(9daf5799) · Commits · 郑智淋 / lammps

src/USER-INTEL/pair_eam_intel.cpp

0 → 100644

+788 −0

File added.

Preview size limit exceeded, changes collapsed.

src/USER-INTEL/pair_eam_intel.h

0 → 100644

+107 −0

Original line number	Diff line number	Diff line
		/* -- 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 PAIR_CLASS

		PairStyle(eam/intel,PairEAMIntel)

		#else

		#ifndef LMP_PAIR_EAM_INTEL_H
		#define LMP_PAIR_EAM_INTEL_H

		#include <stdio.h>
		#include "pair_eam.h"
		#include "fix_intel.h"

		namespace LAMMPS_NS {


		class PairEAMIntel : public PairEAM {
		public:
		friend class FixSemiGrandCanonicalMC; // Alex Stukowski option

		PairEAMIntel(class LAMMPS *);
		virtual ~PairEAMIntel();
		virtual void compute(int, int);
		void init_style();
		int pack_forward_comm(int, int , double , int, int *);
		void unpack_forward_comm(int, int, double *);

		protected:

		FixIntel *fix;
		int _cop, _onetype;
		float *fp_float;

		template <class flt_t>
		int pack_forward_comm(int, int , double , flt_t *);
		template <class flt_t>
		void unpack_forward_comm(int, int, double , flt_t );

		template <class flt_t> class ForceConst;
		template <class flt_t, class acc_t>
		void compute(int eflag, int vflag, IntelBuffers<flt_t,acc_t> *buffers,
		const ForceConst<flt_t> &fc);
		template <int ONETYPE, int EVFLAG, int EFLAG, int NEWTON_PAIR, class flt_t,
		class acc_t>
		void eval(const int offload, const int vflag,
		IntelBuffers<flt_t,acc_t> * buffers,
		const ForceConst<flt_t> &fc, const int astart, const int aend);

		template <class flt_t, class acc_t>
		void pack_force_const(ForceConst<flt_t> &fc,
		IntelBuffers<flt_t, acc_t> *buffers);

		// ----------------------------------------------------------------------

		template <class flt_t>
		class ForceConst {
		public:
		typedef struct { flt_t a, b, c, d; } fc_packed1;
		typedef struct { flt_t a, b, c, d, e, f, g, h; } fc_packed2;

		flt_t **scale_f;
		fc_packed1 rhor_spline_f, rhor_spline_e;
		fc_packed1 frho_spline_f, frho_spline_e;
		fc_packed2 *z2r_spline_t;

		ForceConst() : _ntypes(0), _nr(0) {}
		~ForceConst() { set_ntypes(0, 0, 0, NULL, _cop); }

		void set_ntypes(const int ntypes, const int nr, const int nrho,
		Memory *memory, const int cop);
		inline int rhor_jstride() const { return _nr; }
		inline int rhor_istride() const { return _nr * _ntypes; }
		inline int frho_stride() const { return _nrho; }

		private:
		int _ntypes, _nr, _nrho, _cop;
		Memory *_memory;
		};
		ForceConst<float> force_const_single;
		ForceConst<double> force_const_double;
		};

		}

		#endif
		#endif

		/* ERROR/WARNING messages:

		E: The 'package intel' command is required for /intel styles

		Self-explanatory.

		*/

src/USER-INTEL/pair_lj_charmm_coul_long_intel.cpp

+132 −96

Original line number	Diff line number	Diff line
		@@ -171,6 +171,15 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		const int ntypes = atom->ntypes + 1;
		const int eatom = this->eflag_atom;

		flt_t * _noalias const ccachex = buffers->get_ccachex();
		flt_t * _noalias const ccachey = buffers->get_ccachey();
		flt_t * _noalias const ccachez = buffers->get_ccachez();
		flt_t * _noalias const ccachew = buffers->get_ccachew();
		int * _noalias const ccachei = buffers->get_ccachei();
		int * _noalias const ccachej = buffers->get_ccachej();
		const int ccache_stride = _ccache_stride;


		// Determine how much data to transfer
		int x_size, q_size, f_stride, ev_size, separate_flag;
		IP_PRE_get_transfern(ago, NEWTON_PAIR, EVFLAG, EFLAG, vflag,
		@@ -208,8 +217,10 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		in(x:length(x_size) alloc_if(0) free_if(0)) \
		in(q:length(q_size) alloc_if(0) free_if(0)) \
		in(overflow:length(0) alloc_if(0) free_if(0)) \
		in(nthreads,qqrd2e,g_ewald,inum,nall,ntypes,cut_coulsq,vflag,eatom) \
		in(f_stride,separate_flag,offload) \
		in(ccachex,ccachey,ccachez,ccachew:length(0) alloc_if(0) free_if(0)) \
		in(ccachei,ccachej:length(0) alloc_if(0) free_if(0)) \
		in(ccache_stride,nthreads,qqrd2e,g_ewald,inum,nall,ntypes,cut_coulsq) \
		in(vflag,eatom,f_stride,separate_flag,offload) \
		in(astart,cut_ljsq,cut_lj_innersq,nlocal,inv_denom_lj,minlocal) \
		out(f_start:length(f_stride) alloc_if(0) free_if(0)) \
		out(ev_global:length(ev_size) alloc_if(0) free_if(0)) \
		@@ -246,6 +257,14 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		memset(f + minlocal, 0, f_stride * sizeof(FORCE_T));
		flt_t cutboth = cut_coulsq;

		const int toffs = tid * ccache_stride;
		flt_t * _noalias const tdelx = ccachex + toffs;
		flt_t * _noalias const tdely = ccachey + toffs;
		flt_t * _noalias const tdelz = ccachez + toffs;
		flt_t * _noalias const trsq = ccachew + toffs;
		int * _noalias const tj = ccachei + toffs;
		int * _noalias const tjtype = ccachej + toffs;

		for (int i = iifrom; i < iito; ++i) {
		// const int i = ilist[ii];
		const int itype = x[i].w;
		@@ -270,28 +289,44 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		if (vflag==1) sv0 = sv1 = sv2 = sv3 = sv4 = sv5 = (acc_t)0;
		}

		int ej = 0;
		#if defined(LMP_SIMD_COMPILER)
		#pragma vector aligned
		#pragma simd reduction(+:fxtmp, fytmp, fztmp, fwtmp, sevdwl, secoul, \
		sv0, sv1, sv2, sv3, sv4, sv5)
		#pragma ivdep
		#endif
		for (int jj = 0; jj < jnum; jj++) {
		flt_t forcecoul, forcelj, evdwl, ecoul;
		forcecoul = forcelj = evdwl = ecoul = (flt_t)0.0;

		const int sbindex = jlist[jj] >> SBBITS & 3;
		const int j = jlist[jj] & NEIGHMASK;

		const flt_t delx = xtmp - x[j].x;
		const flt_t dely = ytmp - x[j].y;
		const flt_t delz = ztmp - x[j].z;
		const int jtype = x[j].w;
		const flt_t rsq = delx * delx + dely * dely + delz * delz;
		const flt_t r2inv = (flt_t)1.0 / rsq;

		#ifdef INTEL_VMASK
		if (rsq < cut_coulsq) {
		trsq[ej]=rsq;
		tdelx[ej]=delx;
		tdely[ej]=dely;
		tdelz[ej]=delz;
		tjtype[ej]=x[j].w;
		tj[ej]=jlist[jj];
		ej++;
		}
		}

		#if defined(LMP_SIMD_COMPILER)
		#pragma vector aligned
		#pragma simd reduction(+:fxtmp, fytmp, fztmp, fwtmp, sevdwl, secoul, \
		sv0, sv1, sv2, sv3, sv4, sv5)
		#endif
		for (int jj = 0; jj < ej; jj++) {
		flt_t forcecoul, forcelj, evdwl, ecoul;
		forcecoul = forcelj = evdwl = ecoul = (flt_t)0.0;

		const int j = tj[jj] & NEIGHMASK;
		const int sbindex = tj[jj] >> SBBITS & 3;
		const int jtype = tjtype[jj];
		const flt_t rsq = trsq[jj];
		const flt_t r2inv = (flt_t)1.0 / rsq;

		#ifdef INTEL_ALLOW_TABLE
		if (!ncoultablebits \|\| rsq <= tabinnersq) {
		#endif
		@@ -341,9 +376,6 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		}
		}
		#endif
		#ifdef INTEL_VMASK
		}
		#endif

		#ifdef INTEL_VMASK
		if (rsq < cut_ljsq) {
		@@ -393,9 +425,9 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		if (rsq > cut_ljsq) { forcelj = (flt_t)0.0; evdwl = (flt_t)0.0; }
		#endif

		#ifdef INTEL_VMASK
		if (rsq < cut_coulsq) {
		#endif
		const flt_t delx = tdelx[jj];
		const flt_t dely = tdely[jj];
		const flt_t delz = tdelz[jj];
		const flt_t fpair = (forcecoul + forcelj) * r2inv;
		fxtmp += delx * fpair;
		fytmp += dely * fpair;
		@@ -427,9 +459,6 @@ void PairLJCharmmCoulLongIntel::eval(const int offload, const int vflag,
		IP_PRE_ev_tally_nbor(vflag, ev_pre, fpair,
		delx, dely, delz);
		}
		#ifdef INTEL_VMASK
		}
		#endif
		} // for jj
		f[i].x += fxtmp;
		f[i].y += fytmp;
		@@ -517,6 +546,13 @@ void PairLJCharmmCoulLongIntel::pack_force_const(ForceConst<flt_t> &fc,
		if (ncoultablebits)
		for (int i = 0; i < ncoultablebits; i++) ntable *= 2;

		int off_ccache = 0;
		#ifdef _LMP_INTEL_OFFLOAD
		if (_cop >= 0) off_ccache = 1;
		#endif
		buffers->grow_ccache(off_ccache, comm->nthreads, 1);
		_ccache_stride = buffers->ccache_stride();

		fc.set_ntypes(tp1, ntable, memory, _cop);
		buffers->set_ntypes(tp1);
		flt_t **cutneighsq = buffers->get_cutneighsq();

src/USER-INTEL/pair_lj_charmm_coul_long_intel.h

+1 −1

Original line number	Diff line number	Diff line
		@@ -42,7 +42,7 @@ class PairLJCharmmCoulLongIntel : public PairLJCharmmCoulLong {

		private:
		FixIntel *fix;
		int _cop, _lrt;
		int _cop, _lrt, _ccache_stride;

		template <class flt_t> class ForceConst;
		template <class flt_t, class acc_t>

Admin message