2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012,2013,2014, by the GROMACS development team, led by
5 * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
6 * and including many others, as listed in the AUTHORS file in the
7 * top-level source directory and at http://www.gromacs.org.
9 * GROMACS is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public License
11 * as published by the Free Software Foundation; either version 2.1
12 * of the License, or (at your option) any later version.
14 * GROMACS is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 * Lesser General Public License for more details.
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with GROMACS; if not, see
21 * http://www.gnu.org/licenses, or write to the Free Software Foundation,
22 * Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
24 * If you want to redistribute modifications to GROMACS, please
25 * consider that scientific software is very special. Version
26 * control is crucial - bugs must be traceable. We will be happy to
27 * consider code for inclusion in the official distribution, but
28 * derived work must not be called official GROMACS. Details are found
29 * in the README & COPYING files - if they are missing, get the
30 * official version at http://www.gromacs.org.
32 * To help us fund GROMACS development, we humbly ask that you cite
33 * the research papers on the package. Check out http://www.gromacs.org.
36 * Note: this file was generated by the GROMACS c kernel generator.
42 #include "../nb_kernel.h"
43 #include "types/simple.h"
44 #include "gromacs/math/vec.h"
48 * Gromacs nonbonded kernel: nb_kernel_ElecCSTab_VdwLJ_GeomP1P1_VF_c
49 * Electrostatics interaction: CubicSplineTable
50 * VdW interaction: LennardJones
51 * Geometry: Particle-Particle
52 * Calculate force/pot: PotentialAndForce
55 nb_kernel_ElecCSTab_VdwLJ_GeomP1P1_VF_c
56 (t_nblist * gmx_restrict nlist,
57 rvec * gmx_restrict xx,
58 rvec * gmx_restrict ff,
59 t_forcerec * gmx_restrict fr,
60 t_mdatoms * gmx_restrict mdatoms,
61 nb_kernel_data_t gmx_unused * gmx_restrict kernel_data,
62 t_nrnb * gmx_restrict nrnb)
64 int i_shift_offset,i_coord_offset,j_coord_offset;
65 int j_index_start,j_index_end;
66 int nri,inr,ggid,iidx,jidx,jnr,outeriter,inneriter;
67 real shX,shY,shZ,tx,ty,tz,fscal,rcutoff,rcutoff2;
68 int *iinr,*jindex,*jjnr,*shiftidx,*gid;
69 real *shiftvec,*fshift,*x,*f;
71 real ix0,iy0,iz0,fix0,fiy0,fiz0,iq0,isai0;
73 real jx0,jy0,jz0,fjx0,fjy0,fjz0,jq0,isaj0;
74 real dx00,dy00,dz00,rsq00,rinv00,rinvsq00,r00,qq00,c6_00,c12_00,cexp1_00,cexp2_00;
75 real velec,felec,velecsum,facel,crf,krf,krf2;
78 real rinvsix,rvdw,vvdw,vvdw6,vvdw12,fvdw,fvdw6,fvdw12,vvdwsum,br,vvdwexp,sh_vdw_invrcut6;
82 real rt,vfeps,vftabscale,Y,F,Geps,Heps2,Fp,VV,FF;
90 jindex = nlist->jindex;
92 shiftidx = nlist->shift;
94 shiftvec = fr->shift_vec[0];
95 fshift = fr->fshift[0];
97 charge = mdatoms->chargeA;
100 vdwtype = mdatoms->typeA;
102 vftab = kernel_data->table_elec->data;
103 vftabscale = kernel_data->table_elec->scale;
108 /* Start outer loop over neighborlists */
109 for(iidx=0; iidx<nri; iidx++)
111 /* Load shift vector for this list */
112 i_shift_offset = DIM*shiftidx[iidx];
113 shX = shiftvec[i_shift_offset+XX];
114 shY = shiftvec[i_shift_offset+YY];
115 shZ = shiftvec[i_shift_offset+ZZ];
117 /* Load limits for loop over neighbors */
118 j_index_start = jindex[iidx];
119 j_index_end = jindex[iidx+1];
121 /* Get outer coordinate index */
123 i_coord_offset = DIM*inr;
125 /* Load i particle coords and add shift vector */
126 ix0 = shX + x[i_coord_offset+DIM*0+XX];
127 iy0 = shY + x[i_coord_offset+DIM*0+YY];
128 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
134 /* Load parameters for i particles */
135 iq0 = facel*charge[inr+0];
136 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
138 /* Reset potential sums */
142 /* Start inner kernel loop */
143 for(jidx=j_index_start; jidx<j_index_end; jidx++)
145 /* Get j neighbor index, and coordinate index */
147 j_coord_offset = DIM*jnr;
149 /* load j atom coordinates */
150 jx0 = x[j_coord_offset+DIM*0+XX];
151 jy0 = x[j_coord_offset+DIM*0+YY];
152 jz0 = x[j_coord_offset+DIM*0+ZZ];
154 /* Calculate displacement vector */
159 /* Calculate squared distance and things based on it */
160 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
162 rinv00 = gmx_invsqrt(rsq00);
164 rinvsq00 = rinv00*rinv00;
166 /* Load parameters for j particles */
168 vdwjidx0 = 2*vdwtype[jnr+0];
170 /**************************
171 * CALCULATE INTERACTIONS *
172 **************************/
177 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
178 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
180 /* Calculate table index by multiplying r with table scale and truncate to integer */
186 /* CUBIC SPLINE TABLE ELECTROSTATICS */
189 Geps = vfeps*vftab[vfitab+2];
190 Heps2 = vfeps*vfeps*vftab[vfitab+3];
194 FF = Fp+Geps+2.0*Heps2;
195 felec = -qq00*FF*vftabscale*rinv00;
197 /* LENNARD-JONES DISPERSION/REPULSION */
199 rinvsix = rinvsq00*rinvsq00*rinvsq00;
200 vvdw6 = c6_00*rinvsix;
201 vvdw12 = c12_00*rinvsix*rinvsix;
202 vvdw = vvdw12*(1.0/12.0) - vvdw6*(1.0/6.0);
203 fvdw = (vvdw12-vvdw6)*rinvsq00;
205 /* Update potential sums from outer loop */
211 /* Calculate temporary vectorial force */
216 /* Update vectorial force */
220 f[j_coord_offset+DIM*0+XX] -= tx;
221 f[j_coord_offset+DIM*0+YY] -= ty;
222 f[j_coord_offset+DIM*0+ZZ] -= tz;
224 /* Inner loop uses 55 flops */
226 /* End of innermost loop */
229 f[i_coord_offset+DIM*0+XX] += fix0;
230 f[i_coord_offset+DIM*0+YY] += fiy0;
231 f[i_coord_offset+DIM*0+ZZ] += fiz0;
235 fshift[i_shift_offset+XX] += tx;
236 fshift[i_shift_offset+YY] += ty;
237 fshift[i_shift_offset+ZZ] += tz;
240 /* Update potential energies */
241 kernel_data->energygrp_elec[ggid] += velecsum;
242 kernel_data->energygrp_vdw[ggid] += vvdwsum;
244 /* Increment number of inner iterations */
245 inneriter += j_index_end - j_index_start;
247 /* Outer loop uses 15 flops */
250 /* Increment number of outer iterations */
253 /* Update outer/inner flops */
255 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_VF,outeriter*15 + inneriter*55);
258 * Gromacs nonbonded kernel: nb_kernel_ElecCSTab_VdwLJ_GeomP1P1_F_c
259 * Electrostatics interaction: CubicSplineTable
260 * VdW interaction: LennardJones
261 * Geometry: Particle-Particle
262 * Calculate force/pot: Force
265 nb_kernel_ElecCSTab_VdwLJ_GeomP1P1_F_c
266 (t_nblist * gmx_restrict nlist,
267 rvec * gmx_restrict xx,
268 rvec * gmx_restrict ff,
269 t_forcerec * gmx_restrict fr,
270 t_mdatoms * gmx_restrict mdatoms,
271 nb_kernel_data_t gmx_unused * gmx_restrict kernel_data,
272 t_nrnb * gmx_restrict nrnb)
274 int i_shift_offset,i_coord_offset,j_coord_offset;
275 int j_index_start,j_index_end;
276 int nri,inr,ggid,iidx,jidx,jnr,outeriter,inneriter;
277 real shX,shY,shZ,tx,ty,tz,fscal,rcutoff,rcutoff2;
278 int *iinr,*jindex,*jjnr,*shiftidx,*gid;
279 real *shiftvec,*fshift,*x,*f;
281 real ix0,iy0,iz0,fix0,fiy0,fiz0,iq0,isai0;
283 real jx0,jy0,jz0,fjx0,fjy0,fjz0,jq0,isaj0;
284 real dx00,dy00,dz00,rsq00,rinv00,rinvsq00,r00,qq00,c6_00,c12_00,cexp1_00,cexp2_00;
285 real velec,felec,velecsum,facel,crf,krf,krf2;
288 real rinvsix,rvdw,vvdw,vvdw6,vvdw12,fvdw,fvdw6,fvdw12,vvdwsum,br,vvdwexp,sh_vdw_invrcut6;
292 real rt,vfeps,vftabscale,Y,F,Geps,Heps2,Fp,VV,FF;
300 jindex = nlist->jindex;
302 shiftidx = nlist->shift;
304 shiftvec = fr->shift_vec[0];
305 fshift = fr->fshift[0];
307 charge = mdatoms->chargeA;
308 nvdwtype = fr->ntype;
310 vdwtype = mdatoms->typeA;
312 vftab = kernel_data->table_elec->data;
313 vftabscale = kernel_data->table_elec->scale;
318 /* Start outer loop over neighborlists */
319 for(iidx=0; iidx<nri; iidx++)
321 /* Load shift vector for this list */
322 i_shift_offset = DIM*shiftidx[iidx];
323 shX = shiftvec[i_shift_offset+XX];
324 shY = shiftvec[i_shift_offset+YY];
325 shZ = shiftvec[i_shift_offset+ZZ];
327 /* Load limits for loop over neighbors */
328 j_index_start = jindex[iidx];
329 j_index_end = jindex[iidx+1];
331 /* Get outer coordinate index */
333 i_coord_offset = DIM*inr;
335 /* Load i particle coords and add shift vector */
336 ix0 = shX + x[i_coord_offset+DIM*0+XX];
337 iy0 = shY + x[i_coord_offset+DIM*0+YY];
338 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
344 /* Load parameters for i particles */
345 iq0 = facel*charge[inr+0];
346 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
348 /* Start inner kernel loop */
349 for(jidx=j_index_start; jidx<j_index_end; jidx++)
351 /* Get j neighbor index, and coordinate index */
353 j_coord_offset = DIM*jnr;
355 /* load j atom coordinates */
356 jx0 = x[j_coord_offset+DIM*0+XX];
357 jy0 = x[j_coord_offset+DIM*0+YY];
358 jz0 = x[j_coord_offset+DIM*0+ZZ];
360 /* Calculate displacement vector */
365 /* Calculate squared distance and things based on it */
366 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
368 rinv00 = gmx_invsqrt(rsq00);
370 rinvsq00 = rinv00*rinv00;
372 /* Load parameters for j particles */
374 vdwjidx0 = 2*vdwtype[jnr+0];
376 /**************************
377 * CALCULATE INTERACTIONS *
378 **************************/
383 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
384 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
386 /* Calculate table index by multiplying r with table scale and truncate to integer */
392 /* CUBIC SPLINE TABLE ELECTROSTATICS */
394 Geps = vfeps*vftab[vfitab+2];
395 Heps2 = vfeps*vfeps*vftab[vfitab+3];
397 FF = Fp+Geps+2.0*Heps2;
398 felec = -qq00*FF*vftabscale*rinv00;
400 /* LENNARD-JONES DISPERSION/REPULSION */
402 rinvsix = rinvsq00*rinvsq00*rinvsq00;
403 fvdw = (c12_00*rinvsix-c6_00)*rinvsix*rinvsq00;
407 /* Calculate temporary vectorial force */
412 /* Update vectorial force */
416 f[j_coord_offset+DIM*0+XX] -= tx;
417 f[j_coord_offset+DIM*0+YY] -= ty;
418 f[j_coord_offset+DIM*0+ZZ] -= tz;
420 /* Inner loop uses 46 flops */
422 /* End of innermost loop */
425 f[i_coord_offset+DIM*0+XX] += fix0;
426 f[i_coord_offset+DIM*0+YY] += fiy0;
427 f[i_coord_offset+DIM*0+ZZ] += fiz0;
431 fshift[i_shift_offset+XX] += tx;
432 fshift[i_shift_offset+YY] += ty;
433 fshift[i_shift_offset+ZZ] += tz;
435 /* Increment number of inner iterations */
436 inneriter += j_index_end - j_index_start;
438 /* Outer loop uses 13 flops */
441 /* Increment number of outer iterations */
444 /* Update outer/inner flops */
446 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_F,outeriter*13 + inneriter*46);