2 * This file is part of the GROMACS molecular simulation package.
4 * Copyright (c) 2012,2013, 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.
44 #include "../nb_kernel.h"
45 #include "types/simple.h"
50 * Gromacs nonbonded kernel: nb_kernel_ElecRF_VdwCSTab_GeomP1P1_VF_c
51 * Electrostatics interaction: ReactionField
52 * VdW interaction: CubicSplineTable
53 * Geometry: Particle-Particle
54 * Calculate force/pot: PotentialAndForce
57 nb_kernel_ElecRF_VdwCSTab_GeomP1P1_VF_c
58 (t_nblist * gmx_restrict nlist,
59 rvec * gmx_restrict xx,
60 rvec * gmx_restrict ff,
61 t_forcerec * gmx_restrict fr,
62 t_mdatoms * gmx_restrict mdatoms,
63 nb_kernel_data_t gmx_unused * gmx_restrict kernel_data,
64 t_nrnb * gmx_restrict nrnb)
66 int i_shift_offset,i_coord_offset,j_coord_offset;
67 int j_index_start,j_index_end;
68 int nri,inr,ggid,iidx,jidx,jnr,outeriter,inneriter;
69 real shX,shY,shZ,tx,ty,tz,fscal,rcutoff,rcutoff2;
70 int *iinr,*jindex,*jjnr,*shiftidx,*gid;
71 real *shiftvec,*fshift,*x,*f;
73 real ix0,iy0,iz0,fix0,fiy0,fiz0,iq0,isai0;
75 real jx0,jy0,jz0,fjx0,fjy0,fjz0,jq0,isaj0;
76 real dx00,dy00,dz00,rsq00,rinv00,rinvsq00,r00,qq00,c6_00,c12_00,cexp1_00,cexp2_00;
77 real velec,felec,velecsum,facel,crf,krf,krf2;
80 real rinvsix,rvdw,vvdw,vvdw6,vvdw12,fvdw,fvdw6,fvdw12,vvdwsum,br,vvdwexp,sh_vdw_invrcut6;
84 real rt,vfeps,vftabscale,Y,F,Geps,Heps2,Fp,VV,FF;
92 jindex = nlist->jindex;
94 shiftidx = nlist->shift;
96 shiftvec = fr->shift_vec[0];
97 fshift = fr->fshift[0];
99 charge = mdatoms->chargeA;
103 nvdwtype = fr->ntype;
105 vdwtype = mdatoms->typeA;
107 vftab = kernel_data->table_vdw->data;
108 vftabscale = kernel_data->table_vdw->scale;
113 /* Start outer loop over neighborlists */
114 for(iidx=0; iidx<nri; iidx++)
116 /* Load shift vector for this list */
117 i_shift_offset = DIM*shiftidx[iidx];
118 shX = shiftvec[i_shift_offset+XX];
119 shY = shiftvec[i_shift_offset+YY];
120 shZ = shiftvec[i_shift_offset+ZZ];
122 /* Load limits for loop over neighbors */
123 j_index_start = jindex[iidx];
124 j_index_end = jindex[iidx+1];
126 /* Get outer coordinate index */
128 i_coord_offset = DIM*inr;
130 /* Load i particle coords and add shift vector */
131 ix0 = shX + x[i_coord_offset+DIM*0+XX];
132 iy0 = shY + x[i_coord_offset+DIM*0+YY];
133 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
139 /* Load parameters for i particles */
140 iq0 = facel*charge[inr+0];
141 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
143 /* Reset potential sums */
147 /* Start inner kernel loop */
148 for(jidx=j_index_start; jidx<j_index_end; jidx++)
150 /* Get j neighbor index, and coordinate index */
152 j_coord_offset = DIM*jnr;
154 /* load j atom coordinates */
155 jx0 = x[j_coord_offset+DIM*0+XX];
156 jy0 = x[j_coord_offset+DIM*0+YY];
157 jz0 = x[j_coord_offset+DIM*0+ZZ];
159 /* Calculate displacement vector */
164 /* Calculate squared distance and things based on it */
165 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
167 rinv00 = gmx_invsqrt(rsq00);
169 rinvsq00 = rinv00*rinv00;
171 /* Load parameters for j particles */
173 vdwjidx0 = 2*vdwtype[jnr+0];
175 /**************************
176 * CALCULATE INTERACTIONS *
177 **************************/
182 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
183 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
185 /* Calculate table index by multiplying r with table scale and truncate to integer */
191 /* REACTION-FIELD ELECTROSTATICS */
192 velec = qq00*(rinv00+krf*rsq00-crf);
193 felec = qq00*(rinv00*rinvsq00-krf2);
195 /* CUBIC SPLINE TABLE DISPERSION */
199 Geps = vfeps*vftab[vfitab+2];
200 Heps2 = vfeps*vfeps*vftab[vfitab+3];
204 FF = Fp+Geps+2.0*Heps2;
207 /* CUBIC SPLINE TABLE REPULSION */
210 Geps = vfeps*vftab[vfitab+6];
211 Heps2 = vfeps*vfeps*vftab[vfitab+7];
215 FF = Fp+Geps+2.0*Heps2;
218 fvdw = -(fvdw6+fvdw12)*vftabscale*rinv00;
220 /* Update potential sums from outer loop */
226 /* Calculate temporary vectorial force */
231 /* Update vectorial force */
235 f[j_coord_offset+DIM*0+XX] -= tx;
236 f[j_coord_offset+DIM*0+YY] -= ty;
237 f[j_coord_offset+DIM*0+ZZ] -= tz;
239 /* Inner loop uses 66 flops */
241 /* End of innermost loop */
244 f[i_coord_offset+DIM*0+XX] += fix0;
245 f[i_coord_offset+DIM*0+YY] += fiy0;
246 f[i_coord_offset+DIM*0+ZZ] += fiz0;
250 fshift[i_shift_offset+XX] += tx;
251 fshift[i_shift_offset+YY] += ty;
252 fshift[i_shift_offset+ZZ] += tz;
255 /* Update potential energies */
256 kernel_data->energygrp_elec[ggid] += velecsum;
257 kernel_data->energygrp_vdw[ggid] += vvdwsum;
259 /* Increment number of inner iterations */
260 inneriter += j_index_end - j_index_start;
262 /* Outer loop uses 15 flops */
265 /* Increment number of outer iterations */
268 /* Update outer/inner flops */
270 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_VF,outeriter*15 + inneriter*66);
273 * Gromacs nonbonded kernel: nb_kernel_ElecRF_VdwCSTab_GeomP1P1_F_c
274 * Electrostatics interaction: ReactionField
275 * VdW interaction: CubicSplineTable
276 * Geometry: Particle-Particle
277 * Calculate force/pot: Force
280 nb_kernel_ElecRF_VdwCSTab_GeomP1P1_F_c
281 (t_nblist * gmx_restrict nlist,
282 rvec * gmx_restrict xx,
283 rvec * gmx_restrict ff,
284 t_forcerec * gmx_restrict fr,
285 t_mdatoms * gmx_restrict mdatoms,
286 nb_kernel_data_t gmx_unused * gmx_restrict kernel_data,
287 t_nrnb * gmx_restrict nrnb)
289 int i_shift_offset,i_coord_offset,j_coord_offset;
290 int j_index_start,j_index_end;
291 int nri,inr,ggid,iidx,jidx,jnr,outeriter,inneriter;
292 real shX,shY,shZ,tx,ty,tz,fscal,rcutoff,rcutoff2;
293 int *iinr,*jindex,*jjnr,*shiftidx,*gid;
294 real *shiftvec,*fshift,*x,*f;
296 real ix0,iy0,iz0,fix0,fiy0,fiz0,iq0,isai0;
298 real jx0,jy0,jz0,fjx0,fjy0,fjz0,jq0,isaj0;
299 real dx00,dy00,dz00,rsq00,rinv00,rinvsq00,r00,qq00,c6_00,c12_00,cexp1_00,cexp2_00;
300 real velec,felec,velecsum,facel,crf,krf,krf2;
303 real rinvsix,rvdw,vvdw,vvdw6,vvdw12,fvdw,fvdw6,fvdw12,vvdwsum,br,vvdwexp,sh_vdw_invrcut6;
307 real rt,vfeps,vftabscale,Y,F,Geps,Heps2,Fp,VV,FF;
315 jindex = nlist->jindex;
317 shiftidx = nlist->shift;
319 shiftvec = fr->shift_vec[0];
320 fshift = fr->fshift[0];
322 charge = mdatoms->chargeA;
326 nvdwtype = fr->ntype;
328 vdwtype = mdatoms->typeA;
330 vftab = kernel_data->table_vdw->data;
331 vftabscale = kernel_data->table_vdw->scale;
336 /* Start outer loop over neighborlists */
337 for(iidx=0; iidx<nri; iidx++)
339 /* Load shift vector for this list */
340 i_shift_offset = DIM*shiftidx[iidx];
341 shX = shiftvec[i_shift_offset+XX];
342 shY = shiftvec[i_shift_offset+YY];
343 shZ = shiftvec[i_shift_offset+ZZ];
345 /* Load limits for loop over neighbors */
346 j_index_start = jindex[iidx];
347 j_index_end = jindex[iidx+1];
349 /* Get outer coordinate index */
351 i_coord_offset = DIM*inr;
353 /* Load i particle coords and add shift vector */
354 ix0 = shX + x[i_coord_offset+DIM*0+XX];
355 iy0 = shY + x[i_coord_offset+DIM*0+YY];
356 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
362 /* Load parameters for i particles */
363 iq0 = facel*charge[inr+0];
364 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
366 /* Start inner kernel loop */
367 for(jidx=j_index_start; jidx<j_index_end; jidx++)
369 /* Get j neighbor index, and coordinate index */
371 j_coord_offset = DIM*jnr;
373 /* load j atom coordinates */
374 jx0 = x[j_coord_offset+DIM*0+XX];
375 jy0 = x[j_coord_offset+DIM*0+YY];
376 jz0 = x[j_coord_offset+DIM*0+ZZ];
378 /* Calculate displacement vector */
383 /* Calculate squared distance and things based on it */
384 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
386 rinv00 = gmx_invsqrt(rsq00);
388 rinvsq00 = rinv00*rinv00;
390 /* Load parameters for j particles */
392 vdwjidx0 = 2*vdwtype[jnr+0];
394 /**************************
395 * CALCULATE INTERACTIONS *
396 **************************/
401 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
402 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
404 /* Calculate table index by multiplying r with table scale and truncate to integer */
410 /* REACTION-FIELD ELECTROSTATICS */
411 felec = qq00*(rinv00*rinvsq00-krf2);
413 /* CUBIC SPLINE TABLE DISPERSION */
416 Geps = vfeps*vftab[vfitab+2];
417 Heps2 = vfeps*vfeps*vftab[vfitab+3];
419 FF = Fp+Geps+2.0*Heps2;
422 /* CUBIC SPLINE TABLE REPULSION */
424 Geps = vfeps*vftab[vfitab+6];
425 Heps2 = vfeps*vfeps*vftab[vfitab+7];
427 FF = Fp+Geps+2.0*Heps2;
429 fvdw = -(fvdw6+fvdw12)*vftabscale*rinv00;
433 /* Calculate temporary vectorial force */
438 /* Update vectorial force */
442 f[j_coord_offset+DIM*0+XX] -= tx;
443 f[j_coord_offset+DIM*0+YY] -= ty;
444 f[j_coord_offset+DIM*0+ZZ] -= tz;
446 /* Inner loop uses 53 flops */
448 /* End of innermost loop */
451 f[i_coord_offset+DIM*0+XX] += fix0;
452 f[i_coord_offset+DIM*0+YY] += fiy0;
453 f[i_coord_offset+DIM*0+ZZ] += fiz0;
457 fshift[i_shift_offset+XX] += tx;
458 fshift[i_shift_offset+YY] += ty;
459 fshift[i_shift_offset+ZZ] += tz;
461 /* Increment number of inner iterations */
462 inneriter += j_index_end - j_index_start;
464 /* Outer loop uses 13 flops */
467 /* Increment number of outer iterations */
470 /* Update outer/inner flops */
472 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_F,outeriter*13 + inneriter*53);