1
0
mirror of https://github.com/paboyle/Grid.git synced 2024-11-15 18:25:37 +00:00
Commit Graph

3529 Commits

Author SHA1 Message Date
paboyle
1878bf97d0 Babbage fix 2015-09-30 16:04:01 -07:00
paboyle
3a478e5f2a No compile babbage fix 2015-09-30 16:03:05 -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
paboyle
af89c40462 Better timing tweaks to give sensible results on 24 threads on Edison dual ivybridge nodes. 2015-09-28 16:09:04 -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
eed889ea05 Update on todo list 2015-08-30 12:23:08 +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
Peter Boyle
476da3ee62 Separated IO reader/writers into a proper abstract base,
derived relationship. Have Text/Binary/Xml versions of
Reader & Writer.

Any new Reader/Writer class inheriting the interface can give object serialisation
to any desired format now.

      new file:   lib/serialisation/BaseIO.h
      modified:   lib/serialisation/BinaryIO.h
      modified:   lib/serialisation/Serialisation.h
      modified:   lib/serialisation/TextIO.h
      modified:   lib/serialisation/XmlIO.h

The test uses the Xml, Binary and Text formats as well as cout << Object.
2015-08-21 10:06:33 +01:00
Peter Boyle
35818fdf6c Text and Binary readers 2015-08-20 23:04:38 +01:00
Peter Boyle
091785e5f5 Better list 2015-08-20 17:19:48 +01:00
Peter Boyle
77d299b414 Cosmetic 2015-08-20 16:30:52 +01:00
Peter Boyle
ab81a25073 XMLReader implementation and a virtual Reader/Writer template framework.
Test_serialisation has an example of *code* *free* object serialisation
to both ostream and to XML using macro magic.

Implementing TextReader/TextWriter, YAML, JSON etc.. should be trivial
and we can use configure time options to select the default "Reader" typedef.

Present done with

"using XMLPolicy::Reader"

to pick up the default serialisation strategy.
2015-08-20 16:21:26 +01:00
dd498f993e Merge pull request #1 from paboyle/master
Sync with Peter
2015-08-19 17:27:31 +02:00
Peter Boyle
fdfe194c41 Threading bug in RNG fill fixed. 2015-08-19 14:41:05 +01:00
Peter Boyle
8b070ae54c Gparity now accepting twists through constructor 2015-08-19 11:26:01 +01:00
Peter Boyle
4e085dd0ed Domain wall even-odd 2f HMC with wilson gauge and PV 2f ratio now running and giving small dH.
Azusa is working hard on the rectangle term and we'll hopefully start reproducing plaquettes
from RBC-UKQCD parameters soon !

My new laptop is pretty warm and is starting to groan ;)
2015-08-19 10:26:07 +01:00
Peter Boyle
e8d63c9178 Merge branch 'master' of https://github.com/paboyle/Grid 2015-08-19 05:49:00 +01:00
Peter Boyle
c54c086f17 Even odd preconditioned one flavour ratio
(no support for non-const EE schur block)
2015-08-19 05:46:58 +01:00
Peter Boyle
dd6bb73ee0 Added one flavour rational ratios (unprec) 2015-08-19 04:58:40 +01:00
Peter Boyle
fc160eeccc Added one flavour rational ratios (unprec) 2015-08-19 04:58:40 +01:00
Peter Boyle
48db72259e EvenOdd schur decomposed mpcdagmpc version of rhmc determinant.
dH is also small and plaquette looks right.
2015-08-18 18:37:39 +01:00
Peter Boyle
570150f1d3 EvenOdd schur decomposed mpcdagmpc version of rhmc determinant.
dH is also small and plaquette looks right.
2015-08-18 18:37:39 +01:00
Peter Boyle
9c7840c3a7 rhmc for 1+1 wilson is conserving dH~0.
A good days work  ;)
2015-08-18 16:58:56 +01:00
Peter Boyle
aef98b7226 rhmc for 1+1 wilson is conserving dH~0.
A good days work  ;)
2015-08-18 16:58:56 +01:00
Peter Boyle
5c364f8082 One flavour rational unprec added; untested but does compile.
Moving param structs into a single header for later connection to file I/O using
macromagic.h
2015-08-18 14:40:08 +01:00
Peter Boyle
a842a6c94d One flavour rational unprec added; untested but does compile.
Moving param structs into a single header for later connection to file I/O using
macromagic.h
2015-08-18 14:40:08 +01:00
Peter Boyle
2dd9ad7b0f Update TODO list 2015-08-18 10:43:32 +01:00
Peter Boyle
cd242a2637 Update TODO list 2015-08-18 10:43:32 +01:00
Peter Boyle
bdcbfe9310 Even Odd two flavour ratio added and dH == small 2015-08-18 10:37:08 +01:00
Peter Boyle
9306921ded Even Odd two flavour ratio added and dH == small 2015-08-18 10:37:08 +01:00
Peter Boyle
76f3855629 Merge branch 'master' of https://github.com/paboyle/Grid 2015-08-18 09:23:58 +01:00
Peter Boyle
8621e2409f Merge branch 'master' of https://github.com/paboyle/Grid 2015-08-18 09:23:58 +01:00
Peter Boyle
6212807a77 Small dh obtained in two flavour ratio so looks ok. 2015-08-18 09:21:29 +01:00
Peter Boyle
7622f0c441 Small dh obtained in two flavour ratio so looks ok. 2015-08-18 09:21:29 +01:00
Peter Boyle
0bc38a69ce Adding PV pseudofermion in prep for DWF HMC.
Not compiled this yet, but cloned in from BFM.
2015-08-18 09:19:42 +01:00
Peter Boyle
25d0eae50c Adding PV pseudofermion in prep for DWF HMC.
Not compiled this yet, but cloned in from BFM.
2015-08-18 09:19:42 +01:00
Peter Boyle
24382d77bb Adding PV pseudofermion in prep for DWF HMC.
Not compiled this yet, but cloned in from BFM.
2015-08-17 23:14:48 +01:00