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_ElecCoul_VdwCSTab_GeomP1P1_VF_c
51 * Electrostatics interaction: Coulomb
52 * VdW interaction: CubicSplineTable
53 * Geometry: Particle-Particle
54 * Calculate force/pot: PotentialAndForce
57 nb_kernel_ElecCoul_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;
100 nvdwtype = fr->ntype;
102 vdwtype = mdatoms->typeA;
104 vftab = kernel_data->table_vdw->data;
105 vftabscale = kernel_data->table_vdw->scale;
110 /* Start outer loop over neighborlists */
111 for(iidx=0; iidx<nri; iidx++)
113 /* Load shift vector for this list */
114 i_shift_offset = DIM*shiftidx[iidx];
115 shX = shiftvec[i_shift_offset+XX];
116 shY = shiftvec[i_shift_offset+YY];
117 shZ = shiftvec[i_shift_offset+ZZ];
119 /* Load limits for loop over neighbors */
120 j_index_start = jindex[iidx];
121 j_index_end = jindex[iidx+1];
123 /* Get outer coordinate index */
125 i_coord_offset = DIM*inr;
127 /* Load i particle coords and add shift vector */
128 ix0 = shX + x[i_coord_offset+DIM*0+XX];
129 iy0 = shY + x[i_coord_offset+DIM*0+YY];
130 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
136 /* Load parameters for i particles */
137 iq0 = facel*charge[inr+0];
138 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
140 /* Reset potential sums */
144 /* Start inner kernel loop */
145 for(jidx=j_index_start; jidx<j_index_end; jidx++)
147 /* Get j neighbor index, and coordinate index */
149 j_coord_offset = DIM*jnr;
151 /* load j atom coordinates */
152 jx0 = x[j_coord_offset+DIM*0+XX];
153 jy0 = x[j_coord_offset+DIM*0+YY];
154 jz0 = x[j_coord_offset+DIM*0+ZZ];
156 /* Calculate displacement vector */
161 /* Calculate squared distance and things based on it */
162 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
164 rinv00 = gmx_invsqrt(rsq00);
166 rinvsq00 = rinv00*rinv00;
168 /* Load parameters for j particles */
170 vdwjidx0 = 2*vdwtype[jnr+0];
172 /**************************
173 * CALCULATE INTERACTIONS *
174 **************************/
179 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
180 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
182 /* Calculate table index by multiplying r with table scale and truncate to integer */
188 /* COULOMB ELECTROSTATICS */
190 felec = velec*rinvsq00;
192 /* CUBIC SPLINE TABLE DISPERSION */
196 Geps = vfeps*vftab[vfitab+2];
197 Heps2 = vfeps*vfeps*vftab[vfitab+3];
201 FF = Fp+Geps+2.0*Heps2;
204 /* CUBIC SPLINE TABLE REPULSION */
207 Geps = vfeps*vftab[vfitab+6];
208 Heps2 = vfeps*vfeps*vftab[vfitab+7];
212 FF = Fp+Geps+2.0*Heps2;
215 fvdw = -(fvdw6+fvdw12)*vftabscale*rinv00;
217 /* Update potential sums from outer loop */
223 /* Calculate temporary vectorial force */
228 /* Update vectorial force */
232 f[j_coord_offset+DIM*0+XX] -= tx;
233 f[j_coord_offset+DIM*0+YY] -= ty;
234 f[j_coord_offset+DIM*0+ZZ] -= tz;
236 /* Inner loop uses 62 flops */
238 /* End of innermost loop */
241 f[i_coord_offset+DIM*0+XX] += fix0;
242 f[i_coord_offset+DIM*0+YY] += fiy0;
243 f[i_coord_offset+DIM*0+ZZ] += fiz0;
247 fshift[i_shift_offset+XX] += tx;
248 fshift[i_shift_offset+YY] += ty;
249 fshift[i_shift_offset+ZZ] += tz;
252 /* Update potential energies */
253 kernel_data->energygrp_elec[ggid] += velecsum;
254 kernel_data->energygrp_vdw[ggid] += vvdwsum;
256 /* Increment number of inner iterations */
257 inneriter += j_index_end - j_index_start;
259 /* Outer loop uses 15 flops */
262 /* Increment number of outer iterations */
265 /* Update outer/inner flops */
267 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_VF,outeriter*15 + inneriter*62);
270 * Gromacs nonbonded kernel: nb_kernel_ElecCoul_VdwCSTab_GeomP1P1_F_c
271 * Electrostatics interaction: Coulomb
272 * VdW interaction: CubicSplineTable
273 * Geometry: Particle-Particle
274 * Calculate force/pot: Force
277 nb_kernel_ElecCoul_VdwCSTab_GeomP1P1_F_c
278 (t_nblist * gmx_restrict nlist,
279 rvec * gmx_restrict xx,
280 rvec * gmx_restrict ff,
281 t_forcerec * gmx_restrict fr,
282 t_mdatoms * gmx_restrict mdatoms,
283 nb_kernel_data_t gmx_unused * gmx_restrict kernel_data,
284 t_nrnb * gmx_restrict nrnb)
286 int i_shift_offset,i_coord_offset,j_coord_offset;
287 int j_index_start,j_index_end;
288 int nri,inr,ggid,iidx,jidx,jnr,outeriter,inneriter;
289 real shX,shY,shZ,tx,ty,tz,fscal,rcutoff,rcutoff2;
290 int *iinr,*jindex,*jjnr,*shiftidx,*gid;
291 real *shiftvec,*fshift,*x,*f;
293 real ix0,iy0,iz0,fix0,fiy0,fiz0,iq0,isai0;
295 real jx0,jy0,jz0,fjx0,fjy0,fjz0,jq0,isaj0;
296 real dx00,dy00,dz00,rsq00,rinv00,rinvsq00,r00,qq00,c6_00,c12_00,cexp1_00,cexp2_00;
297 real velec,felec,velecsum,facel,crf,krf,krf2;
300 real rinvsix,rvdw,vvdw,vvdw6,vvdw12,fvdw,fvdw6,fvdw12,vvdwsum,br,vvdwexp,sh_vdw_invrcut6;
304 real rt,vfeps,vftabscale,Y,F,Geps,Heps2,Fp,VV,FF;
312 jindex = nlist->jindex;
314 shiftidx = nlist->shift;
316 shiftvec = fr->shift_vec[0];
317 fshift = fr->fshift[0];
319 charge = mdatoms->chargeA;
320 nvdwtype = fr->ntype;
322 vdwtype = mdatoms->typeA;
324 vftab = kernel_data->table_vdw->data;
325 vftabscale = kernel_data->table_vdw->scale;
330 /* Start outer loop over neighborlists */
331 for(iidx=0; iidx<nri; iidx++)
333 /* Load shift vector for this list */
334 i_shift_offset = DIM*shiftidx[iidx];
335 shX = shiftvec[i_shift_offset+XX];
336 shY = shiftvec[i_shift_offset+YY];
337 shZ = shiftvec[i_shift_offset+ZZ];
339 /* Load limits for loop over neighbors */
340 j_index_start = jindex[iidx];
341 j_index_end = jindex[iidx+1];
343 /* Get outer coordinate index */
345 i_coord_offset = DIM*inr;
347 /* Load i particle coords and add shift vector */
348 ix0 = shX + x[i_coord_offset+DIM*0+XX];
349 iy0 = shY + x[i_coord_offset+DIM*0+YY];
350 iz0 = shZ + x[i_coord_offset+DIM*0+ZZ];
356 /* Load parameters for i particles */
357 iq0 = facel*charge[inr+0];
358 vdwioffset0 = 2*nvdwtype*vdwtype[inr+0];
360 /* Start inner kernel loop */
361 for(jidx=j_index_start; jidx<j_index_end; jidx++)
363 /* Get j neighbor index, and coordinate index */
365 j_coord_offset = DIM*jnr;
367 /* load j atom coordinates */
368 jx0 = x[j_coord_offset+DIM*0+XX];
369 jy0 = x[j_coord_offset+DIM*0+YY];
370 jz0 = x[j_coord_offset+DIM*0+ZZ];
372 /* Calculate displacement vector */
377 /* Calculate squared distance and things based on it */
378 rsq00 = dx00*dx00+dy00*dy00+dz00*dz00;
380 rinv00 = gmx_invsqrt(rsq00);
382 rinvsq00 = rinv00*rinv00;
384 /* Load parameters for j particles */
386 vdwjidx0 = 2*vdwtype[jnr+0];
388 /**************************
389 * CALCULATE INTERACTIONS *
390 **************************/
395 c6_00 = vdwparam[vdwioffset0+vdwjidx0];
396 c12_00 = vdwparam[vdwioffset0+vdwjidx0+1];
398 /* Calculate table index by multiplying r with table scale and truncate to integer */
404 /* COULOMB ELECTROSTATICS */
406 felec = velec*rinvsq00;
408 /* CUBIC SPLINE TABLE DISPERSION */
411 Geps = vfeps*vftab[vfitab+2];
412 Heps2 = vfeps*vfeps*vftab[vfitab+3];
414 FF = Fp+Geps+2.0*Heps2;
417 /* CUBIC SPLINE TABLE REPULSION */
419 Geps = vfeps*vftab[vfitab+6];
420 Heps2 = vfeps*vfeps*vftab[vfitab+7];
422 FF = Fp+Geps+2.0*Heps2;
424 fvdw = -(fvdw6+fvdw12)*vftabscale*rinv00;
428 /* Calculate temporary vectorial force */
433 /* Update vectorial force */
437 f[j_coord_offset+DIM*0+XX] -= tx;
438 f[j_coord_offset+DIM*0+YY] -= ty;
439 f[j_coord_offset+DIM*0+ZZ] -= tz;
441 /* Inner loop uses 53 flops */
443 /* End of innermost loop */
446 f[i_coord_offset+DIM*0+XX] += fix0;
447 f[i_coord_offset+DIM*0+YY] += fiy0;
448 f[i_coord_offset+DIM*0+ZZ] += fiz0;
452 fshift[i_shift_offset+XX] += tx;
453 fshift[i_shift_offset+YY] += ty;
454 fshift[i_shift_offset+ZZ] += tz;
456 /* Increment number of inner iterations */
457 inneriter += j_index_end - j_index_start;
459 /* Outer loop uses 13 flops */
462 /* Increment number of outer iterations */
465 /* Update outer/inner flops */
467 inc_nrnb(nrnb,eNR_NBKERNEL_ELEC_VDW_F,outeriter*13 + inneriter*53);