ff6da364e8
FFT double and single precision gives good performance now in multithreaded code.
2016-08-24 15:05:00 +01:00
88be3b39bb
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
2016-08-22 18:29:36 +01:00
356e7940fd
fftw can be switched off
2016-08-22 16:24:49 +01:00
73ce476890
Include fftw headers
2016-08-22 16:24:21 +01:00
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
17097a93ec
FFTW test ran over 4 mpi processes.
2016-08-17 01:33:55 +01:00
4ab7dbfd57
Instantiate
2016-08-15 23:00:40 +01:00
90e70790f3
Feature for z-Mobius prep
2016-08-15 22:31:29 +01:00
32bc7a6ab8
MPI back out of change that hangs
...
AVX2 for clang, gcc needs the -mfma flag.
2016-08-05 10:36:00 +01:00
93d29bb699
build system improvements after discussion with Peter
2016-08-04 16:19:59 +01:00
9e5b934d21
improved LAPACK configuration
2016-08-02 17:26:54 +01:00
e9f30cab2c
first working version for the new build system
2016-07-30 17:53:18 +01:00
f9e90eeb1f
Sign error on the force for 4d fields fixed
2016-07-16 01:52:44 +01:00
fad5c675eb
sign error on the 4d gparity force
2016-07-16 01:51:56 +01:00
4908b77d46
Fixed conflicts. PLEASE avoid making wholesale cosmetic only changes, this created
...
a HUGE amount of difficult to resolve and understand conflicts .
Wholesale formatting, reordering functions etc... in a central file like Tensor_class
or Grid_vector_types while others are also editing without making substantial functionality
changes creates pain.
2016-07-15 20:59:07 +01:00
f4dd5062d7
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
2016-07-15 19:26:06 +01:00
980ff18956
Solving the instantiation no compile issue
2016-07-15 17:19:44 +01:00
1a6c7204ac
Disable instantiation; Use cache version instead
2016-07-15 00:34:39 +01:00
49310fbab3
Done with red black change over
2016-07-15 00:08:43 +01:00
5c0c8efb9e
Updated file list
2016-07-15 00:02:11 +01:00
dfd714e1ef
Multiple implementations for the 5d hopping terms, depending on cache friendly
...
ops and/or the 5th direction being vectorised
All use 4d redblack.
2016-07-15 00:00:09 +01:00
79a8ca1a62
Rewrite for performance. Impl dependent instantiations give
...
4d linalg impls of the 5d hopping terms (and inverse)
Cache friendly loop orderings of the above
Dense matrix stored and apply to the above
-- Switch to Ls vectorised, and use dense matrix approach for the MooeeInv
and rotate/shift of the Mooee M5D routines.
2016-07-14 23:58:15 +01:00
fb45eb2eb2
5d ls vec rename of impl class
2016-07-14 23:57:26 +01:00
a307274c96
Fermion impl rename for ls vectorised 5d approaches
2016-07-14 23:56:13 +01:00
3f2c44a5fe
Updating the class to 5d selection based on impl type
2016-07-14 23:55:26 +01:00
48fb1cdc11
Update domain 5d vectorised impl type, move the type over to 4d redblack with
...
the dense OO inverse
2016-07-14 23:54:35 +01:00
8a79e93cc2
Rename the 5d domain wall fermion vectorised Ls impl class
2016-07-14 23:53:00 +01:00
dd62a61c5c
Added broadcast and rotation of simd vectors
2016-07-14 23:49:00 +01:00
8f47d0b5ab
Rotation needed for hopping term in fifth dim with Ls vectorised fields
2016-07-14 23:45:36 +01:00
42af132dab
Fix for chris kellys request to peek poke on checkerboarded fields
2016-07-14 23:44:48 +01:00
adbc7c1188
Adding files for multiple implementations (cache opt) and Ls vectorisation
...
of the 5D cayley form chiral fermions for the 5d matrix. With Ls entirely
in the vector direction, s-hopping terms involve rotations.
The serial dependence of the LDU inversion for Mobius and 4d even odd
checkerboarding is removed by simply applying Ls^2 operations (vectorised
many ways) as a dense matrix operation.
This should give similar throughput but high flops (non-compulsory flops)
but enable use of the KNL cache friendly kernels throughout the code.
Ls is still constrained to be a multiple of Nsimd, which is as much as 8 for AVX512
with single precision.
2016-07-14 22:59:21 +01:00
6f47fbb1e2
Disabled parallel for loops in ExtractSlice and InsertSlice due to race conditions. Likely will need to do so for localConvert too.
2016-07-13 10:49:18 -04:00
a3c0fb79b6
Fix to iVector and iMatrix pokeIndex and checkerboard local site indexing.
2016-07-11 17:15:22 -04:00
62601bb649
Bug fix
2016-07-08 20:46:29 +01:00
ef97e32152
Adding persistent communicators
2016-07-08 17:16:08 +01:00
a0676beeb1
Open up dependency on Eigen and FFTW
2016-07-07 22:31:07 +01:00
c5106d0c03
Bugfix
2016-07-07 16:06:30 -04:00
3c49ddfaa4
Merge branch 'temporary-smearing' into develop
2016-07-07 14:04:59 +01:00
ffb8b3116c
Tested smeared RHMC Wilson1p1, accepting
2016-07-07 11:49:36 +01:00
dd8cfff111
Another fix for pedantic compilers
2016-07-06 18:22:15 -04:00
184642adb0
Fix for pedantic compilers
2016-07-06 18:15:15 -04:00
4774a3bcd2
Generalized HotConfiguration and functions it calls to accept gauge fields with precision other than the default.
2016-07-06 18:01:08 -04:00
25fafa9a89
Comment
2016-07-06 16:19:41 -04:00
85ed8175cb
Implemented mixed precision CG. Fixed filelist to exclude lib/Old directory and include Config.h.
2016-07-06 15:57:04 -04:00
df5c788ef2
Merge branch 'develop' into feature/multi_prec
2016-07-06 14:52:28 -04:00
15f22425c8
Added option to prevent CG from exiting when it fails to converge
2016-07-06 14:50:01 -04:00
e87182cf98
Debugged the copy constructor of the Lattice class
2016-07-06 15:31:00 +01:00
e3d5319470
Debugged the real() and imag() functions and added tests to Test_Simd
2016-07-06 14:16:03 +01:00
3e3b367aa9
Small changes in the Log files
2016-07-05 15:05:28 +01:00
3e80947c2b
Cleaned up HMC output. Tested smeared HMCs for single precision (OK)
2016-07-05 12:03:54 +01:00
