Azusa Yamaguchi
|
9ada378e38
|
Add timing
|
2018-05-04 10:58:01 +01:00 |
|
Azusa Yamaguchi
|
587bfcc0f4
|
Add Timing
|
2018-05-03 12:10:31 +01:00 |
|
Azusa Yamaguchi
|
4f4181c54a
|
Merge branch 'feature/staggered-comms-compute' of https://github.com/paboyle/Grid into feature/staggered-comms-compute
|
2018-05-02 14:59:13 +01:00 |
|
Azusa Yamaguchi
|
441ad7498d
|
add Iterative counter
|
2018-05-02 14:21:30 +01:00 |
|
Azusa Yamaguchi
|
96272f3841
|
Merge staggered fix linear operator and reduction
|
2018-04-26 10:33:19 +01:00 |
|
Azusa Yamaguchi
|
5c936d88a0
|
Merge branch 'feature/staggered-comms-compute' of https://github.com/paboyle/Grid into feature/staggered-comms-compute
|
2018-04-26 10:18:37 +01:00 |
|
Azusa Yamaguchi
|
1c64ee926e
|
Faster staggered operator with m^2 term trivial used
|
2018-04-26 10:17:49 +01:00 |
|
Azusa Yamaguchi
|
2cbb72a81c
|
Provide info if EE term is trivial (m^2 factor)
Better timing in staggered 4d case
|
2018-04-26 10:10:07 +01:00 |
|
Azusa Yamaguchi
|
31d83ee046
|
Enable special treatment of constEE cases
|
2018-04-26 10:08:46 +01:00 |
|
Azusa Yamaguchi
|
3e125c5b61
|
Faster linalg on CG optimised against staggered
Sum overhead is bigger for staggered
|
2018-04-26 10:07:19 +01:00 |
|
Azusa Yamaguchi
|
eac6ec4b5e
|
Faster reductions, important on single node staggered
|
2018-04-26 10:03:57 +01:00 |
|
Azusa Yamaguchi
|
213f8db6a2
|
Microsecond resultion
|
2018-04-26 10:01:39 +01:00 |
|
Azusa Yamaguchi
|
80302e95a8
|
MILC Interface
|
2018-03-08 15:34:03 +00:00 |
|
Azusa Yamaguchi
|
b938202081
|
Overlapped Comm for Wilson DhopInternal
|
2018-03-07 14:08:43 +00:00 |
|
Azusa Yamaguchi
|
0f468e2179
|
OverlappedComm for Staggered 5D and 4D.
|
2018-02-22 12:50:09 +00:00 |
|
Azusa Yamaguchi
|
97b9c6f03d
|
No option for interior/exterior split of asm kernels since different directions get interleaved
|
2018-01-22 11:04:19 +00:00 |
|
Azusa Yamaguchi
|
63982819c6
|
No option to overlap comms and compute for asm implementation since different directions are interleaved
in the kernels, introducing if else structure would be too painful
|
2018-01-22 11:03:39 +00:00 |
|
Azusa Yamaguchi
|
24162c9ead
|
Staggered overlap comms comput
|
2018-01-09 13:02:52 +00:00 |
|
azusayamaguchi
|
e55397bc13
|
Staggerd cg
|
2017-11-24 14:18:30 +00:00 |
|
fionnoh
|
1d7ccc6b2c
|
Declaring virtual functions as pure virtual functions.
|
2017-11-09 19:46:57 +00:00 |
|
Azusa Yamaguchi
|
1860b1698c
|
Fixed the bag on MPI_T at Cam
|
2017-11-08 09:03:01 +00:00 |
|
Azusa Yamaguchi
|
9b8d1cc3da
|
Staggered Schur decomposed matrix norm changed to not be the Schur anymore :(
Carleton wanted this for multimass / multishift
|
2017-11-07 14:48:45 +00:00 |
|
Guido Cossu
|
149c3f9e9c
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2017-11-07 14:01:13 +00:00 |
|
Guido Cossu
|
c519aab19d
|
Fixing the MPI memory leak in the communicators
|
2017-11-07 13:55:37 +00:00 |
|
paboyle
|
69929f20bb
|
Destructor fix. Split Grid and MPI3 will not yet work without more effort from me.
|
2017-11-06 23:45:00 +00:00 |
|
paboyle
|
360efd0088
|
Improved treatment of reverse asked for by chris.
Truncate the basis.
Power method renormalises
|
2017-11-02 22:05:31 +00:00 |
|
paboyle
|
27ea2afe86
|
No compile on comms == none fix
|
2017-10-30 01:14:11 +00:00 |
|
paboyle
|
a7f72eb994
|
SHaking out
|
2017-10-30 00:22:06 +00:00 |
|
paboyle
|
501fa1614a
|
Communicator updates for split grid
|
2017-10-30 00:16:12 +00:00 |
|
paboyle
|
fe4d9b003c
|
More digits
|
2017-10-30 00:04:47 +00:00 |
|
paboyle
|
4a699b4da3
|
New rank can be found out
|
2017-10-30 00:04:14 +00:00 |
|
paboyle
|
689323f4ee
|
Reverse dim ordering lexico support
|
2017-10-30 00:03:15 +00:00 |
|
paboyle
|
84b441800f
|
Merge branch 'develop' into feature/lanczos-reorg
|
2017-10-27 14:21:38 +01:00 |
|
paboyle
|
1ef424b139
|
Split grid Y2K bug fix attempt
|
2017-10-27 14:20:35 +01:00 |
|
paboyle
|
f96c800d25
|
Passes reload of coarse basis
|
2017-10-27 09:43:22 +01:00 |
|
paboyle
|
32a52d7583
|
Move the local coherence lanczos into algorithms.
Keep the I/O in the tester. Other people can copy this method to write other I/O formats.
|
2017-10-27 09:04:31 +01:00 |
|
paboyle
|
7fab183c0e
|
Better read test
|
2017-10-27 08:17:49 +01:00 |
|
paboyle
|
9ec9850bdb
|
64bit ftello update
|
2017-10-26 23:34:31 +01:00 |
|
paboyle
|
0c4ddaea0b
|
Cleaning up
|
2017-10-26 23:31:46 +01:00 |
|
paboyle
|
00ebc150ad
|
Mistake in string parse; interface is ambiguous and must fix. Is char * a file, or a XML buffer ?
|
2017-10-26 23:30:37 +01:00 |
|
paboyle
|
0f3e9ae57d
|
Gsites error. Only appeared (so far) in I/O code for even odd fields
|
2017-10-26 23:29:59 +01:00 |
|
Azusa Yamaguchi
|
034de160bf
|
Staggered updates : Schur fixed and added a unit test for Test_staggered_cg_schur.cc giving stronger check
|
2017-10-26 20:58:46 +01:00 |
|
paboyle
|
31f99574fa
|
Moving these out of algorithms
|
2017-10-26 07:47:42 +01:00 |
|
paboyle
|
a34c8a2961
|
Update to IRL; getting close to the structure I would like.
|
2017-10-26 07:45:56 +01:00 |
|
paboyle
|
e9be293444
|
Better messaging
|
2017-10-26 01:59:30 +01:00 |
|
paboyle
|
08583afaff
|
Red black friendly coarsening
|
2017-10-25 23:51:18 +01:00 |
|
paboyle
|
b395a312af
|
Better error messaging
|
2017-10-25 23:50:37 +01:00 |
|
paboyle
|
66295b99aa
|
Bit less verbose SciDAC IO
|
2017-10-25 23:50:05 +01:00 |
|
paboyle
|
b8654be0ef
|
64 bit safe offsets
|
2017-10-25 23:49:23 +01:00 |
|
paboyle
|
f6c3f6bf2d
|
XML serialisation of parms and initialise from parms object
|
2017-10-25 23:47:59 +01:00 |
|