portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2024-11-14 01:35:36 +00:00
Code Releases Activity
2,048 Commits 86 Branches 14 Tags 74 MiB
92ec3404f8
Commit Graph

1416 Commits

Author SHA1 Message Date
azusayamaguchi
202078eb1b Cray / OpenSHMEM ordering differs 2016-10-21 09:07:20 +01:00
paboyle
a762b1fb71 MPI3 working with a bounce through shared memory on my laptop. 
Longer term plan: make the "u_comm_buf" in Stencil point to the shared region and avoid the
send between ranks on same node.
 2016-10-21 09:03:26 +01:00
paboyle
5b5925b8e5 Forgot to add 2016-10-20 17:09:40 +01:00
paboyle
b58adc6a4b commVector 2016-10-20 17:00:15 +01:00
paboyle
f9d5e95d72 allocator template typedefs moved to AlignedAllocator 2016-10-20 16:59:39 +01:00
paboyle
4f8e636a43 commVector 2016-10-20 16:59:16 +01:00
paboyle
9b39f35ae6 commVector different for SHMEM compat 2016-10-20 16:58:53 +01:00
paboyle
5fe2b85cbd MPI3 and shared memory support 2016-10-20 16:58:01 +01:00
paboyle
c7cccaaa69 Comm vector for shmem 2016-10-20 16:57:31 +01:00
paboyle
cbcfea466f MPI3 2016-10-20 16:57:14 +01:00
paboyle
4955672fc3 MPI3 2016-10-20 16:57:00 +01:00
paboyle
8c043da5b7 SHMEM and comms allocator made different 2016-10-20 16:56:05 +01:00
paboyle
3cbe974eb4 Layout 2016-10-20 16:55:21 +01:00
Antonin Portelli
997fd882ff Merge branch 'develop' into feature/feynman-rules 
# Conflicts:
#	lib/Threads.h
#	lib/qcd/action/fermion/WilsonFermion.cc
#	lib/qcd/action/fermion/WilsonFermion.h
#	lib/qcd/utils/SUn.h
#	lib/simd/Grid_avx.h
#	lib/simd/Intel512common.h
 2016-10-19 18:35:18 +01:00
paboyle
7af9b87318 Cache face tables to improve performance. 
Extract merge now looking poor.
 2016-10-18 09:51:37 +01:00
paboyle
811ca45473 GNU clang hack for AVX512 since there are missing reduce intrinsics in Clang 3.9 and GCC-6 AVX512 support 2016-10-17 16:23:21 +01:00
paboyle
bc1a4d40ba Faster integer handling avoid push_back 2016-10-17 16:16:44 +01:00
paboyle
c8079e6621 Time the face gateher in x-dir more carefully 2016-10-13 22:28:50 +01:00
azusayamaguchi
8b0d171c9a 32bit issue on the KNL code variant where byte offsets were stored 2016-10-12 17:49:32 +01:00
azusayamaguchi
8bbd9ebc27 Reversing changes to Stencil class 2016-10-12 13:47:20 +01:00
azusayamaguchi
6472b431f0 __rdpmc needed for gcc, clang++ 2016-10-12 12:29:08 +01:00
azusayamaguchi
bd205a3293 Fixing for non x86 and non KNL 2016-10-12 12:09:15 +01:00
azusayamaguchi
496beffa88 Fix non-KNL build 2016-10-12 12:06:08 +01:00
azusayamaguchi
9b63e97108 align not absolutely required and confuses clang++ 2016-10-12 11:51:21 +01:00
azusayamaguchi
81f2aeaece KNL streaming stores, and KNL performance coutners 2016-10-12 11:45:22 +01:00
paboyle
2d4a45c758 Typecast pointer 2016-10-12 09:14:15 +01:00
paboyle
a123dcd7e9 Static required for shmem. Reading same object twice requires csum reset 2016-10-12 00:29:57 +01:00
paboyle
6b27c42dfe Cosmetic 2016-10-12 00:29:39 +01:00
paboyle
f7c2aa3ba5 runtime by default 2016-10-12 00:29:13 +01:00
paboyle
7240d73184 Parallelise the x faces; fix the segv on KNL with comms 2016-10-11 22:21:07 +01:00
paboyle
42cd148f5e Base pointer for comms buffer under AVX512 assembly 2016-10-11 16:06:06 +01:00
paboyle
6e01264bb7 don't use static by default 2016-10-11 10:03:39 +01:00
paboyle
6f408256bc FMA4 option moved on the align 2016-10-11 10:03:01 +01:00
paboyle
8d11681aac verbose remove 2016-10-10 23:50:42 +01:00
paboyle
3d5c9a1ee9 No compile fix on clang++ 3.9 2016-10-10 23:50:13 +01:00
paboyle
dc389e467c axpy_ssp for any coeff type via template 2016-10-10 23:48:05 +01:00
paboyle
3619167d62 Mass parameter 2016-10-10 23:47:33 +01:00
paboyle
96f1d1b828 Debugged Domain wall and Overlap feynman rules (infinite Ls, finite mass). 2016-10-10 23:46:45 +01:00
paboyle
657e0a8f4d Mass parameter 2016-10-10 23:46:10 +01:00
paboyle
616e7cd83e Mass parameter 2016-10-10 23:45:48 +01:00
paboyle
6f26d2e8d4 Overlap tree level feynman rule 2016-10-10 23:45:18 +01:00
paboyle
c014574504 A "please implement me" feynman rule. If this were abstract virtual it would 
require/force implementation
 2016-10-10 23:44:00 +01:00
paboyle
d7ce164e6e Feynman rule for DWF 2016-10-10 23:43:36 +01:00
paboyle
c0d5b99016 Dminus 2016-10-10 23:43:19 +01:00
paboyle
09ca32d678 Dminus added for Cayley 2016-10-10 23:42:55 +01:00
paboyle
082ae350c6 static schedule by default 2016-10-10 23:42:30 +01:00
Guido Cossu
611b5d74ba Fix for AVX+FMA3 compilation 2016-10-10 15:26:17 +01:00
Guido Cossu
b56c9ffa52 Fix for AVXFMA 2016-10-10 14:43:37 +01:00
Guido Cossu
2e453dfbf5 Added some instrumentation to benchmark the force computation 2016-10-06 17:52:45 +01:00
paboyle
4089984431 Timing hooks 2016-10-06 09:25:12 +01:00
Guido Cossu
c78bbd0f8c Fix ASM compilation 2016-10-04 15:37:32 +01:00
Antonin Portelli
536e2ff073 *.inc removed: please don't commit these files either! 2016-09-27 11:54:03 +01:00
paboyle
87acd06990 Use streaming stores 2016-09-26 10:11:34 +01:00
paboyle
9353b6edfe Fenv out of grid namespace 2016-09-26 10:09:13 +01:00
paboyle
167cc2650e GNU SOURCE problem on travis 2016-09-26 09:58:09 +01:00
paboyle
7089b6d5a5 Setting up but not implemented some QED rules 2016-09-26 09:43:40 +01:00
paboyle
2ba7d43ddd Divide handling 2016-09-26 09:43:14 +01:00
paboyle
836e929565 Divide handling improved 2016-09-26 09:42:22 +01:00
paboyle
b6713ecb60 Momentum space rules for Overlap, DWF untested to date 2016-09-26 09:39:09 +01:00
paboyle
52a39f0fcd Divide in ET 2016-09-26 09:38:38 +01:00
paboyle
81a7a03076 Integer << 2016-09-26 09:38:17 +01:00
paboyle
16b37b956c divide goes to ET 2016-09-26 09:37:59 +01:00
paboyle
567b6cf23f demangle moves to logging 2016-09-26 09:36:51 +01:00
paboyle
296396646d FPE's on macos set up 2016-09-26 09:36:14 +01:00
Guido Cossu
5c190a1b8c Merge branch 'develop' into feature/hirep 2016-09-23 11:06:06 +01:00
Guido Cossu
c4ac6e7e8f Consolidating HMC interface 
Uniformed interface for standard action in fundamental rep and Hirep
 2016-09-23 10:47:42 +01:00
Guido Cossu
510e340e16 Debugged last commit for the Two index representation 2016-09-22 22:16:21 +01:00
Guido Cossu
6ffadca153 Restored number of colours to 3 2016-09-22 14:22:54 +01:00
Guido Cossu
b6597b74e7 Added support for the Two index Symmetric and Antisymmetric representations 
Tested for HMC convergence: OK
Added also a test file showing an example for mixed representations
 2016-09-22 14:17:37 +01:00
Antonin Portelli
0724f7af75 QPX single precision implementation 2016-09-19 18:09:12 +01:00
Antonin Portelli
2e74520821 removed libtool use (BG/Q compatibility) 2016-09-16 15:25:49 +01:00
Antonin Portelli
6dd75ad9e5 Merge branch 'develop' of github.com:paboyle/Grid into feature/bgq 2016-09-16 15:07:54 +01:00
Guido Cossu
fda408ee6f Added first lines for supporting Two Index representations 2016-09-13 10:43:30 +01:00
Guido Cossu
b9c80318a2 Merge branch 'develop' into feature/hirep 2016-09-13 10:01:51 +01:00
Guido Cossu
5df5d52d41 Fix for the Intel compiler 2016-09-12 17:17:20 +01:00
Guido Cossu
f76f281e58 Cleaning files after fix 2016-09-09 11:34:25 +01:00
Guido Cossu
aa20cc8b52 Fixing compilation error with AVX512 flag 2016-09-09 02:58:52 -07:00
Guido Cossu
0fd179fb33 Merge branch 'develop' into feature/hirep 2016-09-01 12:59:53 +01:00
Guido Cossu
f45ef8d114 Minor modification in ActionBase.h 2016-09-01 11:46:46 +01:00
paboyle
8535d433a7 Cold or hot must support any precisoin 2016-08-31 00:27:53 +01:00
paboyle
b573d1f35a Wilson tree level added 2016-08-31 00:27:04 +01:00
paboyle
0c1d7e4daf Mom space prop for Wilson action 2016-08-31 00:26:36 +01:00
paboyle
02e983a0cd Momentum space prop and free prop convolution 2016-08-31 00:26:02 +01:00
paboyle
d15ab66aae FFT moves higher in include order 2016-08-31 00:25:22 +01:00
paboyle
9005b82c6d Multi dim FFT, and normalisation fix 2016-08-31 00:24:52 +01:00
paboyle
3475f45ce7 Demangle support for typeid stuff 2016-08-31 00:23:48 +01:00
paboyle
0744f38866 Demangle support is useful 2016-08-31 00:23:28 +01:00
Guido Cossu
fd5614738d Merge branch 'develop' into feature/hirep 2016-08-30 18:21:36 +01:00
Guido Cossu
b0d3e4bb2c Separating travis builds 2016-08-30 13:44:07 +01:00
Guido Cossu
b512ccbee6 HMC for Adjoint fermions works 
Accepts and reproduces known results

Check initial instability of inverters
when starting from hot configurations
 2016-08-30 11:31:25 +01:00
paboyle
8c89391c02 FFTW unresolved fixed when no fftw3.h 2016-08-24 16:41:47 +01:00
paboyle
bfac5195b8 tidy up 2016-08-24 16:38:36 +01:00
paboyle
744691097f Printing 2016-08-24 15:05:56 +01:00
paboyle
ff6da364e8 FFT double and single precision gives good performance now in multithreaded code. 2016-08-24 15:05:00 +01:00
Antonin Portelli
4d11a6f5f2 first commit for QPX intrinsics 2016-08-23 14:41:44 +01:00
paboyle
88be3b39bb Merge branch 'develop' of https://github.com/paboyle/Grid into develop 2016-08-22 18:29:36 +01:00
paboyle
356e7940fd fftw can be switched off 2016-08-22 16:24:49 +01:00
paboyle
73ce476890 Include fftw headers 2016-08-22 16:24:21 +01:00
paboyle
e423a09974 FFT improved and test_FFT passing under MPI 8 processes, 8^4 for LatticeComplexD and LatticeSpinMatrixD 2016-08-18 02:23:21 +01:00
paboyle
17097a93ec FFTW test ran over 4 mpi processes. 2016-08-17 01:33:55 +01:00