forked from lijiext/lammps
221 lines
6.9 KiB
Plaintext
221 lines
6.9 KiB
Plaintext
// **************************************************************************
|
|
// coul_debye.cu
|
|
// -------------------
|
|
// Trung Dac Nguyen
|
|
//
|
|
// Device code for acceleration of the coul/debye pair style
|
|
//
|
|
// __________________________________________________________________________
|
|
// This file is part of the LAMMPS Accelerator Library (LAMMPS_AL)
|
|
// __________________________________________________________________________
|
|
//
|
|
// begin :
|
|
// email : ndtrung@umich.edu
|
|
// ***************************************************************************/
|
|
|
|
#ifdef NV_KERNEL
|
|
|
|
#include "lal_aux_fun1.h"
|
|
#ifndef _DOUBLE_DOUBLE
|
|
texture<float4> pos_tex;
|
|
texture<float> q_tex;
|
|
#else
|
|
texture<int4,1> pos_tex;
|
|
texture<int2> q_tex;
|
|
#endif
|
|
|
|
#else
|
|
#define pos_tex x_
|
|
#define q_tex q_
|
|
#endif
|
|
|
|
__kernel void k_coul_debye(const __global numtyp4 *restrict x_,
|
|
const __global numtyp *restrict scale,
|
|
const int lj_types,
|
|
const __global numtyp *restrict sp_cl_in,
|
|
const __global int *dev_nbor,
|
|
const __global int *dev_packed,
|
|
__global acctyp4 *restrict ans,
|
|
__global acctyp *restrict engv,
|
|
const int eflag, const int vflag, const int inum,
|
|
const int nbor_pitch,
|
|
const __global numtyp *restrict q_ ,
|
|
const __global numtyp *restrict cutsq,
|
|
const numtyp qqrd2e, const numtyp kappa,
|
|
const int t_per_atom) {
|
|
int tid, ii, offset;
|
|
atom_info(t_per_atom,ii,tid,offset);
|
|
|
|
__local numtyp sp_cl[4];
|
|
sp_cl[0]=sp_cl_in[0];
|
|
sp_cl[1]=sp_cl_in[1];
|
|
sp_cl[2]=sp_cl_in[2];
|
|
sp_cl[3]=sp_cl_in[3];
|
|
|
|
acctyp energy=(acctyp)0;
|
|
acctyp e_coul=(acctyp)0;
|
|
acctyp4 f;
|
|
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
|
|
acctyp virial[6];
|
|
for (int i=0; i<6; i++)
|
|
virial[i]=(acctyp)0;
|
|
|
|
if (ii<inum) {
|
|
int i, numj, nbor, nbor_end;
|
|
__local int n_stride;
|
|
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset,i,numj,
|
|
n_stride,nbor_end,nbor);
|
|
|
|
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
|
|
numtyp qtmp; fetch(qtmp,i,q_tex);
|
|
int itype=ix.w;
|
|
|
|
numtyp factor_coul;
|
|
for ( ; nbor<nbor_end; nbor+=n_stride) {
|
|
|
|
int j=dev_packed[nbor];
|
|
factor_coul = sp_cl[sbmask(j)];
|
|
j &= NEIGHMASK;
|
|
|
|
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
|
|
int jtype=jx.w;
|
|
|
|
// Compute r12
|
|
numtyp delx = ix.x-jx.x;
|
|
numtyp dely = ix.y-jx.y;
|
|
numtyp delz = ix.z-jx.z;
|
|
numtyp rsq = delx*delx+dely*dely+delz*delz;
|
|
|
|
int mtype=itype*lj_types+jtype;
|
|
if (rsq<cutsq[mtype]) {
|
|
numtyp r2inv=ucl_recip(rsq);
|
|
numtyp forcecoul, force, r, rinv, screening;
|
|
|
|
r = ucl_sqrt(rsq);
|
|
rinv = ucl_recip(r);
|
|
fetch(screening,j,q_tex);
|
|
screening *= ucl_exp(-kappa*r);
|
|
forcecoul = qqrd2e*qtmp*scale[mtype]*(kappa+rinv)*screening*factor_coul;
|
|
force = forcecoul * r2inv;
|
|
|
|
f.x+=delx*force;
|
|
f.y+=dely*force;
|
|
f.z+=delz*force;
|
|
|
|
if (eflag>0) {
|
|
e_coul+=qqrd2e*scale[mtype]*qtmp*rinv*screening*factor_coul;
|
|
}
|
|
if (vflag>0) {
|
|
virial[0] += delx*delx*force;
|
|
virial[1] += dely*dely*force;
|
|
virial[2] += delz*delz*force;
|
|
virial[3] += delx*dely*force;
|
|
virial[4] += delx*delz*force;
|
|
virial[5] += dely*delz*force;
|
|
}
|
|
}
|
|
|
|
} // for nbor
|
|
store_answers_q(f,energy,e_coul,virial,ii,inum,tid,t_per_atom,offset,eflag,
|
|
vflag,ans,engv);
|
|
} // if ii
|
|
}
|
|
|
|
__kernel void k_coul_debye_fast(const __global numtyp4 *restrict x_,
|
|
const __global numtyp *restrict scale_in,
|
|
const __global numtyp *restrict sp_cl_in,
|
|
const __global int *dev_nbor,
|
|
const __global int *dev_packed,
|
|
__global acctyp4 *restrict ans,
|
|
__global acctyp *restrict engv,
|
|
const int eflag, const int vflag, const int inum,
|
|
const int nbor_pitch,
|
|
const __global numtyp *restrict q_,
|
|
const __global numtyp *restrict _cutsq,
|
|
const numtyp qqrd2e, const numtyp kappa,
|
|
const int t_per_atom) {
|
|
int tid, ii, offset;
|
|
atom_info(t_per_atom,ii,tid,offset);
|
|
|
|
__local numtyp scale[MAX_SHARED_TYPES*MAX_SHARED_TYPES];
|
|
__local numtyp cutsq[MAX_SHARED_TYPES*MAX_SHARED_TYPES];
|
|
__local numtyp sp_cl[4];
|
|
if (tid<4)
|
|
sp_cl[tid]=sp_cl_in[tid];
|
|
if (tid<MAX_SHARED_TYPES*MAX_SHARED_TYPES) {
|
|
scale[tid]=scale_in[tid];
|
|
cutsq[tid]=_cutsq[tid];
|
|
}
|
|
|
|
acctyp energy=(acctyp)0;
|
|
acctyp e_coul=(acctyp)0;
|
|
acctyp4 f;
|
|
f.x=(acctyp)0; f.y=(acctyp)0; f.z=(acctyp)0;
|
|
acctyp virial[6];
|
|
for (int i=0; i<6; i++)
|
|
virial[i]=(acctyp)0;
|
|
|
|
__syncthreads();
|
|
|
|
if (ii<inum) {
|
|
int i, numj, nbor, nbor_end;
|
|
__local int n_stride;
|
|
nbor_info(dev_nbor,dev_packed,nbor_pitch,t_per_atom,ii,offset,i,numj,
|
|
n_stride,nbor_end,nbor);
|
|
|
|
numtyp4 ix; fetch4(ix,i,pos_tex); //x_[i];
|
|
numtyp qtmp; fetch(qtmp,i,q_tex);
|
|
int iw=ix.w;
|
|
int itype=fast_mul((int)MAX_SHARED_TYPES,iw);
|
|
|
|
numtyp factor_coul;
|
|
for ( ; nbor<nbor_end; nbor+=n_stride) {
|
|
|
|
int j=dev_packed[nbor];
|
|
factor_coul = sp_cl[sbmask(j)];
|
|
j &= NEIGHMASK;
|
|
|
|
numtyp4 jx; fetch4(jx,j,pos_tex); //x_[j];
|
|
int mtype=itype+jx.w;
|
|
|
|
// Compute r12
|
|
numtyp delx = ix.x-jx.x;
|
|
numtyp dely = ix.y-jx.y;
|
|
numtyp delz = ix.z-jx.z;
|
|
numtyp rsq = delx*delx+dely*dely+delz*delz;
|
|
|
|
if (rsq<cutsq[mtype]) {
|
|
numtyp r2inv=ucl_recip(rsq);
|
|
numtyp forcecoul, force, r, rinv, screening;
|
|
|
|
r = ucl_sqrt(rsq);
|
|
rinv = ucl_recip(r);
|
|
fetch(screening,j,q_tex);
|
|
screening *= ucl_exp(-kappa*r);
|
|
forcecoul = qqrd2e*scale[mtype]*qtmp*(kappa+rinv)*screening*factor_coul;
|
|
force = forcecoul * r2inv;
|
|
|
|
f.x+=delx*force;
|
|
f.y+=dely*force;
|
|
f.z+=delz*force;
|
|
|
|
if (eflag>0) {
|
|
e_coul+=qqrd2e*scale[mtype]*qtmp*rinv*screening*factor_coul;
|
|
}
|
|
if (vflag>0) {
|
|
virial[0] += delx*delx*force;
|
|
virial[1] += dely*dely*force;
|
|
virial[2] += delz*delz*force;
|
|
virial[3] += delx*dely*force;
|
|
virial[4] += delx*delz*force;
|
|
virial[5] += dely*delz*force;
|
|
}
|
|
}
|
|
|
|
} // for nbor
|
|
store_answers_q(f,energy,e_coul,virial,ii,inum,tid,t_per_atom,offset,eflag,
|
|
vflag,ans,engv);
|
|
} // if ii
|
|
}
|
|
|