lammps

History

Stan Moore 1422b0413b Update Kokkos library to v2.7.00		2018-05-25 15:00:53 -06:00
..
01_hello_world	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
01_hello_world_lambda	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
02_simple_reduce	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
02_simple_reduce_lambda	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
03_simple_view	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
03_simple_view_lambda	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
04_simple_memoryspaces	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
05_simple_atomics	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
06_simple_mdrangepolicy	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
Advanced_Views	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
Algorithms	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
Hierarchical_Parallelism	Update Kokkos library to v2.7.00	2018-05-25 15:00:53 -06:00
launch_bounds	Update Kokkos library to r2.6.00	2018-03-08 10:57:08 -07:00
CMakeLists.txt	Update Kokkos to v2.04.11	2017-11-06 13:47:33 -07:00
Makefile	Update Kokkos library to v2.03.13	2017-07-31 10:34:21 -06:00
README	Updating Kokkos lib	2016-09-06 23:06:32 +00:00

README

Build the examples by typing in each directory: 
make -j 16

To specify a target device:
make openmp -j 16
make pthreads -j 16
make serial -j 16
make cuda -j 16

The lambda variants can not be build with CUDA=yes at the moment, since
CUDA does not support lambdas from the host. 
Some of the advanced topics try to highlight performance impacts by timing 
different variants of doing the same thing.
Also some of the advanced topics (in particular hierarchical parallelism)
require C++11 even with out using host side lambdas. CUDA 6.5 can be used 
to compile those.