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

Cleaned up the changes in Device and the base class of the pair styles

This commit is contained in:
Trung Nguyen 2019-04-17 00:09:49 -05:00
parent c55009a0ac
commit 1f43efc111
8 changed files with 45 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/gpu/lal_base_atomic.cpp
View File

@ -64,15 +64,12 @@ int BaseAtomicT::init_atomic(const int nlocal, const int nall,
} else
_nbor_data=&(nbor->dev_nbor);
int success=device->init(*ans,false,false,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,false,
_threads_per_atom);
int success=device->init(*ans,false,false,nlocal,nall,maxspecial);
if (success!=0)
return success;
success = device->init_nbor(nbor,nlocal,host_nlocal,nall,maxspecial,_gpu_host,
max_nbors,cell_size,false,_threads_per_atom);
if (success!=0)
return success;

5
lib/gpu/lal_base_charge.cpp
View File

@ -65,15 +65,12 @@ int BaseChargeT::init_atomic(const int nlocal, const int nall,
} else
_nbor_data=&(nbor->dev_nbor);
int success=device->init(*ans,true,false,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,false,
_threads_per_atom);
int success=device->init(*ans,true,false,nlocal,nall,maxspecial);
if (success!=0)
return success;
success = device->init_nbor(nbor,nlocal,host_nlocal,nall,maxspecial,_gpu_host,
max_nbors,cell_size,false,_threads_per_atom);
if (success!=0)
return success;

5
lib/gpu/lal_base_dipole.cpp
View File

@ -66,15 +66,12 @@ int BaseDipoleT::init_atomic(const int nlocal, const int nall,
} else
_nbor_data=&(nbor->dev_nbor);
int success=device->init(*ans,true,true,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,false,
_threads_per_atom);
int success=device->init(*ans,true,true,nlocal,nall,maxspecial);
if (success!=0)
return success;
success = device->init_nbor(nbor,nlocal,host_nlocal,nall,maxspecial,_gpu_host,
max_nbors,cell_size,false,_threads_per_atom);
if (success!=0)
return success;

4
lib/gpu/lal_base_dpd.cpp
View File

@ -65,9 +65,7 @@ int BaseDPDT::init_atomic(const int nlocal, const int nall,
} else
_nbor_data=&(nbor->dev_nbor);
int success=device->init(*ans,false,false,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,false,
_threads_per_atom,true);
int success=device->init(*ans,false,false,nlocal,nall,maxspecial,true);
if (success!=0)
return success;

9
lib/gpu/lal_base_ellipsoid.cpp
View File

@ -71,12 +71,15 @@ int BaseEllipsoidT::init_base(const int nlocal, const int nall,
_threads_per_atom=device->threads_per_atom();
int success=device->init(*ans,false,true,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,true,
1);
int success=device->init(*ans,false,true,nlocal,nall,maxspecial);
if (success!=0)
return success;
success = device->init_nbor(nbor,nlocal,host_nlocal,nall,maxspecial,_gpu_host,
max_nbors,cell_size,true,1);
if (success!=0)
return success;
ucl_device=device->gpu;
atom=&device->atom;

5
lib/gpu/lal_base_three.cpp
View File

@ -78,15 +78,12 @@ int BaseThreeT::init_three(const int nlocal, const int nall,
if (_threads_per_atom*_threads_per_atom>device->warp_size())
return -10;
int success=device->init(*ans,false,false,nlocal,host_nlocal,nall,nbor,
maxspecial,_gpu_host,max_nbors,cell_size,false,
_threads_per_atom);
int success=device->init(*ans,false,false,nlocal,nall,maxspecial);
if (success!=0)
return success;
success = device->init_nbor(nbor,nlocal,host_nlocal,nall,maxspecial,_gpu_host,
max_nbors,cell_size,false,_threads_per_atom);
if (success!=0)
return success;

7
lib/gpu/lal_device.cpp
View File

@ -246,11 +246,8 @@ int DeviceT::set_ocl_params(char *ocl_vendor) {
template <class numtyp, class acctyp>
int DeviceT::init(Answer<numtyp,acctyp> &ans, const bool charge,
const bool rot, const int nlocal,
const int host_nlocal, const int nall,
Neighbor *nbor, const int maxspecial,
const int gpu_host, const int max_nbors,
const double cell_size, const bool pre_cut,
const int threads_per_atom, const bool vel) {
const int nall, const int maxspecial,
const bool vel) {
if (!_device_init)
return -1;
if (sizeof(acctyp)==sizeof(double) && gpu->double_precision()==false)

53
lib/gpu/lal_device.h
View File

@ -53,8 +53,38 @@ class Device {
const int t_per_atom, const double cell_size,
char *vendor_string, const int block_pair);
/// Initialize the device for Atom and Neighbor storage
/** \param rot True if quaternions need to be stored
/// Initialize the device for Atom storage
/** \param charge True if charges need to be stored
* \param rot True if quaternions need to be stored
* \param nlocal Total number of local particles to allocate memory for
* \param host_nlocal Initial number of host particles to allocate memory for
* \param nall Total number of local+ghost particles
*
* Returns:
* - 0 if successfull
* - -1 if fix gpu not found
* - -3 if there is an out of memory error
* - -4 if the GPU library was not compiled for GPU
* - -5 Double precision is not supported on card **/
int init(Answer<numtyp,acctyp> &a, const bool charge, const bool rot,
const int nlocal, const int nall, const int maxspecial,
const bool vel=false);
/// Initialize the device for Atom storage only
/** \param nlocal Total number of local particles to allocate memory for
* \param nall Total number of local+ghost particles
*
* Returns:
* - 0 if successfull
* - -1 if fix gpu not found
* - -3 if there is an out of memory error
* - -4 if the GPU library was not compiled for GPU
* - -5 Double precision is not supported on card **/
int init(Answer<numtyp,acctyp> &ans, const int nlocal, const int nall);
/// Initialize neighbor list storage and build
/** \param charge True if charges need to be stored
* \param rot True if quaternions need to be stored
* \param nlocal Total number of local particles to allocate memory for
* \param host_nlocal Initial number of host particles to allocate memory for
* \param nall Total number of local+ghost particles
@ -73,25 +103,6 @@ class Device {
* - -3 if there is an out of memory error
* - -4 if the GPU library was not compiled for GPU
* - -5 Double precision is not supported on card **/
int init(Answer<numtyp,acctyp> &a, const bool charge, const bool rot,
const int nlocal, const int host_nlocal, const int nall,
Neighbor *nbor, const int maxspecial, const int gpu_host,
const int max_nbors, const double cell_size, const bool pre_cut,
const int threads_per_atom, const bool vel=false);
/// Initialize the device for Atom storage only
/** \param nlocal Total number of local particles to allocate memory for
* \param nall Total number of local+ghost particles
*
* Returns:
* - 0 if successfull
* - -1 if fix gpu not found
* - -3 if there is an out of memory error
* - -4 if the GPU library was not compiled for GPU
* - -5 Double precision is not supported on card **/
int init(Answer<numtyp,acctyp> &ans, const int nlocal, const int nall);
/// Initialize neighbor list build -- callback function from pair
int init_nbor(Neighbor *nbor, const int nlocal,
const int host_nlocal, const int nall,
const int maxspecial, const int gpu_host,