portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-16 23:07:05 +01:00
Code Releases Activity

Systematise the accelerator primitives and locate to Grid/threads/Accelerator.h / Accelerator.cc

Browse Source 
Aim to reduce the amount of cuda and other code variations floating around all over the place.

Will move GpuInit iinto Accelerator.cc from Init.cc
Need to worry about SharedMemoryMPI.cc and the Peer2Peer windows
This commit is contained in:
Peter Boyle
2020-05-08 06:23:55 -07:00
parent 28a1fcaaff
commit f8b8e00090
13 changed files with 557 additions and 718 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
Grid/lattice/Lattice_rng.h
View File

@ -461,8 +461,8 @@ public:
}
{
// Obtain one reseeded generator per thread
int Nthread = GridThread::GetThreads();
// Obtain one reseeded generator per thread
int Nthread = 32; // Hardwire a good level or parallelism
std::vector<RngEngine> seeders(Nthread);
for(int t=0;t<Nthread;t++){
seeders[t] = Reseed(master_engine);