git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@8863 f3b2605a-c512-4ea7-a41b-209d697bcdaa

This commit is contained in:
sjplimp 2012-10-02 19:59:40 +00:00
parent e0540b5c2b
commit fb6436ab4e
268 changed files with 0 additions and 45438 deletions

View File

@ -1,51 +0,0 @@
# Install/unInstall package files in LAMMPS
# do not install child files if parent does not exist
for file in *_omp.cpp *_omp.h pppm*proxy.h pppm*proxy.cpp; do
# let us see if the "rain man" can count the toothpicks...
ofile=`echo $file | sed -e s,_pppm_tip4p_omp,_long_tip4p_omp, \
-e s,pppm.\\*_proxy,pppm_omp, -e s,_pppm_omp,_long_omp, \
-e s,\\\\\\(.\\*\\\\\\)_omp\\\\.h,\\\\1.h, \
-e s,\\\\\\(.\\*\\\\\\)_omp\\\\.cpp,\\\\1.cpp,`
if (test $1 = 1) then
if (test $file = "thr_omp.h") || (test $file = "thr_omp.cpp") then
: # always install those files.
elif (test ! -e ../$ofile) then
continue
fi
cp $file ..
elif (test $1 = 0) then
rm -f ../$file
fi
done
if (test $1 = 1) then
if (test -e ../Makefile.package) then
sed -i -e 's/[^ \t]*OMP[^ \t]* //' ../Makefile.package
sed -i -e 's|^PKG_INC =[ \t]*|&-DLMP_USER_OMP |' ../Makefile.package
fi
# force rebuild of files with LMP_USER_OMP switch
touch ../accelerator_omp.h
cp thr_data.h ..
cp thr_data.cpp ..
elif (test $1 = 0) then
if (test -e ../Makefile.package) then
sed -i -e 's/[^ \t]*OMP[^ \t]* //' ../Makefile.package
fi
# force rebuild of files with LMP_USER_OMP switch
touch ../accelerator_omp.h
rm -f ../thr_data.h
rm -f ../thr_data.cpp
fi

View File

@ -1,46 +0,0 @@
# Update package files in LAMMPS
# copy package file to src if it doesn't exists or is different
# do not copy OpenMP style files, if a non-OpenMP version does
# not exist. Do remove OpenMP style files that have no matching
# non-OpenMP version installed, e.g. after a package has been
# removed
for file in *_omp.cpp *_omp.h pppm*proxy.h pppm*proxy.cpp thr_data.h thr_data.cpp; do
# let us see if the "rain man" can count the toothpicks...
ofile=`echo $file | sed -e s,_pppm_tip4p_omp,_long_tip4p_omp, \
-e s,pppm.\\*_proxy,pppm_omp, -e s,_pppm_omp,_long_omp, \
-e s,\\\\\\(.\\*\\\\\\)_omp\\\\.\\\\\\(h\\\\\\|cpp\\\\\\),\\\\1.\\\\2,`
if (test $file = "thr_omp.h") || (test $file = "thr_omp.cpp") \
|| (test $file = "thr_data.h") || (test $file = "thr_data.cpp") then
if (test ! -e ../$file) then
echo " creating src/$file"
cp $file ..
elif ! cmp -s $file ../$file ; then
echo " updating src/$file"
cp $file ..
fi
elif (test ! -e ../$ofile) then
if (test -e ../$file) then
echo " removing src/$file"
rm -f ../$file
fi
else
if (test ! -e ../$file) then
echo " creating src/$file"
cp $file ..
elif ! cmp -s $file ../$file ; then
echo " updating src/$file"
cp $file ..
fi
fi
done
for file in thr_data.h thr_data.cpp; do
if (test ! -e ../$file) then
echo " creating src/$file"
cp $file ..
elif ! cmp -s $file ../$file ; then
echo " updating src/$file"
cp $file ..
fi
done

View File

@ -1,19 +0,0 @@
This package provides OpenMP multi-threading support and other
optimizations of various LAMMPS pair styles, dihedral styles, and fix
styles.
See this section of the manual to get started:
doc/Section_accelerate.html, sub-section 5.2
The person who created this package is Axel Kohlmeyer at Temple U
(akohlmey at gmail.com). Contact him directly if you have questions.
--------------------------
This directory also contains a shell script:
hack_openmp_for_pgi.sh
which will convert OpenMP directives in src files
into a form compatible with the PGI compiler.

View File

@ -1,196 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_charmm_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCharmmOMP::AngleCharmmOMP(class LAMMPS *lmp)
: AngleCharmm(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCharmmOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCharmmOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double dtheta,tk;
double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
double delxUB,delyUB,delzUB,rsqUB,rUB,dr,rk,forceUB;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// Urey-Bradley bond
delxUB = x[i3][0] - x[i1][0];
delyUB = x[i3][1] - x[i1][1];
delzUB = x[i3][2] - x[i1][2];
rsqUB = delxUB*delxUB + delyUB*delyUB + delzUB*delzUB;
rUB = sqrt(rsqUB);
// Urey-Bradley force & energy
dr = rUB - r_ub[type];
rk = k_ub[type] * dr;
if (rUB > 0.0) forceUB = -2.0*rk/rUB;
else forceUB = 0.0;
if (EFLAG) eangle = rk*dr;
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// harmonic force & energy
dtheta = acos(c) - theta0[type];
tk = k[type] * dtheta;
if (EFLAG) eangle += tk*dtheta;
a = -2.0 * tk * s;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2 - delxUB*forceUB;
f1[1] = a11*dely1 + a12*dely2 - delyUB*forceUB;
f1[2] = a11*delz1 + a12*delz2 - delzUB*forceUB;
f3[0] = a22*delx2 + a12*delx1 + delxUB*forceUB;
f3[1] = a22*dely2 + a12*dely1 + delyUB*forceUB;
f3[2] = a22*delz2 + a12*delz1 + delzUB*forceUB;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(charmm/omp,AngleCharmmOMP)
#else
#ifndef LMP_ANGLE_CHARMM_OMP_H
#define LMP_ANGLE_CHARMM_OMP_H
#include "angle_charmm.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCharmmOMP : public AngleCharmm, public ThrOMP {
public:
AngleCharmmOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,240 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_class2_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleClass2OMP::AngleClass2OMP(class LAMMPS *lmp)
: AngleClass2(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleClass2OMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleClass2OMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double dtheta,dtheta2,dtheta3,dtheta4,de_angle;
double dr1,dr2,tk1,tk2,aa1,aa2,aa11,aa12,aa21,aa22;
double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22,b1,b2;
double vx11,vx12,vy11,vy12,vz11,vz12,vx21,vx22,vy21,vy22,vz21,vz22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// force & energy for angle term
dtheta = acos(c) - theta0[type];
dtheta2 = dtheta*dtheta;
dtheta3 = dtheta2*dtheta;
dtheta4 = dtheta3*dtheta;
de_angle = 2.0*k2[type]*dtheta + 3.0*k3[type]*dtheta2 +
4.0*k4[type]*dtheta3;
a = -de_angle*s;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
if (EFLAG) eangle = k2[type]*dtheta2 + k3[type]*dtheta3 + k4[type]*dtheta4;
// force & energy for bond-bond term
dr1 = r1 - bb_r1[type];
dr2 = r2 - bb_r2[type];
tk1 = bb_k[type] * dr1;
tk2 = bb_k[type] * dr2;
f1[0] -= delx1*tk2/r1;
f1[1] -= dely1*tk2/r1;
f1[2] -= delz1*tk2/r1;
f3[0] -= delx2*tk1/r2;
f3[1] -= dely2*tk1/r2;
f3[2] -= delz2*tk1/r2;
if (EFLAG) eangle += bb_k[type]*dr1*dr2;
// force & energy for bond-angle term
aa1 = s * dr1 * ba_k1[type];
aa2 = s * dr2 * ba_k2[type];
aa11 = aa1 * c / rsq1;
aa12 = -aa1 / (r1 * r2);
aa21 = aa2 * c / rsq1;
aa22 = -aa2 / (r1 * r2);
vx11 = (aa11 * delx1) + (aa12 * delx2);
vx12 = (aa21 * delx1) + (aa22 * delx2);
vy11 = (aa11 * dely1) + (aa12 * dely2);
vy12 = (aa21 * dely1) + (aa22 * dely2);
vz11 = (aa11 * delz1) + (aa12 * delz2);
vz12 = (aa21 * delz1) + (aa22 * delz2);
aa11 = aa1 * c / rsq2;
aa21 = aa2 * c / rsq2;
vx21 = (aa11 * delx2) + (aa12 * delx1);
vx22 = (aa21 * delx2) + (aa22 * delx1);
vy21 = (aa11 * dely2) + (aa12 * dely1);
vy22 = (aa21 * dely2) + (aa22 * dely1);
vz21 = (aa11 * delz2) + (aa12 * delz1);
vz22 = (aa21 * delz2) + (aa22 * delz1);
b1 = ba_k1[type] * dtheta / r1;
b2 = ba_k2[type] * dtheta / r2;
f1[0] -= vx11 + b1*delx1 + vx12;
f1[1] -= vy11 + b1*dely1 + vy12;
f1[2] -= vz11 + b1*delz1 + vz12;
f3[0] -= vx21 + b2*delx2 + vx22;
f3[1] -= vy21 + b2*dely2 + vy22;
f3[2] -= vz21 + b2*delz2 + vz22;
if (EFLAG) eangle += ba_k1[type]*dr1*dtheta + ba_k2[type]*dr2*dtheta;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(class2/omp,AngleClass2OMP)
#else
#ifndef LMP_ANGLE_CLASS2_OMP_H
#define LMP_ANGLE_CLASS2_OMP_H
#include "angle_class2.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleClass2OMP : public AngleClass2, public ThrOMP {
public:
AngleClass2OMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,189 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_delta_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosineDeltaOMP::AngleCosineDeltaOMP(class LAMMPS *lmp)
: AngleCosineDelta(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosineDeltaOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosineDeltaOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2,theta,dtheta,dcostheta,tk;
double eangle,f1[3],f3[3];
double rsq1,rsq2,r1,r2,c,a,cot,a11,a12,a22,b11,b12,b22,c0,s0,s;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
theta = acos(c);
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
cot = c/s;
// force & energy
dtheta = theta - theta0[type];
dcostheta = cos(dtheta);
tk = k[type] * (1.0-dcostheta);
if (EFLAG) eangle = tk;
a = -k[type];
// expand dtheta for cos and sin contribution to force
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
b11 = -a*c*cot / rsq1;
b12 = a*cot / (r1*r2);
b22 = -a*c*cot / rsq2;
c0 = cos(theta0[type]);
s0 = sin(theta0[type]);
f1[0] = (a11*delx1 + a12*delx2)*c0 + (b11*delx1 + b12*delx2)*s0;
f1[1] = (a11*dely1 + a12*dely2)*c0 + (b11*dely1 + b12*dely2)*s0;
f1[2] = (a11*delz1 + a12*delz2)*c0 + (b11*delz1 + b12*delz2)*s0;
f3[0] = (a22*delx2 + a12*delx1)*c0 + (b22*delx2 + b12*delx1)*s0;
f3[1] = (a22*dely2 + a12*dely1)*c0 + (b22*dely2 + b12*dely1)*s0;
f3[2] = (a22*delz2 + a12*delz1)*c0 + (b22*delz2 + b12*delz1)*s0;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/delta/omp,AngleCosineDeltaOMP)
#else
#ifndef LMP_ANGLE_COSINE_DELTA_OMP_H
#define LMP_ANGLE_COSINE_DELTA_OMP_H
#include "angle_cosine_delta.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosineDeltaOMP : public AngleCosineDelta, public ThrOMP {
public:
AngleCosineDeltaOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,166 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosineOMP::AngleCosineOMP(class LAMMPS *lmp)
: AngleCosine(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosineOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosineOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double rsq1,rsq2,r1,r2,c,a,a11,a12,a22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// c = cosine of angle
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// force & energy
if (EFLAG) eangle = k[type]*(1.0+c);
a = k[type];
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/omp,AngleCosineOMP)
#else
#ifndef LMP_ANGLE_COSINE_OMP_H
#define LMP_ANGLE_COSINE_OMP_H
#include "angle_cosine.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosineOMP : public AngleCosine, public ThrOMP {
public:
AngleCosineOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,204 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_periodic_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosinePeriodicOMP::AngleCosinePeriodicOMP(class LAMMPS *lmp)
: AngleCosinePeriodic(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosinePeriodicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosinePeriodicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i,i1,i2,i3,n,m,type,b_factor;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
double tn,tn_1,tn_2,un,un_1,un_2;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// c = cosine of angle
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
m = multiplicity[type];
b_factor = b[type];
// cos(n*x) = Tn(cos(x))
// Tn(x) = Chebyshev polynomials of the first kind: T_0 = 1, T_1 = x, ...
// recurrence relationship:
// Tn(x) = 2*x*T[n-1](x) - T[n-2](x) where T[-1](x) = 0
// also, dTn(x)/dx = n*U[n-1](x)
// where Un(x) = 2*x*U[n-1](x) - U[n-2](x) and U[-1](x) = 0
// finally need to handle special case for n = 1
tn = 1.0;
tn_1 = 1.0;
tn_2 = 0.0;
un = 1.0;
un_1 = 2.0;
un_2 = 0.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// force & energy
tn_2 = c;
for (i = 1; i <= m; i++) {
tn = 2*c*tn_1 - tn_2;
tn_2 = tn_1;
tn_1 = tn;
}
for (i = 2; i <= m; i++) {
un = 2*c*un_1 - un_2;
un_2 = un_1;
un_1 = un;
}
tn = b_factor*pow(-1.0,(double)m)*tn;
un = b_factor*pow(-1.0,(double)m)*m*un;
if (EFLAG) eangle = 2*k[type]*(1.0 - tn);
a = -k[type]*un;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/periodic/omp,AngleCosinePeriodicOMP)
#else
#ifndef LMP_ANGLE_COSINE_PERIODIC_OMP_H
#define LMP_ANGLE_COSINE_PERIODIC_OMP_H
#include "angle_cosine_periodic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosinePeriodicOMP : public AngleCosinePeriodic, public ThrOMP {
public:
AngleCosinePeriodicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,187 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_shift_exp_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosineShiftExpOMP::AngleCosineShiftExpOMP(class LAMMPS *lmp)
: AngleCosineShiftExp(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosineShiftExpOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosineShiftExpOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3],ff;
double rsq1,rsq2,r1,r2,c,s,a11,a12,a22;
double exp2,aa,uumin,cccpsss,cssmscc;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// c = cosine of angle
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// C= sine of angle
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
// force & energy
aa=a[type];
uumin=umin[type];
cccpsss = c*cost[type]+s*sint[type];
cssmscc = c*sint[type]-s*cost[type];
if (doExpansion[type])
{ // |a|<0.01 so use expansions relative precision <1e-5
// std::cout << "Using expansion\n";
if (EFLAG) eangle = -0.125*(1+cccpsss)*(4+aa*(cccpsss-1))*uumin;
ff=0.25*uumin*cssmscc*(2+aa*cccpsss)/s;
}
else
{
// std::cout << "Not using expansion\n";
exp2=exp(0.5*aa*(1+cccpsss));
if (EFLAG) eangle = opt1[type]*(1-exp2);
ff=0.5*a[type]*opt1[type]*exp2*cssmscc/s;
}
a11 = ff*c/ rsq1;
a12 = -ff / (r1*r2);
a22 = ff*c/ rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/shift/exp/omp,AngleCosineShiftExpOMP)
#else
#ifndef LMP_ANGLE_COSINE_SHIFT_EXP_OMP_H
#define LMP_ANGLE_COSINE_SHIFT_EXP_OMP_H
#include "angle_cosine_shift_exp.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosineShiftExpOMP : public AngleCosineShiftExp, public ThrOMP {
public:
AngleCosineShiftExpOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,172 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_shift_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosineShiftOMP::AngleCosineShiftOMP(class LAMMPS *lmp)
: AngleCosineShift(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosineShiftOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosineShiftOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double f1[3],f3[3];
double rsq1,rsq2,r1,r2,c,s,cps,a11,a12,a22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
double eangle = 0.0;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// c = cosine of angle
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// C= sine of angle
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
// force & energy
const double kcos=kcost[type];
const double ksin=ksint[type];
if (EFLAG) eangle = -k[type]-kcos*c-ksin*s;
cps = c/s; // NOTE absorbed one c
a11 = (-kcos +ksin*cps )*c/ rsq1;
a12 = ( kcos -ksin*cps ) / (r1*r2);
a22 = (-kcos +ksin*cps )*c/ rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/shift/omp,AngleCosineShiftOMP)
#else
#ifndef LMP_ANGLE_COSINE_SHIFT_OMP_H
#define LMP_ANGLE_COSINE_SHIFT_OMP_H
#include "angle_cosine_shift.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosineShiftOMP : public AngleCosineShift, public ThrOMP {
public:
AngleCosineShiftOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,171 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_cosine_squared_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleCosineSquaredOMP::AngleCosineSquaredOMP(class LAMMPS *lmp)
: AngleCosineSquared(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleCosineSquaredOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleCosineSquaredOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double dcostheta,tk;
double rsq1,rsq2,r1,r2,c,a,a11,a12,a22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// force & energy
dcostheta = c - cos(theta0[type]);
tk = k[type] * dcostheta;
if (EFLAG) eangle = tk*dcostheta;
a = 2.0 * tk;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(cosine/squared/omp,AngleCosineSquaredOMP)
#else
#ifndef LMP_ANGLE_COSINE_SQUARED_OMP_H
#define LMP_ANGLE_COSINE_SQUARED_OMP_H
#include "angle_cosine_squared.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleCosineSquaredOMP : public AngleCosineSquared, public ThrOMP {
public:
AngleCosineSquaredOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,125 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_dipole_omp.h"
#include "atom.h"
#include "comm.h"
#include "error.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleDipoleOMP::AngleDipoleOMP(class LAMMPS *lmp)
: AngleDipole(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleDipoleOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
if (!force->newton_bond)
error->all(FLERR,"'newton' flag for bonded interactions must be 'on'");
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (eflag)
eval<1>(ifrom, ito, thr);
else
eval<0>(ifrom, ito, thr);
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EFLAG>
void AngleDipoleOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int iRef,iDip,iDummy,n,type;
double delx,dely,delz;
double eangle,tangle;
double r,cosGamma,deltaGamma,kdg,rmu;
const double * const * const x = atom->x; // position vector
const double * const * const mu = atom->mu; // point-dipole components and moment magnitude
double * const * const torque = thr->get_torque();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
const double f1[3] = {0.0, 0.0, 0.0};
const double f3[3] = {0.0, 0.0, 0.0};
for (n = nfrom; n < nto; n++) {
iDip = anglelist[n][0]; // dipole whose orientation is to be restrained
iRef = anglelist[n][1]; // reference atom toward which dipole will point
iDummy = anglelist[n][2]; // dummy atom - irrelevant to the interaction
type = anglelist[n][3];
delx = x[iRef][0] - x[iDip][0];
dely = x[iRef][1] - x[iDip][1];
delz = x[iRef][2] - x[iDip][2];
r = sqrt(delx*delx + dely*dely + delz*delz);
rmu = r * mu[iDip][3];
cosGamma = (mu[iDip][0]*delx+mu[iDip][1]*dely+mu[iDip][2]*delz) / rmu;
deltaGamma = cosGamma - cos(gamma0[type]);
kdg = k[type] * deltaGamma;
if (EFLAG) eangle = kdg * deltaGamma; // energy
tangle = 2.0 * kdg / rmu;
torque[iDip][0] += tangle * (dely*mu[iDip][2] - delz*mu[iDip][1]);
torque[iDip][1] += tangle * (delz*mu[iDip][0] - delx*mu[iDip][2]);
torque[iDip][2] += tangle * (delx*mu[iDip][1] - dely*mu[iDip][0]);
if (EFLAG) // tally energy (virial=0 because force=0)
ev_tally_thr(this,iRef,iDip,iDummy,nlocal,/* NEWTON_BOND */ 1,
eangle,f1,f3,0.0,0.0,0.0,0.0,0.0,0.0,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(dipole/omp,AngleDipoleOMP)
#else
#ifndef LMP_ANGLE_DIPOLE_OMP_H
#define LMP_ANGLE_DIPOLE_OMP_H
#include "angle_dipole.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleDipoleOMP : public AngleDipole, public ThrOMP {
public:
AngleDipoleOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EFLAG>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,175 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_harmonic_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleHarmonicOMP::AngleHarmonicOMP(class LAMMPS *lmp)
: AngleHarmonic(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleHarmonicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleHarmonicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2;
double eangle,f1[3],f3[3];
double dtheta,tk;
double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// force & energy
dtheta = acos(c) - theta0[type];
tk = k[type] * dtheta;
if (EFLAG) eangle = tk*dtheta;
a = -2.0 * tk * s;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(harmonic/omp,AngleHarmonicOMP)
#else
#ifndef LMP_ANGLE_HARMONIC_OMP_H
#define LMP_ANGLE_HARMONIC_OMP_H
#include "angle_harmonic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleHarmonicOMP : public AngleHarmonic, public ThrOMP {
public:
AngleHarmonicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,230 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_sdk_omp.h"
#include "atom.h"
#include "neighbor.h"
#include "domain.h"
#include "comm.h"
#include "force.h"
#include "math_const.h"
#include <math.h>
#include "lj_sdk_common.h"
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
using namespace LJSDKParms;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleSDKOMP::AngleSDKOMP(class LAMMPS *lmp)
: AngleSDK(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleSDKOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleSDKOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double delx1,dely1,delz1,delx2,dely2,delz2,delx3,dely3,delz3;
double eangle,f1[3],f3[3],e13,f13;
double dtheta,tk;
double rsq1,rsq2,rsq3,r1,r2,c,s,a,a11,a12,a22;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// 1-3 LJ interaction.
// we only want to use the repulsive part,
// and it can be scaled (or off).
// so this has to be done here and not in the
// general non-bonded code.
f13 = e13 = delx3 = dely3 = delz3 = 0.0;
if (repflag) {
delx3 = x[i1][0] - x[i3][0];
dely3 = x[i1][1] - x[i3][1];
delz3 = x[i1][2] - x[i3][2];
rsq3 = delx3*delx3 + dely3*dely3 + delz3*delz3;
const int type1 = atom->type[i1];
const int type3 = atom->type[i3];
if (rsq3 < rminsq[type1][type3]) {
const int ljt = lj_type[type1][type3];
const double r2inv = 1.0/rsq3;
if (ljt == LJ12_4) {
const double r4inv=r2inv*r2inv;
f13 = r4inv*(lj1[type1][type3]*r4inv*r4inv - lj2[type1][type3]);
if (EFLAG) e13 = r4inv*(lj3[type1][type3]*r4inv*r4inv - lj4[type1][type3]);
} else if (ljt == LJ9_6) {
const double r3inv = r2inv*sqrt(r2inv);
const double r6inv = r3inv*r3inv;
f13 = r6inv*(lj1[type1][type3]*r3inv - lj2[type1][type3]);
if (EFLAG) e13 = r6inv*(lj3[type1][type3]*r3inv - lj4[type1][type3]);
} else if (ljt == LJ12_6) {
const double r6inv = r2inv*r2inv*r2inv;
f13 = r6inv*(lj1[type1][type3]*r6inv - lj2[type1][type3]);
if (EFLAG) e13 = r6inv*(lj3[type1][type3]*r6inv - lj4[type1][type3]);
}
// make sure energy is 0.0 at the cutoff.
if (EFLAG) e13 -= emin[type1][type3];
f13 *= r2inv;
}
}
// force & energy
dtheta = acos(c) - theta0[type];
tk = k[type] * dtheta;
if (EFLAG) eangle = tk*dtheta;
a = -2.0 * tk * s;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of the 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0] + f13*delx3;
f[i1][1] += f1[1] + f13*dely3;
f[i1][2] += f1[2] + f13*delz3;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0] - f13*delx3;
f[i3][1] += f3[1] - f13*dely3;
f[i3][2] += f3[2] - f13*delz3;
}
if (EVFLAG) {
ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
if (repflag) ev_tally13_thr(this,i1,i3,nlocal,NEWTON_BOND,
e13,f13,delx3,dely3,delz3,thr);
}
}
}

View File

@ -1,47 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(sdk/omp,AngleSDKOMP)
AngleStyle(cg/cmm/omp,AngleSDKOMP)
#else
#ifndef LMP_ANGLE_SDK_OMP_H
#define LMP_ANGLE_SDK_OMP_H
#include "angle_sdk.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleSDKOMP : public AngleSDK, public ThrOMP {
public:
AngleSDKOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,175 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "angle_table_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "math_const.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
AngleTableOMP::AngleTableOMP(class LAMMPS *lmp)
: AngleTable(lmp), ThrOMP(lmp,THR_ANGLE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void AngleTableOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nanglelist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void AngleTableOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,n,type;
double eangle,f1[3],f3[3];
double delx1,dely1,delz1,delx2,dely2,delz2;
double rsq1,rsq2,r1,r2,c,s,a,a11,a12,a22;
double theta,u,mdu; //mdu: minus du, -du/dx=f
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const anglelist = neighbor->anglelist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = anglelist[n][0];
i2 = anglelist[n][1];
i3 = anglelist[n][2];
type = anglelist[n][3];
// 1st bond
delx1 = x[i1][0] - x[i2][0];
dely1 = x[i1][1] - x[i2][1];
delz1 = x[i1][2] - x[i2][2];
rsq1 = delx1*delx1 + dely1*dely1 + delz1*delz1;
r1 = sqrt(rsq1);
// 2nd bond
delx2 = x[i3][0] - x[i2][0];
dely2 = x[i3][1] - x[i2][1];
delz2 = x[i3][2] - x[i2][2];
rsq2 = delx2*delx2 + dely2*dely2 + delz2*delz2;
r2 = sqrt(rsq2);
// angle (cos and sin)
c = delx1*delx2 + dely1*dely2 + delz1*delz2;
c /= r1*r2;
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
s = 1.0/s;
// tabulated force & energy
theta = acos(c);
uf_lookup(type,theta,u,mdu);
if (EFLAG) eangle = u;
a = mdu * s;
a11 = a*c / rsq1;
a12 = -a / (r1*r2);
a22 = a*c / rsq2;
f1[0] = a11*delx1 + a12*delx2;
f1[1] = a11*dely1 + a12*dely2;
f1[2] = a11*delz1 + a12*delz2;
f3[0] = a22*delx2 + a12*delx1;
f3[1] = a22*dely2 + a12*dely1;
f3[2] = a22*delz2 + a12*delz1;
// apply force to each of 3 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= f1[0] + f3[0];
f[i2][1] -= f1[1] + f3[1];
f[i2][2] -= f1[2] + f3[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (EVFLAG) ev_tally_thr(this,i1,i2,i3,nlocal,NEWTON_BOND,eangle,f1,f3,
delx1,dely1,delz1,delx2,dely2,delz2,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef ANGLE_CLASS
AngleStyle(table/omp,AngleTableOMP)
#else
#ifndef LMP_ANGLE_TABLE_OMP_H
#define LMP_ANGLE_TABLE_OMP_H
#include "angle_table.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class AngleTableOMP : public AngleTable, public ThrOMP {
public:
AngleTableOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,132 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_class2_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondClass2OMP::BondClass2OMP(class LAMMPS *lmp)
: BondClass2(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondClass2OMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondClass2OMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,dr2,dr3,dr4,de_bond;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
dr = r - r0[type];
dr2 = dr*dr;
dr3 = dr2*dr;
dr4 = dr3*dr;
// force & energy
de_bond = 2.0*k2[type]*dr + 3.0*k3[type]*dr2 + 4.0*k4[type]*dr3;
if (r > 0.0) fbond = -de_bond/r;
else fbond = 0.0;
if (EFLAG) ebond = k2[type]*dr2 + k3[type]*dr3 + k4[type]*dr4;
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(class2/omp,BondClass2OMP)
#else
#ifndef LMP_BOND_CLASS2_OMP_H
#define LMP_BOND_CLASS2_OMP_H
#include "bond_class2.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondClass2OMP : public BondClass2, public ThrOMP {
public:
BondClass2OMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,162 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_fene_expand_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "error.h"
#include "update.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondFENEExpandOMP::BondFENEExpandOMP(class LAMMPS *lmp)
: BondFENEExpand(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondFENEExpandOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondFENEExpandOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r0sq,rlogarg,sr2,sr6;
double r,rshift,rshiftsq;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
const int tid = thr->get_tid();
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
rshift = r - shift[type];
rshiftsq = rshift*rshift;
r0sq = r0[type] * r0[type];
rlogarg = 1.0 - rshiftsq/r0sq;
// if r -> r0, then rlogarg < 0.0 which is an error
// issue a warning and reset rlogarg = epsilon
// if r > 2*r0 something serious is wrong, abort
if (rlogarg < 0.1) {
char str[128];
sprintf(str,"FENE bond too long: " BIGINT_FORMAT " %d %d %g",
update->ntimestep,atom->tag[i1],atom->tag[i2],sqrt(rsq));
error->warning(FLERR,str,0);
if (check_error_thr((rlogarg <= -3.0),tid,FLERR,"Bad FENE bond"))
return;
rlogarg = 0.1;
}
fbond = -k[type]*rshift/rlogarg/r;
// force from LJ term
if (rshiftsq < TWO_1_3*sigma[type]*sigma[type]) {
sr2 = sigma[type]*sigma[type]/rshiftsq;
sr6 = sr2*sr2*sr2;
fbond += 48.0*epsilon[type]*sr6*(sr6-0.5)/rshift/r;
}
// energy
if (EFLAG) {
ebond = -0.5 * k[type]*r0sq*log(rlogarg);
if (rshiftsq < TWO_1_3*sigma[type]*sigma[type])
ebond += 4.0*epsilon[type]*sr6*(sr6-1.0) + epsilon[type];
}
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(fene/expand/omp,BondFENEExpandOMP)
#else
#ifndef LMP_BOND_FENE_EXPAND_OMP_H
#define LMP_BOND_FENE_EXPAND_OMP_H
#include "bond_fene_expand.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondFENEExpandOMP : public BondFENEExpand, public ThrOMP {
public:
BondFENEExpandOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,158 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_fene_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "error.h"
#include "update.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondFENEOMP::BondFENEOMP(class LAMMPS *lmp)
: BondFENE(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondFENEOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondFENEOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r0sq,rlogarg,sr2,sr6;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
const int tid = thr->get_tid();
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r0sq = r0[type] * r0[type];
rlogarg = 1.0 - rsq/r0sq;
// if r -> r0, then rlogarg < 0.0 which is an error
// issue a warning and reset rlogarg = epsilon
// if r > 2*r0 something serious is wrong, abort
if (rlogarg < 0.1) {
char str[128];
sprintf(str,"FENE bond too long: " BIGINT_FORMAT " %d %d %g",
update->ntimestep,atom->tag[i1],atom->tag[i2],sqrt(rsq));
error->warning(FLERR,str,0);
if (check_error_thr((rlogarg <= -3.0),tid,FLERR,"Bad FENE bond"))
return;
rlogarg = 0.1;
}
fbond = -k[type]/rlogarg;
// force from LJ term
if (rsq < TWO_1_3*sigma[type]*sigma[type]) {
sr2 = sigma[type]*sigma[type]/rsq;
sr6 = sr2*sr2*sr2;
fbond += 48.0*epsilon[type]*sr6*(sr6-0.5)/rsq;
}
// energy
if (EFLAG) {
ebond = -0.5 * k[type]*r0sq*log(rlogarg);
if (rsq < TWO_1_3*sigma[type]*sigma[type])
ebond += 4.0*epsilon[type]*sr6*(sr6-1.0) + epsilon[type];
}
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(fene/omp,BondFENEOMP)
#else
#ifndef LMP_BOND_FENE_OMP_H
#define LMP_BOND_FENE_OMP_H
#include "bond_fene.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondFENEOMP : public BondFENE, public ThrOMP {
public:
BondFENEOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,128 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_harmonic_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondHarmonicOMP::BondHarmonicOMP(class LAMMPS *lmp)
: BondHarmonic(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondHarmonicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondHarmonicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,rk;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
dr = r - r0[type];
rk = k[type] * dr;
// force & energy
if (r > 0.0) fbond = -2.0*rk/r;
else fbond = 0.0;
if (EFLAG) ebond = rk*dr;
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(harmonic/omp,BondHarmonicOMP)
#else
#ifndef LMP_BOND_HARMONIC_OMP_H
#define LMP_BOND_HARMONIC_OMP_H
#include "bond_harmonic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondHarmonicOMP : public BondHarmonic, public ThrOMP {
public:
BondHarmonicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,132 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_harmonic_shift_cut_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondHarmonicShiftCutOMP::BondHarmonicShiftCutOMP(class LAMMPS *lmp)
: BondHarmonicShiftCut(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondHarmonicShiftCutOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondHarmonicShiftCutOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,rk;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
if (r>r1[type]) continue;
dr = r - r0[type];
rk = k[type] * dr;
// force & energy
if (r > 0.0) fbond = -2.0*rk/r;
else fbond = 0.0;
if (EFLAG)
ebond = k[type]*(dr*dr -(r0[type]-r1[type])*(r0[type]-r1[type]) );
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(harmonic/shift/cut/omp,BondHarmonicShiftCutOMP)
#else
#ifndef LMP_BOND_HARMONIC_SHIFT_CUT_OMP_H
#define LMP_BOND_HARMONIC_SHIFT_CUT_OMP_H
#include "bond_harmonic_shift_cut.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondHarmonicShiftCutOMP : public BondHarmonicShiftCut, public ThrOMP {
public:
BondHarmonicShiftCutOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,129 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_harmonic_shift_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondHarmonicShiftOMP::BondHarmonicShiftOMP(class LAMMPS *lmp)
: BondHarmonicShift(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondHarmonicShiftOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondHarmonicShiftOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,rk;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
dr = r - r0[type];
rk = k[type] * dr;
// force & energy
if (r > 0.0) fbond = -2.0*rk/r;
else fbond = 0.0;
if (EFLAG)
ebond = k[type]*(dr*dr -(r0[type]-r1[type])*(r0[type]-r1[type]) );
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(harmonic/shift/omp,BondHarmonicShiftOMP)
#else
#ifndef LMP_BOND_HARMONIC_SHIFT_OMP_H
#define LMP_BOND_HARMONIC_SHIFT_OMP_H
#include "bond_harmonic_shift.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondHarmonicShiftOMP : public BondHarmonicShift, public ThrOMP {
public:
BondHarmonicShiftOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,129 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_morse_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondMorseOMP::BondMorseOMP(class LAMMPS *lmp)
: BondMorse(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondMorseOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondMorseOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,ralpha;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
dr = r - r0[type];
ralpha = exp(-alpha[type]*dr);
// force & energy
if (r > 0.0) fbond = -2.0*d0[type]*alpha[type]*(1-ralpha)*ralpha/r;
else fbond = 0.0;
if (EFLAG) ebond = d0[type]*(1-ralpha)*(1-ralpha);
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(morse/omp,BondMorseOMP)
#else
#ifndef LMP_BOND_MORSE_OMP_H
#define LMP_BOND_MORSE_OMP_H
#include "bond_morse.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondMorseOMP : public BondMorse, public ThrOMP {
public:
BondMorseOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,129 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_nonlinear_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondNonlinearOMP::BondNonlinearOMP(class LAMMPS *lmp)
: BondNonlinear(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondNonlinearOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondNonlinearOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r,dr,drsq,lamdasq,denom,denomsq;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
dr = r - r0[type];
drsq = dr*dr;
lamdasq = lamda[type]*lamda[type];
denom = lamdasq - drsq;
denomsq = denom*denom;
// force & energy
fbond = -epsilon[type]/r * 2.0*dr*lamdasq/denomsq;
if (EFLAG) ebond = epsilon[type] * drsq / denom;
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(nonlinear/omp,BondNonlinearOMP)
#else
#ifndef LMP_BOND_NONLINEAR_OMP_H
#define LMP_BOND_NONLINEAR_OMP_H
#include "bond_nonlinear.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondNonlinearOMP : public BondNonlinear, public ThrOMP {
public:
BondNonlinearOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,197 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_quartic_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include "pair.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondQuarticOMP::BondQuarticOMP(class LAMMPS *lmp)
: BondQuartic(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondQuarticOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
// insure pair->ev_tally() will use 1-4 virial contribution
if (vflag_global == 2)
force->pair->vflag_either = force->pair->vflag_global = 1;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondQuarticOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,m,type,itype,jtype;
double delx,dely,delz,ebond,fbond,evdwl,fpair;
double r,rsq,dr,r2,ra,rb,sr2,sr6;
ebond = evdwl = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
int * const * const bondlist = neighbor->bondlist;
const double * const * const cutsq = force->pair->cutsq;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
// skip bond if already broken
if (bondlist[n][2] <= 0) continue;
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
// if bond breaks, set type to 0
// both in temporary bondlist and permanent bond_type
// if this proc owns both atoms,
// negate bond_type twice if other atom stores it
// if other proc owns 2nd atom, other proc will also break bond
if (rsq > rc[type]*rc[type]) {
bondlist[n][2] = 0;
for (m = 0; m < atom->num_bond[i1]; m++)
if (atom->bond_atom[i1][m] == atom->tag[i2])
atom->bond_type[i1][m] = 0;
if (i2 < atom->nlocal)
for (m = 0; m < atom->num_bond[i2]; m++)
if (atom->bond_atom[i2][m] == atom->tag[i1])
atom->bond_type[i2][m] = 0;
continue;
}
// quartic bond
// 1st portion is from quartic term
// 2nd portion is from LJ term cut at 2^(1/6) with eps = sigma = 1.0
r = sqrt(rsq);
dr = r - rc[type];
r2 = dr*dr;
ra = dr - b1[type];
rb = dr - b2[type];
fbond = -k[type]/r * (r2*(ra+rb) + 2.0*dr*ra*rb);
if (rsq < TWO_1_3) {
sr2 = 1.0/rsq;
sr6 = sr2*sr2*sr2;
fbond += 48.0*sr6*(sr6-0.5)/rsq;
}
if (EFLAG) {
ebond = k[type]*r2*ra*rb + u0[type];
if (rsq < TWO_1_3) ebond += 4.0*sr6*(sr6-1.0) + 1.0;
}
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,ebond,fbond,delx,dely,delz,thr);
// subtract out pairwise contribution from 2 atoms via pair->single()
// required since special_bond = 1,1,1
// tally energy/virial in pair, using newton_bond as newton flag
itype = atom->type[i1];
jtype = atom->type[i2];
if (rsq < cutsq[itype][jtype]) {
evdwl = -force->pair->single(i1,i2,itype,jtype,rsq,1.0,1.0,fpair);
fpair = -fpair;
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fpair;
f[i1][1] += dely*fpair;
f[i1][2] += delz*fpair;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fpair;
f[i2][1] -= dely*fpair;
f[i2][2] -= delz*fpair;
}
if (EVFLAG) ev_tally_thr(force->pair,i1,i2,nlocal,NEWTON_BOND,
evdwl,0.0,fpair,delx,dely,delz,thr);
}
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(quartic/omp,BondQuarticOMP)
#else
#ifndef LMP_BOND_QUARTIC_OMP_H
#define LMP_BOND_QUARTIC_OMP_H
#include "bond_quartic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondQuarticOMP : public BondQuartic, public ThrOMP {
public:
BondQuarticOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,126 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "bond_table_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "neighbor.h"
#include "domain.h"
#include <math.h>
#include "suffix.h"
using namespace LAMMPS_NS;
/* ---------------------------------------------------------------------- */
BondTableOMP::BondTableOMP(class LAMMPS *lmp)
: BondTable(lmp), ThrOMP(lmp,THR_BOND)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void BondTableOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nbondlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void BondTableOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,n,type;
double delx,dely,delz,ebond,fbond;
double rsq,r;
double u,mdu;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const bondlist = neighbor->bondlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = bondlist[n][0];
i2 = bondlist[n][1];
type = bondlist[n][2];
delx = x[i1][0] - x[i2][0];
dely = x[i1][1] - x[i2][1];
delz = x[i1][2] - x[i2][2];
rsq = delx*delx + dely*dely + delz*delz;
r = sqrt(rsq);
// force & energy
uf_lookup(type,r,u,mdu);
fbond = mdu/r;
ebond = u;
// apply force to each of 2 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fbond;
f[i1][1] += dely*fbond;
f[i1][2] += delz*fbond;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] -= delx*fbond;
f[i2][1] -= dely*fbond;
f[i2][2] -= delz*fbond;
}
if (EVFLAG) ev_tally_thr(this,i1,i2,nlocal,NEWTON_BOND,
ebond,fbond,delx,dely,delz,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef BOND_CLASS
BondStyle(table/omp,BondTableOMP)
#else
#ifndef LMP_BOND_TABLE_OMP_H
#define LMP_BOND_TABLE_OMP_H
#include "bond_table.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class BondTableOMP : public BondTable, public ThrOMP {
public:
BondTableOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,322 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "lmptype.h"
#include "mpi.h"
#include "math.h"
#include "dihedral_charmm_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "pair.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
DihedralCharmmOMP::DihedralCharmmOMP(class LAMMPS *lmp)
: DihedralCharmm(lmp), ThrOMP(lmp,THR_DIHEDRAL|THR_CHARMM)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralCharmmOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
// insure pair->ev_tally() will use 1-4 virial contribution
if (weightflag && vflag_global == 2)
force->pair->vflag_either = force->pair->vflag_global = 1;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralCharmmOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,i,m,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double ax,ay,az,bx,by,bz,rasq,rbsq,rgsq,rg,rginv,ra2inv,rb2inv,rabinv;
double df,df1,ddf1,fg,hg,fga,hgb,gaa,gbb;
double dtfx,dtfy,dtfz,dtgx,dtgy,dtgz,dthx,dthy,dthz;
double c,s,p,sx2,sy2,sz2;
int itype,jtype;
double delx,dely,delz,rsq,r2inv,r6inv;
double forcecoul,forcelj,fpair,ecoul,evdwl;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const double * const q = atom->q;
const int * const atomtype = atom->type;
const int * const * const dihedrallist = neighbor->dihedrallist;
const double qqrd2e = force->qqrd2e;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c,s calculation
ax = vb1y*vb2zm - vb1z*vb2ym;
ay = vb1z*vb2xm - vb1x*vb2zm;
az = vb1x*vb2ym - vb1y*vb2xm;
bx = vb3y*vb2zm - vb3z*vb2ym;
by = vb3z*vb2xm - vb3x*vb2zm;
bz = vb3x*vb2ym - vb3y*vb2xm;
rasq = ax*ax + ay*ay + az*az;
rbsq = bx*bx + by*by + bz*bz;
rgsq = vb2xm*vb2xm + vb2ym*vb2ym + vb2zm*vb2zm;
rg = sqrt(rgsq);
rginv = ra2inv = rb2inv = 0.0;
if (rg > 0) rginv = 1.0/rg;
if (rasq > 0) ra2inv = 1.0/rasq;
if (rbsq > 0) rb2inv = 1.0/rbsq;
rabinv = sqrt(ra2inv*rb2inv);
c = (ax*bx + ay*by + az*bz)*rabinv;
s = rg*rabinv*(ax*vb3x + ay*vb3y + az*vb3z);
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
m = multiplicity[type];
p = 1.0;
ddf1 = df1 = 0.0;
for (i = 0; i < m; i++) {
ddf1 = p*c - df1*s;
df1 = p*s + df1*c;
p = ddf1;
}
p = p*cos_shift[type] + df1*sin_shift[type];
df1 = df1*cos_shift[type] - ddf1*sin_shift[type];
df1 *= -m;
p += 1.0;
if (m == 0) {
p = 1.0 + cos_shift[type];
df1 = 0.0;
}
if (EFLAG) edihedral = k[type] * p;
fg = vb1x*vb2xm + vb1y*vb2ym + vb1z*vb2zm;
hg = vb3x*vb2xm + vb3y*vb2ym + vb3z*vb2zm;
fga = fg*ra2inv*rginv;
hgb = hg*rb2inv*rginv;
gaa = -ra2inv*rg;
gbb = rb2inv*rg;
dtfx = gaa*ax;
dtfy = gaa*ay;
dtfz = gaa*az;
dtgx = fga*ax - hgb*bx;
dtgy = fga*ay - hgb*by;
dtgz = fga*az - hgb*bz;
dthx = gbb*bx;
dthy = gbb*by;
dthz = gbb*bz;
df = -k[type] * df1;
sx2 = df*dtgx;
sy2 = df*dtgy;
sz2 = df*dtgz;
f1[0] = df*dtfx;
f1[1] = df*dtfy;
f1[2] = df*dtfz;
f2[0] = sx2 - f1[0];
f2[1] = sy2 - f1[1];
f2[2] = sz2 - f1[2];
f4[0] = df*dthx;
f4[1] = df*dthy;
f4[2] = df*dthz;
f3[0] = -sx2 - f4[0];
f3[1] = -sy2 - f4[1];
f3[2] = -sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
// 1-4 LJ and Coulomb interactions
// tally energy/virial in pair, using newton_bond as newton flag
if (weight[type] > 0.0) {
itype = atomtype[i1];
jtype = atomtype[i4];
delx = x[i1][0] - x[i4][0];
dely = x[i1][1] - x[i4][1];
delz = x[i1][2] - x[i4][2];
rsq = delx*delx + dely*dely + delz*delz;
r2inv = 1.0/rsq;
r6inv = r2inv*r2inv*r2inv;
if (implicit) forcecoul = qqrd2e * q[i1]*q[i4]*r2inv;
else forcecoul = qqrd2e * q[i1]*q[i4]*sqrt(r2inv);
forcelj = r6inv * (lj14_1[itype][jtype]*r6inv - lj14_2[itype][jtype]);
fpair = weight[type] * (forcelj+forcecoul)*r2inv;
if (EFLAG) {
ecoul = weight[type] * forcecoul;
evdwl = r6inv * (lj14_3[itype][jtype]*r6inv - lj14_4[itype][jtype]);
evdwl *= weight[type];
}
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += delx*fpair;
f[i1][1] += dely*fpair;
f[i1][2] += delz*fpair;
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] -= delx*fpair;
f[i4][1] -= dely*fpair;
f[i4][2] -= delz*fpair;
}
if (EVFLAG) ev_tally_thr(force->pair,i1,i4,nlocal,NEWTON_BOND,
evdwl,ecoul,fpair,delx,dely,delz,thr);
}
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(charmm/omp,DihedralCharmmOMP)
#else
#ifndef LMP_DIHEDRAL_CHARMM_OMP_H
#define LMP_DIHEDRAL_CHARMM_OMP_H
#include "dihedral_charmm.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralCharmmOMP : public DihedralCharmm, public ThrOMP {
public:
DihedralCharmmOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,531 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_class2_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.0000001
/* ---------------------------------------------------------------------- */
DihedralClass2OMP::DihedralClass2OMP(class LAMMPS *lmp)
: DihedralClass2(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralClass2OMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralClass2OMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,i,j,k,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral;
double r1mag2,r1,r2mag2,r2,r3mag2,r3;
double sb1,rb1,sb2,rb2,sb3,rb3,c0,r12c1;
double r12c2,costh12,costh13,costh23,sc1,sc2,s1,s2,c;
double cosphi,phi,sinphi,a11,a22,a33,a12,a13,a23,sx1,sx2;
double sx12,sy1,sy2,sy12,sz1,sz2,sz12,dphi1,dphi2,dphi3;
double de_dihedral,t1,t2,t3,t4,cos2phi,cos3phi,bt1,bt2;
double bt3,sumbte,db,sumbtf,at1,at2,at3,da,da1,da2,r1_0;
double r3_0,dr1,dr2,tk1,tk2,s12,sin2;
double dcosphidr[4][3],dphidr[4][3],dbonddr[3][4][3],dthetadr[2][4][3];
double fabcd[4][3];
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// distances
r1mag2 = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z;
r1 = sqrt(r1mag2);
r2mag2 = vb2x*vb2x + vb2y*vb2y + vb2z*vb2z;
r2 = sqrt(r2mag2);
r3mag2 = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z;
r3 = sqrt(r3mag2);
sb1 = 1.0/r1mag2;
rb1 = 1.0/r1;
sb2 = 1.0/r2mag2;
rb2 = 1.0/r2;
sb3 = 1.0/r3mag2;
rb3 = 1.0/r3;
c0 = (vb1x*vb3x + vb1y*vb3y + vb1z*vb3z) * rb1*rb3;
// angles
r12c1 = rb1*rb2;
r12c2 = rb2*rb3;
costh12 = (vb1x*vb2x + vb1y*vb2y + vb1z*vb2z) * r12c1;
costh13 = c0;
costh23 = (vb2xm*vb3x + vb2ym*vb3y + vb2zm*vb3z) * r12c2;
// cos and sin of 2 angles and final c
sin2 = MAX(1.0 - costh12*costh12,0.0);
sc1 = sqrt(sin2);
if (sc1 < SMALL) sc1 = SMALL;
sc1 = 1.0/sc1;
sin2 = MAX(1.0 - costh23*costh23,0.0);
sc2 = sqrt(sin2);
if (sc2 < SMALL) sc2 = SMALL;
sc2 = 1.0/sc2;
s1 = sc1 * sc1;
s2 = sc2 * sc2;
s12 = sc1 * sc2;
c = (c0 + costh12*costh23) * s12;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
cosphi = c;
phi = acos(c);
sinphi = sqrt(1.0 - c*c);
sinphi = MAX(sinphi,SMALL);
a11 = -c*sb1*s1;
a22 = sb2 * (2.0*costh13*s12 - c*(s1+s2));
a33 = -c*sb3*s2;
a12 = r12c1 * (costh12*c*s1 + costh23*s12);
a13 = rb1*rb3*s12;
a23 = r12c2 * (-costh23*c*s2 - costh12*s12);
sx1 = a11*vb1x + a12*vb2x + a13*vb3x;
sx2 = a12*vb1x + a22*vb2x + a23*vb3x;
sx12 = a13*vb1x + a23*vb2x + a33*vb3x;
sy1 = a11*vb1y + a12*vb2y + a13*vb3y;
sy2 = a12*vb1y + a22*vb2y + a23*vb3y;
sy12 = a13*vb1y + a23*vb2y + a33*vb3y;
sz1 = a11*vb1z + a12*vb2z + a13*vb3z;
sz2 = a12*vb1z + a22*vb2z + a23*vb3z;
sz12 = a13*vb1z + a23*vb2z + a33*vb3z;
// set up d(cos(phi))/d(r) and dphi/dr arrays
dcosphidr[0][0] = -sx1;
dcosphidr[0][1] = -sy1;
dcosphidr[0][2] = -sz1;
dcosphidr[1][0] = sx2 + sx1;
dcosphidr[1][1] = sy2 + sy1;
dcosphidr[1][2] = sz2 + sz1;
dcosphidr[2][0] = sx12 - sx2;
dcosphidr[2][1] = sy12 - sy2;
dcosphidr[2][2] = sz12 - sz2;
dcosphidr[3][0] = -sx12;
dcosphidr[3][1] = -sy12;
dcosphidr[3][2] = -sz12;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
dphidr[i][j] = -dcosphidr[i][j] / sinphi;
// energy
dphi1 = phi - phi1[type];
dphi2 = 2.0*phi - phi2[type];
dphi3 = 3.0*phi - phi3[type];
if (EFLAG) edihedral = k1[type]*(1.0 - cos(dphi1)) +
k2[type]*(1.0 - cos(dphi2)) +
k3[type]*(1.0 - cos(dphi3));
de_dihedral = k1[type]*sin(dphi1) + 2.0*k2[type]*sin(dphi2) +
3.0*k3[type]*sin(dphi3);
// torsion forces on all 4 atoms
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] = de_dihedral*dphidr[i][j];
// set up d(bond)/d(r) array
// dbonddr(i,j,k) = bond i, atom j, coordinate k
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++)
dbonddr[i][j][k] = 0.0;
// bond1
dbonddr[0][0][0] = vb1x / r1;
dbonddr[0][0][1] = vb1y / r1;
dbonddr[0][0][2] = vb1z / r1;
dbonddr[0][1][0] = -vb1x / r1;
dbonddr[0][1][1] = -vb1y / r1;
dbonddr[0][1][2] = -vb1z / r1;
// bond2
dbonddr[1][1][0] = vb2x / r2;
dbonddr[1][1][1] = vb2y / r2;
dbonddr[1][1][2] = vb2z / r2;
dbonddr[1][2][0] = -vb2x / r2;
dbonddr[1][2][1] = -vb2y / r2;
dbonddr[1][2][2] = -vb2z / r2;
// bond3
dbonddr[2][2][0] = vb3x / r3;
dbonddr[2][2][1] = vb3y / r3;
dbonddr[2][2][2] = vb3z / r3;
dbonddr[2][3][0] = -vb3x / r3;
dbonddr[2][3][1] = -vb3y / r3;
dbonddr[2][3][2] = -vb3z / r3;
// set up d(theta)/d(r) array
// dthetadr(i,j,k) = angle i, atom j, coordinate k
for (i = 0; i < 2; i++)
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++)
dthetadr[i][j][k] = 0.0;
t1 = costh12 / r1mag2;
t2 = costh23 / r2mag2;
t3 = costh12 / r2mag2;
t4 = costh23 / r3mag2;
// angle12
dthetadr[0][0][0] = sc1 * ((t1 * vb1x) - (vb2x * r12c1));
dthetadr[0][0][1] = sc1 * ((t1 * vb1y) - (vb2y * r12c1));
dthetadr[0][0][2] = sc1 * ((t1 * vb1z) - (vb2z * r12c1));
dthetadr[0][1][0] = sc1 * ((-t1 * vb1x) + (vb2x * r12c1) +
(-t3 * vb2x) + (vb1x * r12c1));
dthetadr[0][1][1] = sc1 * ((-t1 * vb1y) + (vb2y * r12c1) +
(-t3 * vb2y) + (vb1y * r12c1));
dthetadr[0][1][2] = sc1 * ((-t1 * vb1z) + (vb2z * r12c1) +
(-t3 * vb2z) + (vb1z * r12c1));
dthetadr[0][2][0] = sc1 * ((t3 * vb2x) - (vb1x * r12c1));
dthetadr[0][2][1] = sc1 * ((t3 * vb2y) - (vb1y * r12c1));
dthetadr[0][2][2] = sc1 * ((t3 * vb2z) - (vb1z * r12c1));
// angle23
dthetadr[1][1][0] = sc2 * ((t2 * vb2x) + (vb3x * r12c2));
dthetadr[1][1][1] = sc2 * ((t2 * vb2y) + (vb3y * r12c2));
dthetadr[1][1][2] = sc2 * ((t2 * vb2z) + (vb3z * r12c2));
dthetadr[1][2][0] = sc2 * ((-t2 * vb2x) - (vb3x * r12c2) +
(t4 * vb3x) + (vb2x * r12c2));
dthetadr[1][2][1] = sc2 * ((-t2 * vb2y) - (vb3y * r12c2) +
(t4 * vb3y) + (vb2y * r12c2));
dthetadr[1][2][2] = sc2 * ((-t2 * vb2z) - (vb3z * r12c2) +
(t4 * vb3z) + (vb2z * r12c2));
dthetadr[1][3][0] = -sc2 * ((t4 * vb3x) + (vb2x * r12c2));
dthetadr[1][3][1] = -sc2 * ((t4 * vb3y) + (vb2y * r12c2));
dthetadr[1][3][2] = -sc2 * ((t4 * vb3z) + (vb2z * r12c2));
// mid-bond/torsion coupling
// energy on bond2 (middle bond)
cos2phi = cos(2.0*phi);
cos3phi = cos(3.0*phi);
bt1 = mbt_f1[type] * cosphi;
bt2 = mbt_f2[type] * cos2phi;
bt3 = mbt_f3[type] * cos3phi;
sumbte = bt1 + bt2 + bt3;
db = r2 - mbt_r0[type];
if (EFLAG) edihedral += db * sumbte;
// force on bond2
bt1 = -mbt_f1[type] * sinphi;
bt2 = -2.0 * mbt_f2[type] * sin(2.0*phi);
bt3 = -3.0 * mbt_f3[type] * sin(3.0*phi);
sumbtf = bt1 + bt2 + bt3;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] += db*sumbtf*dphidr[i][j] + sumbte*dbonddr[1][i][j];
// end-bond/torsion coupling
// energy on bond1 (first bond)
bt1 = ebt_f1_1[type] * cosphi;
bt2 = ebt_f2_1[type] * cos2phi;
bt3 = ebt_f3_1[type] * cos3phi;
sumbte = bt1 + bt2 + bt3;
db = r1 - ebt_r0_1[type];
if (EFLAG) edihedral += db * (bt1+bt2+bt3);
// force on bond1
bt1 = ebt_f1_1[type] * sinphi;
bt2 = 2.0 * ebt_f2_1[type] * sin(2.0*phi);
bt3 = 3.0 * ebt_f3_1[type] * sin(3.0*phi);
sumbtf = bt1 + bt2 + bt3;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] -= db*sumbtf*dphidr[i][j] + sumbte*dbonddr[0][i][j];
// end-bond/torsion coupling
// energy on bond3 (last bond)
bt1 = ebt_f1_2[type] * cosphi;
bt2 = ebt_f2_2[type] * cos2phi;
bt3 = ebt_f3_2[type] * cos3phi;
sumbte = bt1 + bt2 + bt3;
db = r3 - ebt_r0_2[type];
if (EFLAG) edihedral += db * (bt1+bt2+bt3);
// force on bond3
bt1 = -ebt_f1_2[type] * sinphi;
bt2 = -2.0 * ebt_f2_2[type] * sin(2.0*phi);
bt3 = -3.0 * ebt_f3_2[type] * sin(3.0*phi);
sumbtf = bt1 + bt2 + bt3;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] += db*sumbtf*dphidr[i][j] + sumbte*dbonddr[2][i][j];
// angle/torsion coupling
// energy on angle1
at1 = at_f1_1[type] * cosphi;
at2 = at_f2_1[type] * cos2phi;
at3 = at_f3_1[type] * cos3phi;
sumbte = at1 + at2 + at3;
da = acos(costh12) - at_theta0_1[type];
if (EFLAG) edihedral += da * (at1+at2+at3);
// force on angle1
bt1 = at_f1_1[type] * sinphi;
bt2 = 2.0 * at_f2_1[type] * sin(2.0*phi);
bt3 = 3.0 * at_f3_1[type] * sin(3.0*phi);
sumbtf = bt1 + bt2 + bt3;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] -= da*sumbtf*dphidr[i][j] + sumbte*dthetadr[0][i][j];
// energy on angle2
at1 = at_f1_2[type] * cosphi;
at2 = at_f2_2[type] * cos2phi;
at3 = at_f3_2[type] * cos3phi;
sumbte = at1 + at2 + at3;
da = acos(costh23) - at_theta0_2[type];
if (EFLAG) edihedral += da * (at1+at2+at3);
// force on angle2
bt1 = -at_f1_2[type] * sinphi;
bt2 = -2.0 * at_f2_2[type] * sin(2.0*phi);
bt3 = -3.0 * at_f3_2[type] * sin(3.0*phi);
sumbtf = bt1 + bt2 + bt3;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] += da*sumbtf*dphidr[i][j] + sumbte*dthetadr[1][i][j];
// angle/angle/torsion coupling
da1 = acos(costh12) - aat_theta0_1[type];
da2 = acos(costh23) - aat_theta0_2[type];
if (EFLAG) edihedral += aat_k[type]*da1*da2*cosphi;
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] -= aat_k[type] *
(cosphi * (da2*dthetadr[0][i][j] - da1*dthetadr[1][i][j]) +
sinphi * da1*da2*dphidr[i][j]);
// bond1/bond3 coupling
if (fabs(bb13t_k[type]) > SMALL) {
r1_0 = bb13t_r10[type];
r3_0 = bb13t_r30[type];
dr1 = r1 - r1_0;
dr2 = r3 - r3_0;
tk1 = -bb13t_k[type] * dr1 / r3;
tk2 = -bb13t_k[type] * dr2 / r1;
if (EFLAG) edihedral += bb13t_k[type]*dr1*dr2;
fabcd[0][0] += tk2 * vb1x;
fabcd[0][1] += tk2 * vb1y;
fabcd[0][2] += tk2 * vb1z;
fabcd[1][0] -= tk2 * vb1x;
fabcd[1][1] -= tk2 * vb1y;
fabcd[1][2] -= tk2 * vb1z;
fabcd[2][0] -= tk1 * vb3x;
fabcd[2][1] -= tk1 * vb3y;
fabcd[2][2] -= tk1 * vb3z;
fabcd[3][0] += tk1 * vb3x;
fabcd[3][1] += tk1 * vb3y;
fabcd[3][2] += tk1 * vb3z;
}
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += fabcd[0][0];
f[i1][1] += fabcd[0][1];
f[i1][2] += fabcd[0][2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += fabcd[1][0];
f[i2][1] += fabcd[1][1];
f[i2][2] += fabcd[1][2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += fabcd[2][0];
f[i3][1] += fabcd[2][1];
f[i3][2] += fabcd[2][2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += fabcd[3][0];
f[i4][1] += fabcd[3][1];
f[i4][2] += fabcd[3][2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,
fabcd[0],fabcd[2],fabcd[3],
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(class2/omp,DihedralClass2OMP)
#else
#ifndef LMP_DIHEDRAL_CLASS2_OMP_H
#define LMP_DIHEDRAL_CLASS2_OMP_H
#include "dihedral_class2.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralClass2OMP : public DihedralClass2, public ThrOMP {
public:
DihedralClass2OMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,262 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_cosine_shift_exp_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
DihedralCosineShiftExpOMP::DihedralCosineShiftExpOMP(class LAMMPS *lmp)
: DihedralCosineShiftExp(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralCosineShiftExpOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralCosineShiftExpOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double ax,ay,az,bx,by,bz,rasq,rbsq,rgsq,rg,rginv,ra2inv,rb2inv,rabinv;
double df,fg,hg,fga,hgb,gaa,gbb;
double dtfx,dtfy,dtfz,dtgx,dtgy,dtgz,dthx,dthy,dthz;
double c,s,sx2,sy2,sz2;
double cccpsss,cssmscc,exp2;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c,s calculation
ax = vb1y*vb2zm - vb1z*vb2ym;
ay = vb1z*vb2xm - vb1x*vb2zm;
az = vb1x*vb2ym - vb1y*vb2xm;
bx = vb3y*vb2zm - vb3z*vb2ym;
by = vb3z*vb2xm - vb3x*vb2zm;
bz = vb3x*vb2ym - vb3y*vb2xm;
rasq = ax*ax + ay*ay + az*az;
rbsq = bx*bx + by*by + bz*bz;
rgsq = vb2xm*vb2xm + vb2ym*vb2ym + vb2zm*vb2zm;
rg = sqrt(rgsq);
rginv = ra2inv = rb2inv = 0.0;
if (rg > 0) rginv = 1.0/rg;
if (rasq > 0) ra2inv = 1.0/rasq;
if (rbsq > 0) rb2inv = 1.0/rbsq;
rabinv = sqrt(ra2inv*rb2inv);
c = (ax*bx + ay*by + az*bz)*rabinv;
s = rg*rabinv*(ax*vb3x + ay*vb3y + az*vb3z);
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
double aa=a[type];
double uumin=umin[type];
cccpsss = c*cost[type]+s*sint[type];
cssmscc = c*sint[type]-s*cost[type];
if (doExpansion[type]) {
// |a|<0.001 so use expansions relative precision <1e-5
if (EFLAG) edihedral = -0.125*(1+cccpsss)*(4+aa*(cccpsss-1))*uumin;
df=0.5*uumin*( cssmscc + 0.5*aa*cccpsss);
} else {
exp2=exp(0.5*aa*(1+cccpsss));
if (EFLAG) edihedral = opt1[type]*(1-exp2);
df= 0.5*opt1[type]*aa* ( exp2*cssmscc );
}
fg = vb1x*vb2xm + vb1y*vb2ym + vb1z*vb2zm;
hg = vb3x*vb2xm + vb3y*vb2ym + vb3z*vb2zm;
fga = fg*ra2inv*rginv;
hgb = hg*rb2inv*rginv;
gaa = -ra2inv*rg;
gbb = rb2inv*rg;
dtfx = gaa*ax;
dtfy = gaa*ay;
dtfz = gaa*az;
dtgx = fga*ax - hgb*bx;
dtgy = fga*ay - hgb*by;
dtgz = fga*az - hgb*bz;
dthx = gbb*bx;
dthy = gbb*by;
dthz = gbb*bz;
sx2 = df*dtgx;
sy2 = df*dtgy;
sz2 = df*dtgz;
f1[0] = df*dtfx;
f1[1] = df*dtfy;
f1[2] = df*dtfz;
f2[0] = sx2 - f1[0];
f2[1] = sy2 - f1[1];
f2[2] = sz2 - f1[2];
f4[0] = df*dthx;
f4[1] = df*dthy;
f4[2] = df*dthz;
f3[0] = -sx2 - f4[0];
f3[1] = -sy2 - f4[1];
f3[2] = -sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(cosine/shift/exp/omp,DihedralCosineShiftExpOMP)
#else
#ifndef LMP_DIHEDRAL_COSINE_SHIFT_EXP_OMP_H
#define LMP_DIHEDRAL_COSINE_SHIFT_EXP_OMP_H
#include "dihedral_cosine_shift_exp.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralCosineShiftExpOMP : public DihedralCosineShiftExp, public ThrOMP {
public:
DihedralCosineShiftExpOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,269 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_harmonic_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
DihedralHarmonicOMP::DihedralHarmonicOMP(class LAMMPS *lmp)
: DihedralHarmonic(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralHarmonicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralHarmonicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,i,m,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double ax,ay,az,bx,by,bz,rasq,rbsq,rgsq,rg,rginv,ra2inv,rb2inv,rabinv;
double df,df1,ddf1,fg,hg,fga,hgb,gaa,gbb;
double dtfx,dtfy,dtfz,dtgx,dtgy,dtgz,dthx,dthy,dthz;
double c,s,p,sx2,sy2,sz2;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c,s calculation
ax = vb1y*vb2zm - vb1z*vb2ym;
ay = vb1z*vb2xm - vb1x*vb2zm;
az = vb1x*vb2ym - vb1y*vb2xm;
bx = vb3y*vb2zm - vb3z*vb2ym;
by = vb3z*vb2xm - vb3x*vb2zm;
bz = vb3x*vb2ym - vb3y*vb2xm;
rasq = ax*ax + ay*ay + az*az;
rbsq = bx*bx + by*by + bz*bz;
rgsq = vb2xm*vb2xm + vb2ym*vb2ym + vb2zm*vb2zm;
rg = sqrt(rgsq);
rginv = ra2inv = rb2inv = 0.0;
if (rg > 0) rginv = 1.0/rg;
if (rasq > 0) ra2inv = 1.0/rasq;
if (rbsq > 0) rb2inv = 1.0/rbsq;
rabinv = sqrt(ra2inv*rb2inv);
c = (ax*bx + ay*by + az*bz)*rabinv;
s = rg*rabinv*(ax*vb3x + ay*vb3y + az*vb3z);
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
m = multiplicity[type];
p = 1.0;
ddf1 = df1 = 0.0;
for (i = 0; i < m; i++) {
ddf1 = p*c - df1*s;
df1 = p*s + df1*c;
p = ddf1;
}
p = p*cos_shift[type] + df1*sin_shift[type];
df1 = df1*cos_shift[type] - ddf1*sin_shift[type];
df1 *= -m;
p += 1.0;
if (m == 0) {
p = 1.0 + cos_shift[type];
df1 = 0.0;
}
if (EFLAG) edihedral = k[type] * p;
fg = vb1x*vb2xm + vb1y*vb2ym + vb1z*vb2zm;
hg = vb3x*vb2xm + vb3y*vb2ym + vb3z*vb2zm;
fga = fg*ra2inv*rginv;
hgb = hg*rb2inv*rginv;
gaa = -ra2inv*rg;
gbb = rb2inv*rg;
dtfx = gaa*ax;
dtfy = gaa*ay;
dtfz = gaa*az;
dtgx = fga*ax - hgb*bx;
dtgy = fga*ay - hgb*by;
dtgz = fga*az - hgb*bz;
dthx = gbb*bx;
dthy = gbb*by;
dthz = gbb*bz;
df = -k[type] * df1;
sx2 = df*dtgx;
sy2 = df*dtgy;
sz2 = df*dtgz;
f1[0] = df*dtfx;
f1[1] = df*dtfy;
f1[2] = df*dtfz;
f2[0] = sx2 - f1[0];
f2[1] = sy2 - f1[1];
f2[2] = sz2 - f1[2];
f4[0] = df*dthx;
f4[1] = df*dthy;
f4[2] = df*dthz;
f3[0] = -sx2 - f4[0];
f3[1] = -sy2 - f4[1];
f3[2] = -sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(harmonic/omp,DihedralHarmonicOMP)
#else
#ifndef LMP_DIHEDRAL_HARMONIC_OMP_H
#define LMP_DIHEDRAL_HARMONIC_OMP_H
#include "dihedral_harmonic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralHarmonicOMP : public DihedralHarmonic, public ThrOMP {
public:
DihedralHarmonicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,282 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_helix_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "math_const.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define TOLERANCE 0.05
#define SMALL 0.001
#define SMALLER 0.00001
/* ---------------------------------------------------------------------- */
DihedralHelixOMP::DihedralHelixOMP(class LAMMPS *lmp)
: DihedralHelix(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralHelixOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralHelixOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double sb1,sb2,sb3,rb1,rb3,c0,b1mag2,b1mag,b2mag2;
double b2mag,b3mag2,b3mag,ctmp,r12c1,c1mag,r12c2;
double c2mag,sc1,sc2,s1,s12,c,pd,a,a11,a22;
double a33,a12,a13,a23,sx2,sy2,sz2;
double s2,cx,cy,cz,cmag,dx,phi,si,siinv,sin2;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c0 calculation
sb1 = 1.0 / (vb1x*vb1x + vb1y*vb1y + vb1z*vb1z);
sb2 = 1.0 / (vb2x*vb2x + vb2y*vb2y + vb2z*vb2z);
sb3 = 1.0 / (vb3x*vb3x + vb3y*vb3y + vb3z*vb3z);
rb1 = sqrt(sb1);
rb3 = sqrt(sb3);
c0 = (vb1x*vb3x + vb1y*vb3y + vb1z*vb3z) * rb1*rb3;
// 1st and 2nd angle
b1mag2 = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z;
b1mag = sqrt(b1mag2);
b2mag2 = vb2x*vb2x + vb2y*vb2y + vb2z*vb2z;
b2mag = sqrt(b2mag2);
b3mag2 = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z;
b3mag = sqrt(b3mag2);
ctmp = vb1x*vb2x + vb1y*vb2y + vb1z*vb2z;
r12c1 = 1.0 / (b1mag*b2mag);
c1mag = ctmp * r12c1;
ctmp = vb2xm*vb3x + vb2ym*vb3y + vb2zm*vb3z;
r12c2 = 1.0 / (b2mag*b3mag);
c2mag = ctmp * r12c2;
// cos and sin of 2 angles and final c
sin2 = MAX(1.0 - c1mag*c1mag,0.0);
sc1 = sqrt(sin2);
if (sc1 < SMALL) sc1 = SMALL;
sc1 = 1.0/sc1;
sin2 = MAX(1.0 - c2mag*c2mag,0.0);
sc2 = sqrt(sin2);
if (sc2 < SMALL) sc2 = SMALL;
sc2 = 1.0/sc2;
s1 = sc1 * sc1;
s2 = sc2 * sc2;
s12 = sc1 * sc2;
c = (c0 + c1mag*c2mag) * s12;
cx = vb1y*vb2z - vb1z*vb2y;
cy = vb1z*vb2x - vb1x*vb2z;
cz = vb1x*vb2y - vb1y*vb2x;
cmag = sqrt(cx*cx + cy*cy + cz*cz);
dx = (cx*vb3x + cy*vb3y + cz*vb3z)/cmag/b3mag;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
phi = acos(c);
if (dx < 0.0) phi *= -1.0;
si = sin(phi);
if (fabs(si) < SMALLER) si = SMALLER;
siinv = 1.0/si;
pd = -aphi[type] + 3.0*bphi[type]*sin(3.0*phi)*siinv +
cphi[type]*sin(phi + MY_PI4)*siinv;
if (EFLAG) edihedral = aphi[type]*(1.0 - c) + bphi[type]*(1.0 + cos(3.0*phi)) +
cphi[type]*(1.0 + cos(phi + MY_PI4));
a = pd;
c = c * a;
s12 = s12 * a;
a11 = c*sb1*s1;
a22 = -sb2 * (2.0*c0*s12 - c*(s1+s2));
a33 = c*sb3*s2;
a12 = -r12c1 * (c1mag*c*s1 + c2mag*s12);
a13 = -rb1*rb3*s12;
a23 = r12c2 * (c2mag*c*s2 + c1mag*s12);
sx2 = a12*vb1x + a22*vb2x + a23*vb3x;
sy2 = a12*vb1y + a22*vb2y + a23*vb3y;
sz2 = a12*vb1z + a22*vb2z + a23*vb3z;
f1[0] = a11*vb1x + a12*vb2x + a13*vb3x;
f1[1] = a11*vb1y + a12*vb2y + a13*vb3y;
f1[2] = a11*vb1z + a12*vb2z + a13*vb3z;
f2[0] = -sx2 - f1[0];
f2[1] = -sy2 - f1[1];
f2[2] = -sz2 - f1[2];
f4[0] = a13*vb1x + a23*vb2x + a33*vb3x;
f4[1] = a13*vb1y + a23*vb2y + a33*vb3y;
f4[2] = a13*vb1z + a23*vb2z + a33*vb3z;
f3[0] = sx2 - f4[0];
f3[1] = sy2 - f4[1];
f3[2] = sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(helix/omp,DihedralHelixOMP)
#else
#ifndef LMP_DIHEDRAL_HELIX_OMP_H
#define LMP_DIHEDRAL_HELIX_OMP_H
#include "dihedral_helix.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralHelixOMP : public DihedralHelix, public ThrOMP {
public:
DihedralHelixOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,269 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_multi_harmonic_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
DihedralMultiHarmonicOMP::DihedralMultiHarmonicOMP(class LAMMPS *lmp)
: DihedralMultiHarmonic(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralMultiHarmonicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralMultiHarmonicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double sb1,sb2,sb3,rb1,rb3,c0,b1mag2,b1mag,b2mag2;
double b2mag,b3mag2,b3mag,ctmp,r12c1,c1mag,r12c2;
double c2mag,sc1,sc2,s1,s12,c,pd,a,a11,a22;
double a33,a12,a13,a23,sx2,sy2,sz2;
double s2,sin2;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c0 calculation
sb1 = 1.0 / (vb1x*vb1x + vb1y*vb1y + vb1z*vb1z);
sb2 = 1.0 / (vb2x*vb2x + vb2y*vb2y + vb2z*vb2z);
sb3 = 1.0 / (vb3x*vb3x + vb3y*vb3y + vb3z*vb3z);
rb1 = sqrt(sb1);
rb3 = sqrt(sb3);
c0 = (vb1x*vb3x + vb1y*vb3y + vb1z*vb3z) * rb1*rb3;
// 1st and 2nd angle
b1mag2 = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z;
b1mag = sqrt(b1mag2);
b2mag2 = vb2x*vb2x + vb2y*vb2y + vb2z*vb2z;
b2mag = sqrt(b2mag2);
b3mag2 = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z;
b3mag = sqrt(b3mag2);
ctmp = vb1x*vb2x + vb1y*vb2y + vb1z*vb2z;
r12c1 = 1.0 / (b1mag*b2mag);
c1mag = ctmp * r12c1;
ctmp = vb2xm*vb3x + vb2ym*vb3y + vb2zm*vb3z;
r12c2 = 1.0 / (b2mag*b3mag);
c2mag = ctmp * r12c2;
// cos and sin of 2 angles and final c
sin2 = MAX(1.0 - c1mag*c1mag,0.0);
sc1 = sqrt(sin2);
if (sc1 < SMALL) sc1 = SMALL;
sc1 = 1.0/sc1;
sin2 = MAX(1.0 - c2mag*c2mag,0.0);
sc2 = sqrt(sin2);
if (sc2 < SMALL) sc2 = SMALL;
sc2 = 1.0/sc2;
s1 = sc1 * sc1;
s2 = sc2 * sc2;
s12 = sc1 * sc2;
c = (c0 + c1mag*c2mag) * s12;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// force & energy
// p = sum (i=1,5) a_i * c**(i-1)
// pd = dp/dc
pd = a2[type] + c*(2.0*a3[type] + c*(3.0*a4[type] + c*4.0*a5[type]));
if (EFLAG)
edihedral = a1[type] + c*(a2[type] + c*(a3[type] + c*(a4[type] + c*a5[type])));
a = pd;
c = c * a;
s12 = s12 * a;
a11 = c*sb1*s1;
a22 = -sb2 * (2.0*c0*s12 - c*(s1+s2));
a33 = c*sb3*s2;
a12 = -r12c1*(c1mag*c*s1 + c2mag*s12);
a13 = -rb1*rb3*s12;
a23 = r12c2*(c2mag*c*s2 + c1mag*s12);
sx2 = a12*vb1x + a22*vb2x + a23*vb3x;
sy2 = a12*vb1y + a22*vb2y + a23*vb3y;
sz2 = a12*vb1z + a22*vb2z + a23*vb3z;
f1[0] = a11*vb1x + a12*vb2x + a13*vb3x;
f1[1] = a11*vb1y + a12*vb2y + a13*vb3y;
f1[2] = a11*vb1z + a12*vb2z + a13*vb3z;
f2[0] = -sx2 - f1[0];
f2[1] = -sy2 - f1[1];
f2[2] = -sz2 - f1[2];
f4[0] = a13*vb1x + a23*vb2x + a33*vb3x;
f4[1] = a13*vb1y + a23*vb2y + a33*vb3y;
f4[2] = a13*vb1z + a23*vb2z + a33*vb3z;
f3[0] = sx2 - f4[0];
f3[1] = sy2 - f4[1];
f3[2] = sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(multi/harmonic/omp,DihedralMultiHarmonicOMP)
#else
#ifndef LMP_DIHEDRAL_MULTI_HARMONIC_OMP_H
#define LMP_DIHEDRAL_MULTI_HARMONIC_OMP_H
#include "dihedral_multi_harmonic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralMultiHarmonicOMP : public DihedralMultiHarmonic, public ThrOMP {
public:
DihedralMultiHarmonicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,285 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_opls_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
#define SMALLER 0.00001
/* ---------------------------------------------------------------------- */
DihedralOPLSOMP::DihedralOPLSOMP(class LAMMPS *lmp)
: DihedralOPLS(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralOPLSOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralOPLSOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double edihedral,f1[3],f2[3],f3[3],f4[3];
double sb1,sb2,sb3,rb1,rb3,c0,b1mag2,b1mag,b2mag2;
double b2mag,b3mag2,b3mag,ctmp,r12c1,c1mag,r12c2;
double c2mag,sc1,sc2,s1,s12,c,pd,a,a11,a22;
double a33,a12,a13,a23,sx2,sy2,sz2;
double s2,cx,cy,cz,cmag,dx,phi,si,siinv,sin2;
edihedral = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c0 calculation
sb1 = 1.0 / (vb1x*vb1x + vb1y*vb1y + vb1z*vb1z);
sb2 = 1.0 / (vb2x*vb2x + vb2y*vb2y + vb2z*vb2z);
sb3 = 1.0 / (vb3x*vb3x + vb3y*vb3y + vb3z*vb3z);
rb1 = sqrt(sb1);
rb3 = sqrt(sb3);
c0 = (vb1x*vb3x + vb1y*vb3y + vb1z*vb3z) * rb1*rb3;
// 1st and 2nd angle
b1mag2 = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z;
b1mag = sqrt(b1mag2);
b2mag2 = vb2x*vb2x + vb2y*vb2y + vb2z*vb2z;
b2mag = sqrt(b2mag2);
b3mag2 = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z;
b3mag = sqrt(b3mag2);
ctmp = vb1x*vb2x + vb1y*vb2y + vb1z*vb2z;
r12c1 = 1.0 / (b1mag*b2mag);
c1mag = ctmp * r12c1;
ctmp = vb2xm*vb3x + vb2ym*vb3y + vb2zm*vb3z;
r12c2 = 1.0 / (b2mag*b3mag);
c2mag = ctmp * r12c2;
// cos and sin of 2 angles and final c
sin2 = MAX(1.0 - c1mag*c1mag,0.0);
sc1 = sqrt(sin2);
if (sc1 < SMALL) sc1 = SMALL;
sc1 = 1.0/sc1;
sin2 = MAX(1.0 - c2mag*c2mag,0.0);
sc2 = sqrt(sin2);
if (sc2 < SMALL) sc2 = SMALL;
sc2 = 1.0/sc2;
s1 = sc1 * sc1;
s2 = sc2 * sc2;
s12 = sc1 * sc2;
c = (c0 + c1mag*c2mag) * s12;
cx = vb1y*vb2z - vb1z*vb2y;
cy = vb1z*vb2x - vb1x*vb2z;
cz = vb1x*vb2y - vb1y*vb2x;
cmag = sqrt(cx*cx + cy*cy + cz*cz);
dx = (cx*vb3x + cy*vb3y + cz*vb3z)/cmag/b3mag;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Dihedral problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// force & energy
// p = sum (i=1,4) k_i * (1 + (-1)**(i+1)*cos(i*phi) )
// pd = dp/dc
phi = acos(c);
if (dx < 0.0) phi *= -1.0;
si = sin(phi);
if (fabs(si) < SMALLER) si = SMALLER;
siinv = 1.0/si;
pd = k1[type] - 2.0*k2[type]*sin(2.0*phi)*siinv +
3.0*k3[type]*sin(3.0*phi)*siinv - 4.0*k4[type]*sin(4.0*phi)*siinv;
if (EFLAG) edihedral = k1[type]*(1.0 + c) + k2[type]*(1.0 - cos(2.0*phi))
+ k3[type]*(1.0 + cos(3.0*phi)) + k4[type]*(1.0 - cos(4.0*phi));
a = pd;
c = c * a;
s12 = s12 * a;
a11 = c*sb1*s1;
a22 = -sb2 * (2.0*c0*s12 - c*(s1+s2));
a33 = c*sb3*s2;
a12 = -r12c1 * (c1mag*c*s1 + c2mag*s12);
a13 = -rb1*rb3*s12;
a23 = r12c2 * (c2mag*c*s2 + c1mag*s12);
sx2 = a12*vb1x + a22*vb2x + a23*vb3x;
sy2 = a12*vb1y + a22*vb2y + a23*vb3y;
sz2 = a12*vb1z + a22*vb2z + a23*vb3z;
f1[0] = a11*vb1x + a12*vb2x + a13*vb3x;
f1[1] = a11*vb1y + a12*vb2y + a13*vb3y;
f1[2] = a11*vb1z + a12*vb2z + a13*vb3z;
f2[0] = -sx2 - f1[0];
f2[1] = -sy2 - f1[1];
f2[2] = -sz2 - f1[2];
f4[0] = a13*vb1x + a23*vb2x + a33*vb3x;
f4[1] = a13*vb1y + a23*vb2y + a33*vb3y;
f4[2] = a13*vb1z + a23*vb2z + a33*vb3z;
f3[0] = sx2 - f4[0];
f3[1] = sy2 - f4[1];
f3[2] = sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(opls/omp,DihedralOPLSOMP)
#else
#ifndef LMP_DIHEDRAL_OPLS_OMP_H
#define LMP_DIHEDRAL_OPLS_OMP_H
#include "dihedral_opls.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralOPLSOMP : public DihedralOPLS, public ThrOMP {
public:
DihedralOPLSOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,345 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "dihedral_table_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace DIHEDRAL_TABLE_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
DihedralTableOMP::DihedralTableOMP(class LAMMPS *lmp)
: DihedralTable(lmp), ThrOMP(lmp,THR_DIHEDRAL)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void DihedralTableOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->ndihedrallist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void DihedralTableOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double edihedral,f1[3],f2[3],f3[3],f4[3];
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const dihedrallist = neighbor->dihedrallist;
const int nlocal = atom->nlocal;
// The dihedral angle "phi" is the angle between n123 and n234
// the planes defined by atoms i1,i2,i3, and i2,i3,i4.
//
// Definitions of vectors: vb12, vb23, vb34, perp12on23
// proj12on23, perp43on32, proj43on32
//
// Note: The positions of the 4 atoms are labeled x[i1], x[i2], x[i3], x[i4]
// (which are also vectors)
//
// proj12on23 proj34on23
// ---------> ----------->
// .
// .
// .
// x[i2] . x[i3]
// . __@----------vb23-------->@ . . . . .
// /|\ /| \ |
// | / \ |
// | / \ |
// perp12vs23 / \ |
// | / \ perp34vs23
// | vb12 \ |
// | / vb34 |
// | / \ |
// | / \ |
// | / \ |
// @ \ |
// _\| \|/
// x[i1] @
//
// x[i4]
//
double vb12[g_dim]; // displacement vector from atom i1 towards atom i2
// vb12[d] = x[i2][d] - x[i1][d] (for d=0,1,2)
double vb23[g_dim]; // displacement vector from atom i2 towards atom i3
// vb23[d] = x[i3][d] - x[i2][d] (for d=0,1,2)
double vb34[g_dim]; // displacement vector from atom i3 towards atom i4
// vb34[d] = x[i4][d] - x[i3][d] (for d=0,1,2)
// n123 & n234: These two unit vectors are normal to the planes
// defined by atoms 1,2,3 and 2,3,4.
double n123[g_dim]; //n123=vb23 x vb12 / |vb23 x vb12| ("x" is cross product)
double n234[g_dim]; //n234=vb23 x vb34 / |vb23 x vb34| ("x" is cross product)
double proj12on23[g_dim];
// proj12on23[d] = (vb23[d]/|vb23|) * DotProduct(vb12,vb23)/|vb12|*|vb23|
double proj34on23[g_dim];
// proj34on23[d] = (vb34[d]/|vb23|) * DotProduct(vb34,vb23)/|vb34|*|vb23|
double perp12on23[g_dim];
// perp12on23[d] = v12[d] - proj12on23[d]
double perp34on23[g_dim];
// perp34on23[d] = v34[d] - proj34on23[d]
edihedral = 0.0;
for (n = nfrom; n < nto; n++) {
i1 = dihedrallist[n][0];
i2 = dihedrallist[n][1];
i3 = dihedrallist[n][2];
i4 = dihedrallist[n][3];
type = dihedrallist[n][4];
// ------ Step 1: Compute the dihedral angle "phi" ------
//
// Phi() calculates the dihedral angle.
// This function also calculates the vectors:
// vb12, vb23, vb34, n123, and n234, which we will need later.
double phi = Phi(x[i1], x[i2], x[i3], x[i4], domain,
vb12, vb23, vb34, n123, n234);
// ------ Step 2: Compute the gradient of phi with atomic position: ------
//
// Gradient variables:
//
// dphi_dx1, dphi_dx2, dphi_dx3, dphi_dx4 are the gradients of phi with
// respect to the atomic positions of atoms i1, i2, i3, i4, respectively.
// As an example, consider dphi_dx1. The d'th element is:
double dphi_dx1[g_dim]; // d phi
double dphi_dx2[g_dim]; // dphi_dx1[d] = ---------- (partial derivatives)
double dphi_dx3[g_dim]; // d x[i1][d]
double dphi_dx4[g_dim]; //where d=0,1,2 corresponds to x,y,z (if g_dim==3)
double dot123 = DotProduct(vb12, vb23);
double dot234 = DotProduct(vb23, vb34);
double L23sqr = DotProduct(vb23, vb23);
double L23 = sqrt(L23sqr); // (central bond length)
double inv_L23sqr = 0.0;
double inv_L23 = 0.0;
if (L23sqr != 0.0) {
inv_L23sqr = 1.0 / L23sqr;
inv_L23 = 1.0 / L23;
}
double neg_inv_L23 = -inv_L23;
double dot123_over_L23sqr = dot123 * inv_L23sqr;
double dot234_over_L23sqr = dot234 * inv_L23sqr;
for (int d=0; d < g_dim; ++d) {
// See figure above for a visual definitions of these vectors:
proj12on23[d] = vb23[d] * dot123_over_L23sqr;
proj34on23[d] = vb23[d] * dot234_over_L23sqr;
perp12on23[d] = vb12[d] - proj12on23[d];
perp34on23[d] = vb34[d] - proj34on23[d];
}
// --- Compute the gradient vectors dphi/dx1 and dphi/dx4: ---
// These two gradients point in the direction of n123 and n234,
// and are scaled by the distances of atoms 1 and 4 from the central axis.
// Distance of atom 1 to central axis:
double perp12on23_len = sqrt(DotProduct(perp12on23, perp12on23));
// Distance of atom 4 to central axis:
double perp34on23_len = sqrt(DotProduct(perp34on23, perp34on23));
double inv_perp12on23 = 0.0;
if (perp12on23_len != 0.0) inv_perp12on23 = 1.0 / perp12on23_len;
double inv_perp34on23 = 0.0;
if (perp34on23_len != 0.0) inv_perp34on23 = 1.0 / perp34on23_len;
for (int d=0; d < g_dim; ++d) {
dphi_dx1[d] = n123[d] * inv_perp12on23;
dphi_dx4[d] = n234[d] * inv_perp34on23;
}
// --- Compute the gradient vectors dphi/dx2 and dphi/dx3: ---
//
// This is more tricky because atoms 2 and 3 are shared by both planes
// 123 and 234 (the angle between which defines "phi"). Moving either
// one of these atoms effects both the 123 and 234 planes
// Both the 123 and 234 planes intersect with the plane perpendicular to the
// central bond axis (vb23). The two lines where these intersections occur
// will shift when you move either atom 2 or atom 3. The angle between
// these lines is the dihedral angle, phi. We can define four quantities:
// dphi123_dx2 is the change in "phi" due to the movement of the 123 plane
// ...as a result of moving atom 2.
// dphi234_dx2 is the change in "phi" due to the movement of the 234 plane
// ...as a result of moving atom 2.
// dphi123_dx3 is the change in "phi" due to the movement of the 123 plane
// ...as a result of moving atom 3.
// dphi234_dx3 is the change in "phi" due to the movement of the 234 plane
// ...as a result of moving atom 3.
double proj12on23_len = dot123 * inv_L23;
double proj34on23_len = dot234 * inv_L23;
// Interpretation:
//The magnitude of "proj12on23_len" is the length of the proj12on23 vector.
//The sign is positive if it points in the same direction as the central
//bond (vb23). Otherwise it is negative. The same goes for "proj34on23".
//(In the example figure in the comment above, both variables are positive.)
// The forumula used in the 8 lines below explained here:
// "supporting_information/doc/gradient_formula_explanation/"
double dphi123_dx2_coef = neg_inv_L23 * (L23 + proj12on23_len);
double dphi234_dx2_coef = inv_L23 * proj34on23_len;
double dphi234_dx3_coef = neg_inv_L23 * (L23 + proj34on23_len);
double dphi123_dx3_coef = inv_L23 * proj12on23_len;
for (int d=0; d < g_dim; ++d) {
// Recall that the n123 and n234 plane normal vectors are proportional to
// the dphi/dx1 and dphi/dx2 gradients vectors
// It turns out we can save slightly more CPU cycles by expressing
// dphi/dx2 and dphi/dx3 as linear combinations of dphi/dx1 and dphi/dx2
// which we computed already (instead of n123 & n234).
dphi_dx2[d] = dphi123_dx2_coef*dphi_dx1[d] + dphi234_dx2_coef*dphi_dx4[d];
dphi_dx3[d] = dphi123_dx3_coef*dphi_dx1[d] + dphi234_dx3_coef*dphi_dx4[d];
}
#ifdef DIH_DEBUG_NUM
// ----- Numerical test? -----
cerr << " -- testing gradient for dihedral (n="<<n<<") for atoms ("
<< i1 << "," << i2 << "," << i3 << "," << i4 << ") --" << endl;
PrintGradientComparison(*this, dphi_dx1, dphi_dx2, dphi_dx3, dphi_dx4,
domain, x[i1], x[i2], x[i3], x[i4]);
for (int d=0; d < g_dim; ++d) {
// The sum of all the gradients should be near 0. (translational symmetry)
cerr <<"sum_gradients["<<d<<"]="<<dphi_dx1[d]<<"+"<<dphi_dx2[d]<<"+"<<dphi_dx3[d]<<"+"<<dphi_dx4[d]<<"="<<dphi_dx1[d]+dphi_dx2[d]+dphi_dx3[d]+dphi_dx4[d]<<endl;
// These should sum to zero
assert(abs(dphi_dx1[d]+dphi_dx2[d]+dphi_dx3[d]+dphi_dx4[d]) < 0.0002/L23);
}
#endif // #ifdef DIH_DEBUG_NUM
// ----- Step 3: Calculate the energy and force in the phi direction -----
// tabulated force & energy
double u, m_du_dphi; //u = energy. m_du_dphi = "minus" du/dphi
assert((0.0 <= phi) && (phi <= TWOPI));
uf_lookup(type, phi, u, m_du_dphi);
if (EFLAG) edihedral = u;
// ----- Step 4: Calculate the force direction in real space -----
// chain rule:
// d U d U d phi
// -f = ----- = ----- * -----
// d x d phi d x
for(int d=0; d < g_dim; ++d) {
f1[d] = m_du_dphi * dphi_dx1[d];
f2[d] = m_du_dphi * dphi_dx2[d];
f3[d] = m_du_dphi * dphi_dx3[d];
f4[d] = m_du_dphi * dphi_dx4[d];
}
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,edihedral,f1,f3,f4,
vb12[0],vb12[1],vb12[2],vb23[0],vb23[1],vb23[2],vb34[0],
vb34[1],vb34[2],thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef DIHEDRAL_CLASS
DihedralStyle(table/omp,DihedralTableOMP)
#else
#ifndef LMP_DIHEDRAL_TABLE_OMP_H
#define LMP_DIHEDRAL_TABLE_OMP_H
#include "dihedral_table.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class DihedralTableOMP : public DihedralTable, public ThrOMP {
public:
DihedralTableOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,415 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing authors: Roy Pollock (LLNL), Paul Crozier (SNL)
------------------------------------------------------------------------- */
#include "mpi.h"
#include "ewald_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "memory.h"
#include <math.h>
#include "math_const.h"
#include "suffix.h"
using namespace LAMMPS_NS;
using namespace MathConst;
#define SMALL 0.00001
/* ---------------------------------------------------------------------- */
EwaldOMP::EwaldOMP(LAMMPS *lmp, int narg, char **arg)
: Ewald(lmp, narg, arg), ThrOMP(lmp, THR_KSPACE)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void EwaldOMP::allocate()
{
Ewald::allocate();
// always re-allocate for simplicity.
delete[] sfacrl;
delete[] sfacim;
sfacrl = new double[kmax3d*comm->nthreads];
sfacim = new double[kmax3d*comm->nthreads];
}
/* ----------------------------------------------------------------------
compute the Ewald long-range force, energy, virial
------------------------------------------------------------------------- */
void EwaldOMP::compute(int eflag, int vflag)
{
// set energy/virial flags
if (eflag || vflag) ev_setup(eflag,vflag);
else evflag = evflag_atom = eflag_global = vflag_global =
eflag_atom = vflag_atom = 0;
// extend size of per-atom arrays if necessary
if (atom->nlocal > nmax) {
memory->destroy(ek);
memory->destroy3d_offset(cs,-kmax_created);
memory->destroy3d_offset(sn,-kmax_created);
nmax = atom->nmax;
memory->create(ek,nmax,3,"ewald:ek");
memory->create3d_offset(cs,-kmax,kmax,3,nmax,"ewald:cs");
memory->create3d_offset(sn,-kmax,kmax,3,nmax,"ewald:sn");
kmax_created = kmax;
}
// partial structure factors on each processor
// total structure factor by summing over procs
eik_dot_r();
MPI_Allreduce(sfacrl,sfacrl_all,kcount,MPI_DOUBLE,MPI_SUM,world);
MPI_Allreduce(sfacim,sfacim_all,kcount,MPI_DOUBLE,MPI_SUM,world);
// K-space portion of electric field
// double loop over K-vectors and local atoms
double * const * const f = atom->f;
const double * const q = atom->q;
const int nthreads = comm->nthreads;
const int nlocal = atom->nlocal;
const double qscale = force->qqrd2e * scale;
double eng_tmp = 0.0;
double v0,v1,v2,v3,v4,v5;
v0=v1=v2=v3=v4=v5=0.0;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag) reduction(+:eng_tmp,v0,v1,v2,v3,v4,v5)
#endif
{
int i,j,k,ifrom,ito,tid;
int kx,ky,kz;
double cypz,sypz,exprl,expim,partial;
loop_setup_thr(ifrom, ito, tid, nlocal, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, 0, NULL, NULL, thr);
for (i = ifrom; i < ito; i++) {
ek[i][0] = 0.0;
ek[i][1] = 0.0;
ek[i][2] = 0.0;
}
for (k = 0; k < kcount; k++) {
kx = kxvecs[k];
ky = kyvecs[k];
kz = kzvecs[k];
for (i = ifrom; i < ito; i++) {
cypz = cs[ky][1][i]*cs[kz][2][i] - sn[ky][1][i]*sn[kz][2][i];
sypz = sn[ky][1][i]*cs[kz][2][i] + cs[ky][1][i]*sn[kz][2][i];
exprl = cs[kx][0][i]*cypz - sn[kx][0][i]*sypz;
expim = sn[kx][0][i]*cypz + cs[kx][0][i]*sypz;
partial = expim*sfacrl_all[k] - exprl*sfacim_all[k];
ek[i][0] += partial*eg[k][0];
ek[i][1] += partial*eg[k][1];
ek[i][2] += partial*eg[k][2];
if (evflag_atom) {
const double partial_peratom = exprl*sfacrl_all[k] + expim*sfacim_all[k];
if (eflag_atom) eatom[i] += q[i]*ug[k]*partial_peratom;
if (vflag_atom)
for (j = 0; j < 6; j++)
vatom[i][j] += ug[k]*vg[k][j]*partial_peratom;
}
}
}
// convert E-field to force
for (i = ifrom; i < ito; i++) {
const double fac = qscale*q[i];
f[i][0] += fac*ek[i][0];
f[i][1] += fac*ek[i][1];
f[i][2] += fac*ek[i][2];
}
// global energy
if (eflag_global) {
#if defined(_OPENMP)
#pragma omp for private(k)
#endif
for (k = 0; k < kcount; k++)
eng_tmp += ug[k] * (sfacrl_all[k]*sfacrl_all[k] +
sfacim_all[k]*sfacim_all[k]);
}
// global virial
if (vflag_global) {
#if defined(_OPENMP)
#pragma omp for private(k)
#endif
for (k = 0; k < kcount; k++) {
double uk = ug[k] * (sfacrl_all[k]*sfacrl_all[k] + sfacim_all[k]*sfacim_all[k]);
v0 += uk*vg[k][0];
v1 += uk*vg[k][1];
v2 += uk*vg[k][2];
v3 += uk*vg[k][3];
v4 += uk*vg[k][4];
v5 += uk*vg[k][5];
}
}
// per-atom energy/virial
// energy includes self-energy correction
if (evflag_atom) {
if (eflag_atom) {
for (i = ifrom; i < ito; i++) {
eatom[i] -= g_ewald*q[i]*q[i]/MY_PIS + MY_PI2*q[i]*qsum /
(g_ewald*g_ewald*volume);
eatom[i] *= qscale;
}
}
if (vflag_atom)
for (i = ifrom; i < ito; i++)
for (j = 0; j < 6; j++) vatom[i][j] *= q[i]*qscale;
}
reduce_thr(this, eflag,vflag,thr);
} // end of omp parallel region
if (eflag_global) {
eng_tmp -= g_ewald*qsqsum/MY_PIS +
MY_PI2*qsum*qsum / (g_ewald*g_ewald*volume);
energy = eng_tmp * qscale;
}
if (vflag_global) {
virial[0] = v0 * qscale;
virial[1] = v1 * qscale;
virial[2] = v2 * qscale;
virial[3] = v3 * qscale;
virial[4] = v4 * qscale;
virial[5] = v5 * qscale;
}
if (slabflag) slabcorr();
}
/* ---------------------------------------------------------------------- */
void EwaldOMP::eik_dot_r()
{
const double * const * const x = atom->x;
const double * const q = atom->q;
const int nlocal = atom->nlocal;
const int nthreads = comm->nthreads;
#if defined(_OPENMP)
#pragma omp parallel default(none)
#endif
{
int i,ifrom,ito,k,l,m,n,ic,tid;
double cstr1,sstr1,cstr2,sstr2,cstr3,sstr3,cstr4,sstr4;
double sqk,clpm,slpm;
loop_setup_thr(ifrom, ito, tid, nlocal, nthreads);
double * const sfacrl_thr = sfacrl + tid*kmax3d;
double * const sfacim_thr = sfacim + tid*kmax3d;
n = 0;
// (k,0,0), (0,l,0), (0,0,m)
for (ic = 0; ic < 3; ic++) {
sqk = unitk[ic]*unitk[ic];
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
for (i = ifrom; i < ito; i++) {
cs[0][ic][i] = 1.0;
sn[0][ic][i] = 0.0;
cs[1][ic][i] = cos(unitk[ic]*x[i][ic]);
sn[1][ic][i] = sin(unitk[ic]*x[i][ic]);
cs[-1][ic][i] = cs[1][ic][i];
sn[-1][ic][i] = -sn[1][ic][i];
cstr1 += q[i]*cs[1][ic][i];
sstr1 += q[i]*sn[1][ic][i];
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
}
}
for (m = 2; m <= kmax; m++) {
for (ic = 0; ic < 3; ic++) {
sqk = m*unitk[ic] * m*unitk[ic];
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
for (i = ifrom; i < ito; i++) {
cs[m][ic][i] = cs[m-1][ic][i]*cs[1][ic][i] -
sn[m-1][ic][i]*sn[1][ic][i];
sn[m][ic][i] = sn[m-1][ic][i]*cs[1][ic][i] +
cs[m-1][ic][i]*sn[1][ic][i];
cs[-m][ic][i] = cs[m][ic][i];
sn[-m][ic][i] = -sn[m][ic][i];
cstr1 += q[i]*cs[m][ic][i];
sstr1 += q[i]*sn[m][ic][i];
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
}
}
}
// 1 = (k,l,0), 2 = (k,-l,0)
for (k = 1; k <= kxmax; k++) {
for (l = 1; l <= kymax; l++) {
sqk = (k*unitk[0] * k*unitk[0]) + (l*unitk[1] * l*unitk[1]);
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
cstr2 = 0.0;
sstr2 = 0.0;
for (i = ifrom; i < ito; i++) {
cstr1 += q[i]*(cs[k][0][i]*cs[l][1][i] - sn[k][0][i]*sn[l][1][i]);
sstr1 += q[i]*(sn[k][0][i]*cs[l][1][i] + cs[k][0][i]*sn[l][1][i]);
cstr2 += q[i]*(cs[k][0][i]*cs[l][1][i] + sn[k][0][i]*sn[l][1][i]);
sstr2 += q[i]*(sn[k][0][i]*cs[l][1][i] - cs[k][0][i]*sn[l][1][i]);
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
sfacrl_thr[n] = cstr2;
sfacim_thr[n++] = sstr2;
}
}
}
// 1 = (0,l,m), 2 = (0,l,-m)
for (l = 1; l <= kymax; l++) {
for (m = 1; m <= kzmax; m++) {
sqk = (l*unitk[1] * l*unitk[1]) + (m*unitk[2] * m*unitk[2]);
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
cstr2 = 0.0;
sstr2 = 0.0;
for (i = ifrom; i < ito; i++) {
cstr1 += q[i]*(cs[l][1][i]*cs[m][2][i] - sn[l][1][i]*sn[m][2][i]);
sstr1 += q[i]*(sn[l][1][i]*cs[m][2][i] + cs[l][1][i]*sn[m][2][i]);
cstr2 += q[i]*(cs[l][1][i]*cs[m][2][i] + sn[l][1][i]*sn[m][2][i]);
sstr2 += q[i]*(sn[l][1][i]*cs[m][2][i] - cs[l][1][i]*sn[m][2][i]);
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
sfacrl_thr[n] = cstr2;
sfacim_thr[n++] = sstr2;
}
}
}
// 1 = (k,0,m), 2 = (k,0,-m)
for (k = 1; k <= kxmax; k++) {
for (m = 1; m <= kzmax; m++) {
sqk = (k*unitk[0] * k*unitk[0]) + (m*unitk[2] * m*unitk[2]);
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
cstr2 = 0.0;
sstr2 = 0.0;
for (i = ifrom; i < ito; i++) {
cstr1 += q[i]*(cs[k][0][i]*cs[m][2][i] - sn[k][0][i]*sn[m][2][i]);
sstr1 += q[i]*(sn[k][0][i]*cs[m][2][i] + cs[k][0][i]*sn[m][2][i]);
cstr2 += q[i]*(cs[k][0][i]*cs[m][2][i] + sn[k][0][i]*sn[m][2][i]);
sstr2 += q[i]*(sn[k][0][i]*cs[m][2][i] - cs[k][0][i]*sn[m][2][i]);
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
sfacrl_thr[n] = cstr2;
sfacim_thr[n++] = sstr2;
}
}
}
// 1 = (k,l,m), 2 = (k,-l,m), 3 = (k,l,-m), 4 = (k,-l,-m)
for (k = 1; k <= kxmax; k++) {
for (l = 1; l <= kymax; l++) {
for (m = 1; m <= kzmax; m++) {
sqk = (k*unitk[0] * k*unitk[0]) + (l*unitk[1] * l*unitk[1]) +
(m*unitk[2] * m*unitk[2]);
if (sqk <= gsqmx) {
cstr1 = 0.0;
sstr1 = 0.0;
cstr2 = 0.0;
sstr2 = 0.0;
cstr3 = 0.0;
sstr3 = 0.0;
cstr4 = 0.0;
sstr4 = 0.0;
for (i = ifrom; i < ito; i++) {
clpm = cs[l][1][i]*cs[m][2][i] - sn[l][1][i]*sn[m][2][i];
slpm = sn[l][1][i]*cs[m][2][i] + cs[l][1][i]*sn[m][2][i];
cstr1 += q[i]*(cs[k][0][i]*clpm - sn[k][0][i]*slpm);
sstr1 += q[i]*(sn[k][0][i]*clpm + cs[k][0][i]*slpm);
clpm = cs[l][1][i]*cs[m][2][i] + sn[l][1][i]*sn[m][2][i];
slpm = -sn[l][1][i]*cs[m][2][i] + cs[l][1][i]*sn[m][2][i];
cstr2 += q[i]*(cs[k][0][i]*clpm - sn[k][0][i]*slpm);
sstr2 += q[i]*(sn[k][0][i]*clpm + cs[k][0][i]*slpm);
clpm = cs[l][1][i]*cs[m][2][i] + sn[l][1][i]*sn[m][2][i];
slpm = sn[l][1][i]*cs[m][2][i] - cs[l][1][i]*sn[m][2][i];
cstr3 += q[i]*(cs[k][0][i]*clpm - sn[k][0][i]*slpm);
sstr3 += q[i]*(sn[k][0][i]*clpm + cs[k][0][i]*slpm);
clpm = cs[l][1][i]*cs[m][2][i] - sn[l][1][i]*sn[m][2][i];
slpm = -sn[l][1][i]*cs[m][2][i] - cs[l][1][i]*sn[m][2][i];
cstr4 += q[i]*(cs[k][0][i]*clpm - sn[k][0][i]*slpm);
sstr4 += q[i]*(sn[k][0][i]*clpm + cs[k][0][i]*slpm);
}
sfacrl_thr[n] = cstr1;
sfacim_thr[n++] = sstr1;
sfacrl_thr[n] = cstr2;
sfacim_thr[n++] = sstr2;
sfacrl_thr[n] = cstr3;
sfacim_thr[n++] = sstr3;
sfacrl_thr[n] = cstr4;
sfacim_thr[n++] = sstr4;
}
}
}
}
sync_threads();
data_reduce_thr(sfacrl,kmax3d,nthreads,1,tid);
data_reduce_thr(sfacim,kmax3d,nthreads,1,tid);
} // end of parallel region
}

View File

@ -1,42 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef KSPACE_CLASS
KSpaceStyle(ewald/omp,EwaldOMP)
#else
#ifndef LMP_EWALD_OMP_H
#define LMP_EWALD_OMP_H
#include "ewald.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class EwaldOMP : public Ewald, public ThrOMP {
public:
EwaldOMP(class LAMMPS *, int, char **);
virtual ~EwaldOMP() { };
virtual void allocate();
virtual void compute(int, int);
protected:
virtual void eik_dot_r();
};
}
#endif
#endif

View File

@ -1,112 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "stdio.h"
#include "stdlib.h"
#include "string.h"
#include "fix_gravity_omp.h"
#include "atom.h"
#include "update.h"
#include "domain.h"
#include "input.h"
#include "modify.h"
#include "respa.h"
#include "variable.h"
#include "error.h"
using namespace LAMMPS_NS;
using namespace FixConst;
enum{CHUTE,SPHERICAL,GRADIENT,VECTOR};
enum{CONSTANT,EQUAL};
/* ---------------------------------------------------------------------- */
FixGravityOMP::FixGravityOMP(LAMMPS *lmp, int narg, char **arg) :
FixGravity(lmp, narg, arg) { }
/* ---------------------------------------------------------------------- */
void FixGravityOMP::post_force(int vflag)
{
// update gravity due to variables
if (varflag != CONSTANT) {
modify->clearstep_compute();
if (mstyle == EQUAL) magnitude = input->variable->compute_equal(mvar);
if (vstyle == EQUAL) magnitude = input->variable->compute_equal(vvar);
if (pstyle == EQUAL) magnitude = input->variable->compute_equal(pvar);
if (tstyle == EQUAL) magnitude = input->variable->compute_equal(tvar);
if (xstyle == EQUAL) magnitude = input->variable->compute_equal(xvar);
if (ystyle == EQUAL) magnitude = input->variable->compute_equal(yvar);
if (zstyle == EQUAL) magnitude = input->variable->compute_equal(zvar);
modify->addstep_compute(update->ntimestep + 1);
set_acceleration();
}
const double * const * const x = atom->x;
double * const * const f = atom->f;
double * const rmass = atom->rmass;
double * const mass = atom->mass;
int * const mask = atom->mask;
int * const type = atom->type;
const int nlocal = atom->nlocal;
const double xacc_thr = xacc;
const double yacc_thr = yacc;
const double zacc_thr = zacc;
double massone;
int i;
eflag = 0;
double grav = 0.0;
if (rmass) {
#if defined(_OPENMP)
#pragma omp parallel for private(i,massone) default(none) reduction(-:grav)
#endif
for (i = 0; i < nlocal; i++)
if (mask[i] & groupbit) {
massone = rmass[i];
f[i][0] += massone*xacc_thr;
f[i][1] += massone*yacc_thr;
f[i][2] += massone*zacc_thr;
grav -= massone * (xacc_thr*x[i][0] + yacc_thr*x[i][1] + zacc_thr*x[i][2]);
}
} else {
#if defined(_OPENMP)
#pragma omp parallel for private(i,massone) default(none) reduction(-:grav)
#endif
for (i = 0; i < nlocal; i++)
if (mask[i] & groupbit) {
massone = mass[type[i]];
f[i][0] += massone*xacc_thr;
f[i][1] += massone*yacc_thr;
f[i][2] += massone*zacc_thr;
grav -= massone * (xacc_thr*x[i][0] + yacc_thr*x[i][1] + zacc_thr*x[i][2]);
}
}
egrav = grav;
}
/* ---------------------------------------------------------------------- */
void FixGravityOMP::post_force_respa(int vflag, int ilevel, int iloop)
{
if (ilevel == nlevels_respa-1) post_force(vflag);
}

View File

@ -1,38 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(gravity/omp,FixGravityOMP)
#else
#ifndef LMP_FIX_GRAVITY_OMP_H
#define LMP_FIX_GRAVITY_OMP_H
#include "fix_gravity.h"
namespace LAMMPS_NS {
class FixGravityOMP : public FixGravity {
public:
FixGravityOMP(class LAMMPS *, int, char **);
virtual void post_force(int);
virtual void post_force_respa(int, int, int);
};
}
#endif
#endif

View File

@ -1,137 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "math.h"
#include "stdio.h"
#include "string.h"
#include "fix_nve_sphere_omp.h"
#include "atom.h"
#include "atom_vec.h"
#include "update.h"
#include "respa.h"
#include "force.h"
#include "error.h"
using namespace LAMMPS_NS;
using namespace FixConst;
#define INERTIA 0.4 // moment of inertia prefactor for sphere
enum{NONE,DIPOLE};
/* ---------------------------------------------------------------------- */
/* ---------------------------------------------------------------------- */
void FixNVESphereOMP::initial_integrate(int vflag)
{
double * const * const x = atom->x;
double * const * const v = atom->v;
const double * const * const f = atom->f;
double * const * const omega = atom->omega;
const double * const * const torque = atom->torque;
const double * const radius = atom->radius;
const double * const rmass = atom->rmass;
const int * const mask = atom->mask;
const int nlocal = (igroup == atom->firstgroup) ? atom->nfirst : atom->nlocal;
int i;
// set timestep here since dt may have changed or come via rRESPA
const double dtfrotate = dtf / INERTIA;
// update v,x,omega for all particles
// d_omega/dt = torque / inertia
#if defined(_OPENMP)
#pragma omp parallel for private(i) default(none)
#endif
for (i = 0; i < nlocal; i++) {
if (mask[i] & groupbit) {
const double dtfm = dtf / rmass[i];
v[i][0] += dtfm * f[i][0];
v[i][1] += dtfm * f[i][1];
v[i][2] += dtfm * f[i][2];
x[i][0] += dtv * v[i][0];
x[i][1] += dtv * v[i][1];
x[i][2] += dtv * v[i][2];
const double dtirotate = dtfrotate / (radius[i]*radius[i]*rmass[i]);
omega[i][0] += dtirotate * torque[i][0];
omega[i][1] += dtirotate * torque[i][1];
omega[i][2] += dtirotate * torque[i][2];
}
}
// update mu for dipoles
// d_mu/dt = omega cross mu
// renormalize mu to dipole length
if (extra == DIPOLE) {
double * const * const mu = atom->mu;
#if defined(_OPENMP)
#pragma omp parallel for private(i) default(none)
#endif
for (i = 0; i < nlocal; i++) {
double g0,g1,g2,msq,scale;
if (mask[i] & groupbit) {
if (mu[i][3] > 0.0) {
g0 = mu[i][0] + dtv * (omega[i][1]*mu[i][2]-omega[i][2]*mu[i][1]);
g1 = mu[i][1] + dtv * (omega[i][2]*mu[i][0]-omega[i][0]*mu[i][2]);
g2 = mu[i][2] + dtv * (omega[i][0]*mu[i][1]-omega[i][1]*mu[i][0]);
msq = g0*g0 + g1*g1 + g2*g2;
scale = mu[i][3]/sqrt(msq);
mu[i][0] = g0*scale;
mu[i][1] = g1*scale;
mu[i][2] = g2*scale;
}
}
}
}
}
/* ---------------------------------------------------------------------- */
void FixNVESphereOMP::final_integrate()
{
double * const * const v = atom->v;
const double * const * const f = atom->f;
double * const * const omega = atom->omega;
const double * const * const torque = atom->torque;
const double * const rmass = atom->rmass;
const double * const radius = atom->radius;
const int * const mask = atom->mask;
const int nlocal = (igroup == atom->firstgroup) ? atom->nfirst : atom->nlocal;
int i;
// set timestep here since dt may have changed or come via rRESPA
const double dtfrotate = dtf / INERTIA;
// update v,omega for all particles
// d_omega/dt = torque / inertia
#if defined(_OPENMP)
#pragma omp parallel for private(i) default(none)
#endif
for (i = 0; i < nlocal; i++)
if (mask[i] & groupbit) {
const double dtfm = dtf / rmass[i];
v[i][0] += dtfm * f[i][0];
v[i][1] += dtfm * f[i][1];
v[i][2] += dtfm * f[i][2];
const double dtirotate = dtfrotate / (radius[i]*radius[i]*rmass[i]);
omega[i][0] += dtirotate * torque[i][0];
omega[i][1] += dtirotate * torque[i][1];
omega[i][2] += dtirotate * torque[i][2];
}
}

View File

@ -1,39 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(nve/sphere/omp,FixNVESphereOMP)
#else
#ifndef LMP_FIX_NVE_SPHERE_OMP_H
#define LMP_FIX_NVE_SPHERE_OMP_H
#include "fix_nve_sphere.h"
namespace LAMMPS_NS {
class FixNVESphereOMP : public FixNVESphere {
public:
FixNVESphereOMP(class LAMMPS *lmp, int narg, char **arg) :
FixNVESphere(lmp, narg, arg) {};
virtual void initial_integrate(int);
virtual void final_integrate();
};
}
#endif
#endif

View File

@ -1,330 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
OpenMP based threading support for LAMMPS
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "atom.h"
#include "comm.h"
#include "error.h"
#include "force.h"
#include "neighbor.h"
#include "neigh_request.h"
#include "update.h"
#include "integrate.h"
#include "min.h"
#include "fix_omp.h"
#include "thr_data.h"
#include "thr_omp.h"
#include "pair_hybrid.h"
#include "bond_hybrid.h"
#include "angle_hybrid.h"
#include "dihedral_hybrid.h"
#include "improper_hybrid.h"
#include "kspace.h"
#include <string.h>
#include <stdlib.h>
#include <stdio.h>
#include "suffix.h"
#if defined(LMP_USER_CUDA)
#include "cuda_modify_flags.h"
#endif
using namespace LAMMPS_NS;
using namespace FixConst;
#if defined(LMP_USER_CUDA)
using namespace FixConstCuda;
#endif
static int get_tid()
{
int tid = 0;
#if defined(_OPENMP)
tid = omp_get_thread_num();
#endif
return tid;
}
/* ---------------------------------------------------------------------- */
FixOMP::FixOMP(LAMMPS *lmp, int narg, char **arg) : Fix(lmp, narg, arg),
thr(NULL), last_omp_style(NULL), last_pair_hybrid(NULL),
_nthr(-1), _neighbor(true), _newton(false)
{
if ((narg < 4) || (narg > 6)) error->all(FLERR,"Illegal fix OMP command");
if (strcmp(arg[1],"all") != 0) error->all(FLERR,"Illegal fix OMP command");
int nthreads = 1;
if (narg > 3) {
#if defined(_OPENMP)
if (strcmp(arg[3],"*") == 0)
#pragma omp parallel default(none) shared(nthreads)
nthreads = omp_get_num_threads();
else
nthreads = atoi(arg[3]);
#endif
}
if (nthreads < 1)
error->all(FLERR,"Illegal number of threads requested.");
if (nthreads != comm->nthreads) {
#if defined(_OPENMP)
omp_set_num_threads(nthreads);
#endif
comm->nthreads = nthreads;
if (comm->me == 0) {
if (screen)
fprintf(screen," reset %d OpenMP thread(s) per MPI task\n", nthreads);
if (logfile)
fprintf(logfile," reset %d OpenMP thread(s) per MPI task\n", nthreads);
}
}
if (narg > 4) {
if (strcmp(arg[4],"force/neigh") == 0)
_neighbor = true;
else if (strcmp(arg[4],"force") == 0)
_neighbor = false;
else
error->all(FLERR,"Illegal fix omp mode requested.");
if (comm->me == 0) {
const char * const mode = _neighbor ? "OpenMP capable" : "serial";
if (screen)
fprintf(screen," using %s neighbor list subroutines\n", mode);
if (logfile)
fprintf(logfile," using %s neighbor list subroutines\n", mode);
}
}
#if 0 /* to be enabled when we can switch between half and full neighbor lists */
if (narg > 5) {
if (strcmp(arg[5],"neigh/half") == 0)
_newton = true;
else if (strcmp(arg[5],"neigh/full") == 0)
_newton = false;
else
error->all(FLERR,"Illegal fix OMP command");
if (comm->me == 0) {
const char * const mode = _newton ? "half" : "full";
if (screen)
fprintf(screen," using /omp styles with %s neighbor list builds\n", mode);
if (logfile)
fprintf(logfile," using /omp styles with %s neighbor list builds\n", mode);
}
}
#endif
// allocate list for per thread accumulator manager class instances
// and then have each thread create an instance of this class to
// encourage the OS to use storage that is "close" to each thread's CPU.
thr = new ThrData *[nthreads];
_nthr = nthreads;
#if defined(_OPENMP)
#pragma omp parallel default(none)
#endif
{
const int tid = get_tid();
thr[tid] = new ThrData(tid);
}
}
/* ---------------------------------------------------------------------- */
FixOMP::~FixOMP()
{
#if defined(_OPENMP)
#pragma omp parallel default(none)
#endif
{
const int tid = get_tid();
delete thr[tid];
}
delete[] thr;
}
/* ---------------------------------------------------------------------- */
int FixOMP::setmask()
{
// compatibility with USER-CUDA
// our fix doesn't need any data transfer.
#if defined(LMP_USER_CUDA)
if (lmp->cuda) {
int mask = 0;
mask |= PRE_FORCE_CUDA;
mask |= PRE_FORCE_RESPA;
mask |= MIN_PRE_FORCE;
return mask;
}
#endif
int mask = 0;
mask |= PRE_FORCE;
mask |= PRE_FORCE_RESPA;
mask |= MIN_PRE_FORCE;
return mask;
}
/* ---------------------------------------------------------------------- */
void FixOMP::init()
{
if (strstr(update->integrate_style,"respa") != NULL)
error->all(FLERR,"Cannot use r-RESPA with /omp styles");
int check_hybrid;
last_pair_hybrid = NULL;
last_omp_style = NULL;
const char *last_omp_name = NULL;
const char *last_hybrid_name = NULL;
const char *last_force_name = NULL;
// determine which is the last force style with OpenMP
// support as this is the one that has to reduce the forces
#define CheckStyleForOMP(name) \
check_hybrid = 0; \
if (force->name) { \
if ( (strcmp(force->name ## _style,"hybrid") == 0) || \
(strcmp(force->name ## _style,"hybrid/overlay") == 0) ) \
check_hybrid=1; \
if (force->name->suffix_flag & Suffix::OMP) { \
last_force_name = (const char *) #name; \
last_omp_name = force->name ## _style; \
last_omp_style = (void *) force->name; \
} \
}
#define CheckHybridForOMP(name,Class) \
if (check_hybrid) { \
Class ## Hybrid *style = (Class ## Hybrid *) force->name; \
for (int i=0; i < style->nstyles; i++) { \
if (style->styles[i]->suffix_flag & Suffix::OMP) { \
last_force_name = (const char *) #name; \
last_omp_name = style->keywords[i]; \
last_omp_style = style->styles[i]; \
} \
} \
}
CheckStyleForOMP(pair);
CheckHybridForOMP(pair,Pair);
if (check_hybrid) {
last_pair_hybrid = last_omp_style;
last_hybrid_name = last_omp_name;
}
CheckStyleForOMP(bond);
CheckHybridForOMP(bond,Bond);
CheckStyleForOMP(angle);
CheckHybridForOMP(angle,Angle);
CheckStyleForOMP(dihedral);
CheckHybridForOMP(dihedral,Dihedral);
CheckStyleForOMP(improper);
CheckHybridForOMP(improper,Improper);
CheckStyleForOMP(kspace);
#undef CheckStyleForOMP
#undef CheckHybridForOMP
set_neighbor_omp();
// diagnostic output
if (comm->me == 0) {
if (last_omp_style) {
if (last_pair_hybrid) {
if (screen)
fprintf(screen,"Hybrid pair style last /omp style %s\n", last_hybrid_name);
if (logfile)
fprintf(logfile,"Hybrid pair style last /omp style %s\n", last_hybrid_name);
}
if (screen)
fprintf(screen,"Last active /omp style is %s_style %s\n",
last_force_name, last_omp_name);
if (logfile)
fprintf(logfile,"Last active /omp style is %s_style %s\n",
last_force_name, last_omp_name);
} else {
if (screen)
fprintf(screen,"No /omp style for force computation currently active\n");
if (logfile)
fprintf(screen,"No /omp style for force computation currently active\n");
}
}
}
/* ---------------------------------------------------------------------- */
void FixOMP::set_neighbor_omp()
{
// select or deselect multi-threaded neighbor
// list build depending on setting in package omp.
// NOTE: since we are at the top of the list of
// fixes, we cannot adjust neighbor lists from
// other fixes. those have to be re-implemented
// as /omp fix styles. :-(
const int neigh_omp = _neighbor ? 1 : 0;
const int nrequest = neighbor->nrequest;
for (int i = 0; i < nrequest; ++i)
neighbor->requests[i]->omp = neigh_omp;
}
/* ---------------------------------------------------------------------- */
// adjust size and clear out per thread accumulator arrays
void FixOMP::pre_force(int)
{
const int nall = atom->nlocal + atom->nghost;
double **f = atom->f;
double **torque = atom->torque;
double *erforce = atom->erforce;
double *de = atom->de;
double *drho = atom->drho;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(f,torque,erforce,de,drho)
#endif
{
const int tid = get_tid();
thr[tid]->check_tid(tid);
thr[tid]->init_force(nall,f,torque,erforce,de,drho);
}
}
/* ---------------------------------------------------------------------- */
double FixOMP::memory_usage()
{
double bytes = comm->nthreads * (sizeof(ThrData *) + sizeof(ThrData));
bytes += comm->nthreads * thr[0]->memory_usage();
return bytes;
}

View File

@ -1,73 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(OMP,FixOMP)
#else
#ifndef LMP_FIX_OMP_H
#define LMP_FIX_OMP_H
#include "fix.h"
namespace LAMMPS_NS {
class ThrData;
class FixOMP : public Fix {
friend class ThrOMP;
public:
FixOMP(class LAMMPS *, int, char **);
virtual ~FixOMP();
virtual int setmask();
virtual void init();
virtual void pre_force(int);
virtual void setup_pre_force(int vflag) { pre_force(vflag); };
virtual void min_setup_pre_force(int vflag) { pre_force(vflag); };
virtual void min_pre_force(int vflag) { pre_force(vflag); };
virtual void setup_pre_force_respa(int vflag,int) { pre_force(vflag); };
virtual void pre_force_respa(int vflag,int,int) { pre_force(vflag); };
virtual double memory_usage();
ThrData *get_thr(int tid) { return thr[tid]; };
int get_nthr() const { return _nthr; }
protected:
ThrData **thr;
void *last_omp_style; // pointer to the style that needs
// to do the general force reduction
void *last_pair_hybrid; // pointer to the pair style that needs
// to call virial_fdot_compute()
public:
bool get_neighbor() const {return _neighbor;};
bool get_newton() const {return _newton;};
private:
int _nthr; // number of currently active ThrData object
bool _neighbor; // en/disable threads for neighbor list construction
bool _newton; // en/disable newton's 3rd law for local atoms.
void set_neighbor_omp();
};
}
#endif
#endif

View File

@ -1,50 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Mike Parks (SNL)
------------------------------------------------------------------------- */
#include "fix_peri_neigh_omp.h"
#include "fix_omp.h"
#include "modify.h"
#include "neighbor.h"
#include "neigh_request.h"
using namespace LAMMPS_NS;
using namespace FixConst;
/* ---------------------------------------------------------------------- */
void FixPeriNeighOMP::init()
{
if (!first) return;
// determine status of neighbor flag of the omp package command
int ifix = modify->find_fix("package_omp");
int use_omp = 0;
if (ifix >=0) {
FixOMP * fix = static_cast<FixOMP *>(lmp->modify->fix[ifix]);
if (fix->get_neighbor()) use_omp = 1;
}
// need a full neighbor list once
int irequest = neighbor->request((void *) this);
neighbor->requests[irequest]->pair = 0;
neighbor->requests[irequest]->fix = 1;
neighbor->requests[irequest]->half = 0;
neighbor->requests[irequest]->full = 1;
neighbor->requests[irequest]->omp = use_omp;
neighbor->requests[irequest]->occasional = 1;
}

View File

@ -1,38 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(PERI_NEIGH_OMP,FixPeriNeighOMP)
#else
#ifndef LMP_FIX_PERI_NEIGH_OMP_H
#define LMP_FIX_PERI_NEIGH_OMP_H
#include "fix_peri_neigh.h"
namespace LAMMPS_NS {
class FixPeriNeighOMP : public FixPeriNeigh {
public:
FixPeriNeighOMP(class LAMMPS *lmp, int narg, char **argv) :
FixPeriNeigh(lmp,narg,argv) {};
virtual void init();
};
}
#endif
#endif

View File

@ -1,192 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "lmptype.h"
#include "mpi.h"
#include "math.h"
#include "fix_qeq_comb_omp.h"
#include "fix_omp.h"
#include "atom.h"
#include "comm.h"
#include "force.h"
#include "group.h"
#include "memory.h"
#include "modify.h"
#include "error.h"
#include "neighbor.h"
#include "neigh_list.h"
#include "neigh_request.h"
#include "respa.h"
#include "update.h"
#include "pair_comb_omp.h"
#include <string.h>
using namespace LAMMPS_NS;
using namespace FixConst;
/* ---------------------------------------------------------------------- */
FixQEQCombOMP::FixQEQCombOMP(LAMMPS *lmp, int narg, char **arg)
: FixQEQComb(lmp, narg, arg)
{
if (narg < 5) error->all(FLERR,"Illegal fix qeq/comb/omp command");
}
/* ---------------------------------------------------------------------- */
void FixQEQCombOMP::init()
{
if (!atom->q_flag)
error->all(FLERR,"Fix qeq/comb/omp requires atom attribute q");
comb = (PairComb *) force->pair_match("comb/omp",1);
if (comb == NULL)
comb = (PairComb *) force->pair_match("comb",1);
if (comb == NULL) error->all(FLERR,"Must use pair_style comb or comb/omp with fix qeq/comb");
if (strstr(update->integrate_style,"respa"))
nlevels_respa = ((Respa *) update->integrate)->nlevels;
ngroup = group->count(igroup);
if (ngroup == 0) error->all(FLERR,"Fix qeq/comb group has no atoms");
// determine status of neighbor flag of the omp package command
int ifix = modify->find_fix("package_omp");
int use_omp = 0;
if (ifix >=0) {
FixOMP * fix = static_cast<FixOMP *>(lmp->modify->fix[ifix]);
if (fix->get_neighbor()) use_omp = 1;
}
int irequest = neighbor->request(this);
neighbor->requests[irequest]->pair = 0;
neighbor->requests[irequest]->fix = 1;
neighbor->requests[irequest]->half = 0;
neighbor->requests[irequest]->full = 1;
neighbor->requests[irequest]->omp = use_omp;
}
/* ---------------------------------------------------------------------- */
void FixQEQCombOMP::post_force(int vflag)
{
int i,ii,iloop,loopmax,inum,*ilist;
double heatpq,qmass,dtq,dtq2;
double enegchkall,enegmaxall;
if (update->ntimestep % nevery) return;
// reallocate work arrays if necessary
// qf = charge force
// q1 = charge displacement
// q2 = tmp storage of charge force for next iteration
if (atom->nmax > nmax) {
memory->destroy(qf);
memory->destroy(q1);
memory->destroy(q2);
nmax = atom->nmax;
memory->create(qf,nmax,"qeq:qf");
memory->create(q1,nmax,"qeq:q1");
memory->create(q2,nmax,"qeq:q2");
vector_atom = qf;
}
// more loops for first-time charge equilibrium
iloop = 0;
if (firstflag) loopmax = 500;
else loopmax = 200;
// charge-equilibration loop
if (me == 0 && fp)
fprintf(fp,"Charge equilibration on step " BIGINT_FORMAT "\n",
update->ntimestep);
heatpq = 0.05;
qmass = 0.016;
dtq = 0.01;
dtq2 = 0.5*dtq*dtq/qmass;
double enegchk = 0.0;
double enegtot = 0.0;
double enegmax = 0.0;
double *q = atom->q;
int *mask = atom->mask;
inum = comb->list->inum;
ilist = comb->list->ilist;
for (ii = 0; ii < inum; ii++) {
i = ilist[ii];
q1[i] = q2[i] = qf[i] = 0.0;
}
for (iloop = 0; iloop < loopmax; iloop ++ ) {
for (ii = 0; ii < inum; ii++) {
i = ilist[ii];
if (mask[i] & groupbit) {
q1[i] += qf[i]*dtq2 - heatpq*q1[i];
q[i] += q1[i];
}
}
comm->forward_comm_fix(this);
if(comb) enegtot = comb->yasu_char(qf,igroup);
enegtot /= ngroup;
enegchk = enegmax = 0.0;
for (ii = 0; ii < inum ; ii++) {
i = ilist[ii];
if (mask[i] & groupbit) {
q2[i] = enegtot-qf[i];
enegmax = MAX(enegmax,fabs(q2[i]));
enegchk += fabs(q2[i]);
qf[i] = q2[i];
}
}
MPI_Allreduce(&enegchk,&enegchkall,1,MPI_DOUBLE,MPI_SUM,world);
enegchk = enegchkall/ngroup;
MPI_Allreduce(&enegmax,&enegmaxall,1,MPI_DOUBLE,MPI_MAX,world);
enegmax = enegmaxall;
if (enegchk <= precision && enegmax <= 100.0*precision) break;
if (me == 0 && fp)
fprintf(fp," iteration: %d, enegtot %.6g, "
"enegmax %.6g, fq deviation: %.6g\n",
iloop,enegtot,enegmax,enegchk);
for (ii = 0; ii < inum; ii++) {
i = ilist[ii];
if (mask[i] & groupbit)
q1[i] += qf[i]*dtq2 - heatpq*q1[i];
}
}
if (me == 0 && fp) {
if (iloop == loopmax)
fprintf(fp,"Charges did not converge in %d iterations\n",iloop);
else
fprintf(fp,"Charges converged in %d iterations to %.10f tolerance\n",
iloop,enegchk);
}
}

View File

@ -1,32 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(qeq/comb/omp,FixQEQCombOMP)
#else
#ifndef LMP_FIX_QEQ_COMB_OMP_H
#define LMP_FIX_QEQ_COMB_OMP_H
#include "fix_qeq_comb.h"
namespace LAMMPS_NS {
class FixQEQCombOMP : public FixQEQComb {
public:
FixQEQCombOMP(class LAMMPS *, int, char **);
virtual void init();
virtual void post_force(int);
};
}
#endif
#endif

View File

@ -1,152 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "string.h"
#include "stdio.h"
#include "fix_shear_history_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "neigh_list.h"
#include "force.h"
#include "pair.h"
#include "update.h"
#include "modify.h"
#include "error.h"
#if defined(_OPENMP)
#include <omp.h>
#endif
using namespace LAMMPS_NS;
using namespace FixConst;
#define MAXTOUCH 15
/* ----------------------------------------------------------------------
copy shear partner info from neighbor lists to atom arrays
so can be exchanged with atoms
------------------------------------------------------------------------- */
void FixShearHistoryOMP::pre_exchange()
{
const int nlocal = atom->nlocal;
const int nghost = atom->nghost;
const int nall = nlocal + nghost;
const int nthreads = comm->nthreads;
int flag = 0;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(flag)
#endif
{
#if defined(_OPENMP)
const int tid = omp_get_thread_num();
#else
const int tid = 0;
#endif
// each thread works on a fixed chunk of local and ghost atoms.
const int ldelta = 1 + nlocal/nthreads;
const int lfrom = tid*ldelta;
const int lmax = lfrom +ldelta;
const int lto = (lmax > nlocal) ? nlocal : lmax;
const int gdelta = 1 + nghost/nthreads;
const int gfrom = nlocal + tid*gdelta;
const int gmax = gfrom + gdelta;
const int gto = (gmax > nall) ? nall : gmax;
int i,j,ii,jj,m,inum,jnum;
int *ilist,*jlist,*numneigh,**firstneigh;
int *touch,**firsttouch;
double *shear,*allshear,**firstshear;
// zero npartners for all current atoms
for (i = lfrom; i < lto; i++) npartner[i] = 0;
// copy shear info from neighbor list atoms to atom arrays
int *tag = atom->tag;
NeighList *list = pair->list;
inum = list->inum;
ilist = list->ilist;
numneigh = list->numneigh;
firstneigh = list->firstneigh;
firsttouch = list->listgranhistory->firstneigh;
firstshear = list->listgranhistory->firstdouble;
for (ii = 0; ii < inum; ii++) {
i = ilist[ii];
jlist = firstneigh[i];
allshear = firstshear[i];
jnum = numneigh[i];
touch = firsttouch[i];
for (jj = 0; jj < jnum; jj++) {
if (touch[jj]) {
j = jlist[jj];
j &= NEIGHMASK;
shear = &allshear[3*jj];
if ((i >= lfrom) && (i < lto)) {
if (npartner[i] < MAXTOUCH) {
m = npartner[i];
partner[i][m] = tag[j];
shearpartner[i][m][0] = shear[0];
shearpartner[i][m][1] = shear[1];
shearpartner[i][m][2] = shear[2];
}
npartner[i]++;
}
if ((j >= lfrom) && (j < lto)) {
if (npartner[j] < MAXTOUCH) {
m = npartner[j];
partner[j][m] = tag[i];
shearpartner[j][m][0] = -shear[0];
shearpartner[j][m][1] = -shear[1];
shearpartner[j][m][2] = -shear[2];
}
npartner[j]++;
}
if ((j >= gfrom) && (j < gto)) {
npartner[j]++;
}
}
}
}
// test for too many touching neighbors
int myflag = 0;
for (i = lfrom; i < lto; i++)
if (npartner[i] >= MAXTOUCH) myflag = 1;
if (myflag)
#if defined(_OPENMP)
#pragma omp atomic
#endif
++flag;
}
int flag_all;
MPI_Allreduce(&flag,&flag_all,1,MPI_INT,MPI_SUM,world);
if (flag_all)
error->all(FLERR,"Too many touching neighbors - boost MAXTOUCH");
}

View File

@ -1,38 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(SHEAR_HISTORY/omp,FixShearHistoryOMP)
#else
#ifndef LMP_FIX_SHEAR_HISTORY_OMP_H
#define LMP_FIX_SHEAR_HISTORY_OMP_H
#include "fix_shear_history.h"
namespace LAMMPS_NS {
class FixShearHistoryOMP : public FixShearHistory {
public:
FixShearHistoryOMP(class LAMMPS *lmp, int narg, char **argv)
: FixShearHistory(lmp,narg,argv) {};
virtual void pre_exchange();
};
}
#endif
#endif

View File

@ -1,148 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "fix_wall_gran_omp.h"
#include "atom.h"
#include "update.h"
using namespace LAMMPS_NS;
using namespace FixConst;
enum{XPLANE=0,YPLANE=1,ZPLANE=2,ZCYLINDER}; // XYZ PLANE need to be 0,1,2
enum{HOOKE,HOOKE_HISTORY,HERTZ_HISTORY};
#define BIG 1.0e20
/* ---------------------------------------------------------------------- */
FixWallGranOMP::FixWallGranOMP(LAMMPS *lmp, int narg, char **arg) :
FixWallGran(lmp, narg, arg) { }
/* ---------------------------------------------------------------------- */
void FixWallGranOMP::post_force(int vflag)
{
double vwall[3];
// set position of wall to initial settings and velocity to 0.0
// if wiggle or shear, set wall position and velocity accordingly
double wlo = lo;
double whi = hi;
vwall[0] = vwall[1] = vwall[2] = 0.0;
if (wiggle) {
double arg = omega * (update->ntimestep - time_origin) * dt;
if (wallstyle == axis) {
wlo = lo + amplitude - amplitude*cos(arg);
whi = hi + amplitude - amplitude*cos(arg);
}
vwall[axis] = amplitude*omega*sin(arg);
} else if (wshear) vwall[axis] = vshear;
// loop over all my atoms
// rsq = distance from wall
// dx,dy,dz = signed distance from wall
// for rotating cylinder, reset vwall based on particle position
// skip atom if not close enough to wall
// if wall was set to NULL, it's skipped since lo/hi are infinity
// compute force and torque on atom if close enough to wall
// via wall potential matched to pair potential
// set shear if pair potential stores history
double * const * const x = atom->x;
double * const * const v = atom->v;
double * const * const f = atom->f;
double * const * const omega = atom->omega;
double * const * const torque = atom->torque;
double * const radius = atom->radius;
double * const rmass = atom->rmass;
const int * const mask = atom->mask;
const int nlocal = atom->nlocal;
shearupdate = (update->setupflag) ? 0 : 1;
int i;
#if defined(_OPENMP)
#pragma omp parallel for private(i) default(none) firstprivate(vwall,wlo,whi)
#endif
for (i = 0; i < nlocal; i++) {
if (mask[i] & groupbit) {
double dx,dy,dz,del1,del2,delxy,delr,rsq;
dx = dy = dz = 0.0;
if (wallstyle == XPLANE) {
del1 = x[i][0] - wlo;
del2 = whi - x[i][0];
if (del1 < del2) dx = del1;
else dx = -del2;
} else if (wallstyle == YPLANE) {
del1 = x[i][1] - wlo;
del2 = whi - x[i][1];
if (del1 < del2) dy = del1;
else dy = -del2;
} else if (wallstyle == ZPLANE) {
del1 = x[i][2] - wlo;
del2 = whi - x[i][2];
if (del1 < del2) dz = del1;
else dz = -del2;
} else if (wallstyle == ZCYLINDER) {
delxy = sqrt(x[i][0]*x[i][0] + x[i][1]*x[i][1]);
delr = cylradius - delxy;
if (delr > radius[i]) dz = cylradius;
else {
dx = -delr/delxy * x[i][0];
dy = -delr/delxy * x[i][1];
if (wshear && axis != 2) {
vwall[0] = vshear * x[i][1]/delxy;
vwall[1] = -vshear * x[i][0]/delxy;
vwall[2] = 0.0;
}
}
}
rsq = dx*dx + dy*dy + dz*dz;
if (rsq > radius[i]*radius[i]) {
if (pairstyle != HOOKE) {
shear[i][0] = 0.0;
shear[i][1] = 0.0;
shear[i][2] = 0.0;
}
} else {
if (pairstyle == HOOKE)
hooke(rsq,dx,dy,dz,vwall,v[i],f[i],omega[i],torque[i],
radius[i],rmass[i]);
else if (pairstyle == HOOKE_HISTORY)
hooke_history(rsq,dx,dy,dz,vwall,v[i],f[i],omega[i],torque[i],
radius[i],rmass[i],shear[i]);
else if (pairstyle == HERTZ_HISTORY)
hertz_history(rsq,dx,dy,dz,vwall,v[i],f[i],omega[i],torque[i],
radius[i],rmass[i],shear[i]);
}
}
}
}
/* ---------------------------------------------------------------------- */
void FixWallGranOMP::post_force_respa(int vflag, int ilevel, int iloop)
{
if (ilevel == nlevels_respa-1) post_force(vflag);
}

View File

@ -1,38 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifdef FIX_CLASS
FixStyle(wall/gran/omp,FixWallGranOMP)
#else
#ifndef LMP_FIX_WALL_GRAN_OMP_H
#define LMP_FIX_WALL_GRAN_OMP_H
#include "fix_wall_gran.h"
namespace LAMMPS_NS {
class FixWallGranOMP : public FixWallGran {
public:
FixWallGranOMP(class LAMMPS *, int, char **);
virtual void post_force(int);
virtual void post_force_respa(int, int, int);
};
}
#endif
#endif

View File

@ -1,8 +0,0 @@
#!/bin/sh
for f in *.h *.cpp
do \
sed -e '/#pragma omp/s/^\(.*default\)(none)\(.*\)$/\1(shared)\2/' \
-e '/#pragma omp/s/shared([a-z0-9,_]\+)//' \
-i.bak $f
done

View File

@ -1,698 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_class2_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperClass2OMP::ImproperClass2OMP(class LAMMPS *lmp)
: ImproperClass2(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperClass2OMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperClass2OMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,i,j,k,n,type;
double eimproper;
double delr[3][3],rmag[3],rinvmag[3],rmag2[3];
double theta[3],costheta[3],sintheta[3];
double cossqtheta[3],sinsqtheta[3],invstheta[3];
double rABxrCB[3],rDBxrAB[3],rCBxrDB[3];
double ddelr[3][4],dr[3][4][3],dinvr[3][4][3];
double dthetadr[3][4][3],dinvsth[3][4][3];
double dinv3r[4][3],dinvs3r[3][4][3];
double drCBxrDB[3],rCBxdrDB[3],drDBxrAB[3],rDBxdrAB[3];
double drABxrCB[3],rABxdrCB[3];
double dot1,dot2,dd[3];
double fdot[3][4][3],ftmp,invs3r[3],inv3r;
double t,tt1,tt3,sc1;
double dotCBDBAB,dotDBABCB,dotABCBDB;
double chi,deltachi,d2chi,cossin2;
double drAB[3][4][3],drCB[3][4][3],drDB[3][4][3];
double dchi[3][4][3],dtotalchi[4][3];
double schiABCD,chiABCD,schiCBDA,chiCBDA,schiDBAC,chiDBAC;
double fabcd[4][3];
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++) {
dthetadr[i][j][k] = 0.0;
drAB[i][j][k] = 0.0;
drCB[i][j][k] = 0.0;
drDB[i][j][k] = 0.0;
}
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
if (k0[type] == 0.0) continue;
// difference vectors
delr[0][0] = x[i1][0] - x[i2][0];
delr[0][1] = x[i1][1] - x[i2][1];
delr[0][2] = x[i1][2] - x[i2][2];
delr[1][0] = x[i3][0] - x[i2][0];
delr[1][1] = x[i3][1] - x[i2][1];
delr[1][2] = x[i3][2] - x[i2][2];
delr[2][0] = x[i4][0] - x[i2][0];
delr[2][1] = x[i4][1] - x[i2][1];
delr[2][2] = x[i4][2] - x[i2][2];
// bond lengths and associated values
for (i = 0; i < 3; i++) {
rmag2[i] = delr[i][0]*delr[i][0] + delr[i][1]*delr[i][1] +
delr[i][2]*delr[i][2];
rmag[i] = sqrt(rmag2[i]);
rinvmag[i] = 1.0/rmag[i];
}
// angle ABC, CBD, ABD
costheta[0] = (delr[0][0]*delr[1][0] + delr[0][1]*delr[1][1] +
delr[0][2]*delr[1][2]) / (rmag[0]*rmag[1]);
costheta[1] = (delr[1][0]*delr[2][0] + delr[1][1]*delr[2][1] +
delr[1][2]*delr[2][2]) / (rmag[1]*rmag[2]);
costheta[2] = (delr[0][0]*delr[2][0] + delr[0][1]*delr[2][1] +
delr[0][2]*delr[2][2]) / (rmag[0]*rmag[2]);
// angle error check
for (i = 0; i < 3; i++) {
if (costheta[i] == -1.0) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,
"Improper problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me, thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
}
for (i = 0; i < 3; i++) {
if (costheta[i] > 1.0) costheta[i] = 1.0;
if (costheta[i] < -1.0) costheta[i] = -1.0;
theta[i] = acos(costheta[i]);
cossqtheta[i] = costheta[i]*costheta[i];
sintheta[i] = sin(theta[i]);
invstheta[i] = 1.0/sintheta[i];
sinsqtheta[i] = sintheta[i]*sintheta[i];
}
// cross & dot products
cross(delr[0],delr[1],rABxrCB);
cross(delr[2],delr[0],rDBxrAB);
cross(delr[1],delr[2],rCBxrDB);
dotCBDBAB = dot(rCBxrDB,delr[0]);
dotDBABCB = dot(rDBxrAB,delr[1]);
dotABCBDB = dot(rABxrCB,delr[2]);
t = rmag[0] * rmag[1] * rmag[2];
inv3r = 1.0/t;
invs3r[0] = invstheta[1] * inv3r;
invs3r[1] = invstheta[2] * inv3r;
invs3r[2] = invstheta[0] * inv3r;
// chi ABCD, CBDA, DBAC
// final chi is average of three
schiABCD = dotCBDBAB * invs3r[0];
chiABCD = asin(schiABCD);
schiCBDA = dotDBABCB * invs3r[1];
chiCBDA = asin(schiCBDA);
schiDBAC = dotABCBDB * invs3r[2];
chiDBAC = asin(schiDBAC);
chi = (chiABCD + chiCBDA + chiDBAC) / 3.0;
deltachi = chi - chi0[type];
d2chi = deltachi * deltachi;
// energy
if (EFLAG) eimproper = k0[type]*d2chi;
// forces
// define d(delr)
// i = bond AB/CB/DB, j = atom A/B/C/D
ddelr[0][0] = 1.0;
ddelr[0][1] = -1.0;
ddelr[0][2] = 0.0;
ddelr[0][3] = 0.0;
ddelr[1][0] = 0.0;
ddelr[1][1] = -1.0;
ddelr[1][2] = 1.0;
ddelr[1][3] = 0.0;
ddelr[2][0] = 0.0;
ddelr[2][1] = -1.0;
ddelr[2][2] = 0.0;
ddelr[2][3] = 1.0;
// compute d(|r|)/dr and d(1/|r|)/dr for each direction, bond and atom
// define d(r) for each r
// i = bond AB/CB/DB, j = atom A/B/C/D, k = X/Y/Z
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++) {
dr[i][j][k] = delr[i][k] * ddelr[i][j] / rmag[i];
dinvr[i][j][k] = -dr[i][j][k] / rmag2[i];
}
// compute d(1 / (|r_AB| * |r_CB| * |r_DB|) / dr
// i = atom A/B/C/D, j = X/Y/Z
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
dinv3r[i][j] = rinvmag[1] * (rinvmag[2] * dinvr[0][i][j] +
rinvmag[0] * dinvr[2][i][j]) +
rinvmag[2] * rinvmag[0] * dinvr[1][i][j];
// compute d(theta)/d(r) for 3 angles
// angleABC
tt1 = costheta[0] / rmag2[0];
tt3 = costheta[0] / rmag2[1];
sc1 = 1.0 / sqrt(1.0 - cossqtheta[0]);
dthetadr[0][0][0] = sc1 * ((tt1 * delr[0][0]) -
(delr[1][0] * rinvmag[0] * rinvmag[1]));
dthetadr[0][0][1] = sc1 * ((tt1 * delr[0][1]) -
(delr[1][1] * rinvmag[0] * rinvmag[1]));
dthetadr[0][0][2] = sc1 * ((tt1 * delr[0][2]) -
(delr[1][2] * rinvmag[0] * rinvmag[1]));
dthetadr[0][1][0] = -sc1 * ((tt1 * delr[0][0]) -
(delr[1][0] * rinvmag[0] * rinvmag[1]) +
(tt3 * delr[1][0]) -
(delr[0][0] * rinvmag[0] * rinvmag[1]));
dthetadr[0][1][1] = -sc1 * ((tt1 * delr[0][1]) -
(delr[1][1] * rinvmag[0] * rinvmag[1]) +
(tt3 * delr[1][1]) -
(delr[0][1] * rinvmag[0] * rinvmag[1]));
dthetadr[0][1][2] = -sc1 * ((tt1 * delr[0][2]) -
(delr[1][2] * rinvmag[0] * rinvmag[1]) +
(tt3 * delr[1][2]) -
(delr[0][2] * rinvmag[0] * rinvmag[1]));
dthetadr[0][2][0] = sc1 * ((tt3 * delr[1][0]) -
(delr[0][0] * rinvmag[0] * rinvmag[1]));
dthetadr[0][2][1] = sc1 * ((tt3 * delr[1][1]) -
(delr[0][1] * rinvmag[0] * rinvmag[1]));
dthetadr[0][2][2] = sc1 * ((tt3 * delr[1][2]) -
(delr[0][2] * rinvmag[0] * rinvmag[1]));
// angleCBD
tt1 = costheta[1] / rmag2[1];
tt3 = costheta[1] / rmag2[2];
sc1 = 1.0 / sqrt(1.0 - cossqtheta[1]);
dthetadr[1][2][0] = sc1 * ((tt1 * delr[1][0]) -
(delr[2][0] * rinvmag[1] * rinvmag[2]));
dthetadr[1][2][1] = sc1 * ((tt1 * delr[1][1]) -
(delr[2][1] * rinvmag[1] * rinvmag[2]));
dthetadr[1][2][2] = sc1 * ((tt1 * delr[1][2]) -
(delr[2][2] * rinvmag[1] * rinvmag[2]));
dthetadr[1][1][0] = -sc1 * ((tt1 * delr[1][0]) -
(delr[2][0] * rinvmag[1] * rinvmag[2]) +
(tt3 * delr[2][0]) -
(delr[1][0] * rinvmag[2] * rinvmag[1]));
dthetadr[1][1][1] = -sc1 * ((tt1 * delr[1][1]) -
(delr[2][1] * rinvmag[1] * rinvmag[2]) +
(tt3 * delr[2][1]) -
(delr[1][1] * rinvmag[2] * rinvmag[1]));
dthetadr[1][1][2] = -sc1 * ((tt1 * delr[1][2]) -
(delr[2][2] * rinvmag[1] * rinvmag[2]) +
(tt3 * delr[2][2]) -
(delr[1][2] * rinvmag[2] * rinvmag[1]));
dthetadr[1][3][0] = sc1 * ((tt3 * delr[2][0]) -
(delr[1][0] * rinvmag[2] * rinvmag[1]));
dthetadr[1][3][1] = sc1 * ((tt3 * delr[2][1]) -
(delr[1][1] * rinvmag[2] * rinvmag[1]));
dthetadr[1][3][2] = sc1 * ((tt3 * delr[2][2]) -
(delr[1][2] * rinvmag[2] * rinvmag[1]));
// angleABD
tt1 = costheta[2] / rmag2[0];
tt3 = costheta[2] / rmag2[2];
sc1 = 1.0 / sqrt(1.0 - cossqtheta[2]);
dthetadr[2][0][0] = sc1 * ((tt1 * delr[0][0]) -
(delr[2][0] * rinvmag[0] * rinvmag[2]));
dthetadr[2][0][1] = sc1 * ((tt1 * delr[0][1]) -
(delr[2][1] * rinvmag[0] * rinvmag[2]));
dthetadr[2][0][2] = sc1 * ((tt1 * delr[0][2]) -
(delr[2][2] * rinvmag[0] * rinvmag[2]));
dthetadr[2][1][0] = -sc1 * ((tt1 * delr[0][0]) -
(delr[2][0] * rinvmag[0] * rinvmag[2]) +
(tt3 * delr[2][0]) -
(delr[0][0] * rinvmag[2] * rinvmag[0]));
dthetadr[2][1][1] = -sc1 * ((tt1 * delr[0][1]) -
(delr[2][1] * rinvmag[0] * rinvmag[2]) +
(tt3 * delr[2][1]) -
(delr[0][1] * rinvmag[2] * rinvmag[0]));
dthetadr[2][1][2] = -sc1 * ((tt1 * delr[0][2]) -
(delr[2][2] * rinvmag[0] * rinvmag[2]) +
(tt3 * delr[2][2]) -
(delr[0][2] * rinvmag[2] * rinvmag[0]));
dthetadr[2][3][0] = sc1 * ((tt3 * delr[2][0]) -
(delr[0][0] * rinvmag[2] * rinvmag[0]));
dthetadr[2][3][1] = sc1 * ((tt3 * delr[2][1]) -
(delr[0][1] * rinvmag[2] * rinvmag[0]));
dthetadr[2][3][2] = sc1 * ((tt3 * delr[2][2]) -
(delr[0][2] * rinvmag[2] * rinvmag[0]));
// compute d( 1 / sin(theta))/dr
// i = angle, j = atom, k = direction
for (i = 0; i < 3; i++) {
cossin2 = -costheta[i] / sinsqtheta[i];
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++)
dinvsth[i][j][k] = cossin2 * dthetadr[i][j][k];
}
// compute d(1 / sin(theta) * |r_AB| * |r_CB| * |r_DB|)/dr
// i = angle, j = atom
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++) {
dinvs3r[0][i][j] = (invstheta[1] * dinv3r[i][j]) +
(inv3r * dinvsth[1][i][j]);
dinvs3r[1][i][j] = (invstheta[2] * dinv3r[i][j]) +
(inv3r * dinvsth[2][i][j]);
dinvs3r[2][i][j] = (invstheta[0] * dinv3r[i][j]) +
(inv3r * dinvsth[0][i][j]);
}
// drCB(i,j,k), etc
// i = vector X'/Y'/Z', j = atom A/B/C/D, k = direction X/Y/Z
for (i = 0; i < 3; i++) {
drCB[i][1][i] = -1.0;
drAB[i][1][i] = -1.0;
drDB[i][1][i] = -1.0;
drDB[i][3][i] = 1.0;
drCB[i][2][i] = 1.0;
drAB[i][0][i] = 1.0;
}
// d((r_CB x r_DB) dot r_AB)
// r_CB x d(r_DB)
// d(r_CB) x r_DB
// (r_CB x d(r_DB)) + (d(r_CB) x r_DB)
// (r_CB x d(r_DB)) + (d(r_CB) x r_DB) dot r_AB
// d(r_AB) dot (r_CB x r_DB)
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++) {
cross(delr[1],drDB[i][j],rCBxdrDB);
cross(drCB[i][j],delr[2],drCBxrDB);
for (k = 0; k < 3; k++) dd[k] = rCBxdrDB[k] + drCBxrDB[k];
dot1 = dot(dd,delr[0]);
dot2 = dot(rCBxrDB,drAB[i][j]);
fdot[0][j][i] = dot1 + dot2;
}
// d((r_DB x r_AB) dot r_CB)
// r_DB x d(r_AB)
// d(r_DB) x r_AB
// (r_DB x d(r_AB)) + (d(r_DB) x r_AB)
// (r_DB x d(r_AB)) + (d(r_DB) x r_AB) dot r_CB
// d(r_CB) dot (r_DB x r_AB)
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++) {
cross(delr[2],drAB[i][j],rDBxdrAB);
cross(drDB[i][j],delr[0],drDBxrAB);
for (k = 0; k < 3; k++) dd[k] = rDBxdrAB[k] + drDBxrAB[k];
dot1 = dot(dd,delr[1]);
dot2 = dot(rDBxrAB,drCB[i][j]);
fdot[1][j][i] = dot1 + dot2;
}
// d((r_AB x r_CB) dot r_DB)
// r_AB x d(r_CB)
// d(r_AB) x r_CB
// (r_AB x d(r_CB)) + (d(r_AB) x r_CB)
// (r_AB x d(r_CB)) + (d(r_AB) x r_CB) dot r_DB
// d(r_DB) dot (r_AB x r_CB)
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++) {
cross(delr[0],drCB[i][j],rABxdrCB);
cross(drAB[i][j],delr[1],drABxrCB);
for (k = 0; k < 3; k++) dd[k] = rABxdrCB[k] + drABxrCB[k];
dot1 = dot(dd,delr[2]);
dot2 = dot(rABxrCB,drDB[i][j]);
fdot[2][j][i] = dot1 + dot2;
}
// force on each atom
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++) {
ftmp = (fdot[0][i][j] * invs3r[0]) +
(dinvs3r[0][i][j] * dotCBDBAB);
dchi[0][i][j] = ftmp / cos(chiABCD);
ftmp = (fdot[1][i][j] * invs3r[1]) +
(dinvs3r[1][i][j] * dotDBABCB);
dchi[1][i][j] = ftmp / cos(chiCBDA);
ftmp = (fdot[2][i][j] * invs3r[2]) +
(dinvs3r[2][i][j] * dotABCBDB);
dchi[2][i][j] = ftmp / cos(chiDBAC);
dtotalchi[i][j] = (dchi[0][i][j]+dchi[1][i][j]+dchi[2][i][j]) / 3.0;
}
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] = -2.0*k0[type] * deltachi*dtotalchi[i][j];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += fabcd[0][0];
f[i1][1] += fabcd[0][1];
f[i1][2] += fabcd[0][2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += fabcd[1][0];
f[i2][1] += fabcd[1][1];
f[i2][2] += fabcd[1][2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += fabcd[2][0];
f[i3][1] += fabcd[2][1];
f[i3][2] += fabcd[2][2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += fabcd[3][0];
f[i4][1] += fabcd[3][1];
f[i4][2] += fabcd[3][2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,
fabcd[0],fabcd[2],fabcd[3],
delr[0][0],delr[0][1],delr[0][2],
delr[1][0],delr[1][1],delr[1][2],
delr[2][0]-delr[1][0],delr[2][1]-delr[1][1],
delr[2][2]-delr[1][2],thr);
}
// compute angle-angle interactions
angleangle_thr<EVFLAG, EFLAG, NEWTON_BOND>(nfrom,nto,thr);
}
/* ----------------------------------------------------------------------
angle-angle interactions within improper
------------------------------------------------------------------------- */
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperClass2OMP::angleangle_thr(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,i,j,k,n,type;
double eimproper;
double delxAB,delyAB,delzAB,rABmag2,rAB;
double delxBC,delyBC,delzBC,rBCmag2,rBC;
double delxBD,delyBD,delzBD,rBDmag2,rBD;
double costhABC,thetaABC,costhABD;
double thetaABD,costhCBD,thetaCBD,dthABC,dthCBD,dthABD;
double sc1,t1,t3,r12;
double dthetadr[3][4][3],fabcd[4][3];
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
// difference vectors
delxAB = x[i1][0] - x[i2][0];
delyAB = x[i1][1] - x[i2][1];
delzAB = x[i1][2] - x[i2][2];
delxBC = x[i3][0] - x[i2][0];
delyBC = x[i3][1] - x[i2][1];
delzBC = x[i3][2] - x[i2][2];
delxBD = x[i4][0] - x[i2][0];
delyBD = x[i4][1] - x[i2][1];
delzBD = x[i4][2] - x[i2][2];
// bond lengths
rABmag2 = delxAB*delxAB + delyAB*delyAB + delzAB*delzAB;
rAB = sqrt(rABmag2);
rBCmag2 = delxBC*delxBC + delyBC*delyBC + delzBC*delzBC;
rBC = sqrt(rBCmag2);
rBDmag2 = delxBD*delxBD + delyBD*delyBD + delzBD*delzBD;
rBD = sqrt(rBDmag2);
// angle ABC, ABD, CBD
costhABC = (delxAB*delxBC + delyAB*delyBC + delzAB*delzBC) / (rAB * rBC);
if (costhABC > 1.0) costhABC = 1.0;
if (costhABC < -1.0) costhABC = -1.0;
thetaABC = acos(costhABC);
costhABD = (delxAB*delxBD + delyAB*delyBD + delzAB*delzBD) / (rAB * rBD);
if (costhABD > 1.0) costhABD = 1.0;
if (costhABD < -1.0) costhABD = -1.0;
thetaABD = acos(costhABD);
costhCBD = (delxBC*delxBD + delyBC*delyBD + delzBC*delzBD) /(rBC * rBD);
if (costhCBD > 1.0) costhCBD = 1.0;
if (costhCBD < -1.0) costhCBD = -1.0;
thetaCBD = acos(costhCBD);
dthABC = thetaABC - aa_theta0_1[type];
dthABD = thetaABD - aa_theta0_2[type];
dthCBD = thetaCBD - aa_theta0_3[type];
// energy
if (EFLAG) eimproper = aa_k2[type] * dthABC * dthABD +
aa_k1[type] * dthABC * dthCBD +
aa_k3[type] * dthABD * dthCBD;
// d(theta)/d(r) array
// angle i, atom j, coordinate k
for (i = 0; i < 3; i++)
for (j = 0; j < 4; j++)
for (k = 0; k < 3; k++)
dthetadr[i][j][k] = 0.0;
// angle ABC
sc1 = sqrt(1.0/(1.0 - costhABC*costhABC));
t1 = costhABC / rABmag2;
t3 = costhABC / rBCmag2;
r12 = 1.0 / (rAB * rBC);
dthetadr[0][0][0] = sc1 * ((t1 * delxAB) - (delxBC * r12));
dthetadr[0][0][1] = sc1 * ((t1 * delyAB) - (delyBC * r12));
dthetadr[0][0][2] = sc1 * ((t1 * delzAB) - (delzBC * r12));
dthetadr[0][1][0] = sc1 * ((-t1 * delxAB) + (delxBC * r12) +
(-t3 * delxBC) + (delxAB * r12));
dthetadr[0][1][1] = sc1 * ((-t1 * delyAB) + (delyBC * r12) +
(-t3 * delyBC) + (delyAB * r12));
dthetadr[0][1][2] = sc1 * ((-t1 * delzAB) + (delzBC * r12) +
(-t3 * delzBC) + (delzAB * r12));
dthetadr[0][2][0] = sc1 * ((t3 * delxBC) - (delxAB * r12));
dthetadr[0][2][1] = sc1 * ((t3 * delyBC) - (delyAB * r12));
dthetadr[0][2][2] = sc1 * ((t3 * delzBC) - (delzAB * r12));
// angle CBD
sc1 = sqrt(1.0/(1.0 - costhCBD*costhCBD));
t1 = costhCBD / rBCmag2;
t3 = costhCBD / rBDmag2;
r12 = 1.0 / (rBC * rBD);
dthetadr[1][2][0] = sc1 * ((t1 * delxBC) - (delxBD * r12));
dthetadr[1][2][1] = sc1 * ((t1 * delyBC) - (delyBD * r12));
dthetadr[1][2][2] = sc1 * ((t1 * delzBC) - (delzBD * r12));
dthetadr[1][1][0] = sc1 * ((-t1 * delxBC) + (delxBD * r12) +
(-t3 * delxBD) + (delxBC * r12));
dthetadr[1][1][1] = sc1 * ((-t1 * delyBC) + (delyBD * r12) +
(-t3 * delyBD) + (delyBC * r12));
dthetadr[1][1][2] = sc1 * ((-t1 * delzBC) + (delzBD * r12) +
(-t3 * delzBD) + (delzBC * r12));
dthetadr[1][3][0] = sc1 * ((t3 * delxBD) - (delxBC * r12));
dthetadr[1][3][1] = sc1 * ((t3 * delyBD) - (delyBC * r12));
dthetadr[1][3][2] = sc1 * ((t3 * delzBD) - (delzBC * r12));
// angle ABD
sc1 = sqrt(1.0/(1.0 - costhABD*costhABD));
t1 = costhABD / rABmag2;
t3 = costhABD / rBDmag2;
r12 = 1.0 / (rAB * rBD);
dthetadr[2][0][0] = sc1 * ((t1 * delxAB) - (delxBD * r12));
dthetadr[2][0][1] = sc1 * ((t1 * delyAB) - (delyBD * r12));
dthetadr[2][0][2] = sc1 * ((t1 * delzAB) - (delzBD * r12));
dthetadr[2][1][0] = sc1 * ((-t1 * delxAB) + (delxBD * r12) +
(-t3 * delxBD) + (delxAB * r12));
dthetadr[2][1][1] = sc1 * ((-t1 * delyAB) + (delyBD * r12) +
(-t3 * delyBD) + (delyAB * r12));
dthetadr[2][1][2] = sc1 * ((-t1 * delzAB) + (delzBD * r12) +
(-t3 * delzBD) + (delzAB * r12));
dthetadr[2][3][0] = sc1 * ((t3 * delxBD) - (delxAB * r12));
dthetadr[2][3][1] = sc1 * ((t3 * delyBD) - (delyAB * r12));
dthetadr[2][3][2] = sc1 * ((t3 * delzBD) - (delzAB * r12));
// angleangle forces
for (i = 0; i < 4; i++)
for (j = 0; j < 3; j++)
fabcd[i][j] = -
((aa_k1[type] *
(dthABC*dthetadr[1][i][j] + dthCBD*dthetadr[0][i][j])) +
(aa_k2[type] *
(dthABC*dthetadr[2][i][j] + dthABD*dthetadr[0][i][j])) +
(aa_k3[type] *
(dthABD*dthetadr[1][i][j] + dthCBD*dthetadr[2][i][j])));
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += fabcd[0][0];
f[i1][1] += fabcd[0][1];
f[i1][2] += fabcd[0][2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += fabcd[1][0];
f[i2][1] += fabcd[1][1];
f[i2][2] += fabcd[1][2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += fabcd[2][0];
f[i3][1] += fabcd[2][1];
f[i3][2] += fabcd[2][2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += fabcd[3][0];
f[i4][1] += fabcd[3][1];
f[i4][2] += fabcd[3][2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,
fabcd[0],fabcd[2],fabcd[3],delxAB,delyAB,delzAB,
delxBC,delyBC,delzBC,delxBD,delyBD,delzBD,thr);
}
}

View File

@ -1,50 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(class2/omp,ImproperClass2OMP)
#else
#ifndef LMP_IMPROPER_CLASS2_OMP_H
#define LMP_IMPROPER_CLASS2_OMP_H
#include "improper_class2.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperClass2OMP : public ImproperClass2, public ThrOMP {
public:
ImproperClass2OMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void angleangle_thr(int, int, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,267 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_cossq_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperCossqOMP::ImproperCossqOMP(class LAMMPS *lmp)
: ImproperCossq(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperCossqOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperCossqOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
double eimproper,f1[3],f2[3],f3[3],f4[3];
double rjisq, rji, rlksq, rlk, cosphi, angfac;
double cjiji, clkji, clklk, cfact1, cfact2, cfact3;
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
/* separation vector between i1 and i2, (i2-i1) */
vb1x = x[i2][0] - x[i1][0];
vb1y = x[i2][1] - x[i1][1];
vb1z = x[i2][2] - x[i1][2];
rjisq = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z ;
rji = sqrt(rjisq);
/* separation vector between i2 and i3 (i3-i2) */
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
/* separation vector between i3 and i4, (i4-i3) */
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
rlksq = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z ;
rlk = sqrt(rlksq);
cosphi = (vb3x*vb1x + vb3y*vb1y + vb3z*vb1z)/(rji * rlk);
/* Check that cos(phi) is in the correct limits. */
if (cosphi > 1.0 + TOLERANCE || cosphi < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Improper problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
/* Apply corrections to round-off errors. */
if (cosphi > 1.0) cosphi -= SMALL;
if (cosphi < -1.0) cosphi += SMALL;
/* Calculate the angle: */
double torangle = acos(cosphi);
cosphi = cos(torangle - chi[type]);
if (EFLAG) eimproper = 0.5 * k[type] * cosphi * cosphi;
/*
printf("The tags: %d-%d-%d-%d, of type %d .\n",atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4],type);
printf("The ji vector: %f, %f, %f.\nThe lk vector: %f, %f, %f.\n", vb1x,vb1y,vb1z,vb3x,vb3y,vb3z);
printf("The cosine of the angle: %-1.16e.\n", cosphi);
printf("The energy of the improper: %-1.16e with prefactor %-1.16e.\n", eimproper, 0.5*k[type]);
*/
/* Work out forces. */
angfac = - k[type] * cosphi;
cjiji = rjisq;
clklk = rlksq;
/*CLKJI = RXLK * RXJI + RYLK * RYJI + RZLK * RZJI */
clkji = vb3x*vb1x + vb3y*vb1y + vb3z*vb1z;
/*CFACT1 = CLKLK * CJIJI
CFACT1 = SQRT(CFACT1)
CFACT1 = ANGFAC / CFACT1*/
cfact1 = angfac / sqrt(clklk * cjiji);
/*CFACT2 = CLKJI / CLKLK*/
cfact2 = clkji / clklk;
/*CFACT3 = CLKJI / CJIJI*/
cfact3 = clkji / cjiji;
/*FIX = -RXLK + CFACT3 * RXJI
FIY = -RYLK + CFACT3 * RYJI
FIZ = -RZLK + CFACT3 * RZJI*/
f1[0] = - vb3x + cfact3 * vb1x;
f1[1] = - vb3y + cfact3 * vb1y;
f1[2] = - vb3z + cfact3 * vb1z;
/*FJX = -FIX
FJY = -FIY
FJZ = -FIZ*/
f2[0] = - f1[0];
f2[1] = - f1[1];
f2[2] = - f1[2];
/*FKX = CFACT2 * RXLK - RXJI
FKY = CFACT2 * RYLK - RYJI
FKZ = CFACT2 * RZLK - RZJI*/
f3[0] = cfact2 * vb3x - vb1x;
f3[1] = cfact2 * vb3y - vb1y;
f3[2] = cfact2 * vb3z - vb1z;
/*FLX = -FKX
FLY = -FKY
FLZ = -FKZ*/
f4[0] = - f3[0];
f4[1] = - f3[1];
f4[2] = - f3[2];
/*FIX = FIX * CFACT1
FIY = FIY * CFACT1
FIZ = FIZ * CFACT1*/
f1[0] *= cfact1;
f1[1] *= cfact1;
f1[2] *= cfact1;
/*FJX = FJX * CFACT1
FJY = FJY * CFACT1
FJZ = FJZ * CFACT1*/
f2[0] *= cfact1;
f2[1] *= cfact1;
f2[2] *= cfact1;
/*FKX = FKX * CFACT1
FKY = FKY * CFACT1
FKZ = FKZ * CFACT1*/
f3[0] *= cfact1;
f3[1] *= cfact1;
f3[2] *= cfact1;
/*FLX = FLX * CFACT1
FLY = FLY * CFACT1
FLZ = FLZ * CFACT1*/
f4[0] *= cfact1;
f4[1] *= cfact1;
f4[2] *= cfact1;
/* Apply force to each of 4 atoms */
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,f1,f3,f4,
-vb1x,-vb1y,-vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(cossq/omp,ImproperCossqOMP)
#else
#ifndef LMP_IMPROPER_COSSQ_OMP_H
#define LMP_IMPROPER_COSSQ_OMP_H
#include "improper_cossq.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperCossqOMP : public ImproperCossq, public ThrOMP {
public:
ImproperCossqOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,298 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_cvff_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperCvffOMP::ImproperCvffOMP(class LAMMPS *lmp)
: ImproperCvff(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperCvffOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperCvffOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,m,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,vb2xm,vb2ym,vb2zm;
double eimproper,f1[3],f2[3],f3[3],f4[3];
double sb1,sb2,sb3,rb1,rb3,c0,b1mag2,b1mag,b2mag2;
double b2mag,b3mag2,b3mag,ctmp,r12c1,c1mag,r12c2;
double c2mag,sc1,sc2,s1,s2,s12,c,p,pd,rc2,a,a11,a22;
double a33,a12,a13,a23,sx2,sy2,sz2;
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
// 1st bond
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
// 2nd bond
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb2xm = -vb2x;
vb2ym = -vb2y;
vb2zm = -vb2z;
// 3rd bond
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
// c0 calculation
sb1 = 1.0 / (vb1x*vb1x + vb1y*vb1y + vb1z*vb1z);
sb2 = 1.0 / (vb2x*vb2x + vb2y*vb2y + vb2z*vb2z);
sb3 = 1.0 / (vb3x*vb3x + vb3y*vb3y + vb3z*vb3z);
rb1 = sqrt(sb1);
rb3 = sqrt(sb3);
c0 = (vb1x*vb3x + vb1y*vb3y + vb1z*vb3z) * rb1*rb3;
// 1st and 2nd angle
b1mag2 = vb1x*vb1x + vb1y*vb1y + vb1z*vb1z;
b1mag = sqrt(b1mag2);
b2mag2 = vb2x*vb2x + vb2y*vb2y + vb2z*vb2z;
b2mag = sqrt(b2mag2);
b3mag2 = vb3x*vb3x + vb3y*vb3y + vb3z*vb3z;
b3mag = sqrt(b3mag2);
ctmp = vb1x*vb2x + vb1y*vb2y + vb1z*vb2z;
r12c1 = 1.0 / (b1mag*b2mag);
c1mag = ctmp * r12c1;
ctmp = vb2xm*vb3x + vb2ym*vb3y + vb2zm*vb3z;
r12c2 = 1.0 / (b2mag*b3mag);
c2mag = ctmp * r12c2;
// cos and sin of 2 angles and final c
sc1 = sqrt(1.0 - c1mag*c1mag);
if (sc1 < SMALL) sc1 = SMALL;
sc1 = 1.0/sc1;
sc2 = sqrt(1.0 - c2mag*c2mag);
if (sc2 < SMALL) sc2 = SMALL;
sc2 = 1.0/sc2;
s1 = sc1 * sc1;
s2 = sc2 * sc2;
s12 = sc1 * sc2;
c = (c0 + c1mag*c2mag) * s12;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Improper problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
// force & energy
// p = 1 + cos(n*phi) for d = 1
// p = 1 - cos(n*phi) for d = -1
// pd = dp/dc / 2
m = multiplicity[type];
if (m == 2) {
p = 2.0*c*c;
pd = 2.0*c;
} else if (m == 3) {
rc2 = c*c;
p = (4.0*rc2-3.0)*c + 1.0;
pd = 6.0*rc2 - 1.5;
} else if (m == 4) {
rc2 = c*c;
p = 8.0*(rc2-1)*rc2 + 2.0;
pd = (16.0*rc2-8.0)*c;
} else if (m == 6) {
rc2 = c*c;
p = ((32.0*rc2-48.0)*rc2 + 18.0)*rc2;
pd = (96.0*(rc2-1.0)*rc2 + 18.0)*c;
} else if (m == 1) {
p = c + 1.0;
pd = 0.5;
} else if (m == 5) {
rc2 = c*c;
p = ((16.0*rc2-20.0)*rc2 + 5.0)*c + 1.0;
pd = (40.0*rc2-30.0)*rc2 + 2.5;
} else if (m == 0) {
p = 2.0;
pd = 0.0;
}
if (sign[type] == -1) {
p = 2.0 - p;
pd = -pd;
}
if (EFLAG) eimproper = k[type]*p;
a = 2.0 * k[type] * pd;
c = c * a;
s12 = s12 * a;
a11 = c*sb1*s1;
a22 = -sb2*(2.0*c0*s12 - c*(s1+s2));
a33 = c*sb3*s2;
a12 = -r12c1*(c1mag*c*s1 + c2mag*s12);
a13 = -rb1*rb3*s12;
a23 = r12c2*(c2mag*c*s2 + c1mag*s12);
sx2 = a12*vb1x + a22*vb2x + a23*vb3x;
sy2 = a12*vb1y + a22*vb2y + a23*vb3y;
sz2 = a12*vb1z + a22*vb2z + a23*vb3z;
f1[0] = a11*vb1x + a12*vb2x + a13*vb3x;
f1[1] = a11*vb1y + a12*vb2y + a13*vb3y;
f1[2] = a11*vb1z + a12*vb2z + a13*vb3z;
f2[0] = -sx2 - f1[0];
f2[1] = -sy2 - f1[1];
f2[2] = -sz2 - f1[2];
f4[0] = a13*vb1x + a23*vb2x + a33*vb3x;
f4[1] = a13*vb1y + a23*vb2y + a33*vb3y;
f4[2] = a13*vb1z + a23*vb2z + a33*vb3z;
f3[0] = sx2 - f4[0];
f3[1] = sy2 - f4[1];
f3[2] = sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(cvff/omp,ImproperCvffOMP)
#else
#ifndef LMP_IMPROPER_CVFF_OMP_H
#define LMP_IMPROPER_CVFF_OMP_H
#include "improper_cvff.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperCvffOMP : public ImproperCvff, public ThrOMP {
public:
ImproperCvffOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,240 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_harmonic_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperHarmonicOMP::ImproperHarmonicOMP(class LAMMPS *lmp)
: ImproperHarmonic(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperHarmonicOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperHarmonicOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
double eimproper,f1[3],f2[3],f3[3],f4[3];
double ss1,ss2,ss3,r1,r2,r3,c0,c1,c2,s1,s2;
double s12,c,s,domega,a,a11,a22,a33,a12,a13,a23;
double sx2,sy2,sz2;
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
// geometry of 4-body
vb1x = x[i1][0] - x[i2][0];
vb1y = x[i1][1] - x[i2][1];
vb1z = x[i1][2] - x[i2][2];
vb2x = x[i3][0] - x[i2][0];
vb2y = x[i3][1] - x[i2][1];
vb2z = x[i3][2] - x[i2][2];
vb3x = x[i4][0] - x[i3][0];
vb3y = x[i4][1] - x[i3][1];
vb3z = x[i4][2] - x[i3][2];
ss1 = 1.0 / (vb1x*vb1x + vb1y*vb1y + vb1z*vb1z);
ss2 = 1.0 / (vb2x*vb2x + vb2y*vb2y + vb2z*vb2z);
ss3 = 1.0 / (vb3x*vb3x + vb3y*vb3y + vb3z*vb3z);
r1 = sqrt(ss1);
r2 = sqrt(ss2);
r3 = sqrt(ss3);
// sin and cos of angle
c0 = (vb1x * vb3x + vb1y * vb3y + vb1z * vb3z) * r1 * r3;
c1 = (vb1x * vb2x + vb1y * vb2y + vb1z * vb2z) * r1 * r2;
c2 = -(vb3x * vb2x + vb3y * vb2y + vb3z * vb2z) * r3 * r2;
s1 = 1.0 - c1*c1;
if (s1 < SMALL) s1 = SMALL;
s1 = 1.0 / s1;
s2 = 1.0 - c2*c2;
if (s2 < SMALL) s2 = SMALL;
s2 = 1.0 / s2;
s12 = sqrt(s1*s2);
c = (c1*c2 + c0) * s12;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Improper problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) c = 1.0;
if (c < -1.0) c = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
// force & energy
domega = acos(c) - chi[type];
a = k[type] * domega;
if (EFLAG) eimproper = a*domega;
a = -a * 2.0/s;
c = c * a;
s12 = s12 * a;
a11 = c*ss1*s1;
a22 = -ss2 * (2.0*c0*s12 - c*(s1+s2));
a33 = c*ss3*s2;
a12 = -r1*r2*(c1*c*s1 + c2*s12);
a13 = -r1*r3*s12;
a23 = r2*r3*(c2*c*s2 + c1*s12);
sx2 = a22*vb2x + a23*vb3x + a12*vb1x;
sy2 = a22*vb2y + a23*vb3y + a12*vb1y;
sz2 = a22*vb2z + a23*vb3z + a12*vb1z;
f1[0] = a12*vb2x + a13*vb3x + a11*vb1x;
f1[1] = a12*vb2y + a13*vb3y + a11*vb1y;
f1[2] = a12*vb2z + a13*vb3z + a11*vb1z;
f2[0] = -sx2 - f1[0];
f2[1] = -sy2 - f1[1];
f2[2] = -sz2 - f1[2];
f4[0] = a23*vb2x + a33*vb3x + a13*vb1x;
f4[1] = a23*vb2y + a33*vb3y + a13*vb1y;
f4[2] = a23*vb2z + a33*vb3z + a13*vb1z;
f3[0] = sx2 - f4[0];
f3[1] = sy2 - f4[1];
f3[2] = sz2 - f4[2];
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0];
f[i1][1] += f1[1];
f[i1][2] += f1[2];
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f2[0];
f[i2][1] += f2[1];
f[i2][2] += f2[2];
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f3[0];
f[i3][1] += f3[1];
f[i3][2] += f3[2];
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0];
f[i4][1] += f4[1];
f[i4][2] += f4[2];
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(harmonic/omp,ImproperHarmonicOMP)
#else
#ifndef LMP_IMPROPER_HARMONIC_OMP_H
#define LMP_IMPROPER_HARMONIC_OMP_H
#include "improper_harmonic.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperHarmonicOMP : public ImproperHarmonic, public ThrOMP {
public:
ImproperHarmonicOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,261 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_ring_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperRingOMP::ImproperRingOMP(class LAMMPS *lmp)
: ImproperRing(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperRingOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperRingOMP::eval(int nfrom, int nto, ThrData * const thr)
{
/* Be careful!: "chi" is the equilibrium angle in radians. */
int i1,i2,i3,i4,n,type;
double eimproper;
/* Compatibility variables. */
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
double f1[3], f3[3], f4[3];
/* Actual computation variables. */
int at1[3], at2[3], at3[3], icomb;
double bvec1x[3], bvec1y[3], bvec1z[3],
bvec2x[3], bvec2y[3], bvec2z[3],
bvec1n[3], bvec2n[3], bend_angle[3];
double angle_summer, angfac, cfact1, cfact2, cfact3;
double cjiji, ckjji, ckjkj, fix, fiy, fiz, fjx, fjy, fjz, fkx, fky, fkz;
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
/* A description of the potential can be found in
Macromolecules 35, pp. 1463-1472 (2002). */
for (n = nfrom; n < nto; n++) {
/* Take the ids of the atoms contributing to the improper potential. */
i1 = improperlist[n][0]; /* Atom "1" of Figure 1 from the above reference.*/
i2 = improperlist[n][1]; /* Atom "2" ... */
i3 = improperlist[n][2]; /* Atom "3" ... */
i4 = improperlist[n][3]; /* Atom "9" ... */
type = improperlist[n][4];
/* Calculate the necessary variables for LAMMPS implementation.
if (evflag) ev_tally(i1,i2,i3,i4,nlocal,newton_bond,eimproper,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z);
Although, they are irrelevant to the calculation of the potential, we keep
them for maximal compatibility. */
vb1x = x[i1][0] - x[i2][0]; vb1y = x[i1][1] - x[i2][1]; vb1z = x[i1][2] - x[i2][2];
vb2x = x[i3][0] - x[i2][0]; vb2y = x[i3][1] - x[i2][1]; vb2z = x[i3][2] - x[i2][2];
vb3x = x[i4][0] - x[i3][0]; vb3y = x[i4][1] - x[i3][1]; vb3z = x[i4][2] - x[i3][2];
/* Pass the atom tags to form the necessary combinations. */
at1[0] = i1; at2[0] = i2; at3[0] = i4; /* ids: 1-2-9 */
at1[1] = i1; at2[1] = i2; at3[1] = i3; /* ids: 1-2-3 */
at1[2] = i4; at2[2] = i2; at3[2] = i3; /* ids: 9-2-3 */
/* Initialize the sum of the angles differences. */
angle_summer = 0.0;
/* Take a loop over the three angles, defined by each triad: */
for (icomb = 0; icomb < 3; icomb ++) {
/* Bond vector connecting the first and the second atom. */
bvec1x[icomb] = x[at2[icomb]][0] - x[at1[icomb]][0];
bvec1y[icomb] = x[at2[icomb]][1] - x[at1[icomb]][1];
bvec1z[icomb] = x[at2[icomb]][2] - x[at1[icomb]][2];
/* also calculate the norm of the vector: */
bvec1n[icomb] = sqrt( bvec1x[icomb]*bvec1x[icomb]
+ bvec1y[icomb]*bvec1y[icomb]
+ bvec1z[icomb]*bvec1z[icomb]);
/* Bond vector connecting the second and the third atom. */
bvec2x[icomb] = x[at3[icomb]][0] - x[at2[icomb]][0];
bvec2y[icomb] = x[at3[icomb]][1] - x[at2[icomb]][1];
bvec2z[icomb] = x[at3[icomb]][2] - x[at2[icomb]][2];
/* also calculate the norm of the vector: */
bvec2n[icomb] = sqrt( bvec2x[icomb]*bvec2x[icomb]
+ bvec2y[icomb]*bvec2y[icomb]
+ bvec2z[icomb]*bvec2z[icomb]);
/* Calculate the bending angle of the atom triad: */
bend_angle[icomb] = ( bvec2x[icomb]*bvec1x[icomb]
+ bvec2y[icomb]*bvec1y[icomb]
+ bvec2z[icomb]*bvec1z[icomb]);
bend_angle[icomb] /= (bvec1n[icomb] * bvec2n[icomb]);
if (bend_angle[icomb] > 1.0) bend_angle[icomb] -= SMALL;
if (bend_angle[icomb] < -1.0) bend_angle[icomb] += SMALL;
/* Append the current angle to the sum of angle differences. */
angle_summer += (bend_angle[icomb] - chi[type]);
}
if (EFLAG) eimproper = (1.0/6.0) *k[type] * pow(angle_summer,6.0);
/*
printf("The tags: %d-%d-%d-%d, of type %d .\n",atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4],type);
// printf("The coordinates of the first: %f, %f, %f.\n", x[i1][0], x[i1][1], x[i1][2]);
// printf("The coordinates of the second: %f, %f, %f.\n", x[i2][0], x[i2][1], x[i2][2]);
// printf("The coordinates of the third: %f, %f, %f.\n", x[i3][0], x[i3][1], x[i3][2]);
// printf("The coordinates of the fourth: %f, %f, %f.\n", x[i4][0], x[i4][1], x[i4][2]);
printf("The angles are: %f / %f / %f equilibrium: %f.\n", bend_angle[0], bend_angle[1], bend_angle[2],chi[type]);
printf("The energy of the improper: %f with prefactor %f.\n", eimproper,(1.0/6.0)*k[type]);
printf("The sum of the angles: %f.\n", angle_summer);
*/
/* Force calculation acting on all atoms.
Calculate the derivatives of the potential. */
angfac = k[type] * pow(angle_summer,5.0);
f1[0] = 0.0; f1[1] = 0.0; f1[2] = 0.0;
f3[0] = 0.0; f3[1] = 0.0; f3[2] = 0.0;
f4[0] = 0.0; f4[1] = 0.0; f4[2] = 0.0;
/* Take a loop over the three angles, defined by each triad: */
for (icomb = 0; icomb < 3; icomb ++)
{
/* Calculate the squares of the distances. */
cjiji = bvec1n[icomb] * bvec1n[icomb]; ckjkj = bvec2n[icomb] * bvec2n[icomb];
ckjji = bvec2x[icomb] * bvec1x[icomb]
+ bvec2y[icomb] * bvec1y[icomb]
+ bvec2z[icomb] * bvec1z[icomb] ;
cfact1 = angfac / (sqrt(ckjkj * cjiji));
cfact2 = ckjji / ckjkj;
cfact3 = ckjji / cjiji;
/* Calculate the force acted on the thrid atom of the angle. */
fkx = cfact2 * bvec2x[icomb] - bvec1x[icomb];
fky = cfact2 * bvec2y[icomb] - bvec1y[icomb];
fkz = cfact2 * bvec2z[icomb] - bvec1z[icomb];
/* Calculate the force acted on the first atom of the angle. */
fix = bvec2x[icomb] - cfact3 * bvec1x[icomb];
fiy = bvec2y[icomb] - cfact3 * bvec1y[icomb];
fiz = bvec2z[icomb] - cfact3 * bvec1z[icomb];
/* Finally, calculate the force acted on the middle atom of the angle.*/
fjx = - fix - fkx; fjy = - fiy - fky; fjz = - fiz - fkz;
/* Consider the appropriate scaling of the forces: */
fix *= cfact1; fiy *= cfact1; fiz *= cfact1;
fjx *= cfact1; fjy *= cfact1; fjz *= cfact1;
fkx *= cfact1; fky *= cfact1; fkz *= cfact1;
if (at1[icomb] == i1) {f1[0] += fix; f1[1] += fiy; f1[2] += fiz;}
else if (at2[icomb] == i1) {f1[0] += fjx; f1[1] += fjy; f1[2] += fjz;}
else if (at3[icomb] == i1) {f1[0] += fkx; f1[1] += fky; f1[2] += fkz;}
if (at1[icomb] == i3) {f3[0] += fix; f3[1] += fiy; f3[2] += fiz;}
else if (at2[icomb] == i3) {f3[0] += fjx; f3[1] += fjy; f3[2] += fjz;}
else if (at3[icomb] == i3) {f3[0] += fkx; f3[1] += fky; f3[2] += fkz;}
if (at1[icomb] == i4) {f4[0] += fix; f4[1] += fiy; f4[2] += fiz;}
else if (at2[icomb] == i4) {f4[0] += fjx; f4[1] += fjy; f4[2] += fjz;}
else if (at3[icomb] == i4) {f4[0] += fkx; f4[1] += fky; f4[2] += fkz;}
/* Store the contribution to the global arrays: */
/* Take the id of the atom from the at1[icomb] element, i1 = at1[icomb]. */
if (NEWTON_BOND || at1[icomb] < nlocal) {
f[at1[icomb]][0] += fix;
f[at1[icomb]][1] += fiy;
f[at1[icomb]][2] += fiz;
}
/* Take the id of the atom from the at2[icomb] element, i2 = at2[icomb]. */
if (NEWTON_BOND || at2[icomb] < nlocal) {
f[at2[icomb]][0] += fjx;
f[at2[icomb]][1] += fjy;
f[at2[icomb]][2] += fjz;
}
/* Take the id of the atom from the at3[icomb] element, i3 = at3[icomb]. */
if (NEWTON_BOND || at3[icomb] < nlocal) {
f[at3[icomb]][0] += fkx;
f[at3[icomb]][1] += fky;
f[at3[icomb]][2] += fkz;
}
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(ring/omp,ImproperRingOMP)
#else
#ifndef LMP_IMPROPER_RING_OMP_H
#define LMP_IMPROPER_RING_OMP_H
#include "improper_ring.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperRingOMP : public ImproperRing, public ThrOMP {
public:
ImproperRingOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,256 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#include "math.h"
#include "improper_umbrella_omp.h"
#include "atom.h"
#include "comm.h"
#include "neighbor.h"
#include "domain.h"
#include "force.h"
#include "update.h"
#include "error.h"
#include "suffix.h"
using namespace LAMMPS_NS;
#define TOLERANCE 0.05
#define SMALL 0.001
/* ---------------------------------------------------------------------- */
ImproperUmbrellaOMP::ImproperUmbrellaOMP(class LAMMPS *lmp)
: ImproperUmbrella(lmp), ThrOMP(lmp,THR_IMPROPER)
{
suffix_flag |= Suffix::OMP;
}
/* ---------------------------------------------------------------------- */
void ImproperUmbrellaOMP::compute(int eflag, int vflag)
{
if (eflag || vflag) {
ev_setup(eflag,vflag);
} else evflag = 0;
const int nall = atom->nlocal + atom->nghost;
const int nthreads = comm->nthreads;
const int inum = neighbor->nimproperlist;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(eflag,vflag)
#endif
{
int ifrom, ito, tid;
loop_setup_thr(ifrom, ito, tid, inum, nthreads);
ThrData *thr = fix->get_thr(tid);
ev_setup_thr(eflag, vflag, nall, eatom, vatom, thr);
if (evflag) {
if (eflag) {
if (force->newton_bond) eval<1,1,1>(ifrom, ito, thr);
else eval<1,1,0>(ifrom, ito, thr);
} else {
if (force->newton_bond) eval<1,0,1>(ifrom, ito, thr);
else eval<1,0,0>(ifrom, ito, thr);
}
} else {
if (force->newton_bond) eval<0,0,1>(ifrom, ito, thr);
else eval<0,0,0>(ifrom, ito, thr);
}
reduce_thr(this, eflag, vflag, thr);
} // end of omp parallel region
}
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void ImproperUmbrellaOMP::eval(int nfrom, int nto, ThrData * const thr)
{
int i1,i2,i3,i4,n,type;
double eimproper,f1[3],f2[3],f3[3],f4[3];
double vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z;
double domega,c,a,s,projhfg,dhax,dhay,dhaz,dahx,dahy,dahz,cotphi;
double ax,ay,az,ra2,rh2,ra,rh,rar,rhr,arx,ary,arz,hrx,hry,hrz;
eimproper = 0.0;
const double * const * const x = atom->x;
double * const * const f = thr->get_f();
const int * const * const improperlist = neighbor->improperlist;
const int nlocal = atom->nlocal;
for (n = nfrom; n < nto; n++) {
i1 = improperlist[n][0];
i2 = improperlist[n][1];
i3 = improperlist[n][2];
i4 = improperlist[n][3];
type = improperlist[n][4];
// 1st bond
vb1x = x[i2][0] - x[i1][0];
vb1y = x[i2][1] - x[i1][1];
vb1z = x[i2][2] - x[i1][2];
// 2nd bond
vb2x = x[i3][0] - x[i1][0];
vb2y = x[i3][1] - x[i1][1];
vb2z = x[i3][2] - x[i1][2];
// 3rd bond
vb3x = x[i4][0] - x[i1][0];
vb3y = x[i4][1] - x[i1][1];
vb3z = x[i4][2] - x[i1][2];
// c0 calculation
// A = vb1 X vb2 is perpendicular to IJK plane
ax = vb1y*vb2z-vb1z*vb2y;
ay = vb1z*vb2x-vb1x*vb2z;
az = vb1x*vb2y-vb1y*vb2x;
ra2 = ax*ax+ay*ay+az*az;
rh2 = vb3x*vb3x+vb3y*vb3y+vb3z*vb3z;
ra = sqrt(ra2);
rh = sqrt(rh2);
if (ra < SMALL) ra = SMALL;
if (rh < SMALL) rh = SMALL;
rar = 1/ra;
rhr = 1/rh;
arx = ax*rar;
ary = ay*rar;
arz = az*rar;
hrx = vb3x*rhr;
hry = vb3y*rhr;
hrz = vb3z*rhr;
c = arx*hrx+ary*hry+arz*hrz;
// error check
if (c > 1.0 + TOLERANCE || c < (-1.0 - TOLERANCE)) {
int me = comm->me;
if (screen) {
char str[128];
sprintf(str,"Improper problem: %d/%d " BIGINT_FORMAT " %d %d %d %d",
me,thr->get_tid(),update->ntimestep,
atom->tag[i1],atom->tag[i2],atom->tag[i3],atom->tag[i4]);
error->warning(FLERR,str,0);
fprintf(screen," 1st atom: %d %g %g %g\n",
me,x[i1][0],x[i1][1],x[i1][2]);
fprintf(screen," 2nd atom: %d %g %g %g\n",
me,x[i2][0],x[i2][1],x[i2][2]);
fprintf(screen," 3rd atom: %d %g %g %g\n",
me,x[i3][0],x[i3][1],x[i3][2]);
fprintf(screen," 4th atom: %d %g %g %g\n",
me,x[i4][0],x[i4][1],x[i4][2]);
}
}
if (c > 1.0) s = 1.0;
if (c < -1.0) s = -1.0;
s = sqrt(1.0 - c*c);
if (s < SMALL) s = SMALL;
cotphi = c/s;
projhfg = (vb3x*vb1x+vb3y*vb1y+vb3z*vb1z) /
sqrt(vb1x*vb1x+vb1y*vb1y+vb1z*vb1z);
projhfg += (vb3x*vb2x+vb3y*vb2y+vb3z*vb2z) /
sqrt(vb2x*vb2x+vb2y*vb2y+vb2z*vb2z);
if (projhfg > 0.0) {
s *= -1.0;
cotphi *= -1.0;
}
// force and energy
// if w0 = 0: E = k * (1 - cos w)
// if w0 != 0: E = 0.5 * C (cos w - cos w0)^2, C = k/(sin(w0)^2
if (w0[type] == 0.0) {
if (EFLAG) eimproper = kw[type] * (1.0-s);
a = -kw[type];
} else {
domega = s - cos(w0[type]);
a = 0.5 * C[type] * domega;
if (EFLAG) eimproper = a * domega;
a *= 2.0;
}
// dhax = diffrence between H and A in X direction, etc
a = a*cotphi;
dhax = hrx-c*arx;
dhay = hry-c*ary;
dhaz = hrz-c*arz;
dahx = arx-c*hrx;
dahy = ary-c*hry;
dahz = arz-c*hrz;
f2[0] = (dhay*vb1z - dhaz*vb1y)*rar;
f2[1] = (dhaz*vb1x - dhax*vb1z)*rar;
f2[2] = (dhax*vb1y - dhay*vb1x)*rar;
f3[0] = (-dhay*vb2z + dhaz*vb2y)*rar;
f3[1] = (-dhaz*vb2x + dhax*vb2z)*rar;
f3[2] = (-dhax*vb2y + dhay*vb2x)*rar;
f4[0] = dahx*rhr;
f4[1] = dahy*rhr;
f4[2] = dahz*rhr;
f1[0] = -(f2[0] + f3[0] + f4[0]);
f1[1] = -(f2[1] + f3[1] + f4[1]);
f1[2] = -(f2[2] + f3[2] + f4[2]);
// apply force to each of 4 atoms
if (NEWTON_BOND || i1 < nlocal) {
f[i1][0] += f1[0]*a;
f[i1][1] += f1[1]*a;
f[i1][2] += f1[2]*a;
}
if (NEWTON_BOND || i2 < nlocal) {
f[i2][0] += f3[0]*a;
f[i2][1] += f3[1]*a;
f[i2][2] += f3[2]*a;
}
if (NEWTON_BOND || i3 < nlocal) {
f[i3][0] += f2[0]*a;
f[i3][1] += f2[1]*a;
f[i3][2] += f2[2]*a;
}
if (NEWTON_BOND || i4 < nlocal) {
f[i4][0] += f4[0]*a;
f[i4][1] += f4[1]*a;
f[i4][2] += f4[2]*a;
}
if (EVFLAG)
ev_tally_thr(this,i1,i2,i3,i4,nlocal,NEWTON_BOND,eimproper,f1,f3,f4,
vb1x,vb1y,vb1z,vb2x,vb2y,vb2z,vb3x,vb3y,vb3z,thr);
}
}

View File

@ -1,46 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
/* ----------------------------------------------------------------------
Contributing author: Axel Kohlmeyer (Temple U)
------------------------------------------------------------------------- */
#ifdef IMPROPER_CLASS
ImproperStyle(umbrella/omp,ImproperUmbrellaOMP)
#else
#ifndef LMP_IMPROPER_UMBRELLA_OMP_H
#define LMP_IMPROPER_UMBRELLA_OMP_H
#include "improper_umbrella.h"
#include "thr_omp.h"
namespace LAMMPS_NS {
class ImproperUmbrellaOMP : public ImproperUmbrella, public ThrOMP {
public:
ImproperUmbrellaOMP(class LAMMPS *lmp);
virtual void compute(int, int);
private:
template <int EVFLAG, int EFLAG, int NEWTON_BOND>
void eval(int ifrom, int ito, ThrData * const thr);
};
}
#endif
#endif

View File

@ -1,183 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
build half list from full list
pair stored once if i,j are both owned and i < j
pair stored by me if j is ghost (also stored by proc owning j)
works if full list is a skip list
------------------------------------------------------------------------- */
void Neighbor::half_from_full_no_newton_omp(NeighList *list)
{
const int inum_full = list->listfull->inum;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(inum_full);
int i,j,ii,jj,n,jnum,joriginal;
int *neighptr,*jlist;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *ilist_full = list->listfull->ilist;
int *numneigh_full = list->listfull->numneigh;
int **firstneigh_full = list->listfull->firstneigh;
// each thread works on its own page
int npage = tid;
int npnt = 0;
// loop over atoms in full list
for (ii = ifrom; ii < ito; ii++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
// only one thread at a time may check whether we
// need new neighbor list pages and then add to them.
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
// loop over parent full list
i = ilist_full[ii];
jlist = firstneigh_full[i];
jnum = numneigh_full[i];
for (jj = 0; jj < jnum; jj++) {
joriginal = jlist[jj];
j = joriginal & NEIGHMASK;
if (j > i) neighptr[n++] = joriginal;
}
ilist[ii] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = inum_full;
}
/* ----------------------------------------------------------------------
build half list from full list
pair stored once if i,j are both owned and i < j
if j is ghost, only store if j coords are "above and to the right" of i
works if full list is a skip list
------------------------------------------------------------------------- */
void Neighbor::half_from_full_newton_omp(NeighList *list)
{
const int inum_full = list->listfull->inum;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(inum_full);
int i,j,ii,jj,n,jnum,joriginal;
int *neighptr,*jlist;
double xtmp,ytmp,ztmp;
double **x = atom->x;
int nlocal = atom->nlocal;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *ilist_full = list->listfull->ilist;
int *numneigh_full = list->listfull->numneigh;
int **firstneigh_full = list->listfull->firstneigh;
// each thread works on its own page
int npage = tid;
int npnt = 0;
// loop over parent full list
for (ii = ifrom; ii < ito; ii++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
// only one thread at a time may check whether we
// need new neighbor list pages and then add to them.
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
i = ilist_full[ii];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over full neighbor list
jlist = firstneigh_full[i];
jnum = numneigh_full[i];
for (jj = 0; jj < jnum; jj++) {
joriginal = jlist[jj];
j = joriginal & NEIGHMASK;
if (j < nlocal) {
if (i > j) continue;
} else {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
neighptr[n++] = joriginal;
}
ilist[ii] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = inum_full;
}

View File

@ -1,579 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "domain.h"
#include "group.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
N^2 search for all neighbors
every neighbor pair appears in list of both atoms i and j
------------------------------------------------------------------------- */
void Neighbor::full_nsq_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,n,itype,jtype,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int nall = atom->nlocal + atom->nghost;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int npage = tid;
int npnt = 0;
// loop over owned atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms, owned and ghost
// skip i = j
for (j = 0; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = 0;
}
/* ----------------------------------------------------------------------
N^2 search for all neighbors
include neighbors of ghost atoms, but no "special neighbors" for ghosts
every neighbor pair appears in list of both atoms i and j
------------------------------------------------------------------------- */
void Neighbor::full_nsq_ghost_omp(NeighList *list)
{
const int nlocal = atom->nlocal;
const int nall = nlocal + atom->nghost;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nall);
int i,j,n,itype,jtype,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int npage = tid;
int npnt = 0;
// loop over owned & ghost atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms, owned and ghost
// skip i = j
// no molecular test when i = ghost atom
if (i < nlocal) {
for (j = 0; j < nall; j++) {
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
} else {
for (j = 0; j < nall; j++) {
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighghostsq[itype][jtype]) neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = nall - nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction for all neighbors
every neighbor pair appears in list of both atoms i and j
------------------------------------------------------------------------- */
void Neighbor::full_bin_omp(NeighList *list)
{
// bin owned & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
int npage = tid;
int npnt = 0;
// loop over owned atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in surrounding bins in stencil including self
// skip i = j
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = 0;
}
/* ----------------------------------------------------------------------
binned neighbor list construction for all neighbors
include neighbors of ghost atoms, but no "special neighbors" for ghosts
every neighbor pair appears in list of both atoms i and j
------------------------------------------------------------------------- */
void Neighbor::full_bin_ghost_omp(NeighList *list)
{
// bin owned & ghost atoms
bin_atoms();
const int nlocal = atom->nlocal;
const int nall = nlocal + atom->nghost;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nall);
int i,j,k,n,itype,jtype,ibin,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int xbin,ybin,zbin,xbin2,ybin2,zbin2;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
int **stencilxyz = list->stencilxyz;
int npage = tid;
int npnt = 0;
// loop over owned & ghost atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in surrounding bins in stencil including self
// when i is a ghost atom, must check if stencil bin is out of bounds
// skip i = j
// no molecular test when i = ghost atom
if (i < nlocal) {
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
} else {
ibin = coord2bin(x[i],xbin,ybin,zbin);
for (k = 0; k < nstencil; k++) {
xbin2 = xbin + stencilxyz[k][0];
ybin2 = ybin + stencilxyz[k][1];
zbin2 = zbin + stencilxyz[k][2];
if (xbin2 < 0 || xbin2 >= mbinx ||
ybin2 < 0 || ybin2 >= mbiny ||
zbin2 < 0 || zbin2 >= mbinz) continue;
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (i == j) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighghostsq[itype][jtype]) neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = nall - nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction for all neighbors
multi-type stencil is itype dependent and is distance checked
every neighbor pair appears in list of both atoms i and j
------------------------------------------------------------------------- */
void Neighbor::full_multi_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which,ns;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr,*s;
double *cutsq,*distsq;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *nstencil_multi = list->nstencil_multi;
int **stencil_multi = list->stencil_multi;
double **distsq_multi = list->distsq_multi;
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in other bins in stencil, including self
// skip if i,j neighbor cutoff is less than bin distance
// skip i = j
ibin = coord2bin(x[i]);
s = stencil_multi[itype];
distsq = distsq_multi[itype];
cutsq = cutneighsq[itype];
ns = nstencil_multi[itype];
for (k = 0; k < ns; k++) {
for (j = binhead[ibin+s[k]]; j >= 0; j = bins[j]) {
jtype = type[j];
if (cutsq[jtype] < distsq[k]) continue;
if (i == j) continue;
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = 0;
}

View File

@ -1,657 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "group.h"
#include "fix_shear_history.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
granular particles
N^2 / 2 search for neighbor pairs with partial Newton's 3rd law
shear history must be accounted for when a neighbor pair is added
pair added to list if atoms i and j are both owned and i < j
pair added if j is ghost (also stored by proc owning j)
------------------------------------------------------------------------- */
void Neighbor::granular_nsq_no_newton_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
FixShearHistory * const fix_history = list->fix_history;
NeighList * listgranhistory = list->listgranhistory;
NEIGH_OMP_INIT;
if (fix_history)
if (nthreads > listgranhistory->maxpage)
listgranhistory->add_pages(nthreads - listgranhistory->maxpage);
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list,listgranhistory)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,m,n,nn;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
double radi,radsum,cutsq;
int *neighptr,*touchptr;
double *shearptr;
int *npartner,**partner;
double ***shearpartner;
int **firsttouch;
double **firstshear;
double **x = atom->x;
double *radius = atom->radius;
int *tag = atom->tag;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int nall = atom->nlocal + atom->nghost;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
if (fix_history) {
npartner = fix_history->npartner;
partner = fix_history->partner;
shearpartner = fix_history->shearpartner;
firsttouch = listgranhistory->firstneigh;
firstshear = listgranhistory->firstdouble;
}
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
{
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) {
list->add_pages(nthreads);
if (fix_history)
listgranhistory->add_pages(nthreads);
}
}
n = nn = 0;
neighptr = &(list->pages[npage][npnt]);
if (fix_history) {
touchptr = &(listgranhistory->pages[npage][npnt]);
shearptr = &(listgranhistory->dpages[npage][3*npnt]);
}
}
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
radi = radius[i];
// loop over remaining atoms, owned and ghost
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) {
neighptr[n] = j;
if (fix_history) {
if (rsq < radsum*radsum) {
for (m = 0; m < npartner[i]; m++)
if (partner[i][m] == tag[j]) break;
if (m < npartner[i]) {
touchptr[n] = 1;
shearptr[nn++] = shearpartner[i][m][0];
shearptr[nn++] = shearpartner[i][m][1];
shearptr[nn++] = shearpartner[i][m][2];
} else {
touchptr[n] = 0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
}
} else {
touchptr[n] = 0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
}
}
n++;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
if (fix_history) {
firsttouch[i] = touchptr;
firstshear[i] = shearptr;
}
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
granular particles
N^2 / 2 search for neighbor pairs with full Newton's 3rd law
no shear history is allowed for this option
pair added to list if atoms i and j are both owned and i < j
if j is ghost only me or other proc adds pair
decision based on itag,jtag tests
------------------------------------------------------------------------- */
void Neighbor::granular_nsq_newton_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,n,itag,jtag;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
double radi,radsum,cutsq;
int *neighptr;
double **x = atom->x;
double *radius = atom->radius;
int *tag = atom->tag;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int nall = atom->nlocal + atom->nghost;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itag = tag[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
radi = radius[i];
// loop over remaining atoms, owned and ghost
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
if (j >= nlocal) {
jtag = tag[j];
if (itag > jtag) {
if ((itag+jtag) % 2 == 0) continue;
} else if (itag < jtag) {
if ((itag+jtag) % 2 == 1) continue;
} else {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
}
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) neighptr[n++] = j;
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
granular particles
binned neighbor list construction with partial Newton's 3rd law
shear history must be accounted for when a neighbor pair is added
each owned atom i checks own bin and surrounding bins in non-Newton stencil
pair stored once if i,j are both owned and i < j
pair stored by me if j is ghost (also stored by proc owning j)
------------------------------------------------------------------------- */
void Neighbor::granular_bin_no_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
FixShearHistory * const fix_history = list->fix_history;
NeighList * listgranhistory = list->listgranhistory;
NEIGH_OMP_INIT;
if (fix_history)
if (nthreads > listgranhistory->maxpage)
listgranhistory->add_pages(nthreads - listgranhistory->maxpage);
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list,listgranhistory)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,m,n,nn,ibin;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
double radi,radsum,cutsq;
int *neighptr,*touchptr;
double *shearptr;
int *npartner,**partner;
double ***shearpartner;
int **firsttouch;
double **firstshear;
// loop over each atom, storing neighbors
double **x = atom->x;
double *radius = atom->radius;
int *tag = atom->tag;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
if (fix_history) {
npartner = fix_history->npartner;
partner = fix_history->partner;
shearpartner = fix_history->shearpartner;
firsttouch = listgranhistory->firstneigh;
firstshear = listgranhistory->firstdouble;
}
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
{
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) {
list->add_pages(nthreads);
if (fix_history)
listgranhistory->add_pages(nthreads);
}
}
n = nn = 0;
neighptr = &(list->pages[npage][npnt]);
if (fix_history) {
touchptr = &(listgranhistory->pages[npage][npnt]);
shearptr = &(listgranhistory->dpages[npage][3*npnt]);
}
}
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
radi = radius[i];
ibin = coord2bin(x[i]);
// loop over all atoms in surrounding bins in stencil including self
// only store pair if i < j
// stores own/own pairs only once
// stores own/ghost pairs on both procs
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (j <= i) continue;
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) {
neighptr[n] = j;
if (fix_history) {
if (rsq < radsum*radsum) {
for (m = 0; m < npartner[i]; m++)
if (partner[i][m] == tag[j]) break;
if (m < npartner[i]) {
touchptr[n] = 1;
shearptr[nn++] = shearpartner[i][m][0];
shearptr[nn++] = shearpartner[i][m][1];
shearptr[nn++] = shearpartner[i][m][2];
} else {
touchptr[n] = 0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
}
} else {
touchptr[n] = 0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
shearptr[nn++] = 0.0;
}
}
n++;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
if (fix_history) {
firsttouch[i] = touchptr;
firstshear[i] = shearptr;
}
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
granular particles
binned neighbor list construction with full Newton's 3rd law
no shear history is allowed for this option
each owned atom i checks its own bin and other bins in Newton stencil
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::granular_bin_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,ibin;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
double radi,radsum,cutsq;
int *neighptr;
// loop over each atom, storing neighbors
double **x = atom->x;
double *radius = atom->radius;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
n = 0;
neighptr = &(list->pages[npage][npnt]);
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
radi = radius[i];
// loop over rest of atoms in i's bin, ghosts are at end of linked list
// if j is owned atom, store it, since j is beyond i in linked list
// if j is ghost, only store if j coords are "above and to the right" of i
for (j = bins[i]; j >= 0; j = bins[j]) {
if (j >= nlocal) {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) neighptr[n++] = j;
}
// loop over all atoms in other bins in stencil, store every pair
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
granular particles
binned neighbor list construction with Newton's 3rd law for triclinic
no shear history is allowed for this option
each owned atom i checks its own bin and other bins in triclinic stencil
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::granular_bin_newton_tri_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,ibin;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
double radi,radsum,cutsq;
int *neighptr;
// loop over each atom, storing neighbors
double **x = atom->x;
double *radius = atom->radius;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
n = 0;
neighptr = &(list->pages[npage][npnt]);
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
radi = radius[i];
// loop over all atoms in bins in stencil
// pairs for atoms j "below" i are excluded
// below = lower z or (equal z and lower y) or (equal zy and lower x)
// (equal zyx and j <= i)
// latter excludes self-self interaction but allows superposed atoms
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp) {
if (x[j][0] < xtmp) continue;
if (x[j][0] == xtmp && j <= i) continue;
}
}
if (exclude && exclusion(i,j,type[i],type[j],mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
radsum = radi + radius[j];
cutsq = (radsum+skin) * (radsum+skin);
if (rsq <= cutsq) neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}

View File

@ -1,522 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "domain.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
binned neighbor list construction with partial Newton's 3rd law
each owned atom i checks own bin and other bins in stencil
pair stored once if i,j are both owned and i < j
pair stored by me if j is ghost (also stored by proc owning j)
------------------------------------------------------------------------- */
void Neighbor::half_bin_no_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in other bins in stencil including self
// only store pair if i < j
// stores own/own pairs only once
// stores own/ghost pairs on both procs
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (j <= i) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction with partial Newton's 3rd law
include neighbors of ghost atoms, but no "special neighbors" for ghosts
owned and ghost atoms check own bin and other bins in stencil
pair stored once if i,j are both owned and i < j
pair stored by me if i owned and j ghost (also stored by proc owning j)
pair stored once if i,j are both ghost and i < j
------------------------------------------------------------------------- */
void Neighbor::half_bin_no_newton_ghost_omp(NeighList *list)
{
const int nlocal = atom->nlocal;
const int nall = nlocal + atom->nghost;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nall);
int i,j,k,n,itype,jtype,ibin,which;
int xbin,ybin,zbin,xbin2,ybin2,zbin2;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
// bin local & ghost atoms
bin_atoms();
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
int **stencilxyz = list->stencilxyz;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in other bins in stencil including self
// when i is a ghost atom, must check if stencil bin is out of bounds
// only store pair if i < j
// stores own/own pairs only once
// stores own/ghost pairs with owned atom only, on both procs
// stores ghost/ghost pairs only once
// no molecular test when i = ghost atom
if (i < nlocal) {
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (j <= i) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
} else {
ibin = coord2bin(x[i],xbin,ybin,zbin);
for (k = 0; k < nstencil; k++) {
xbin2 = xbin + stencilxyz[k][0];
ybin2 = ybin + stencilxyz[k][1];
zbin2 = zbin + stencilxyz[k][2];
if (xbin2 < 0 || xbin2 >= mbinx ||
ybin2 < 0 || ybin2 >= mbiny ||
zbin2 < 0 || zbin2 >= mbinz) continue;
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (j <= i) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighghostsq[itype][jtype]) neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
list->gnum = nall - atom->nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction with full Newton's 3rd law
each owned atom i checks its own bin and other bins in Newton stencil
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::half_bin_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over rest of atoms in i's bin, ghosts are at end of linked list
// if j is owned atom, store it, since j is beyond i in linked list
// if j is ghost, only store if j coords are "above and to the right" of i
for (j = bins[i]; j >= 0; j = bins[j]) {
if (j >= nlocal) {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
// OLD: if (which >= 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
// loop over all atoms in other bins in stencil, store every pair
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
// OLD: if (which >= 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction with Newton's 3rd law for triclinic
each owned atom i checks its own bin and other bins in triclinic stencil
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::half_bin_newton_tri_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int nstencil = list->nstencil;
int *stencil = list->stencil;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in bins in stencil
// pairs for atoms j "below" i are excluded
// below = lower z or (equal z and lower y) or (equal zy and lower x)
// (equal zyx and j <= i)
// latter excludes self-self interaction but allows superposed atoms
ibin = coord2bin(x[i]);
for (k = 0; k < nstencil; k++) {
for (j = binhead[ibin+stencil[k]]; j >= 0; j = bins[j]) {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp) {
if (x[j][0] < xtmp) continue;
if (x[j][0] == xtmp && j <= i) continue;
}
}
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}

View File

@ -1,405 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "domain.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
binned neighbor list construction with partial Newton's 3rd law
each owned atom i checks own bin and other bins in stencil
multi-type stencil is itype dependent and is distance checked
pair stored once if i,j are both owned and i < j
pair stored by me if j is ghost (also stored by proc owning j)
------------------------------------------------------------------------- */
void Neighbor::half_multi_no_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which,ns;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr,*s;
double *cutsq,*distsq;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *nstencil_multi = list->nstencil_multi;
int **stencil_multi = list->stencil_multi;
double **distsq_multi = list->distsq_multi;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in other bins in stencil including self
// only store pair if i < j
// skip if i,j neighbor cutoff is less than bin distance
// stores own/own pairs only once
// stores own/ghost pairs on both procs
ibin = coord2bin(x[i]);
s = stencil_multi[itype];
distsq = distsq_multi[itype];
cutsq = cutneighsq[itype];
ns = nstencil_multi[itype];
for (k = 0; k < ns; k++) {
for (j = binhead[ibin+s[k]]; j >= 0; j = bins[j]) {
if (j <= i) continue;
jtype = type[j];
if (cutsq[jtype] < distsq[k]) continue;
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction with full Newton's 3rd law
each owned atom i checks its own bin and other bins in Newton stencil
multi-type stencil is itype dependent and is distance checked
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::half_multi_newton_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which,ns;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr,*s;
double *cutsq,*distsq;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *nstencil_multi = list->nstencil_multi;
int **stencil_multi = list->stencil_multi;
double **distsq_multi = list->distsq_multi;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over rest of atoms in i's bin, ghosts are at end of linked list
// if j is owned atom, store it, since j is beyond i in linked list
// if j is ghost, only store if j coords are "above and to the right" of i
for (j = bins[i]; j >= 0; j = bins[j]) {
if (j >= nlocal) {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
// loop over all atoms in other bins in stencil, store every pair
// skip if i,j neighbor cutoff is less than bin distance
ibin = coord2bin(x[i]);
s = stencil_multi[itype];
distsq = distsq_multi[itype];
cutsq = cutneighsq[itype];
ns = nstencil_multi[itype];
for (k = 0; k < ns; k++) {
for (j = binhead[ibin+s[k]]; j >= 0; j = bins[j]) {
jtype = type[j];
if (cutsq[jtype] < distsq[k]) continue;
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
binned neighbor list construction with Newton's 3rd law for triclinic
each owned atom i checks its own bin and other bins in triclinic stencil
multi-type stencil is itype dependent and is distance checked
every pair stored exactly once by some processor
------------------------------------------------------------------------- */
void Neighbor::half_multi_newton_tri_omp(NeighList *list)
{
// bin local & ghost atoms
bin_atoms();
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,k,n,itype,jtype,ibin,which,ns;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr,*s;
double *cutsq,*distsq;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int *nstencil_multi = list->nstencil_multi;
int **stencil_multi = list->stencil_multi;
double **distsq_multi = list->distsq_multi;
// each thread works on its own page
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over all atoms in bins, including self, in stencil
// skip if i,j neighbor cutoff is less than bin distance
// bins below self are excluded from stencil
// pairs for atoms j "below" i are excluded
// below = lower z or (equal z and lower y) or (equal zy and lower x)
// (equal zyx and j <= i)
// latter excludes self-self interaction but allows superposed atoms
ibin = coord2bin(x[i]);
s = stencil_multi[itype];
distsq = distsq_multi[itype];
cutsq = cutneighsq[itype];
ns = nstencil_multi[itype];
for (k = 0; k < ns; k++) {
for (j = binhead[ibin+s[k]]; j >= 0; j = bins[j]) {
jtype = type[j];
if (cutsq[jtype] < distsq[k]) continue;
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp) {
if (x[j][0] < xtmp) continue;
if (x[j][0] == xtmp && j <= i) continue;
}
}
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}

View File

@ -1,350 +0,0 @@
/* ----------------------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#include "neighbor.h"
#include "neighbor_omp.h"
#include "neigh_list.h"
#include "atom.h"
#include "comm.h"
#include "domain.h"
#include "group.h"
#include "error.h"
using namespace LAMMPS_NS;
/* ----------------------------------------------------------------------
N^2 / 2 search for neighbor pairs with partial Newton's 3rd law
pair stored once if i,j are both owned and i < j
pair stored by me if j is ghost (also stored by proc owning j)
------------------------------------------------------------------------- */
void Neighbor::half_nsq_no_newton_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
const int nall = atom->nlocal + atom->nghost;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,n,itype,jtype,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
// each thread works on its own page
int npage = tid;
int npnt = 0;
// loop over owned atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over remaining atoms, owned and ghost
// only store pair if i < j
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}
/* ----------------------------------------------------------------------
N^2 / 2 search for neighbor pairs with partial Newton's 3rd law
include neighbors of ghost atoms, but no "special neighbors" for ghosts
pair stored once if i,j are both owned and i < j
pair stored by me if i owned and j ghost (also stored by proc owning j)
pair stored once if i,j are both ghost and i < j
------------------------------------------------------------------------- */
void Neighbor::half_nsq_no_newton_ghost_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
const int nall = nlocal + atom->nghost;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nall);
int i,j,n,itype,jtype,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
// each thread works on its own page
int npage = tid;
int npnt = 0;
// loop over owned & ghost atoms, storing neighbors
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over remaining atoms, owned and ghost
// only store pair if i < j
// stores own/own pairs only once
// stores own/ghost pairs with owned atom only, on both procs
// stores ghost/ghost pairs only once
// no molecular test when i = ghost atom
if (i < nlocal) {
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
} else {
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = atom->nlocal;
list->gnum = nall - atom->nlocal;
}
/* ----------------------------------------------------------------------
N^2 / 2 search for neighbor pairs with full Newton's 3rd law
every pair stored exactly once by some processor
decision on ghost atoms based on itag,jtag tests
------------------------------------------------------------------------- */
void Neighbor::half_nsq_newton_omp(NeighList *list)
{
const int nlocal = (includegroup) ? atom->nfirst : atom->nlocal;
const int bitmask = (includegroup) ? group->bitmask[includegroup] : 0;
NEIGH_OMP_INIT;
#if defined(_OPENMP)
#pragma omp parallel default(none) shared(list)
#endif
NEIGH_OMP_SETUP(nlocal);
int i,j,n,itype,jtype,itag,jtag,which;
double xtmp,ytmp,ztmp,delx,dely,delz,rsq;
int *neighptr;
// loop over each atom, storing neighbors
int **special = atom->special;
int **nspecial = atom->nspecial;
int *tag = atom->tag;
double **x = atom->x;
int *type = atom->type;
int *mask = atom->mask;
int *molecule = atom->molecule;
int nall = atom->nlocal + atom->nghost;
int molecular = atom->molecular;
int *ilist = list->ilist;
int *numneigh = list->numneigh;
int **firstneigh = list->firstneigh;
int npage = tid;
int npnt = 0;
for (i = ifrom; i < ito; i++) {
#if defined(_OPENMP)
#pragma omp critical
#endif
if (pgsize - npnt < oneatom) {
npnt = 0;
npage += nthreads;
if (npage >= list->maxpage) list->add_pages(nthreads);
}
neighptr = &(list->pages[npage][npnt]);
n = 0;
itag = tag[i];
itype = type[i];
xtmp = x[i][0];
ytmp = x[i][1];
ztmp = x[i][2];
// loop over remaining atoms, owned and ghost
// itag = jtag is possible for long cutoffs that include images of self
for (j = i+1; j < nall; j++) {
if (includegroup && !(mask[j] & bitmask)) continue;
if (j >= nlocal) {
jtag = tag[j];
if (itag > jtag) {
if ((itag+jtag) % 2 == 0) continue;
} else if (itag < jtag) {
if ((itag+jtag) % 2 == 1) continue;
} else {
if (x[j][2] < ztmp) continue;
if (x[j][2] == ztmp) {
if (x[j][1] < ytmp) continue;
if (x[j][1] == ytmp && x[j][0] < xtmp) continue;
}
}
}
jtype = type[j];
if (exclude && exclusion(i,j,itype,jtype,mask,molecule)) continue;
delx = xtmp - x[j][0];
dely = ytmp - x[j][1];
delz = ztmp - x[j][2];
rsq = delx*delx + dely*dely + delz*delz;
if (rsq <= cutneighsq[itype][jtype]) {
if (molecular) {
which = find_special(special[i],nspecial[i],tag[j]);
if (which == 0) neighptr[n++] = j;
else if (domain->minimum_image_check(delx,dely,delz))
neighptr[n++] = j;
else if (which > 0) neighptr[n++] = j ^ (which << SBBITS);
} else neighptr[n++] = j;
}
}
ilist[i] = i;
firstneigh[i] = neighptr;
numneigh[i] = n;
npnt += n;
if (n > oneatom)
error->one(FLERR,"Neighbor list overflow, boost neigh_modify one");
}
NEIGH_OMP_CLOSE;
list->inum = nlocal;
}

File diff suppressed because it is too large Load Diff

View File

@ -1,59 +0,0 @@
/* -*- c++ -*- ----------------------------------------------------------
LAMMPS - Large-scale Atomic/Molecular Massively Parallel Simulator
http://lammps.sandia.gov, Sandia National Laboratories
Steve Plimpton, sjplimp@sandia.gov
Copyright (2003) Sandia Corporation. Under the terms of Contract
DE-AC04-94AL85000 with Sandia Corporation, the U.S. Government retains
certain rights in this software. This software is distributed under
the GNU General Public License.
See the README file in the top-level LAMMPS directory.
------------------------------------------------------------------------- */
#ifndef LMP_NEIGHBOR_OMP_H
#define LMP_NEIGHBOR_OMP_H
#if defined(_OPENMP)
#include <omp.h>
#endif
namespace LAMMPS_NS {
// these macros hide some ugly and redundant OpenMP related stuff
#if defined(_OPENMP)
// make sure we have at least one page for each thread
#define NEIGH_OMP_INIT \
const int nthreads = comm->nthreads; \
if (nthreads > list->maxpage) \
list->add_pages(nthreads - list->maxpage)
// get thread id and then assign each thread a fixed chunk of atoms
#define NEIGH_OMP_SETUP(num) \
{ \
const int tid = omp_get_thread_num(); \
const int idelta = 1 + num/nthreads; \
const int ifrom = tid*idelta; \
const int ito = ((ifrom + idelta) > num) \
? num : (ifrom+idelta); \
#define NEIGH_OMP_CLOSE }
#else /* !defined(_OPENMP) */
#define NEIGH_OMP_INIT \
const int nthreads = comm->nthreads;
#define NEIGH_OMP_SETUP(num) \
const int tid = 0; \
const int ifrom = 0; \
const int ito = num
#define NEIGH_OMP_CLOSE
#endif
}
#endif

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