1
0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-12 20:27:06 +01:00
Commit Graph

384 Commits

Author SHA1 Message Date
497e7e4c53 BG/Q compatibility fix 2016-02-23 15:57:38 +00:00
6aeaf6f568 Parallel IO worked on. I'm puzzled because I already thought I shook this out on MacOS + OpenMPI and then
turned up problems on the BlueWaters Cray.

Gets 75MB/s from home filesystem on parallel configuration read. Need to make the RNG IO parallel,
and also to look at aggregating bigger writes for the parallel write.
Not sure what the home filesystem is.
2016-02-21 08:03:21 -06:00
40f2db9bc0 Disable metropolis step until 10 traj covered. Should move to exposing these
in XML input and start having "applications" directory.
2016-02-21 08:01:44 -06:00
3425751cb8 Missing return value 2016-02-19 01:06:03 +00:00
22422a84d9 Small problem in compressor fix 2016-02-17 19:03:09 -06:00
c9fadf97a5 Simplify the compressor interface again. 2016-02-17 18:16:45 -06:00
81395e85d1 Regressing to not overlap comms and compute becasue bluewaters, edison, and cori are so rubbish at it. 2016-02-16 13:56:44 -06:00
a0fc47c6f9 Cheaper implementation 2016-02-15 16:02:36 -06:00
e2f73e3ead Updates for shmem 2016-02-10 16:50:32 -08:00
neo
6371676a75 Correcting some compilation errors for clang-sse 2016-02-10 11:37:03 +09:00
fc6ad65751 Pushed the overlap comms tweaks 2016-01-11 06:34:22 -08:00
dafc74020c Overlap comms compute improvements in hand op kernels, and better timing from Edison and Cori 2016-01-10 16:54:27 -08:00
d19321dfde Overlap comms compute changes 2016-01-10 19:20:16 +00:00
c99d748da6 Timing reports in benchmarks now reflect the asynch comms thread statistics 2016-01-04 14:42:16 +00:00
02452afd36 Optional overlap of comms with compute 2016-01-04 14:18:40 +00:00
331768dcff Added overlap comms compute mode 2016-01-03 01:38:11 +00:00
aae8bf31a7 Global edit adding copyright and license info to every source file. 2016-01-02 14:51:32 +00:00
1e68b1c1bd Create a benign default for gparity twists 2016-01-02 14:06:53 +00:00
5a80930dd2 Charge conjugation boundary conditions for gauge fields implemented as a policy
class, changing the nature of covariant Cshifts used in
plaquettes, rectangles and staples.

As a result same code is used for the plaq and rect action independent of the BC type.

Should probably isolate the BC in a separate class that Gimpl takes as a template param.
Do the same with smearing policies.

This would then allow composition of BC with smearing etc....
2016-01-02 13:37:25 +00:00
841a37f941 Fix to WilsonCompressor that fixes a bug in comms phase due to the sign change on gamma
matrix in hopping term.
Add logging of time spent in CG.
2015-12-29 23:49:41 +00:00
e6cad3821c Logging improvement 2015-12-29 19:51:18 +00:00
98de1cbb6a Optimised version of rectangle term staples.
~3.4x faster than the naive.
2015-12-29 19:22:59 +00:00
f7d61b8b81 Plaq plus rectangle and Iwasaki, Symanzik DBW2.
http://arxiv.org/pdf/hep-lat/0610075.pdf plaq and rect regress plausibly over 100 trajectories
and under HMC with average plaq and rectangle coming out ok.
2015-12-28 16:39:26 +00:00
78c4e862ef Plaq, Rectangle, Iwasaki, Symanzik and DBW2 workign and HMC regresses to http://arxiv.org/pdf/hep-lat/0610075.pdf 2015-12-28 16:38:31 +00:00
0afcf1cf13 Moved all the HMC tests over to using a single HmcRunner class that manages checkpoint strategies and such like 2015-12-22 11:19:25 +00:00
08edbb5cbe HMC bit repro across checkpoints. Fixed parallel RNG issue with threading.
Conclusion: c++11 distributions not thread safe and must us distinct dist as well as distinct engine
per site. Makes sense when you think of box muller. Also added a reset of dist on fill to ensure
repro across checkpoints.
2015-12-22 08:54:40 +00:00
0abfbcc8eb Naming of files improvement. 2015-12-21 15:37:26 +00:00
1b94253ba4 Logging improvement 2015-12-21 15:36:28 +00:00
36e6f9ac7b Bug fix. Guess not initialised in refresh step; didn't hit before due to luck in not having a vector
created with NAN data.
2015-12-21 15:34:35 +00:00
2f41691c11 Bug fix. Guess was not zeroed prior to CG call. Was earlier accidentally benign just due to luck. 2015-12-21 15:33:36 +00:00
31ca609d12 HMC checkpointing .
Need a general HMC framework to work in restart.
2015-12-20 02:29:51 +00:00
e108e708a3 Wilson TM tests and compiles in 2015-12-17 23:06:33 +00:00
67ccb043f1 Added TM fermions for DSDR etc.. 2015-12-17 22:34:28 +00:00
34a0fde2ad Fixes to fermion force terms after sign of gamma_mu (0...3) change.
Thought I had already committed these.

Believe I have got the Gparity fermion force working.

* tests/Test_gpdwf_force.cc     -- correctly predicts dS for two flavour pseudofermion
                                   based on a small dt update of U field.

* tests/Test_hmc_EODWFRatio_Gparity.cc -- ran 1 trajectory on 8^4 with dH=0.21.

Need to accumulate a full plaquette log to believe fully which will take some hours of run time.
2015-12-15 23:14:12 +00:00
3ce10aa975 Fix a regression failure on Mobius; chroma regression added 2015-12-10 22:55:00 +00:00
b2c02a6106 Runs fastst on cori 2015-11-28 16:58:16 -08:00
e9ff25b06b Small threading change makes a difference on Cori. 2015-11-07 00:07:05 -08:00
05a7029600 Stencil change 2015-11-07 00:06:31 -08:00
899ca41cb8 Merge branch 'master' of github.com:paboyle/Grid
Conflicts:
	lib/qcd/action/fermion/WilsonFermion5D.cc
2015-11-06 03:50:04 -08:00
d29b4c1dee Assembler files 2015-11-06 03:48:48 -08:00
a2ff068e29 Asm and threading for many core 2015-11-06 03:47:14 -08:00
17af18dcab Changes for AVX512 assembler 2015-11-06 03:45:51 -08:00
28022755ae Stencil class name global change to StencilImpl typedef 2015-11-06 05:30:17 -06:00
1159de165c Asm option for AVX512 2015-11-05 22:04:51 -08:00
16c7993434 Merge branch 'master' of github.com:paboyle/Grid
Conflicts:
	lib/simd/Grid_avx512.h
	lib/simd/Grid_imci.h
2015-11-04 03:32:10 -08:00
4e65ad21ac Adding a routine for AVX512 / IMCI with explicit assembly implementations 2015-11-04 03:15:08 -08:00
abb23df83f formatting only 2015-11-04 10:00:27 +00:00
1878bf97d0 Babbage fix 2015-09-30 16:04:01 -07:00
a660ce716b No compile babbage fix 2015-09-30 16:02:44 -07:00
64d64d1ab6 Updating to modify non-inlining permute routines and hopefully get better reg use and
enhance performance.
2015-09-25 08:55:04 -07:00