mirror of
https://github.com/paboyle/Grid.git
synced 2024-11-15 02:05:37 +00:00
88 lines
3.2 KiB
C++
88 lines
3.2 KiB
C++
/*************************************************************************************
|
|
|
|
Grid physics library, www.github.com/paboyle/Grid
|
|
|
|
Source file: ./lib/lattice/Lattice_local.h
|
|
|
|
Copyright (C) 2015
|
|
|
|
Author: Peter Boyle <paboyle@ph.ed.ac.uk>
|
|
|
|
This program is free software; you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation; either version 2 of the License, or
|
|
(at your option) any later version.
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License along
|
|
with this program; if not, write to the Free Software Foundation, Inc.,
|
|
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
|
|
See the full license in the file "LICENSE" in the top level distribution directory
|
|
*************************************************************************************/
|
|
/* END LEGAL */
|
|
#ifndef GRID_LATTICE_LOCALREDUCTION_H
|
|
#define GRID_LATTICE_LOCALREDUCTION_H
|
|
|
|
///////////////////////////////////////////////
|
|
// localInner, localNorm, outerProduct
|
|
///////////////////////////////////////////////
|
|
|
|
NAMESPACE_BEGIN(Grid);
|
|
|
|
/////////////////////////////////////////////////////
|
|
// Non site, reduced locally reduced routines
|
|
/////////////////////////////////////////////////////
|
|
|
|
// localNorm2,
|
|
template<class vobj>
|
|
inline auto localNorm2 (const Lattice<vobj> &rhs)-> Lattice<typename vobj::tensor_reduced>
|
|
{
|
|
Lattice<typename vobj::tensor_reduced> ret(rhs.Grid());
|
|
autoView( rhs_v , rhs, AcceleratorRead);
|
|
autoView( ret_v , ret, AcceleratorWrite);
|
|
accelerator_for(ss,rhs_v.size(),vobj::Nsimd(),{
|
|
coalescedWrite(ret_v[ss],innerProduct(rhs_v(ss),rhs_v(ss)));
|
|
});
|
|
return ret;
|
|
}
|
|
|
|
// localInnerProduct
|
|
template<class vobj>
|
|
inline auto localInnerProduct (const Lattice<vobj> &lhs,const Lattice<vobj> &rhs) -> Lattice<typename vobj::tensor_reduced>
|
|
{
|
|
Lattice<typename vobj::tensor_reduced> ret(rhs.Grid());
|
|
autoView( lhs_v , lhs, AcceleratorRead);
|
|
autoView( rhs_v , rhs, AcceleratorRead);
|
|
autoView( ret_v , ret, AcceleratorWrite);
|
|
accelerator_for(ss,rhs_v.size(),vobj::Nsimd(),{
|
|
coalescedWrite(ret_v[ss],innerProduct(lhs_v(ss),rhs_v(ss)));
|
|
});
|
|
return ret;
|
|
}
|
|
|
|
// outerProduct Scalar x Scalar -> Scalar
|
|
// Vector x Vector -> Matrix
|
|
template<class ll,class rr>
|
|
inline auto outerProduct (const Lattice<ll> &lhs,const Lattice<rr> &rhs) -> Lattice<decltype(outerProduct(ll(),rr()))>
|
|
{
|
|
typedef decltype(coalescedRead(ll())) sll;
|
|
typedef decltype(coalescedRead(rr())) srr;
|
|
Lattice<decltype(outerProduct(ll(),rr()))> ret(rhs.Grid());
|
|
autoView( lhs_v , lhs, AcceleratorRead);
|
|
autoView( rhs_v , rhs, AcceleratorRead);
|
|
autoView( ret_v , ret, AcceleratorWrite);
|
|
accelerator_for(ss,rhs_v.size(),1,{
|
|
// FIXME had issues with scalar version of outer
|
|
// Use vector [] operator and don't read coalesce this loop
|
|
ret_v[ss]=outerProduct(lhs_v[ss],rhs_v[ss]);
|
|
});
|
|
return ret;
|
|
}
|
|
NAMESPACE_END(Grid);
|
|
#endif
|