning dihedrals ...
+  18 = max dihedrals/atom
+  scanning impropers ...
+  2 = max impropers/atom
+  reading bonds ...
+  27723 bonds
+  reading angles ...
+  40467 angles
+  reading dihedrals ...
+  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
+
+replicate	$x $y $z
+replicate	2 $y $z
+replicate	2 2 $z
+replicate	2 2 1
+  orthogonal box = (-27.5 -38.5 -36.3646) to (82.5 115.5 36.3615)
+  2 by 2 by 1 MPI processor grid
+  128000 atoms
+  110892 bonds
+  161868 angles
+  227316 dihedrals
+  4136 impropers
+  4 = max # of 1-2 neighbors
+  12 = max # of 1-3 neighbors
+  24 = max # of 1-4 neighbors
+  26 = max # of special neighbors
+
+fix             1 all shake 0.0001 5 0 m 1.0 a 232
+  6468 = # of size 2 clusters
+  14532 = # of size 3 clusters
+  2988 = # of size 4 clusters
+  16932 = # of frozen angles
+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
+
+thermo          50
+thermo_style    multi
+timestep        2.0
+
+run		100
+PPPM initialization ...
+WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:316)
+  G vector (1/distance) = 0.248593
+  grid = 48 60 36
+  stencil order = 5
+  estimated absolute RMS force accuracy = 0.0359793
+  estimated relative force accuracy = 0.00010835
+  using double precision FFTs
+  3d grid and FFT values/proc = 41615 25920
+Neighbor list info ...
+  1 neighbor list requests
+  update every 1 steps, delay 5 steps, check yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 12
+  ghost atom cutoff = 12
+  binsize = 6 -> bins = 19 26 13
+Memory usage per processor = 96.9597 Mbytes
+---------------- Step        0 ----- CPU =      0.0000 (sec) ----------------
+TotEng   =   -101425.4887 KinEng   =     85779.3251 Temp     =       299.0304 
+PotEng   =   -187204.8138 E_bond   =     10151.9760 E_angle  =     43685.4968 
+E_dihed  =     20847.1460 E_impro  =       854.0463 E_vdwl   =     -9231.4537 
+E_coul   =    827053.5824 E_long   =  -1080565.6077 Press    =      -149.0358 
+Volume   =   1231980.1340 
+---------------- Step       50 ----- CPU =     18.1689 (sec) ----------------
+TotEng   =   -101320.0211 KinEng   =     86003.4933 Temp     =       299.8118 
+PotEng   =   -187323.5144 E_bond   =      9887.1189 E_angle  =     43346.8448 
+E_dihed  =     20958.7108 E_impro  =       908.4721 E_vdwl   =     -7973.4486 
+E_coul   =    826141.5493 E_long   =  -1080592.7617 Press    =       238.0404 
+Volume   =   1232126.1814 
+---------------- Step      100 ----- CPU =     37.2027 (sec) ----------------
+TotEng   =   -101157.9546 KinEng   =     86355.7413 Temp     =       301.0398 
+PotEng   =   -187513.6959 E_bond   =     10272.0456 E_angle  =     43128.7018 
+E_dihed  =     20794.0107 E_impro  =       867.0928 E_vdwl   =     -7587.2409 
+E_coul   =    825584.2416 E_long   =  -1080572.5474 Press    =        15.1729 
+Volume   =   1232535.8440 
+Loop time of 37.2028 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 0.464 ns/day, 51.671 hours/ns, 2.688 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 25.431     | 25.738     | 25.984     |   4.0 | 69.18
+Bond    | 1.2966     | 1.3131     | 1.3226     |   0.9 |  3.53
+Kspace  | 3.7563     | 4.0123     | 4.3127     |  10.0 | 10.79
+Neigh   | 4.3778     | 4.378      | 4.3782     |   0.0 | 11.77
+Comm    | 0.1903     | 0.19549    | 0.20485    |   1.3 |  0.53
+Output  | 0.00031805 | 0.00037521 | 0.00039601 |   0.2 |  0.00
+Modify  | 1.4861     | 1.5051     | 1.5122     |   0.9 |  4.05
+Other   |            | 0.05992    |            |       |  0.16
+
+Nlocal:    32000 ave 32000 max 32000 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Nghost:    47957 ave 47957 max 47957 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs:    1.20281e+07 ave 1.20572e+07 max 1.19991e+07 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+
+Total # of neighbors = 48112540
+Ave neighs/atom = 375.879
+Ave special neighs/atom = 7.43187
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:38

doc/.gitignore

@@ -0,0 +1,5 @@
+/html
+/LAMMPS.epub
+/LAMMPS.mobi
+/Manual.pdf
+/Developer.pdf

doc/Eqs/fix_ti_rs_force.tex

@@ -1,11 +0,0 @@
-\documentclass[12pt]{article}
-
-\usepackage{amsmath}
-
-\begin{document}
-
-$$
-  F_{\text{total}} = \lambda F_{\text{int}}
-$$
-
-\end{document}

doc/Eqs/fix_ti_rs_function_1.tex

@@ -1,9 +0,0 @@
-\documentclass[12pt]{article}
-
-\begin{document}
-
-$$
-  \lambda(\tau) = \lambda_i + \tau \left( \lambda_f - \lambda_i \right)
-$$
-
-\end{document}

doc/Eqs/fix_ti_rs_function_2.tex

@@ -1,9 +0,0 @@
-\documentclass[12pt]{article}
-
-\begin{document}
-
-$$
-  \lambda(\tau) = \frac{\lambda_i}{1 + \tau \left( \frac{\lambda_i}{\lambda_f} - 1 \right)}
-$$
-
-\end{document}

doc/Eqs/fix_ti_rs_function_3.tex

@@ -1,9 +0,0 @@
-\documentclass[12pt]{article}
-
-\begin{document}
-
-$$
-  \lambda(\tau) = \frac{\lambda_i}{ 1 + \log_2(1+\tau) \left( \frac{\lambda_i}{\lambda_f} - 1 \right)}
-$$
-
-\end{document}

doc/Eqs/fix_ti_spring_force.tex

@@ -1,11 +0,0 @@
-\documentclass[12pt]{article}
-
-\usepackage{amsmath}
-
-\begin{document}
-
-$$
-  F_{\text{total}} = \left( 1-\lambda \right) F_{\text{solid}} + \lambda F_{\text{harm}}
-$$
-
-\end{document}

doc/Eqs/improper_umbrella.tex

@@ -1,13 +0,0 @@
-\documentstyle[12pt]{article}
-
-\begin{document}
-
-$$
-E=\frac{1}{2}K\left( \frac{1+cos\omega_0}{sin\omega_0}\right) ^2 \left( cos\omega - cos\omega_0\right) \qquad \omega_0 \neq 0^o
-$$
-
-$$
-E=K\left( 1-cos\omega\right)  \qquad \omega_0 = 0^o
-$$
-
-\end{document}

doc/Eqs/pair_comb2.tex

@@ -1,22 +0,0 @@
-\documentclass[12pt]{article}
-
-\begin{document}
-
-\begin{table}[h]
-\begin{tabular}{|c|c|c|c|c|c|c|c|}
-\hline
-   & $O$ & $Cu$ & $N$ & $C$ & $H$ & $Ti$ & $Zn$ \\ \hline
-$O$	& F & F & F & F & F & F & F \\ \hline
-$Cu$	& F & F & P & F & F & P & F \\ \hline
-$N$ 	& F & P & F & M & F & P & P \\ \hline
-$C$   	& F & F & M & F & F & M & M \\ \hline
-$H$   	& F & F & F & F & F & M & M \\ \hline
-$Ti$   	& F & P & P & M & M & F & P \\ \hline
-$Zn$  	& F & F & P & M & M & P & F \\ \hline
-\multicolumn{8}{l}{F: Fully optimized} \\
-\multicolumn{8}{l}{M: Only optimized for dimer molecule} \\
-\multicolumn{8}{l}{P: in Progress but have it from mixing rule} \\
-\end{tabular}
-\end{table}
-
-\end{document}

doc/Makefile

@@ -0,0 +1,145 @@
+# Makefile for LAMMPS documentation
+
+SHELL 	      = /bin/bash
+SHA1          = $(shell echo $USER-$PWD | python utils/sha1sum.py)
+BUILDDIR      = /tmp/lammps-docs-$(SHA1)
+RSTDIR        = $(BUILDDIR)/rst
+VENV          = $(BUILDDIR)/docenv
+TXT2RST       = $(VENV)/bin/txt2rst
+
+PYTHON        = $(shell which python3)
+HAS_PYTHON3    = NO
+HAS_VIRTUALENV = NO
+
+ifeq ($(shell which python3 >/dev/null 2>&1; echo $$?), 0)
+HAS_PYTHON3 = YES
+endif
+
+ifeq ($(shell which virtualenv >/dev/null 2>&1; echo $$?), 0)
+HAS_VIRTUALENV = YES
+endif
+
+SOURCES=$(wildcard src/*.txt)
+OBJECTS=$(SOURCES:src/%.txt=$(RSTDIR)/%.rst)
+
+.PHONY: help clean-all clean epub html pdf old venv
+
+# ------------------------------------------
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       create HTML doc pages in html dir"
+	@echo "  pdf        create Manual.pdf and Developer.pdf in this dir"
+	@echo "  old        create old-style HTML doc pages in old dir"
+	@echo "  fetch      fetch HTML and PDF files from LAMMPS web site"
+	@echo "  epub       create ePUB format manual for e-book readers"
+	@echo "  clean      remove all intermediate RST files"
+	@echo "  clean-all  reset the entire build environment"
+	@echo "  txt2html   build txt2html tool"
+
+# ------------------------------------------
+
+clean-all:
+	rm -rf $(BUILDDIR)/* utils/txt2html/txt2html.exe
+
+clean:
+	rm -rf $(RSTDIR)
+
+html: $(OBJECTS)
+	@(\
+		. $(VENV)/bin/activate ;\
+		cp -r src/* $(RSTDIR)/ ;\
+		sphinx-build -j 8 -b html -c utils/sphinx-config -d $(BUILDDIR)/doctrees $(RSTDIR) html ;\
+		deactivate ;\
+	)
+	-rm html/searchindex.js
+	@rm -rf html/_sources
+	@rm -rf html/PDF
+	@rm -rf html/USER
+	@cp -r src/PDF html/PDF
+	@cp -r src/USER html/USER
+	@rm -rf html/PDF/.[sg]*
+	@rm -rf html/USER/.[sg]*
+	@rm -rf html/USER/*/.[sg]*
+	@rm -rf html/USER/*/*.[sg]*
+	@echo "Build finished. The HTML pages are in doc/html."
+
+epub: $(OBJECTS)
+	@mkdir -p epub
+	@rm -f LAMMPS.epub
+	@cp src/JPG/lammps-logo.png epub/
+	@(\
+		. $(VENV)/bin/activate ;\
+		cp -r src/* $(RSTDIR)/ ;\
+		sphinx-build -j 8 -b epub -c utils/sphinx-config -d $(BUILDDIR)/doctrees $(RSTDIR) epub ;\
+		deactivate ;\
+	)
+	@mv  epub/LAMMPS.epub .
+	@rm -rf epub
+	@echo "Build finished. The ePUB manual file is created."
+
+pdf: utils/txt2html/txt2html.exe
+	@(\
+		cd src; \
+		../utils/txt2html/txt2html.exe -b *.txt; \
+		htmldoc --batch lammps.book;          \
+		for s in `echo *.txt | sed -e 's,\.txt,\.html,g'` ; \
+			do grep -q $$s lammps.book || \
+			echo doc file $$s missing in src/lammps.book; done; \
+		rm *.html; \
+		cd Developer; \
+		pdflatex developer; \
+		pdflatex developer; \
+		mv developer.pdf ../../Developer.pdf; \
+	)
+
+old: utils/txt2html/txt2html.exe
+	@rm -rf old
+	@mkdir old; mkdir old/Eqs; mkdir old/JPG; mkdir old/PDF
+	@cd src; ../utils/txt2html/txt2html.exe -b *.txt; \
+	  mv *.html ../old; \
+	  cp Eqs/*.jpg ../old/Eqs; \
+	  cp JPG/* ../old/JPG; \
+	  cp PDF/* ../old/PDF;
+
+fetch:
+	@rm -rf html_www Manual_www.pdf Developer_www.pdf
+	@curl -s -o Manual_www.pdf http://lammps.sandia.gov/doc/Manual.pdf
+	@curl -s -o Developer_www.pdf http://lammps.sandia.gov/doc/Developer.pdf
+	@curl -s -o lammps-doc.tar.gz http://lammps.sandia.gov/tars/lammps-doc.tar.gz
+	@tar xzf lammps-doc.tar.gz
+	@rm -f lammps-doc.tar.gz
+
+txt2html: utils/txt2html/txt2html.exe
+
+# ------------------------------------------
+
+utils/txt2html/txt2html.exe: utils/txt2html/txt2html.cpp
+	g++ -O -Wall -o $@ $<
+
+$(RSTDIR)/%.rst : src/%.txt $(TXT2RST)
+	@(\
+		mkdir -p $(RSTDIR) ; \
+		. $(VENV)/bin/activate ;\
+		txt2rst $< > $@ ;\
+		deactivate ;\
+	)
+
+$(VENV):
+	@if [ "$(HAS_PYTHON3)" == "NO" ] ; then echo "Python3 was not found! Please check README.md for further instructions" 1>&2; exit 1; fi
+	@if [ "$(HAS_VIRTUALENV)" == "NO" ] ; then echo "virtualenv was not found! Please check README.md for further instructions" 1>&2; exit 1; fi
+	@( \
+		virtualenv -p $(PYTHON) $(VENV); \
+		. $(VENV)/bin/activate; \
+		pip install Sphinx; \
+		pip install sphinxcontrib-images; \
+		deactivate;\
+	)
+
+$(TXT2RST): $(VENV)
+	@( \
+		. $(VENV)/bin/activate; \
+		(cd utils/converters;\
+		python setup.py develop);\
+		deactivate;\
+	)

doc/Manual.html

@@ -1,420 +0,0 @@
-<HTML>
-<HEAD>
-<TITLE>LAMMPS Users Manual</TITLE>
-<META NAME="docnumber" CONTENT="1 Feb 2014 version">
-<META NAME="author" CONTENT="http://lammps.sandia.gov - Sandia National Laboratories">
-<META NAME="copyright" CONTENT="Copyright (2003) Sandia Corporation.  This software and manual is distributed under the GNU General Public License.">
-</HEAD>
-
-<BODY>
-
-<CENTER><A HREF = "http://lammps.sandia.gov">LAMMPS WWW Site</A> - <A HREF = "Manual.html">LAMMPS Documentation</A> - <A HREF = "Section_commands.html#comm">LAMMPS Commands</A> 
-</CENTER>
-
-
-
-
-
-
-<HR>
-
-<H1></H1>
-
-<CENTER><H3>LAMMPS Documentation 
-</H3></CENTER>
-<CENTER><H4>1 Feb 2014 version 
-</H4></CENTER>
-<H4>Version info: 
-</H4>
-<P>The LAMMPS "version" is the date when it was released, such as 1 May
-2010. LAMMPS is updated continuously.  Whenever we fix a bug or add a
-feature, we release it immediately, and post a notice on <A HREF = "http://lammps.sandia.gov/bug.html">this page of
-the WWW site</A>.  Each dated copy of LAMMPS contains all the
-features and bug-fixes up to and including that version date. The
-version date is printed to the screen and logfile every time you run
-LAMMPS. It is also in the file src/version.h and in the LAMMPS
-directory name created when you unpack a tarball, and at the top of
-the first page of the manual (this page).
-</P>
-<UL><LI>If you browse the HTML doc pages on the LAMMPS WWW site, they always
-describe the most current version of LAMMPS. 
-
-<LI>If you browse the HTML doc pages included in your tarball, they
-describe the version you have. 
-
-<LI>The <A HREF = "Manual.pdf">PDF file</A> on the WWW site or in the tarball is updated
-about once per month.  This is because it is large, and we don't want
-it to be part of every patch. 
-
-<LI>There is also a <A HREF = "Developer.pdf">Developer.pdf</A> file in the doc
-directory, which describes the internal structure and algorithms of
-LAMMPS.  
-</UL>
-<P>LAMMPS stands for Large-scale Atomic/Molecular Massively Parallel
-Simulator.
-</P>
-<P>LAMMPS is a classical molecular dynamics simulation code designed to
-run efficiently on parallel computers.  It was developed at Sandia
-National Laboratories, a US Department of Energy facility, with
-funding from the DOE.  It is an open-source code, distributed freely
-under the terms of the GNU Public License (GPL).
-</P>
-<P>The primary developers of LAMMPS are <A HREF = "http://www.sandia.gov/~sjplimp">Steve Plimpton</A>, Aidan
-Thompson, and Paul Crozier who can be contacted at
-sjplimp,athomps,pscrozi at sandia.gov.  The <A HREF = "http://lammps.sandia.gov">LAMMPS WWW Site</A> at
-http://lammps.sandia.gov has more information about the code and its
-uses.
-</P>
-
-
-
-
-<HR>
-
-<P>The LAMMPS documentation is organized into the following sections.  If
-you find errors or omissions in this manual or have suggestions for
-useful information to add, please send an email to the developers so
-we can improve the LAMMPS documentation.
-</P>
-<P>Once you are familiar with LAMMPS, you may want to bookmark <A HREF = "Section_commands.html#comm">this
-page</A> at Section_commands.html#comm since
-it gives quick access to documentation for all LAMMPS commands.
-</P>
-<P><A HREF = "Manual.pdf">PDF file</A> of the entire manual, generated by
-<A HREF = "http://www.easysw.com/htmldoc">htmldoc</A>
-</P>
-<OL><LI><A HREF = "Section_intro.html">Introduction</A> 
-
-<UL>  1.1 <A HREF = "Section_intro.html#intro_1">What is LAMMPS</A> 
-<BR>
-  1.2 <A HREF = "Section_intro.html#intro_2">LAMMPS features</A> 
-<BR>
-  1.3 <A HREF = "Section_intro.html#intro_3">LAMMPS non-features</A> 
-<BR>
-  1.4 <A HREF = "Section_intro.html#intro_4">Open source distribution</A> 
-<BR>
-  1.5 <A HREF = "Section_intro.html#intro_5">Acknowledgments and citations</A> 
-<BR></UL>
-<LI><A HREF = "Section_start.html">Getting started</A> 
-
-<UL>  2.1 <A HREF = "Section_start.html#start_1">What's in the LAMMPS distribution</A> 
-<BR>
-  2.2 <A HREF = "Section_start.html#start_2">Making LAMMPS</A> 
-<BR>
-  2.3 <A HREF = "Section_start.html#start_3">Making LAMMPS with optional packages</A> 
-<BR>
-  2.4 <A HREF = "Section_start.html#start_4">Building LAMMPS via the Make.py script</A> 
-<BR>
-  2.5 <A HREF = "Section_start.html#start_5">Building LAMMPS as a library</A> 
-<BR>
-  2.6 <A HREF = "Section_start.html#start_6">Running LAMMPS</A> 
-<BR>
-  2.7 <A HREF = "Section_start.html#start_7">Command-line options</A> 
-<BR>
-  2.8 <A HREF = "Section_start.html#start_8">Screen output</A> 
-<BR>
-  2.9 <A HREF = "Section_start.html#start_9">Tips for users of previous versions</A> 
-<BR></UL>
-<LI><A HREF = "Section_commands.html">Commands</A> 
-
-<UL>  3.1 <A HREF = "Section_commands.html#cmd_1">LAMMPS input script</A> 
-<BR>
-  3.2 <A HREF = "Section_commands.html#cmd_2">Parsing rules</A> 
-<BR>
-  3.3 <A HREF = "Section_commands.html#cmd_3">Input script structure</A> 
-<BR>
-  3.4 <A HREF = "Section_commands.html#cmd_4">Commands listed by category</A> 
-<BR>
-  3.5 <A HREF = "Section_commands.html#cmd_5">Commands listed alphabetically</A> 
-<BR></UL>
-<LI><A HREF = "Section_packages.html">Packages</A> 
-
-<UL>  4.1 <A HREF = "Section_packages.html#pkg_1">Standard packages</A> 
-<BR>
-  4.2 <A HREF = "Section_packages.html#pkg_2">User packages</A> 
-<BR></UL>
-<LI><A HREF = "Section_accelerate.html">Accelerating LAMMPS performance</A> 
-
-<UL>  5.1 <A HREF = "Section_accelerate.html#acc_1">Measuring performance</A> 
-<BR>
-  5.2 <A HREF = "Section_accelerate.html#acc_2">General strategies</A> 
-<BR>
-  5.3 <A HREF = "Section_accelerate.html#acc_3">Packages with optimized styles</A> 
-<BR>
-  5.4 <A HREF = "Section_accelerate.html#acc_4">OPT package</A> 
-<BR>
-  5.5 <A HREF = "Section_accelerate.html#acc_5">USER-OMP package</A> 
-<BR>
-  5.6 <A HREF = "Section_accelerate.html#acc_6">GPU package</A> 
-<BR>
-  5.7 <A HREF = "Section_accelerate.html#acc_7">USER-CUDA package</A> 
-<BR>
-  5.8 <A HREF = "Section_accelerate.html#acc_8">Comparison of GPU and USER-CUDA packages</A> 
-<BR></UL>
-<LI><A HREF = "Section_howto.html">How-to discussions</A> 
-
-<UL>  6.1 <A HREF = "Section_howto.html#howto_1">Restarting a simulation</A> 
-<BR>
-  6.2 <A HREF = "Section_howto.html#howto_2">2d simulations</A> 
-<BR>
-  6.3 <A HREF = "Section_howto.html#howto_3">CHARMM and AMBER force fields</A> 
-<BR>
-  6.4 <A HREF = "Section_howto.html#howto_4">Running multiple simulations from one input script</A> 
-<BR>
-  6.5 <A HREF = "Section_howto.html#howto_5">Multi-replica simulations</A> 
-<BR>
-  6.6 <A HREF = "Section_howto.html#howto_6">Granular models</A> 
-<BR>
-  6.7 <A HREF = "Section_howto.html#howto_7">TIP3P water model</A> 
-<BR>
-  6.8 <A HREF = "Section_howto.html#howto_8">TIP4P water model</A> 
-<BR>
-  6.9 <A HREF = "Section_howto.html#howto_9">SPC water model</A> 
-<BR>
-  6.10 <A HREF = "Section_howto.html#howto_10">Coupling LAMMPS to other codes</A> 
-<BR>
-  6.11 <A HREF = "Section_howto.html#howto_11">Visualizing LAMMPS snapshots</A> 
-<BR>
-  6.12 <A HREF = "Section_howto.html#howto_12">Triclinic (non-orthogonal) simulation boxes</A> 
-<BR>
-  6.13 <A HREF = "Section_howto.html#howto_13">NEMD simulations</A> 
-<BR>
-  6.14 <A HREF = "Section_howto.html#howto_14">Finite-size spherical and aspherical particles</A> 
-<BR>
-  6.15 <A HREF = "Section_howto.html#howto_15">Output from LAMMPS (thermo, dumps, computes, fixes, variables)</A> 
-<BR>
-  6.16 <A HREF = "Section_howto.html#howto_16">Thermostatting, barostatting, and compute temperature</A> 
-<BR>
-  6.17 <A HREF = "Section_howto.html#howto_17">Walls</A> 
-<BR>
-  6.18 <A HREF = "Section_howto.html#howto_18">Elastic constants</A> 
-<BR>
-  6.19 <A HREF = "Section_howto.html#howto_19">Library interface to LAMMPS</A> 
-<BR>
-  6.20 <A HREF = "Section_howto.html#howto_20">Calculating thermal conductivity</A> 
-<BR>
-  6.21 <A HREF = "Section_howto.html#howto_21">Calculating viscosity</A> 
-<BR></UL>
-<LI><A HREF = "Section_example.html">Example problems</A> 
-
-<LI><A HREF = "Section_perf.html">Performance & scalability</A> 
-
-<LI><A HREF = "Section_tools.html">Additional tools</A> 
-
-<LI><A HREF = "Section_modify.html">Modifying & extending LAMMPS</A> 
-
-<UL>  10.1 <A HREF = "Section_modify.html#mod_1">Atom styles</A> 
-<BR>
-  10.2 <A HREF = "Section_modify.html#mod_2">Bond, angle, dihedral, improper potentials</A> 
-<BR>
-  10.3 <A HREF = "Section_modify.html#mod_3">Compute styles</A> 
-<BR>
-  10.4 <A HREF = "Section_modify.html#mod_4">Dump styles</A> 
-<BR>
-  10.5 <A HREF = "Section_modify.html#mod_5">Dump custom output options</A> 
-<BR>
-  10.6 <A HREF = "Section_modify.html#mod_6">Fix styles</A> 
-<BR>
-  10.7 <A HREF = "Section_modify.html#mod_7">Input script commands</A> 
-<BR>
-  10.8 <A HREF = "Section_modify.html#mod_8">Kspace computations</A> 
-<BR>
-  10.9 <A HREF = "Section_modify.html#mod_9">Minimization styles</A> 
-<BR>
-  10.10 <A HREF = "Section_modify.html#mod_10">Pairwise potentials</A> 
-<BR>
-  10.11 <A HREF = "Section_modify.html#mod_11">Region styles</A> 
-<BR>
-  10.12 <A HREF = "Section_modify.html#mod_12">Body styles</A> 
-<BR>
-  10.13 <A HREF = "Section_modify.html#mod_13">Thermodynamic output options</A> 
-<BR>
-  10.14 <A HREF = "Section_modify.html#mod_14">Variable options</A> 
-<BR>
-  10.15 <A HREF = "Section_modify.html#mod_15">Submitting new features for inclusion in LAMMPS</A> 
-<BR></UL>
-<LI><A HREF = "Section_python.html">Python interface</A> 
-
-<UL>  11.1 <A HREF = "Section_python.html#py_1">Building LAMMPS as a shared library</A> 
-<BR>
-  11.2 <A HREF = "Section_python.html#py_2">Installing the Python wrapper into Python</A> 
-<BR>
-  11.3 <A HREF = "Section_python.html#py_3">Extending Python with MPI to run in parallel</A> 
-<BR>
-  11.4 <A HREF = "Section_python.html#py_4">Testing the Python-LAMMPS interface</A> 
-<BR>
-  11.5 <A HREF = "Section_python.html#py_5">Using LAMMPS from Python</A> 
-<BR>
-  11.6 <A HREF = "Section_python.html#py_6">Example Python scripts that use LAMMPS</A> 
-<BR></UL>
-<LI><A HREF = "Section_errors.html">Errors</A> 
-
-<UL>  12.1 <A HREF = "Section_errors.html#err_1">Common problems</A> 
-<BR>
-  12.2 <A HREF = "Section_errors.html#err_2">Reporting bugs</A> 
-<BR>
-  12.3 <A HREF = "Section_errors.html#err_3">Error & warning messages</A> 
-<BR></UL>
-<LI><A HREF = "Section_history.html">Future and history</A> 
-
-<UL>  13.1 <A HREF = "Section_history.html#hist_1">Coming attractions</A> 
-<BR>
-  13.2 <A HREF = "Section_history.html#hist_2">Past versions</A> 
-<BR></UL>
-
-</OL>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-</BODY>
-
-</HTML>