fionnoh
|
b5fc5e2030
|
All to all module update that hit a promising milestone. Commiting for a reference for future changes.
|
2018-06-20 10:59:07 +01:00 |
|
Daniel Richtmann
|
cc5d025ea4
|
WilsonMG: Adapt staggered GMRES/MR tests to "new" constructor
|
2018-06-18 16:20:20 +02:00 |
|
paboyle
|
6c97a6a071
|
Coalescing version of the kernel
|
2018-06-13 20:52:29 +01:00 |
|
paboyle
|
73bb2d5128
|
Ugly hack to speed up compile on GPU; we don't use the hand kernels on GPU anyway so why compile
|
2018-06-13 20:35:28 +01:00 |
|
paboyle
|
b710fec6ea
|
Gpu code first version of specialised kernel
|
2018-06-13 20:34:39 +01:00 |
|
paboyle
|
b2a8cd60f5
|
Doubled gauge field is useful
|
2018-06-13 20:27:47 +01:00 |
|
paboyle
|
867ee364ab
|
Explicit instantiation hooks
|
2018-06-13 20:27:12 +01:00 |
|
paboyle
|
25becc9324
|
GPU tweaks for benchmarking; really necessary?
|
2018-06-13 20:26:07 +01:00 |
|
paboyle
|
94d1ae4c82
|
Some prep work for GPU shared memory. Need to be careful, as will try GPU direct
RDMA and inter-GPU memory sharing on SUmmit later
|
2018-06-13 20:24:06 +01:00 |
|
paboyle
|
2075b177ef
|
CUDA_ARCH more carefule treatment
|
2018-06-13 20:22:34 +01:00 |
|
paboyle
|
847c761ccc
|
Move sfw IEEE fp16 into central location
|
2018-06-13 20:22:01 +01:00 |
|
paboyle
|
8287ed8383
|
New GPU vector targets
|
2018-06-13 20:21:35 +01:00 |
|
paboyle
|
e6be7416f4
|
Use managed memory
|
2018-06-13 20:14:00 +01:00 |
|
paboyle
|
26863b6d95
|
User Managed memory
|
2018-06-13 20:13:42 +01:00 |
|
paboyle
|
ebd730bd54
|
Adding 2D loops
|
2018-06-13 20:13:01 +01:00 |
|
paboyle
|
066be31a3b
|
Optional GPU target SIMD types; work in progress and trying experiments
|
2018-06-13 20:07:55 +01:00 |
|
paboyle
|
7a4c142955
|
Add GPU specific simd targets
|
2018-06-13 19:55:30 +01:00 |
|
Daniel Richtmann
|
ddcb53bce2
|
Merge remote-tracking branch 'upstream/develop' into feature/wilsonmg
|
2018-06-13 09:50:37 +02:00 |
|
Daniel Richtmann
|
d1c80e1d46
|
WilsonMG: Correct years in copyright line
|
2018-06-13 09:44:09 +02:00 |
|
Daniel Richtmann
|
c73cc7d354
|
WilsonMG: Add tests with MG preconditioner running single precision, outer solver running in double
|
2018-06-12 16:10:48 +02:00 |
|
Daniel Richtmann
|
49fdc324a0
|
WilsonMG: Make MG correctness checks abort on failing tests
|
2018-06-12 16:10:48 +02:00 |
|
Daniel Richtmann
|
f32714a2d1
|
WilsonMG: Make running MG correctness checks optional via commandline
|
2018-06-12 16:10:48 +02:00 |
|
Daniel Richtmann
|
73a955be20
|
WilsonMG: Move tests for Wilson & WilsonClover into separate files
|
2018-06-12 16:10:48 +02:00 |
|
Daniel Richtmann
|
66b7a0f871
|
WilsonMG: Move multigrid class to separate file
|
2018-06-12 16:10:48 +02:00 |
|
Daniel Richtmann
|
2ab9d4bc56
|
WilsonMG: Fix random behavior in GMRES
From time to time I saw random since the basis vectors were not initialized
properly.
|
2018-06-12 15:01:31 +02:00 |
|
Daniel Richtmann
|
4f41cd114d
|
WilsonMG: Add a mixed precision version of FGMRES
This version does everything in double prec but accepts a preconditioner working
in single precision.
|
2018-06-12 15:01:31 +02:00 |
|
Daniel Richtmann
|
11c4f5e32c
|
WilsonMG: Provide command line switch for reading in input xml + move default params to constructor of MultiGridParams
|
2018-06-12 15:01:31 +02:00 |
|
Daniel Richtmann
|
e9b9550298
|
WilsonMG: Fix incompatibility with single prec MG in construction of simd layout on coarser grids
|
2018-06-12 15:01:31 +02:00 |
|
Daniel Richtmann
|
7564fedf68
|
WilsonMG: Set subspace to zero to avoid random behavior
|
2018-06-12 15:01:31 +02:00 |
|
|
|
8db0ef9736
|
Merge pull request #168 from jch1g10/feature/qed-fvol
Feature/qed fvol
|
2018-06-08 20:09:06 +02:00 |
|
Guido Cossu
|
95d4b46446
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2018-06-08 11:30:29 +01:00 |
|
paboyle
|
251b904a28
|
Merge branch 'release/ISC-freeze-2'
|
2018-06-04 21:09:48 +01:00 |
|
paboyle
|
5dfd216a34
|
Better thread safety
|
2018-06-04 21:08:44 +01:00 |
|
paboyle
|
5a112feac3
|
Merge branch 'release/ISC-freeze-1'
|
2018-06-04 18:49:40 +01:00 |
|
paboyle
|
c2e8d0aa88
|
Solve g++ problem on the lanczos test
|
2018-06-04 18:34:15 +01:00 |
|
James Harrison
|
0fe5aeffbb
|
Merge branch 'feature/hadrons' into feature/qed-fvol
|
2018-06-04 16:59:43 +01:00 |
|
James Harrison
|
7fbc469046
|
Merge branch 'develop' into feature/hadrons
|
2018-06-04 16:58:30 +01:00 |
|
paboyle
|
bf96a4bdbf
|
Merge branch 'master' into develop
|
2018-06-04 14:03:11 +01:00 |
|
paboyle
|
84685c9bc3
|
Overflow fix
|
2018-06-04 13:42:07 +01:00 |
|
fionnoh
|
a8d4156997
|
Added a Hadrons module that computes the all-to-all v and w vectors
|
2018-05-31 17:18:58 +01:00 |
|
fionnoh
|
c18074869b
|
Changes to Hadrons SchurRB solver to allow for a subtract_guess boolean to be passed
|
2018-05-31 17:17:16 +01:00 |
|
fionnoh
|
f4c6d39238
|
CHanges made to SchurRB solvers to allow for the subtraction of a guess after solve
|
2018-05-31 17:16:20 +01:00 |
|
|
|
200d35b38a
|
Merge branch 'develop' into feature/hadrons
|
2018-05-28 11:52:47 +02:00 |
|
|
|
eb52e84d09
|
Merge branch 'feature/hadrons' of github.com:paboyle/Grid into feature/hadrons
|
2018-05-28 11:50:27 +02:00 |
|
|
|
72abc34764
|
Merge pull request #166 from guelpers/feature/hadrons
Feature/hadrons
|
2018-05-28 11:49:46 +02:00 |
|
|
|
e3164d4c7b
|
Hadrons: env function to get volume in double
|
2018-05-28 11:39:17 +02:00 |
|
James Harrison
|
f5db386c55
|
Change MODULE_REGISTER_NS -> MODULE_REGISTER in UnitEM, ScalarVP and VPCounterTerms
|
2018-05-22 16:16:21 +01:00 |
|
James Harrison
|
294ee70a7a
|
Merge branch 'feature/hadrons' into feature/qed-fvol
# Conflicts:
# extras/Hadrons/modules.inc
# lib/qcd/action/gauge/Photon.h
|
2018-05-21 18:02:41 +01:00 |
|
Azusa Yamaguchi
|
013ea4e8d1
|
Merge branch 'feature/staggered-comms-compute' into develop
|
2018-05-21 13:11:56 +01:00 |
|
Azusa Yamaguchi
|
7fbbb31a50
|
Merge branch 'develop' into feature/staggered-comms-compute
Conflicts:
lib/qcd/action/fermion/ImprovedStaggeredFermion.cc
|
2018-05-21 13:07:29 +01:00 |
|
