portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2026-07-17 15:43:27 +01:00
Code Releases Activity
155 Commits 95 Branches 14 Tags
9f9796b888c1721f6d2e53988413b57fe967208b
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Peter Boyle 55ccb8ccf4 Wilson perf improvements with Gauge prefetching 2015-05-06 06:37:21 +01:00
Peter Boyle b9d16a7191 streaming store cases 2015-05-05 18:14:09 +01:00
Peter Boyle 07d57b6d55 Streaming store option 2015-05-05 18:13:06 +01:00
Peter Boyle 5ebc7a1756 Added streaming stores 2015-05-05 18:09:28 +01:00
Peter Boyle bf60764e4b Updated bandwidth test 2015-05-05 18:08:53 +01:00
Peter Boyle 890b13dd5b Added a makefile 2015-05-05 17:56:42 +01:00
Peter Boyle aeda7b923d Back to vector for now; cost of init loop is clear in the a*x + y 
loop in memory benchmark and must move to better container class.
 2015-05-03 09:48:13 +01:00
Peter Boyle 193860dbc8 Comms and memory benchmarks added 2015-05-03 09:44:47 +01:00
Peter Boyle 99a1ff423d Added a comms benchmark 2015-05-02 23:51:43 +01:00
Peter Boyle f663be2a6c Added a comms benchmark 2015-05-02 23:42:30 +01:00
Peter Boyle 4a1d4f1b3c Starting a benchmarking sub dir 2015-05-02 17:52:36 +01:00
Peter Boyle 31fd146cc0 Improving the byte swap support for portability 2015-05-01 10:57:33 +01:00
Peter Boyle c770f96be7 Merge branch 'master' of https://github.com/paboyle/Grid 2015-04-30 16:40:13 +01:00
Peter Boyle a98c01c86a Integrated Lebesgue code and been playing with alternate implementations of the wilson dop without 
any particular success in increasing the performance.
 2015-04-30 16:39:06 +01:00
Peter Boyle d5b1bfb4bb Merge pull request #1 from mspraggs/patch-1 
Added <map> include to GridNerscIO.h
 2015-04-30 09:46:48 +01:00
Peter Boyle b7090ebba4 Benchmark wilson dhop now; 14.6GF on one core, not as fast as SU(3)xSU(3) [23GF] but still not too shabby. 
Disassembling output shows ugly sequences in the permute sector. Could comparatively benchmark with and without
the if-else structure to see how much I'm losing.

Drops to 9GF as it falls out of cache. Moving to Lebesgue ordering should help there. Substantive progress.
 2015-04-29 06:50:18 +01:00
Peter Boyle c72db6c6f6 Fixed the stencil sector and Wilson now agrees between stencil based implementation 
and the cshift based implementation. Managed to reduce the volume of code in this
sector a little, but consolidation would be good, perhaps taking common
logic out into simple helper functions
 2015-04-29 06:23:56 +01:00
Peter Boyle 25d523c0f4 Shaken out stencil to the point where I think wilson dslash is correct. 
Need to audit code carefully, consolidate between stencil and cshift,
and then benchmark and optimise.
 2015-04-28 08:11:59 +01:00
Peter Boyle f159495a9d Reworking CSHIFT and Stencil. Implementing Wilson and discovered rework is required 2015-04-27 13:45:07 +01:00
Peter Boyle 94f728bee4 Big updates with progress towards wilson matrix 2015-04-26 15:51:09 +01:00
Peter Boyle 51f0da7b93 Starting the implementation of wilson; incomplete and committing non-functional code which 
is not yet included from elsewhere or linked to the build system.
 2015-04-25 14:33:02 +01:00
Peter Boyle 9dacdc947d Update to TODO list 2015-04-25 13:04:26 +01:00
Peter Boyle c5fa18eb20 Added two spinor functionality required to support the Wilson hopping term. 2015-04-25 12:54:06 +01:00
Peter Boyle 8b4073d84c Dirac done ; remove from TODO 2015-04-24 22:56:37 +01:00
Peter Boyle 9ec3529864 Improved the gamma quite a bit. 
Serial rng's which are set on node zero and broadcaste
 2015-04-24 20:21:40 +01:00
Peter Boyle 42eac283e2 static names and enum list 2015-04-24 19:12:14 +01:00
Peter Boyle 38598190c3 Vectors now too and right multiple of matrix with gamma 2015-04-24 19:08:29 +01:00
Peter Boyle 2e275e1e65 Removed summation 2015-04-24 18:42:44 +01:00
Peter Boyle 80463ecaea Cleared the code out from Grid_summation to lattice/Grid_lattice_transfer.h 2015-04-24 18:41:34 +01:00
Peter Boyle 128ad0999f Moved code from summation into transfer and reduction 2015-04-24 18:40:44 +01:00
Peter Boyle d707c4e0a3 First implementation of Dirac matrices as a Gamma class. 2015-04-24 18:20:03 +01:00
Peter Boyle b9939e3974 Reorganised the TODO. Really getting somewhere 2015-04-23 20:42:30 +01:00
Peter Boyle 3083d2e908 Rename Grid_QCD 2015-04-23 20:42:09 +01:00
Peter Boyle 898f64cdd7 move 2015-04-23 20:41:22 +01:00
Peter Boyle 52a6ba9767 Slice summation working. May move this into lattice/Grid_lattice_reduction however 2015-04-23 15:13:00 +01:00
Peter Boyle 4d2198ea56 Begginings of slice summation and subblocking 2015-04-23 11:04:59 +01:00
Peter Boyle 7007d6a176 Consolidate index to coor in a single routine 2015-04-23 11:04:19 +01:00
Peter Boyle a37a9789c9 Snippets from Guido to optimise Reduce 2015-04-23 08:31:40 +01:00
Peter Boyle 5c8858f31b Better description of Intel's many ISA targets 2015-04-23 08:02:51 +01:00
Peter Boyle 47292de769 Fixing endian on linux I hope 2015-04-23 07:51:15 +01:00
Peter Boyle b32c14b433 Got the NERSC IO working and fixed a bug in cshift. 2015-04-22 22:46:48 +01:00
Peter Boyle 42f167ea37 Rework of RNG to use C++11 random. Should work correctly maintaining parallel RNG across 
a machine. If a "fixedSeed" is used, randoms should be reproducible across different machine
decomposition since the generators are physically indexed and assigned in lexico ordering.
 2015-04-19 14:55:58 +01:00
Peter Boyle f6ab726cef Update to task list 2015-04-19 14:55:16 +01:00
Peter Boyle 5483ed641e Split all OMP directives into lattice subdir for easy maintainance of 
parallelism and future OMP 4.0 offload.
 2015-04-18 22:17:01 +01:00
Peter Boyle d929f88421 Update 2015-04-18 22:16:31 +01:00
Peter Boyle 6bd11d920a Finishing the reorg 2015-04-18 21:24:10 +01:00
Peter Boyle 8ddfa7e6b0 Reorganisation 2015-04-18 21:23:32 +01:00
Peter Boyle e5a25dfcb1 Build reorg with which I am a bit happier 2015-04-18 21:22:50 +01:00
Peter Boyle c94b7cc43c Clean up 2015-04-18 20:52:40 +01:00
Peter Boyle 25a8266638 More files, shorter each. 2015-04-18 20:45:00 +01:00
Peter Boyle 6eae2c1083 Shrinking and organising the files 2015-04-18 20:44:19 +01:00
Peter Boyle 354347ce91 Split up into multiple files 2015-04-18 18:54:30 +01:00
Peter Boyle 2eb5ab26bf splitting into smaller, multiple files for readability and easy find. 2015-04-18 18:47:43 +01:00
Peter Boyle af72ade26a Cleanup 2015-04-18 18:37:56 +01:00
Peter Boyle e7661d3b12 Reorg 2015-04-18 18:37:22 +01:00
Peter Boyle cffad66894 Reorganise to keep files smaller 2015-04-18 18:36:48 +01:00
Peter Boyle df9056eb4b Rename 2015-04-18 17:10:45 +01:00
Peter Boyle 2ee9322a8f Clean up caps. 2015-04-18 17:09:48 +01:00
Peter Boyle b0ce9e3934 Clean up capitalisation 2015-04-18 17:09:24 +01:00
Peter Boyle 5e9a82b72b Rename 2015-04-18 17:07:37 +01:00
Peter Boyle b5356935e9 Renaming 2015-04-18 17:07:09 +01:00
Peter Boyle eb0925d702 Cleaing up 2015-04-18 16:42:47 +01:00
Peter Boyle b47d33c4f1 Shaken out the peekIndex support. 
Hardwire constants "SpinIndex, ColourIndex" and LorentzIndex in Grid_QCD.h
 2015-04-18 16:17:41 +01:00
Peter Boyle 26148c3323 Build reorg 2015-04-18 14:56:05 +01:00
Peter Boyle c656164015 Reorg of build structure 2015-04-18 14:55:00 +01:00
Peter Boyle 57586c8e05 peekIndex update 2015-04-18 14:36:01 +01:00
Peter Boyle d6c02e72d6 typo 2015-04-18 12:40:55 +01:00
paboyle d4aa37112d Update README.md 2015-04-18 12:21:37 +01:00
Peter Boyle 81367eaa12 Got traceIndex, transposeIndex fully working. 
Need to think about peekIndex interface and () based indexing.
 2015-04-18 12:17:13 +01:00
Peter Boyle 23df6cf18e SSE flag changed 2015-04-16 17:22:52 +01:00
Peter Boyle 3e41cfecf1 Better code 2015-04-16 15:20:19 +01:00
Peter Boyle 5aac6dc85b spin trace type work 2015-04-16 14:48:21 +01:00
Peter Boyle 6d71ff98e5 Improving the trace support to support any index tracing and simplifying 
implmentation in some ways
 2015-04-16 14:47:28 +01:00
Peter Boyle 3cb04f555d Typo in capital 2015-04-15 12:03:38 +01:00
Peter Boyle b59553bd65 Some bug fixes 2015-04-14 23:20:16 +01:00
Peter Boyle 94f9e781f4 Reduce now going through MPI. 2015-04-14 22:40:40 +01:00
Peter Boyle 2ae42c40a8 Modified 2015-04-14 20:25:51 +01:00
Peter Boyle 1eee664092 Stencil code pretty much shaken out. 
Beginning of inner product and norm2.
 2015-04-14 20:22:04 +01:00
Peter Boyle eb2dd37e3c where switched back on 2015-04-10 05:54:02 +02:00
Peter Boyle 69d578478a Fixing the comms=none compile 2015-04-10 05:53:09 +02:00
Peter Boyle d9a454bc9f Fixing nocompile 2015-04-10 05:24:01 +02:00
Peter Boyle 516bc0c666 MPI exposed incorrectly in main 2015-04-10 05:22:36 +02:00
Peter Boyle f373517d2e Patch for comms none nocompile 2015-04-10 05:21:48 +02:00
Peter Boyle 8f5281563e "where" and integer comparisons logic implemented for conditional 
assignment. LatticeCoordinate helper to get global (reduced) coordinate.

Some more work of similar type perhaps needed, but the bulk of the required
structure for masked array assignment is now in place.
 2015-04-09 08:06:03 +02:00
Peter Boyle 4666acfbb0 Remove stub files 2015-04-06 11:29:55 +01:00
Peter Boyle 4cd678ddb4 Some popular configure commands 2015-04-06 11:28:00 +01:00
Peter Boyle 48a38ef4fd Major rework of extract/merge/permute processing debugged and working. 2015-04-06 11:26:24 +01:00
Peter Boyle 57cd8d87f5 Removing older file 2015-04-06 09:27:17 +01:00
Peter Boyle e06a11ee5e Bringing in LatticeInteger with the idea of implemented predicated 
assignment, subsets etc.
c.f the QDP++ "where" syntax
 2015-04-06 06:30:48 +01:00
Peter Boyle d5eee231e0 Clean up but no major changes 2015-04-03 22:54:13 +01:00
Peter Boyle d081715504 TODO list for preparing this for real use and QDP++ replacement. 2015-04-03 09:28:58 +01:00
Peter Boyle d066450a24 Reorg 2015-04-03 05:51:05 +01:00
Peter Boyle b47314f726 MPI added 2015-04-03 05:34:51 +01:00
Peter Boyle 2de009d994 Patch 2015-04-03 05:33:13 +01:00
Peter Boyle cebf90195c Merge branch 'master' of https://github.com/paboyle/Grid 2015-04-03 05:32:12 +01:00
Peter Boyle cc21f0a709 Removing the Xcode project 2015-04-03 05:30:58 +01:00
Peter Boyle d198fcbc1c Renamed the namespace to Grid 2015-04-03 05:29:54 +01:00
Peter Boyle c86f79c4be Rename some files to make naming consistent 2015-04-03 04:58:03 +01:00
Peter Boyle 9ba89e64dc MPI is now working and passing basic tests. Will start to construct a more sensible test suite shortly 
since testing requirements now go beyond what a single Grid_main.cc can do.

Will need a more organised src tree for this and will require substantial reorg of build system.
 2015-04-03 04:52:53 +01:00
Peter Boyle 1a9d4d3655 Merge branch 'master' of https://github.com/paboyle/Grid 2015-03-29 22:05:16 +01:00