jianmu
/
lammps
forked from lijiext/lammps
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@15080 f3b2605a-c512-4ea7-a41b-209d697bcdaa

This commit is contained in:
sjplimp 2016-05-31 16:20:32 +00:00
parent 5b94aa3ae8
commit 04e401ae4b
13 changed files with 13 additions and 106 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/GPU/fix_gpu.cpp
View File

@ -80,9 +80,6 @@ FixGPU::FixGPU(LAMMPS *lmp, int narg, char **arg) :
{
if (lmp->citeme) lmp->citeme->add(cite_gpu_package);
if (lmp->cuda)
error->all(FLERR,"Cannot use GPU package with USER-CUDA package enabled");
if (narg < 4) error->all(FLERR,"Illegal package gpu command");
int ngpu = atoi(arg[3]);

19
src/USER-OMP/fix_omp.cpp
View File

@ -45,15 +45,8 @@
#include "suffix.h"
#if defined(LMP_USER_CUDA)
#include "cuda_modify_flags.h"
#endif
using namespace LAMMPS_NS;
using namespace FixConst;
#if defined(LMP_USER_CUDA)
using namespace FixConstCuda;
#endif
static int get_tid()
{
@ -157,18 +150,6 @@ FixOMP::~FixOMP()
int FixOMP::setmask()
{
// compatibility with USER-CUDA
// our fix doesn't need any data transfer.
#if defined(LMP_USER_CUDA)
if (lmp->cuda) {
int mask = 0;
mask |= PRE_FORCE_CUDA;
mask |= PRE_FORCE_RESPA;
mask |= MIN_PRE_FORCE;
return mask;
}
#endif
int mask = 0;
mask |= PRE_FORCE;
mask |= PRE_FORCE_RESPA;

27
src/atom.cpp
View File

@ -32,7 +32,6 @@
#include "domain.h"
#include "group.h"
#include "molecule.h"
#include "accelerator_cuda.h"
#include "atom_masks.h"
#include "math_const.h"
#include "memory.h"
@ -44,7 +43,6 @@ using namespace MathConst;
#define DELTA 1
#define DELTA_MEMSTR 1024
#define EPSILON 1.0e-6
#define CUDA_CHUNK 3000
enum{LAYOUT_UNIFORM,LAYOUT_NONUNIFORM,LAYOUT_TILED}; // several files
@ -1716,10 +1714,6 @@ void Atom::sort()
nextsort = (update->ntimestep/sortfreq)*sortfreq + sortfreq;
// download data from GPU if necessary
if (lmp->cuda && !lmp->cuda->oncpu) lmp->cuda->downloadAll();
// re-setup sort bins if needed
if (domain->box_change) setup_sort_bins();
@ -1795,10 +1789,6 @@ void Atom::sort()
current[empty] = permute[empty];
}
// upload data back to GPU if necessary
if (lmp->cuda && !lmp->cuda->oncpu) lmp->cuda->uploadAll();
// sanity check that current = permute
//int flag = 0;
@ -1817,25 +1807,12 @@ void Atom::setup_sort_bins()
{
// binsize:
// user setting if explicitly set
// 1/2 of neighbor cutoff for non-CUDA
// CUDA_CHUNK atoms/proc for CUDA
// default = 1/2 of neighbor cutoff
// check if neighbor cutoff = 0.0
double binsize;
if (userbinsize > 0.0) binsize = userbinsize;
else if (!lmp->cuda) binsize = 0.5 * neighbor->cutneighmax;
else {
if (domain->dimension == 3) {
double vol = (domain->boxhi[0]-domain->boxlo[0]) *
(domain->boxhi[1]-domain->boxlo[1]) *
(domain->boxhi[2]-domain->boxlo[2]);
binsize = pow(1.0*CUDA_CHUNK/natoms*vol,1.0/3.0);
} else {
double area = (domain->boxhi[0]-domain->boxlo[0]) *
(domain->boxhi[1]-domain->boxlo[1]);
binsize = pow(1.0*CUDA_CHUNK/natoms*area,1.0/2.0);
}
}
else binsize = 0.5 * neighbor->cutneighmax;
if (binsize == 0.0) error->all(FLERR,"Atom sorting has bin size = 0.0");
double bininv = 1.0/binsize;

4
src/atom_vec.cpp
View File

@ -33,7 +33,7 @@ AtomVec::AtomVec(LAMMPS *lmp) : Pointers(lmp)
mass_type = dipole_type = 0;
forceclearflag = 0;
size_data_bonus = 0;
cudable = kokkosable = 0;
kokkosable = 0;
nargcopy = 0;
argcopy = NULL;
@ -81,8 +81,6 @@ void AtomVec::init()
deform_groupbit = domain->deform_groupbit;
h_rate = domain->h_rate;
if (lmp->cuda != NULL && !cudable)
error->all(FLERR,"USER-CUDA package requires a cuda enabled atom_style");
if (lmp->kokkos != NULL && !kokkosable)
error->all(FLERR,"KOKKOS package requires a kokkos enabled atom_style");
}

2
src/atom_vec.h
View File

@ -43,9 +43,7 @@ class AtomVec : protected Pointers {
class Molecule **onemols; // list of molecules for style template
int nset; // # of molecules in list
int cudable; // 1 if atom style is CUDA-enabled
int kokkosable; // 1 if atom style is KOKKOS-enabled
int *maxsend; // CUDA-specific variable
int nargcopy; // copy of command-line args for atom_style command
char **argcopy; // used when AtomVec is realloced (restart,replicate)

4
src/comm_tiled.cpp
View File

@ -45,8 +45,6 @@ enum{LAYOUT_UNIFORM,LAYOUT_NONUNIFORM,LAYOUT_TILED}; // several files
CommTiled::CommTiled(LAMMPS *lmp) : Comm(lmp)
{
if (lmp->cuda)
error->all(FLERR,"USER-CUDA package does not yet support comm_style tiled");
if (lmp->kokkos)
error->all(FLERR,"KOKKOS package does not yet support comm_style tiled");
@ -65,8 +63,6 @@ CommTiled::CommTiled(LAMMPS *lmp) : Comm(lmp)
//
CommTiled::CommTiled(LAMMPS *lmp, Comm *oldcomm) : Comm(*oldcomm)
{
if (lmp->cuda)
error->all(FLERR,"USER-CUDA package does not yet support comm_style tiled");
if (lmp->kokkos)
error->all(FLERR,"KOKKOS package does not yet support comm_style tiled");

5
src/info.cpp
View File

@ -17,7 +17,6 @@
#include <string.h>
#include "info.h"
#include "accelerator_cuda.h"
#include "accelerator_kokkos.h"
#include "atom.h"
#include "comm.h"
@ -476,9 +475,7 @@ bool Info::is_active(const char *category, const char *name)
const int len = strlen(name);
if (strcmp(category,"package") == 0) {
if (strcmp(name,"cuda") == 0) {
return (lmp->cuda && lmp->cuda->cuda_exists) ? true : false;
} else if (strcmp(name,"gpu") == 0) {
if (strcmp(name,"gpu") == 0) {
return (modify->find_fix("package_gpu") >= 0) ? true : false;
} else if (strcmp(name,"intel") == 0) {
return (modify->find_fix("package_intel") >= 0) ? true : false;

9
src/input.cpp
View File

@ -46,7 +46,6 @@
#include "special.h"
#include "timer.h"
#include "variable.h"
#include "accelerator_cuda.h"
#include "accelerator_kokkos.h"
#include "error.h"
#include "memory.h"
@ -1567,13 +1566,7 @@ void Input::package()
// same checks for packages existing as in LAMMPS::post_create()
// since can be invoked here by package command in input script
if (strcmp(arg[0],"cuda") == 0) {
if (lmp->cuda == NULL || lmp->cuda->cuda_exists == 0)
error->all(FLERR,
"Package cuda command without USER-CUDA package enabled");
lmp->cuda->accelerator(narg-1,&arg[1]);
} else if (strcmp(arg[0],"gpu") == 0) {
if (strcmp(arg[0],"gpu") == 0) {
if (!modify->check_package("GPU"))
error->all(FLERR,"Package gpu command without GPU package installed");

23
src/lammps.cpp
View File

@ -581,7 +581,6 @@ LAMMPS::~LAMMPS()
if (world != universe->uworld) MPI_Comm_free(&world);
delete cuda;
delete kokkos;
delete [] suffix;
delete [] suffix2;
@ -603,16 +602,13 @@ void LAMMPS::create()
// Comm class must be created before Atom class
// so that nthreads is defined when create_avec invokes grow()
if (cuda) comm = new CommCuda(this);
else if (kokkos) comm = new CommKokkos(this);
if (kokkos) comm = new CommKokkos(this);
else comm = new CommBrick(this);
if (cuda) neighbor = new NeighborCuda(this);
else if (kokkos) neighbor = new NeighborKokkos(this);
if (kokkos) neighbor = new NeighborKokkos(this);
else neighbor = new Neighbor(this);
if (cuda) domain = new DomainCuda(this);
else if (kokkos) domain = new DomainKokkos(this);
if (kokkos) domain = new DomainKokkos(this);
#ifdef LMP_USER_OMP
else domain = new DomainOMP(this);
#else
@ -630,8 +626,7 @@ void LAMMPS::create()
group = new Group(this);
force = new Force(this); // must be after group, to create temperature
if (cuda) modify = new ModifyCuda(this);
else if (kokkos) modify = new ModifyKokkos(this);
if (kokkos) modify = new ModifyKokkos(this);
else modify = new Modify(this);
output = new Output(this); // must be after group, so "all" exists
@ -651,19 +646,16 @@ void LAMMPS::create()
void LAMMPS::post_create()
{
// default package commands triggered by "-c on" and "-k on"
// default package command triggered by "-k on"
if (cuda && cuda->cuda_exists) input->one("package cuda 1");
if (kokkos && kokkos->kokkos_exists) input->one("package kokkos");
// suffix will always be set if suffix_enable = 1
// check that USER-CUDA and KOKKOS package classes were instantiated
// check that KOKKOS package classes were instantiated
// check that GPU, INTEL, USER-OMP fixes were compiled with LAMMPS
if (!suffix_enable) return;
if (strcmp(suffix,"cuda") == 0 && (cuda == NULL || cuda->cuda_exists == 0))
error->all(FLERR,"Using suffix cuda without USER-CUDA package enabled");
if (strcmp(suffix,"gpu") == 0 && !modify->check_package("GPU"))
error->all(FLERR,"Using suffix gpu without GPU package installed");
if (strcmp(suffix,"intel") == 0 && !modify->check_package("INTEL"))
@ -771,7 +763,6 @@ void LAMMPS::help()
{
fprintf(screen,
"\nCommand line options:\n\n"
"-cuda on/off : turn CUDA mode on or off (-c)\n"
"-echo none/screen/log/both : echoing of input script (-e)\n"
"-help : print this help message (-h)\n"
"-in filename : read input from file, not stdin (-i)\n"
@ -785,7 +776,7 @@ void LAMMPS::help()
"-restart rfile dfile ... : convert restart to data file (-r)\n"
"-reorder topology-specs : processor reordering (-r)\n"
"-screen none/filename : where to send screen output (-sc)\n"
"-suffix cuda/gpu/opt/omp : style suffix to apply (-sf)\n"
"-suffix gpu/intel/opt/omp : style suffix to apply (-sf)\n"
"-var varname value : set index style variable (-v)\n\n");
fprintf(screen,"Style options compiled with this executable\n\n");

1
src/lammps.h
View File

@ -50,7 +50,6 @@ class LAMMPS {
int num_package; // number of cmdline package commands
int cite_enable; // 1 if generating log.cite, 0 if disabled
class Cuda *cuda; // CUDA accelerator class
class KokkosLMP *kokkos; // KOKKOS accelerator class
class AtomKokkos *atomKK; // KOKKOS version of Atom class

7
src/output.cpp
View File

@ -30,7 +30,6 @@
#include "force.h"
#include "dump.h"
#include "write_restart.h"
#include "accelerator_cuda.h"
#include "memory.h"
#include "error.h"
@ -290,11 +289,8 @@ void Output::write(bigint ntimestep)
{
// next_dump does not force output on last step of run
// wrap dumps that invoke computes or eval of variable with clear/add
// download data from GPU if necessary
if (next_dump_any == ntimestep) {
if (lmp->cuda && !lmp->cuda->oncpu) lmp->cuda->downloadAll();
for (int idump = 0; idump < ndump; idump++) {
if (next_dump[idump] == ntimestep) {
if (dump[idump]->clearstep || every_dump[idump] == 0)
@ -321,12 +317,9 @@ void Output::write(bigint ntimestep)
// next_restart does not force output on last step of run
// for toggle = 0, replace "*" with current timestep in restart filename
// download data from GPU if necessary
// eval of variable may invoke computes so wrap with clear/add
if (next_restart == ntimestep) {
if (lmp->cuda && !lmp->cuda->oncpu) lmp->cuda->downloadAll();
if (next_restart_single == ntimestep) {
char *file = new char[strlen(restart1) + 16];
char *ptr = strchr(restart1,'*');

5
src/pair.cpp
View File

@ -34,7 +34,6 @@
#include "update.h"
#include "modify.h"
#include "compute.h"
#include "accelerator_cuda.h"
#include "suffix.h"
#include "atom_masks.h"
#include "memory.h"
@ -99,7 +98,7 @@ Pair::Pair(LAMMPS *lmp) : Pointers(lmp)
num_tally_compute = 0;
list_tally_compute = NULL;
// CUDA and KOKKOS per-fix data masks
// KOKKOS per-fix data masks
datamask = ALL_MASK;
datamask_ext = ALL_MASK;
@ -810,8 +809,6 @@ void Pair::ev_setup(int eflag, int vflag)
if (vflag_atom == 0) vflag_either = 0;
if (vflag_either == 0 && eflag_either == 0) evflag = 0;
} else vflag_fdotr = 0;
if (lmp->cuda) lmp->cuda->evsetup_eatom_vatom(eflag_atom,vflag_atom);
}
/* ----------------------------------------------------------------------

10
src/update.cpp
View File

@ -85,16 +85,6 @@ Update::~Update()
void Update::init()
{
// if USER-CUDA mode is enabled:
// integrate/minimize style must be CUDA variant
if (whichflag == 1 && lmp->cuda)
if (strstr(integrate_style,"cuda") == NULL)
error->all(FLERR,"USER-CUDA mode requires CUDA variant of run style");
if (whichflag == 2 && lmp->cuda)
if (strstr(minimize_style,"cuda") == NULL)
error->all(FLERR,"USER-CUDA mode requires CUDA variant of min style");
// init the appropriate integrate and/or minimize class
// if neither (e.g. from write_restart) then just return