portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2024-11-13 01:05:36 +00:00
Code Releases Activity

GPU clean up, remove parallel_for. Split into accelerator_loop, thread_loop

Browse Source 
cases, and collides with parallel_for in thrust
This commit is contained in:
Peter Boyle 2019-01-01 15:06:46 +00:00
parent 9d866d062a
commit 8c91e82ee8
2 changed files with 0 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Grid/tensors/Tensor_inner.h
View File

@ -117,7 +117,6 @@ auto innerProduct (const iMatrix<l,N>& lhs,const iMatrix<r,N>& rhs) -> iScalar<d
{ {
typedef decltype(innerProduct(lhs._internal[0][0],rhs._internal[0][0])) ret_t; typedef decltype(innerProduct(lhs._internal[0][0],rhs._internal[0][0])) ret_t;
iScalar<ret_t> ret; iScalar<ret_t> ret;
iScalar<ret_t> tmp;
ret=Zero(); ret=Zero();
for(int c1=0;c1<N;c1++){ for(int c1=0;c1<N;c1++){
for(int c2=0;c2<N;c2++){ for(int c2=0;c2<N;c2++){

28
Grid/threads/Pragmas.h
View File

@ -46,34 +46,6 @@ Author: paboyle <paboyle@ph.ed.ac.uk>
#define UNROLL _Pragma("unroll") #define UNROLL _Pragma("unroll")
//////////////////////////////////////////////////////////////////////////////////
// Old primitives; shortly deprecate
//////////////////////////////////////////////////////////////////////////////////
#ifdef GRID_OMP
#define PARALLEL_FOR_LOOP _Pragma("omp parallel for schedule(static)")
#define PARALLEL_FOR_LOOP_INTERN _Pragma("omp for schedule(static)")
#define PARALLEL_NESTED_LOOP2 _Pragma("omp parallel for collapse(2)")
#define PARALLEL_NESTED_LOOP5 _Pragma("omp parallel for collapse(5)")
#define PARALLEL_REGION _Pragma("omp parallel")
#define PARALLEL_CRITICAL _Pragma("omp critical")
#else
#define PARALLEL_FOR_LOOP
#define PARALLEL_FOR_LOOP_INTERN
#define PARALLEL_FOR_LOOP_REDUCE(op, var)
#define PARALLEL_NESTED_LOOP2
#define PARALLEL_NESTED_LOOP5
#define PARALLEL_REGION
#define PARALLEL_CRITICAL
#endif
#define parallel_region PARALLEL_REGION
#define parallel_for PARALLEL_FOR_LOOP for
#define parallel_for_internal PARALLEL_FOR_LOOP_INTERN for
#define parallel_for_nest2 PARALLEL_NESTED_LOOP2 for
#define parallel_for_nest5 PARALLEL_NESTED_LOOP5 for
#define parallel_critical PARALLEL_CRITICAL
////////////////////////////////////////////////////////////////////////////////// //////////////////////////////////////////////////////////////////////////////////
// New primitives; explicit host thread calls, and accelerator data parallel calls // New primitives; explicit host thread calls, and accelerator data parallel calls
////////////////////////////////////////////////////////////////////////////////// //////////////////////////////////////////////////////////////////////////////////