81441e98f4
HIP runs sensible
2020-09-16 03:35:03 +01:00
ecd3f890f5
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
2020-09-16 02:30:14 +01:00
288c615782
Hip improvements
2020-09-16 00:31:50 +01:00
c273fb051c
Peek poke laattice
2020-09-01 15:27:59 -04:00
e21fef17df
real and imag part not in ET
2020-08-31 23:56:26 -04:00
7d14a3c086
Where working
2020-08-31 23:53:46 -04:00
9522dcd611
Remove dead commented ouot coode
2020-08-31 23:40:29 -04:00
ed469898dc
coalesced ET expressions
2020-08-31 23:38:40 -04:00
1eee94a809
Sorting real/im in read coalesced GPU ET
2020-08-31 23:36:49 -04:00
3448b7387c
Almost there to coalesced ET
2020-08-26 17:04:49 -04:00
dbaa24ebf6
further GPU memory access fixes (with this GPT passes all single-rank tests on non-summit GPUs)
2020-08-13 16:14:15 +02:00
27b4fbf3f0
assert for forbidden code path and fix check for faster CPU codepath in basisRotate
2020-08-03 07:57:33 -04:00
197612bc7a
fast cpu basisRotate and other small cleanups
2020-07-30 07:08:54 -04:00
936c5ecf69
Reduction GPU no compile fix
2020-06-24 17:28:31 -04:00
22cfbdbbb3
Boost precision in inner products in single
2020-06-24 12:52:31 -04:00
b949cf6b12
PeekLocal needs a view to keep thread safe.
...
ALLOCATION_CACHEE reenable
2020-06-19 17:13:27 -04:00
b5e87e8d97
summit compile fixes
2020-06-12 18:16:12 -04:00
5f5807d60a
cleanup
2020-06-12 14:48:23 -04:00
7974acff54
merged sycl to feature-gpt
2020-06-12 06:49:38 -04:00
84c19587e7
Offload
2020-06-10 19:59:31 -04:00
a7ffc61e82
acceleratorSIMTlane()
2020-06-10 19:58:33 -04:00
cdf0a04fc5
Merge branch 'develop' into sycl
2020-06-09 04:00:12 -04:00
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
f67830587f
Accelerator loop use
2020-06-03 22:50:09 -04:00
8cfd5d2639
Need lattice view
2020-06-03 09:11:28 -04:00
7bc0166c1c
SYCLL maknig happy - must avoid non ttrivial copy constructors
2020-05-25 08:34:19 -07:00
cb0d1b3399
hopefullly fix buildd fail
2020-05-24 21:27:00 -04:00
d1f1ccc705
HIP changes
2020-05-24 21:18:49 -04:00
92b342a477
Hip reduction too
2020-05-24 13:50:28 -04:00
8285e41574
View location / access mode
2020-05-21 16:14:41 -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
a7635fd5ba
summit mem
2020-05-18 17:52:26 -04:00
ebb60330c9
Automatic data motion options beginning
2020-05-17 16:34:25 -04:00
32fbdf4fb1
Merge pull request #5 from paboyle/develop
...
Sync upstream
2020-05-13 09:02:56 +02:00
0e3c49f687
TransposeIndex was broken by Christoph
2020-05-12 17:57:01 -04:00
162e4bb567
no automatic prefetching for now
2020-05-12 07:01:23 -04:00
bbbee5660d
First compiile on HiP
2020-05-10 05:28:09 -04:00
c83471bfd0
Fix missing checkerboards for adj und conjugate
2020-05-08 16:44:03 +02:00
f8b8e00090
Systematise the accelerator primitives and locate to Grid/threads/Accelerator.h / Accelerator.cc
...
Aim to reduce the amount of cuda and other code variations floating around all over the place.
Will move GpuInit iinto Accelerator.cc from Init.cc
Need to worry about SharedMemoryMPI.cc and the Peer2Peer windows
2020-05-08 06:23:55 -07:00
3c6ffcb48c
Merge branch 'develop' into feature/gpt
2020-05-06 15:03:35 +02:00
87984ece7d
add Lattice_basis.h
2020-05-06 08:47:18 -04:00
e9b295f967
Synchronize blocking infrastructure with GPT
2020-05-06 08:42:28 -04:00
28a1fcaaff
First compile against SYCL
2020-05-05 11:13:27 -07:00
6b64727161
disable comments
2020-05-05 05:05:36 -04:00
04863f8f38
debug new AcceleratorView
2020-05-04 16:07:03 -04:00
2a1387e992
rankInnerProduct
2020-05-03 17:27:11 -04:00
9bfa51bffb
cleanup comment
2020-05-03 09:12:52 -04:00
38532753f4
interface cleanup
2020-05-03 08:58:32 -04:00
949be9605c
fix pragmas
2020-05-02 16:20:03 -04:00
63cf201ee7
Add AdviseInfrequentUse
2020-05-02 11:38:42 -04:00
