Peter Boyle
c650bb3f3d
Very small merge speed up.
2016-02-16 18:41:53 -06:00
Peter Boyle
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
Peter Boyle
340a29b735
More careful sequencing of comms
2016-02-15 16:04:59 -06:00
Peter Boyle
a0fc47c6f9
Cheaper implementation
2016-02-15 16:02:36 -06:00
Peter Boyle
42a9ac71d2
BUg fix, wait till complete.
2016-02-14 16:21:21 -06:00
Peter Boyle
41c2b09184
Shmem comms [NO MPI] target added. The dwf test runs and passes.
...
Not really shaken out to my satisfaction though as I want more tests done, so don't declare as working.
But committing my current while I try a few experimentals.
2016-02-14 14:24:38 -06:00
paboyle
294dbf1bf0
Compile on OpenMPI shmem
2016-02-11 23:45:51 +00:00
Peter Boyle
9548c8b91f
Had to break this out for universal access through the code base.
2016-02-11 07:40:09 -06:00
Peter Boyle
7f927a541c
Shmem related fixes for shmem compile
2016-02-11 07:37:39 -06:00
paboyle
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
Jung
bd84c23298
definitions reconciled.
2016-01-25 16:30:59 -05:00
Jung
7aa8d5e8af
Faiing to compile, comparing with master
2016-01-25 16:03:02 -05:00
Jung
6012b0ec23
Checking in changes before changing to chulwoo-dec12-2015
2016-01-25 09:40:58 -05:00
Jung
411ac49dd7
GparityWilsonTM typedef added. Not yet tested
...
Conflicts:
configure
lib/qcd/action/fermion/WilsonKernels.h
2016-01-25 01:36:28 -05:00
Jung
b8fb05a422
Addtional routines for Lanczos (SYM2, Chebyshef)..
2016-01-25 01:26:25 -05:00
Jung
5c57d4f403
Merge branch 'master' of https://github.com/paboyle/Grid into scidac1_2
...
Conflicts:
lib/qcd/action/fermion/WilsonKernels.h
2016-01-11 11:36:45 -05:00
paboyle
fc6ad65751
Pushed the overlap comms tweaks
2016-01-11 06:34:22 -08:00
paboyle
dafc74020c
Overlap comms compute improvements in hand op kernels, and better timing from Edison and Cori
2016-01-10 16:54:27 -08:00
paboyle
d19321dfde
Overlap comms compute changes
2016-01-10 19:20:16 +00:00
Jung
5924e5a562
Merge branch 'master' of https://github.com/paboyle/Grid into scidac1_2
...
Conflicts:
configure
lib/qcd/action/Actions.h
lib/qcd/action/fermion/WilsonKernels.h
2016-01-06 03:44:57 -05:00
paboyle
c99d748da6
Timing reports in benchmarks now reflect the asynch comms thread statistics
2016-01-04 14:42:16 +00:00
paboyle
02452afd36
Optional overlap of comms with compute
2016-01-04 14:18:40 +00:00
paboyle
331768dcff
Added overlap comms compute mode
2016-01-03 01:38:11 +00:00
paboyle
4aac345bea
Updated logging to colour code according to message type
2016-01-02 17:21:14 +00:00
paboyle
15c0022042
GPLv2 clarified, and copyright message and banner in Init function.
...
Color is just showing off....
2016-01-02 15:22:30 +00:00
paboyle
aae8bf31a7
Global edit adding copyright and license info to every source file.
2016-01-02 14:51:32 +00:00
paboyle
1e68b1c1bd
Create a benign default for gparity twists
2016-01-02 14:06:53 +00:00
paboyle
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
paboyle
145a295231
Bug fix for stencil with large shifts (3+), would be important to naik term for example but did not
...
impact Wilson based nearest neighbour stencils.
2015-12-30 19:29:48 +00:00
paboyle
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
Azusa Yamaguchi
e6cad3821c
Logging improvement
2015-12-29 19:51:18 +00:00
Azusa Yamaguchi
98de1cbb6a
Optimised version of rectangle term staples.
...
~3.4x faster than the naive.
2015-12-29 19:22:59 +00:00
Azusa Yamaguchi
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
Azusa Yamaguchi
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
1e0be161e5
MacroMagic: inline functions to avoid double symbol issues
2015-12-23 14:20:05 +00:00
paboyle
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
paboyle
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
paboyle
0abfbcc8eb
Naming of files improvement.
2015-12-21 15:37:26 +00:00
paboyle
1b94253ba4
Logging improvement
2015-12-21 15:36:28 +00:00
paboyle
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
paboyle
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
paboyle
09bfe52840
Remove extraneous variable
2015-12-21 15:30:28 +00:00
paboyle
8c9010d0f4
Isnan check on guess and convergence assert on result
2015-12-21 15:29:46 +00:00
paboyle
42c583265c
Remove timestamp
2015-12-21 15:28:03 +00:00
paboyle
539d698492
Prototypes for CML routines
2015-12-21 15:26:42 +00:00
paboyle
31ca609d12
HMC checkpointing .
...
Need a general HMC framework to work in restart.
2015-12-20 02:29:51 +00:00
paboyle
5710966324
Options to use mersenne twister OR ranlux48 via --enable-rng flag at configure time.
...
Can save and restore RNG state via new (serial) I/O routines in a NERSC header style file.
Store a Parallel (one per site) and a single serial RNG file.
2015-12-19 18:32:25 +00:00
paboyle
e108e708a3
Wilson TM tests and compiles in
2015-12-17 23:06:33 +00:00
paboyle
6f0198d4d9
Merge branch 'master' of https://github.com/paboyle/Grid
2015-12-17 22:34:54 +00:00
paboyle
67ccb043f1
Added TM fermions for DSDR etc..
2015-12-17 22:34:28 +00:00
Azusa Yamaguchi
24a5a81c53
SSE compile fix
2015-12-16 09:09:37 +00:00
Jung
eb1759d7ea
Added Gparity instantiation to no HANDOPT case
...
deleted configure (as intended?)
2015-12-16 00:04:09 -05:00
paboyle
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
Jung
bc34b7e808
Merge branch 'master' of https://github.com/paboyle/Grid into scidac1_2
...
Conflicts:
lib/qcd/action/fermion/WilsonKernels.h
tests/Make.inc
2015-12-15 11:11:59 -05:00
Jung
284453c5e9
Added gparity mobius defs, added params to ScaledShamir
...
checking in before puling master
2015-12-14 12:15:06 -05:00
paboyle
af855cc129
Updating to fix peek poke to checkerboarded arrays since Chulwoo needs this.
2015-12-12 07:11:46 +00:00
paboyle
47fe6b5a7c
Merge branch 'master' of https://github.com/aportelli/Grid into aportelli-master
2015-12-10 23:14:52 +00:00
paboyle
b3ef09a54d
Merge branch 'master' of https://github.com/paboyle/Grid
2015-12-10 23:05:38 +00:00
paboyle
3ce10aa975
Fix a regression failure on Mobius; chroma regression added
2015-12-10 22:55:00 +00:00
Azusa Yamaguchi
a32a59fc43
Merge branch 'master' of https://github.com/paboyle/Grid
2015-12-09 12:48:44 +00:00
200de272ed
IO: serialisable enums
2015-12-08 13:54:00 +00:00
d68a72e28b
IO: code cleaning and string binary IO fix
2015-12-08 13:53:33 +00:00
17f9268a55
XmlIO: minor code cleaning
2015-12-07 18:30:00 +00:00
78f0c2595d
autotool file accidentally committed
2015-12-07 18:28:06 +00:00
Jung
f2b4edc090
Fixes for Gparity comparison with CPS (Instantiation, Gamma matrix convention)
2015-12-07 02:04:57 -05:00
Jung
fb81acca3c
Merge branch 'master' of https://github.com/paboyle/Grid
2015-12-03 12:11:10 -05:00
paboyle
93356fd246
No compile fixes on gcc/Cray
2015-11-29 03:14:44 -08:00
paboyle
ca42fe6d32
Merge branch 'master' of github.com:paboyle/Grid
...
Merge done
Conflicts:
lib/serialisation/XmlIO.h
tests/Test_stencil.cc
2015-11-28 17:03:43 -08:00
paboyle
6b97b271ae
Integer divide useful
2015-11-28 17:01:20 -08:00
paboyle
fa01ae5980
integer divide
2015-11-28 17:00:34 -08:00
paboyle
113131b01c
THis failed for some reason. Suspect Antonin has made more progress.
2015-11-28 16:59:59 -08:00
paboyle
b2c02a6106
Runs fastst on cori
2015-11-28 16:58:16 -08:00
paboyle
02d730513a
Divide function
2015-11-28 16:54:43 -08:00
paboyle
d875c2bd39
More verbose useful
2015-11-28 16:54:19 -08:00
paboyle
cc32ba615a
Verbose changes
2015-11-28 16:53:54 -08:00
paboyle
6684739452
Better to drop KMP_AFFINITY override
2015-11-28 16:52:44 -08:00
Peter Boyle
bc4b252883
Merge branch 'master' of https://github.com/paboyle/Grid
2015-11-29 00:33:01 +00:00
Peter Boyle
11cf0f08f3
This file is not yet debugged.
2015-11-29 00:32:45 +00:00
Peter Boyle
8a33846095
No compile fix
2015-11-29 00:29:58 +00:00
Peter Boyle
54f04ee5c9
Perf event interface was linux specfic and use ifdef to protect
2015-11-29 00:24:48 +00:00
Peter Boyle
825875fd48
compile fixes
2015-11-29 00:24:25 +00:00
Peter Boyle
f8290bfd58
Compile fixes
2015-11-29 00:24:04 +00:00
Azusa Yamaguchi
967be91692
update merge
2015-11-26 09:51:41 +00:00
06f8ecea04
Merge commit '899ca41cb8c8f47771bfd37cd895cbc2184e5560'
2015-11-16 18:16:25 +00:00
af19118113
new I/O interface
2015-11-16 18:14:37 +00:00
paboyle
e9ff25b06b
Small threading change makes a difference on Cori.
2015-11-07 00:07:05 -08:00
paboyle
05a7029600
Stencil change
2015-11-07 00:06:31 -08:00
paboyle
b04b8914fd
EXECINFO change
2015-11-07 00:05:57 -08:00
paboyle
899ca41cb8
Merge branch 'master' of github.com:paboyle/Grid
...
Conflicts:
lib/qcd/action/fermion/WilsonFermion5D.cc
2015-11-06 03:50:04 -08:00
paboyle
d29b4c1dee
Assembler files
2015-11-06 03:48:48 -08:00
paboyle
a2ff068e29
Asm and threading for many core
2015-11-06 03:47:14 -08:00
paboyle
b362f8d27b
Threading for many core
2015-11-06 03:46:41 -08:00
paboyle
64770d9052
Threading changes for many core and asm calls
2015-11-06 03:46:21 -08:00
paboyle
17af18dcab
Changes for AVX512 assembler
2015-11-06 03:45:51 -08:00
Peter Boyle
28022755ae
Stencil class name global change to StencilImpl typedef
2015-11-06 05:30:17 -06:00
Peter Boyle
955b482aaf
Partial optimisation of the extraction/merger of simd vecs.
2015-11-06 05:26:20 -06:00
Peter Boyle
f9b2fce93b
Changing whole stencil class to be template and not just single functions
2015-11-06 05:25:10 -06:00
Peter Boyle
473fa28a6c
Partial optimisation; comms in x-dir for red black dslash will be slow as the checker skipping block strided
...
loops are non threadable. Will need to write a kernel for these instead and drive them with a lookup table
to make a look sufficiently simple to thread.
2015-11-06 05:23:23 -06:00
Peter Boyle
5d854c869c
Stencil interface changes
2015-11-06 05:22:33 -06:00
Peter Boyle
880ff88362
Comms optimisation
2015-11-06 05:22:18 -06:00
Azusa Yamaguchi
4690acc3c8
Don't know why peter committed these as they didn't compile
2015-11-06 10:31:48 +00:00
Azusa Yamaguchi
3281745fde
Exec info and linux check to stop non-portable code breaking
2015-11-06 10:31:24 +00:00
paboyle
1159de165c
Asm option for AVX512
2015-11-05 22:04:51 -08:00
paboyle
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
paboyle
6be9716e6f
New file
2015-11-04 03:26:28 -08:00
paboyle
4a41c885ed
Use Linux kernel interface to hardware performance counters. Dead useful.
2015-11-04 03:24:19 -08:00
paboyle
757b31ed42
Threading for KNC mods.
2015-11-04 03:22:14 -08:00
paboyle
ac7d1f26ad
Either blocking or lebesgue curve
2015-11-04 03:19:16 -08:00
paboyle
1a8bf938b3
Use either sub-blocking or lebesgue
2015-11-04 03:18:51 -08:00
paboyle
63a2993827
Exec info an cache blocking
2015-11-04 03:16:56 -08:00
paboyle
4e65ad21ac
Adding a routine for AVX512 / IMCI with explicit assembly implementations
2015-11-04 03:15:08 -08:00
Peter Boyle
dfc1de6f60
Merge branch 'master' of github.com:paboyle/Grid
2015-11-04 05:14:26 -06:00
Peter Boyle
3b7576ad53
Switch off for now
2015-11-04 05:13:29 -06:00
paboyle
9b5d31ffc1
mac , mult routines
...
Lines# with '#' will be ignored, and an empty message aborts the commit.
2015-11-04 03:10:34 -08:00
paboyle
a38762159c
Inline assembly hooks for AVX 512. Better way in some ways than BAGEL to generate assembly.
...
Updated Grid_avx512.h
2015-11-04 03:09:06 -08:00
Peter Boyle
ffc5dab17f
AMD FMA4 support added for Interlagos/BlueWaters
2015-11-04 04:29:58 -06:00
Peter Boyle
96608c70d1
chrono causing some problems on Cray systems. Suspend use for now
2015-11-04 04:28:31 -06:00
Peter Boyle
d35d63b171
Algorithm in
2015-11-04 04:27:44 -06:00
Peter Boyle
24044dbc56
Debugged a problem with checkerboarded cshift in the checker dimension which arose
...
only when mpi spread out in the checker dimension. Added a test that trapped and helped debug this
2015-11-04 10:00:55 +00:00
Peter Boyle
abb23df83f
formatting only
2015-11-04 10:00:27 +00:00
Peter Boyle
12c5ec813c
Useful debug messages (commented out) are included for preservation in case I need to revisit this
2015-11-04 09:59:27 +00:00
Peter Boyle
1271508ca2
Bug fix for spread out in x (EO) direction.
...
This is really annoying -- it is very hard to thread the loops with the index
recursion on buffer offset in the red-black case. Must think of a good threading
solution here.
2015-11-04 09:57:57 +00:00
Peter Boyle
ec5af35166
EO bug fix when spread out in x-direction
2015-11-04 09:56:58 +00:00
Peter Boyle
0f59356e86
Problem in comms fixed
2015-11-02 00:00:15 +00:00
8709117aea
Log: generalised Logger class to allow separate logs in Grid-based applications
2015-10-27 17:31:13 +00:00
e6b9aa9076
Config.h removed form repository
2015-10-27 10:47:07 +00:00
Peter Boyle
8889af45ca
FMA4 added
2015-10-09 01:00:53 +02:00
Peter Boyle
83afb2e26a
Poly support for lanczos
2015-10-09 00:43:21 +02:00
Peter Boyle
6d06bd9493
Minor change in commented out code
2015-10-09 00:42:21 +02:00
Peter Boyle
6ee23f409e
Lanczos addition
2015-10-09 00:41:00 +02:00
Peter Boyle
2d95dac6b6
Lanczos untested/partially tested additions. In middle of shake out but at least compiles
2015-10-09 00:40:25 +02:00
Peter Boyle
814c79f38d
SIMD improvements for mac and madd use in complex for avx, sse
2015-10-09 00:38:52 +02:00
paboyle
1878bf97d0
Babbage fix
2015-09-30 16:04:01 -07:00
paboyle
a660ce716b
No compile babbage fix
2015-09-30 16:02:44 -07:00
paboyle
f4b6d1dfea
NGO stores reenabled
2015-09-30 16:02:14 -07:00
paboyle
23813ac798
No compile on babbage fix
2015-09-30 16:01:28 -07:00
Peter Boyle
9f4f65cb46
Added a decoupled memory system benchmark to remove thread synch overhead
2015-09-26 18:23:57 -07:00
Peter Boyle
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
Peter Boyle
5ef42add2d
Changes to remove warnings under icc; disambiguate AVX512 from IMCI correctly
...
and drop swizzles in AVX512. Don't know why these compiled.
2015-09-23 05:23:45 -07:00
Peter Boyle
2f38ebc446
Reintroducing the hand unrolled loops
2015-09-08 17:45:30 +01:00
Peter Boyle
638d6675ee
Tested rms dH is ~ dt^4 numerically, so believe the ForceGradient is correct now.
...
Paranoia makes me want to diddle with the FG step to ensure dt^2 reappears.
2015-08-31 16:33:20 +01:00
Peter Boyle
357c6ab46d
Reunitarise. Complete the HMC and integrator changes.
2015-08-31 16:32:04 +01:00
Peter Boyle
755dca9533
Added ForceGradient integrator. dH dropped so seems to work. Will only
...
believe it is right once I have pulled a dt^4 error scaling plot out.
2015-08-31 06:23:02 +01:00
Peter Boyle
29fd004d54
Unified integrator and integrator algorithm into virtual class used as a policy for the
...
HMC.
2015-08-30 13:39:19 +01:00
Peter Boyle
aa52fdadcc
Global edit on HMC sector -- making GaugeField a template parameter and
...
preparing to pass integrator, smearing, bc's as policy classes to hmc.
Propose to unify "integrator" and integrator algorithm in a base/derived
way to override step. Want to read through ForceGradient to ensure
that abstraction covers the force gradient case.
2015-08-30 12:18:34 +01:00
Peter Boyle
76d752585b
Started a tidy up in the HMC sector. Now comfortable with the two level integrators;
...
to a little figure out what Guido had done & why -- but there is a neat saving of force
evaluations across the nesting time boundary making use of linearity of the leapP in dt.
I cleaned up the printing, reduced the volume of code, in the process sharing printing
between all integrators. Placed an assert that the total integration time for all integrators
must match at end of trajectory.
Have now verified e-dH = 1 for nested integrators in Wilson/Wilson runs with both
Omelyan and with Leapfrog so substantial confidence gained.
2015-08-29 17:18:43 +01:00
Peter Boyle
dc814f30da
Binary IO file for generic Grid array parallel I/O.
...
Number of IO MPI tasks can be varied by selecting which
dimensions use parallel IO and which dimensions use Serial send to boss
I/O.
Thus can neck down from, say 1024 nodes = 4x4x8x8 to {1,8,32,64,128,256,1024} nodes
doing the I/O.
Interpolates nicely between ALL nodes write their data, a single boss per time-plane
in processor space [old UKQCD fortran code did this], and a single node doing all I/O.
Not sure I have the transfer sizes big enough and am not overly convinced fstream
is guaranteed to not give buffer inconsistencies unless I set streambuf size to zero.
Practically it has worked on 8 tasks, 2x1x2x2 writing /cloning NERSC configurations
on my MacOS + OpenMPI and Clang environment.
It is VERY easy to switch to pwrite at a later date, and also easy to send x-strips around from
each node in order to gather bigger chunks at the syscall level.
That would push us up to the circa 8x 18*4*8 == 4KB size write chunk, and by taking, say, x/y non
parallel we get to 16MB contiguous chunks written in multi 4KB transactions
per IOnode in 64^3 lattices for configuration I/O.
I suspect this is fine for system performance.
2015-08-26 13:40:29 +01:00
Peter Boyle
612957f057
pull in original license.
2015-08-21 10:19:08 +01:00
Peter Boyle
cea8ac9a22
Credits to orig source where I found the macro tricks.
2015-08-21 10:14:53 +01:00
