ICODE-ADC/lammps
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updating to master

Browse Source
This commit is contained in:
Stan Moore
2017-06-19 10:56:24 -06:00
parent 2cf83d9fca bc0241576f
commit da0dcbe0bb
792 changed files with 70217 additions and 16059 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
doc/Makefile
View File

@ -100,6 +100,7 @@ epub: $(OBJECTS)
pdf: utils/txt2html/txt2html.exe
@(\
set -e; \
cd src; \
../utils/txt2html/txt2html.exe -b *.txt; \
htmldoc --batch lammps.book; \

BIN
doc/src/Eqs/cnp_cutoff.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 13 KiB

14
doc/src/Eqs/cnp_cutoff.tex Normal file
View File

@ -0,0 +1,14 @@
\documentclass[12pt,article]{article}
\usepackage{indentfirst}
\usepackage{amsmath}
\begin{document}
\begin{eqnarray*}
r_{c}^{fcc} & = & \frac{1}{2} \left(\frac{\sqrt{2}}{2} + 1\right) \mathrm{a} \simeq 0.8536 \:\mathrm{a} \\
r_{c}^{bcc} & = & \frac{1}{2}(\sqrt{2} + 1) \mathrm{a} \simeq 1.207 \:\mathrm{a} \\
r_{c}^{hcp} & = & \frac{1}{2}\left(1+\sqrt{\frac{4+2x^{2}}{3}}\right) \mathrm{a}
\end{eqnarray*}
\end{document}

BIN
doc/src/Eqs/cnp_cutoff2.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.5 KiB

12
doc/src/Eqs/cnp_cutoff2.tex Normal file
View File

@ -0,0 +1,12 @@
\documentclass[12pt,article]{article}
\usepackage{indentfirst}
\usepackage{amsmath}
\begin{document}
$$
Rc + Rs > 2*{\rm cutoff}
$$
\end{document}

BIN
doc/src/Eqs/cnp_eq.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 23 KiB

9
doc/src/Eqs/cnp_eq.tex Normal file
View File

@ -0,0 +1,9 @@
\documentclass[12pt]{article}
\begin{document}
$$
Q_{i} = \frac{1}{n_i}\sum_{j = 1}^{n_i} | \sum_{k = 1}^{n_{ij}} \vec{R}_{ik} + \vec{R}_{jk} |^2
$$
\end{document}

BIN
doc/src/Eqs/pair_lj_sf.jpg
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 15 KiB

11
doc/src/Eqs/pair_lj_sf.tex
View File

@ -1,11 +0,0 @@
\documentclass[12pt]{article}
\begin{document}
\begin{eqnarray*}
F & = & F_{\mathrm{LJ}}(r) - F_{\mathrm{LJ}}(r_{\mathrm{c}}) \qquad r < r_{\mathrm{c}} \\
E & = & E_{\mathrm{LJ}}(r) - E_{\mathrm{LJ}}(r_{\mathrm{c}}) + (r - r_{\mathrm{c}}) F_{\mathrm{LJ}}(r_{\mathrm{c}}) \qquad r < r_{\mathrm{c}} \\
\mathrm{with} \qquad E_{\mathrm{LJ}}(r) & = & 4 \epsilon \left[ \left(\frac{\sigma}{r}\right)^{12} - \left(\frac{\sigma}{r}\right)^6 \right] \qquad \mathrm{and} \qquad F_{\mathrm{LJ}}(r) = - E^\prime_{\mathrm{LJ}}(r)
\end{eqnarray*}
\end{document}

6
doc/src/Section_commands.txt
View File

@ -717,7 +717,7 @@ package"_Section_start.html#start_3.
"phonon"_fix_phonon.html,
"pimd"_fix_pimd.html,
"qbmsst"_fix_qbmsst.html,
"qeq/reax"_fix_qeq_reax.html,
"qeq/reax (ko)"_fix_qeq_reax.html,
"qmmm"_fix_qmmm.html,
"qtb"_fix_qtb.html,
"reax/c/bonds"_fix_reax_bonds.html,
@ -831,6 +831,7 @@ package"_Section_start.html#start_3.
"ackland/atom"_compute_ackland_atom.html,
"basal/atom"_compute_basal_atom.html,
"cnp/atom"_compute_cnp_atom.html,
"dpd"_compute_dpd.html,
"dpd/atom"_compute_dpd_atom.html,
"fep"_compute_fep.html,
@ -1038,7 +1039,6 @@ package"_Section_start.html#start_3.
"lj/sdk (gko)"_pair_sdk.html,
"lj/sdk/coul/long (go)"_pair_sdk.html,
"lj/sdk/coul/msm (o)"_pair_sdk.html,
"lj/sf (o)"_pair_lj_sf.html,
"meam/spline (o)"_pair_meam_spline.html,
"meam/sw/spline"_pair_meam_sw_spline.html,
"mgpt"_pair_mgpt.html,
@ -1057,7 +1057,7 @@ package"_Section_start.html#start_3.
"oxdna2/excv"_pair_oxdna2.html,
"oxdna2/stk"_pair_oxdna2.html,
"quip"_pair_quip.html,
"reax/c (k)"_pair_reaxc.html,
"reax/c (ko)"_pair_reaxc.html,
"smd/hertz"_pair_smd_hertz.html,
"smd/tlsph"_pair_smd_tlsph.html,
"smd/triangulated/surface"_pair_smd_triangulated_surface.html,

8
doc/src/Section_errors.txt
View File

@ -8890,6 +8890,14 @@ This is a requirement to use this potential. :dd
See the newton command. This is a restriction to use this potential. :dd
{Pair style vashishta/gpu requires atom IDs} :dt
This is a requirement to use this potential. :dd
{Pair style vashishta/gpu requires newton pair off} :dt
See the newton command. This is a restriction to use this potential. :dd
{Pair style tersoff/gpu requires atom IDs} :dt
This is a requirement to use the tersoff/gpu potential. :dd

6
doc/src/Section_packages.txt
View File

@ -1502,7 +1502,7 @@ oxDNA model of Doye, Louis and Ouldridge at the University of Oxford.
This includes Langevin-type rigid-body integrators with improved
stability.
[Author:] Oliver Henrich (University of Edinburgh).
[Author:] Oliver Henrich (University of Strathclyde, Glasgow).
[Install or un-install:]
@ -2027,8 +2027,8 @@ algorithm to formulate single-particle constraint functions
g(xi,yi,zi) = 0 and their derivative (i.e. the normal of the manifold)
n = grad(g).
[Author:] Stefan Paquay (Eindhoven University of Technology (TU/e), The
Netherlands)
[Author:] Stefan Paquay (until 2017: Eindhoven University of Technology (TU/e), The
Netherlands; since 2017: Brandeis University, Waltham, MA, USA)
[Install or un-install:]

4
doc/src/compute_cna_atom.txt
View File

@ -26,7 +26,7 @@ Define a computation that calculates the CNA (Common Neighbor
Analysis) pattern for each atom in the group. In solid-state systems
the CNA pattern is a useful measure of the local crystal structure
around an atom. The CNA methodology is described in "(Faken)"_#Faken
and "(Tsuzuki)"_#Tsuzuki.
and "(Tsuzuki)"_#Tsuzuki1.
Currently, there are five kinds of CNA patterns LAMMPS recognizes:
@ -93,5 +93,5 @@ above.
:link(Faken)
[(Faken)] Faken, Jonsson, Comput Mater Sci, 2, 279 (1994).
:link(Tsuzuki)
:link(Tsuzuki1)
[(Tsuzuki)] Tsuzuki, Branicio, Rino, Comput Phys Comm, 177, 518 (2007).

111
doc/src/compute_cnp_atom.txt Normal file
View File

@ -0,0 +1,111 @@
"LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
:link(lws,http://lammps.sandia.gov)
:link(ld,Manual.html)
:link(lc,Section_commands.html#comm)
:line
compute cnp/atom command :h3
[Syntax:]
compute ID group-ID cnp/atom cutoff :pre
ID, group-ID are documented in "compute"_compute.html command
cnp/atom = style name of this compute command
cutoff = cutoff distance for nearest neighbors (distance units) :ul
[Examples:]
compute 1 all cnp/atom 3.08 :pre
[Description:]
Define a computation that calculates the Common Neighborhood
Parameter (CNP) for each atom in the group. In solid-state systems
the CNP is a useful measure of the local crystal structure
around an atom and can be used to characterize whether the
atom is part of a perfect lattice, a local defect (e.g. a dislocation
or stacking fault), or at a surface.
The value of the CNP parameter will be 0.0 for atoms not in the
specified compute group. Note that normally a CNP calculation should
only be performed on single component systems.
This parameter is computed using the following formula from
"(Tsuzuki)"_#Tsuzuki2
:c,image(Eqs/cnp_eq.jpg)
where the index {j} goes over the {n}i nearest neighbors of atom
{i}, and the index {k} goes over the {n}ij common nearest neighbors
between atom {i} and atom {j}. Rik and Rjk are the vectors connecting atom
{k} to atoms {i} and {j}. The quantity in the double sum is computed
for each atom.
The CNP calculation is sensitive to the specified cutoff value.
You should ensure that the appropriate nearest neighbors of an atom are
found within the cutoff distance for the presumed crystal structure.
E.g. 12 nearest neighbor for perfect FCC and HCP crystals, 14 nearest
neighbors for perfect BCC crystals. These formulas can be used to
obtain a good cutoff distance:
:c,image(Eqs/cnp_cutoff.jpg)
where a is the lattice constant for the crystal structure concerned
and in the HCP case, x = (c/a) / 1.633, where 1.633 is the ideal c/a
for HCP crystals.
Also note that since the CNP calculation in LAMMPS uses the neighbors
of an owned atom to find the nearest neighbors of a ghost atom, the
following relation should also be satisfied:
:c,image(Eqs/cnp_cutoff2.jpg)
where Rc is the cutoff distance of the potential, Rs is the skin
distance as specified by the "neighbor"_neighbor.html command, and
cutoff is the argument used with the compute cnp/atom command. LAMMPS
will issue a warning if this is not the case.
The neighbor list needed to compute this quantity is constructed each
time the calculation is performed (e.g. each time a snapshot of atoms
is dumped). Thus it can be inefficient to compute/dump this quantity
too frequently or to have multiple compute/dump commands, each with a
{cnp/atom} style.
[Output info:]
This compute calculates a per-atom vector, which can be accessed by
any command that uses per-atom values from a compute as input. See
"Section 6.15"_Section_howto.html#howto_15 for an overview of
LAMMPS output options.
The per-atom vector values will be real positive numbers. Some typical CNP
values:
FCC lattice = 0.0
BCC lattice = 0.0
HCP lattice = 4.4 :pre
FCC (111) surface ~ 13.0
FCC (100) surface ~ 26.5
FCC dislocation core ~ 11 :pre
[Restrictions:]
This compute is part of the USER-MISC package. It is only enabled if
LAMMPS was built with that package. See the "Making
LAMMPS"_Section_start.html#start_3 section for more info.
[Related commands:]
"compute cna/atom"_compute_cna_atom.html
"compute centro/atom"_compute_centro_atom.html
[Default:] none
:line
:link(Tsuzuki2)
[(Tsuzuki)] Tsuzuki, Branicio, Rino, Comput Phys Comm, 177, 518 (2007).

11
doc/src/compute_sna_atom.txt
View File

@ -231,11 +231,12 @@ the numbers of columns are 930, 2790, and 5580, respectively.
If the {quadratic} keyword value is set to 1, then additional
columns are appended to each per-atom array, corresponding to
a matrix of quantities that are products of two bispectrum components. If the
number of bispectrum components is {K}, then the number of matrix elements
is {K}^2. These are output in subblocks of {K}^2 columns, using the same
ordering of columns and sub-blocks as was used for the bispectrum
components.
the products of all distinct pairs of bispectrum components. If the
number of bispectrum components is {K}, then the number of distinct pairs
is {K}({K}+1)/2. These are output in subblocks of {K}({K}+1)/2 columns, using the same
ordering of sub-blocks as was used for the bispectrum
components. Within each sub-block, the ordering is upper-triangular,
(1,1),(1,2)...(1,{K}),(2,1)...({K}-1,{K}-1),({K}-1,{K}),({K},{K})
These values can be accessed by any command that uses per-atom values
from a compute as input. See "Section

1
doc/src/computes.txt
View File

@ -17,6 +17,7 @@ Computes :h1
compute_chunk_atom
compute_cluster_atom
compute_cna_atom
compute_cnp_atom
compute_com
compute_com_chunk
compute_contact_atom

1
doc/src/dihedral_spherical.txt
View File

@ -18,6 +18,7 @@ dihedral_coeff 1 1 286.1 1 124 1 1 90.0 0 1 90.0 0
dihedral_coeff 1 3 69.3 1 93.9 1 1 90 0 1 90 0 &
49.1 0 0.00 0 1 74.4 1 0 0.00 0 &
25.2 0 0.00 0 0 0.00 0 1 48.1 1
:pre
[Description:]

24
doc/src/dump_modify.txt
View File

@ -16,7 +16,8 @@ dump-ID = ID of dump to modify :ulb,l
one or more keyword/value pairs may be appended :l
these keywords apply to various dump styles :l
keyword = {append} or {buffer} or {element} or {every} or {fileper} or {first} or {flush} or {format} or {image} or {label} or {nfile} or {pad} or {precision} or {region} or {scale} or {sort} or {thresh} or {unwrap} :l
{append} arg = {yes} or {no}
{append} arg = {yes} or {no} or {at} N
N = index of frame written upon first dump
{buffer} arg = {yes} or {no}
{element} args = E1 E2 ... EN, where N = # of atom types
E1,...,EN = element name, e.g. C or Fe or Ga
@ -41,6 +42,7 @@ keyword = {append} or {buffer} or {element} or {every} or {fileper} or {first} o
{region} arg = region-ID or "none"
{scale} arg = {yes} or {no}
{sfactor} arg = coordinate scaling factor (> 0.0)
{thermo} arg = {yes} or {no}
{tfactor} arg = time scaling factor (> 0.0)
{sort} arg = {off} or {id} or N or -N
off = no sorting of per-atom lines within a snapshot
@ -139,12 +141,13 @@ and {dcd}. It also applies only to text output files, not to binary
or gzipped or image/movie files. If specified as {yes}, then dump
snapshots are appended to the end of an existing dump file. If
specified as {no}, then a new dump file will be created which will
overwrite an existing file with the same name. This keyword can only
take effect if the dump_modify command is used after the
"dump"_dump.html command, but before the first command that causes
dump snapshots to be output, e.g. a "run"_run.html or
"minimize"_minimize.html command. Once the dump file has been opened,
this keyword has no further effect.
overwrite an existing file with the same name. If the {at} option is present
({netcdf} only), then the frame to append to can be specified. Negative values
are counted from the end of the file. This keyword can only take effect if the
dump_modify command is used after the "dump"_dump.html command, but before the
first command that causes dump snapshots to be output, e.g. a "run"_run.html or
"minimize"_minimize.html command. Once the dump file has been opened, this
keyword has no further effect.
:line
@ -413,6 +416,13 @@ most effective when the typical magnitude of position data is between
:line
The {thermo} keyword ({netcdf} only) triggers writing of "thermo"_thermo.html
information to the dump file alongside per-atom data. The data included in the
dump file is identical to the data specified by
"thermo_style"_thermo_style.html.
:line
The {region} keyword only applies to the dump {custom}, {cfg},
{image}, and {movie} styles. If specified, only atoms in the region
will be written to the dump file or included in the image/movie. Only

16
doc/src/dump_netcdf.txt
View File

@ -24,7 +24,7 @@ args = list of atom attributes, same as for "dump_style custom"_dump.html :l,ule
[Examples:]
dump 1 all netcdf 100 traj.nc type x y z vx vy vz
dump_modify 1 append yes at -1 global c_thermo_pe c_thermo_temp c_thermo_press
dump_modify 1 append yes at -1 thermo yes
dump 1 all netcdf/mpiio 1000 traj.nc id type x y z :pre
[Description:]
@ -44,7 +44,7 @@ rank.
NetCDF files can be directly visualized via the following tools:
Ovito (http://www.ovito.org/). Ovito supports the AMBER convention and
all of the above extensions. :ule,b
all extensions of this dump style. :ule,b
VMD (http://www.ks.uiuc.edu/Research/vmd/). :l
@ -52,15 +52,9 @@ AtomEye (http://www.libatoms.org/). The libAtoms version of AtomEye
contains a NetCDF reader that is not present in the standard
distribution of AtomEye. :l,ule
In addition to per-atom data, global data can be included in the dump
file, which are the kinds of values output by the
"thermo_style"_thermo_style.html command . See "Section howto
6.15"_Section_howto.html#howto_15 for an explanation of per-atom
versus global data. The global output written into the dump file can
be from computes, fixes, or variables, by prefixing the compute/fix ID
or variable name with "c_" or "f_" or "v_" respectively, as in the
example above. These global values are specified via the "dump_modify
global"_dump_modify.html command.
In addition to per-atom data, "thermo"_thermo.html data can be included in the
dump file. The data included in the dump file is identical to the data specified
by "thermo_style"_thermo_style.html.
:link(netcdf-home,http://www.unidata.ucar.edu/software/netcdf/)
:link(pnetcdf-home,http://trac.mcs.anl.gov/projects/parallel-netcdf/)

2
doc/src/fix_adapt.txt
View File

@ -47,7 +47,7 @@ keyword = {scale} or {reset} :l
fix 1 all adapt 1 pair soft a 1 1 v_prefactor
fix 1 all adapt 1 pair soft a 2* 3 v_prefactor
fix 1 all adapt 1 pair lj/cut epsilon * * v_scale1 coul/cut scale 3 3 v_scale2 scale yes reset yes
fix 1 all adapt 10 atom diameter v_size
fix 1 all adapt 10 atom diameter v_size :pre
variable ramp_up equal "ramp(0.01,0.5)"
fix stretch all adapt 1 bond harmonic r0 1 v_ramp_up :pre

6
doc/src/fix_deform.txt
View File

@ -565,8 +565,10 @@ more instructions on how to use the accelerated styles effectively.
[Restart, fix_modify, output, run start/stop, minimize info:]
No information about this fix is written to "binary restart
files"_restart.html. None of the "fix_modify"_fix_modify.html options
This fix will restore the initial box settings from "binary restart
files"_restart.html, which allows the fix to be properly continue
deformation, when using the start/stop options of the "run"_run.html
command. None of the "fix_modify"_fix_modify.html options
are relevant to this fix. No global or per-atom quantities are stored
by this fix for access by various "output
commands"_Section_howto.html#howto_15.

4
doc/src/fix_langevin_drude.txt
View File

@ -67,11 +67,11 @@ The Langevin forces are computed as
\(F_r'\) is a random force proportional to
\(\sqrt \{ \frac \{2\, k_B \mathtt\{Tcom\}\, m'\}
\{\mathrm dt\, \mathtt\{damp\_com\} \}
\} \). :b
\} \).
\(f_r'\) is a random force proportional to
\(\sqrt \{ \frac \{2\, k_B \mathtt\{Tdrude\}\, m'\}
\{\mathrm dt\, \mathtt\{damp\_drude\} \}
\} \). :b
\} \).
Then the real forces acting on the particles are computed from the inverse
transform:
\begin\{equation\} F = \frac M \{M'\}\, F' - f' \end\{equation\}

194
doc/src/fix_neb.txt
View File

@ -10,68 +10,156 @@ fix neb command :h3
[Syntax:]
fix ID group-ID neb Kspring :pre
fix ID group-ID neb Kspring keyword value :pre
ID, group-ID are documented in "fix"_fix.html command
neb = style name of this fix command
Kspring = inter-replica spring constant (force/distance units) :ul
ID, group-ID are documented in "fix"_fix.html command :ulb,l
neb = style name of this fix command :l
Kspring = parallel spring constant (force/distance units or force units) :l
zero or more keyword/value pairs may be appended :l
keyword = {nudg_style} or {perp} or {freend} or {freend_k_spring} :l
{nudg_style} value = {neigh} or {idealpos}
{neigh} = the parallel nudging force is calculated from the distances to neighbouring replicas (in this case, Kspring is in force/distance units)
{idealpos} = the parallel nudging force is proportional to the distance between the replica and its interpolated ideal position (in this case Kspring is in force units)
{perp} value {none} or kspring2
{none} = no perpendicular spring force is applied
{kspring2} = spring constant for the perpendicular nudging force (in force/distance units)
{freeend} value = {none} or {ini} or {final} or {finaleini} or {final2eini}
{none} = no nudging force is applied to the first and last replicas
{ini} = set the first replica to be a free end
{final} = set the last replica to be a free end
{finaleini} = set the last replica to be a free end and set its target energy as that of the first replica
{final2eini} = same as {finaleini} plus prevent intermediate replicas to have a lower energy than the first replica
{freeend_kspring} value = kspring3
kspring3 = spring constant of the perpendicular spring force (per distance units)
:pre
[Examples:]
fix 1 active neb 10.0 :pre
fix 1 active neb 10.0
fix 2 all neb 1.0 perp 1.0 freeend final
fix 1 all neb 1.0 nudg_style idealpos freeend final2eini freend_kspring 1:pre
[Description:]
Add inter-replica forces to atoms in the group for a multi-replica
Add a nudging force to atoms in the group for a multi-replica
simulation run via the "neb"_neb.html command to perform a nudged
elastic band (NEB) calculation for transition state finding. Hi-level
explanations of NEB are given with the "neb"_neb.html command and in
"Section 6.5"_Section_howto.html#howto_5 of the manual. The fix
neb command must be used with the "neb" command to define how
inter-replica forces are computed.
elastic band (NEB) calculation for finding the transition state.
Hi-level explanations of NEB are given with the "neb"_neb.html command
and in "Section_howto 5"_Section_howto.html#howto_5 of the manual.
The fix neb command must be used with the "neb" command and defines
how nudging inter-replica forces are computed. A NEB calculation is
divided in two stages. In the first stage n replicas are relaxed
toward a MEP and in a second stage, the climbing image scheme (see
"(Henkelman2)"_#Henkelman2) is turned on so that the replica having
the highest energy relaxes toward the saddle point (i.e. the point of
highest energy along the MEP).
Only the N atoms in the fix group experience inter-replica forces.
Atoms in the two end-point replicas do not experience these forces,
but those in intermediate replicas do. During the initial stage of
NEB, the 3N-length vector of interatomic forces Fi = -Grad(V) acting
on the atoms of each intermediate replica I is altered, as described
in the "(Henkelman1)"_#Henkelman1 paper, to become:
One purpose of the nudging forces is to keep the replicas equally
spaced. During the NEB, the 3N-length vector of interatomic force Fi
= -Grad(V) of replicas i is altered. For all intermediate replicas
(i.e. for 1<i<n) but the climbing replica the force vector
becomes:
Fi = -Grad(V) + (Grad(V) dot That) That + Kspring (| Ri+i - Ri | - | Ri - Ri-1 |) That :pre
Fi = -Grad(V) + (Grad(V) dot That) That + Fnudgparallel + Fspringperp :pre
Ri are the atomic coordinates of replica I; Ri-1 and Ri+1 are the
coordinates of its neighbor replicas. That (t with a hat over it) is
the unit "tangent" vector for replica I which is a function of Ri,
Ri-1, Ri+1, and the potential energy of the 3 replicas; it points
roughly in the direction of (Ri+i - Ri-1); see the
"(Henkelman1)"_#Henkelman1 paper for details.
That is the unit "tangent" vector for replica i and is a function of
Ri, Ri-1, Ri+1, and the potential energy of the 3 replicas; it points
roughly in the direction of (Ri+i - Ri-1) (see the
"(Henkelman1)"_#Henkelman1 paper for details). Ri are the atomic
coordinates of replica i; Ri-1 and Ri+1 are the coordinates of its
neighbor replicas. The term (Grad(V) dot That) is used to remove the
component of the gradient parallel to the path which would tend to
distribute the replica unevenly along the path. Fnudgparallel is an
artificial nudging force which is applied only in the tangent direction
and which maintains the replicas equally spaced (see below for more
information). Fspringperp is an optinal artificial spring which is
applied only perpendicular to the tangent and which prevent the paths
from forming too acute kinks (see below for more information).
The first two terms in the above equation are the component of the
interatomic forces perpendicular to the tangent vector. The last term
is a spring force between replica I and its neighbors, parallel to the
tangent vector direction with the specified spring constant {Kspring}.
The keyword {nudg_style} allow to specify how to parallel
nudging force is computed. With a value of idealpos, the spring
force is computed as suggested in "(E)"_#E :
The effect of the first two terms is to push the atoms of each replica
toward the minimum energy path (MEP) of conformational states that
transition over the energy barrier. The MEP for an energy barrier is
defined as a sequence of 3N-dimensional states which cross the barrier
at its saddle point, each of which has a potential energy gradient
parallel to the MEP itself.
Fnudgparallel=-{Kspring}* (RD-RDideal)/(2 meanDist) :pre
The effect of the last term is to push each replica away from its two
neighbors in a direction along the MEP, so that the final set of
states are equidistant from each other.
where RD is the "reaction coordinate" see "neb"_neb.html section, and
RDideal is the ideal RD for which all the images are equally spaced
(i.e. RDideal = (i-1)*meanDist when the climbing image is off, where i
is the replica number). The meanDist is the average distance between
replicas.
During the second stage of NEB, the forces on the N atoms in the
replica nearest the top of the energy barrier are altered so that it
climbs to the top of the barrier and finds the saddle point. The
forces on atoms in this replica are described in the
"(Henkelman2)"_#Henkelman2 paper, and become:
When {nudg_style} has a value of neigh (or by default), the parallel
nudging force is computed as in "(Henkelman1)"_#Henkelman1 by
connecting each intermediate replica with the previous and the next
image:
Fnudgparallel= {Kspring}* (|Ri+1 - Ri| - |Ri - Ri-1|) :pre
The parallel nudging force associated with the key word idealpos should
usually be more efficient at keeping the images equally spaced.
:line
The keyword {perp} allows to add a spring force perpendicular to the
path in order to prevent the path from becoming too kinky. It can
improve significantly the convergence of the NEB when the resolution
is poor (i.e. when too few images are used) (see "(Maras)"_#Maras1).
The perpendicular spring force is given by
Fspringperp = {Kspringperp} * f(Ri-1,Ri,Ri+1) (Ri+1 + Ri-1 - 2 Ri) :pre
f(Ri-1 Ri R+1) is a smooth scalar function of the angle Ri-1 Ri
Ri+1. It is equal to 0 when the path is straight and is equal to 1
when the angle Ri-1 Ri Ri+1 is accute. f(Ri-1 Ri R+1) is defined in
"(Jonsson)"_#Jonsson
:line
By default, the force acting on the first and last replicas is not
altered so that during the NEB relaxation, these ending replicas relax
toward local minima. However it is possible to use the key word
{freeend} to allow either the initial or the final replica to relax
toward a MEP while constraining its energy. The interatomic force Fi
for the free end image becomes :
Fi = -Grad(V)+ (Grad(V) dot That + (E-ETarget)*kspring3) That, {when} Grad(V) dot That < 0
Fi = -Grad(V)+ (Grad(V) dot That + (ETarget- E)*kspring3) That, {when} Grad(V) dot That > 0
:pre
where E is the energy of the free end replica and ETarget is the
target energy.
When the value {ini} ({final}) is used after the keyword {freeend},
the first (last) replica is considered as a free end. The target
energy is set to the energy of the replica at starting of the NEB
calculation. When the value {finaleini} or {final2eini} is used the
last image is considered as a free end and the target energy is equal
to the energy of the first replica (which can evolve during the NEB
relaxation). With the value {finaleini}, when the initial path is too
far from the MEP, an intermediate repilica might relax "faster" and
get a lower energy than the last replica. The benefit of the free end
is then lost since this intermediate replica will relax toward a local
minima. This behavior can be prevented by using the value {final2eini}
which remove entirely the contribution of the gradient for all
intermediate replica which have a lower energy than the initial one
thus preventing these replicae to over-relax. After converging a NEB
with the {final2eini} value it is recommended to check that all
intermediate replica have a larger energy than the initial
replica. Finally note that if the last replica converges toward a
local minimum with a larger energy than the energy of the first
replica, a free end neb calculation with the value {finaleini} or
{final2eini} cannot reach the convergence criteria.
:line
In the second stage of the NEB, the interatomic force Fi for the
climbing replica (which is the replica of highest energy) becomes:
Fi = -Grad(V) + 2 (Grad(V) dot That) That :pre
The inter-replica forces for the other replicas are unchanged from the
first equation.
[Restart, fix_modify, output, run start/stop, minimize info:]
@ -96,7 +184,11 @@ for more info on packages.
"neb"_neb.html
[Default:] none
[Default:]
The option defaults are nudg_style = neigh, perp = none, freeend = none and freend_kspring = 1.
:line
:link(Henkelman1)
[(Henkelman1)] Henkelman and Jonsson, J Chem Phys, 113, 9978-9985 (2000).
@ -104,3 +196,15 @@ for more info on packages.
:link(Henkelman2)
[(Henkelman2)] Henkelman, Uberuaga, Jonsson, J Chem Phys, 113,
9901-9904 (2000).
:link(E)
[(E)] E, Ren, Vanden-Eijnden, Phys Rev B, 66, 052301 (2002)
:link(Jonsson)
[(Jonsson)] Jonsson, Mills and Jacobsen, in Classical and Quantum
Dynamics in Condensed Phase Simulations, edited by Berne, Ciccotti, and Coker
World Scientific, Singapore, 1998, p. 385
:link(Maras1)
[(Maras)] Maras, Trushin, Stukowski, Ala-Nissila, Jonsson,
Comp Phys Comm, 205, 13-21 (2016)

10
doc/src/fix_qeq_reax.txt
View File

@ -8,17 +8,19 @@
fix qeq/reax command :h3
fix qeq/reax/kk command :h3
fix qeq/reax/omp command :h3
[Syntax:]
fix ID group-ID qeq/reax Nevery cutlo cuthi tolerance params :pre
fix ID group-ID qeq/reax Nevery cutlo cuthi tolerance params args :pre
ID, group-ID are documented in "fix"_fix.html command
qeq/reax = style name of this fix command
Nevery = perform QEq every this many steps
cutlo,cuthi = lo and hi cutoff for Taper radius
tolerance = precision to which charges will be equilibrated
params = reax/c or a filename :ul
params = reax/c or a filename
args = {dual} (optional) :ul
[Examples:]
@ -59,6 +61,10 @@ potential file, except that eta is defined here as twice the eta value
in the ReaxFF file. Note that unlike the rest of LAMMPS, the units
of this fix are hard-coded to be A, eV, and electronic charge.
The optional {dual} keyword allows to perform the optimization
of the S and T matrices in parallel. This is only supported for
the {qeq/reax/omp} style. Otherwise they are processed separately.
[Restart, fix_modify, output, run start/stop, minimize info:]
No information about this fix is written to "binary restart

65
doc/src/fix_rigid.txt
View File

@ -31,11 +31,12 @@ bodystyle = {single} or {molecule} or {group} :l
groupID1, groupID2, ... = list of N group IDs :pre
zero or more keyword/value pairs may be appended :l
keyword = {langevin} or {temp} or {iso} or {aniso} or {x} or {y} or {z} or {couple} or {tparam} or {pchain} or {dilate} or {force} or {torque} or {infile} :l
keyword = {langevin} or {reinit} or {temp} or {iso} or {aniso} or {x} or {y} or {z} or {couple} or {tparam} or {pchain} or {dilate} or {force} or {torque} or {infile} :l
{langevin} values = Tstart Tstop Tperiod seed
Tstart,Tstop = desired temperature at start/stop of run (temperature units)
Tdamp = temperature damping parameter (time units)
seed = random number seed to use for white noise (positive integer)
{reinit} = {yes} or {no}
{temp} values = Tstart Tstop Tdamp
Tstart,Tstop = desired temperature at start/stop of run (temperature units)
Tdamp = temperature damping parameter (time units)
@ -68,10 +69,10 @@ keyword = {langevin} or {temp} or {iso} or {aniso} or {x} or {y} or {z} or {coup
[Examples:]
fix 1 clump rigid single
fix 1 clump rigid single reinit yes
fix 1 clump rigid/small molecule
fix 1 clump rigid single force 1 off off on langevin 1.0 1.0 1.0 428984
fix 1 polychains rigid/nvt molecule temp 1.0 1.0 5.0
fix 1 polychains rigid/nvt molecule temp 1.0 1.0 5.0 reinit no
fix 1 polychains rigid molecule force 1*5 off off off force 6*10 off off on
fix 1 polychains rigid/small molecule langevin 1.0 1.0 1.0 428984
fix 2 fluid rigid group 3 clump1 clump2 clump3 torque * off off off
@ -87,7 +88,12 @@ means that each timestep the total force and torque on each rigid body
is computed as the sum of the forces and torques on its constituent
particles. The coordinates, velocities, and orientations of the atoms
in each body are then updated so that the body moves and rotates as a
single entity.
single entity. This is implemented by creating internal data structures
for each rigid body and performing time integration on these data
structures. Positions, velocities, and orientations of the constituent
particles are regenerated from the rigid body data structures in every
time step. This restricts which operations and fixes can be applied to
rigid bodies. See below for a detailed discussion.
Examples of large rigid bodies are a colloidal particle, or portions
of a biomolecule such as a protein.
@ -148,8 +154,9 @@ differences may accumulate to produce divergent trajectories.
NOTE: You should not update the atoms in rigid bodies via other
time-integration fixes (e.g. "fix nve"_fix_nve.html, "fix
nvt"_fix_nh.html, "fix npt"_fix_nh.html), or you will be integrating
their motion more than once each timestep. When performing a hybrid
nvt"_fix_nh.html, "fix npt"_fix_nh.html, "fix move"_fix_move.html),
or you will have conflicting updates to positions and velocities
resulting in unphysical behavior in most cases. When performing a hybrid
simulation with some atoms in rigid bodies, and some not, a separate
time integration fix like "fix nve"_fix_nve.html or "fix
nvt"_fix_nh.html should be used for the non-rigid particles.
@ -165,23 +172,29 @@ setting the force on them to 0.0 (via the "fix
setforce"_fix_setforce.html command), and integrating them as usual
(e.g. via the "fix nve"_fix_nve.html command).
NOTE: The aggregate properties of each rigid body are calculated one
time at the start of the first simulation run after these fixes are
specified. The properties include the position and velocity of the
center-of-mass of the body, its moments of inertia, and its angular
momentum. This is done using the properties of the constituent atoms
of the body at that point in time (or see the {infile} keyword
option). Thereafter, changing properties of individual atoms in the
body will have no effect on a rigid body's dynamics, unless they
affect the "pair_style"_pair_style.html interactions that individual
particles are part of. For example, you might think you could
displace the atoms in a body or add a large velocity to each atom in a
body to make it move in a desired direction before a 2nd run is
IMPORTANT NOTE: The aggregate properties of each rigid body are
calculated at the start of a simulation run and are maintained in
internal data structures. The properties include the position and
velocity of the center-of-mass of the body, its moments of inertia, and
its angular momentum. This is done using the properties of the
constituent atoms of the body at that point in time (or see the {infile}
keyword option). Thereafter, changing these properties of individual
atoms in the body will have no effect on a rigid body's dynamics, unless
they effect any computation of per-atom forces or torques. If the
keyword {reinit} is set to {yes} (the default), the rigid body data
structures will be recreated at the beginning of each {run} command;
if the keyword {reinit} is set to {no}, the rigid body data structures
will be built only at the very first {run} command and maintained for
as long as the rigid fix is defined. For example, you might think you
could displace the atoms in a body or add a large velocity to each atom
in a body to make it move in a desired direction before a 2nd run is
performed, using the "set"_set.html or
"displace_atoms"_displace_atoms.html or "velocity"_velocity.html
command. But these commands will not affect the internal attributes
of the body, and the position and velocity of individual atoms in the
body will be reset when time integration starts.
commands. But these commands will not affect the internal attributes
of the body unless {reinit} is set to {yes}. With {reinit} set to {no}
(or using the {infile} option, which implies {reinit} {no}) the position
and velocity of individual atoms in the body will be reset when time
integration starts again.
:line
@ -401,6 +414,14 @@ couple none :pre
The keyword/value option pairs are used in the following ways.
The {reinit} keyword determines, whether the rigid body properties
are reinitialized between run commands. With the option {yes} (the
default) this is done, with the option {no} this is not done. Turning
off the reinitialization can be helpful to protect rigid bodies against
unphysical manipulations between runs or when properties cannot be
easily recomputed (e.g. when read from a file). When using the {infile}
keyword, the {reinit} option is automatically set to {no}.
The {langevin} and {temp} and {tparam} keywords perform thermostatting
of the rigid bodies, altering both their translational and rotational
degrees of freedom. What is meant by "temperature" of a collection of
@ -778,7 +799,7 @@ exclude, "fix shake"_fix_shake.html
The option defaults are force * on on on and torque * on on on,
meaning all rigid bodies are acted on by center-of-mass force and
torque. Also Tchain = Pchain = 10, Titer = 1, Torder = 3.
torque. Also Tchain = Pchain = 10, Titer = 1, Torder = 3, reinit = yes.
:line

2
doc/src/lammps.book
View File

@ -301,6 +301,7 @@ compute_centro_atom.html
compute_chunk_atom.html
compute_cluster_atom.html
compute_cna_atom.html
compute_cnp_atom.html
compute_com.html
compute_com_chunk.html
compute_contact_atom.html
@ -446,7 +447,6 @@ pair_lj96.html
pair_lj_cubic.html
pair_lj_expand.html
pair_lj_long.html
pair_lj_sf.html
pair_lj_smooth.html
pair_lj_smooth_linear.html
pair_lj_soft.html

7
doc/src/manifolds.txt
View File

@ -24,14 +24,15 @@ to the relevant fixes.
{manifold} @ {parameters} @ {equation} @ {description}
cylinder @ R @ x^2 + y^2 - R^2 = 0 @ Cylinder along z-axis, axis going through (0,0,0)
cylinder_dent @ R l a @ x^2 + y^2 - r(z)^2 = 0, r(x) = R if | z | > l, r(z) = R - a*(1 + cos(z/l))/2 otherwise @ A cylinder with a dent around z = 0
dumbbell @ a A B c @ -( x^2 + y^2 ) * (a^2 - z^2/c^2) * ( 1 + (A*sin(B*z^2))^4) = 0 @ A dumbbell @
dumbbell @ a A B c @ -( x^2 + y^2 ) + (a^2 - z^2/c^2) * ( 1 + (A*sin(B*z^2))^4) = 0 @ A dumbbell
ellipsoid @ a b c @ (x/a)^2 + (y/b)^2 + (z/c)^2 = 0 @ An ellipsoid
gaussian_bump @ A l rc1 rc2 @ if( x < rc1) -z + A * exp( -x^2 / (2 l^2) ); else if( x < rc2 ) -z + a + b*x + c*x^2 + d*x^3; else z @ A Gaussian bump at x = y = 0, smoothly tapered to a flat plane z = 0.
plane @ a b c x0 y0 z0 @ a*(x-x0) + b*(y-y0) + c*(z-z0) = 0 @ A plane with normal (a,b,c) going through point (x0,y0,z0)
plane_wiggle @ a w @ z - a*sin(w*x) = 0 @ A plane with a sinusoidal modulation on z along x.
sphere @ R @ x^2 + y^2 + z^2 - R^2 = 0 @ A sphere of radius R
supersphere @ R q @ | x |^q + | y |^q + | z |^q - R^q = 0 @ A supersphere of hyperradius R
spine @ a, A, B, B2, c @ -(x^2 + y^2)*(a^2 - z^2/f(z)^2)*(1 + (A*sin(g(z)*z^2))^4), f(z) = c if z > 0, 1 otherwise; g(z) = B if z > 0, B2 otherwise @ An approximation to a dendtritic spine
spine_two @ a, A, B, B2, c @ -(x^2 + y^2)*(a^2 - z^2/f(z)^2)*(1 + (A*sin(g(z)*z^2))^2), f(z) = c if z > 0, 1 otherwise; g(z) = B if z > 0, B2 otherwise @ Another approximation to a dendtritic spine
spine @ a, A, B, B2, c @ -(x^2 + y^2) + (a^2 - z^2/f(z)^2)*(1 + (A*sin(g(z)*z^2))^4), f(z) = c if z > 0, 1 otherwise; g(z) = B if z > 0, B2 otherwise @ An approximation to a dendtritic spine
spine_two @ a, A, B, B2, c @ -(x^2 + y^2) + (a^2 - z^2/f(z)^2)*(1 + (A*sin(g(z)*z^2))^2), f(z) = c if z > 0, 1 otherwise; g(z) = B if z > 0, B2 otherwise @ Another approximation to a dendtritic spine
thylakoid @ wB LB lB @ Various, see "(Paquay)"_#Paquay1 @ A model grana thylakoid consisting of two block-like compartments connected by a bridge of width wB, length LB and taper length lB
torus @ R r @ (R - sqrt( x^2 + y^2 ) )^2 + z^2 - r^2 @ A torus with large radius R and small radius r, centered on (0,0,0) :tb(s=@)

217
doc/src/neb.txt
View File

@ -10,7 +10,7 @@ neb command :h3
[Syntax:]
neb etol ftol N1 N2 Nevery file-style arg :pre
neb etol ftol N1 N2 Nevery file-style arg keyword :pre
etol = stopping tolerance for energy (energy units) :ulb,l
ftol = stopping tolerance for force (force units) :l
@ -20,18 +20,21 @@ Nevery = print replica energies and reaction coordinates every this many timeste
file-style = {final} or {each} or {none} :l
{final} arg = filename
filename = file with initial coords for final replica
coords for intermediate replicas are linearly interpolated between first and last replica
coords for intermediate replicas are linearly interpolated
between first and last replica
{each} arg = filename
filename = unique filename for each replica (except first) with its initial coords
{none} arg = no argument
all replicas assumed to already have their initial coords :pre
filename = unique filename for each replica (except first)
with its initial coords
{none} arg = no argument all replicas assumed to already have
their initial coords :pre
keyword = {verbose}
:ule
[Examples:]
neb 0.1 0.0 1000 500 50 final coords.final
neb 0.0 0.001 1000 500 50 each coords.initial.$i
neb 0.0 0.001 1000 500 50 none :pre
neb 0.0 0.001 1000 500 50 none verbose :pre
[Description:]
@ -43,8 +46,8 @@ NEB is a method for finding both the atomic configurations and height
of the energy barrier associated with a transition state, e.g. for an
atom to perform a diffusive hop from one energy basin to another in a
coordinated fashion with its neighbors. The implementation in LAMMPS
follows the discussion in these 3 papers: "(HenkelmanA)"_#HenkelmanA,
"(HenkelmanB)"_#HenkelmanB, and "(Nakano)"_#Nakano3.
follows the discussion in these 4 papers: "(HenkelmanA)"_#HenkelmanA,
"(HenkelmanB)"_#HenkelmanB, "(Nakano)"_#Nakano3 and "(Maras)"_#Maras2.
Each replica runs on a partition of one or more processors. Processor
partitions are defined at run-time using the -partition command-line
@ -70,18 +73,17 @@ I.e. the simulation domain, the number of atoms, the interaction
potentials, and the starting configuration when the neb command is
issued should be the same for every replica.
In a NEB calculation each atom in a replica is connected to the same
atom in adjacent replicas by springs, which induce inter-replica
forces. These forces are imposed by the "fix neb"_fix_neb.html
command, which must be used in conjunction with the neb command. The
group used to define the fix neb command defines the NEB atoms which
are the only ones that inter-replica springs are applied to. If the
group does not include all atoms, then non-NEB atoms have no
inter-replica springs and the forces they feel and their motion is
computed in the usual way due only to other atoms within their
replica. Conceptually, the non-NEB atoms provide a background force
field for the NEB atoms. They can be allowed to move during the NEB
minimization procedure (which will typically induce different
In a NEB calculation each replica is connected to other replicas by
inter-replica nudging forces. These forces are imposed by the "fix
neb"_fix_neb.html command, which must be used in conjunction with the
neb command. The group used to define the fix neb command defines the
NEB atoms which are the only ones that inter-replica springs are
applied to. If the group does not include all atoms, then non-NEB
atoms have no inter-replica springs and the forces they feel and their
motion is computed in the usual way due only to other atoms within
their replica. Conceptually, the non-NEB atoms provide a background
force field for the NEB atoms. They can be allowed to move during the
NEB minimization procedure (which will typically induce different
coordinates for non-NEB atoms in different replicas), or held fixed
using other LAMMPS commands such as "fix setforce"_fix_setforce.html.
Note that the "partition"_partition.html command can be used to invoke
@ -93,33 +95,18 @@ specified in different manners via the {file-style} setting, as
discussed below. Only atoms whose initial coordinates should differ
from the current configuration need be specified.
Conceptually, the initial configuration for the first replica should
be a state with all the atoms (NEB and non-NEB) having coordinates on
one side of the energy barrier. A perfect energy minimum is not
required, since atoms in the first replica experience no spring forces
from the 2nd replica. Thus the damped dynamics minimization will
drive the first replica to an energy minimum if it is not already
there. However, you will typically get better convergence if the
initial state is already at a minimum. For example, for a system with
a free surface, the surface should be fully relaxed before attempting
a NEB calculation.
Likewise, the initial configuration of the final replica should be a
state with all the atoms (NEB and non-NEB) on the other side of the
energy barrier. Again, a perfect energy minimum is not required,
since the atoms in the last replica also experience no spring forces
from the next-to-last replica, and thus the damped dynamics
minimization will drive it to an energy minimum.
Conceptually, the initial and final configurations for the first
replica should be states on either side of an energy barrier.
As explained below, the initial configurations of intermediate
replicas can be atomic coordinates interpolated in a linear fashion
between the first and last replicas. This is often adequate state for
between the first and last replicas. This is often adequate for
simple transitions. For more complex transitions, it may lead to slow
convergence or even bad results if the minimum energy path (MEP, see
below) of states over the barrier cannot be correctly converged to
from such an initial configuration. In this case, you will want to
generate initial states for the intermediate replicas that are
geometrically closer to the MEP and read them in.
from such an initial path. In this case, you will want to generate
initial states for the intermediate replicas that are geometrically
closer to the MEP and read them in.
:line
@ -135,10 +122,11 @@ is assigned to be a fraction of the distance. E.g. if there are 10
replicas, the 2nd replica will assign a position that is 10% of the
distance along a line between the starting and final point, and the
9th replica will assign a position that is 90% of the distance along
the line. Note that this procedure to produce consistent coordinates
across all the replicas, the current coordinates need to be the same
in all replicas. LAMMPS does not check for this, but invalid initial
configurations will likely result if it is not the case.
the line. Note that for this procedure to produce consistent
coordinates across all the replicas, the current coordinates need to
be the same in all replicas. LAMMPS does not check for this, but
invalid initial configurations will likely result if it is not the
case.
NOTE: The "distance" between the starting and final point is
calculated in a minimum-image sense for a periodic simulation box.
@ -150,8 +138,8 @@ interpolation is outside the periodic box, the atom will be wrapped
back into the box when the NEB calculation begins.
For a {file-style} setting of {each}, a filename is specified which is
assumed to be unique to each replica. This can be done by
using a variable in the filename, e.g.
assumed to be unique to each replica. This can be done by using a
variable in the filename, e.g.
variable i equal part
neb 0.0 0.001 1000 500 50 each coords.initial.$i :pre
@ -198,11 +186,10 @@ The minimizer tolerances for energy and force are set by {etol} and
A non-zero {etol} means that the NEB calculation will terminate if the
energy criterion is met by every replica. The energies being compared
to {etol} do not include any contribution from the inter-replica
forces, since these are non-conservative. A non-zero {ftol} means
that the NEB calculation will terminate if the force criterion is met
by every replica. The forces being compared to {ftol} include the
inter-replica forces between an atom and its images in adjacent
replicas.
nudging forces, since these are non-conservative. A non-zero {ftol}
means that the NEB calculation will terminate if the force criterion
is met by every replica. The forces being compared to {ftol} include
the inter-replica nudging forces.
The maximum number of iterations in each stage is set by {N1} and
{N2}. These are effectively timestep counts since each iteration of
@ -220,27 +207,27 @@ finding a good energy barrier. {N1} and {N2} must both be multiples
of {Nevery}.
In the first stage of NEB, the set of replicas should converge toward
the minimum energy path (MEP) of conformational states that transition
over the barrier. The MEP for a barrier is defined as a sequence of
3N-dimensional states that cross the barrier at its saddle point, each
of which has a potential energy gradient parallel to the MEP itself.
The replica states will also be roughly equally spaced along the MEP
due to the inter-replica spring force added by the "fix
neb"_fix_neb.html command.
a minimum energy path (MEP) of conformational states that transition
over a barrier. The MEP for a transition is defined as a sequence of
3N-dimensional states, each of which has a potential energy gradient
parallel to the MEP itself. The configuration of highest energy along
a MEP corresponds to a saddle point. The replica states will also be
roughly equally spaced along the MEP due to the inter-replica nugding
force added by the "fix neb"_fix_neb.html command.
In the second stage of NEB, the replica with the highest energy
is selected and the inter-replica forces on it are converted to a
force that drives its atom coordinates to the top or saddle point of
the barrier, via the barrier-climbing calculation described in
In the second stage of NEB, the replica with the highest energy is
selected and the inter-replica forces on it are converted to a force
that drives its atom coordinates to the top or saddle point of the
barrier, via the barrier-climbing calculation described in
"(HenkelmanB)"_#HenkelmanB. As before, the other replicas rearrange
themselves along the MEP so as to be roughly equally spaced.
When both stages are complete, if the NEB calculation was successful,
one of the replicas should be an atomic configuration at the top or
saddle point of the barrier, the potential energies for the set of
replicas should represent the energy profile of the barrier along the
MEP, and the configurations of the replicas should be a sequence of
configurations along the MEP.
the configurations of the replicas should be along (close to) the MEP
and the replica with the highest energy should be an atomic
configuration at (close to) the saddle point of the transition. The
potential energies for the set of replicas represents the energy
profile of the transition along the MEP.
:line
@ -284,9 +271,9 @@ ID2 x2 y2 z2
...
IDN xN yN zN :pre
The fields are the atom ID, followed by the x,y,z coordinates.
The lines can be listed in any order. Additional trailing information
on the line is OK, such as a comment.
The fields are the atom ID, followed by the x,y,z coordinates. The
lines can be listed in any order. Additional trailing information on
the line is OK, such as a comment.
Note that for a typical NEB calculation you do not need to specify
initial coordinates for very many atoms to produce differing starting
@ -310,38 +297,54 @@ this case), the print-out to the screen and master log.lammps file
contains a line of output, printed once every {Nevery} timesteps. It
contains the timestep, the maximum force per replica, the maximum
force per atom (in any replica), potential gradients in the initial,
final, and climbing replicas, the forward and backward energy barriers,
the total reaction coordinate (RDT), and the normalized reaction
coordinate and potential energy of each replica.
final, and climbing replicas, the forward and backward energy
barriers, the total reaction coordinate (RDT), and the normalized
reaction coordinate and potential energy of each replica.
The "maximum force per replica" is
the two-norm of the 3N-length force vector for the atoms in each
replica, maximized across replicas, which is what the {ftol} setting
is checking against. In this case, N is all the atoms in each
replica. The "maximum force per atom" is the maximum force component
of any atom in any replica. The potential gradients are the two-norm
of the 3N-length force vector solely due to the interaction potential i.e.
without adding in inter-replica forces. Note that inter-replica forces
are zero in the initial and final replicas, and only affect
the direction in the climbing replica. For this reason, the "maximum
force per replica" is often equal to the potential gradient in the
climbing replica. In the first stage of NEB, there is no climbing
replica, and so the potential gradient in the highest energy replica
is reported, since this replica will become the climbing replica
in the second stage of NEB.
The "maximum force per replica" is the two-norm of the 3N-length force
vector for the atoms in each replica, maximized across replicas, which
is what the {ftol} setting is checking against. In this case, N is
all the atoms in each replica. The "maximum force per atom" is the
maximum force component of any atom in any replica. The potential
gradients are the two-norm of the 3N-length force vector solely due to
the interaction potential i.e. without adding in inter-replica
forces.
The "reaction coordinate" (RD) for each
replica is the two-norm of the 3N-length vector of distances between
its atoms and the preceding replica's atoms, added to the RD of the
preceding replica. The RD of the first replica RD1 = 0.0;
the RD of the final replica RDN = RDT, the total reaction coordinate.
The normalized RDs are divided by RDT,
so that they form a monotonically increasing sequence
from zero to one. When computing RD, N only includes the atoms
being operated on by the fix neb command.
The "reaction coordinate" (RD) for each replica is the two-norm of the
3N-length vector of distances between its atoms and the preceding
replica's atoms, added to the RD of the preceding replica. The RD of
the first replica RD1 = 0.0; the RD of the final replica RDN = RDT,
the total reaction coordinate. The normalized RDs are divided by RDT,
so that they form a monotonically increasing sequence from zero to
one. When computing RD, N only includes the atoms being operated on by
the fix neb command.
The forward (reverse) energy barrier is the potential energy of the
highest replica minus the energy of the first (last) replica.
Supplementary informations for all replicas can be printed out to the
screen and master log.lammps file by adding the verbose keyword. These
informations include the following. The "path angle" (pathangle) for
the replica i which is the angle between the 3N-length vectors (Ri-1 -
Ri) and (Ri+1 - Ri) (where Ri is the atomic coordinates of replica
i). A "path angle" of 180 indicates that replicas i-1, i and i+1 are
aligned. "angletangrad" is the angle between the 3N-length tangent
vector and the 3N-length force vector at image i. The tangent vector
is calculated as in "(HenkelmanA)"_#HenkelmanA for all intermediate
replicas and at R2 - R1 and RM - RM-1 for the first and last replica,
respectively. "anglegrad" is the angle between the 3N-length energy
gradient vector of replica i and that of replica i+1. It is not
defined for the final replica and reads nan. gradV is the norm of the
energy gradient of image i. ReplicaForce is the two-norm of the
3N-length force vector (including nudging forces) for replica i.
MaxAtomForce is the maximum force component of any atom in replica i.
When a NEB calculation does not converge properly, these suplementary
informations can help understanding what is going wrong. For instance
when the path angle becomes accute the definition of tangent used in
the NEB calculation is questionable and the NEB cannot may diverge
"(Maras)"_#Maras2.
The forward (reverse) energy barrier is the potential energy of the highest
replica minus the energy of the first (last) replica.
When running on multiple partitions, LAMMPS produces additional log
files for each partition, e.g. log.lammps.0, log.lammps.1, etc. For a
@ -396,12 +399,16 @@ This command can only be used if LAMMPS was built with the REPLICA
package. See the "Making LAMMPS"_Section_start.html#start_3 section
for more info on packages.
:line
[Related commands:]
"prd"_prd.html, "temper"_temper.html, "fix
langevin"_fix_langevin.html, "fix viscous"_fix_viscous.html
"prd"_prd.html, "temper"_temper.html, "fix langevin"_fix_langevin.html,
"fix viscous"_fix_viscous.html
[Default:] none
[Default:]
none
:line
@ -414,3 +421,7 @@ langevin"_fix_langevin.html, "fix viscous"_fix_viscous.html
:link(Nakano3)
[(Nakano)] Nakano, Comp Phys Comm, 178, 280-289 (2008).
:link(Maras2)
[(Maras)] Maras, Trushin, Stukowski, Ala-Nissila, Jonsson,
Comp Phys Comm, 205, 13-21 (2016)

6
doc/src/package.txt
View File

@ -574,9 +574,9 @@ is used. If it is not used, you must invoke the package intel
command in your input script or or via the "-pk intel" "command-line
switch"_Section_start.html#start_7.
For the KOKKOS package, the option defaults neigh = full, neigh/qeq
= full, newton = off, binsize = 0.0, and comm = device. These settings
are made automatically by the required "-k on" "command-line
For the KOKKOS package, the option defaults neigh = full,
neigh/qeq = full, newton = off, binsize = 0.0, and comm = device.
These settings are made automatically by the required "-k on" "command-line
switch"_Section_start.html#start_7. You can change them bu using the
package kokkos command in your input script or via the "-pk kokkos"
"command-line switch"_Section_start.html#start_7.

114
doc/src/pair_lj_sf.txt
View File

@ -1,114 +0,0 @@
"LAMMPS WWW Site"_lws - "LAMMPS Documentation"_ld - "LAMMPS Commands"_lc :c
:link(lws,http://lammps.sandia.gov)
:link(ld,Manual.html)
:link(lc,Section_commands.html#comm)
:line
pair_style lj/sf command :h3
pair_style lj/sf/omp command :h3
[Syntax:]
pair_style lj/sf cutoff :pre
cutoff = global cutoff for Lennard-Jones interactions (distance units) :ul
[Examples:]
pair_style lj/sf 2.5
pair_coeff * * 1.0 1.0
pair_coeff 1 1 1.0 1.0 3.0 :pre
[Description:]
Style {lj/sf} computes a truncated and force-shifted LJ interaction
(Shifted Force Lennard-Jones), so that both the potential and the
force go continuously to zero at the cutoff "(Toxvaerd)"_#Toxvaerd:
:c,image(Eqs/pair_lj_sf.jpg)
The following coefficients must be defined for each pair of atoms
types via the "pair_coeff"_pair_coeff.html command as in the examples
above, or in the data file or restart files read by the
"read_data"_read_data.html or "read_restart"_read_restart.html
commands, or by mixing as described below:
epsilon (energy units)
sigma (distance units)
cutoff (distance units) :ul
The last coefficient is optional. If not specified, the global
LJ cutoff specified in the pair_style command is used.
:line
Styles with a {gpu}, {intel}, {kk}, {omp}, or {opt} suffix are
functionally the same as the corresponding style without the suffix.
They have been optimized to run faster, depending on your available
hardware, as discussed in "Section 5"_Section_accelerate.html
of the manual. The accelerated styles take the same arguments and
should produce the same results, except for round-off and precision
issues.
These accelerated styles are part of the GPU, USER-INTEL, KOKKOS,
USER-OMP and OPT packages, respectively. They are only enabled if
LAMMPS was built with those packages. See the "Making
LAMMPS"_Section_start.html#start_3 section for more info.
You can specify the accelerated styles explicitly in your input script
by including their suffix, or you can use the "-suffix command-line
switch"_Section_start.html#start_7 when you invoke LAMMPS, or you can
use the "suffix"_suffix.html command in your input script.
See "Section 5"_Section_accelerate.html of the manual for
more instructions on how to use the accelerated styles effectively.
:line
[Mixing, shift, table, tail correction, restart, rRESPA info]:
For atom type pairs I,J and I != J, the epsilon and sigma
coefficients and cutoff distance for this pair style can be mixed.
Rin is a cutoff value and is mixed like the cutoff. The
default mix value is {geometric}. See the "pair_modify" command for
details.
The "pair_modify"_pair_modify.html shift option is not relevant for
this pair style, since the pair interaction goes to 0.0 at the cutoff.
The "pair_modify"_pair_modify.html table option is not relevant
for this pair style.
This pair style does not support the "pair_modify"_pair_modify.html
tail option for adding long-range tail corrections to energy and
pressure, since the energy of the pair interaction is smoothed to 0.0
at the cutoff.
This pair style writes its information to "binary restart
files"_restart.html, so pair_style and pair_coeff commands do not need
to be specified in an input script that reads a restart file.
This pair style can only be used via the {pair} keyword of the
"run_style respa"_run_style.html command. It does not support the
{inner}, {middle}, {outer} keywords.
:line
[Restrictions:]
This pair style is part of the USER-MISC package. It is only enabled
if LAMMPS was built with that package. See the "Making
LAMMPS"_Section_start.html#start_3 section for more info.
[Related commands:]
"pair_coeff"_pair_coeff.html
[Default:] none
:line
:link(Toxvaerd)
[(Toxvaerd)] Toxvaerd, Dyre, J Chem Phys, 134, 081102 (2011).

31
doc/src/pair_lj_smooth_linear.txt
View File

@ -11,26 +11,26 @@ pair_style lj/smooth/linear/omp command :h3
[Syntax:]
pair_style lj/smooth/linear Rc :pre
pair_style lj/smooth/linear cutoff :pre
Rc = cutoff for lj/smooth/linear interactions (distance units) :ul
cutoff = global cutoff for Lennard-Jones interactions (distance units) :ul
[Examples:]
pair_style lj/smooth/linear 5.456108274435118
pair_coeff * * 0.7242785984051078 2.598146797350056
pair_coeff 1 1 20.0 1.3 9.0 :pre
pair_style lj/smooth/linear 2.5
pair_coeff * * 1.0 1.0
pair_coeff 1 1 0.3 3.0 9.0 :pre
[Description:]
Style {lj/smooth/linear} computes a LJ interaction that combines the
standard 12/6 Lennard-Jones function and subtracts a linear term that
includes the cutoff distance Rc, as in this formula:
Style {lj/smooth/linear} computes a truncated and force-shifted LJ
interaction (aka Shifted Force Lennard-Jones) that combines the
standard 12/6 Lennard-Jones function and subtracts a linear term based
on the cutoff distance, so that both, the potential and the force, go
continuously to zero at the cutoff Rc "(Toxvaerd)"_#Toxvaerd:
:c,image(Eqs/pair_lj_smooth_linear.jpg)
At the cutoff Rc, the energy and force (its 1st derivative) will be 0.0.
The following coefficients must be defined for each pair of atoms
types via the "pair_coeff"_pair_coeff.html command as in the examples
above, or in the data file or restart files read by the
@ -41,8 +41,8 @@ epsilon (energy units)
sigma (distance units)
cutoff (distance units) :ul
The last coefficient is optional. If not specified, the global value
for Rc is used.
The last coefficient is optional. If not specified, the global
LJ cutoff specified in the pair_style command is used.
:line
@ -76,10 +76,11 @@ and cutoff distance can be mixed. The default mix value is geometric.
See the "pair_modify" command for details.
This pair style does not support the "pair_modify"_pair_modify.html
shift option for the energy of the pair interaction.
shift option for the energy of the pair interaction, since it goes
to 0.0 at the cutoff by construction.
The "pair_modify"_pair_modify.html table option is not relevant for
this pair style.
The "pair_modify"_pair_modify.html table option is not relevant
for this pair style.
This pair style does not support the "pair_modify"_pair_modify.html
tail option for adding long-range tail corrections to energy and

2
doc/src/pair_morse.txt
View File

@ -36,7 +36,7 @@ args = list of arguments for a particular style :ul
pair_style morse 2.5
pair_style morse/smooth/linear 2.5
pair_coeff * * 100.0 2.0 1.5
pair_coeff 1 1 100.0 2.0 1.5 3.0
pair_coeff 1 1 100.0 2.0 1.5 3.0 :pre
pair_style morse/soft 4 0.9 10.0
pair_coeff * * 100.0 2.0 1.5 1.0

9
doc/src/pair_python.txt
View File

@ -74,7 +74,7 @@ placeholders for atom types that will be used with other potentials.
The python potential file has to start with the following code:
from __future__ import print_function
#
class LAMMPSPairPotential(object):
def __init__(self):
self.pmap=dict()
@ -163,9 +163,10 @@ pair_write 1 1 2000 rsq 0.01 2.5 lj1_lj2.table lj :pre
Note that it is strongly recommended to try to [delete] the potential
table file before generating it. Since the {pair_write} command will
always append to a table file, which pair style table will use the
first match. Thus when changing the potential function in the python
class, the table pair style will still read the old variant.
always [append] to a table file, while pair style table will use the
[first match]. Thus when changing the potential function in the python
class, the table pair style will still read the old variant unless the
table file is first deleted.
After switching the pair style to {table}, the potential tables need
to be assigned to the LAMMPS atom types like this:

1
doc/src/pair_reaxc.txt
View File

@ -8,6 +8,7 @@
pair_style reax/c command :h3
pair_style reax/c/kk command :h3
pair_style reax/c/omp command :h3
[Syntax:]

16
doc/src/pair_snap.txt
View File

@ -10,7 +10,8 @@ pair_style snap command :h3
[Syntax:]
pair_style snap :pre
pair_style snap
:pre
[Examples:]
@ -19,11 +20,11 @@ pair_coeff * * InP.snapcoeff In P InP.snapparam In In P P :pre
[Description:]
Style {snap} computes interactions
Pair style {snap} computes interactions
using the spectral neighbor analysis potential (SNAP)
"(Thompson)"_#Thompson20142. Like the GAP framework of Bartok et al.
"(Bartok2010)"_#Bartok20102, "(Bartok2013)"_#Bartok2013
it uses bispectrum components
which uses bispectrum components
to characterize the local neighborhood of each atom
in a very general way. The mathematical definition of the
bispectrum calculation used by SNAP is identical
@ -139,10 +140,15 @@ The default values for these keywords are
{rmin0} = 0.0
{diagonalstyle} = 3
{switchflag} = 0
{bzeroflag} = 1 :ul
{bzeroflag} = 1
{quadraticflag} = 1 :ul
Detailed definitions of these keywords are given on the "compute
Detailed definitions for all the keywords are given on the "compute
sna/atom"_compute_sna_atom.html doc page.
If {quadraticflag} is set to 1, then the SNAP energy expression includes the quadratic term,
0.5*B^t.alpha.B, where alpha is a symmetric {K} by {K} matrix.
The SNAP element file should contain {K}({K}+1)/2 additional coefficients
for each element, the upper-triangular elements of alpha.
:line

1
doc/src/pair_vashishta.txt
View File

@ -7,6 +7,7 @@
:line
pair_style vashishta command :h3
pair_style vashishta/gpu command :h3
pair_style vashishta/omp command :h3
pair_style vashishta/kk command :h3
pair_style vashishta/table command :h3

2
doc/src/pair_zero.txt
View File

@ -14,7 +14,7 @@ pair_style zero cutoff {nocoeff} :pre
zero = style name of this pair style
cutoff = global cutoff (distance units)
nocoeff = ignore all pair_coeff parameters (optional) :l
nocoeff = ignore all pair_coeff parameters (optional) :ul
[Examples:]

1
doc/src/pairs.txt
View File

@ -49,7 +49,6 @@ Pair Styles :h1
pair_lj_cubic
pair_lj_expand
pair_lj_long
pair_lj_sf
pair_lj_smooth
pair_lj_smooth_linear
pair_lj_soft

6
doc/src/set.txt
View File

@ -80,6 +80,7 @@ keyword = {type} or {type/fraction} or {mol} or {x} or {y} or {z} or \
value can be an atom-style variable (see below)
{image} nx ny nz
nx,ny,nz = which periodic image of the simulation box the atom is in
any of nx,ny,nz can be an atom-style variable (see below)
{bond} value = bond type for all bonds between selected atoms
{angle} value = angle type for all angles between selected atoms
{dihedral} value = dihedral type for all dihedrals between selected atoms
@ -363,9 +364,8 @@ A value of -1 means subtract 1 box length to get the true value.
LAMMPS updates these flags as atoms cross periodic boundaries during
the simulation. The flags can be output with atom snapshots via the
"dump"_dump.html command. If a value of NULL is specified for any of
nx,ny,nz, then the current image value for that dimension is
unchanged. For non-periodic dimensions only a value of 0 can be
specified. This keyword does not allow use of atom-style variables.
nx,ny,nz, then the current image value for that dimension is unchanged.
For non-periodic dimensions only a value of 0 can be specified.
This command can be useful after a system has been equilibrated and
atoms have diffused one or more box lengths in various directions.
This command can then reset the image values for atoms so that they

8
doc/src/special_bonds.txt
View File

@ -65,7 +65,13 @@ sense to define permanent bonds between atoms that interact via these
potentials, though such bonds may exist elsewhere in your system,
e.g. when using the "pair_style hybrid"_pair_hybrid.html command.
Thus LAMMPS ignores special_bonds settings when manybody potentials
are calculated.
are calculated. Please note, that the existence of explicit bonds
for atoms that are described by a manybody potential will alter the
neigborlist and thus can render the computation of those interactions
invalid, since those pairs are not only used to determine direct
pairwise interactions but also neighbors of neighbors and more.
The recommended course of action is to remove such bonds, or - if
that is not possible - use a special bonds setting of 1.0 1.0 1.0.
NOTE: Unlike some commands in LAMMPS, you cannot use this command
multiple times in an incremental fashion: e.g. to first set the LJ

1
doc/src/tutorial_pylammps.txt
View File

@ -10,6 +10,7 @@ PyLammps Tutorial :h1
<!-- RST
.. contents::
END_RST -->
Overview :h2

2
examples/COUPLE/simple/simple.cpp
View File

@ -153,7 +153,7 @@ int main(int narg, char **arg)
for (int i = 0; i < natoms; i++) type[i] = 1;
lmp->input->one("delete_atoms group all");
lammps_create_atoms(lmp,natoms,NULL,type,x,v);
lammps_create_atoms(lmp,natoms,NULL,type,x,v,NULL,0);
lmp->input->one("run 10");
}

2
examples/USER/cgdna/util/generate.py
View File

@ -14,7 +14,7 @@
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Oliver Henrich (EPCC, University of Edinburgh)
Contributing author: Oliver Henrich (University of Strathclyde, Glasgow)
------------------------------------------------------------------------- */
"""

30009
examples/USER/misc/cnp/Cu_Mishin1.eam Normal file
View File

File diff suppressed because it is too large Load Diff

51
examples/USER/misc/cnp/in.cnp Normal file
View File

@ -0,0 +1,51 @@
# Generation and relaxation of a partial dislocation in Cu perfect FCC crystal
# Initialization
units metal
boundary p p p
atom_style atomic
# create simulation box and system
lattice fcc 3.615 origin 0.01 0.01 0.01 orient x -1 -1 2 orient y 1 1 1 orient z -1 1 0
region mdbox block 0 3 0.0 14.0 0 84 units lattice
region system block 0 3 1.1 13.1 0 84 units lattice
create_box 2 mdbox
create_atoms 1 region system
# Define atoms mass and force field
mass * 63.54
pair_style eam/alloy
pair_coeff * * Cu_Mishin1.eam Cu Cu
# Delete a plane of atoms along the z direction to generate a partial dislocation
region dislocation_atoms block 0 3 7 14 41.9 42.1 units lattice
delete_atoms region dislocation_atoms
region quarter_up block 0 3 7 11 0 84 units lattice
group middle region quarter_up
# specify simulation parameters
timestep 0.004
# Relax configuration using conjugate gradient
#min_style cg
#minimize 1.0e-4 1.0e-6 100 1000
# Setup calculations
compute 1 all cnp/atom 3.086
compute 2 all cna/atom 3.086
compute 3 all centro/atom fcc
compute 4 all coord/atom cutoff 3.086
dump 1 all custom 100 dump.lammpstrj id type xu yu zu c_1 c_2 c_3 c_4
### Set up thermo display
thermo 10
thermo_style custom step atoms temp press pe ke etotal
# Relax the system performing a langevin dynamics (freeze motion along y 111 direction)
fix 1 all nve
fix 2 all langevin 50 1 0.1 699483
fix 3 all setforce NULL 0.0 NULL
fix 4 middle setforce 0.0 0.0 0.0
run 100
unfix 4
run 200

185
examples/USER/misc/cnp/log.31May17.cnp.g++.4 Normal file
View File

@ -0,0 +1,185 @@
LAMMPS (19 May 2017)
OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (../comm.cpp:90)
using 1 OpenMP thread(s) per MPI task
# Generation and relaxation of a partial dislocation in Cu perfect FCC crystal
# Initialization
units metal
boundary p p p
atom_style atomic
# create simulation box and system
lattice fcc 3.615 origin 0.01 0.01 0.01 orient x -1 -1 2 orient y 1 1 1 orient z -1 1 0
Lattice spacing in x,y,z = 5.90327 6.26136 5.11238
region mdbox block 0 3 0.0 14.0 0 84 units lattice
region system block 0 3 1.1 13.1 0 84 units lattice
create_box 2 mdbox
Created orthogonal box = (0 0 0) to (17.7098 87.6591 429.44)
1 by 1 by 4 MPI processor grid
create_atoms 1 region system
Created 48384 atoms
# Define atoms mass and force field
mass * 63.54
pair_style eam/alloy
pair_coeff * * Cu_Mishin1.eam Cu Cu
# Delete a plane of atoms along the z direction to generate a partial dislocation
region dislocation_atoms block 0 3 7 14 41.9 42.1 units lattice
delete_atoms region dislocation_atoms
Deleted 76 atoms, new total = 48308
region quarter_up block 0 3 7 11 0 84 units lattice
group middle region quarter_up
16080 atoms in group middle
# specify simulation parameters
timestep 0.004
# Relax configuration using conjugate gradient
#min_style cg
#minimize 1.0e-4 1.0e-6 100 1000
# Setup calculations
compute 1 all cnp/atom 3.086
compute 2 all cna/atom 3.086
compute 3 all centro/atom fcc
compute 4 all coord/atom cutoff 3.086
dump 1 all custom 100 dump.lammpstrj id type xu yu zu c_1 c_2 c_3 c_4
### Set up thermo display
thermo 10
thermo_style custom step atoms temp press pe ke etotal
# Relax the system performing a langevin dynamics (freeze motion along y 111 direction)
fix 1 all nve
fix 2 all langevin 50 1 0.1 699483
fix 3 all setforce NULL 0.0 NULL
fix 4 middle setforce 0.0 0.0 0.0
run 100
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 7.50679
ghost atom cutoff = 7.50679
binsize = 3.75339, bins = 5 24 115
5 neighbor lists, perpetual/occasional/extra = 1 4 0
(1) pair eam/alloy, perpetual
attributes: half, newton on
pair build: half/bin/atomonly/newton
stencil: half/bin/3d/newton
bin: standard
(2) compute cnp/atom, occasional
attributes: full, newton on
pair build: full/bin/atomonly
stencil: full/bin/3d
bin: standard
(3) compute cna/atom, occasional
attributes: full, newton on
pair build: full/bin/atomonly
stencil: full/bin/3d
bin: standard
(4) compute centro/atom, occasional
attributes: full, newton on
pair build: full/bin/atomonly
stencil: full/bin/3d
bin: standard
(5) compute coord/atom, occasional
attributes: full, newton on
pair build: full/bin/atomonly
stencil: full/bin/3d
bin: standard
Per MPI rank memory allocation (min/avg/max) = 45.41 | 45.41 | 45.41 Mbytes
Step Atoms Temp Press PotEng KinEng TotEng
0 48308 0 -3388.0911 -169746.07 0 -169746.07
10 48308 7.35092 -3091.0864 -169715.96 45.900393 -169670.05
20 48308 9.9162268 -2822.7045 -169678.51 61.918604 -169616.59
30 48308 12.351316 -2726.7195 -169666.35 77.123716 -169589.23
40 48308 13.302856 -2703.586 -169662.9 83.06529 -169579.83
50 48308 12.782228 -2706.8662 -169662.36 79.814401 -169582.55
60 48308 12.198179 -2772.4206 -169670.02 76.167503 -169593.86
70 48308 10.663322 -2841.3384 -169677.48 66.583595 -169610.9
80 48308 9.1169804 -2932.3896 -169687.85 56.927974 -169630.92
90 48308 7.2905076 -3029.9433 -169699.09 45.523167 -169653.56
100 48308 5.4063635 -3139.4496 -169711.65 33.758252 -169677.89
Loop time of 10.9003 on 4 procs for 100 steps with 48308 atoms
Performance: 3.171 ns/day, 7.570 hours/ns, 9.174 timesteps/s
31.8% CPU use with 4 MPI tasks x 1 OpenMP threads
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 9.8764 | 9.9587 | 10.021 | 1.6 | 91.36
Neigh | 0 | 0 | 0 | 0.0 | 0.00
Comm | 0.1232 | 0.18385 | 0.26683 | 12.1 | 1.69
Output | 0.45385 | 0.45451 | 0.45634 | 0.2 | 4.17
Modify | 0.25026 | 0.2537 | 0.25744 | 0.5 | 2.33
Other | | 0.04949 | | | 0.45
Nlocal: 12077 ave 12096 max 12020 min
Histogram: 1 0 0 0 0 0 0 0 0 3
Nghost: 14204 ave 14261 max 14109 min
Histogram: 1 0 0 0 0 1 0 0 0 2
Neighs: 814050 ave 818584 max 809212 min
Histogram: 1 0 0 0 0 2 0 0 0 1
FullNghs: 1.6281e+06 ave 1.63296e+06 max 1.61808e+06 min
Histogram: 1 0 0 0 0 0 1 0 0 2
Total # of neighbors = 6512400
Ave neighs/atom = 134.81
Neighbor list builds = 0
Dangerous builds = 0
unfix 4
run 200
Per MPI rank memory allocation (min/avg/max) = 45.41 | 45.41 | 45.41 Mbytes
Step Atoms Temp Press PotEng KinEng TotEng
100 48308 5.4063635 -3139.4496 -169711.65 33.758252 -169677.89
110 48308 15.260795 -2793.119 -169677.24 95.290993 -169581.95
120 48308 18.548656 -2433.1584 -169624.79 115.82096 -169508.97
130 48308 22.15831 -2276.626 -169604.28 138.36025 -169465.92
140 48308 24.393841 -2208.1771 -169596.16 152.31929 -169443.84
150 48308 24.797558 -2173.3145 -169591.43 154.84016 -169436.59
160 48308 24.73371 -2188.909 -169593.08 154.44148 -169438.64
170 48308 24.128467 -2220.3404 -169596.96 150.66225 -169446.29
180 48308 22.975708 -2275.1244 -169602.72 143.46422 -169459.26
190 48308 21.936324 -2348.3762 -169610.59 136.97413 -169473.61
200 48308 20.516249 -2432.8447 -169619.98 128.10694 -169491.87
210 48308 19.000566 -2510.2915 -169628.58 118.64276 -169509.93
220 48308 17.490407 -2597.299 -169638.24 109.21307 -169529.03
230 48308 16.062482 -2684.1203 -169648.31 100.29687 -169548.01
240 48308 14.360342 -2768.2313 -169657.7 89.668411 -169568.03
250 48308 12.802315 -2852.6965 -169666.99 79.939831 -169587.05
260 48308 11.258205 -2944.4533 -169677.52 70.298142 -169607.23
270 48308 9.6159129 -3038.6304 -169688.06 60.043393 -169628.02
280 48308 7.972425 -3129.0826 -169698.03 49.781176 -169648.25
290 48308 6.3752377 -3219.2054 -169708.23 39.808067 -169668.42
300 48308 4.7374688 -3306.1468 -169718.27 29.58156 -169688.69
Loop time of 23.0164 on 4 procs for 200 steps with 48308 atoms
Performance: 3.003 ns/day, 7.992 hours/ns, 8.689 timesteps/s
31.8% CPU use with 4 MPI tasks x 1 OpenMP threads
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 20.221 | 20.423 | 20.57 | 3.1 | 88.73
Neigh | 0 | 0 | 0 | 0.0 | 0.00
Comm | 0.27748 | 0.42603 | 0.62832 | 21.4 | 1.85
Output | 1.5454 | 1.5473 | 1.5529 | 0.3 | 6.72
Modify | 0.48886 | 0.49773 | 0.50842 | 1.1 | 2.16
Other | | 0.1221 | | | 0.53
Nlocal: 12077 ave 12096 max 12020 min
Histogram: 1 0 0 0 0 0 0 0 0 3
Nghost: 14204 ave 14261 max 14109 min
Histogram: 1 0 0 0 0 1 0 0 0 2
Neighs: 814094 ave 818584 max 809212 min
Histogram: 1 0 0 0 0 2 0 0 0 1
FullNghs: 1.62852e+06 ave 1.63296e+06 max 1.61892e+06 min
Histogram: 1 0 0 0 0 0 0 1 0 2
Total # of neighbors = 6514094
Ave neighs/atom = 134.845
Neighbor list builds = 0
Dangerous builds = 0
Total wall time: 0:00:35

1145
examples/USER/misc/grem/lj-temper/0/log.lammps.0
View File

File diff suppressed because it is too large Load Diff

1145
examples/USER/misc/grem/lj-temper/1/log.lammps.1
View File

File diff suppressed because it is too large Load Diff

1145
examples/USER/misc/grem/lj-temper/2/log.lammps.2
View File

File diff suppressed because it is too large Load Diff

1145
examples/USER/misc/grem/lj-temper/3/log.lammps.3
View File

File diff suppressed because it is too large Load Diff

8
examples/USER/misc/grem/lj-temper/in.gREM-temper
View File

@ -18,13 +18,13 @@ read_data ${rep}/lj.data
#dump dump all xyz 1000 ${rep}/dump.xyz
thermo 10
thermo_style custom step temp pe etotal press vol
timestep 1.0
fix fxnpt all npt temp ${T0} ${T0} 1000.0 iso ${press} ${press} 10000.0
fix fxgREM all grem ${lambda} -.03 -30000 fxnpt
thermo 10
thermo_style custom step temp f_fxgREM pe etotal press vol
thermo_modify press fxgREM_press
timestep 1.0
temper/grem 10000 100 ${lambda} fxgREM fxnpt 10294 98392 #${walker}

177
examples/USER/tally/log.12Jun17.force.1 Normal file
View File

@ -0,0 +1,177 @@
LAMMPS (19 May 2017)
units real
atom_style full
read_data data.spce
orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
1 by 1 by 1 MPI processor grid
reading atoms ...
4500 atoms
scanning bonds ...
2 = max bonds/atom
scanning angles ...
1 = max angles/atom
reading bonds ...
3000 bonds
reading angles ...
1500 angles
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
1 = max # of 1-4 neighbors
2 = max # of special neighbors
pair_style lj/cut/coul/long 12.0 12.0
kspace_style pppm 1.0e-4
pair_coeff 1 1 0.15535 3.166
pair_coeff * 2 0.0000 0.0000
bond_style harmonic
angle_style harmonic
dihedral_style none
improper_style none
bond_coeff 1 1000.00 1.000
angle_coeff 1 100.0 109.47
special_bonds lj/coul 0.0 0.0 1.0
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
2 = max # of special neighbors
neighbor 2.0 bin
fix 1 all shake 0.0001 20 0 b 1 a 1
0 = # of size 2 clusters
0 = # of size 3 clusters
0 = # of size 4 clusters
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 26.54 | 26.54 | 26.54 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 3e-06 on 1 procs for 0 steps with 4500 atoms
group one molecule 1 2
6 atoms in group one
# the following section shows equivalences between using the force/tally compute and other computes and thermo keywords
# compute pairwise force between two molecules and everybody
compute fpa one group/group all pair yes kspace no boundary no
# tally pairwise force between two molecules and the all molecules
compute c1 one force/tally all
# tally the force of all with all (should be zero)
compute c2 all force/tally all
# collect per atom data. only reduce over the first group.
compute one one reduce sum c_c1[1] c_c1[2] c_c1[3]
compute red all reduce sum c_c2[1] c_c2[2] c_c2[3]
# determine magnitude of force
variable fpa equal sqrt(c_fpa[1]*c_fpa[1]+c_fpa[2]*c_fpa[2]+c_fpa[3]*c_fpa[3])
variable for equal sqrt(c_one[1]*c_one[1]+c_one[2]*c_one[2]+c_one[3]*c_one[3])
# round to 10**-10 absolute precision.
variable ref equal round(1e10*sqrt(c_red[1]*c_red[1]+c_red[2]*c_red[2]+c_red[3]*c_red[3]))*1e-10
variable all equal round(1e10*c_c2)*1e-10
velocity all create 300 432567 dist uniform
timestep 2.0
# v_fpa and v_for and c_c1, c_fpa[] and c_one[] should all each have the same value. v_ref and c_c2 should be zero
thermo_style custom step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref v_all
thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:77)
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:77)
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
2 neighbor lists, perpetual/occasional/extra = 1 1 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
(2) compute group/group, occasional, copy from (1)
attributes: half, newton on
pair build: copy
stencil: none
bin: none
Per MPI rank memory allocation (min/avg/max) = 28.47 | 28.47 | 28.47 Mbytes
Step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref v_all
0 22.7331 22.7331 22.7331 -17.068295 -17.068295 -8.8348335 -8.8348334 -12.141369 -12.141369 0 0
10 11.736901 11.736901 11.736901 -3.3897029 -3.3897029 9.1193856 9.1193856 -6.5651786 -6.5651786 0 0
20 5.6120339 5.6120339 5.6120339 -0.60046861 -0.60046861 -4.4481306 -4.4481306 3.3687528 3.3687528 0 0
30 17.29261 17.29261 17.29261 6.179302 6.179302 -10.593979 -10.593979 12.190906 12.190906 0 0
40 18.664433 18.664433 18.664433 5.4727782 5.4727782 -6.9329319 -6.9329319 16.442148 16.442148 0 0
50 12.130407 12.130407 12.130407 -1.0321196 -1.0321196 8.0035558 8.0035558 -9.0567428 -9.0567428 0 0
Loop time of 13.9507 on 1 procs for 50 steps with 4500 atoms
Performance: 0.619 ns/day, 38.752 hours/ns, 3.584 timesteps/s
32.0% CPU use with 1 MPI tasks x no OpenMP threads
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 12.594 | 12.594 | 12.594 | 0.0 | 90.27
Bond | 7.3e-05 | 7.3e-05 | 7.3e-05 | 0.0 | 0.00
Kspace | 0.56296 | 0.56296 | 0.56296 | 0.0 | 4.04
Neigh | 0.65858 | 0.65858 | 0.65858 | 0.0 | 4.72
Comm | 0.019093 | 0.019093 | 0.019093 | 0.0 | 0.14
Output | 0.055025 | 0.055025 | 0.055025 | 0.0 | 0.39
Modify | 0.057276 | 0.057276 | 0.057276 | 0.0 | 0.41
Other | | 0.004003 | | | 0.03
Nlocal: 4500 ave 4500 max 4500 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 21131 ave 21131 max 21131 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 2.60198e+06 ave 2.60198e+06 max 2.60198e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 2601983
Ave neighs/atom = 578.218
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:15

177
examples/USER/tally/log.12Jun17.force.4 Normal file
View File

@ -0,0 +1,177 @@
LAMMPS (19 May 2017)
units real
atom_style full
read_data data.spce
orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
2 by 2 by 1 MPI processor grid
reading atoms ...
4500 atoms
scanning bonds ...
2 = max bonds/atom
scanning angles ...
1 = max angles/atom
reading bonds ...
3000 bonds
reading angles ...
1500 angles
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
1 = max # of 1-4 neighbors
2 = max # of special neighbors
pair_style lj/cut/coul/long 12.0 12.0
kspace_style pppm 1.0e-4
pair_coeff 1 1 0.15535 3.166
pair_coeff * 2 0.0000 0.0000
bond_style harmonic
angle_style harmonic
dihedral_style none
improper_style none
bond_coeff 1 1000.00 1.000
angle_coeff 1 100.0 109.47
special_bonds lj/coul 0.0 0.0 1.0
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
2 = max # of special neighbors
neighbor 2.0 bin
fix 1 all shake 0.0001 20 0 b 1 a 1
0 = # of size 2 clusters
0 = # of size 3 clusters
0 = # of size 4 clusters
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 10.6 | 10.61 | 10.61 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 4.5e-06 on 4 procs for 0 steps with 4500 atoms
group one molecule 1 2
6 atoms in group one
# the following section shows equivalences between using the force/tally compute and other computes and thermo keywords
# compute pairwise force between two molecules and everybody
compute fpa one group/group all pair yes kspace no boundary no
# tally pairwise force between two molecules and the all molecules
compute c1 one force/tally all
# tally the force of all with all (should be zero)
compute c2 all force/tally all
# collect per atom data. only reduce over the first group.
compute one one reduce sum c_c1[1] c_c1[2] c_c1[3]
compute red all reduce sum c_c2[1] c_c2[2] c_c2[3]
# determine magnitude of force
variable fpa equal sqrt(c_fpa[1]*c_fpa[1]+c_fpa[2]*c_fpa[2]+c_fpa[3]*c_fpa[3])
variable for equal sqrt(c_one[1]*c_one[1]+c_one[2]*c_one[2]+c_one[3]*c_one[3])
# round to 10**-10 absolute precision.
variable ref equal round(1e10*sqrt(c_red[1]*c_red[1]+c_red[2]*c_red[2]+c_red[3]*c_red[3]))*1e-10
variable all equal round(1e10*c_c2)*1e-10
velocity all create 300 432567 dist uniform
timestep 2.0
# v_fpa and v_for and c_c1, c_fpa[] and c_one[] should all each have the same value. v_ref and c_c2 should be zero
thermo_style custom step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref v_all
thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:77)
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:77)
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
2 neighbor lists, perpetual/occasional/extra = 1 1 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
(2) compute group/group, occasional, copy from (1)
attributes: half, newton on
pair build: copy
stencil: none
bin: none
Per MPI rank memory allocation (min/avg/max) = 11.58 | 11.59 | 11.6 Mbytes
Step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref v_all
0 22.7331 22.7331 22.7331 -17.068295 -17.068295 -8.8348335 -8.8348334 -12.141369 -12.141369 0 0
10 11.736901 11.736901 11.736901 -3.3897029 -3.3897029 9.1193856 9.1193856 -6.5651786 -6.5651786 0 0
20 5.6120339 5.6120339 5.6120339 -0.60046861 -0.60046861 -4.4481306 -4.4481306 3.3687528 3.3687528 0 0
30 17.29261 17.29261 17.29261 6.179302 6.179302 -10.593979 -10.593979 12.190906 12.190906 0 0
40 18.664433 18.664433 18.664433 5.4727782 5.4727782 -6.9329319 -6.9329319 16.442148 16.442148 0 0
50 12.130407 12.130407 12.130407 -1.0321196 -1.0321196 8.0035558 8.0035558 -9.0567428 -9.0567428 0 0
Loop time of 4.31614 on 4 procs for 50 steps with 4500 atoms
Performance: 2.002 ns/day, 11.989 hours/ns, 11.584 timesteps/s
31.6% CPU use with 4 MPI tasks x no OpenMP threads
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 3.5075 | 3.6114 | 3.7489 | 4.7 | 83.67
Bond | 8.6e-05 | 0.00010525 | 0.000141 | 0.0 | 0.00
Kspace | 0.2581 | 0.39489 | 0.49723 | 14.2 | 9.15
Neigh | 0.19826 | 0.19888 | 0.19918 | 0.1 | 4.61
Comm | 0.034639 | 0.037137 | 0.038938 | 0.9 | 0.86
Output | 0.025465 | 0.025997 | 0.027558 | 0.6 | 0.60
Modify | 0.044022 | 0.044175 | 0.044407 | 0.1 | 1.02
Other | | 0.003593 | | | 0.08
Nlocal: 1125 ave 1148 max 1097 min
Histogram: 1 0 0 1 0 0 0 0 1 1
Nghost: 12212.5 ave 12269 max 12162 min
Histogram: 1 0 0 1 0 1 0 0 0 1
Neighs: 650496 ave 675112 max 631353 min
Histogram: 1 0 0 1 1 0 0 0 0 1
Total # of neighbors = 2601983
Ave neighs/atom = 578.218
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:04

98
examples/USER/tally/log.21Aug15.pe.1 → examples/USER/tally/log.12Jun17.pe.1
View File

@ -1,5 +1,4 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
LAMMPS (19 May 2017)
units real
atom_style full
@ -50,6 +49,35 @@ fix 1 all shake 0.0001 20 0 b 1 a 1
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 26.54 | 26.54 | 26.54 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 1e-06 on 1 procs for 0 steps with 4500 atoms
group oxy type 1
1500 atoms in group oxy
group hyd type 2
@ -88,6 +116,7 @@ thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
@ -95,38 +124,49 @@ PPPM initialization ...
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:75)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:75)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:77)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:77)
Neighbor list info ...
2 neighbor list requests
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 17.381 Mbytes
Step epa epa E_vdwl vdwl E_coul coul eref pe c2 pair
0 -516632.19 -516632.19 3169.9382 3169.9382 46213.889 46213.889 49383.827 49383.827 49383.827 49383.827
10 -517027.36 -517027.36 3099.1322 3099.1322 45891.84 45891.84 48990.972 48990.972 48990.972 48990.972
20 -516828.06 -516828.06 3101.4321 3101.4321 45884.14 45884.14 48985.572 48985.572 48985.572 48985.572
30 -517032.1 -517032.1 3198.5939 3198.5939 45793.571 45793.571 48992.165 48992.165 48992.165 48992.165
40 -517095.56 -517095.56 3244.0797 3244.0797 45715.265 45715.265 48959.345 48959.345 48959.345 48959.345
50 -517273.54 -517273.54 3274.9142 3274.9142 45665.997 45665.997 48940.911 48940.911 48940.911 48940.911
binsize = 7, bins = 6 6 6
2 neighbor lists, perpetual/occasional/extra = 1 1 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
(2) compute group/group, occasional, copy from (1)
attributes: half, newton on
pair build: copy
stencil: none
bin: none
Per MPI rank memory allocation (min/avg/max) = 29.08 | 29.08 | 29.08 Mbytes
Step c_epa v_epa E_vdwl v_vdwl E_coul v_coul v_eref v_pe c_c2 v_pair
0 -516634.27 -516634.27 3169.9427 3169.9427 46212.482 46212.482 49382.425 49382.425 49382.425 49382.425
10 -517027.35 -517027.35 3099.1374 3099.1374 45891.866 45891.866 48991.003 48991.003 48991.003 48991.003
20 -516828.05 -516828.05 3101.4373 3101.4373 45884.156 45884.156 48985.594 48985.594 48985.594 48985.594
30 -517032.07 -517032.07 3198.5951 3198.5951 45793.595 45793.595 48992.191 48992.191 48992.191 48992.191
40 -517095.54 -517095.54 3244.0771 3244.0771 45715.292 45715.292 48959.369 48959.369 48959.369 48959.369
50 -517273.5 -517273.5 3274.9097 3274.9097 45666.025 45666.025 48940.935 48940.935 48940.935 48940.935
Loop time of 15.3339 on 1 procs for 50 steps with 4500 atoms
Loop time of 4.31105 on 1 procs for 50 steps with 4500 atoms
100.1% CPU use with 1 MPI tasks x 1 OpenMP threads
Performance: 2.004 ns/day 11.975 hours/ns 11.598 timesteps/s
Performance: 0.563 ns/day, 42.594 hours/ns, 3.261 timesteps/s
32.0% CPU use with 1 MPI tasks x no OpenMP threads
MPI task timings breakdown:
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 3.5071 | 3.5071 | 3.5071 | 0.0 | 81.35
Bond | 0.00025034 | 0.00025034 | 0.00025034 | 0.0 | 0.01
Kspace | 0.19991 | 0.19991 | 0.19991 | 0.0 | 4.64
Neigh | 0.31459 | 0.31459 | 0.31459 | 0.0 | 7.30
Comm | 0.010338 | 0.010338 | 0.010338 | 0.0 | 0.24
Output | 0.24722 | 0.24722 | 0.24722 | 0.0 | 5.73
Modify | 0.029466 | 0.029466 | 0.029466 | 0.0 | 0.68
Other | | 0.002182 | | | 0.05
Pair | 13.432 | 13.432 | 13.432 | 0.0 | 87.60
Bond | 0.000365 | 0.000365 | 0.000365 | 0.0 | 0.00
Kspace | 0.581 | 0.581 | 0.581 | 0.0 | 3.79
Neigh | 0.66081 | 0.66081 | 0.66081 | 0.0 | 4.31
Comm | 0.019908 | 0.019908 | 0.019908 | 0.0 | 0.13
Output | 0.57731 | 0.57731 | 0.57731 | 0.0 | 3.76
Modify | 0.058515 | 0.058515 | 0.058515 | 0.0 | 0.38
Other | | 0.003889 | | | 0.03
Nlocal: 4500 ave 4500 max 4500 min
Histogram: 1 0 0 0 0 0 0 0 0 0
@ -135,10 +175,10 @@ Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 2.60198e+06 ave 2.60198e+06 max 2.60198e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 2601984
Ave neighs/atom = 578.219
Total # of neighbors = 2601983
Ave neighs/atom = 578.218
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:04
Total wall time: 0:00:16

98
examples/USER/tally/log.21Aug15.pe.4 → examples/USER/tally/log.12Jun17.pe.4
View File

@ -1,5 +1,4 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
LAMMPS (19 May 2017)
units real
atom_style full
@ -50,6 +49,35 @@ fix 1 all shake 0.0001 20 0 b 1 a 1
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 10.6 | 10.61 | 10.61 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 1.75e-06 on 4 procs for 0 steps with 4500 atoms
group oxy type 1
1500 atoms in group oxy
group hyd type 2
@ -88,6 +116,7 @@ thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
@ -95,38 +124,49 @@ PPPM initialization ...
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:75)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:75)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:77)
WARNING: Compute pe/tally only called from pair style (../compute_pe_tally.cpp:77)
Neighbor list info ...
2 neighbor list requests
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 8.44413 Mbytes
Step epa epa E_vdwl vdwl E_coul coul eref pe c2 pair
0 -516632.19 -516632.19 3169.9382 3169.9382 46213.889 46213.889 49383.827 49383.827 49383.827 49383.827
10 -517027.36 -517027.36 3099.1322 3099.1322 45891.84 45891.84 48990.972 48990.972 48990.972 48990.972
20 -516828.06 -516828.06 3101.4321 3101.4321 45884.14 45884.14 48985.572 48985.572 48985.572 48985.572
30 -517032.1 -517032.1 3198.5939 3198.5939 45793.571 45793.571 48992.165 48992.165 48992.165 48992.165
40 -517095.56 -517095.56 3244.0797 3244.0797 45715.265 45715.265 48959.345 48959.345 48959.345 48959.345
50 -517273.54 -517273.54 3274.9142 3274.9142 45665.997 45665.997 48940.911 48940.911 48940.911 48940.911
binsize = 7, bins = 6 6 6
2 neighbor lists, perpetual/occasional/extra = 1 1 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
(2) compute group/group, occasional, copy from (1)
attributes: half, newton on
pair build: copy
stencil: none
bin: none
Per MPI rank memory allocation (min/avg/max) = 11.86 | 11.87 | 11.88 Mbytes
Step c_epa v_epa E_vdwl v_vdwl E_coul v_coul v_eref v_pe c_c2 v_pair
0 -516634.27 -516634.27 3169.9427 3169.9427 46212.482 46212.482 49382.425 49382.425 49382.425 49382.425
10 -517027.35 -517027.35 3099.1374 3099.1374 45891.866 45891.866 48991.003 48991.003 48991.003 48991.003
20 -516828.05 -516828.05 3101.4373 3101.4373 45884.156 45884.156 48985.594 48985.594 48985.594 48985.594
30 -517032.07 -517032.07 3198.5951 3198.5951 45793.595 45793.595 48992.191 48992.191 48992.191 48992.191
40 -517095.54 -517095.54 3244.0771 3244.0771 45715.292 45715.292 48959.369 48959.369 48959.369 48959.369
50 -517273.5 -517273.5 3274.9097 3274.9097 45666.025 45666.025 48940.935 48940.935 48940.935 48940.935
Loop time of 2.32344 on 4 procs for 50 steps with 4500 atoms
Loop time of 1.20533 on 4 procs for 50 steps with 4500 atoms
100.0% CPU use with 4 MPI tasks x 1 OpenMP threads
Performance: 7.168 ns/day 3.348 hours/ns 41.482 timesteps/s
Performance: 3.719 ns/day, 6.454 hours/ns, 21.520 timesteps/s
64.0% CPU use with 4 MPI tasks x no OpenMP threads
MPI task timings breakdown:
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 0.87053 | 0.90325 | 0.94364 | 2.8 | 74.94
Bond | 0.00015402 | 0.00018191 | 0.00020909 | 0.2 | 0.02
Kspace | 0.061657 | 0.10164 | 0.13394 | 8.4 | 8.43
Neigh | 0.088292 | 0.088332 | 0.088373 | 0.0 | 7.33
Comm | 0.017319 | 0.017806 | 0.018291 | 0.4 | 1.48
Output | 0.07067 | 0.070706 | 0.070813 | 0.0 | 5.87
Modify | 0.021655 | 0.021694 | 0.02173 | 0.0 | 1.80
Other | | 0.001719 | | | 0.14
Pair | 1.5561 | 1.8883 | 2.0327 | 14.1 | 81.27
Bond | 8.8e-05 | 0.000116 | 0.000135 | 0.0 | 0.00
Kspace | 0.094718 | 0.1933 | 0.26055 | 14.1 | 8.32
Neigh | 0.085117 | 0.1073 | 0.1147 | 3.9 | 4.62
Comm | 0.014156 | 0.017907 | 0.020005 | 1.8 | 0.77
Output | 0.071634 | 0.090599 | 0.097665 | 3.6 | 3.90
Modify | 0.019447 | 0.024101 | 0.026277 | 1.8 | 1.04
Other | | 0.001804 | | | 0.08
Nlocal: 1125 ave 1148 max 1097 min
Histogram: 1 0 0 1 0 0 0 0 1 1
@ -135,10 +175,10 @@ Histogram: 1 0 0 1 0 1 0 0 0 1
Neighs: 650496 ave 675112 max 631353 min
Histogram: 1 0 0 1 1 0 0 0 0 1
Total # of neighbors = 2601984
Ave neighs/atom = 578.219
Total # of neighbors = 2601983
Ave neighs/atom = 578.218
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:01
Total wall time: 0:00:02

85
examples/USER/tally/log.21Aug15.stress.1 → examples/USER/tally/log.12Jun17.stress.1
View File

@ -1,5 +1,4 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
LAMMPS (19 May 2017)
units real
atom_style full
@ -50,6 +49,35 @@ fix 1 all shake 0.0001 20 0 b 1 a 1
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 26.54 | 26.54 | 26.54 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 2e-06 on 1 procs for 0 steps with 4500 atoms
group one molecule 1 2
6 atoms in group one
@ -79,6 +107,7 @@ thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
@ -86,38 +115,32 @@ PPPM initialization ...
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:75)
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:75)
Neighbor list info ...
1 neighbor list requests
update every 1 steps, delay 10 steps, check yes
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 24.631 Mbytes
Step press spa press one ref
0 26497.547 26497.547 26497.547 -2357033.6 -2357033.6
10 23665.073 23665.073 23665.073 -2096057.3 -2096057.3
20 23338.149 23338.149 23338.149 -2034283 -2034283
30 25946.4 25946.4 25946.4 -2002817 -2002817
40 27238.349 27238.349 27238.349 -2155411.5 -2155411.5
50 27783.092 27783.092 27783.092 -1862190.3 -1862190.3
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:79)
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:79)
Per MPI rank memory allocation (min/avg/max) = 35.9 | 35.9 | 35.9 Mbytes
Step c_press v_spa v_press v_one v_ref
0 26496.811 26496.811 26496.811 -2356992.7 -2356992.7
10 23665.129 23665.129 23665.129 -2096059 -2096059
20 23338.197 23338.197 23338.197 -2034284.1 -2034284.1
30 25946.434 25946.434 25946.434 -2002815.3 -2002815.3
40 27238.374 27238.374 27238.374 -2155408.7 -2155408.7
50 27783.107 27783.107 27783.107 -1862191.5 -1862191.5
Loop time of 14.2089 on 1 procs for 50 steps with 4500 atoms
Loop time of 4.15609 on 1 procs for 50 steps with 4500 atoms
100.1% CPU use with 1 MPI tasks x 1 OpenMP threads
Performance: 2.079 ns/day 11.545 hours/ns 12.031 timesteps/s
Performance: 0.608 ns/day, 39.469 hours/ns, 3.519 timesteps/s
32.0% CPU use with 1 MPI tasks x no OpenMP threads
MPI task timings breakdown:
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 3.6444 | 3.6444 | 3.6444 | 0.0 | 87.69
Bond | 0.0016105 | 0.0016105 | 0.0016105 | 0.0 | 0.04
Kspace | 0.22345 | 0.22345 | 0.22345 | 0.0 | 5.38
Neigh | 0.23588 | 0.23588 | 0.23588 | 0.0 | 5.68
Comm | 0.010035 | 0.010035 | 0.010035 | 0.0 | 0.24
Output | 0.0084085 | 0.0084085 | 0.0084085 | 0.0 | 0.20
Modify | 0.029978 | 0.029978 | 0.029978 | 0.0 | 0.72
Other | | 0.002368 | | | 0.06
Pair | 12.983 | 12.983 | 12.983 | 0.0 | 91.37
Bond | 0.002788 | 0.002788 | 0.002788 | 0.0 | 0.02
Kspace | 0.62745 | 0.62745 | 0.62745 | 0.0 | 4.42
Neigh | 0.49839 | 0.49839 | 0.49839 | 0.0 | 3.51
Comm | 0.018597 | 0.018597 | 0.018597 | 0.0 | 0.13
Output | 0.015852 | 0.015852 | 0.015852 | 0.0 | 0.11
Modify | 0.058415 | 0.058415 | 0.058415 | 0.0 | 0.41
Other | | 0.004126 | | | 0.03
Nlocal: 4500 ave 4500 max 4500 min
Histogram: 1 0 0 0 0 0 0 0 0 0
@ -132,4 +155,4 @@ Ave special neighs/atom = 2
Neighbor list builds = 3
Dangerous builds = 0
Total wall time: 0:00:04
Total wall time: 0:00:15

87
examples/USER/tally/log.21Aug15.stress.4 → examples/USER/tally/log.12Jun17.stress.4
View File

@ -1,5 +1,4 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
LAMMPS (19 May 2017)
units real
atom_style full
@ -50,6 +49,35 @@ fix 1 all shake 0.0001 20 0 b 1 a 1
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
# make certain that shake constraints are satisfied
run 0 post no
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
Neighbor list info ...
update every 1 steps, delay 10 steps, check yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7, bins = 6 6 6
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair lj/cut/coul/long, perpetual
attributes: half, newton on
pair build: half/bin/newton
stencil: half/bin/3d/newton
bin: standard
Per MPI rank memory allocation (min/avg/max) = 10.6 | 10.61 | 10.61 Mbytes
Step Temp E_pair E_mol TotEng Press
0 0 -16692.358 0 -16692.358 -1289.8319
Loop time of 4e-06 on 4 procs for 0 steps with 4500 atoms
group one molecule 1 2
6 atoms in group one
@ -79,6 +107,7 @@ thermo 10
run 50
PPPM initialization ...
WARNING: Using 12-bit tables for long-range coulomb (../kspace.cpp:321)
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
@ -86,44 +115,38 @@ PPPM initialization ...
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:75)
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:75)
Neighbor list info ...
1 neighbor list requests
update every 1 steps, delay 10 steps, check yes
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 12.0691 Mbytes
Step press spa press one ref
0 26497.547 26497.547 26497.547 -2357033.6 -2357033.6
10 23665.073 23665.073 23665.073 -2096057.3 -2096057.3
20 23338.149 23338.149 23338.149 -2034283 -2034283
30 25946.4 25946.4 25946.4 -2002817 -2002817
40 27238.349 27238.349 27238.349 -2155411.5 -2155411.5
50 27783.092 27783.092 27783.092 -1862190.3 -1862190.3
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:79)
WARNING: Compute stress/tally only called from pair style (../compute_stress_tally.cpp:79)
Per MPI rank memory allocation (min/avg/max) = 15.25 | 15.26 | 15.27 Mbytes
Step c_press v_spa v_press v_one v_ref
0 26496.811 26496.811 26496.811 -2356992.7 -2356992.7
10 23665.129 23665.129 23665.129 -2096059 -2096059
20 23338.197 23338.197 23338.197 -2034284.1 -2034284.1
30 25946.434 25946.434 25946.434 -2002815.3 -2002815.3
40 27238.374 27238.374 27238.374 -2155408.7 -2155408.7
50 27783.107 27783.107 27783.107 -1862191.5 -1862191.5
Loop time of 4.32017 on 4 procs for 50 steps with 4500 atoms
Loop time of 1.17266 on 4 procs for 50 steps with 4500 atoms
100.0% CPU use with 4 MPI tasks x 1 OpenMP threads
Performance: 7.368 ns/day 3.257 hours/ns 42.638 timesteps/s
Performance: 2.000 ns/day, 12.000 hours/ns, 11.574 timesteps/s
31.8% CPU use with 4 MPI tasks x no OpenMP threads
MPI task timings breakdown:
MPI task timing breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 0.89832 | 0.93222 | 0.98611 | 3.4 | 79.50
Bond | 0.00081754 | 0.00096095 | 0.0011327 | 0.4 | 0.08
Kspace | 0.068058 | 0.12154 | 0.15522 | 9.4 | 10.36
Neigh | 0.065756 | 0.065785 | 0.065824 | 0.0 | 5.61
Comm | 0.017489 | 0.017982 | 0.018623 | 0.4 | 1.53
Output | 0.010985 | 0.011017 | 0.011111 | 0.1 | 0.94
Modify | 0.021429 | 0.021491 | 0.021551 | 0.0 | 1.83
Other | | 0.001671 | | | 0.14
Pair | 3.5816 | 3.6917 | 3.839 | 4.9 | 85.45
Bond | 0.001579 | 0.0016563 | 0.001709 | 0.1 | 0.04
Kspace | 0.22505 | 0.3716 | 0.48023 | 15.3 | 8.60
Neigh | 0.14558 | 0.14568 | 0.14575 | 0.0 | 3.37
Comm | 0.032009 | 0.03441 | 0.036274 | 0.8 | 0.80
Output | 0.02253 | 0.023115 | 0.024844 | 0.7 | 0.54
Modify | 0.046954 | 0.047086 | 0.047132 | 0.0 | 1.09
Other | | 0.004935 | | | 0.11
Nlocal: 1125 ave 1154 max 1092 min
Histogram: 1 0 0 0 1 0 1 0 0 1
Nghost: 12263.5 ave 12300 max 12219 min
Histogram: 1 0 1 0 0 0 0 0 0 2
Neighs: 650438 ave 678786 max 626279 min
Neighs: 650438 ave 678787 max 626279 min
Histogram: 1 0 0 1 1 0 0 0 0 1
Total # of neighbors = 2601750
@ -132,4 +155,4 @@ Ave special neighs/atom = 2
Neighbor list builds = 3
Dangerous builds = 0
Total wall time: 0:00:01
Total wall time: 0:00:04

136
examples/USER/tally/log.21Aug15.force.1
View File

@ -1,136 +0,0 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
units real
atom_style full
read_data data.spce
orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
1 by 1 by 1 MPI processor grid
reading atoms ...
4500 atoms
scanning bonds ...
2 = max bonds/atom
scanning angles ...
1 = max angles/atom
reading bonds ...
3000 bonds
reading angles ...
1500 angles
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
1 = max # of 1-4 neighbors
2 = max # of special neighbors
pair_style lj/cut/coul/long 12.0 12.0
kspace_style pppm 1.0e-4
pair_coeff 1 1 0.15535 3.166
pair_coeff * 2 0.0000 0.0000
bond_style harmonic
angle_style harmonic
dihedral_style none
improper_style none
bond_coeff 1 1000.00 1.000
angle_coeff 1 100.0 109.47
special_bonds lj/coul 0.0 0.0 1.0
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
2 = max # of special neighbors
neighbor 2.0 bin
fix 1 all shake 0.0001 20 0 b 1 a 1
0 = # of size 2 clusters
0 = # of size 3 clusters
0 = # of size 4 clusters
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
group one molecule 1 2
6 atoms in group one
# the following section shows equivalences between using the pe/tally compute and other computes and thermo keywords
# compute pairwise force between two molecules and everybody
compute fpa one group/group all pair yes kspace no boundary no
# tally pairwise force between two molecules and the all molecules
compute c1 one force/tally all
# tally the force of all with all (should be zero)
compute c2 all force/tally all
# collect per atom data. only reduce over the first group.
compute one one reduce sum c_c1[1] c_c1[2] c_c1[3]
compute red all reduce sum c_c2[1] c_c2[2] c_c2[3]
# determine magnitude of force
variable fpa equal sqrt(c_fpa[1]*c_fpa[1]+c_fpa[2]*c_fpa[2]+c_fpa[3]*c_fpa[3])
variable for equal sqrt(c_one[1]*c_one[1]+c_one[2]*c_one[2]+c_one[3]*c_one[3])
# round to 10**-10 absolute precision.
variable ref equal round(1e10*sqrt(c_red[1]*c_red[1]+c_red[2]*c_red[2]+c_red[3]*c_red[3]))*1e-10
velocity all create 300 432567 dist uniform
timestep 2.0
# v_fpa and v_for and c_c1, c_fpa[] and c_one[] should all each have the same value. v_ref and c_c2 should be zero
thermo_style custom step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref c_c2
thermo 10
run 50
PPPM initialization ...
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 8000 3375
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:75)
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:75)
Neighbor list info ...
2 neighbor list requests
update every 1 steps, delay 10 steps, check yes
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 16.7648 Mbytes
Step fpa for c1 fpa[1] one[1] fpa[2] one[2] fpa[3] one[3] ref c2
0 22.732789 22.732789 22.732789 -17.068392 -17.068392 -8.8345214 -8.8345214 -12.140878 -12.140878 0 0
10 11.736915 11.736915 11.736915 -3.3898298 -3.3898298 9.119272 9.119272 -6.5652948 -6.5652948 0 0
20 5.6119761 5.6119761 5.6119761 -0.60028931 -0.60028931 -4.4479886 -4.4479886 3.368876 3.368876 0 0
30 17.292617 17.292617 17.292617 6.1793856 6.1793856 -10.593927 -10.593927 12.190919 12.190919 0 0
40 18.664226 18.664226 18.664226 5.4725079 5.4725079 -6.933046 -6.933046 16.441955 16.441955 0 0
50 12.130282 12.130282 12.130282 -1.0321244 -1.0321244 8.0032646 8.0032646 -9.0568326 -9.0568326 0 0
Loop time of 4.11825 on 1 procs for 50 steps with 4500 atoms
100.0% CPU use with 1 MPI tasks x 1 OpenMP threads
Performance: 2.098 ns/day 11.440 hours/ns 12.141 timesteps/s
MPI task timings breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 3.5286 | 3.5286 | 3.5286 | 0.0 | 85.68
Bond | 6.1274e-05 | 6.1274e-05 | 6.1274e-05 | 0.0 | 0.00
Kspace | 0.1937 | 0.1937 | 0.1937 | 0.0 | 4.70
Neigh | 0.31454 | 0.31454 | 0.31454 | 0.0 | 7.64
Comm | 0.01037 | 0.01037 | 0.01037 | 0.0 | 0.25
Output | 0.039355 | 0.039355 | 0.039355 | 0.0 | 0.96
Modify | 0.029273 | 0.029273 | 0.029273 | 0.0 | 0.71
Other | | 0.002351 | | | 0.06
Nlocal: 4500 ave 4500 max 4500 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Nghost: 21131 ave 21131 max 21131 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Neighs: 2.60198e+06 ave 2.60198e+06 max 2.60198e+06 min
Histogram: 1 0 0 0 0 0 0 0 0 0
Total # of neighbors = 2601984
Ave neighs/atom = 578.219
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:04

136
examples/USER/tally/log.21Aug15.force.4
View File

@ -1,136 +0,0 @@
LAMMPS (21 Aug 2015-ICMS)
using 1 OpenMP thread(s) per MPI task
units real
atom_style full
read_data data.spce
orthogonal box = (0.02645 0.02645 0.02641) to (35.5328 35.5328 35.4736)
2 by 2 by 1 MPI processor grid
reading atoms ...
4500 atoms
scanning bonds ...
2 = max bonds/atom
scanning angles ...
1 = max angles/atom
reading bonds ...
3000 bonds
reading angles ...
1500 angles
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
1 = max # of 1-4 neighbors
2 = max # of special neighbors
pair_style lj/cut/coul/long 12.0 12.0
kspace_style pppm 1.0e-4
pair_coeff 1 1 0.15535 3.166
pair_coeff * 2 0.0000 0.0000
bond_style harmonic
angle_style harmonic
dihedral_style none
improper_style none
bond_coeff 1 1000.00 1.000
angle_coeff 1 100.0 109.47
special_bonds lj/coul 0.0 0.0 1.0
2 = max # of 1-2 neighbors
1 = max # of 1-3 neighbors
2 = max # of special neighbors
neighbor 2.0 bin
fix 1 all shake 0.0001 20 0 b 1 a 1
0 = # of size 2 clusters
0 = # of size 3 clusters
0 = # of size 4 clusters
1500 = # of frozen angles
fix 2 all nvt temp 300.0 300.0 100.0
group one molecule 1 2
6 atoms in group one
# the following section shows equivalences between using the pe/tally compute and other computes and thermo keywords
# compute pairwise force between two molecules and everybody
compute fpa one group/group all pair yes kspace no boundary no
# tally pairwise force between two molecules and the all molecules
compute c1 one force/tally all
# tally the force of all with all (should be zero)
compute c2 all force/tally all
# collect per atom data. only reduce over the first group.
compute one one reduce sum c_c1[1] c_c1[2] c_c1[3]
compute red all reduce sum c_c2[1] c_c2[2] c_c2[3]
# determine magnitude of force
variable fpa equal sqrt(c_fpa[1]*c_fpa[1]+c_fpa[2]*c_fpa[2]+c_fpa[3]*c_fpa[3])
variable for equal sqrt(c_one[1]*c_one[1]+c_one[2]*c_one[2]+c_one[3]*c_one[3])
# round to 10**-10 absolute precision.
variable ref equal round(1e10*sqrt(c_red[1]*c_red[1]+c_red[2]*c_red[2]+c_red[3]*c_red[3]))*1e-10
velocity all create 300 432567 dist uniform
timestep 2.0
# v_fpa and v_for and c_c1, c_fpa[] and c_one[] should all each have the same value. v_ref and c_c2 should be zero
thermo_style custom step v_fpa v_for c_c1 c_fpa[1] c_one[1] c_fpa[2] c_one[2] c_fpa[3] c_one[3] v_ref c_c2
thermo 10
run 50
PPPM initialization ...
G vector (1/distance) = 0.218482
grid = 15 15 15
stencil order = 5
estimated absolute RMS force accuracy = 0.0319435
estimated relative force accuracy = 9.61968e-05
using double precision FFTs
3d grid and FFT values/proc = 3380 960
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:75)
WARNING: Compute force/tally only called from pair style (../compute_force_tally.cpp:75)
Neighbor list info ...
2 neighbor list requests
update every 1 steps, delay 10 steps, check yes
master list distance cutoff = 14
ghost atom cutoff = 14
binsize = 7 -> bins = 6 6 6
Memory usage per processor = 8.16441 Mbytes
Step fpa for c1 fpa[1] one[1] fpa[2] one[2] fpa[3] one[3] ref c2
0 22.732789 22.732789 22.732789 -17.068392 -17.068392 -8.8345214 -8.8345214 -12.140878 -12.140878 0 0
10 11.736915 11.736915 11.736915 -3.3898298 -3.3898298 9.119272 9.119272 -6.5652948 -6.5652948 0 0
20 5.6119761 5.6119761 5.6119761 -0.60028931 -0.60028931 -4.4479886 -4.4479886 3.368876 3.368876 0 0
30 17.292617 17.292617 17.292617 6.1793856 6.1793856 -10.593927 -10.593927 12.190919 12.190919 0 0
40 18.664226 18.664226 18.664226 5.4725079 5.4725079 -6.933046 -6.933046 16.441955 16.441955 0 0
50 12.130282 12.130282 12.130282 -1.0321244 -1.0321244 8.0032646 8.0032646 -9.0568326 -9.0568326 0 0
Loop time of 1.13658 on 4 procs for 50 steps with 4500 atoms
100.0% CPU use with 4 MPI tasks x 1 OpenMP threads
Performance: 7.602 ns/day 3.157 hours/ns 43.991 timesteps/s
MPI task timings breakdown:
Section | min time | avg time | max time |%varavg| %total
---------------------------------------------------------------
Pair | 0.85795 | 0.89088 | 0.93636 | 3.0 | 78.38
Bond | 3.4571e-05 | 4.4644e-05 | 5.4598e-05 | 0.1 | 0.00
Kspace | 0.059847 | 0.1051 | 0.1384 | 8.9 | 9.25
Neigh | 0.085891 | 0.085954 | 0.086 | 0.0 | 7.56
Comm | 0.01758 | 0.018091 | 0.019178 | 0.5 | 1.59
Output | 0.013697 | 0.013725 | 0.013805 | 0.0 | 1.21
Modify | 0.021068 | 0.021137 | 0.021205 | 0.0 | 1.86
Other | | 0.001656 | | | 0.15
Nlocal: 1125 ave 1148 max 1097 min
Histogram: 1 0 0 1 0 0 0 0 1 1
Nghost: 12212.5 ave 12269 max 12162 min
Histogram: 1 0 0 1 0 1 0 0 0 1
Neighs: 650496 ave 675112 max 631353 min
Histogram: 1 0 0 1 1 0 0 0 0 1
Total # of neighbors = 2601984
Ave neighs/atom = 578.219
Ave special neighs/atom = 2
Neighbor list builds = 4
Dangerous builds = 1
Total wall time: 0:00:01

6
examples/neb/README
View File

@ -2,13 +2,19 @@ Run these examples as:
mpirun -np 4 lmp_g++ -partition 4x1 -in in.neb.hop1
mpirun -np 4 lmp_g++ -partition 4x1 -in in.neb.hop2
mpirun -np 4 lmp_g++ -partition 4x1 -in in.neb.hop1freeend
mpirun -np 3 lmp_g++ -partition 3x1 -in in.neb.sivac
mpirun -np 8 lmp_g++ -partition 4x2 -in in.neb.hop1
mpirun -np 8 lmp_g++ -partition 4x2 -in in.neb.hop2
mpirun -np 8 lmp_g++ -partition 4x2 -in in.neb.hop1freeend
mpirun -np 6 lmp_g++ -partition 3x2 -in in.neb.sivac
mpirun -np 9 lmp_g++ -partition 3x3 -in in.neb.sivac
Note that more than 4 replicas should be used for a precise estimate
of the activation energy corresponding to a transition.
If you uncomment the dump command lines in the input scripts, you can
create dump files to do visualization from via Python tools: (see
lammps/tools/README and lammps/tools/python/README for more info on

2
examples/neb/in.neb.hop1
View File

@ -51,7 +51,7 @@ set group nebatoms type 3
group nonneb subtract all nebatoms
fix 1 lower setforce 0.0 0.0 0.0
fix 2 nebatoms neb 1.0
fix 2 nebatoms neb 1.0 nudg_style idealpos
fix 3 all enforce2d
thermo 100

56
examples/neb/in.neb.hop1freeend Normal file
View File

@ -0,0 +1,56 @@
# 2d NEB surface simulation, hop from surface to become adatom
dimension 2
boundary p s p
atom_style atomic
neighbor 0.3 bin
neigh_modify delay 5
atom_modify map array sort 0 0.0
variable u uloop 20
# create geometry with flat surface
lattice hex 0.9
region box block 0 20 0 10 -0.25 0.25
read_data initial.hop1freeend
# LJ potentials
pair_style lj/cut 2.5
pair_coeff * * 1.0 1.0 2.5
pair_modify shift yes
# define groups
region 1 block INF INF INF 1.25 INF INF
group lower region 1
group mobile subtract all lower
set group lower type 2
timestep 0.05
# group of NEB atoms - either block or single atom ID 412
region surround block 10 18 17 20 0 0 units box
group nebatoms region surround
#group nebatoms id 412
set group nebatoms type 3
group nonneb subtract all nebatoms
fix 1 lower setforce 0.0 0.0 0.0
fix 2 nebatoms neb 1.0 nudg_style idealpos freeend ini
fix 3 all enforce2d
thermo 100
#dump 1 nebatoms atom 10 dump.neb.$u
#dump 2 nonneb atom 10 dump.nonneb.$u
# run NEB for 2000 steps or to force tolerance
min_style quickmin
neb 0.0 0.1 1000 1000 100 final final.hop1

860
examples/neb/initial.hop1freeend Normal file
View File

@ -0,0 +1,860 @@
LAMMPS data file via write_data, version 4 May 2017, timestep = 155
420 atoms
3 atom types
0.0000000000000000e+00 2.2653923264628304e+01 xlo xhi
2.1918578738841410e-01 1.9932852254455714e+01 ylo yhi
-2.8317404080785380e-01 2.8317404080785380e-01 zlo zhi
Masses
1 1
2 1
3 1
Atoms # atomic
1 2 0.0000000000000000e+00 2.2114806707013038e-01 0.0000000000000000e+00 0 0 0
2 2 5.6634808161570760e-01 1.1832938184587634e+00 0.0000000000000000e+00 0 0 0
3 2 1.1326961632314152e+00 2.2114806707013018e-01 0.0000000000000000e+00 0 0 0
4 2 1.6990442448471228e+00 1.1832938184587634e+00 0.0000000000000000e+00 0 0 0
5 2 2.2653923264628304e+00 2.2114806707013032e-01 0.0000000000000000e+00 0 0 0
6 2 2.8317404080785380e+00 1.1832938184587634e+00 0.0000000000000000e+00 0 0 0
7 2 3.3980884896942456e+00 2.2114806707013024e-01 0.0000000000000000e+00 0 0 0
8 2 3.9644365713099532e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
9 2 4.5307846529256608e+00 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
10 2 5.0971327345413684e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
11 2 5.6634808161570760e+00 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
12 2 6.2298288977727836e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
13 2 6.7961769793884912e+00 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
14 2 7.3625250610041988e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
15 2 7.9288731426199064e+00 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
16 2 8.4952212242356140e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
17 2 9.0615693058513216e+00 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
18 2 9.6279173874670292e+00 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
19 2 1.0194265469082737e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
20 2 1.0760613550698444e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
21 2 1.1326961632314152e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
22 2 1.1893309713929860e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
23 2 1.2459657795545567e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
24 2 1.3026005877161275e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
25 2 1.3592353958776982e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
26 2 1.4158702040392690e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
27 2 1.4725050122008398e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
28 2 1.5291398203624105e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
29 2 1.5857746285239813e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
30 2 1.6424094366855520e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
31 2 1.6990442448471228e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
32 2 1.7556790530086936e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
33 2 1.8123138611702643e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
34 2 1.8689486693318351e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
35 2 1.9255834774934058e+01 2.2114806707013010e-01 0.0000000000000000e+00 0 0 0
36 2 1.9822182856549766e+01 1.1832938184587636e+00 0.0000000000000000e+00 0 0 0
37 2 2.0388530938165474e+01 2.2114806707013024e-01 0.0000000000000000e+00 0 0 0
38 2 2.0954879019781181e+01 1.1832938184587634e+00 0.0000000000000000e+00 0 0 0
39 2 2.1521227101396889e+01 2.2114806707013043e-01 0.0000000000000000e+00 0 0 0
40 2 2.2087575183012596e+01 1.1832938184587634e+00 0.0000000000000000e+00 0 0 0
41 2 5.5197595012095140e-17 2.1414943053865136e+00 0.0000000000000000e+00 0 0 0
42 1 5.6653050195082300e-01 3.1000166664180786e+00 0.0000000000000000e+00 0 0 0
43 2 1.1326961632314152e+00 2.1414943053865136e+00 0.0000000000000000e+00 0 0 0
44 1 1.6992713312703549e+00 3.1000339212153092e+00 0.0000000000000000e+00 0 0 0
45 2 2.2653923264628304e+00 2.1414943053865136e+00 0.0000000000000000e+00 0 0 0
46 1 2.8319979330663916e+00 3.1000568858502824e+00 0.0000000000000000e+00 0 0 0
47 2 3.3980884896942456e+00 2.1414943053865136e+00 0.0000000000000000e+00 0 0 0
48 1 3.9647072056144004e+00 3.1000829051868171e+00 0.0000000000000000e+00 0 0 0
49 2 4.5307846529256608e+00 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
50 1 5.0973978903306154e+00 3.1001089282984520e+00 0.0000000000000000e+00 0 0 0
51 2 5.6634808161570760e+00 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
52 1 6.2300706856774344e+00 3.1001320005511488e+00 0.0000000000000000e+00 0 0 0
53 2 6.7961769793884912e+00 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
54 1 7.3627281418365298e+00 3.1001497026412643e+00 0.0000000000000000e+00 0 0 0
55 2 7.9288731426199064e+00 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
56 1 8.4953743353575657e+00 3.1001604410839558e+00 0.0000000000000000e+00 0 0 0
57 2 9.0615693058513216e+00 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
58 1 9.6280143647524650e+00 3.1001635457640377e+00 0.0000000000000000e+00 0 0 0
59 2 1.0194265469082737e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
60 1 1.0760653757776259e+01 3.1001591904894030e+00 0.0000000000000000e+00 0 0 0
61 2 1.1326961632314152e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
62 1 1.1893297897551465e+01 3.1001481997229781e+00 0.0000000000000000e+00 0 0 0
63 2 1.2459657795545567e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
64 1 1.3025951551034638e+01 3.1001318239711781e+00 0.0000000000000000e+00 0 0 0
65 2 1.3592353958776982e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
66 1 1.4158618530491893e+01 3.1001115545681470e+00 0.0000000000000000e+00 0 0 0
67 2 1.4725050122008398e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
68 1 1.5291301468763761e+01 3.1000890162853869e+00 0.0000000000000000e+00 0 0 0
69 2 1.5857746285239813e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
70 1 1.6424001663467980e+01 3.1000659357603495e+00 0.0000000000000000e+00 0 0 0
71 2 1.6990442448471228e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
72 1 1.7556718955895743e+01 3.1000441476131195e+00 0.0000000000000000e+00 0 0 0
73 2 1.8123138611702643e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
74 1 1.8689451647636982e+01 3.1000255781755963e+00 0.0000000000000000e+00 0 0 0
75 2 1.9255834774934058e+01 2.1414943053865132e+00 0.0000000000000000e+00 0 0 0
76 1 1.9822196505112320e+01 3.1000121466922494e+00 0.0000000000000000e+00 0 0 0
77 2 2.0388530938165474e+01 2.1414943053865136e+00 0.0000000000000000e+00 0 0 0
78 1 2.0954948927196146e+01 3.1000055506449713e+00 0.0000000000000000e+00 0 0 0
79 2 2.1521227101396889e+01 2.1414943053865141e+00 0.0000000000000000e+00 0 0 0
80 1 2.2087703334137267e+01 3.1000069547492535e+00 0.0000000000000000e+00 0 0 0
81 1 3.1056926716504509e-04 4.0585004644184055e+00 0.0000000000000000e+00 0 0 0
82 1 5.6689331628382078e-01 5.0169857265632762e+00 0.0000000000000000e+00 0 0 0
83 1 1.1331010876667682e+00 4.0585336877518543e+00 0.0000000000000000e+00 0 0 0
84 1 1.6997107179473134e+00 5.0170595571637469e+00 0.0000000000000000e+00 0 0 0
85 1 2.2658691471408239e+00 4.0585832735991989e+00 0.0000000000000000e+00 0 0 0
86 1 2.8324913387275488e+00 5.0171576059016481e+00 0.0000000000000000e+00 0 0 0
87 1 3.3986077265334802e+00 4.0586437183143182e+00 0.0000000000000000e+00 0 0 0
88 1 3.9652274946581523e+00 5.0172690174612651e+00 0.0000000000000000e+00 0 0 0
89 1 4.5313127263524615e+00 4.0587080892871539e+00 0.0000000000000000e+00 0 0 0
90 1 5.0979153202534064e+00 5.0173813990872880e+00 0.0000000000000000e+00 0 0 0
91 1 5.6639833195247755e+00 4.0587690704404489e+00 0.0000000000000000e+00 0 0 0
92 1 6.2305551824295442e+00 5.0174824868813017e+00 0.0000000000000000e+00 0 0 0
93 1 6.7966220748571669e+00 4.0588200390400129e+00 0.0000000000000000e+00 0 0 0
94 1 7.3631519876339633e+00 5.0175617795367824e+00 0.0000000000000000e+00 0 0 0
95 1 7.9292347620768062e+00 4.0588559557915787e+00 0.0000000000000000e+00 0 0 0
96 1 8.4957150696300925e+00 5.0176118394895646e+00 0.0000000000000000e+00 0 0 0
97 1 9.0618297669257259e+00 4.0588738859603266e+00 0.0000000000000000e+00 0 0 0
98 1 9.6282574219214077e+00 5.0176289672989007e+00 0.0000000000000000e+00 0 0 0
99 1 1.0194417159454611e+01 4.0588730767572860e+00 0.0000000000000000e+00 0 0 0
100 1 1.0760794315385466e+01 5.0176131474245498e+00 0.0000000000000000e+00 0 0 0
101 1 1.1327007580768864e+01 4.0588546552053515e+00 0.0000000000000000e+00 0 0 0
102 1 1.1893341583868121e+01 5.0175674119454996e+00 0.0000000000000000e+00 0 0 0
103 1 1.2459611156068675e+01 4.0588211205885418e+00 0.0000000000000000e+00 0 0 0
104 1 1.3025913928919357e+01 5.0174969437432848e+00 0.0000000000000000e+00 0 0 0
105 1 1.3592236588154931e+01 4.0587758328652299e+00 0.0000000000000000e+00 0 0 0
106 1 1.4158523495745847e+01 5.0174082592346645e+00 0.0000000000000000e+00 0 0 0
107 1 1.4724890484932756e+01 4.0587226477181808e+00 0.0000000000000000e+00 0 0 0
108 1 1.5291178803597106e+01 5.0173086870307237e+00 0.0000000000000000e+00 0 0 0
109 1 1.5857576888353359e+01 4.0586657476126140e+00 0.0000000000000000e+00 0 0 0
110 1 1.6423884000624799e+01 5.0172061640888863e+00 0.0000000000000000e+00 0 0 0
111 1 1.6990296946466405e+01 4.0586096139851531e+00 0.0000000000000000e+00 0 0 0
112 1 1.7556638404998214e+01 5.0171091825602536e+00 0.0000000000000000e+00 0 0 0
113 1 1.8123048711157228e+01 4.0585590083330025e+00 0.0000000000000000e+00 0 0 0
114 1 1.8689436384449273e+01 5.0170266065355777e+00 0.0000000000000000e+00 0 0 0
115 1 1.9255827121600600e+01 4.0585188068824696e+00 0.0000000000000000e+00 0 0 0
116 1 1.9822267727126505e+01 5.0169670887341100e+00 0.0000000000000000e+00 0 0 0
117 1 2.0388624292977298e+01 4.0584935738800203e+00 0.0000000000000000e+00 0 0 0
118 1 2.0955118660666272e+01 5.0169379847636248e+00 0.0000000000000000e+00 0 0 0
119 1 2.1521430213723754e+01 4.0584868720623906e+00 0.0000000000000000e+00 0 0 0
120 1 2.2087973498256840e+01 5.0169439545250629e+00 0.0000000000000000e+00 0 0 0
121 1 6.5693888433665819e-04 5.9753894955957820e+00 0.0000000000000000e+00 0 0 0
122 1 5.6732815172745055e-01 6.9338399304063270e+00 0.0000000000000000e+00 0 0 0
123 1 1.1335287178365945e+00 5.9754794631117711e+00 0.0000000000000000e+00 0 0 0
124 1 1.7002170239497103e+00 6.9340002985609068e+00 0.0000000000000000e+00 0 0 0
125 1 2.2663607603415961e+00 5.9756128140497200e+00 0.0000000000000000e+00 0 0 0
126 1 2.8330530781363672e+00 6.9342120448719999e+00 0.0000000000000000e+00 0 0 0
127 1 3.3991419489134609e+00 5.9757753571666763e+00 0.0000000000000000e+00 0 0 0
128 1 3.9658260192240613e+00 6.9344537679961507e+00 0.0000000000000000e+00 0 0 0
129 1 4.5318648361825700e+00 5.9759497256682410e+00 0.0000000000000000e+00 0 0 0
130 1 5.0985283212441441e+00 6.9347011709619251e+00 0.0000000000000000e+00 0 0 0
131 1 5.6645260085061278e+00 5.9761173336292988e+00 0.0000000000000000e+00 0 0 0
132 1 6.2311560978848899e+00 6.9349290616610286e+00 0.0000000000000000e+00 0 0 0
133 1 6.7971269443565747e+00 5.9762605495489280e+00 0.0000000000000000e+00 0 0 0
134 1 7.3637111409380722e+00 6.9351139899270322e+00 0.0000000000000000e+00 0 0 0
135 1 7.9296749255956041e+00 5.9763649377635293e+00 0.0000000000000000e+00 0 0 0
136 1 8.4962030194710927e+00 6.9352373287964380e+00 0.0000000000000000e+00 0 0 0
137 1 9.0621832354873675e+00 5.9764210443253543e+00 0.0000000000000000e+00 0 0 0
138 1 9.6286498073427680e+00 6.9352878316174378e+00 0.0000000000000000e+00 0 0 0
139 1 1.0194670187278859e+01 5.9764252099845692e+00 0.0000000000000000e+00 0 0 0
140 1 1.0761076657788550e+01 6.9352626758233988e+00 0.0000000000000000e+00 0 0 0
141 1 1.1327157075090911e+01 5.9763792530010624e+00 0.0000000000000000e+00 0 0 0
142 1 1.1893512574619942e+01 6.9351667929726579e+00 0.0000000000000000e+00 0 0 0
143 1 1.2459665575239395e+01 5.9762893326393627e+00 0.0000000000000000e+00 0 0 0
144 1 1.3025986375565017e+01 6.9350110693313853e+00 0.0000000000000000e+00 0 0 0
145 1 1.3592215193397568e+01 5.9761645662970668e+00 0.0000000000000000e+00 0 0 0
146 1 1.4158522852873338e+01 6.9348103731164086e+00 0.0000000000000000e+00 0 0 0
147 1 1.4724821146400661e+01 5.9760159211600943e+00 0.0000000000000000e+00 0 0 0
148 1 1.5291139696354101e+01 6.9345821426564456e+00 0.0000000000000000e+00 0 0 0
149 1 1.5857492801384174e+01 5.9758556179168476e+00 0.0000000000000000e+00 0 0 0
150 1 1.6423845342403485e+01 6.9343457083902562e+00 0.0000000000000000e+00 0 0 0
151 1 1.6990232659392920e+01 5.9756969240409656e+00 0.0000000000000000e+00 0 0 0
152 1 1.7556637811168688e+01 6.9341219348234606e+00 0.0000000000000000e+00 0 0 0
153 1 1.8123035927190724e+01 5.9755539362099377e+00 0.0000000000000000e+00 0 0 0
154 1 1.8689504786395585e+01 6.9339324030079297e+00 0.0000000000000000e+00 0 0 0
155 1 1.9255890870078105e+01 5.9754408656724385e+00 0.0000000000000000e+00 0 0 0
156 1 1.9822425360651039e+01 6.9337974543626846e+00 0.0000000000000000e+00 0 0 0
157 1 2.0388780199969101e+01 5.9753705251759808e+00 0.0000000000000000e+00 0 0 0
158 1 2.0955373611320280e+01 6.9337330661143222e+00 0.0000000000000000e+00 0 0 0
159 1 2.1521683507254988e+01 5.9753521824721574e+00 0.0000000000000000e+00 0 0 0
160 1 2.2088323232189435e+01 6.9337475792566039e+00 0.0000000000000000e+00 0 0 0
161 1 1.1151815023353693e-03 7.8921416571122727e+00 0.0000000000000000e+00 0 0 0
162 1 5.6789887436851039e-01 8.8505576275120745e+00 0.0000000000000000e+00 0 0 0
163 1 1.1340615020344891e+00 7.8923152028921146e+00 0.0000000000000000e+00 0 0 0
164 1 1.7008494977197184e+00 8.8508369646616227e+00 0.0000000000000000e+00 0 0 0
165 1 2.2669564852467339e+00 7.8925678787693965e+00 0.0000000000000000e+00 0 0 0
166 1 2.8337429988374914e+00 8.8512007799959171e+00 0.0000000000000000e+00 0 0 0
167 1 3.3997890834793392e+00 7.8928753791925752e+00 0.0000000000000000e+00 0 0 0
168 1 3.9665700017177907e+00 8.8516188392723496e+00 0.0000000000000000e+00 0 0 0
169 1 4.5325491541722158e+00 7.8932093579911635e+00 0.0000000000000000e+00 0 0 0
170 1 5.0993179760197034e+00 8.8520570451664753e+00 0.0000000000000000e+00 0 0 0
171 1 5.6652272696563086e+00 7.8935385042762318e+00 0.0000000000000000e+00 0 0 0
172 1 6.2319722558852177e+00 8.8524768944511472e+00 0.0000000000000000e+00 0 0 0
173 1 6.7978170214800082e+00 7.8938302754648539e+00 0.0000000000000000e+00 0 0 0
174 1 7.3645207249719933e+00 8.8528366651387476e+00 0.0000000000000000e+00 0 0 0
175 1 7.9303191911043118e+00 7.8940542651579788e+00 0.0000000000000000e+00 0 0 0
176 1 8.4969615618418324e+00 8.8530963542120293e+00 0.0000000000000000e+00 0 0 0
177 1 9.0627458585593441e+00 7.8941868850969135e+00 0.0000000000000000e+00 0 0 0
178 1 9.6293104463590424e+00 8.8532254399208412e+00 0.0000000000000000e+00 0 0 0
179 1 1.0195121730902658e+01 7.8942152485172352e+00 0.0000000000000000e+00 0 0 0
180 1 1.0761602408503441e+01 8.8532092085980238e+00 0.0000000000000000e+00 0 0 0
181 1 1.1327481649719793e+01 7.8941385508356099e+00 0.0000000000000000e+00 0 0 0
182 1 1.1893886870241856e+01 8.8530505445055354e+00 0.0000000000000000e+00 0 0 0
183 1 1.2459865179342737e+01 7.8939667557582798e+00 0.0000000000000000e+00 0 0 0
184 1 1.3026218291904378e+01 8.8527674547956821e+00 0.0000000000000000e+00 0 0 0
185 1 1.3592310202433307e+01 7.8937178025905181e+00 0.0000000000000000e+00 0 0 0
186 1 1.4158645900042497e+01 8.8523887379317436e+00 0.0000000000000000e+00 0 0 0
187 1 1.4724847145311326e+01 7.8934149070498600e+00 0.0000000000000000e+00 0 0 0
188 1 1.5291205081244327e+01 8.8519503874602243e+00 0.0000000000000000e+00 0 0 0
189 1 1.5857494607334019e+01 7.8930848995638652e+00 0.0000000000000000e+00 0 0 0
190 1 1.6423911366860466e+01 8.8514936483282209e+00 0.0000000000000000e+00 0 0 0
191 1 1.6990256625068444e+01 7.8927574412240151e+00 0.0000000000000000e+00 0 0 0
192 1 1.7556757521848787e+01 8.8510636099500459e+00 0.0000000000000000e+00 0 0 0
193 1 1.8123121878813144e+01 7.8924640508501298e+00 0.0000000000000000e+00 0 0 0
194 1 1.8689714850348466e+01 8.8507060559423465e+00 0.0000000000000000e+00 0 0 0
195 1 1.9256065579477248e+01 7.8922356001392169e+00 0.0000000000000000e+00 0 0 0
196 1 1.9822740225596814e+01 8.8504608774193994e+00 0.0000000000000000e+00 0 0 0
197 1 2.0389054599310764e+01 7.8920977743942782e+00 0.0000000000000000e+00 0 0 0
198 1 2.0955788196198530e+01 8.8503534864083591e+00 0.0000000000000000e+00 0 0 0
199 1 2.1522054950758765e+01 7.8920658349416701e+00 0.0000000000000000e+00 0 0 0
200 1 2.2088823030833748e+01 8.8503894045591807e+00 0.0000000000000000e+00 0 0 0
201 1 1.7402898961801966e-03 9.8087331458102049e+00 0.0000000000000000e+00 0 0 0
202 1 5.6862550253253785e-01 1.0767129063577668e+01 0.0000000000000000e+00 0 0 0
203 1 1.1347351125604563e+00 9.8090210312609756e+00 0.0000000000000000e+00 0 0 0
204 1 1.7016010961270076e+00 1.0767553944884048e+01 0.0000000000000000e+00 0 0 0
205 1 2.2676800733457139e+00 9.8094251915038573e+00 0.0000000000000000e+00 0 0 0
206 1 2.8345388558320415e+00 1.0768094021206529e+01 0.0000000000000000e+00 0 0 0
207 1 3.4005711921286008e+00 9.8099146303251388e+00 0.0000000000000000e+00 0 0 0
208 1 3.9674359888022686e+00 1.0768719604543580e+01 0.0000000000000000e+00 0 0 0
209 1 4.5333977826109315e+00 9.8104561733570019e+00 0.0000000000000000e+00 0 0 0
210 1 5.1002760963180327e+00 1.0769398202643465e+01 0.0000000000000000e+00 0 0 0
211 1 5.6661407887052828e+00 9.8110111848429966e+00 0.0000000000000000e+00 0 0 0
212 1 6.2330282022400469e+00 1.0770087202120337e+01 0.0000000000000000e+00 0 0 0
213 1 6.7987755062394477e+00 9.8115326503110527e+00 0.0000000000000000e+00 0 0 0
214 1 7.3656514287550623e+00 1.0770727843890981e+01 0.0000000000000000e+00 0 0 0
215 1 7.9312798141889260e+00 9.8119658218493768e+00 0.0000000000000000e+00 0 0 0
216 1 8.4981076412551477e+00 1.0771244633836279e+01 0.0000000000000000e+00 0 0 0
217 1 9.0636474998261161e+00 9.8122560909429151e+00 0.0000000000000000e+00 0 0 0
218 1 9.6303843877347930e+00 1.0771559046035311e+01 0.0000000000000000e+00 0 0 0
219 1 1.0195900672859819e+01 9.8123627359180627e+00 0.0000000000000000e+00 0 0 0
220 1 1.0762516251278290e+01 1.0771614844517241e+01 0.0000000000000000e+00 0 0 0
221 1 1.1328091472906591e+01 9.8122692653101016e+00 0.0000000000000000e+00 0 0 0
222 1 1.1894584725285364e+01 1.0771394980275380e+01 0.0000000000000000e+00 0 0 0
223 1 1.2460291956550108e+01 9.8119854743716211e+00 0.0000000000000000e+00 0 0 0
224 1 1.3026697175518089e+01 1.0770922584297365e+01 0.0000000000000000e+00 0 0 0
225 1 1.3592577560562113e+01 9.8115426529845742e+00 0.0000000000000000e+00 0 0 0
226 1 1.4158957523975143e+01 1.0770251678533704e+01 0.0000000000000000e+00 0 0 0
227 1 1.4725010595311739e+01 9.8109868569230709e+00 0.0000000000000000e+00 0 0 0
228 1 1.5291439665423439e+01 1.0769456959141509e+01 0.0000000000000000e+00 0 0 0
229 1 1.5857627568713173e+01 9.8103742214932304e+00 0.0000000000000000e+00 0 0 0
230 1 1.6424169320270668e+01 1.0768628052568168e+01 0.0000000000000000e+00 0 0 0
231 1 1.6990431516954079e+01 9.8097684628141781e+00 0.0000000000000000e+00 0 0 0
232 1 1.7557116532362020e+01 1.0767864432631596e+01 0.0000000000000000e+00 0 0 0
233 1 1.8123390991250901e+01 9.8092369760472078e+00 0.0000000000000000e+00 0 0 0
234 1 1.8690204705628890e+01 1.0767262063551410e+01 0.0000000000000000e+00 0 0 0
235 1 1.9256448808830498e+01 9.8088413825519911e+00 0.0000000000000000e+00 0 0 0
236 1 1.9823340586830241e+01 1.0766888821404979e+01 0.0000000000000000e+00 0 0 0
237 1 2.0389541413400988e+01 9.8086229912274785e+00 0.0000000000000000e+00 0 0 0
238 1 2.0956458511796701e+01 1.0766759511236279e+01 0.0000000000000000e+00 0 0 0
239 1 2.1522621458778595e+01 9.8085916713182311e+00 0.0000000000000000e+00 0 0 0
240 1 2.2089529168272502e+01 1.0766851883618157e+01 0.0000000000000000e+00 0 0 0
241 1 2.5440858595377333e-03 1.1725176449724485e+01 0.0000000000000000e+00 0 0 0
242 1 5.6945959459694062e-01 1.2683596360703445e+01 0.0000000000000000e+00 0 0 0
243 1 1.1355189649219313e+00 1.1725603142335736e+01 0.0000000000000000e+00 0 0 0
244 1 1.7023827890664067e+00 1.2684167657575470e+01 0.0000000000000000e+00 0 0 0
245 1 2.2684713496063051e+00 1.1726169790097240e+01 0.0000000000000000e+00 0 0 0
246 1 2.8353214317297493e+00 1.2684869845626739e+01 0.0000000000000000e+00 0 0 0
247 1 3.4014115221528614e+00 1.1726849793467629e+01 0.0000000000000000e+00 0 0 0
248 1 3.9682847366436711e+00 1.2685690043118647e+01 0.0000000000000000e+00 0 0 0
249 1 4.5343333925353440e+00 1.1727620546655658e+01 0.0000000000000000e+00 0 0 0
250 1 5.1012595788864648e+00 1.2686617936467927e+01 0.0000000000000000e+00 0 0 0
251 1 5.6672100999124009e+00 1.1728453321807010e+01 0.0000000000000000e+00 0 0 0
252 1 6.2342050679378476e+00 1.2687631443781253e+01 0.0000000000000000e+00 0 0 0
253 1 6.7999929539663801e+00 1.1729301393807379e+01 0.0000000000000000e+00 0 0 0
254 1 7.3670487632296053e+00 1.2688678524169049e+01 0.0000000000000000e+00 0 0 0
255 1 7.9326168577620031e+00 1.1730088752185795e+01 0.0000000000000000e+00 0 0 0
256 1 8.4996909972151879e+00 1.2689657545646673e+01 0.0000000000000000e+00 0 0 0
257 1 9.0650186324858186e+00 1.1730705889838760e+01 0.0000000000000000e+00 0 0 0
258 1 9.6320279172941738e+00 1.2690401359419884e+01 0.0000000000000000e+00 0 0 0
259 1 1.0197176988949883e+01 1.1731033591325737e+01 0.0000000000000000e+00 0 0 0
260 1 1.0764025265158372e+01 1.2690719979755405e+01 0.0000000000000000e+00 0 0 0
261 1 1.1329151471753224e+01 1.1730992082437087e+01 0.0000000000000000e+00 0 0 0
262 1 1.1895793457864773e+01 1.2690499952724066e+01 0.0000000000000000e+00 0 0 0
263 1 1.2461074954083520e+01 1.1730568008302011e+01 0.0000000000000000e+00 0 0 0
264 1 1.3027557263784812e+01 1.2689744664661927e+01 0.0000000000000000e+00 0 0 0
265 1 1.3593109813371450e+01 1.1729811224797992e+01 0.0000000000000000e+00 0 0 0
266 1 1.4159562461497188e+01 1.2688557996910490e+01 0.0000000000000000e+00 0 0 0
267 1 1.4725395146103379e+01 1.1728816806025771e+01 0.0000000000000000e+00 0 0 0
268 1 1.5291979336937130e+01 1.2687112353846338e+01 0.0000000000000000e+00 0 0 0
269 1 1.5858003969640130e+01 1.1727709969544065e+01 0.0000000000000000e+00 0 0 0
270 1 1.6424834380846097e+01 1.2685627373535834e+01 0.0000000000000000e+00 0 0 0
271 1 1.6990919595491782e+01 1.1726637864021814e+01 0.0000000000000000e+00 0 0 0
272 1 1.7557997576834389e+01 1.2684345428666392e+01 0.0000000000000000e+00 0 0 0
273 1 1.8124040077451223e+01 1.1725751812758334e+01 0.0000000000000000e+00 0 0 0
274 1 1.8691233014266899e+01 1.2683475493290855e+01 0.0000000000000000e+00 0 0 0
275 1 1.9257221467828444e+01 1.1725167602985902e+01 0.0000000000000000e+00 0 0 0
276 1 1.9824402296022900e+01 1.2683041511515679e+01 0.0000000000000000e+00 0 0 0
277 1 2.0390369399207284e+01 1.1724905550220807e+01 0.0000000000000000e+00 0 0 0
278 1 2.0957468093457749e+01 1.2682973372169659e+01 0.0000000000000000e+00 0 0 0
279 1 2.1523449818304549e+01 1.1724927159323300e+01 0.0000000000000000e+00 0 0 0
280 1 2.2090449109149038e+01 1.2683182366055206e+01 0.0000000000000000e+00 0 0 0
281 1 3.4599372752678664e-03 1.3641562113178441e+01 0.0000000000000000e+00 0 0 0
282 1 5.7026645299712297e-01 1.4600072778762289e+01 0.0000000000000000e+00 0 0 0
283 1 1.1363018176625184e+00 1.3642122621820601e+01 0.0000000000000000e+00 0 0 0
284 1 1.7030304397851530e+00 1.4600744808517264e+01 0.0000000000000000e+00 0 0 0
285 1 2.2691832178537314e+00 1.3642819174389231e+01 0.0000000000000000e+00 0 0 0
286 1 2.8358920720180945e+00 1.4601540713388465e+01 0.0000000000000000e+00 0 0 0
287 1 3.4021290160499604e+00 1.3643644649633430e+01 0.0000000000000000e+00 0 0 0
288 1 3.9688713598453158e+00 1.4602477110803298e+01 0.0000000000000000e+00 0 0 0
289 1 4.5351441054704758e+00 1.3644605343002951e+01 0.0000000000000000e+00 0 0 0
290 1 5.1019693529741863e+00 1.4603583498422479e+01 0.0000000000000000e+00 0 0 0
291 1 5.6682074099496385e+00 1.3645707993168530e+01 0.0000000000000000e+00 0 0 0
292 1 6.2351598742721581e+00 1.4604888485699654e+01 0.0000000000000000e+00 0 0 0
293 1 6.8012626955016664e+00 1.3646941178415421e+01 0.0000000000000000e+00 0 0 0
294 1 7.3683745276621622e+00 1.4606397643582930e+01 0.0000000000000000e+00 0 0 0
295 1 7.9342088141787288e+00 1.3648248663869856e+01 0.0000000000000000e+00 0 0 0
296 1 8.5014805494154277e+00 1.4608055299059714e+01 0.0000000000000000e+00 0 0 0
297 1 9.0668968877652869e+00 1.3649493406156790e+01 0.0000000000000000e+00 0 0 0
298 1 9.6342620410232698e+00 1.4609684783907733e+01 0.0000000000000000e+00 0 0 0
299 1 1.0199152905272882e+01 1.3650407439181874e+01 0.0000000000000000e+00 0 0 0
300 1 1.0766413330496736e+01 1.4610836305969919e+01 0.0000000000000000e+00 0 0 0
301 1 1.1330921232704116e+01 1.3650669393063648e+01 0.0000000000000000e+00 0 0 0
302 1 1.1897841502623006e+01 1.4610930556808350e+01 0.0000000000000000e+00 0 0 0
303 1 1.2462421601307861e+01 1.3650120591395567e+01 0.0000000000000000e+00 0 0 0
304 1 1.3029018938638984e+01 1.4609761134444172e+01 0.0000000000000000e+00 0 0 0
305 1 1.3594046992755665e+01 1.3648816127477271e+01 0.0000000000000000e+00 0 0 0
306 1 1.4160647838817273e+01 1.4607529632893289e+01 0.0000000000000000e+00 0 0 0
307 1 1.4726158301286814e+01 1.3646976680611393e+01 0.0000000000000000e+00 0 0 0
308 1 1.5293172565463893e+01 1.4604737496674128e+01 0.0000000000000000e+00 0 0 0
309 1 1.5858902039329786e+01 1.3644935977195637e+01 0.0000000000000000e+00 0 0 0
310 1 1.6426542400228328e+01 1.4602024837155536e+01 0.0000000000000000e+00 0 0 0
311 1 1.6992136000094352e+01 1.3643085312965626e+01 0.0000000000000000e+00 0 0 0
312 1 1.7559955069272618e+01 1.4600235886953440e+01 0.0000000000000000e+00 0 0 0
313 1 1.8125444003110619e+01 1.3641827838397322e+01 0.0000000000000000e+00 0 0 0
314 1 1.8693119558449155e+01 1.4599324386000902e+01 0.0000000000000000e+00 0 0 0
315 1 1.9258622464532973e+01 1.3641178402937728e+01 0.0000000000000000e+00 0 0 0
316 1 1.9826034884164418e+01 1.4599040434292966e+01 0.0000000000000000e+00 0 0 0
317 1 2.0391639577074734e+01 1.3641005830730871e+01 0.0000000000000000e+00 0 0 0
318 1 2.0958793244869717e+01 1.4599158580846662e+01 0.0000000000000000e+00 0 0 0
319 1 2.1524539566888354e+01 1.3641168546895004e+01 0.0000000000000000e+00 0 0 0
320 1 2.2091487241099536e+01 1.4599530965127977e+01 0.0000000000000000e+00 0 0 0
321 1 4.3165808837657372e-03 1.5558056864296654e+01 0.0000000000000000e+00 0 0 0
322 1 5.7083714563799326e-01 1.6516708751979007e+01 0.0000000000000000e+00 0 0 0
323 1 1.1369032012442155e+00 1.5558694023524415e+01 0.0000000000000000e+00 0 0 0
324 1 1.7033478671452040e+00 1.6517390053019362e+01 0.0000000000000000e+00 0 0 0
325 1 2.2696166894760093e+00 1.5559438272441989e+01 0.0000000000000000e+00 0 0 0
326 1 2.8360390517176817e+00 1.6518173675862919e+01 0.0000000000000000e+00 0 0 0
327 1 3.4024835472607537e+00 1.5560308985846410e+01 0.0000000000000000e+00 0 0 0
328 1 3.9689280293273477e+00 1.6519102391285173e+01 0.0000000000000000e+00 0 0 0
329 1 4.5355194771089229e+00 1.5561347597079759e+01 0.0000000000000000e+00 0 0 0
330 1 5.1020300316691811e+00 1.6520241802728972e+01 0.0000000000000000e+00 0 0 0
331 1 5.6687261068083830e+00 1.5562609975559823e+01 0.0000000000000000e+00 0 0 0
332 1 6.2353553251066147e+00 1.6521676870813170e+01 0.0000000000000000e+00 0 0 0
333 1 6.8020803209306022e+00 1.5564154380715671e+01 0.0000000000000000e+00 0 0 0
334 1 7.3688969132482525e+00 1.6523504940606951e+01 0.0000000000000000e+00 0 0 0
335 1 7.9355107433004930e+00 1.5566016713593251e+01 0.0000000000000000e+00 0 0 0
336 1 8.5025988576228730e+00 1.6525815249413437e+01 0.0000000000000000e+00 0 0 0
337 1 9.0688572861916743e+00 1.5568159644275148e+01 0.0000000000000000e+00 0 0 0
338 1 9.6362867759002064e+00 1.6528628994685398e+01 0.0000000000000000e+00 0 0 0
339 1 1.0201819017728946e+01 1.5570385216229328e+01 0.0000000000000000e+00 0 0 0
340 1 1.0769583800973923e+01 1.6531845844888416e+01 0.0000000000000000e+00 0 0 0
341 1 1.1333827071325254e+01 1.5571891707346142e+01 0.0000000000000000e+00 0 0 0
342 1 1.1901384079738815e+01 1.6533906438348030e+01 0.0000000000000000e+00 0 0 0
343 1 1.2464735369608531e+01 1.5571536667850689e+01 0.0000000000000000e+00 0 0 0
344 1 1.3031616332415751e+01 1.6532264065445577e+01 0.0000000000000000e+00 0 0 0
345 1 1.3595655007692846e+01 1.5569123466092078e+01 0.0000000000000000e+00 0 0 0
346 1 1.4162673858547034e+01 1.6527452690896975e+01 0.0000000000000000e+00 0 0 0
347 1 1.4727720485417455e+01 1.5565353830287787e+01 0.0000000000000000e+00 0 0 0
348 1 1.5296922688141537e+01 1.6520776714395723e+01 0.0000000000000000e+00 0 0 0
349 1 1.5861362778086731e+01 1.5561222799294468e+01 0.0000000000000000e+00 0 0 0
350 1 1.6430601172841506e+01 1.6517208583528205e+01 0.0000000000000000e+00 0 0 0
351 1 1.6994922716392164e+01 1.5558699760506759e+01 0.0000000000000000e+00 0 0 0
352 1 1.7563499738678178e+01 1.6515675589984340e+01 0.0000000000000000e+00 0 0 0
353 1 1.8128019408521833e+01 1.5557486534354460e+01 0.0000000000000000e+00 0 0 0
354 1 1.8695872352982320e+01 1.6515215010141834e+01 0.0000000000000000e+00 0 0 0
355 1 1.9260742856192188e+01 1.5557098710840322e+01 0.0000000000000000e+00 0 0 0
356 1 1.9828039670247652e+01 1.6515278710047973e+01 0.0000000000000000e+00 0 0 0
357 1 2.0393271644052639e+01 1.5557181842904438e+01 0.0000000000000000e+00 0 0 0
358 1 2.0960186167839215e+01 1.6515618076673135e+01 0.0000000000000000e+00 0 0 0
359 1 2.1525740973565441e+01 1.5557536533469163e+01 0.0000000000000000e+00 0 0 0
360 1 2.2092409007659992e+01 1.6516113225524911e+01 0.0000000000000000e+00 0 0 0
361 1 4.8529541639103424e-03 1.7474826118864232e+01 0.0000000000000000e+00 0 0 0
362 1 5.7093835977538809e-01 1.8433654344787417e+01 0.0000000000000000e+00 0 0 0
363 1 1.1371184592334547e+00 1.7475436697267657e+01 0.0000000000000000e+00 0 0 0
364 1 1.7031721612449391e+00 1.8434245395923575e+01 0.0000000000000000e+00 0 0 0
365 1 2.2695912343467985e+00 1.7476125500853652e+01 0.0000000000000000e+00 0 0 0
366 1 2.8356286616018873e+00 1.8434926390559969e+01 0.0000000000000000e+00 0 0 0
367 1 3.4022762478393873e+00 1.7476929029147396e+01 0.0000000000000000e+00 0 0 0
368 1 3.9683006032101118e+00 1.8435747821965681e+01 0.0000000000000000e+00 0 0 0
369 1 4.5351848152653442e+00 1.7477909278192492e+01 0.0000000000000000e+00 0 0 0
370 1 5.1011966627212457e+00 1.8436786379097875e+01 0.0000000000000000e+00 0 0 0
371 1 5.6683370882181823e+00 1.7479154484464996e+01 0.0000000000000000e+00 0 0 0
372 1 6.2343468444568826e+00 1.8438149387991913e+01 0.0000000000000000e+00 0 0 0
373 1 6.8017614989468314e+00 1.7480782103907771e+01 0.0000000000000000e+00 0 0 0
374 1 7.3678106610096554e+00 1.8439986240742563e+01 0.0000000000000000e+00 0 0 0
375 1 7.9354841298542631e+00 1.7482944033551004e+01 0.0000000000000000e+00 0 0 0
376 1 8.5016878917981664e+00 1.8442513240991936e+01 0.0000000000000000e+00 0 0 0
377 1 9.0694835466447152e+00 1.7485826099637269e+01 0.0000000000000000e+00 0 0 0
378 1 9.6361298737773780e+00 1.8446058020412732e+01 0.0000000000000000e+00 0 0 0
379 3 1.0203552137528503e+01 1.7489611887918201e+01 0.0000000000000000e+00 0 0 0
380 3 1.0771411102042309e+01 1.8452757080501815e+01 0.0000000000000000e+00 0 0 0
381 3 1.1337379036649208e+01 1.7494680029430171e+01 0.0000000000000000e+00 0 0 0
382 3 1.1906745469447291e+01 1.8462022833637111e+01 0.0000000000000000e+00 0 0 0
383 3 1.2469280552911147e+01 1.7497259990645460e+01 0.0000000000000000e+00 0 0 0
384 3 1.3036336275216634e+01 1.8467761987124586e+01 0.0000000000000000e+00 0 0 0
385 3 1.3598327635293121e+01 1.7492598542232617e+01 0.0000000000000000e+00 0 0 0
386 3 1.4175415687021504e+01 1.8442378825657116e+01 0.0000000000000000e+00 0 0 0
387 3 1.4734039006741700e+01 1.7480807237018496e+01 0.0000000000000000e+00 0 0 0
388 3 1.5307067776131944e+01 1.8435324828663727e+01 0.0000000000000000e+00 0 0 0
389 3 1.5867533841026015e+01 1.7475841850521086e+01 0.0000000000000000e+00 0 0 0
390 3 1.6437492616293390e+01 1.8432690656917494e+01 0.0000000000000000e+00 0 0 0
391 3 1.6999775067986949e+01 1.7473899503923125e+01 0.0000000000000000e+00 0 0 0
392 3 1.7567888910690055e+01 1.8431965422256074e+01 0.0000000000000000e+00 0 0 0
393 1 1.8131542880564929e+01 1.7473449678636637e+01 0.0000000000000000e+00 0 0 0
394 1 1.8698655140485940e+01 1.8432031695013379e+01 0.0000000000000000e+00 0 0 0
395 1 1.9263155459010161e+01 1.7473512474723787e+01 0.0000000000000000e+00 0 0 0
396 1 1.9829735002682860e+01 1.8432284732233299e+01 0.0000000000000000e+00 0 0 0
397 1 2.0394851027090610e+01 1.7473827778588312e+01 0.0000000000000000e+00 0 0 0
398 1 2.0961149629160545e+01 1.8432663919612150e+01 0.0000000000000000e+00 0 0 0
399 1 2.1526715232103822e+01 1.7474283624212315e+01 0.0000000000000000e+00 0 0 0
400 1 2.2092870034810801e+01 1.8433127631588540e+01 0.0000000000000000e+00 0 0 0
401 1 4.8013042136807321e-03 1.9396043340320471e+01 0.0000000000000000e+00 0 0 0
402 1 1.1367941837037772e+00 1.9396530996055038e+01 0.0000000000000000e+00 0 0 0
403 1 2.2690256110731926e+00 1.9397098404349112e+01 0.0000000000000000e+00 0 0 0
404 1 3.4014603716469214e+00 1.9397780714315690e+01 0.0000000000000000e+00 0 0 0
405 1 4.5340819027961929e+00 1.9398637844588755e+01 0.0000000000000000e+00 0 0 0
406 1 5.6668967352607975e+00 1.9399756780683603e+01 0.0000000000000000e+00 0 0 0
407 1 6.7999442980869498e+00 1.9401258783163115e+01 0.0000000000000000e+00 0 0 0
408 1 7.9333186797521877e+00 1.9403316975932661e+01 0.0000000000000000e+00 0 0 0
409 1 9.0672196895765094e+00 1.9406194727028712e+01 0.0000000000000000e+00 0 0 0
410 3 1.0202094493927524e+01 1.9410357283161499e+01 0.0000000000000000e+00 0 0 0
411 3 1.1344493619984819e+01 1.9424786980556338e+01 0.0000000000000000e+00 0 0 0
412 3 1.2637742177785299e+01 1.9930889974773997e+01 0.0000000000000000e+00 0 0 0
413 3 1.3631034994726834e+01 1.9413135103231994e+01 0.0000000000000000e+00 0 0 0
414 3 1.4752642655140622e+01 1.9401337789912994e+01 0.0000000000000000e+00 0 0 0
415 3 1.5877850085888255e+01 1.9396855373999653e+01 0.0000000000000000e+00 0 0 0
416 3 1.7005401679016000e+01 1.9395287677046394e+01 0.0000000000000000e+00 0 0 0
417 1 1.8134615217150579e+01 1.9394983390043944e+01 0.0000000000000000e+00 0 0 0
418 1 1.9264825666738730e+01 1.9395059679793604e+01 0.0000000000000000e+00 0 0 0
419 1 2.0395687437852093e+01 1.9395286212420899e+01 0.0000000000000000e+00 0 0 0
420 1 2.1527023164623820e+01 1.9395624428209523e+01 0.0000000000000000e+00 0 0 0
Velocities
1 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
2 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
3 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
4 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
5 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
6 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
7 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
8 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
9 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
10 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
11 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
12 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
13 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
14 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
15 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
16 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
17 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
18 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
19 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
20 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
21 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
22 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
23 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
24 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
25 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
26 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
27 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
28 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
29 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
30 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
31 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
32 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
33 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
34 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
35 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
36 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
37 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
38 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
39 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
40 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
41 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
42 1.4582830912290846e-05 8.8846352819582645e-06 0.0000000000000000e+00
43 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
44 1.7312859198533731e-05 8.9315474912415886e-06 0.0000000000000000e+00
45 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
46 1.9675072488620216e-05 9.1850485538530490e-06 0.0000000000000000e+00
47 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
48 2.1433074233334628e-05 9.6286706528260491e-06 0.0000000000000000e+00
49 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
50 2.2405931370299284e-05 1.0203419110643709e-05 0.0000000000000000e+00
51 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
52 2.2491059900157929e-05 1.0820884817441812e-05 0.0000000000000000e+00
53 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
54 2.1681031416712071e-05 1.1392109985469690e-05 0.0000000000000000e+00
55 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
56 2.0060641760669130e-05 1.1861625865799975e-05 0.0000000000000000e+00
57 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
58 1.7796484401635950e-05 1.2218953480137158e-05 0.0000000000000000e+00
59 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
60 1.5112094617093786e-05 1.2477438154365889e-05 0.0000000000000000e+00
61 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
62 1.2267198630926124e-05 1.2639445999779870e-05 0.0000000000000000e+00
63 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
64 9.5350822789358476e-06 1.2675742401072055e-05 0.0000000000000000e+00
65 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
66 7.1824119616190063e-06 1.2539493069881058e-05 0.0000000000000000e+00
67 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
68 5.4428729520064613e-06 1.2202930059423273e-05 0.0000000000000000e+00
69 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
70 4.4916342132800272e-06 1.1686680302800539e-05 0.0000000000000000e+00
71 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
72 4.4211188598874964e-06 1.1059784694772424e-05 0.0000000000000000e+00
73 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
74 5.2335171901646275e-06 1.0413115381938121e-05 0.0000000000000000e+00
75 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
76 6.8418345483267640e-06 9.8270961040952689e-06 0.0000000000000000e+00
77 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
78 9.0862581078626780e-06 9.3562441357185347e-06 0.0000000000000000e+00
79 0.0000000000000000e+00 0.0000000000000000e+00 0.0000000000000000e+00
80 1.1750898218046424e-05 9.0341536486321376e-06 0.0000000000000000e+00
81 2.6507896911975861e-05 1.6371545140358991e-05 0.0000000000000000e+00
82 4.4071318998573086e-05 2.1693750644120881e-05 0.0000000000000000e+00
83 3.1968282279407066e-05 1.6236651087870452e-05 0.0000000000000000e+00
84 5.1796828963389391e-05 2.2204255617741203e-05 0.0000000000000000e+00
85 3.6954144790935994e-05 1.6513220966131449e-05 0.0000000000000000e+00
86 5.8466837911599906e-05 2.3765145047455889e-05 0.0000000000000000e+00
87 4.0988263449448856e-05 1.7195597287912591e-05 0.0000000000000000e+00
88 6.3421700984930829e-05 2.6202560196158383e-05 0.0000000000000000e+00
89 4.3676514981254302e-05 1.8262201659237366e-05 0.0000000000000000e+00
90 6.6189231995872341e-05 2.9208208903089284e-05 0.0000000000000000e+00
91 4.4757820844412710e-05 1.9680681285465242e-05 0.0000000000000000e+00
92 6.6503049702947023e-05 3.2363912757959332e-05 0.0000000000000000e+00
93 4.4112984955796063e-05 2.1371026788621213e-05 0.0000000000000000e+00
94 6.4345177020566643e-05 3.5287785267920645e-05 0.0000000000000000e+00
95 4.1787976800244936e-05 2.3162941413835267e-05 0.0000000000000000e+00
96 5.9928744845970383e-05 3.7723007380205399e-05 0.0000000000000000e+00
97 3.7995079634412303e-05 2.4792875906820557e-05 0.0000000000000000e+00
98 5.3679482622744082e-05 3.9576112916242527e-05 0.0000000000000000e+00
99 3.3102802347870566e-05 2.5962643816709875e-05 0.0000000000000000e+00
100 4.6196928202386916e-05 4.0841431876258162e-05 0.0000000000000000e+00
101 2.7604731797030090e-05 2.6452929465938663e-05 0.0000000000000000e+00
102 3.8198605610544056e-05 4.1488731650403403e-05 0.0000000000000000e+00
103 2.2062125644364829e-05 2.6211631192676194e-05 0.0000000000000000e+00
104 3.0461532031511585e-05 4.1405446569862951e-05 0.0000000000000000e+00
105 1.7036890410487144e-05 2.5367151114186193e-05 0.0000000000000000e+00
106 2.3743747198513856e-05 4.0442707371844690e-05 0.0000000000000000e+00
107 1.3025410253023063e-05 2.4148417954514280e-05 0.0000000000000000e+00
108 1.8714618137705143e-05 3.8535713097978544e-05 0.0000000000000000e+00
109 1.0408634299164180e-05 2.2777378345262281e-05 0.0000000000000000e+00
110 1.5879886471080462e-05 3.5803991688099920e-05 0.0000000000000000e+00
111 9.4236282619897256e-06 2.1395799353203516e-05 0.0000000000000000e+00
112 1.5528508660313246e-05 3.2559849894401442e-05 0.0000000000000000e+00
113 1.0151636970505765e-05 2.0069631778223131e-05 0.0000000000000000e+00
114 1.7697076907652322e-05 2.9219489273322326e-05 0.0000000000000000e+00
115 1.2515393741428794e-05 1.8835255026813244e-05 0.0000000000000000e+00
116 2.2166639673992795e-05 2.6190973817683679e-05 0.0000000000000000e+00
117 1.6287686218571795e-05 1.7749195377506077e-05 0.0000000000000000e+00
118 2.8490182736201632e-05 2.3793837746782787e-05 0.0000000000000000e+00
119 2.1107512829311378e-05 1.6897890319175769e-05 0.0000000000000000e+00
120 3.6037837106045466e-05 2.2245603004594772e-05 0.0000000000000000e+00
121 5.3754680927831089e-05 2.5818243561840512e-05 0.0000000000000000e+00
122 7.3852984703953750e-05 2.7472934391924166e-05 0.0000000000000000e+00
123 6.4028996009385391e-05 2.5673459200729887e-05 0.0000000000000000e+00
124 8.5908169593167111e-05 2.8779655657983422e-05 0.0000000000000000e+00
125 7.3452059594226324e-05 2.6972883064637495e-05 0.0000000000000000e+00
126 9.6325597970378315e-05 3.2438649799599460e-05 0.0000000000000000e+00
127 8.1100712408732978e-05 2.9661132010523619e-05 0.0000000000000000e+00
128 1.0416393664254911e-04 3.7996059391476322e-05 0.0000000000000000e+00
129 8.6279187735689372e-05 3.3655093070911189e-05 0.0000000000000000e+00
130 1.0867812733907078e-04 4.4662561906767820e-05 0.0000000000000000e+00
131 8.8474833676771911e-05 3.8743354165649700e-05 0.0000000000000000e+00
132 1.0953332540892396e-04 5.1642519960343192e-05 0.0000000000000000e+00
133 8.7489301482666931e-05 4.4565301821478113e-05 0.0000000000000000e+00
134 1.0664519563149365e-04 5.8191926603172465e-05 0.0000000000000000e+00
135 8.3386685919597045e-05 5.0496180582897816e-05 0.0000000000000000e+00
136 1.0029664202627839e-04 6.3854180722835299e-05 0.0000000000000000e+00
137 7.6554421387387345e-05 5.5724916856637890e-05 0.0000000000000000e+00
138 9.1026233328924885e-05 6.8337584627018583e-05 0.0000000000000000e+00
139 6.7636782318513533e-05 5.9415263115523977e-05 0.0000000000000000e+00
140 7.9687801662836277e-05 7.1465060890868459e-05 0.0000000000000000e+00
141 5.7497112140338785e-05 6.0967609586633220e-05 0.0000000000000000e+00
142 6.7357844628560681e-05 7.3031410372387953e-05 0.0000000000000000e+00
143 4.7129030804640708e-05 6.0212629249287861e-05 0.0000000000000000e+00
144 5.5250218292995579e-05 7.2797466423152327e-05 0.0000000000000000e+00
145 3.7563119690651669e-05 5.7436898093437411e-05 0.0000000000000000e+00
146 4.4567659752612482e-05 7.0555413628180241e-05 0.0000000000000000e+00
147 2.9761856381290211e-05 5.3240161725660877e-05 0.0000000000000000e+00
148 3.6379968408071024e-05 6.6254587745984145e-05 0.0000000000000000e+00
149 2.4507249328654254e-05 4.8297754292616488e-05 0.0000000000000000e+00
150 3.1513287993668526e-05 6.0149614548130757e-05 0.0000000000000000e+00
151 2.2321658045569226e-05 4.3171432510556026e-05 0.0000000000000000e+00
152 3.0489149535510922e-05 5.2826430989590112e-05 0.0000000000000000e+00
153 2.3406691442805219e-05 3.8251620084219645e-05 0.0000000000000000e+00
154 3.3434005351227340e-05 4.5149642749209296e-05 0.0000000000000000e+00
155 2.7646263937105427e-05 3.3806816567877322e-05 0.0000000000000000e+00
156 4.0072022728543377e-05 3.8051851023877120e-05 0.0000000000000000e+00
157 3.4612453095456479e-05 3.0084179504664271e-05 0.0000000000000000e+00
158 4.9715995320497382e-05 3.2366348850974144e-05 0.0000000000000000e+00
159 4.3610755492928814e-05 2.7338724794948033e-05 0.0000000000000000e+00
160 6.1380291935873857e-05 2.8717537667974358e-05 0.0000000000000000e+00
161 8.1494982491825407e-05 2.8148953219575557e-05 0.0000000000000000e+00
162 1.0332280599497646e-04 2.6201503829225565e-05 0.0000000000000000e+00
163 9.5761847160871774e-05 2.7946357434336516e-05 0.0000000000000000e+00
164 1.1864695815872809e-04 2.8356135457834722e-05 0.0000000000000000e+00
165 1.0885399470738391e-04 3.0748146450938071e-05 0.0000000000000000e+00
166 1.3196232705661449e-04 3.4623883717438410e-05 0.0000000000000000e+00
167 1.1960145227112585e-04 3.6566084099414615e-05 0.0000000000000000e+00
168 1.4195026861275745e-04 4.3922046815628174e-05 0.0000000000000000e+00
169 1.2694731664409029e-04 4.5104351462522260e-05 0.0000000000000000e+00
170 1.4795217588335909e-04 5.5130340832613979e-05 0.0000000000000000e+00
171 1.3031757484079781e-04 5.5906601170376687e-05 0.0000000000000000e+00
172 1.4942385512754647e-04 6.7008660580344934e-05 0.0000000000000000e+00
173 1.2933895493945637e-04 6.7959205844179285e-05 0.0000000000000000e+00
174 1.4640862693120205e-04 7.8808347871067721e-05 0.0000000000000000e+00
175 1.2418770632620368e-04 7.9948632905278019e-05 0.0000000000000000e+00
176 1.3899686227644703e-04 8.9704374162949410e-05 0.0000000000000000e+00
177 1.1530175670323509e-04 9.0294899930563893e-05 0.0000000000000000e+00
178 1.2781482749801704e-04 9.8919094420893419e-05 0.0000000000000000e+00
179 1.0353662297703481e-04 9.7655023731693666e-05 0.0000000000000000e+00
180 1.1373191796318627e-04 1.0541969215504335e-04 0.0000000000000000e+00
181 8.9924310567240939e-05 1.0107679026970171e-04 0.0000000000000000e+00
182 9.8144155759054283e-05 1.0842945197242355e-04 0.0000000000000000e+00
183 7.5715426026251240e-05 1.0020899633485792e-04 0.0000000000000000e+00
184 8.2585472575644195e-05 1.0759497773947524e-04 0.0000000000000000e+00
185 6.2273313315312773e-05 9.5280171371694988e-05 0.0000000000000000e+00
186 6.8676150395344254e-05 1.0303784847881596e-04 0.0000000000000000e+00
187 5.0970916505555661e-05 8.7088088473526171e-05 0.0000000000000000e+00
188 5.7773431465618642e-05 9.5162943772818259e-05 0.0000000000000000e+00
189 4.3046171895633206e-05 7.6794608467548045e-05 0.0000000000000000e+00
190 5.1018825812688962e-05 8.4471826448580955e-05 0.0000000000000000e+00
191 3.9350805046373119e-05 6.5685772521718177e-05 0.0000000000000000e+00
192 4.9118794840322114e-05 7.1798478806600616e-05 0.0000000000000000e+00
193 4.0296544731752153e-05 5.4848218154306130e-05 0.0000000000000000e+00
194 5.2373823993379091e-05 5.8337807582076184e-05 0.0000000000000000e+00
195 4.5754994278033105e-05 4.5116316024063770e-05 0.0000000000000000e+00
196 6.0480102795976155e-05 4.5653533328626764e-05 0.0000000000000000e+00
197 5.5147574075957093e-05 3.7092945765346277e-05 0.0000000000000000e+00
198 7.2607642712602124e-05 3.5308098903458904e-05 0.0000000000000000e+00
199 6.7490113431981086e-05 3.1302088338741595e-05 0.0000000000000000e+00
200 8.7399794370653100e-05 2.8568976378293145e-05 0.0000000000000000e+00
201 1.0893722215793989e-04 2.3548242675947018e-05 0.0000000000000000e+00
202 1.3096734611020011e-04 1.8222479559561189e-05 0.0000000000000000e+00
203 1.2587405764826476e-04 2.3075086083653581e-05 0.0000000000000000e+00
204 1.4794813469964918e-04 2.1310741972757686e-05 0.0000000000000000e+00
205 1.4140062010542452e-04 2.7813335553710658e-05 0.0000000000000000e+00
206 1.6232505969042551e-04 3.0392445992766945e-05 0.0000000000000000e+00
207 1.5397074924697088e-04 3.7554013992723016e-05 0.0000000000000000e+00
208 1.7307084911688810e-04 4.3967269632201604e-05 0.0000000000000000e+00
209 1.6265299884253917e-04 5.1975640619979227e-05 0.0000000000000000e+00
210 1.7920198664424654e-04 6.0190020213309052e-05 0.0000000000000000e+00
211 1.6652150024137926e-04 6.9718144800536699e-05 0.0000000000000000e+00
212 1.8081789854731273e-04 7.8360099041392683e-05 0.0000000000000000e+00
213 1.6556181720350750e-04 8.9018344965798718e-05 0.0000000000000000e+00
214 1.7752817256212197e-04 9.7575999242155437e-05 0.0000000000000000e+00
215 1.5977208852566740e-04 1.0737397867986304e-04 0.0000000000000000e+00
216 1.6979140654165145e-04 1.1697357648400367e-04 0.0000000000000000e+00
217 1.4991716557360079e-04 1.2288188040735228e-04 0.0000000000000000e+00
218 1.5773246565703171e-04 1.3407831270088809e-04 0.0000000000000000e+00
219 1.3669127604115129e-04 1.3409320273816903e-04 0.0000000000000000e+00
220 1.4251229678068216e-04 1.4611735938454550e-04 0.0000000000000000e+00
221 1.2122307334826826e-04 1.4035076438954076e-04 0.0000000000000000e+00
222 1.2529950168048559e-04 1.5081786662543979e-04 0.0000000000000000e+00
223 1.0469592755885001e-04 1.4095013503932427e-04 0.0000000000000000e+00
224 1.0808583047877408e-04 1.4794462550140816e-04 0.0000000000000000e+00
225 8.8627241500263001e-05 1.3548056521811501e-04 0.0000000000000000e+00
226 9.2458332531887566e-05 1.3885968265358318e-04 0.0000000000000000e+00
227 7.4741877098264211e-05 1.2401626995789950e-04 0.0000000000000000e+00
228 8.0205883060811833e-05 1.2520982577425913e-04 0.0000000000000000e+00
229 6.4625586397733592e-05 1.0787656142000266e-04 0.0000000000000000e+00
230 7.2455365263725255e-05 1.0828209149006050e-04 0.0000000000000000e+00
231 5.9588283630412220e-05 8.9170324651604443e-05 0.0000000000000000e+00
232 7.0192628935414336e-05 8.8909581629389317e-05 0.0000000000000000e+00
233 6.0204784194593798e-05 7.0300012127155753e-05 0.0000000000000000e+00
234 7.3736654845263383e-05 6.8446290010432812e-05 0.0000000000000000e+00
235 6.6430610182749772e-05 5.3155748135392397e-05 0.0000000000000000e+00
236 8.2877314926921305e-05 4.8905829630990080e-05 0.0000000000000000e+00
237 7.7513488386102286e-05 3.9091588598701160e-05 0.0000000000000000e+00
238 9.6520171103331445e-05 3.2781173935459572e-05 0.0000000000000000e+00
239 9.2232416915701703e-05 2.8983592081175541e-05 0.0000000000000000e+00
240 1.1323768745207866e-04 2.2099480605147771e-05 0.0000000000000000e+00
241 1.3459865563319741e-04 1.2703227752398906e-05 0.0000000000000000e+00
242 1.5474472990034682e-04 4.9028952578147883e-06 0.0000000000000000e+00
243 1.5215092550023015e-04 1.2097129719583488e-05 0.0000000000000000e+00
244 1.7049283829256650e-04 9.1706083284784945e-06 0.0000000000000000e+00
245 1.6776008627299133e-04 1.9099097427610624e-05 0.0000000000000000e+00
246 1.8333367243371162e-04 2.1604042292807520e-05 0.0000000000000000e+00
247 1.8008195062651708e-04 3.3615378061081087e-05 0.0000000000000000e+00
248 1.9189650531499411e-04 3.9685789135164573e-05 0.0000000000000000e+00
249 1.8783573502138761e-04 5.4407048131235179e-05 0.0000000000000000e+00
250 1.9614236422538478e-04 6.1776442206818580e-05 0.0000000000000000e+00
251 1.9089458289321614e-04 7.9516349638183995e-05 0.0000000000000000e+00
252 1.9558796322159504e-04 8.6892146170328155e-05 0.0000000000000000e+00
253 1.8874887732394583e-04 1.0500710476222600e-04 0.0000000000000000e+00
254 1.9152092472987035e-04 1.1597519058197392e-04 0.0000000000000000e+00
255 1.8256170726520249e-04 1.2813543516461412e-04 0.0000000000000000e+00
256 1.8317412822647789e-04 1.4660018932962857e-04 0.0000000000000000e+00
257 1.7255263462072589e-04 1.4676532692364173e-04 0.0000000000000000e+00
258 1.7180488878385214e-04 1.7463142934331309e-04 0.0000000000000000e+00
259 1.5968255923162790e-04 1.6112886872639011e-04 0.0000000000000000e+00
260 1.5736418072846288e-04 1.9373036611985696e-04 0.0000000000000000e+00
261 1.4438478717201006e-04 1.7104686393958903e-04 0.0000000000000000e+00
262 1.4172732865070544e-04 1.9993397606046031e-04 0.0000000000000000e+00
263 1.2780764883044244e-04 1.7581062997197168e-04 0.0000000000000000e+00
264 1.2551429537422006e-04 1.9326020335803872e-04 0.0000000000000000e+00
265 1.1143818436667695e-04 1.7279653463973672e-04 0.0000000000000000e+00
266 1.1129339275113247e-04 1.7696772682632424e-04 0.0000000000000000e+00
267 9.7026315827934351e-05 1.6059526683700199e-04 0.0000000000000000e+00
268 1.0011077369688101e-04 1.5518094661065159e-04 0.0000000000000000e+00
269 8.6522173578507114e-05 1.3949676203897713e-04 0.0000000000000000e+00
270 9.3664351269599769e-05 1.3012327167812935e-04 0.0000000000000000e+00
271 8.1291625785936272e-05 1.1272276579557331e-04 0.0000000000000000e+00
272 9.2500602391673231e-05 1.0286100151558550e-04 0.0000000000000000e+00
273 8.2174156364853157e-05 8.4321872533994066e-05 0.0000000000000000e+00
274 9.7130125497925732e-05 7.4496044974704109e-05 0.0000000000000000e+00
275 8.9034151680274584e-05 5.8030339746749375e-05 0.0000000000000000e+00
276 1.0678389790186836e-04 4.7638087115883802e-05 0.0000000000000000e+00
277 1.0119535639935181e-04 3.6303198355693708e-05 0.0000000000000000e+00
278 1.2094537118731950e-04 2.5060744325496045e-05 0.0000000000000000e+00
279 1.1693017924424426e-04 2.0976803055913763e-05 0.0000000000000000e+00
280 1.3749539877318216e-04 1.0260590705305633e-05 0.0000000000000000e+00
281 1.5664700963922696e-04 -2.3143582219387062e-06 0.0000000000000000e+00
282 1.7213521099798126e-04 -1.0893217653461935e-05 0.0000000000000000e+00
283 1.7163725578470403e-04 -2.7032144307298500e-06 0.0000000000000000e+00
284 1.8302101438290170e-04 -4.7015876043674941e-06 0.0000000000000000e+00
285 1.8408986700031230e-04 7.3762135624856621e-06 0.0000000000000000e+00
286 1.9034465344562048e-04 1.1634737927368466e-05 0.0000000000000000e+00
287 1.9261711656854316e-04 2.7002357232706195e-05 0.0000000000000000e+00
288 1.9361558083412500e-04 3.5128829947321527e-05 0.0000000000000000e+00
289 1.9675951681764233e-04 5.4504542291358708e-05 0.0000000000000000e+00
290 1.9229119872704733e-04 6.3160704993402156e-05 0.0000000000000000e+00
291 1.9589287639141945e-04 8.5624062570252574e-05 0.0000000000000000e+00
292 1.8763172746254775e-04 9.5926064062507038e-05 0.0000000000000000e+00
293 1.9144012028784324e-04 1.1574950605207010e-04 0.0000000000000000e+00
294 1.7925388721026504e-04 1.3336630569376064e-04 0.0000000000000000e+00
295 1.8325338492376081e-04 1.3941523897602475e-04 0.0000000000000000e+00
296 1.7111384196688562e-04 1.7606151476373124e-04 0.0000000000000000e+00
297 1.7441139798144990e-04 1.5854503282415543e-04 0.0000000000000000e+00
298 1.6032326888461984e-04 2.1446583056531008e-04 0.0000000000000000e+00
299 1.6387438500404321e-04 1.7460023770546828e-04 0.0000000000000000e+00
300 1.5074052192984994e-04 2.4020838682409438e-04 0.0000000000000000e+00
301 1.5148519378157811e-04 1.8980377776341359e-04 0.0000000000000000e+00
302 1.3966552521236660e-04 2.4774151750977874e-04 0.0000000000000000e+00
303 1.3793365457372421e-04 2.0064007271268226e-04 0.0000000000000000e+00
304 1.2999175496236775e-04 2.3635880684653166e-04 0.0000000000000000e+00
305 1.2445809284142433e-04 2.0319207617434042e-04 0.0000000000000000e+00
306 1.2058479570330461e-04 2.1223162942725083e-04 0.0000000000000000e+00
307 1.1335261202324864e-04 1.9202689248144918e-04 0.0000000000000000e+00
308 1.1489966476687653e-04 1.8116775432026056e-04 0.0000000000000000e+00
309 1.0607147008139182e-04 1.6763704556867280e-04 0.0000000000000000e+00
310 1.1336585045824133e-04 1.4707143380834897e-04 0.0000000000000000e+00
311 1.0344655043634243e-04 1.3351953844142965e-04 0.0000000000000000e+00
312 1.1682664536528110e-04 1.1117223278055075e-04 0.0000000000000000e+00
313 1.0584011765559926e-04 9.5633260364903774e-05 0.0000000000000000e+00
314 1.2284574193182076e-04 7.5987122603626839e-05 0.0000000000000000e+00
315 1.1395109003961985e-04 5.9134539871496392e-05 0.0000000000000000e+00
316 1.3307867183720012e-04 4.1776312299002252e-05 0.0000000000000000e+00
317 1.2588269209880162e-04 2.9470198058979825e-05 0.0000000000000000e+00
318 1.4544292811228404e-04 1.3605886591663147e-05 0.0000000000000000e+00
319 1.4084591944156649e-04 8.4739193403876596e-06 0.0000000000000000e+00
320 1.5916834934516234e-04 -4.8366910892216897e-06 0.0000000000000000e+00
321 1.7356992275325834e-04 -1.8042780077684453e-05 0.0000000000000000e+00
322 1.8147503918697350e-04 -2.4540925551368165e-05 0.0000000000000000e+00
323 1.8163463266840930e-04 -1.7130129888846129e-05 0.0000000000000000e+00
324 1.8253898079463108e-04 -1.5598547575766951e-05 0.0000000000000000e+00
325 1.8657806229653399e-04 -3.4133038182733444e-06 0.0000000000000000e+00
326 1.8037702210949025e-04 5.3434050311440554e-06 0.0000000000000000e+00
327 1.8771879764928681e-04 2.1715518823040016e-05 0.0000000000000000e+00
328 1.7471074558026713e-04 3.4539745108762290e-05 0.0000000000000000e+00
329 1.8460873128030577e-04 5.4984524671188725e-05 0.0000000000000000e+00
330 1.6600292929781353e-04 6.9008728811924969e-05 0.0000000000000000e+00
331 1.7796512641162431e-04 9.1385034689547154e-05 0.0000000000000000e+00
332 1.5410918238014520e-04 1.0736588228516046e-04 0.0000000000000000e+00
333 1.6795483683047752e-04 1.2318778434343078e-04 0.0000000000000000e+00
334 1.4157775831030313e-04 1.5014040855437159e-04 0.0000000000000000e+00
335 1.5785083269945281e-04 1.4650075439474400e-04 0.0000000000000000e+00
336 1.2665633684184470e-04 1.9516493438247949e-04 0.0000000000000000e+00
337 1.4652933492756114e-04 1.5825492457397368e-04 0.0000000000000000e+00
338 1.2214547186144981e-04 2.4167794353872549e-04 0.0000000000000000e+00
339 1.4180074826065196e-04 1.7604592446691659e-04 0.0000000000000000e+00
340 1.1255092108513610e-04 2.7260123374319155e-04 0.0000000000000000e+00
341 1.3761399094902802e-04 1.9706727165017120e-04 0.0000000000000000e+00
342 1.1522842530577449e-04 2.7911375117613133e-04 0.0000000000000000e+00
343 1.2918411829601699e-04 2.1803343236056900e-04 0.0000000000000000e+00
344 1.1734351128622201e-04 2.6571681944023359e-04 0.0000000000000000e+00
345 1.2254276275087787e-04 2.2432204295978476e-04 0.0000000000000000e+00
346 1.1974443872507096e-04 2.3680090433102696e-04 0.0000000000000000e+00
347 1.2071540692597284e-04 2.1269652219509870e-04 0.0000000000000000e+00
348 1.2270101616137648e-04 1.9743779542515523e-04 0.0000000000000000e+00
349 1.2264642729289398e-04 1.8508739809863369e-04 0.0000000000000000e+00
350 1.3383017178927455e-04 1.5156768459346495e-04 0.0000000000000000e+00
351 1.2577540617175406e-04 1.4740321111045147e-04 0.0000000000000000e+00
352 1.4340773421068627e-04 1.1293118958385223e-04 0.0000000000000000e+00
353 1.3341749813102418e-04 1.0072504549123244e-04 0.0000000000000000e+00
354 1.5386164243670204e-04 7.2227623415051933e-05 0.0000000000000000e+00
355 1.4204167491417043e-04 5.6498808092830119e-05 0.0000000000000000e+00
356 1.6279824866213127e-04 3.3429940217178515e-05 0.0000000000000000e+00
357 1.5267578941533281e-04 1.9709016910970241e-05 0.0000000000000000e+00
358 1.7110318234027366e-04 1.1467794122178855e-06 0.0000000000000000e+00
359 1.6340539277356244e-04 -5.5189289771696855e-06 0.0000000000000000e+00
360 1.7740714701955653e-04 -1.8977834327990608e-05 0.0000000000000000e+00
361 1.8452802730369313e-04 -2.8832061973687458e-05 0.0000000000000000e+00
362 1.8186625712888205e-04 -2.9558136605260799e-05 0.0000000000000000e+00
363 1.8024969476821697e-04 -2.5772260635909678e-05 0.0000000000000000e+00
364 1.6761747789816595e-04 -1.7724478134172529e-05 0.0000000000000000e+00
365 1.7295655435232461e-04 -8.2023972909357763e-06 0.0000000000000000e+00
366 1.5167563906890865e-04 7.1136721706312189e-06 0.0000000000000000e+00
367 1.6300729193455892e-04 2.1421261796460145e-05 0.0000000000000000e+00
368 1.3513262146713916e-04 4.1132163185070293e-05 0.0000000000000000e+00
369 1.5092813590493438e-04 5.9201618093873702e-05 0.0000000000000000e+00
370 1.1841008358865480e-04 8.0419467894957835e-05 0.0000000000000000e+00
371 1.3728404354778657e-04 9.8997396367778159e-05 0.0000000000000000e+00
372 1.0207956567589023e-04 1.2179874114308306e-04 0.0000000000000000e+00
373 1.2285830843381253e-04 1.3408468250307866e-04 0.0000000000000000e+00
374 8.5374614775879387e-05 1.6300686953091837e-04 0.0000000000000000e+00
375 1.0823800239604665e-04 1.5689628308888026e-04 0.0000000000000000e+00
376 7.0794245443767117e-05 2.0076846781781206e-04 0.0000000000000000e+00
377 9.4916240542002045e-05 1.6757505383186989e-04 0.0000000000000000e+00
378 5.3305776376960658e-05 2.3409206018084466e-04 0.0000000000000000e+00
379 9.7006448817647123e-05 1.6923635825827552e-04 0.0000000000000000e+00
380 7.3465624650027872e-05 2.8247344576399282e-04 0.0000000000000000e+00
381 1.0549927592481066e-04 2.0928780749128950e-04 0.0000000000000000e+00
382 8.2435739649036618e-05 2.8810010190574649e-04 0.0000000000000000e+00
383 1.0402453921892486e-04 2.4985200604758925e-04 0.0000000000000000e+00
384 1.0698549586748876e-04 2.9499323828433428e-04 0.0000000000000000e+00
385 1.0406074064549273e-04 2.4902814952768373e-04 0.0000000000000000e+00
386 1.2548092418124016e-04 2.5651719838597350e-04 0.0000000000000000e+00
387 1.2351646868146525e-04 2.1977784401163054e-04 0.0000000000000000e+00
388 1.5004190410192569e-04 2.0137571208681400e-04 0.0000000000000000e+00
389 1.3393580166351108e-04 1.9255393507981809e-04 0.0000000000000000e+00
390 1.6295883087441844e-04 1.5199213302359484e-04 0.0000000000000000e+00
391 1.5063751113547077e-04 1.4694859067203417e-04 0.0000000000000000e+00
392 1.8000897081745795e-04 1.0619343548646192e-04 0.0000000000000000e+00
393 1.6561309378602883e-04 9.7037670677296156e-05 0.0000000000000000e+00
394 1.9382745100814531e-04 6.5648980655922534e-05 0.0000000000000000e+00
395 1.7695741527044807e-04 4.9716511735790200e-05 0.0000000000000000e+00
396 2.0065188597728214e-04 2.5746708320466968e-05 0.0000000000000000e+00
397 1.8297867804266331e-04 1.0615003992406336e-05 0.0000000000000000e+00
398 1.9982611540716595e-04 -6.5682876870518107e-06 0.0000000000000000e+00
399 1.8556554896400902e-04 -1.6509803537161082e-05 0.0000000000000000e+00
400 1.9312536581833663e-04 -2.5912353602364910e-05 0.0000000000000000e+00
401 1.9023801410824606e-04 -2.7464462701394523e-05 0.0000000000000000e+00
402 1.6698242474704196e-04 -2.2099770957974276e-05 0.0000000000000000e+00
403 1.4243470745724796e-04 -2.3480099448894497e-06 0.0000000000000000e+00
404 1.1876992118927330e-04 2.8893674554990122e-05 0.0000000000000000e+00
405 9.7519654816455303e-05 6.7473438674861880e-05 0.0000000000000000e+00
406 7.9406575250692843e-05 1.0857040090545463e-04 0.0000000000000000e+00
407 6.4539515581651943e-05 1.4692649268945184e-04 0.0000000000000000e+00
408 5.1587395282262643e-05 1.7813848972085620e-04 0.0000000000000000e+00
409 3.9112490387149122e-05 1.9658956051422694e-04 0.0000000000000000e+00
410 5.0646024795521216e-05 2.1400372314275622e-04 0.0000000000000000e+00
411 5.0846759072495365e-05 2.4269431977691632e-04 0.0000000000000000e+00
412 -1.1482904584733112e-04 -1.4373303263865990e-04 0.0000000000000000e+00
413 1.5511043799162975e-04 2.5875085720661746e-04 0.0000000000000000e+00
414 1.6626514293530906e-04 2.1735425519646309e-04 0.0000000000000000e+00
415 1.8641734272053080e-04 1.7687638118890660e-04 0.0000000000000000e+00
416 2.0380463041431767e-04 1.3085055646827544e-04 0.0000000000000000e+00
417 2.1756044245783355e-04 8.4550353671555104e-05 0.0000000000000000e+00
418 2.2486305540664193e-04 4.3653832482456800e-05 0.0000000000000000e+00
419 2.2188236489361566e-04 7.6524745655054321e-06 0.0000000000000000e+00
420 2.0949238720629205e-04 -1.7218568434280989e-05 0.0000000000000000e+00

2
examples/snap/Ta06A.snapparam
View File

@ -8,8 +8,8 @@ twojmax 6
# optional
gamma 1
rfac0 0.99363
rmin0 0
diagonalstyle 3
bzeroflag 0
quadraticflag 0

2
examples/snap/W_2940_2017_2.snap
View File

@ -5,7 +5,7 @@ variable zblcutinner equal 4
variable zblcutouter equal 4.8
variable zblz equal 74
# Specify hybrid with SNAP, ZBL, and long-range Coulomb
# Specify hybrid with SNAP and ZBL
pair_style hybrid/overlay &
zbl ${zblcutinner} ${zblcutouter} &

2
examples/snap/W_2940_2017_2.snapparam
View File

@ -6,8 +6,8 @@ twojmax 8
# optional
gamma 1
rfac0 0.99363
rmin0 0
diagonalstyle 3
bzeroflag 0
quadraticflag 0

2
examples/snap/W_2940_2017_2_He_JW2013.snap
View File

@ -5,7 +5,7 @@ variable zblcutinner equal 4
variable zblcutouter equal 4.8
variable zblz equal 74
# Specify hybrid with SNAP, ZBL, and long-range Coulomb
# Specify hybrid with SNAP and ZBL
pair_style hybrid/overlay zbl ${zblcutinner} ${zblcutouter} snap table spline 10000 table spline 10000
pair_coeff 1 1 zbl ${zblz} ${zblz}

1
lib/gpu/Makefile.linux.mixed
View File

@ -8,7 +8,6 @@
EXTRAMAKE = Makefile.lammps.standard
CUDA_HOME = /usr/local/cuda
CUDA_HOME = /home/projects/openmpi/1.8.1/intel/13.1.SP1.106/cuda/6.0.37
NVCC = nvcc
# Kepler CUDA

14
lib/gpu/Nvidia.makefile
View File

@ -63,6 +63,7 @@ OBJS = $(OBJ_DIR)/lal_atom.o $(OBJ_DIR)/lal_ans.o \
$(OBJ_DIR)/lal_lj_coul_debye.o $(OBJ_DIR)/lal_lj_coul_debye_ext.o \
$(OBJ_DIR)/lal_coul_dsf.o $(OBJ_DIR)/lal_coul_dsf_ext.o \
$(OBJ_DIR)/lal_sw.o $(OBJ_DIR)/lal_sw_ext.o \
$(OBJ_DIR)/lal_vashishta.o $(OBJ_DIR)/lal_vashishta_ext.o \
$(OBJ_DIR)/lal_beck.o $(OBJ_DIR)/lal_beck_ext.o \
$(OBJ_DIR)/lal_mie.o $(OBJ_DIR)/lal_mie_ext.o \
$(OBJ_DIR)/lal_soft.o $(OBJ_DIR)/lal_soft_ext.o \
@ -117,6 +118,7 @@ CBNS = $(OBJ_DIR)/device.cubin $(OBJ_DIR)/device_cubin.h \
$(OBJ_DIR)/lj_coul_debye.cubin $(OBJ_DIR)/lj_coul_debye_cubin.h \
$(OBJ_DIR)/coul_dsf.cubin $(OBJ_DIR)/coul_dsf_cubin.h \
$(OBJ_DIR)/sw.cubin $(OBJ_DIR)/sw_cubin.h \
$(OBJ_DIR)/vashishta.cubin $(OBJ_DIR)/vashishta_cubin.h \
$(OBJ_DIR)/beck.cubin $(OBJ_DIR)/beck_cubin.h \
$(OBJ_DIR)/mie.cubin $(OBJ_DIR)/mie_cubin.h \
$(OBJ_DIR)/soft.cubin $(OBJ_DIR)/soft_cubin.h \
@ -613,6 +615,18 @@ $(OBJ_DIR)/lal_coul_dsf.o: $(ALL_H) lal_coul_dsf.h lal_coul_dsf.cpp $(OBJ_DIR)/c
$(OBJ_DIR)/lal_coul_dsf_ext.o: $(ALL_H) lal_coul_dsf.h lal_coul_dsf_ext.cpp lal_base_charge.h
$(CUDR) -o $@ -c lal_coul_dsf_ext.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/vashishta.cubin: lal_vashishta.cu lal_precision.h lal_preprocessor.h
$(CUDA) --cubin -DNV_KERNEL -o $@ lal_vashishta.cu
$(OBJ_DIR)/vashishta_cubin.h: $(OBJ_DIR)/vashishta.cubin $(OBJ_DIR)/vashishta.cubin
$(BIN2C) -c -n vashishta $(OBJ_DIR)/vashishta.cubin > $(OBJ_DIR)/vashishta_cubin.h
$(OBJ_DIR)/lal_vashishta.o: $(ALL_H) lal_vashishta.h lal_vashishta.cpp $(OBJ_DIR)/vashishta_cubin.h $(OBJ_DIR)/lal_base_three.o
$(CUDR) -o $@ -c lal_vashishta.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/lal_vashishta_ext.o: $(ALL_H) lal_vashishta.h lal_vashishta_ext.cpp lal_base_three.h
$(CUDR) -o $@ -c lal_vashishta_ext.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/sw.cubin: lal_sw.cu lal_precision.h lal_preprocessor.h
$(CUDA) --cubin -DNV_KERNEL -o $@ lal_sw.cu

12
lib/gpu/Opencl.makefile
View File

@ -52,6 +52,7 @@ OBJS = $(OBJ_DIR)/lal_atom.o $(OBJ_DIR)/lal_answer.o \
$(OBJ_DIR)/lal_lj_coul_debye.o $(OBJ_DIR)/lal_lj_coul_debye_ext.o \
$(OBJ_DIR)/lal_coul_dsf.o $(OBJ_DIR)/lal_coul_dsf_ext.o \
$(OBJ_DIR)/lal_sw.o $(OBJ_DIR)/lal_sw_ext.o \
$(OBJ_DIR)/lal_vashishta.o $(OBJ_DIR)/lal_vashishta_ext.o \
$(OBJ_DIR)/lal_beck.o $(OBJ_DIR)/lal_beck_ext.o \
$(OBJ_DIR)/lal_mie.o $(OBJ_DIR)/lal_mie_ext.o \
$(OBJ_DIR)/lal_soft.o $(OBJ_DIR)/lal_soft_ext.o \
@ -92,7 +93,7 @@ KERS = $(OBJ_DIR)/device_cl.h $(OBJ_DIR)/atom_cl.h \
$(OBJ_DIR)/tersoff_cl.h $(OBJ_DIR)/tersoff_zbl_cl.h \
$(OBJ_DIR)/tersoff_mod_cl.h $(OBJ_DIR)/coul_cl.h \
$(OBJ_DIR)/coul_debye_cl.h $(OBJ_DIR)/zbl_cl.h \
$(OBJ_DIR)/lj_cubic_cl.h
$(OBJ_DIR)/lj_cubic_cl.h $(OBJ_DIR)/vashishta_cl.h
OCL_EXECS = $(BIN_DIR)/ocl_get_devices
@ -450,6 +451,15 @@ $(OBJ_DIR)/lal_sw.o: $(ALL_H) lal_sw.h lal_sw.cpp $(OBJ_DIR)/sw_cl.h $(OBJ_DIR)
$(OBJ_DIR)/lal_sw_ext.o: $(ALL_H) lal_sw.h lal_sw_ext.cpp lal_base_three.h
$(OCL) -o $@ -c lal_sw_ext.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/vashishta_cl.h: lal_vashishta.cu $(PRE1_H)
$(BSH) ./geryon/file_to_cstr.sh vashishta $(PRE1_H) lal_vashishta.cu $(OBJ_DIR)/vashishta_cl.h;
$(OBJ_DIR)/lal_vashishta.o: $(ALL_H) lal_vashishta.h lal_vashishta.cpp $(OBJ_DIR)/vashishta_cl.h $(OBJ_DIR)/vashishta_cl.h $(OBJ_DIR)/lal_base_three.o
$(OCL) -o $@ -c lal_vashishta.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/lal_vashishta_ext.o: $(ALL_H) lal_vashishta.h lal_vashishta_ext.cpp lal_base_three.h
$(OCL) -o $@ -c lal_vashishta_ext.cpp -I$(OBJ_DIR)
$(OBJ_DIR)/beck_cl.h: lal_beck.cu $(PRE1_H)
$(BSH) ./geryon/file_to_cstr.sh beck $(PRE1_H) lal_beck.cu $(OBJ_DIR)/beck_cl.h;

283
lib/gpu/lal_vashishta.cpp Normal file
View File

@ -0,0 +1,283 @@
/***************************************************************************
vashishta.cpp
-------------------
Anders Hafreager (UiO)
Class for acceleration of the vashishta pair style.
__________________________________________________________________________
This file is part of the LAMMPS Accelerator Library (LAMMPS_AL)
__________________________________________________________________________
begin : Mon June 12, 2017
email : andershaf@gmail.com
***************************************************************************/
#if defined(USE_OPENCL)
#include "vashishta_cl.h"
#elif defined(USE_CUDART)
const char *vashishta=0;
#else
#include "vashishta_cubin.h"
#endif
#include "lal_vashishta.h"
#include <cassert>
using namespace LAMMPS_AL;
#define VashishtaT Vashishta<numtyp, acctyp>
extern Device<PRECISION,ACC_PRECISION> device;
template <class numtyp, class acctyp>
VashishtaT::Vashishta() : BaseThree<numtyp,acctyp>(), _allocated(false) {
}
template <class numtyp, class acctyp>
VashishtaT::~Vashishta() {
clear();
}
template <class numtyp, class acctyp>
int VashishtaT::bytes_per_atom(const int max_nbors) const {
return this->bytes_per_atom_atomic(max_nbors);
}
template <class numtyp, class acctyp>
int VashishtaT::init(const int ntypes, const int nlocal, const int nall, const int max_nbors,
const double cell_size, const double gpu_split, FILE *_screen,
int* host_map, const int nelements, int*** host_elem2param, const int nparams,
const double* cutsq, const double* r0,
const double* gamma, const double* eta,
const double* lam1inv, const double* lam4inv,
const double* zizj, const double* mbigd,
const double* dvrc, const double* big6w,
const double* heta, const double* bigh,
const double* bigw, const double* c0,
const double* costheta, const double* bigb,
const double* big2b, const double* bigc)
{
int success;
success=this->init_three(nlocal,nall,max_nbors,0,cell_size,gpu_split,
_screen,vashishta,"k_vashishta","k_vashishta_three_center",
"k_vashishta_three_end");
if (success!=0)
return success;
// If atom type constants fit in shared memory use fast kernel
int lj_types=ntypes;
shared_types=false;
int max_shared_types=this->device->max_shared_types();
if (lj_types<=max_shared_types && this->_block_size>=max_shared_types) {
lj_types=max_shared_types;
shared_types=true;
}
_lj_types=lj_types;
_nparams = nparams;
_nelements = nelements;
UCL_H_Vec<numtyp4> dview(nparams,*(this->ucl_device),
UCL_WRITE_ONLY);
for (int i=0; i<nparams; i++) {
dview[i].x=(numtyp)0;
dview[i].y=(numtyp)0;
dview[i].z=(numtyp)0;
dview[i].w=(numtyp)0;
}
// pack coefficients into arrays
param1.alloc(nparams,*(this->ucl_device),UCL_READ_ONLY);
for (int i=0; i<nparams; i++) {
dview[i].x=static_cast<numtyp>(eta[i]);
dview[i].y=static_cast<numtyp>(lam1inv[i]);
dview[i].z=static_cast<numtyp>(lam4inv[i]);
dview[i].w=static_cast<numtyp>(zizj[i]);
}
ucl_copy(param1,dview,false);
param1_tex.get_texture(*(this->pair_program),"param1_tex");
param1_tex.bind_float(param1,4);
param2.alloc(nparams,*(this->ucl_device),UCL_READ_ONLY);
for (int i=0; i<nparams; i++) {
dview[i].x=static_cast<numtyp>(mbigd[i]);
dview[i].y=static_cast<numtyp>(dvrc[i]);
dview[i].z=static_cast<numtyp>(big6w[i]);
dview[i].w=static_cast<numtyp>(heta[i]);
}
ucl_copy(param2,dview,false);
param2_tex.get_texture(*(this->pair_program),"param2_tex");
param2_tex.bind_float(param2,4);
param3.alloc(nparams,*(this->ucl_device),UCL_READ_ONLY);
for (int i=0; i<nparams; i++) {
dview[i].x=static_cast<numtyp>(bigh[i]);
dview[i].y=static_cast<numtyp>(bigw[i]);
dview[i].z=static_cast<numtyp>(dvrc[i]);
dview[i].w=static_cast<numtyp>(c0[i]);
}
ucl_copy(param3,dview,false);
param3_tex.get_texture(*(this->pair_program),"param3_tex");
param3_tex.bind_float(param3,4);
param4.alloc(nparams,*(this->ucl_device),UCL_READ_ONLY);
for (int i=0; i<nparams; i++) {
double r0sq = r0[i]*r0[i]-1e-4; // TODO: should we have the 1e-4?
dview[i].x=static_cast<numtyp>(r0sq);
dview[i].y=static_cast<numtyp>(gamma[i]);
dview[i].z=static_cast<numtyp>(cutsq[i]);
dview[i].w=static_cast<numtyp>(r0[i]);
}
ucl_copy(param4,dview,false);
param4_tex.get_texture(*(this->pair_program),"param4_tex");
param4_tex.bind_float(param4,4);
param5.alloc(nparams,*(this->ucl_device),UCL_READ_ONLY);
for (int i=0; i<nparams; i++) {
dview[i].x=static_cast<numtyp>(bigc[i]);
dview[i].y=static_cast<numtyp>(costheta[i]);
dview[i].z=static_cast<numtyp>(bigb[i]);
dview[i].w=static_cast<numtyp>(big2b[i]);
}
ucl_copy(param5,dview,false);
param5_tex.get_texture(*(this->pair_program),"param5_tex");
param5_tex.bind_float(param5,4);
UCL_H_Vec<int> dview_elem2param(nelements*nelements*nelements,
*(this->ucl_device), UCL_WRITE_ONLY);
elem2param.alloc(nelements*nelements*nelements,*(this->ucl_device),
UCL_READ_ONLY);
for (int i = 0; i < nelements; i++)
for (int j = 0; j < nelements; j++)
for (int k = 0; k < nelements; k++) {
int idx = i*nelements*nelements+j*nelements+k;
dview_elem2param[idx] = host_elem2param[i][j][k];
}
ucl_copy(elem2param,dview_elem2param,false);
UCL_H_Vec<int> dview_map(lj_types, *(this->ucl_device), UCL_WRITE_ONLY);
for (int i = 0; i < ntypes; i++)
dview_map[i] = host_map[i];
map.alloc(lj_types,*(this->ucl_device), UCL_READ_ONLY);
ucl_copy(map,dview_map,false);
_allocated=true;
this->_max_bytes=param1.row_bytes()+param2.row_bytes()+param3.row_bytes()+param4.row_bytes()+param5.row_bytes()+
map.row_bytes()+elem2param.row_bytes();
return 0;
}
template <class numtyp, class acctyp>
void VashishtaT::clear() {
if (!_allocated)
return;
_allocated=false;
param1.clear();
param2.clear();
param3.clear();
param4.clear();
param5.clear();
map.clear();
elem2param.clear();
this->clear_atomic();
}
template <class numtyp, class acctyp>
double VashishtaT::host_memory_usage() const {
return this->host_memory_usage_atomic()+sizeof(Vashishta<numtyp,acctyp>);
}
#define KTHREADS this->_threads_per_atom
#define JTHREADS this->_threads_per_atom
// ---------------------------------------------------------------------------
// Calculate energies, forces, and torques
// ---------------------------------------------------------------------------
template <class numtyp, class acctyp>
void VashishtaT::loop(const bool _eflag, const bool _vflag, const int evatom) {
// Compute the block size and grid size to keep all cores busy
int BX=this->block_pair();
int eflag, vflag;
if (_eflag)
eflag=1;
else
eflag=0;
if (_vflag)
vflag=1;
else
vflag=0;
int GX=static_cast<int>(ceil(static_cast<double>(this->ans->inum())/
(BX/this->_threads_per_atom)));
// this->_nbor_data == nbor->dev_packed for gpu_nbor == 0 and tpa > 1
// this->_nbor_data == nbor->dev_nbor for gpu_nbor == 1 or tpa == 1
int ainum=this->ans->inum();
int nbor_pitch=this->nbor->nbor_pitch();
this->time_pair.start();
this->k_pair.set_size(GX,BX);
this->k_pair.run(&this->atom->x, &param1, &param2, &param3, &param4, &param5,
&map, &elem2param, &_nelements,
&this->nbor->dev_nbor, &this->_nbor_data->begin(),
&this->ans->force, &this->ans->engv,
&eflag, &vflag, &ainum, &nbor_pitch,
&this->_threads_per_atom);
BX=this->block_size();
GX=static_cast<int>(ceil(static_cast<double>(this->ans->inum())/
(BX/(KTHREADS*JTHREADS))));
this->k_three_center.set_size(GX,BX);
this->k_three_center.run(&this->atom->x, &param1, &param2, &param3, &param4, &param5,
&map, &elem2param, &_nelements,
&this->nbor->dev_nbor, &this->_nbor_data->begin(),
&this->ans->force, &this->ans->engv, &eflag, &vflag, &ainum,
&nbor_pitch, &this->_threads_per_atom, &evatom);
Answer<numtyp,acctyp> *end_ans;
#ifdef THREE_CONCURRENT
end_ans=this->ans2;
#else
end_ans=this->ans;
#endif
if (evatom!=0) {
this->k_three_end_vatom.set_size(GX,BX);
this->k_three_end_vatom.run(&this->atom->x, &param1, &param2, &param3, &param4, &param5,
&map, &elem2param, &_nelements,
&this->nbor->dev_nbor, &this->_nbor_data->begin(),
&this->nbor->dev_acc,
&end_ans->force, &end_ans->engv, &eflag, &vflag, &ainum,
&nbor_pitch, &this->_threads_per_atom, &this->_gpu_nbor);
} else {
this->k_three_end.set_size(GX,BX);
this->k_three_end.run(&this->atom->x, &param1, &param2, &param3, &param4, &param5,
&map, &elem2param, &_nelements,
&this->nbor->dev_nbor, &this->_nbor_data->begin(),
&this->nbor->dev_acc,
&end_ans->force, &end_ans->engv, &eflag, &vflag, &ainum,
&nbor_pitch, &this->_threads_per_atom, &this->_gpu_nbor);
}
this->time_pair.stop();
}
template class Vashishta<PRECISION,ACC_PRECISION>;

744
lib/gpu/lal_vashishta.cu Normal file
View File

@ -0,0 +1,744 @@
// **************************************************************************
// vashishta.cu
// -------------------
// Anders Hafreager (UiO)
//
// Device code for acceleration of the vashishta pair style
//
// __________________________________________________________________________
// This file is part of the LAMMPS Accelerator Library (LAMMPS_AL)
// __________________________________________________________________________
//
// begin : Mon June 12, 2017
// email : andershaf@gmail.com
// ***************************************************************************/
#ifdef NV_KERNEL
#include "lal_aux_fun1.h"
#ifndef _DOUBLE_DOUBLE
texture<float4> pos_tex;
texture<float4> param1_tex;
texture<float4> param2_tex;
texture<float4> param3_tex;
texture<float4> param4_tex;
texture<float4> param5_tex;
#else
texture<int4,1> pos_tex;
texture<int4> param1_tex;
texture<int4> param2_tex;
texture<int4> param3_tex;
texture<int4> param4_tex;
texture<int4> param5_tex;
#endif
#else
#define pos_tex x_
#define param1_tex param1
#define param2_tex param2
#define param3_tex param3
#define param4_tex param4
#define param5_tex param5
#endif
#define THIRD (numtyp)0.66666666666666666667
//#define THREE_CONCURRENT
#if (ARCH < 300)
#define store_answers_p(f, energy, virial, ii, inum, tid, t_per_atom, offset, \
eflag, vflag, ans, engv) \
if (t_per_atom>1) { \
__local acctyp red_acc[6][BLOCK_ELLIPSE]; \
red_acc[0][tid]=f.x; \
red_acc[1][tid]=f.y; \
red_acc[2][tid]=f.z; \
red_acc[3][tid]=energy; \
for (unsigned int s=t_per_atom/2; s>0; s>>=1) { \
if (offset < s) { \
for (int r=0; r<4; r++) \
red_acc[r][tid] += red_acc[r][tid+s]; \
} \
} \
f.x=red_acc[0][tid]; \
f.y=red_acc[1][tid]; \
f.z=red_acc[2][tid]; \
energy=red_acc[3][tid]; \
if (vflag>0) { \
for (int r=0; r<6; r++) \
red_acc[r][tid]=virial[r]; \
for (unsigned int s=t_per_atom/2; s>0; s>>=1) { \
if (offset < s) { \
for (int r=0; r<6; r++) \
red_acc[r][tid] += red_acc[r][tid+s]; \
} \
} \
for (int r=0; r<6; r++) \
virial[r]=red_acc[r][tid]; \
} \
} \
if (offset==0) { \
int ei=ii; \
if (eflag>0) { \
engv[ei]+=energy*(acctyp)0.5; \
ei+=inum; \
} \
if (vflag>0) { \
for (int i=0; i<6; i++) { \
engv[ei]+=virial[i]*(acctyp)0.5; \
ei+=inum; \
} \
} \
acctyp4 old=ans[ii]; \
old.x+=f.x; \
old.y+=f.y; \
old.z+=f.z; \
ans[ii]=old; \
}
#else
#define store_answers_p(f, energy, virial, ii, inum, tid, t_per_atom, offset, \
eflag, vflag, ans, engv) \
if (t_per_atom>1) { \
for (unsigned int s=t_per_atom/2; s>0; s>>=1) { \
f.x += shfl_xor(f.x, s, t_per_atom); \
f.y += shfl_xor(f.y, s, t_per_atom); \
f.z += shfl_xor(f.z, s, t_per_atom); \
energy += shfl_xor(energy, s, t_per_atom); \
} \
if (vflag>0) { \
for (unsigned int s=t_per_atom/2; s>0; s>>=1) { \
for (int r=0; r<6; r++) \
virial[r] += shfl_xor(virial[r], s, t_per_atom); \
} \
} \
} \
if (offset==0) { \
int ei=ii; \
if (eflag>0) { \
engv[ei]+=energy*(acctyp)0.5; \
ei+=inum; \
} \
if (vflag>0) { \
for (int i=0; i<6; i++) { \
engv[ei]+=virial[i]*(acctyp)0.5; \
ei+=inum; \
} \
} \
acctyp4 old=ans[ii]; \
old.x+=f.x; \
old.y+=f.y; \
old.z+=f.z; \
ans[ii]=old; \
}
#endif
__kernel void k_vashishta(const __global numtyp4 *restrict x_,
const __global numtyp4 *restrict param1,
const __global numtyp4 *restrict param2,
const __global numtyp4 *restrict param3,
const __global numtyp4 *restrict param4,
const __global numtyp4 *restrict param5,
const __global int *restrict map,
const __global int *restrict elem2param,
const int nelements,
const __global int * dev_nbor,
const __global int * dev_packed,
__global acctyp4 *restrict ans,
__global acctyp *restrict engv,
const int eflag, const int vflag, const int inum,
const int nbor_pitch, const int t_per_atom) {
__local int n_stride;
int tid, ii, offset;
atom_info(t_per_atom,ii,tid,offset);
acctyp energy=(acctyp)0;
acctyp4 f;
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
acctyp virial[6];
for (int i=0; i<6; i++)
virial[i]=(acctyp)0;
__syncthreads();
if (ii<inum) {
int nbor, nbor_end;
int i, numj;
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset,i,numj,
n_stride,nbor_end,nbor);
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
int itype=ix.w;
itype=map[itype];
for ( ; nbor<nbor_end; nbor+=n_stride) {
int j=dev_packed[nbor];
j &= NEIGHMASK;
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
int jtype=jx.w;
jtype=map[jtype];
int ijparam=elem2param[itype*nelements*nelements+jtype*nelements+jtype];
// Compute r12
numtyp delx = ix.x-jx.x;
numtyp dely = ix.y-jx.y;
numtyp delz = ix.z-jx.z;
numtyp rsq = delx*delx+dely*dely+delz*delz;
if (rsq<param4[ijparam].z) { // cutsq = param4[ijparam].z
numtyp4 param1_ijparam; fetch4(param1_ijparam,ijparam,param1_tex);
numtyp param1_eta=param1_ijparam.x;
numtyp param1_lam1inv=param1_ijparam.y;
numtyp param1_lam4inv=param1_ijparam.z;
numtyp param1_zizj=param1_ijparam.w;
numtyp4 param2_ijparam; fetch4(param2_ijparam,ijparam,param2_tex);
numtyp param2_mbigd=param2_ijparam.x;
numtyp param2_dvrc =param2_ijparam.y;
numtyp param2_big6w=param2_ijparam.z;
numtyp param2_heta =param2_ijparam.w;
numtyp4 param3_ijparam; fetch4(param3_ijparam,ijparam,param3_tex);
numtyp param3_bigh=param3_ijparam.x;
numtyp param3_bigw=param3_ijparam.y;
numtyp param3_dvrc=param3_ijparam.z;
numtyp param3_c0 =param3_ijparam.w;
numtyp r=sqrt(rsq);
numtyp rinvsq=1.0/rsq;
numtyp r4inv = rinvsq*rinvsq;
numtyp r6inv = rinvsq*r4inv;
numtyp reta = pow(r,-param1_eta);
numtyp lam1r = r*param1_lam1inv;
numtyp lam4r = r*param1_lam4inv;
numtyp vc2 = param1_zizj * exp(-lam1r)/r;
numtyp vc3 = param2_mbigd * r4inv*exp(-lam4r);
numtyp force = (param2_dvrc*r
- (4.0*vc3 + lam4r*vc3+param2_big6w*r6inv
- param2_heta*reta - vc2 - lam1r*vc2)
) * rinvsq;
f.x+=delx*force;
f.y+=dely*force;
f.z+=delz*force;
if (eflag>0)
energy += (param3_bigh*reta+vc2-vc3-param3_bigw*r6inv-r*param3_dvrc+param3_c0);
if (vflag>0) {
virial[0] += delx*delx*force;
virial[1] += dely*dely*force;
virial[2] += delz*delz*force;
virial[3] += delx*dely*force;
virial[4] += delx*delz*force;
virial[5] += dely*delz*force;
}
}
} // for nbor
store_answers(f,energy,virial,ii,inum,tid,t_per_atom,offset,eflag,vflag,
ans,engv);
} // if ii
}
#define threebody(delr1x, delr1y, delr1z, eflag, energy) \
{ \
numtyp r1 = ucl_sqrt(rsq1); \
numtyp rinvsq1 = ucl_recip(rsq1); \
numtyp rainv1 = ucl_recip(r1 - param_r0_ij); \
numtyp gsrainv1 = param_gamma_ij * rainv1; \
numtyp gsrainvsq1 = gsrainv1*rainv1/r1; \
numtyp expgsrainv1 = ucl_exp(gsrainv1); \
\
numtyp r2 = ucl_sqrt(rsq2); \
numtyp rinvsq2 = ucl_recip(rsq2); \
numtyp rainv2 = ucl_recip(r2 - param_r0_ik); \
numtyp gsrainv2 = param_gamma_ik * rainv2; \
numtyp gsrainvsq2 = gsrainv2*rainv2/r2; \
numtyp expgsrainv2 = ucl_exp(gsrainv2); \
\
numtyp rinv12 = ucl_recip(r1*r2); \
numtyp cs = (delr1x*delr2x + delr1y*delr2y + delr1z*delr2z) * rinv12; \
numtyp delcs = cs - param_costheta_ijk; \
numtyp delcssq = delcs*delcs; \
numtyp pcsinv = param_bigc_ijk*delcssq+1.0; \
numtyp pcsinvsq = pcsinv*pcsinv; \
numtyp pcs = delcssq/pcsinv; \
\
numtyp facexp = expgsrainv1*expgsrainv2; \
\
numtyp facrad = param_bigb_ijk * facexp*pcs; \
numtyp frad1 = facrad*gsrainvsq1; \
numtyp frad2 = facrad*gsrainvsq2; \
numtyp facang = param_big2b_ijk * facexp*delcs/pcsinvsq; \
numtyp facang12 = rinv12*facang; \
numtyp csfacang = cs*facang; \
numtyp csfac1 = rinvsq1*csfacang; \
\
fjx = delr1x*(frad1+csfac1)-delr2x*facang12; \
fjy = delr1y*(frad1+csfac1)-delr2y*facang12; \
fjz = delr1z*(frad1+csfac1)-delr2z*facang12; \
\
numtyp csfac2 = rinvsq2*csfacang; \
\
fkx = delr2x*(frad2+csfac2)-delr1x*facang12; \
fky = delr2y*(frad2+csfac2)-delr1y*facang12; \
fkz = delr2z*(frad2+csfac2)-delr1z*facang12; \
\
if (eflag>0) \
energy+=facrad; \
if (vflag>0) { \
virial[0] += delr1x*fjx + delr2x*fkx; \
virial[1] += delr1y*fjy + delr2y*fky; \
virial[2] += delr1z*fjz + delr2z*fkz; \
virial[3] += delr1x*fjy + delr2x*fky; \
virial[4] += delr1x*fjz + delr2x*fkz; \
virial[5] += delr1y*fjz + delr2y*fkz; \
} \
}
#define threebody_half(delr1x, delr1y, delr1z) \
{ \
numtyp r1 = ucl_sqrt(rsq1); \
numtyp rinvsq1 = ucl_recip(rsq1); \
numtyp rainv1 = ucl_recip(r1 - param_r0_ij); \
numtyp gsrainv1 = param_gamma_ij * rainv1; \
numtyp gsrainvsq1 = gsrainv1*rainv1/r1; \
numtyp expgsrainv1 = ucl_exp(gsrainv1); \
\
numtyp r2 = ucl_sqrt(rsq2); \
numtyp rainv2 = ucl_recip(r2 - param_r0_ik); \
numtyp gsrainv2 = param_gamma_ik * rainv2; \
numtyp expgsrainv2 = ucl_exp(gsrainv2); \
\
numtyp rinv12 = ucl_recip(r1*r2); \
numtyp cs = (delr1x*delr2x + delr1y*delr2y + delr1z*delr2z) * rinv12; \
numtyp delcs = cs - param_costheta_ijk; \
numtyp delcssq = delcs*delcs; \
numtyp pcsinv = param_bigc_ijk*delcssq+1.0; \
numtyp pcsinvsq = pcsinv*pcsinv; \
numtyp pcs = delcssq/pcsinv; \
\
numtyp facexp = expgsrainv1*expgsrainv2; \
\
numtyp facrad = param_bigb_ijk * facexp*pcs; \
numtyp frad1 = facrad*gsrainvsq1; \
numtyp facang = param_big2b_ijk * facexp*delcs/pcsinvsq; \
numtyp facang12 = rinv12*facang; \
numtyp csfacang = cs*facang; \
numtyp csfac1 = rinvsq1*csfacang; \
\
fjx = delr1x*(frad1+csfac1)-delr2x*facang12; \
fjy = delr1y*(frad1+csfac1)-delr2y*facang12; \
fjz = delr1z*(frad1+csfac1)-delr2z*facang12; \
}
__kernel void k_vashishta_three_center(const __global numtyp4 *restrict x_,
const __global numtyp4 *restrict param1,
const __global numtyp4 *restrict param2,
const __global numtyp4 *restrict param3,
const __global numtyp4 *restrict param4,
const __global numtyp4 *restrict param5,
const __global int *restrict map,
const __global int *restrict elem2param,
const int nelements,
const __global int * dev_nbor,
const __global int * dev_packed,
__global acctyp4 *restrict ans,
__global acctyp *restrict engv,
const int eflag, const int vflag,
const int inum, const int nbor_pitch,
const int t_per_atom, const int evatom) {
__local int tpa_sq, n_stride;
tpa_sq=fast_mul(t_per_atom,t_per_atom);
numtyp param_gamma_ij, param_r0sq_ij, param_r0_ij, param_gamma_ik, param_r0sq_ik, param_r0_ik;
numtyp param_costheta_ijk, param_bigc_ijk, param_bigb_ijk, param_big2b_ijk;
int tid, ii, offset;
atom_info(tpa_sq,ii,tid,offset);
acctyp energy=(acctyp)0;
acctyp4 f;
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
acctyp virial[6];
for (int i=0; i<6; i++)
virial[i]=(acctyp)0;
__syncthreads();
if (ii<inum) {
int i, numj, nbor_j, nbor_end;
int offset_j=offset/t_per_atom;
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset_j,i,numj,
n_stride,nbor_end,nbor_j);
int offset_k=tid & (t_per_atom-1);
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
int itype=ix.w;
itype=map[itype];
for ( ; nbor_j<nbor_end; nbor_j+=n_stride) {
int j=dev_packed[nbor_j];
j &= NEIGHMASK;
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
int jtype=jx.w;
jtype=map[jtype];
// Compute r12
numtyp delr1x = jx.x-ix.x;
numtyp delr1y = jx.y-ix.y;
numtyp delr1z = jx.z-ix.z;
numtyp rsq1 = delr1x*delr1x+delr1y*delr1y+delr1z*delr1z;
int ijparam=elem2param[itype*nelements*nelements+jtype*nelements+jtype];
numtyp4 param4_ijparam; fetch4(param4_ijparam,ijparam,param4_tex);
param_r0sq_ij=param4_ijparam.x;
if (rsq1 > param_r0sq_ij) continue;
param_gamma_ij=param4_ijparam.y;
param_r0_ij=param4_ijparam.w;
int nbor_k=nbor_j-offset_j+offset_k;
if (nbor_k<=nbor_j)
nbor_k+=n_stride;
for ( ; nbor_k<nbor_end; nbor_k+=n_stride) {
int k=dev_packed[nbor_k];
k &= NEIGHMASK;
numtyp4 kx; fetch4(kx,k,pos_tex);
int ktype=kx.w;
ktype=map[ktype];
int ikparam=elem2param[itype*nelements*nelements+ktype*nelements+ktype];
numtyp4 param4_ikparam; fetch4(param4_ikparam,ikparam,param4_tex);
numtyp delr2x = kx.x-ix.x;
numtyp delr2y = kx.y-ix.y;
numtyp delr2z = kx.z-ix.z;
numtyp rsq2 = delr2x*delr2x + delr2y*delr2y + delr2z*delr2z;
param_r0sq_ik=param4_ikparam.x;
if (rsq2 < param_r0sq_ik) {
param_gamma_ik=param4_ikparam.y;
param_r0_ik=param4_ikparam.w;
int ijkparam=elem2param[itype*nelements*nelements+jtype*nelements+ktype];
numtyp4 param5_ijkparam; fetch4(param5_ijkparam,ijkparam,param5_tex);
param_bigc_ijk=param5_ijkparam.x;
param_bigb_ijk=param5_ijkparam.z;
param_big2b_ijk=param5_ijkparam.w;
param_costheta_ijk=param5_ijkparam.y;
numtyp fjx, fjy, fjz, fkx, fky, fkz;
threebody(delr1x,delr1y,delr1z,eflag,energy);
f.x -= fjx + fkx;
f.y -= fjy + fky;
f.z -= fjz + fkz;
}
}
} // for nbor
numtyp pre;
if (evatom==1)
pre=THIRD;
else
pre=(numtyp)2.0;
energy*=pre;
for (int i=0; i<6; i++)
virial[i]*=pre;
store_answers_p(f,energy,virial,ii,inum,tid,tpa_sq,offset,
eflag,vflag,ans,engv);
} // if ii
}
__kernel void k_vashishta_three_end(const __global numtyp4 *restrict x_,
const __global numtyp4 *restrict param1,
const __global numtyp4 *restrict param2,
const __global numtyp4 *restrict param3,
const __global numtyp4 *restrict param4,
const __global numtyp4 *restrict param5,
const __global int *restrict map,
const __global int *restrict elem2param,
const int nelements,
const __global int * dev_nbor,
const __global int * dev_packed,
const __global int * dev_acc,
__global acctyp4 *restrict ans,
__global acctyp *restrict engv,
const int eflag, const int vflag,
const int inum, const int nbor_pitch,
const int t_per_atom, const int gpu_nbor) {
__local int tpa_sq, n_stride;
tpa_sq=fast_mul(t_per_atom,t_per_atom);
numtyp param_gamma_ij, param_r0sq_ij, param_r0_ij, param_gamma_ik, param_r0sq_ik, param_r0_ik;
numtyp param_costheta_ijk, param_bigc_ijk, param_bigb_ijk, param_big2b_ijk;
int tid, ii, offset;
atom_info(tpa_sq,ii,tid,offset);
acctyp energy=(acctyp)0;
acctyp4 f;
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
acctyp virial[6];
for (int i=0; i<6; i++)
virial[i]=(acctyp)0;
__syncthreads();
if (ii<inum) {
int i, numj, nbor_j, nbor_end, k_end;
int offset_j=offset/t_per_atom;
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset_j,i,numj,
n_stride,nbor_end,nbor_j);
int offset_k=tid & (t_per_atom-1);
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
int itype=ix.w;
itype=map[itype];
for ( ; nbor_j<nbor_end; nbor_j+=n_stride) {
int j=dev_packed[nbor_j];
j &= NEIGHMASK;
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
int jtype=jx.w;
jtype=map[jtype];
// Compute r12
numtyp delr1x = ix.x-jx.x;
numtyp delr1y = ix.y-jx.y;
numtyp delr1z = ix.z-jx.z;
numtyp rsq1 = delr1x*delr1x+delr1y*delr1y+delr1z*delr1z;
int ijparam=elem2param[itype*nelements*nelements+jtype*nelements+jtype];
numtyp4 param4_ijparam; fetch4(param4_ijparam,ijparam,param4_tex);
param_r0sq_ij = param4_ijparam.x;
if (rsq1 > param_r0sq_ij) continue;
param_gamma_ij=param4_ijparam.y;
param_r0_ij = param4_ijparam.w;
int nbor_k,numk;
if (dev_nbor==dev_packed) {
if (gpu_nbor) nbor_k=j+nbor_pitch;
else nbor_k=dev_acc[j]+nbor_pitch;
numk=dev_nbor[nbor_k];
nbor_k+=nbor_pitch+fast_mul(j,t_per_atom-1);
k_end=nbor_k+fast_mul(numk/t_per_atom,n_stride)+(numk & (t_per_atom-1));
nbor_k+=offset_k;
} else {
nbor_k=dev_acc[j]+nbor_pitch;
numk=dev_nbor[nbor_k];
nbor_k+=nbor_pitch;
nbor_k=dev_nbor[nbor_k];
k_end=nbor_k+numk;
nbor_k+=offset_k;
}
for ( ; nbor_k<k_end; nbor_k+=n_stride) {
int k=dev_packed[nbor_k];
k &= NEIGHMASK;
if (k == i) continue;
numtyp4 kx; fetch4(kx,k,pos_tex);
int ktype=kx.w;
ktype=map[ktype];
int ikparam=elem2param[jtype*nelements*nelements+ktype*nelements+ktype]; //jk
numtyp delr2x = kx.x - jx.x;
numtyp delr2y = kx.y - jx.y;
numtyp delr2z = kx.z - jx.z;
numtyp rsq2 = delr2x*delr2x + delr2y*delr2y + delr2z*delr2z;
numtyp4 param4_ikparam; fetch4(param4_ikparam,ikparam,param4_tex);
param_r0sq_ik=param4_ikparam.x;
if (rsq2 < param_r0sq_ik) {
param_gamma_ik=param4_ikparam.y;
param_r0_ik=param4_ikparam.w;
int ijkparam=elem2param[jtype*nelements*nelements+itype*nelements+ktype]; //jik
numtyp4 param5_ijkparam; fetch4(param5_ijkparam,ijkparam,param5_tex);
param_bigc_ijk=param5_ijkparam.x;
param_costheta_ijk=param5_ijkparam.y;
param_bigb_ijk=param5_ijkparam.z;
param_big2b_ijk=param5_ijkparam.w;
numtyp fjx, fjy, fjz;
//if (evatom==0) {
threebody_half(delr1x,delr1y,delr1z);
//} else {
// numtyp fkx, fky, fkz;
// threebody(delr1x,delr1y,delr1z,eflag,energy);
//}
f.x += fjx;
f.y += fjy;
f.z += fjz;
}
}
} // for nbor
#ifdef THREE_CONCURRENT
store_answers(f,energy,virial,ii,inum,tid,tpa_sq,offset,
eflag,vflag,ans,engv);
#else
store_answers_p(f,energy,virial,ii,inum,tid,tpa_sq,offset,
eflag,vflag,ans,engv);
#endif
} // if ii
}
__kernel void k_vashishta_three_end_vatom(const __global numtyp4 *restrict x_,
const __global numtyp4 *restrict param1,
const __global numtyp4 *restrict param2,
const __global numtyp4 *restrict param3,
const __global numtyp4 *restrict param4,
const __global numtyp4 *restrict param5,
const __global int *restrict map,
const __global int *restrict elem2param,
const int nelements,
const __global int * dev_nbor,
const __global int * dev_packed,
const __global int * dev_acc,
__global acctyp4 *restrict ans,
__global acctyp *restrict engv,
const int eflag, const int vflag,
const int inum, const int nbor_pitch,
const int t_per_atom, const int gpu_nbor) {
__local int tpa_sq, n_stride;
tpa_sq=fast_mul(t_per_atom,t_per_atom);
numtyp param_gamma_ij, param_r0sq_ij, param_r0_ij, param_gamma_ik, param_r0sq_ik, param_r0_ik;
numtyp param_costheta_ijk, param_bigc_ijk, param_bigb_ijk, param_big2b_ijk;
int tid, ii, offset;
atom_info(tpa_sq,ii,tid,offset);
acctyp energy=(acctyp)0;
acctyp4 f;
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
acctyp virial[6];
for (int i=0; i<6; i++)
virial[i]=(acctyp)0;
__syncthreads();
if (ii<inum) {
int i, numj, nbor_j, nbor_end, k_end;
int offset_j=offset/t_per_atom;
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset_j,i,numj,
n_stride,nbor_end,nbor_j);
int offset_k=tid & (t_per_atom-1);
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
int itype=ix.w;
itype=map[itype];
for ( ; nbor_j<nbor_end; nbor_j+=n_stride) {
int j=dev_packed[nbor_j];
j &= NEIGHMASK;
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
int jtype=jx.w;
jtype=map[jtype];
// Compute r12
numtyp delr1x = ix.x-jx.x;
numtyp delr1y = ix.y-jx.y;
numtyp delr1z = ix.z-jx.z;
numtyp rsq1 = delr1x*delr1x+delr1y*delr1y+delr1z*delr1z;
int ijparam=elem2param[itype*nelements*nelements+jtype*nelements+jtype];
numtyp4 param4_ijparam; fetch4(param4_ijparam,ijparam,param4_tex);
param_r0sq_ij=param4_ijparam.x;
if (rsq1 > param_r0sq_ij) continue;
param_gamma_ij=param4_ijparam.y;
param_r0_ij=param4_ijparam.w;
int nbor_k,numk;
if (dev_nbor==dev_packed) {
if (gpu_nbor) nbor_k=j+nbor_pitch;
else nbor_k=dev_acc[j]+nbor_pitch;
numk=dev_nbor[nbor_k];
nbor_k+=nbor_pitch+fast_mul(j,t_per_atom-1);
k_end=nbor_k+fast_mul(numk/t_per_atom,n_stride)+(numk & (t_per_atom-1));
nbor_k+=offset_k;
} else {
nbor_k=dev_acc[j]+nbor_pitch;
numk=dev_nbor[nbor_k];
nbor_k+=nbor_pitch;
nbor_k=dev_nbor[nbor_k];
k_end=nbor_k+numk;
nbor_k+=offset_k;
}
for ( ; nbor_k<k_end; nbor_k+=n_stride) {
int k=dev_packed[nbor_k];
k &= NEIGHMASK;
if (k == i) continue;
numtyp4 kx; fetch4(kx,k,pos_tex);
int ktype=kx.w;
ktype=map[ktype];
int ikparam=elem2param[jtype*nelements*nelements+ktype*nelements+ktype]; // jk
numtyp4 param4_ikparam; fetch4(param4_ikparam,ikparam,param4_tex);
numtyp delr2x = kx.x - jx.x;
numtyp delr2y = kx.y - jx.y;
numtyp delr2z = kx.z - jx.z;
numtyp rsq2 = delr2x*delr2x + delr2y*delr2y + delr2z*delr2z;
param_r0sq_ik=param4_ikparam.x;
if (rsq2 < param_r0sq_ik) {
param_gamma_ik=param4_ikparam.y;
param_r0_ik=param4_ikparam.w;
int ijkparam=elem2param[jtype*nelements*nelements+itype*nelements+ktype]; // jik
numtyp4 param5_ijkparam; fetch4(param5_ijkparam,ijkparam,param5_tex);
param_bigc_ijk=param5_ijkparam.x;
param_costheta_ijk=param5_ijkparam.y;
param_bigb_ijk=param5_ijkparam.z;
param_big2b_ijk=param5_ijkparam.w;
numtyp fjx, fjy, fjz, fkx, fky, fkz;
threebody(delr1x,delr1y,delr1z,eflag,energy);
f.x += fjx;
f.y += fjy;
f.z += fjz;
}
}
} // for nbor
energy*=THIRD;
for (int i=0; i<6; i++)
virial[i]*=THIRD;
#ifdef THREE_CONCURRENT
store_answers(f,energy,virial,ii,inum,tid,tpa_sq,offset,
eflag,vflag,ans,engv);
#else
store_answers_p(f,energy,virial,ii,inum,tid,tpa_sq,offset,
eflag,vflag,ans,engv);
#endif
} // if ii
}

97
lib/gpu/lal_vashishta.h Normal file
View File

@ -0,0 +1,97 @@
/***************************************************************************
vashishta.h
-------------------
Anders Hafreager (UiO9)
Class for acceleration of the vashishta pair style.
__________________________________________________________________________
This file is part of the LAMMPS Accelerator Library (LAMMPS_AL)
__________________________________________________________________________
begin : Mon June 12, 2017
email : andershaf@gmail.com
***************************************************************************/
#ifndef LAL_VASHISHTA_H
#define LAL_VASHISHTA_H
#include "lal_base_three.h"
namespace LAMMPS_AL {
template <class numtyp, class acctyp>
class Vashishta : public BaseThree<numtyp, acctyp> {
public:
Vashishta();
~Vashishta();
/// Clear any previous data and set up for a new LAMMPS run
/** \param max_nbors initial number of rows in the neighbor matrix
* \param cell_size cutoff + skin
* \param gpu_split fraction of particles handled by device
*
* Returns:
* - 0 if successfull
* - -1 if fix gpu not found
* - -3 if there is an out of memory error
* - -4 if the GPU library was not compiled for GPU
* - -5 Double precision is not supported on card **/
int init(const int ntypes, const int nlocal, const int nall, const int max_nbors,
const double cell_size, const double gpu_split, FILE *screen,
int* host_map, const int nelements, int*** host_elem2param, const int nparams,
const double* cutsq, const double* r0,
const double* gamma, const double* eta,
const double* lam1inv, const double* lam4inv,
const double* zizj, const double* mbigd,
const double* dvrc, const double* big6w,
const double* heta, const double* bigh,
const double* bigw, const double* c0,
const double* costheta, const double* bigb,
const double* big2b, const double* bigc);
/// Clear all host and device data
/** \note This is called at the beginning of the init() routine **/
void clear();
/// Returns memory usage on device per atom
int bytes_per_atom(const int max_nbors) const;
/// Total host memory used by library for pair style
double host_memory_usage() const;
// --------------------------- TYPE DATA --------------------------
/// If atom type constants fit in shared memory, use fast kernels
bool shared_types;
/// Number of atom types
int _lj_types;
/// param1.x = eta, param1.y = lam1inv, param1.z = lam4inv, param1.w = zizj
UCL_D_Vec<numtyp4> param1;
/// param2.x = mbigd, param2.y = dvrc, param2.z = big6w, param2.w = heta
UCL_D_Vec<numtyp4> param2;
/// param3.x = bigh, param3.y = bigw, param3.z = dvrc, param3.w = c0
UCL_D_Vec<numtyp4> param3;
/// param4.x = r0sq, param4.y = gamma, param4.z = cutsq, param4.w = r0
UCL_D_Vec<numtyp4> param4;
/// param5.x = bigc, param5.y = costheta, param5.z = bigb, param5.w = big2b
UCL_D_Vec<numtyp4> param5;
UCL_D_Vec<int> elem2param;
UCL_D_Vec<int> map;
int _nparams,_nelements;
UCL_Texture param1_tex, param2_tex, param3_tex, param4_tex, param5_tex;
private:
bool _allocated;
void loop(const bool _eflag, const bool _vflag, const int evatom);
};
}
#endif

134
lib/gpu/lal_vashishta_ext.cpp Normal file
View File

@ -0,0 +1,134 @@
/***************************************************************************
vashishta_ext.cpp
-------------------
Anders Hafreager (UiO)
Class for acceleration of the vashishta pair style.
__________________________________________________________________________
This file is part of the LAMMPS Accelerator Library (LAMMPS_AL)
__________________________________________________________________________
begin : Mon June 12, 2017
email : andershaf@gmail.com
***************************************************************************/
#include <iostream>
#include <cassert>
#include <math.h>
#include "lal_vashishta.h"
using namespace LAMMPS_AL;
static Vashishta<PRECISION,ACC_PRECISION> VashishtaMF;
// ---------------------------------------------------------------------------
// Allocate memory on host and device and copy constants to device
// ---------------------------------------------------------------------------
int vashishta_gpu_init(const int ntypes, const int inum, const int nall, const int max_nbors,
const double cell_size, int &gpu_mode, FILE *screen,
int* host_map, const int nelements, int*** host_elem2param, const int nparams,
const double* cutsq, const double* r0,
const double* gamma, const double* eta,
const double* lam1inv, const double* lam4inv,
const double* zizj, const double* mbigd,
const double* dvrc, const double* big6w,
const double* heta, const double* bigh,
const double* bigw, const double* c0,
const double* costheta, const double* bigb,
const double* big2b, const double* bigc) {
VashishtaMF.clear();
gpu_mode=VashishtaMF.device->gpu_mode();
double gpu_split=VashishtaMF.device->particle_split();
int first_gpu=VashishtaMF.device->first_device();
int last_gpu=VashishtaMF.device->last_device();
int world_me=VashishtaMF.device->world_me();
int gpu_rank=VashishtaMF.device->gpu_rank();
int procs_per_gpu=VashishtaMF.device->procs_per_gpu();
// disable host/device split for now
if (gpu_split != 1.0)
return -8;
VashishtaMF.device->init_message(screen,"vashishta/gpu",first_gpu,last_gpu);
bool message=false;
if (VashishtaMF.device->replica_me()==0 && screen)
message=true;
if (message) {
fprintf(screen,"Initializing Device and compiling on process 0...");
fflush(screen);
}
int init_ok=0;
if (world_me==0)
init_ok=VashishtaMF.init(ntypes, inum, nall, 500, cell_size, gpu_split, screen,
host_map, nelements, host_elem2param, nparams,
cutsq, r0, gamma, eta, lam1inv,
lam4inv, zizj, mbigd, dvrc, big6w, heta, bigh, bigw,
c0, costheta, bigb, big2b, bigc);
VashishtaMF.device->world_barrier();
if (message)
fprintf(screen,"Done.\n");
for (int i=0; i<procs_per_gpu; i++) {
if (message) {
if (last_gpu-first_gpu==0)
fprintf(screen,"Initializing Device %d on core %d...",first_gpu,i);
else
fprintf(screen,"Initializing Devices %d-%d on core %d...",first_gpu,
last_gpu,i);
fflush(screen);
}
if (gpu_rank==i && world_me!=0)
init_ok=VashishtaMF.init(ntypes, inum, nall, 500, cell_size, gpu_split, screen,
host_map, nelements, host_elem2param, nparams,
cutsq, r0, gamma, eta, lam1inv,
lam4inv, zizj, mbigd, dvrc, big6w, heta, bigh, bigw,
c0, costheta, bigb, big2b, bigc);
VashishtaMF.device->gpu_barrier();
if (message)
fprintf(screen,"Done.\n");
}
if (message)
fprintf(screen,"\n");
if (init_ok==0)
VashishtaMF.estimate_gpu_overhead();
return init_ok;
}
void vashishta_gpu_clear() {
VashishtaMF.clear();
}
int ** vashishta_gpu_compute_n(const int ago, const int inum_full,
const int nall, double **host_x, int *host_type,
double *sublo, double *subhi, tagint *tag, int **nspecial,
tagint **special, const bool eflag, const bool vflag,
const bool eatom, const bool vatom, int &host_start,
int **ilist, int **jnum, const double cpu_time,
bool &success) {
return VashishtaMF.compute(ago, inum_full, nall, host_x, host_type, sublo,
subhi, tag, nspecial, special, eflag, vflag, eatom,
vatom, host_start, ilist, jnum, cpu_time, success);
}
void vashishta_gpu_compute(const int ago, const int nlocal, const int nall,
const int nlist, double **host_x, int *host_type,
int *ilist, int *numj, int **firstneigh, const bool eflag,
const bool vflag, const bool eatom, const bool vatom,
int &host_start, const double cpu_time, bool &success) {
VashishtaMF.compute(ago,nlocal,nall,nlist,host_x,host_type,ilist,numj,
firstneigh,eflag,vflag,eatom,vatom,host_start,cpu_time,success);
}
double vashishta_gpu_bytes() {
return VashishtaMF.host_memory_usage();
}

48
lib/kokkos/CHANGELOG.md
View File

@ -1,5 +1,53 @@
# Change Log
## [2.03.05](https://github.com/kokkos/kokkos/tree/2.03.05) (2017-05-27)
[Full Changelog](https://github.com/kokkos/kokkos/compare/2.03.00...2.03.05)
**Implemented enhancements:**
- Harmonize Custom Reductions over nesting levels [\#802](https://github.com/kokkos/kokkos/issues/802)
- Prevent users directly including KokkosCore\_config.h [\#815](https://github.com/kokkos/kokkos/issues/815)
- DualView aborts on concurrent host/device modify \(in debug mode\) [\#814](https://github.com/kokkos/kokkos/issues/814)
- Abort when running on a NVIDIA CC5.0 or higher architecture with code compiled for CC \< 5.0 [\#813](https://github.com/kokkos/kokkos/issues/813)
- Add "name" function to ExecSpaces [\#806](https://github.com/kokkos/kokkos/issues/806)
- Allow null Future in task spawn dependences [\#795](https://github.com/kokkos/kokkos/issues/795)
- Add Unit Tests for Kokkos::complex [\#785](https://github.com/kokkos/kokkos/issues/785)
- Add pow function for Kokkos::complex [\#784](https://github.com/kokkos/kokkos/issues/784)
- Square root of a complex [\#729](https://github.com/kokkos/kokkos/issues/729)
- Command line processing of --threads argument prevents users from having any commandline arguments starting with --threads [\#760](https://github.com/kokkos/kokkos/issues/760)
- Protected deprecated API with appropriate macro [\#756](https://github.com/kokkos/kokkos/issues/756)
- Allow task scheduler memory pool to be used by tasks [\#747](https://github.com/kokkos/kokkos/issues/747)
- View bounds checking on host-side performance: constructing a std::string [\#723](https://github.com/kokkos/kokkos/issues/723)
- Add check for AppleClang as compiler distinct from check for Clang. [\#705](https://github.com/kokkos/kokkos/issues/705)
- Uninclude source files for specific configurations to prevent link warning. [\#701](https://github.com/kokkos/kokkos/issues/701)
- Add --small option to snapshot script [\#697](https://github.com/kokkos/kokkos/issues/697)
- CMake Standalone Support [\#674](https://github.com/kokkos/kokkos/issues/674)
- CMake build unit test and install [\#808](https://github.com/kokkos/kokkos/issues/808)
- CMake: Fix having kokkos as a subdirectory in a pure cmake project [\#629](https://github.com/kokkos/kokkos/issues/629)
- Tribits macro assumes build directory is in top level source directory [\#654](https://github.com/kokkos/kokkos/issues/654)
- Use bin/nvcc\_wrapper, not config/nvcc\_wrapper [\#562](https://github.com/kokkos/kokkos/issues/562)
- Allow MemoryPool::allocate\(\) to be called from multiple threads per warp. [\#487](https://github.com/kokkos/kokkos/issues/487)
- Allow MemoryPool::allocate\\(\\) to be called from multiple threads per warp. [\#487](https://github.com/kokkos/kokkos/issues/487)
- Move OpenMP 4.5 OpenMPTarget backend into Develop [\#456](https://github.com/kokkos/kokkos/issues/456)
- Testing on ARM testbed [\#288](https://github.com/kokkos/kokkos/issues/288)
**Fixed bugs:**
- Fix label in OpenMP parallel\_reduce verify\_initialized [\#834](https://github.com/kokkos/kokkos/issues/834)
- TeamScratch Level 1 on Cuda hangs [\#820](https://github.com/kokkos/kokkos/issues/820)
- \[bug\] memory pool. [\#786](https://github.com/kokkos/kokkos/issues/786)
- Some Reduction Tests fail on Intel 18 with aggressive vectorization on [\#774](https://github.com/kokkos/kokkos/issues/774)
- Error copying dynamic view on copy of memory pool [\#773](https://github.com/kokkos/kokkos/issues/773)
- CUDA stack overflow with TaskDAG test [\#758](https://github.com/kokkos/kokkos/issues/758)
- ThreadVectorRange Customized Reduction Bug [\#739](https://github.com/kokkos/kokkos/issues/739)
- set\_scratch\_size overflows [\#726](https://github.com/kokkos/kokkos/issues/726)
- Get wrong results for compiler checks in Makefile on OS X. [\#706](https://github.com/kokkos/kokkos/issues/706)
- Fix check if multiple host architectures enabled. [\#702](https://github.com/kokkos/kokkos/issues/702)
- Threads Backend Does not Pass on Cray Compilers [\#609](https://github.com/kokkos/kokkos/issues/609)
- Rare bug in memory pool where allocation can finish on superblock in empty state [\#452](https://github.com/kokkos/kokkos/issues/452)
- LDFLAGS in core/unit\_test/Makefile: potential "undefined reference" to pthread lib [\#148](https://github.com/kokkos/kokkos/issues/148)
## [2.03.00](https://github.com/kokkos/kokkos/tree/2.03.00) (2017-04-25)
[Full Changelog](https://github.com/kokkos/kokkos/compare/2.02.15...2.03.00)

40
lib/kokkos/CMakeLists.txt
View File

@ -5,11 +5,12 @@ ELSE()
ENDIF()
IF(NOT KOKKOS_HAS_TRILINOS)
CMAKE_MINIMUM_REQUIRED(VERSION 2.8.11 FATAL_ERROR)
INCLUDE(cmake/tribits.cmake)
SET(CMAKE_CXX_STANDARD 11)
ENDIF()
cmake_minimum_required(VERSION 3.1 FATAL_ERROR)
project(Kokkos CXX)
INCLUDE(cmake/kokkos.cmake)
ELSE()
#------------------------------------------------------------------------------
#
# A) Forward delcare the package so that certain options are also defined for
# subpackages
@ -17,14 +18,13 @@ ENDIF()
TRIBITS_PACKAGE_DECL(Kokkos) # ENABLE_SHADOWING_WARNINGS)
#------------------------------------------------------------------------------
#
# B) Define the common options for Kokkos first so they can be used by
# subpackages as well.
#
# mfh 01 Aug 2016: See Issue #61:
#
# https://github.com/kokkos/kokkos/issues/61
@ -98,12 +98,13 @@ TRIBITS_ADD_OPTION_AND_DEFINE(
)
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_Qthreads
Kokkos_ENABLE_QTHREAD
KOKKOS_HAVE_QTHREADS
"Enable Qthreads support in Kokkos."
"${TPL_ENABLE_QTHREADS}"
"${TPL_ENABLE_QTHREAD}"
)
# TODO: No longer an option in Kokkos. Needs to be removed.
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_CXX11
KOKKOS_HAVE_CXX11
@ -118,6 +119,7 @@ TRIBITS_ADD_OPTION_AND_DEFINE(
"${TPL_ENABLE_HWLOC}"
)
# TODO: This is currently not used in Kokkos. Should it be removed?
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_MPI
KOKKOS_HAVE_MPI
@ -154,13 +156,27 @@ TRIBITS_ADD_OPTION_AND_DEFINE(
"${Kokkos_ENABLE_Debug_Bounds_Check_DEFAULT}"
)
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_Debug_DualView_Modify_Check
KOKKOS_ENABLE_DEBUG_DUALVIEW_MODIFY_CHECK
"Enable abort when Kokkos::DualView modified on host and device without sync."
"${Kokkos_ENABLE_DEBUG}"
)
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_Profiling
KOKKOS_ENABLE_PROFILING_INTERNAL
KOKKOS_ENABLE_PROFILING
"Enable KokkosP profiling support for kernel data collections."
"${TPL_ENABLE_DLlib}"
)
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_Profiling_Load_Print
KOKKOS_ENABLE_PROFILING_LOAD_PRINT
"Print to standard output which profiling library was loaded."
OFF
)
# placeholder for future device...
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_ENABLE_Winthread
@ -169,6 +185,7 @@ TRIBITS_ADD_OPTION_AND_DEFINE(
"${TPL_ENABLE_Winthread}"
)
# TODO: No longer an option in Kokkos. Needs to be removed.
# use new/old View
TRIBITS_ADD_OPTION_AND_DEFINE(
Kokkos_USING_DEPRECATED_VIEW
@ -177,12 +194,12 @@ TRIBITS_ADD_OPTION_AND_DEFINE(
OFF
)
#------------------------------------------------------------------------------
#
# C) Install Kokkos' executable scripts
#
# nvcc_wrapper is Kokkos' wrapper for NVIDIA's NVCC CUDA compiler.
# Kokkos needs nvcc_wrapper in order to build. Other libraries and
# executables also need nvcc_wrapper. Thus, we need to install it.
@ -199,6 +216,8 @@ INSTALL(PROGRAMS ${CMAKE_CURRENT_SOURCE_DIR}/bin/nvcc_wrapper DESTINATION bin)
TRIBITS_PROCESS_SUBPACKAGES()
#------------------------------------------------------------------------------
#
# E) If Kokkos itself is enabled, process the Kokkos package
#
@ -213,3 +232,4 @@ TRIBITS_EXCLUDE_FILES(
)
TRIBITS_PACKAGE_POSTPROCESS()
ENDIF()

220
lib/kokkos/Makefile.kokkos
View File

@ -35,13 +35,16 @@ KOKKOS_INTERNAL_USE_MEMKIND := $(strip $(shell echo $(KOKKOS_USE_TPLS) | grep "e
# Check for advanced settings.
KOKKOS_INTERNAL_OPT_RANGE_AGGRESSIVE_VECTORIZATION := $(strip $(shell echo $(KOKKOS_OPTIONS) | grep "aggressive_vectorization" | wc -l))
KOKKOS_INTERNAL_DISABLE_PROFILING := $(strip $(shell echo $(KOKKOS_OPTIONS) | grep "disable_profiling" | wc -l))
KOKKOS_INTERNAL_DISABLE_DUALVIEW_MODIFY_CHECK := $(strip $(shell echo $(KOKKOS_OPTIONS) | grep "disable_dualview_modify_check" | wc -l))
KOKKOS_INTERNAL_ENABLE_PROFILING_LOAD_PRINT := $(strip $(shell echo $(KOKKOS_OPTIONS) | grep "enable_profile_load_print" | wc -l))
KOKKOS_INTERNAL_CUDA_USE_LDG := $(strip $(shell echo $(KOKKOS_CUDA_OPTIONS) | grep "use_ldg" | wc -l))
KOKKOS_INTERNAL_CUDA_USE_UVM := $(strip $(shell echo $(KOKKOS_CUDA_OPTIONS) | grep "force_uvm" | wc -l))
KOKKOS_INTERNAL_CUDA_USE_RELOC := $(strip $(shell echo $(KOKKOS_CUDA_OPTIONS) | grep "rdc" | wc -l))
KOKKOS_INTERNAL_CUDA_USE_LAMBDA := $(strip $(shell echo $(KOKKOS_CUDA_OPTIONS) | grep "enable_lambda" | wc -l))
# Check for Kokkos Host Execution Spaces one of which must be on.
KOKKOS_INTERNAL_USE_OPENMP := $(strip $(shell echo $(KOKKOS_DEVICES) | grep OpenMP | wc -l))
KOKKOS_INTERNAL_USE_OPENMPTARGET := $(strip $(shell echo $(KOKKOS_DEVICES) | grep OpenMPTarget | wc -l))
KOKKOS_INTERNAL_USE_OPENMP := $(strip $(shell echo $(subst OpenMPTarget,,$(KOKKOS_DEVICES)) | grep OpenMP | wc -l))
KOKKOS_INTERNAL_USE_PTHREADS := $(strip $(shell echo $(KOKKOS_DEVICES) | grep Pthread | wc -l))
KOKKOS_INTERNAL_USE_QTHREADS := $(strip $(shell echo $(KOKKOS_DEVICES) | grep Qthreads | wc -l))
KOKKOS_INTERNAL_USE_SERIAL := $(strip $(shell echo $(KOKKOS_DEVICES) | grep Serial | wc -l))
@ -64,24 +67,25 @@ ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
endif
# Check OS.
KOKKOS_OS := $(shell uname -s)
KOKKOS_INTERNAL_OS_CYGWIN := $(shell uname -s | grep CYGWIN | wc -l)
KOKKOS_INTERNAL_OS_LINUX := $(shell uname -s | grep Linux | wc -l)
KOKKOS_INTERNAL_OS_DARWIN := $(shell uname -s | grep Darwin | wc -l)
KOKKOS_OS := $(strip $(shell uname -s))
KOKKOS_INTERNAL_OS_CYGWIN := $(strip $(shell uname -s | grep CYGWIN | wc -l))
KOKKOS_INTERNAL_OS_LINUX := $(strip $(shell uname -s | grep Linux | wc -l))
KOKKOS_INTERNAL_OS_DARWIN := $(strip $(shell uname -s | grep Darwin | wc -l))
# Check compiler.
KOKKOS_INTERNAL_COMPILER_INTEL := $(shell $(CXX) --version 2>&1 | grep "Intel Corporation" | wc -l)
KOKKOS_INTERNAL_COMPILER_PGI := $(shell $(CXX) --version 2>&1 | grep PGI | wc -l)
KOKKOS_INTERNAL_COMPILER_XL := $(shell $(CXX) -qversion 2>&1 | grep XL | wc -l)
KOKKOS_INTERNAL_COMPILER_CRAY := $(shell $(CXX) -craype-verbose 2>&1 | grep "CC-" | wc -l)
KOKKOS_INTERNAL_COMPILER_NVCC := $(shell $(CXX) --version 2>&1 | grep "nvcc" | wc -l)
KOKKOS_INTERNAL_COMPILER_INTEL := $(strip $(shell $(CXX) --version 2>&1 | grep "Intel Corporation" | wc -l))
KOKKOS_INTERNAL_COMPILER_PGI := $(strip $(shell $(CXX) --version 2>&1 | grep PGI | wc -l))
KOKKOS_INTERNAL_COMPILER_XL := $(strip $(shell $(CXX) -qversion 2>&1 | grep XL | wc -l))
KOKKOS_INTERNAL_COMPILER_CRAY := $(strip $(shell $(CXX) -craype-verbose 2>&1 | grep "CC-" | wc -l))
KOKKOS_INTERNAL_COMPILER_NVCC := $(strip $(shell $(CXX) --version 2>&1 | grep nvcc | wc -l))
KOKKOS_INTERNAL_COMPILER_CLANG := $(strip $(shell $(CXX) --version 2>&1 | grep clang | wc -l))
KOKKOS_INTERNAL_COMPILER_APPLE_CLANG := $(strip $(shell $(CXX) --version 2>&1 | grep "apple-darwin" | wc -l))
ifneq ($(OMPI_CXX),)
KOKKOS_INTERNAL_COMPILER_NVCC := $(shell $(OMPI_CXX) --version 2>&1 | grep "nvcc" | wc -l)
KOKKOS_INTERNAL_COMPILER_NVCC := $(strip $(shell $(OMPI_CXX) --version 2>&1 | grep "nvcc" | wc -l))
endif
ifneq ($(MPICH_CXX),)
KOKKOS_INTERNAL_COMPILER_NVCC := $(shell $(MPICH_CXX) --version 2>&1 | grep "nvcc" | wc -l)
KOKKOS_INTERNAL_COMPILER_NVCC := $(strip $(shell $(MPICH_CXX) --version 2>&1 | grep "nvcc" | wc -l))
endif
KOKKOS_INTERNAL_COMPILER_CLANG := $(shell $(CXX) --version 2>&1 | grep "clang" | wc -l)
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 2)
KOKKOS_INTERNAL_COMPILER_CLANG = 1
@ -90,6 +94,11 @@ ifeq ($(KOKKOS_INTERNAL_COMPILER_XL), 2)
KOKKOS_INTERNAL_COMPILER_XL = 1
endif
# Apple Clang passes both clang and apple clang tests, so turn off clang.
ifeq ($(KOKKOS_INTERNAL_COMPILER_APPLE_CLANG), 1)
KOKKOS_INTERNAL_COMPILER_CLANG = 0
endif
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_COMPILER_CLANG_VERSION := $(shell clang --version | grep version | cut -d ' ' -f3 | tr -d '.')
@ -97,15 +106,20 @@ ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
ifeq ($(shell test $(KOKKOS_INTERNAL_COMPILER_CLANG_VERSION) -lt 400; echo $$?),0)
$(error Compiling Cuda code directly with Clang requires version 4.0.0 or higher)
endif
KOKKOS_INTERNAL_CUDA_USE_LAMBDA := 1
endif
endif
# Set OpenMP flags.
ifeq ($(KOKKOS_INTERNAL_COMPILER_PGI), 1)
KOKKOS_INTERNAL_OPENMP_FLAG := -mp
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_OPENMP_FLAG := -fopenmp=libomp
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_APPLE_CLANG), 1)
KOKKOS_INTERNAL_OPENMP_FLAG := -fopenmp=libomp
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_XL), 1)
KOKKOS_INTERNAL_OPENMP_FLAG := -qsmp=omp
@ -119,7 +133,16 @@ else
endif
endif
endif
endif
ifeq ($(KOKKOS_INTERNAL_COMPILER_XL), 1)
KOKKOS_INTERNAL_OPENMPTARGET_FLAG := -DKOKKOS_IBM_XL_OMP45_WORKAROUND -qsmp=omp -qoffload -qnoeh
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_OPENMPTARGET_FLAG := -DKOKKOS_BUG_WORKAROUND_IBM_CLANG_OMP45_VIEW_INIT -fopenmp-implicit-declare-target -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp -fopenmp=libomp
endif
endif
# Set C++11 flags.
ifeq ($(KOKKOS_INTERNAL_COMPILER_PGI), 1)
KOKKOS_INTERNAL_CXX11_FLAG := --c++11
else
@ -146,7 +169,7 @@ KOKKOS_INTERNAL_USE_ARCH_SKX := $(strip $(shell echo $(KOKKOS_ARCH) | grep SKX |
KOKKOS_INTERNAL_USE_ARCH_KNL := $(strip $(shell echo $(KOKKOS_ARCH) | grep KNL | wc -l))
# NVIDIA based.
NVCC_WRAPPER := $(KOKKOS_PATH)/config/nvcc_wrapper
NVCC_WRAPPER := $(KOKKOS_PATH)/bin/nvcc_wrapper
KOKKOS_INTERNAL_USE_ARCH_KEPLER30 := $(strip $(shell echo $(KOKKOS_ARCH) | grep Kepler30 | wc -l))
KOKKOS_INTERNAL_USE_ARCH_KEPLER32 := $(strip $(shell echo $(KOKKOS_ARCH) | grep Kepler32 | wc -l))
KOKKOS_INTERNAL_USE_ARCH_KEPLER35 := $(strip $(shell echo $(KOKKOS_ARCH) | grep Kepler35 | wc -l))
@ -180,10 +203,20 @@ ifeq ($(KOKKOS_INTERNAL_USE_ARCH_NVIDIA), 0)
+ $(KOKKOS_INTERNAL_USE_ARCH_MAXWELL53) | bc))
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_NVIDIA), 1)
ifeq ($(KOKKOS_INTERNAL_USE_OPENMPTARGET), 1)
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_NVCC_PATH := $(shell which nvcc)
CUDA_PATH ?= $(KOKKOS_INTERNAL_NVCC_PATH:/bin/nvcc=)
KOKKOS_INTERNAL_OPENMPTARGET_FLAG := $(KOKKOS_INTERNAL_OPENMPTARGET_FLAG) --cuda-path=$(CUDA_PATH)
endif
endif
endif
# ARM based.
KOKKOS_INTERNAL_USE_ARCH_ARMV80 := $(strip $(shell echo $(KOKKOS_ARCH) | grep ARMv80 | wc -l))
KOKKOS_INTERNAL_USE_ARCH_ARMV81 := $(strip $(shell echo $(KOKKOS_ARCH) | grep ARMv81 | wc -l))
KOKKOS_INTERNAL_USE_ARCH_ARMV8_THUNDERX := $(strip $(shell echo $(KOKKOS_ARCH) | grep ARMv8-ThunderX | wc -l))
KOKKOS_INTERNAL_USE_ARCH_ARM := $(strip $(shell echo $(KOKKOS_INTERNAL_USE_ARCH_ARMV80)+$(KOKKOS_INTERNAL_USE_ARCH_ARMV81)+$(KOKKOS_INTERNAL_USE_ARCH_ARMV8_THUNDERX) | bc))
# IBM based.
KOKKOS_INTERNAL_USE_ARCH_BGQ := $(strip $(shell echo $(KOKKOS_ARCH) | grep BGQ | wc -l))
@ -206,8 +239,11 @@ KOKKOS_INTERNAL_USE_ISA_X86_64 := $(strip $(shell echo $(KOKKOS_INTERNAL_USE_
KOKKOS_INTERNAL_USE_ISA_KNC := $(strip $(shell echo $(KOKKOS_INTERNAL_USE_ARCH_KNC) | bc ))
KOKKOS_INTERNAL_USE_ISA_POWERPCLE := $(strip $(shell echo $(KOKKOS_INTERNAL_USE_ARCH_POWER8)+$(KOKKOS_INTERNAL_USE_ARCH_POWER9) | bc ))
# Decide whether we can support transactional memory
KOKKOS_INTERNAL_USE_TM := $(strip $(shell echo $(KOKKOS_INTERNAL_USE_ARCH_BDW)+$(KOKKOS_INTERNAL_USE_ARCH_SKX) | bc ))
# Incompatible flags?
KOKKOS_INTERNAL_USE_ARCH_MULTIHOST := $(strip $(shell echo "$(KOKKOS_INTERNAL_USE_ARCH_AVX)+$(KOKKOS_INTERNAL_USE_ARCH_AVX2)+$(KOKKOS_INTERNAL_USE_ARCH_KNC)+$(KOKKOS_INTERNAL_USE_ARCH_IBM)+$(KOKKOS_INTERNAL_USE_ARCH_AMDAVX)+$(KOKKOS_INTERNAL_USE_ARCH_ARMV80)+$(KOKKOS_INTERNAL_USE_ARCH_ARMV81)+$(KOKKOS_INTERNAL_USE_ARCH_ARMV8_THUNDERX)>1" | bc ))
KOKKOS_INTERNAL_USE_ARCH_MULTIHOST := $(strip $(shell echo "$(KOKKOS_INTERNAL_USE_ARCH_AVX)+$(KOKKOS_INTERNAL_USE_ARCH_AVX2)+$(KOKKOS_INTERNAL_USE_ARCH_AVX512MIC)+$(KOKKOS_INTERNAL_USE_ARCH_AVX512XEON)+$(KOKKOS_INTERNAL_USE_ARCH_KNC)+$(KOKKOS_INTERNAL_USE_ARCH_IBM)+$(KOKKOS_INTERNAL_USE_ARCH_ARM)>1" | bc ))
KOKKOS_INTERNAL_USE_ARCH_MULTIGPU := $(strip $(shell echo "$(KOKKOS_INTERNAL_USE_ARCH_NVIDIA)>1" | bc))
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_MULTIHOST), 1)
@ -240,12 +276,22 @@ tmp := $(shell echo "Makefile constructed configuration:" >> KokkosCore_config.t
tmp := $(shell date >> KokkosCore_config.tmp)
tmp := $(shell echo "----------------------------------------------*/" >> KokkosCore_config.tmp)
tmp := $(shell echo '\#if !defined(KOKKOS_MACROS_HPP) || defined(KOKKOS_CORE_CONFIG_H)' >> KokkosCore_config.tmp)
tmp := $(shell echo '\#error "Do not include KokkosCore_config.h directly; include Kokkos_Macros.hpp instead."' >> KokkosCore_config.tmp)
tmp := $(shell echo '\#else' >> KokkosCore_config.tmp)
tmp := $(shell echo '\#define KOKKOS_CORE_CONFIG_H' >> KokkosCore_config.tmp)
tmp := $(shell echo '\#endif' >> KokkosCore_config.tmp)
tmp := $(shell echo "/* Execution Spaces */" >> KokkosCore_config.tmp)
ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
tmp := $(shell echo "\#define KOKKOS_HAVE_CUDA 1" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMPTARGET), 1)
tmp := $(shell echo '\#define KOKKOS_ENABLE_OPENMPTARGET 1' >> KokkosCore_config.tmp)
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMP), 1)
tmp := $(shell echo '\#define KOKKOS_HAVE_OPENMP 1' >> KokkosCore_config.tmp)
endif
@ -262,6 +308,12 @@ ifeq ($(KOKKOS_INTERNAL_USE_SERIAL), 1)
tmp := $(shell echo "\#define KOKKOS_HAVE_SERIAL 1" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_USE_TM), 1)
tmp := $(shell echo "\#ifndef __CUDA_ARCH__" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ENABLE_TM" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#endif" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_USE_ISA_X86_64), 1)
tmp := $(shell echo "\#ifndef __CUDA_ARCH__" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_USE_ISA_X86_64" >> KokkosCore_config.tmp )
@ -296,10 +348,18 @@ ifeq ($(KOKKOS_INTERNAL_ENABLE_DEBUG), 1)
ifeq ($(KOKKOS_INTERNAL_COMPILER_NVCC), 1)
KOKKOS_CXXFLAGS += -lineinfo
endif
KOKKOS_CXXFLAGS += -g
KOKKOS_LDFLAGS += -g -ldl
tmp := $(shell echo "\#define KOKKOS_ENABLE_DEBUG_BOUNDS_CHECK 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_HAVE_DEBUG 1" >> KokkosCore_config.tmp )
ifeq ($(KOKKOS_INTERNAL_DISABLE_DUALVIEW_MODIFY_CHECK), 0)
tmp := $(shell echo "\#define KOKKOS_ENABLE_DEBUG_DUALVIEW_MODIFY_CHECK 1" >> KokkosCore_config.tmp )
endif
endif
ifeq ($(KOKKOS_INTERNAL_ENABLE_PROFILING_LOAD_PRINT), 1)
tmp := $(shell echo "\#define KOKKOS_ENABLE_PROFILING_LOAD_PRINT 1" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_USE_HWLOC), 1)
@ -311,8 +371,6 @@ endif
ifeq ($(KOKKOS_INTERNAL_USE_LIBRT), 1)
tmp := $(shell echo "\#define KOKKOS_USE_LIBRT 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define PREC_TIMER 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOSP_ENABLE_RTLIB 1" >> KokkosCore_config.tmp )
KOKKOS_LIBS += -lrt
endif
@ -323,8 +381,8 @@ ifeq ($(KOKKOS_INTERNAL_USE_MEMKIND), 1)
tmp := $(shell echo "\#define KOKKOS_HAVE_HBWSPACE 1" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_DISABLE_PROFILING), 1)
tmp := $(shell echo "\#define KOKKOS_ENABLE_PROFILING 0" >> KokkosCore_config.tmp )
ifeq ($(KOKKOS_INTERNAL_DISABLE_PROFILING), 0)
tmp := $(shell echo "\#define KOKKOS_ENABLE_PROFILING" >> KokkosCore_config.tmp )
endif
tmp := $(shell echo "/* Optimization Settings */" >> KokkosCore_config.tmp)
@ -336,14 +394,16 @@ endif
tmp := $(shell echo "/* Cuda Settings */" >> KokkosCore_config.tmp)
ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
ifeq ($(KOKKOS_INTERNAL_CUDA_USE_LDG), 1)
tmp := $(shell echo "\#define KOKKOS_CUDA_USE_LDG_INTRINSIC 1" >> KokkosCore_config.tmp )
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
tmp := $(shell echo "\#define KOKKOS_CUDA_USE_LDG_INTRINSIC 1" >> KokkosCore_config.tmp )
endif
endif
ifeq ($(KOKKOS_INTERNAL_CUDA_USE_UVM), 1)
tmp := $(shell echo "\#define KOKKOS_CUDA_USE_UVM 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_USE_CUDA_UVM 1" >> KokkosCore_config.tmp )
endif
ifeq ($(KOKKOS_INTERNAL_CUDA_USE_RELOC), 1)
@ -367,6 +427,9 @@ ifeq ($(KOKKOS_INTERNAL_CUDA_USE_LAMBDA), 1)
endif
endif
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
tmp := $(shell echo "\#define KOKKOS_CUDA_CLANG_WORKAROUND" >> KokkosCore_config.tmp )
endif
endif
# Add Architecture flags.
@ -469,7 +532,7 @@ ifeq ($(KOKKOS_INTERNAL_USE_ARCH_POWER9), 1)
endif
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_AVX2), 1)
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_HSW), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_AVX2 1" >> KokkosCore_config.tmp )
ifeq ($(KOKKOS_INTERNAL_COMPILER_INTEL), 1)
@ -491,6 +554,28 @@ ifeq ($(KOKKOS_INTERNAL_USE_ARCH_AVX2), 1)
endif
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_BDW), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_AVX2 1" >> KokkosCore_config.tmp )
ifeq ($(KOKKOS_INTERNAL_COMPILER_INTEL), 1)
KOKKOS_CXXFLAGS += -xCORE-AVX2
KOKKOS_LDFLAGS += -xCORE-AVX2
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_CRAY), 1)
else
ifeq ($(KOKKOS_INTERNAL_COMPILER_PGI), 1)
KOKKOS_CXXFLAGS += -tp=haswell
KOKKOS_LDFLAGS += -tp=haswell
else
# Assume that this is a really a GNU compiler.
KOKKOS_CXXFLAGS += -march=core-avx2 -mtune=core-avx2 -mrtm
KOKKOS_LDFLAGS += -march=core-avx2 -mtune=core-avx2 -mrtm
endif
endif
endif
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_AVX512MIC), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_AVX512MIC 1" >> KokkosCore_config.tmp )
@ -505,8 +590,8 @@ ifeq ($(KOKKOS_INTERNAL_USE_ARCH_AVX512MIC), 1)
else
# Asssume that this is really a GNU compiler.
KOKKOS_CXXFLAGS += -march=knl
KOKKOS_LDFLAGS += -march=knl
KOKKOS_CXXFLAGS += -march=knl -mtune=knl
KOKKOS_LDFLAGS += -march=knl -mtune=knl
endif
endif
endif
@ -526,8 +611,8 @@ ifeq ($(KOKKOS_INTERNAL_USE_ARCH_AVX512XEON), 1)
else
# Nothing here yet.
KOKKOS_CXXFLAGS += -march=skylake-avx512
KOKKOS_LDFLAGS += -march=skylake-avx512
KOKKOS_CXXFLAGS += -march=skylake-avx512 -mtune=skylake-avx512 -mrtm
KOKKOS_LDFLAGS += -march=skylake-avx512 -mtune=skylake-avx512 -mrtm
endif
endif
endif
@ -541,70 +626,67 @@ endif
# Figure out the architecture flag for Cuda.
ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
ifeq ($(KOKKOS_INTERNAL_COMPILER_NVCC), 1)
KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG=-arch
KOKKOS_INTERNAL_CUDA_ARCH_FLAG=-arch
endif
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG=--cuda-gpu-arch
KOKKOS_INTERNAL_CUDA_ARCH_FLAG=--cuda-gpu-arch
KOKKOS_CXXFLAGS += -x cuda
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_KEPLER30), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER30 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_30
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_30
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_30
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_KEPLER32), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER32 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_32
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_32
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_32
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_KEPLER35), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER35 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_35
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_35
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_35
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_KEPLER37), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_KEPLER37 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_37
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_37
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_37
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_MAXWELL50), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL50 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_50
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_50
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_50
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_MAXWELL52), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL52 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_52
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_52
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_52
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_MAXWELL53), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_MAXWELL53 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_53
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_53
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_PASCAL61), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL61 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_61
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_61
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_53
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_PASCAL60), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL60 1" >> KokkosCore_config.tmp )
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_60
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_COMPILER_CUDA_ARCH_FLAG)=sm_60
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_60
endif
ifeq ($(KOKKOS_INTERNAL_USE_ARCH_PASCAL61), 1)
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL 1" >> KokkosCore_config.tmp )
tmp := $(shell echo "\#define KOKKOS_ARCH_PASCAL61 1" >> KokkosCore_config.tmp )
KOKKOS_INTERNAL_CUDA_ARCH_FLAG := $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)=sm_61
endif
ifneq ($(KOKKOS_INTERNAL_USE_ARCH_NVIDIA), 0)
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)
ifeq ($(KOKKOS_INTERNAL_COMPILER_NVCC), 1)
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_CUDA_ARCH_FLAG)
endif
endif
endif
KOKKOS_INTERNAL_LS_CONFIG := $(shell ls KokkosCore_config.h)
@ -630,9 +712,24 @@ KOKKOS_SRC += $(wildcard $(KOKKOS_PATH)/containers/src/impl/*.cpp)
ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
KOKKOS_SRC += $(wildcard $(KOKKOS_PATH)/core/src/Cuda/*.cpp)
KOKKOS_HEADERS += $(wildcard $(KOKKOS_PATH)/core/src/Cuda/*.hpp)
KOKKOS_CXXFLAGS += -I$(CUDA_PATH)/include
KOKKOS_CPPFLAGS += -I$(CUDA_PATH)/include
KOKKOS_LDFLAGS += -L$(CUDA_PATH)/lib64
KOKKOS_LIBS += -lcudart -lcuda
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_CXXFLAGS += --cuda-path=$(CUDA_PATH)
endif
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMPTARGET), 1)
KOKKOS_SRC += $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTarget_Exec.cpp $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTargetSpace.cpp
KOKKOS_HEADERS += $(wildcard $(KOKKOS_PATH)/core/src/OpenMPTarget/*.hpp)
ifeq ($(KOKKOS_INTERNAL_USE_CUDA), 1)
KOKKOS_CXXFLAGS += -Xcompiler $(KOKKOS_INTERNAL_OPENMPTARGET_FLAG)
else
KOKKOS_CXXFLAGS += $(KOKKOS_INTERNAL_OPENMPTARGET_FLAG)
endif
KOKKOS_LDFLAGS += $(KOKKOS_INTERNAL_OPENMPTARGET_FLAG)
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMP), 1)
@ -666,10 +763,27 @@ endif
ifeq ($(KOKKOS_INTERNAL_COMPILER_CLANG), 1)
KOKKOS_INTERNAL_GCC_PATH = $(shell which g++)
KOKKOS_INTERNAL_GCC_TOOLCHAIN = $(KOKKOS_INTERNAL_GCC_PATH:/bin/g++=)
KOKKOS_CXXFLAGS += --gcc-toolchain=$(KOKKOS_INTERNAL_GCC_TOOLCHAIN) -DKOKKOS_CUDA_CLANG_WORKAROUND -DKOKKOS_CUDA_USE_LDG_INTRINSIC
KOKKOS_CXXFLAGS += --gcc-toolchain=$(KOKKOS_INTERNAL_GCC_TOOLCHAIN)
KOKKOS_LDFLAGS += --gcc-toolchain=$(KOKKOS_INTERNAL_GCC_TOOLCHAIN)
endif
# Don't include Kokkos_HBWSpace.cpp if not using MEMKIND to avoid a link warning.
ifneq ($(KOKKOS_INTERNAL_USE_MEMKIND), 1)
KOKKOS_SRC := $(filter-out $(KOKKOS_PATH)/core/src/impl/Kokkos_HBWSpace.cpp,$(KOKKOS_SRC))
endif
# Don't include Kokkos_Profiling_Interface.cpp if not using profiling to avoid a link warning.
ifeq ($(KOKKOS_INTERNAL_DISABLE_PROFILING), 1)
KOKKOS_SRC := $(filter-out $(KOKKOS_PATH)/core/src/impl/Kokkos_Profiling_Interface.cpp,$(KOKKOS_SRC))
endif
# Don't include Kokkos_Serial.cpp or Kokkos_Serial_Task.cpp if not using Serial
# device to avoid a link warning.
ifneq ($(KOKKOS_INTERNAL_USE_SERIAL), 1)
KOKKOS_SRC := $(filter-out $(KOKKOS_PATH)/core/src/impl/Kokkos_Serial.cpp,$(KOKKOS_SRC))
KOKKOS_SRC := $(filter-out $(KOKKOS_PATH)/core/src/impl/Kokkos_Serial_Task.cpp,$(KOKKOS_SRC))
endif
# With Cygwin functions such as fdopen and fileno are not defined
# when strict ansi is enabled. strict ansi gets enabled with --std=c++11
# though. So we hard undefine it here. Not sure if that has any bad side effects

13
lib/kokkos/Makefile.targets
View File

@ -53,11 +53,20 @@ Kokkos_Qthreads_Task.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/Qthreads/K
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMP), 1)
Kokkos_OpenMPexec.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMPexec.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMPexec.cpp
Kokkos_OpenMP_Exec.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMP_Exec.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMP_Exec.cpp
Kokkos_OpenMP_Task.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMP_Task.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMP/Kokkos_OpenMP_Task.cpp
endif
ifeq ($(KOKKOS_INTERNAL_USE_OPENMPTARGET), 1)
Kokkos_OpenMPTarget_Exec.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTarget_Exec.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTarget_Exec.cpp
Kokkos_OpenMPTargetSpace.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTargetSpace.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTargetSpace.cpp
#Kokkos_OpenMPTarget_Task.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTarget_Task.cpp
# $(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/OpenMPTarget/Kokkos_OpenMPTarget_Task.cpp
endif
Kokkos_HBWSpace.o: $(KOKKOS_CPP_DEPENDS) $(KOKKOS_PATH)/core/src/impl/Kokkos_HBWSpace.cpp
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) -c $(KOKKOS_PATH)/core/src/impl/Kokkos_HBWSpace.cpp

1
lib/kokkos/algorithms/src/KokkosAlgorithms_dummy.cpp
View File

@ -0,0 +1 @@
void KOKKOS_ALGORITHMS_SRC_DUMMY_PREVENT_LINK_ERROR() {}

6
lib/kokkos/algorithms/src/Kokkos_Random.hpp
View File

@ -674,7 +674,7 @@ namespace Kokkos {
const double V = 2.0*drand() - 1.0;
S = U*U+V*V;
}
return U*sqrt(-2.0*log(S)/S);
return U*std::sqrt(-2.0*log(S)/S);
}
KOKKOS_INLINE_FUNCTION
@ -923,7 +923,7 @@ namespace Kokkos {
const double V = 2.0*drand() - 1.0;
S = U*U+V*V;
}
return U*sqrt(-2.0*log(S)/S);
return U*std::sqrt(-2.0*log(S)/S);
}
KOKKOS_INLINE_FUNCTION
@ -1183,7 +1183,7 @@ namespace Kokkos {
const double V = 2.0*drand() - 1.0;
S = U*U+V*V;
}
return U*sqrt(-2.0*log(S)/S);
return U*std::sqrt(-2.0*log(S)/S);
}
KOKKOS_INLINE_FUNCTION

11
lib/kokkos/algorithms/unit_tests/Makefile
View File

@ -8,7 +8,7 @@ default: build_all
echo "End Build"
ifneq (,$(findstring Cuda,$(KOKKOS_DEVICES)))
CXX = $(KOKKOS_PATH)/config/nvcc_wrapper
CXX = $(KOKKOS_PATH)/bin/nvcc_wrapper
else
CXX = g++
endif
@ -49,16 +49,16 @@ ifeq ($(KOKKOS_INTERNAL_USE_SERIAL), 1)
endif
KokkosAlgorithms_UnitTest_Cuda: $(OBJ_CUDA) $(KOKKOS_LINK_DEPENDS)
$(LINK) $(KOKKOS_LDFLAGS) $(LDFLAGS) $(EXTRA_PATH) $(OBJ_CUDA) $(KOKKOS_LIBS) $(LIB) -o KokkosAlgorithms_UnitTest_Cuda
$(LINK) $(EXTRA_PATH) $(OBJ_CUDA) $(KOKKOS_LIBS) $(LIB) $(KOKKOS_LDFLAGS) $(LDFLAGS) -o KokkosAlgorithms_UnitTest_Cuda
KokkosAlgorithms_UnitTest_Threads: $(OBJ_THREADS) $(KOKKOS_LINK_DEPENDS)
$(LINK) $(KOKKOS_LDFLAGS) $(LDFLAGS) $(EXTRA_PATH) $(OBJ_THREADS) $(KOKKOS_LIBS) $(LIB) -o KokkosAlgorithms_UnitTest_Threads
$(LINK) $(EXTRA_PATH) $(OBJ_THREADS) $(KOKKOS_LIBS) $(LIB) $(KOKKOS_LDFLAGS) $(LDFLAGS) -o KokkosAlgorithms_UnitTest_Threads
KokkosAlgorithms_UnitTest_OpenMP: $(OBJ_OPENMP) $(KOKKOS_LINK_DEPENDS)
$(LINK) $(KOKKOS_LDFLAGS) $(LDFLAGS) $(EXTRA_PATH) $(OBJ_OPENMP) $(KOKKOS_LIBS) $(LIB) -o KokkosAlgorithms_UnitTest_OpenMP
$(LINK) $(EXTRA_PATH) $(OBJ_OPENMP) $(KOKKOS_LIBS) $(LIB) $(KOKKOS_LDFLAGS) $(LDFLAGS) -o KokkosAlgorithms_UnitTest_OpenMP
KokkosAlgorithms_UnitTest_Serial: $(OBJ_SERIAL) $(KOKKOS_LINK_DEPENDS)
$(LINK) $(KOKKOS_LDFLAGS) $(LDFLAGS) $(EXTRA_PATH) $(OBJ_SERIAL) $(KOKKOS_LIBS) $(LIB) -o KokkosAlgorithms_UnitTest_Serial
$(LINK) $(EXTRA_PATH) $(OBJ_SERIAL) $(KOKKOS_LIBS) $(LIB) $(KOKKOS_LDFLAGS) $(LDFLAGS) -o KokkosAlgorithms_UnitTest_Serial
test-cuda: KokkosAlgorithms_UnitTest_Cuda
./KokkosAlgorithms_UnitTest_Cuda
@ -86,4 +86,3 @@ clean: kokkos-clean
gtest-all.o:$(GTEST_PATH)/gtest/gtest-all.cc
$(CXX) $(KOKKOS_CPPFLAGS) $(KOKKOS_CXXFLAGS) $(CXXFLAGS) $(EXTRA_INC) -c $(GTEST_PATH)/gtest/gtest-all.cc

10
lib/kokkos/algorithms/unit_tests/TestCuda.cpp
View File

@ -41,7 +41,10 @@
//@HEADER
*/
#include <stdint.h>
#include <Kokkos_Macros.hpp>
#ifdef KOKKOS_ENABLE_CUDA
#include <cstdint>
#include <iostream>
#include <iomanip>
@ -49,8 +52,6 @@
#include <Kokkos_Core.hpp>
#ifdef KOKKOS_ENABLE_CUDA
#include <TestRandom.hpp>
#include <TestSort.hpp>
@ -105,6 +106,7 @@ CUDA_SORT_UNSIGNED(171)
#undef CUDA_RANDOM_XORSHIFT1024
#undef CUDA_SORT_UNSIGNED
}
#else
void KOKKOS_ALGORITHMS_UNITTESTS_TESTCUDA_PREVENT_LINK_ERROR() {}
#endif /* #ifdef KOKKOS_ENABLE_CUDA */

10
lib/kokkos/algorithms/unit_tests/TestOpenMP.cpp
View File

@ -41,8 +41,11 @@
//@HEADER
*/
#include <gtest/gtest.h>
#include <Kokkos_Macros.hpp>
#ifdef KOKKOS_ENABLE_OPENMP
#include <gtest/gtest.h>
#include <Kokkos_Core.hpp>
//----------------------------------------------------------------------------
@ -52,7 +55,6 @@
namespace Test {
#ifdef KOKKOS_ENABLE_OPENMP
class openmp : public ::testing::Test {
protected:
static void SetUpTestCase()
@ -97,6 +99,8 @@ OPENMP_SORT_UNSIGNED(171)
#undef OPENMP_RANDOM_XORSHIFT64
#undef OPENMP_RANDOM_XORSHIFT1024
#undef OPENMP_SORT_UNSIGNED
#endif
} // namespace test
#else
void KOKKOS_ALGORITHMS_UNITTESTS_TESTOPENMP_PREVENT_LINK_ERROR() {}
#endif

6
lib/kokkos/algorithms/unit_tests/TestRandom.hpp
View File

@ -295,7 +295,7 @@ struct test_random_scalar {
parallel_reduce (num_draws/1024, functor_type (pool, density_1d, density_3d), result);
//printf("Result: %lf %lf %lf\n",result.mean/num_draws/3,result.variance/num_draws/3,result.covariance/num_draws/2);
double tolerance = 1.6*sqrt(1.0/num_draws);
double tolerance = 1.6*std::sqrt(1.0/num_draws);
double mean_expect = 0.5*Kokkos::rand<rnd_type,Scalar>::max();
double variance_expect = 1.0/3.0*mean_expect*mean_expect;
double mean_eps = mean_expect/(result.mean/num_draws/3)-1.0;
@ -321,7 +321,7 @@ struct test_random_scalar {
typedef test_histogram1d_functor<typename RandomGenerator::device_type> functor_type;
parallel_reduce (HIST_DIM1D, functor_type (density_1d, num_draws), result);
double tolerance = 6*sqrt(1.0/HIST_DIM1D);
double tolerance = 6*std::sqrt(1.0/HIST_DIM1D);
double mean_expect = 1.0*num_draws*3/HIST_DIM1D;
double variance_expect = 1.0*num_draws*3/HIST_DIM1D*(1.0-1.0/HIST_DIM1D);
double covariance_expect = -1.0*num_draws*3/HIST_DIM1D/HIST_DIM1D;
@ -354,7 +354,7 @@ struct test_random_scalar {
typedef test_histogram3d_functor<typename RandomGenerator::device_type> functor_type;
parallel_reduce (HIST_DIM1D, functor_type (density_3d, num_draws), result);
double tolerance = 6*sqrt(1.0/HIST_DIM1D);
double tolerance = 6*std::sqrt(1.0/HIST_DIM1D);
double mean_expect = 1.0*num_draws/HIST_DIM1D;
double variance_expect = 1.0*num_draws/HIST_DIM1D*(1.0-1.0/HIST_DIM1D);
double covariance_expect = -1.0*num_draws/HIST_DIM1D/HIST_DIM1D;

8
lib/kokkos/algorithms/unit_tests/TestSerial.cpp
View File

@ -41,6 +41,9 @@
//@HEADER
*/
#include <Kokkos_Macros.hpp>
#ifdef KOKKOS_ENABLE_SERIAL
#include <gtest/gtest.h>
#include <Kokkos_Core.hpp>
@ -55,7 +58,6 @@
namespace Test {
#ifdef KOKKOS_ENABLE_SERIAL
class serial : public ::testing::Test {
protected:
static void SetUpTestCase()
@ -93,7 +95,9 @@ SERIAL_SORT_UNSIGNED(171)
#undef SERIAL_RANDOM_XORSHIFT1024
#undef SERIAL_SORT_UNSIGNED
#endif // KOKKOS_ENABLE_SERIAL
} // namespace Test
#else
void KOKKOS_ALGORITHMS_UNITTESTS_TESTSERIAL_PREVENT_LINK_ERROR() {}
#endif // KOKKOS_ENABLE_SERIAL

13
lib/kokkos/algorithms/unit_tests/TestSort.hpp
View File

@ -39,8 +39,8 @@
// ************************************************************************
//@HEADER
#ifndef TESTSORT_HPP_
#define TESTSORT_HPP_
#ifndef KOKKOS_ALGORITHMS_UNITTESTS_TESTSORT_HPP
#define KOKKOS_ALGORITHMS_UNITTESTS_TESTSORT_HPP
#include <gtest/gtest.h>
#include<Kokkos_Core.hpp>
@ -212,7 +212,12 @@ void test_dynamic_view_sort(unsigned int n )
const size_t upper_bound = 2 * n ;
typename KeyDynamicViewType::memory_pool
pool( memory_space() , 2 * n * sizeof(KeyType) );
pool( memory_space()
, n * sizeof(KeyType) * 1.2
, 500 /* min block size in bytes */
, 30000 /* max block size in bytes */
, 1000000 /* min superblock size in bytes */
);
KeyDynamicViewType keys("Keys",pool,upper_bound);
@ -272,4 +277,4 @@ void test_sort(unsigned int N)
}
}
#endif /* TESTSORT_HPP_ */
#endif /* KOKKOS_ALGORITHMS_UNITTESTS_TESTSORT_HPP */

8
lib/kokkos/algorithms/unit_tests/TestThreads.cpp
View File

@ -41,6 +41,9 @@
//@HEADER
*/
#include <Kokkos_Macros.hpp>
#ifdef KOKKOS_ENABLE_THREADS
#include <gtest/gtest.h>
#include <Kokkos_Core.hpp>
@ -55,7 +58,6 @@
namespace Test {
#ifdef KOKKOS_ENABLE_PTHREAD
class threads : public ::testing::Test {
protected:
static void SetUpTestCase()
@ -107,7 +109,9 @@ THREADS_SORT_UNSIGNED(171)
#undef THREADS_RANDOM_XORSHIFT1024
#undef THREADS_SORT_UNSIGNED
#endif
} // namespace Test
#else
void KOKKOS_ALGORITHMS_UNITTESTS_TESTTHREADS_PREVENT_LINK_ERROR() {}
#endif

2
lib/kokkos/benchmarks/bytes_and_flops/Makefile
View File

@ -7,7 +7,7 @@ default: build
echo "Start Build"
ifneq (,$(findstring Cuda,$(KOKKOS_DEVICES)))
CXX = ${KOKKOS_PATH}/config/nvcc_wrapper
CXX = ${KOKKOS_PATH}/bin/nvcc_wrapper
EXE = bytes_and_flops.cuda
KOKKOS_DEVICES = "Cuda,OpenMP"
KOKKOS_ARCH = "SNB,Kepler35"

2
lib/kokkos/benchmarks/gather/Makefile
View File

@ -7,7 +7,7 @@ default: build
echo "Start Build"
ifneq (,$(findstring Cuda,$(KOKKOS_DEVICES)))
CXX = ${KOKKOS_PATH}/config/nvcc_wrapper
CXX = ${KOKKOS_PATH}/bin/nvcc_wrapper
EXE = gather.cuda
KOKKOS_DEVICES = "Cuda,OpenMP"
KOKKOS_ARCH = "SNB,Kepler35"

18
lib/kokkos/cmake/KokkosConfig.cmake.in Normal file
View File

@ -0,0 +1,18 @@
# - Config file for the Kokkos package
# It defines the following variables
# Kokkos_INCLUDE_DIRS - include directories for Kokkos
# Kokkos_LIBRARIES - libraries to link against
# Compute paths
GET_FILENAME_COMPONENT(Kokkos_CMAKE_DIR "${CMAKE_CURRENT_LIST_FILE}" PATH)
SET(Kokkos_INCLUDE_DIRS "@CONF_INCLUDE_DIRS@")
# Our library dependencies (contains definitions for IMPORTED targets)
IF(NOT TARGET kokkos AND NOT Kokkos_BINARY_DIR)
INCLUDE("${Kokkos_CMAKE_DIR}/KokkosTargets.cmake")
ENDIF()
# These are IMPORTED targets created by KokkosTargets.cmake
SET(Kokkos_LIBRARY_DIRS @INSTALL_LIB_DIR@)
SET(Kokkos_LIBRARIES @Kokkos_LIBRARIES_NAMES@)
SET(Kokkos_TPL_LIBRARIES @KOKKOS_LIBS@)

20
lib/kokkos/cmake/Modules/FindHWLOC.cmake Normal file
View File

@ -0,0 +1,20 @@
#.rst:
# FindHWLOC
# ----------
#
# Try to find HWLOC.
#
# The following variables are defined:
#
# HWLOC_FOUND - System has HWLOC
# HWLOC_INCLUDE_DIR - HWLOC include directory
# HWLOC_LIBRARIES - Libraries needed to use HWLOC
find_path(HWLOC_INCLUDE_DIR hwloc.h)
find_library(HWLOC_LIBRARIES hwloc)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(HWLOC DEFAULT_MSG
HWLOC_INCLUDE_DIR HWLOC_LIBRARIES)
mark_as_advanced(HWLOC_INCLUDE_DIR HWLOC_LIBRARIES)

20
lib/kokkos/cmake/Modules/FindMemkind.cmake Normal file
View File

@ -0,0 +1,20 @@
#.rst:
# FindMemkind
# ----------
#
# Try to find Memkind.
#
# The following variables are defined:
#
# MEMKIND_FOUND - System has Memkind
# MEMKIND_INCLUDE_DIR - Memkind include directory
# MEMKIND_LIBRARIES - Libraries needed to use Memkind
find_path(MEMKIND_INCLUDE_DIR memkind.h)
find_library(MEMKIND_LIBRARIES memkind)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(Memkind DEFAULT_MSG
MEMKIND_INCLUDE_DIR MEMKIND_LIBRARIES)
mark_as_advanced(MEMKIND_INCLUDE_DIR MEMKIND_LIBRARIES)

20
lib/kokkos/cmake/Modules/FindQthreads.cmake Normal file
View File

@ -0,0 +1,20 @@
#.rst:
# FindQthreads
# ----------
#
# Try to find Qthreads.
#
# The following variables are defined:
#
# QTHREADS_FOUND - System has Qthreads
# QTHREADS_INCLUDE_DIR - Qthreads include directory
# QTHREADS_LIBRARIES - Libraries needed to use Qthreads
find_path(QTHREADS_INCLUDE_DIR qthread.h)
find_library(QTHREADS_LIBRARIES qthread)
include(FindPackageHandleStandardArgs)
find_package_handle_standard_args(Qthreads DEFAULT_MSG
QTHREADS_INCLUDE_DIR QTHREADS_LIBRARIES)
mark_as_advanced(QTHREADS_INCLUDE_DIR QTHREADS_LIBRARIES)

1198
lib/kokkos/cmake/kokkos.cmake Normal file
View File

File diff suppressed because it is too large Load Diff

44
lib/kokkos/config/kokkos-trilinos-integration-procedure.txt
View File

@ -60,34 +60,12 @@ Step 2:
// -------------------------------------------------------------------------------- //
Step 3:
3.1. Build and test Trilinos with 3 different configurations; a configure-all script is provided in Trilinos and should be modified to test each of the following 3 configurations with appropriate environment variable(s):
3.1. Build and test Trilinos with 4 different configurations; Run scripts for white and shepard are provided in kokkos/config/trilinos-integration
- GCC/4.7.2-OpenMP/Complex
Run tests with the following environment variable:
Usually its a good idea to run those script via nohup.
You can run all four at the same time, use separate directories for each.
export OMP_NUM_THREADS=2
- Intel/15.0.2-Serial/NoComplex
- GCC/4.8.4/CUDA/7.5.18-Cuda/Serial/NoComplex
Run tests with the following environment variables:
export CUDA_LAUNCH_BLOCKING=1
export CUDA_MANAGED_FORCE_DEVICE_ALLOC=1
mkdir Build
cd Build
cp TRILINOS_PATH/sampleScripts/Sandia-SEMS/configure-all ./
** Set the path to Trilinos appropriately within the configure-all script **
source $SEMS_MODULE_ROOT/utils/sems-modules-init.sh kokkos
source configure-all
make -k (-k means "keep going" to get past build errors; -j12 can also be specified to build with 12 threads, for example)
ctest
3.2. Compare the failed test output to the test output on the dashboard ( testing.sandia.gov/cdash select Trilinos ); investigate and fix problems if new tests fail after the Kokkos snapshot
3.2. Compare the failed test output between the pristine and the updated runs; investigate and fix problems if new tests fail after the Kokkos snapshot
// -------------------------------------------------------------------------------- //
@ -134,7 +112,7 @@ Step 4: Once all Trilinos tests pass promote Kokkos develop branch to master on
master: sha1
develop: sha1
git push --follow-tags origin master
4.4. Do NOT push yet
// -------------------------------------------------------------------------------- //
@ -156,9 +134,15 @@ Step 5:
python KOKKOS_PATH/config/snapshot.py KOKKOS_PATH TRILINOS_PATH/packages
5.3. Push the updated develop branch of Trilinos to Github - congratulations!!!
5.3. Run checkin-test to push to trilinos using the CI build modules (gcc/4.9.3)
(From Trilinos directory):
git push
The modules are listed in kokkos/config/trilinos-integration/checkin-test
Run checkin-test, forward dependencies and optional dependencies must be enabled
If push failed because someone else clearly broke something, push manually.
If push failed for unclear reasons, investigate, fix, and potentially start over from step 2 after reseting your local kokkos/master branch
Step 6: Push Kokkos to master
git push --follow-tags origin master
// -------------------------------------------------------------------------------- //

2
lib/kokkos/config/kokkos_dev/config-core-all.sh
View File

@ -13,7 +13,7 @@
# module load cmake/2.8.11.2 gcc/4.8.3 cuda/6.5.14 nvcc-wrapper/gnu
#
# The 'nvcc-wrapper' module should load a script that matches
# kokkos/config/nvcc_wrapper
# kokkos/bin/nvcc_wrapper
#
#-----------------------------------------------------------------------------
# Source and installation directories:

2
lib/kokkos/config/kokkos_dev/config-core-cuda-omp-hwloc.sh
View File

@ -13,7 +13,7 @@
# module load cmake/2.8.11.2 gcc/4.8.3 cuda/6.5.14 nvcc-wrapper/gnu
#
# The 'nvcc-wrapper' module should load a script that matches
# kokkos/config/nvcc_wrapper
# kokkos/bin/nvcc_wrapper
#
#-----------------------------------------------------------------------------
# Source and installation directories:

2
lib/kokkos/config/kokkos_dev/config-core-cuda.sh
View File

@ -13,7 +13,7 @@
# module load cmake/2.8.11.2 gcc/4.8.3 cuda/6.5.14 nvcc-wrapper/gnu
#
# The 'nvcc-wrapper' module should load a script that matches
# kokkos/config/nvcc_wrapper
# kokkos/bin/nvcc_wrapper
#
#-----------------------------------------------------------------------------
# Source and installation directories:

1
lib/kokkos/config/master_history.txt
View File

@ -6,3 +6,4 @@ tag: 2.02.01 date: 11:01:2016 master: 9c698c86 develop: b0072304
tag: 2.02.07 date: 12:16:2016 master: 4b4cc4ba develop: 382c0966
tag: 2.02.15 date: 02:10:2017 master: 8c64cd93 develop: 28dea8b6
tag: 2.03.00 date: 04:25:2017 master: 120d9ce7 develop: 015ba641
tag: 2.03.05 date: 05:27:2017 master: 36b92f43 develop: 79073186

38
lib/kokkos/config/snapshot.py
View File

@ -27,7 +27,7 @@ import subprocess, argparse, re, doctest, os, datetime, traceback
def parse_cmdline(description):
parser = argparse.ArgumentParser(usage="snapshot.py [options] source destination", description=description)
parser.add_argument("-n", "--no-comit", action="store_false", dest="create_commit", default=True,
parser.add_argument("-n", "--no-commit", action="store_false", dest="create_commit", default=True,
help="Do not perform a commit or create a commit message.")
parser.add_argument("-v", "--verbose", action="store_true", dest="verbose_mode", default=False,
help="Enable verbose mode.")
@ -39,6 +39,8 @@ def parse_cmdline(description):
help="Type of repository of the source, use none to skip all repository operations.")
parser.add_argument("--dest-repo", choices=["git","none"], default="",
help="Type of repository of the destination, use none to skip all repository operations.")
parser.add_argument("--small", action="store_true", dest="small_mode",
help="Don't include tests and other extra files when copying.")
parser.add_argument("source", help="Source project to snapshot from.")
parser.add_argument("destination", help="Destination to snapshot too.")
@ -60,7 +62,7 @@ def validate_options(options):
options.destination = os.path.abspath(options.destination)
if os.path.exists(options.source):
apparent_source_repo_type, source_root = deterimine_repo_type(options.source)
apparent_source_repo_type, source_root = determine_repo_type(options.source)
else:
raise RuntimeError("Could not find source directory of %s." % options.source)
options.source_root = source_root
@ -69,7 +71,7 @@ def validate_options(options):
print "Could not find destination directory of %s so it will be created." % options.destination
os.makedirs(options.destination)
apparent_dest_repo_type, dest_root = deterimine_repo_type(options.destination)
apparent_dest_repo_type, dest_root = determine_repo_type(options.destination)
options.dest_root = dest_root
#error on svn repo types for now
@ -119,7 +121,7 @@ def run_cmd(cmd, options, working_dir="."):
return proc_stdout, proc_stderr
#end run_cmd
def deterimine_repo_type(location):
def determine_repo_type(location):
apparent_repo_type = "none"
while location != "":
@ -133,16 +135,32 @@ def deterimine_repo_type(location):
location = location[:location.rfind(os.sep)]
return apparent_repo_type, location
#end deterimine_repo_type
#end determine_repo_type
def rsync(source, dest, options):
rsync_cmd = ["rsync", "-ar", "--delete"]
if options.debug_mode:
rsync_cmd.append("-v")
if options.small_mode or options.source_repo == "git":
rsync_cmd.append("--delete-excluded")
if options.small_mode:
rsync_cmd.append("--include=config/master_history.txt")
rsync_cmd.append("--include=cmake/tpls")
rsync_cmd.append("--exclude=benchmarks/")
rsync_cmd.append("--exclude=config/*")
rsync_cmd.append("--exclude=doc/")
rsync_cmd.append("--exclude=example/")
rsync_cmd.append("--exclude=tpls/")
rsync_cmd.append("--exclude=HOW_TO_SNAPSHOT")
rsync_cmd.append("--exclude=unit_test")
rsync_cmd.append("--exclude=unit_tests")
rsync_cmd.append("--exclude=perf_test")
rsync_cmd.append("--exclude=performance_tests")
if options.source_repo == "git":
rsync_cmd.append("--exclude=.git")
rsync_cmd.append("--exclude=.git*")
rsync_cmd.append(options.source)
rsync_cmd.append(options.destination)
@ -192,7 +210,6 @@ def find_git_commit_information(options):
source_name = source_name[:-1]
return commit_id, commit_log, source_name, source_location
#end find_git_commit_information
def do_git_commit(message, options):
@ -223,7 +240,6 @@ def verify_git_repo_clean(location, options):
print "WARNING: %s is not clean. Proceeding anyway." % location
print "WARNING: This could lead to differences in the source and destination."
print "WARNING: It could also lead to extra files being included in the snapshot commit."
#end verify_git_repo_clean
def main(options):
@ -256,10 +272,6 @@ def main(options):
cwd = os.getcwd()
print "No commit done by request. Please use file at:"
print "%s%sif you wish to commit this to a repo later." % (cwd+"/"+file_name, os.linesep)
#end main
if (__name__ == "__main__"):

Some files were not shown because too many files have changed in this diff Show More