|
|
538e64e5b4
|
Cleaning up the CG reproduciblity test. More info reported
|
2016-12-08 05:50:40 +00:00 |
|
|
|
791cb050c8
|
Comms improvements
|
2016-11-01 11:35:43 +00:00 |
|
|
|
09f66100d3
|
MPI 3 compile on non-linux
|
2016-10-25 06:01:12 +01:00 |
|
|
|
b94478fa51
|
mpi, mpi3, shmem all compile.
mpi, mpi3 pass single node multi-rank
|
2016-10-24 23:45:31 +01:00 |
|
|
|
b6a65059a2
|
Update to use shared memory to contain the stencil comms buffers
Tested on 2.1.1.1 1.2.1.1 4.1.1.1 1.4.1.1 2.2.1.1 subnode decompositions
|
2016-10-24 17:30:43 +01:00 |
|
|
|
c190221fd3
|
Internal SHM comms in non-simd directions working
Need to fix simd directions
|
2016-10-22 18:14:27 +01:00 |
|
|
|
910b8dd6a1
|
use simd type
|
2016-10-21 22:35:29 +01:00 |
|
|
|
09fd5c43a7
|
Reasonably fast version
|
2016-10-21 15:17:39 +01:00 |
|
|
|
f331809c27
|
Use variable type for loop
|
2016-10-21 13:35:37 +01:00 |
|
|
|
306160ad9a
|
bcopy threaded
|
2016-10-21 12:07:28 +01:00 |
|
|
|
a762b1fb71
|
MPI3 working with a bounce through shared memory on my laptop.
Longer term plan: make the "u_comm_buf" in Stencil point to the shared region and avoid the
send between ranks on same node.
|
2016-10-21 09:03:26 +01:00 |
|
|
|
b58adc6a4b
|
commVector
|
2016-10-20 17:00:15 +01:00 |
|
