portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-17 23:37:06 +01:00
Code Releases Activity

Finally starting to get decent performance on Volta

Browse Source
This commit is contained in:
Peter Boyle
2018-07-13 12:06:18 -04:00
parent 2cc07450f4
commit b2b5137d28
5 changed files with 203 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
lib/simd/Grid_gpu_vec.h
View File

@ -36,7 +36,9 @@ Author: Peter Boyle <paboyle@ph.ed.ac.uk>
namespace Grid {
#define COALESCE_GRANULARITY (16) // bytes for coalesce granularity of target: Pascal, Volta
//#define COALESCE_GRANULARITY (64) // bytes for coalesce granularity of target: Pascal, Volta
//#define COALESCE_GRANULARITY (32) // bytes for coalesce granularity of target: Pascal, Volta
#define COALESCE_GRANULARITY (16) // bytes for coalesce granularity of target: Pascal, Volta
template<class pair>
class GpuComplex {