73434db636
Merge remote-tracking branch 'upstream/develop' into feature/ddalphaamg
2018-01-09 10:43:33 +01:00
e564d11687
Allow resize of the shared memory buffers
2018-01-08 15:20:26 +00:00
0b2162f375
Clean up
2018-01-08 14:06:53 +00:00
44f65526e0
Simplify communicators
2018-01-08 11:35:43 +00:00
43e48542ab
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
2018-01-08 11:34:45 +00:00
0b85f1bfc8
Simplify the communicator proliferation: mpi and none.
2018-01-08 11:33:47 +00:00
9947cfbf14
Simplify number of communicator cases
2018-01-08 11:33:01 +00:00
357badce5e
Simplify communicator case proliferation
2018-01-08 11:32:16 +00:00
0091eec23a
Simplify communicator cases
2018-01-08 11:31:32 +00:00
9e9c2962df
Simplify comms layer proliferation
2018-01-08 11:30:22 +00:00
b91282ad46
Simplify comms layer proliferation
2018-01-08 11:28:52 +00:00
0a68470f9a
Simplify comms layers
2018-01-08 11:28:30 +00:00
6ecf280723
Simplify comms layer proliferation
2018-01-08 11:28:04 +00:00
7eeab7f995
Simplify comms layers
2018-01-08 11:27:43 +00:00
c6411f8514
Merge remote-tracking branch 'upstream/develop' into feature/ddalphaamg
2018-01-08 10:37:10 +01:00
portelli
f3a77f4b7f
Merge branch 'feature/hadrons' into feature/hadrons-new-memory-model
2017-12-12 14:05:23 +00:00
portelli
2401360784
Merge pull request #138 from guelpers/feature/hadrons
...
bug fix in sequential insertion of conserved vector current
2017-12-11 18:53:41 +01:00
2cfb50cbe5
bug fix in sequential insertion of conserved vector current
2017-12-08 11:13:39 +00:00
portelli
f9aa39e1c4
global memory debug through command line flag
2017-12-07 14:40:58 +01:00
df152648d6
Fix error in MR code when compiling for single precision
2017-12-06 18:00:58 +01:00
portelli
e78794688a
memory profiler improvement
2017-12-06 16:50:25 +01:00
portelli
29e2eddea8
Merge branch 'develop' into feature/hadrons-new-memory-model
2017-12-06 16:49:21 +01:00
portelli
0a038ea15a
Merge branch 'develop' into feature/hadrons
2017-12-06 16:49:10 +01:00
portelli
62eb1f0e59
FermionOperator virtual destructor needed for polymorphism
2017-12-06 16:48:17 +01:00
9579c9c327
Threading improvement
2017-12-05 14:12:22 +00:00
c24d4c8d0e
Improved parallel RNG init
2017-12-05 13:01:10 +00:00
a14038051f
Improved AllToAll asserts
2017-12-05 11:43:25 +00:00
3e560b9462
Faster RNG init
2017-12-05 11:42:05 +00:00
d93c6760ec
Faster code for split unsplit
2017-12-05 11:39:26 +00:00
ae3b7713a9
Cold start doesnt need RNG
2017-12-05 11:36:31 +00:00
portelli
33cb509d4b
Merge branch 'develop' into feature/hadrons
2017-12-01 19:45:32 +00:00
portelli
456c78c233
Merge branch 'develop' into feature/hadrons-new-memory-model
2017-12-01 19:45:12 +00:00
portelli
2fd4989029
Merge branch 'develop' of github.com:paboyle/Grid into develop
2017-12-01 19:44:31 +00:00
portelli
2427a21428
minor serial IO fixes, XML now issues warning when trying to read absent nodes, these becomes
2017-12-01 19:44:07 +00:00
28ceacec45
Split/Unsplit working
2017-11-27 15:13:29 +00:00
4987edbd44
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
2017-11-27 12:34:56 +00:00
1f04e56038
Believe split/unsplit works, but need to make pretty
2017-11-27 12:33:08 +00:00
4bfc8c85c3
Clean up verbose communicator create
2017-11-27 12:32:37 +00:00
e55397bc13
Staggerd cg
2017-11-24 14:18:30 +00:00
0afa22747d
Merge remote-tracking branch 'upstream/develop' into feature/new-solver-algorithms
2017-11-24 10:11:42 +01:00
94b8fb5686
Debug in progress
2017-11-19 01:39:04 +00:00
fa43206c79
Remove some empty lines
2017-11-10 13:48:38 +01:00
1d7ccc6b2c
Declaring virtual functions as pure virtual functions.
2017-11-09 19:46:57 +00:00
a367835bf2
Set everything up for the implementation of FCAGMRES
...
The current implementation is the exact same code as normal FGMRES. This commit
only sets up the "framework" for the implementation of FCAGMRES, i.e., a test
and an include in the algorithms header file.
2017-11-09 17:30:41 +01:00
d7743591ea
Fix some minor formatting errors
2017-11-09 17:28:19 +01:00
c6cbe533ea
Set everything up for the implementation of CAGMRES
...
The current implementation is the exact same code as normal GMRES. This commit
only sets up the "framework" for the implementation of CAGMRES, i.e., a test and
an include in the algorithms header file.
2017-11-09 17:14:44 +01:00
8402ab6cf9
Some minor formatting improvements
2017-11-09 12:52:04 +01:00
c63095345e
Remove some superfluous comments
2017-11-09 12:47:20 +01:00
a7ae46b61e
Remove some comments
2017-11-08 16:58:20 +01:00
cd63052205
Remove everything preconditioner-related in GMRES code
2017-11-08 16:57:40 +01:00
Daniel Richtmann
paboyle
portelli
Vera Guelpers
azusayamaguchi
fionnoh