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
62601bb649
Bug fix
2016-07-08 20:46:29 +01:00
ef97e32152
Adding persistent communicators
2016-07-08 17:16:08 +01:00
c667d9fdcc
Trying to make compile clean on travis; seem to have a make -j 4 problem with fftw
2016-07-07 23:26:39 +01:00
7dbb94bab2
Update
2016-07-07 22:51:37 +01:00
236dcc820b
typo fix
2016-07-07 22:46:11 +01:00
a42a441a6a
Rename the reconfigure script to ./autogen.sh
2016-07-07 22:35:45 +01:00
a0676beeb1
Open up dependency on Eigen and FFTW
2016-07-07 22:31:07 +01:00
fc4a043663
Colors and banner clean up
2016-07-02 16:15:38 +01:00
61ba50665e
Merge branch 'hotfix/v0.5.1' into develop
2016-07-01 16:34:30 +01:00
bfe14000a9
Double compile fix
2016-07-01 16:33:51 +01:00
1ceff48133
Merge branch 'release/v0.5.0' into develop
2016-06-30 15:15:59 -07:00
680645f849
Merge branch 'release/v0.5.0'
2016-06-30 15:15:03 -07:00
3fc6e03ad1
Version file
2016-06-30 14:44:09 -07:00
2d6614f3a1
Merge branch 'feature/knl-cache-opt' into develop
2016-06-30 14:36:20 -07:00
4e041b5103
Merge branch 'feature/knl-cache-opt' of https://github.com/paboyle/Grid into feature/knl-cache-opt
2016-06-30 14:36:08 -07:00
712b9a3489
Asm only for avx512
2016-06-30 14:35:02 -07:00
bdaa5b1767
Updated to have perfect prefetching for the s-vectorised kernel with any cache blocking.
2016-06-30 14:35:02 -07:00
8fcefc021a
Improved the prefetching when using cache blocking codes
2016-06-30 14:35:02 -07:00
1445189361
COntrol the prefetch strategy
2016-06-30 14:35:02 -07:00
05c884a62a
Prefetch change
2016-06-30 14:35:01 -07:00
a25bec87d9
Prefetch during save
2016-06-30 14:35:01 -07:00
2d8bb4c594
Tweaks
2016-06-30 14:35:01 -07:00
51cb2d4328
update file lists
2016-06-30 14:35:01 -07:00
6d58cb2a68
Enable reordering of the loops in the assembler for cache friendly.
...
This gets in the way of L2 prefetching however. Do next next link in stencil
prefetching.
2016-06-30 14:35:01 -07:00
c8b35d960c
Merge branch 'develop' of https://github.com/paboyle/Grid into feature/knl-cache-opt
2016-06-30 14:30:49 -07:00
532f41dd61
Asm only for avx512
2016-06-30 14:00:34 -07:00
661b0ab45d
Updated to have perfect prefetching for the s-vectorised kernel with any cache blocking.
2016-06-30 13:07:42 -07:00
4bc08ed995
Improved the prefetching when using cache blocking codes
2016-06-26 12:54:14 -07:00
b2933a0557
COntrol the prefetch strategy
2016-06-25 12:55:25 -07:00
db057cc276
Prefetch change
2016-06-25 12:54:50 -07:00
22e88eaf54
Prefetch during save
2016-06-25 12:54:14 -07:00
09fe3caebd
Tweaks
2016-06-25 11:08:05 -07:00
5e02392f9c
Fixed compilation error for benchmark_dwf
...
Some parts were assuming floating point precision
2016-06-20 12:30:51 +01:00
17a8f51a9b
update file lists
2016-06-19 11:59:10 -07:00
1b7f88dd00
Enable reordering of the loops in the assembler for cache friendly.
...
This gets in the way of L2 prefetching however. Do next next link in stencil
prefetching.
2016-06-19 11:45:58 -07:00
portelli
d6737e4bd8
Travis fix for Linux clang builds
2016-06-14 19:15:08 +01:00
portelli
d539888e57
Merge pull request #37 from rprollins/fix/mpi_communicator
...
Removed write to stdout in constructor for MPI CartesianCommunicator
2016-06-14 17:25:40 +01:00
86187d7cca
Removed write to stdout in constructor for MPI CartesianCommunicator
2016-06-14 15:34:20 +01:00
87418e7df1
Slightly faster prefetching perf.
2016-06-13 02:32:52 -07:00
55f65b81b5
Improvements to the assembler interface that let us move chunks of the
...
site and s loop into the kernels. This will save on function call overhead and
guarantee L2 prefetching strategy is right since OMP can't distribute the
sub-chunks of work.
2016-06-09 01:12:36 -07:00
d9408893b3
Prefetching in the normal kernel implementation.
2016-06-08 05:43:48 -07:00
05acc22920
placeholder for non temporal loads optimisation
2016-06-07 13:18:21 -07:00
8ac021de73
Added a test an fixed it for red black precon Ls innermost vectorised DWF
2016-06-07 13:16:56 -07:00
e503ef5590
Cleaned up
2016-06-07 00:11:36 +01:00
a7682b0060
Only instantiate the one routine to avoid duplicate symbol under g++5/MacOS
2016-06-06 23:48:21 +01:00
d4c9d71fc8
Merge branch 'master' of https://github.com/paboyle/Grid
2016-06-06 07:06:54 -07:00
786ca52c43
Problems remain in the red black preconditioning of the Ls vectorisation
2016-06-06 07:05:51 -07:00
048ac04abc
Update Benchmark_dwf.cc
2016-06-03 13:44:41 +01:00
f78d89bcbe
Update Lebesgue.cc
...
kill verbose
2016-06-03 13:33:42 +01:00
paboyle
Guido Cossu
portelli
Richard Rollins
Azusa Yamaguchi
Peter Boyle