Tom Deakin
c534600d04
[RAJA] Use Index_type for iterator index type instead of hardcoding int
2017-04-06 10:36:01 +01:00
Tom Deakin
5f9b288570
[RAJA] Declare pointers using RAJA_RESTRICT
2017-04-06 10:15:11 +01:00
Tom Deakin
1bd4adfe7b
[RAJA] Align the memory to 2MB pages
2017-04-06 10:14:51 +01:00
Tom Deakin
d42bcd4675
Merge remote-tracking branch 'origin/init-arrays' into devel
2016-11-04 09:17:54 +00:00
James Price
7f4761ae52
Replace write_arrays with init_arrays
...
This allows each model to initialise their arrays with a parallel
approach, which yields the first touch required for good performance
on NUMA architectures.
2016-11-02 11:22:01 +00:00
James Price
829d21c1d6
Merge branch 'master' into kernel-dot
2016-11-01 16:20:27 +00:00
James Price
3045208aae
[RAJA] Parallel first touch
2016-11-01 16:18:43 +00:00
Tom Deakin
f32cf3bad3
Merge branch 'master' into kernel-dot
...
Conflicts:
main.cpp
2016-10-24 13:53:58 +01:00
Tom Deakin
b54d94b82d
[RAJA] Use global defined scalar value
2016-10-24 13:30:55 +01:00
Tom Deakin
7408ab0366
Add RAJA dot kernel
2016-10-24 11:34:40 +01:00
Tom Deakin
31cb567e21
Switch data from 1.0, 2.0 and 3.0 to 0.1, 0.2, and 0.3 resp.
...
Using integers for maths gets unstable past 38 interations even
in double precision. Using the original values/10 is safe up to
the default 100 iterations.
2016-05-11 15:51:19 +01:00
Matthew Martineau
1a60f130eb
Fixed memory management for GPU, now working with OpenMP and CUDA
2016-05-06 13:17:04 +01:00
Matthew Martineau
45381da0b2
Initial commit of in progress developments of RAJA and KOKKOS stream
2016-05-06 10:46:35 +01:00
