|
|
add86cd7f4
|
Abandon ET for clover application, use construct similar to multLink
|
2022-02-01 23:09:06 +01:00 |
|
|
|
e83423fee6
|
Refactor clover to align with other files and prepare for upcoming changes
|
2022-02-01 23:09:06 +01:00 |
|
|
|
195ab2888d
|
Merge branch 'develop' into develop
|
2021-10-27 20:26:57 -04:00 |
|
|
|
ba7e371b90
|
Warning free compile on Tursa.
Hopefully got all reqd virtual dtors
|
2021-10-21 19:56:52 +01:00 |
|
|
|
4b24800132
|
AVX512 drop mixed precision as well
|
2021-09-15 16:29:47 -04:00 |
|
|
|
3d0f88e702
|
A64FX drop mixed precision as well
|
2021-09-15 18:38:32 +02:00 |
|
|
|
4c88104a73
|
Fix compile warns
|
2021-09-11 23:08:05 +01:00 |
|
|
|
770680669d
|
Whitespace removal.
|
2021-08-04 09:21:59 +01:00 |
|
|
|
0cdfc5cf22
|
Merge remote-tracking branch 'upstream/develop' into develop
|
2021-07-30 14:40:55 +01:00 |
|
|
|
8cfc7342cd
|
staggered hand unroll read coalesce
|
2021-05-05 14:17:18 -07:00 |
|
|
|
54c6b1376d
|
Quick fix of conserved current implementation in CayleyFermion5D. Now function treats current insertion with appropriate periodic boundary conditions in the mu=3 direction.
|
2021-04-21 16:56:46 +01:00 |
|
|
|
f3f11b586f
|
Tadpole sign now in front of forward hopping term to be consistent with previous implementation and analytic form.
|
2021-04-17 12:44:27 +01:00 |
|
|
|
8083e3f7e8
|
Sign factor for tadpole implementation corrected.
|
2021-04-15 11:14:31 +01:00 |
|
|
|
895244ecc3
|
Merge with upstream; implemented conserved tadpole for Shamir action.
|
2021-04-06 13:46:33 +01:00 |
|
|
|
addeb621a7
|
Implemented tadpole operator for Shamir action.
|
2021-04-06 13:45:37 +01:00 |
|
|
|
bb89a82a07
|
Staggered coalseced read
|
2021-03-29 20:01:15 +02:00 |
|
|
|
51f506553c
|
Read out the local ID once, and store
|
2021-03-12 15:33:04 +01:00 |
|
|
|
0e21adb3f6
|
Gives 200GF/s on SyCL/DG1 8^4, doesn't uglify develop for other platforms too badly.
Easy to revert to clean more C++ stylistic code. Theres a SYCL_HACK macro I will clean up later once dpcpp
evolves a central nervous systems.
|
2021-03-10 05:40:51 -08:00 |
|
|
|
679d1d22f7
|
Sycl happier
|
2021-03-03 11:21:43 -08:00 |
|
|
|
442336bd96
|
Hand unrolled to use optimised code paths on GPU for coalesced reads in Wilson case.
Other cases to do. This now includes comms code path.
|
2021-03-02 14:50:51 +01:00 |
|
|
|
e3d019bc2f
|
Enable performance counting in WilsonFermion like in others
|
2021-02-22 15:25:40 +01:00 |
|
|
|
45d49d8648
|
clean up
|
2020-12-19 03:35:18 +01:00 |
|
|
|
3f9ae6e7e7
|
Merge branch 'develop' into feature/a64fx-3
|
2020-12-19 02:37:11 +01:00 |
|
|
|
4dd9e39e0d
|
up to +36% performance gain for dslash/dwf on QPACE 4 using GCC 10.1.1
|
2020-12-19 00:54:31 +01:00 |
|
|
|
873519e960
|
Enable existing conserved current code for CUDA (compiles OK for CUDA 10.1). Add option to Test_cayley_mres to load a configuration
|
2020-12-14 16:06:10 +00:00 |
|
|
|
b3881d2636
|
Thread inversion of clover term
|
2020-10-30 16:18:58 +01:00 |
|
|
|
bf3c9857e0
|
Closure changes
|
2020-10-14 21:37:14 -04:00 |
|
|
|
ace9cd64bb
|
dpcpp happy
|
2020-09-29 08:03:46 -07:00 |
|
|
|
2859955a03
|
HIP requires "inline"
|
2020-09-16 00:36:13 +01:00 |
|
|
|
cc220abd1d
|
inline for HIP
|
2020-09-16 00:35:38 +01:00 |
|
|
|
d1c0c0197e
|
HipCC requires inline on definition
|
2020-09-16 00:35:06 +01:00 |
|
|
|
fd9424ef27
|
innlines required to make HIP happy
|
2020-09-16 00:34:32 +01:00 |
|
|
|
a5c35c4024
|
Make HIP / Vega happy
|
2020-09-16 00:33:53 +01:00 |
|
|
|
0e88bf4bff
|
remove Nils's default pragma
|
2020-07-29 10:24:35 -04:00 |
|
|
|
bbd145382b
|
enable --enable-simd=A64FX in configure
|
2020-07-08 12:43:51 +02:00 |
|
|
|
8726e94ea7
|
merge upstream develop
|
2020-07-07 20:26:47 +02:00 |
|
|
|
b949cf6b12
|
PeekLocal needs a view to keep thread safe.
ALLOCATION_CACHEE reenable
|
2020-06-19 17:13:27 -04:00 |
|
|
|
1aa988b2af
|
Comms overlap fix UVM case
|
2020-06-19 01:21:14 -04:00 |
|
|
|
fd97f64612
|
Merge branch 'sycl' of https://github.com/paboyle/Grid into sycl
|
2020-06-10 12:58:13 -04:00 |
|
|
|
8720aecb80
|
Offload more loops
|
2020-06-10 12:57:55 -04:00 |
|
|
|
cdf0a04fc5
|
Merge branch 'develop' into sycl
|
2020-06-09 04:00:12 -04:00 |
|
|
|
e97f3688db
|
Fix the HMC issue - kernel was launchnig asynchronously
|
2020-06-08 17:01:15 -04:00 |
|
|
|
433766ac62
|
revert Add/SubTimesI and prefetching in stencil
This reverts commit 9b2699226c.
|
2020-06-08 12:02:53 +02:00 |
|
|
|
1a4c8c3387
|
Global edit with change to View usage. autoView() creates a wrapper object that closes the view when scope closes.
|
2020-06-05 18:52:35 -04:00 |
|
|
|
5ee3ea2144
|
round-up after testing of prefetches in stencil close
|
2020-06-03 11:58:20 +02:00 |
|
|
|
91c81cab30
|
some corrections; compiles on my laptop; untested
|
2020-05-29 18:19:22 +02:00 |
|
|
|
38164f8480
|
include counters in WilsonFermionImplementation.h
|
2020-05-29 17:59:26 +02:00 |
|
|
|
006cc8a8f1
|
Staggereed move to accelerator
|
2020-05-28 08:33:06 -04:00 |
|
|
|
7860a50f70
|
Make view specify where and drive data motion - first cut.
This is a compile tiime option --enable-unified=yes/no
|
2020-05-21 16:13:16 -04:00 |
|
|
|
9e085bd04e
|
guard prevents multiple A64FX build messages
|
2020-05-20 19:16:30 +02:00 |
|
