|
b24a504d7c
|
hook to access last parallel I/O performance measurement
|
2020-10-09 20:28:54 +01:00 |
|
Peter Boyle
|
992ef6e9fc
|
more runtime
|
2020-10-08 22:19:20 -04:00 |
|
Peter Boyle
|
f32a320bc3
|
Single prec benchmark in double prec compile
|
2020-10-08 19:52:08 -04:00 |
|
Peter Boyle
|
5f0fe029d2
|
Improve meemory benchmarks for GPU (avoid host mem ping pong)
|
2020-10-08 19:51:28 -04:00 |
|
|
6b1486e89b
|
fixing number of colours defaulting to 4 in most cases
|
2020-10-08 16:31:24 +01:00 |
|
Peter Boyle
|
3f9c427a3a
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2020-10-07 13:12:57 -04:00 |
|
Peter Boyle
|
d201277652
|
Expose Nc as a compile time configure option.
Remove precision option
|
2020-10-07 13:07:00 -04:00 |
|
|
fdda7cf9cf
|
Merge branch 'feature/benchmark-io-update' into develop
|
2020-10-07 15:57:53 +01:00 |
|
|
e22d30f715
|
Merge branch 'develop' into feature/benchmark-io-update
|
2020-10-07 15:56:39 +01:00 |
|
|
1ba25a0d8c
|
more I/O benchmark code cleaning
|
2020-10-07 15:38:41 +01:00 |
|
|
9ba3647bdf
|
script to convert I/O benchmark logs to CSV
|
2020-10-07 15:35:03 +01:00 |
|
|
5ee832f738
|
I/O benchmark code cleaning
|
2020-10-07 15:31:51 +01:00 |
|
Peter Boyle
|
35a69a5133
|
SU4 x SU4
|
2020-10-06 21:48:35 -04:00 |
|
|
e9c5a271a8
|
fixing potential issues with log alignment and timer I/O
|
2020-10-06 17:58:16 +01:00 |
|
|
acac2d6938
|
standard C/C++ I/O in benchmark
|
2020-10-06 17:57:00 +01:00 |
|
Peter Boyle
|
ace9cd64bb
|
dpcpp happy
|
2020-09-29 08:03:46 -07:00 |
|
Peter Boyle
|
a3e2aeb603
|
dpcpp options happiness
|
2020-09-29 06:50:10 -07:00 |
|
Peter Boyle
|
049dd25785
|
Revert accidental commit thanks michael
|
2020-09-23 04:13:50 -04:00 |
|
Peter Boyle
|
d43d372294
|
Merge pull request #311 from mmphys/bugfix/MPIasynch
Asynchronous calls removed - reflect this in Communicator_none.cc
|
2020-09-22 10:41:48 -04:00 |
|
Michael Marshall
|
b71a081cba
|
Asynchronous calls removed - reflect this in Communicator_none.cc
(Opportunistic doc update - OpenMP support on Mac OS)
|
2020-09-21 09:33:23 +01:00 |
|
Peter Boyle
|
c48909590b
|
MPI asynch call removal
|
2020-09-17 20:47:32 +01:00 |
|
Peter Boyle
|
446ef40570
|
HIP IPC
|
2020-09-17 20:31:46 +01:00 |
|
Peter Boyle
|
81441e98f4
|
HIP runs sensible
|
2020-09-16 03:35:03 +01:00 |
|
Peter Boyle
|
ecd3f890f5
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2020-09-16 02:30:14 +01:00 |
|
Peter Boyle
|
1c881ce23c
|
HIP does not like half2 visible members x and y so must define own Half2
|
2020-09-16 02:28:33 +01:00 |
|
Peter Boyle
|
dacbbdd051
|
Hip Happy Birthday
|
2020-09-16 00:37:02 +01:00 |
|
Peter Boyle
|
2859955a03
|
HIP requires "inline"
|
2020-09-16 00:36:13 +01:00 |
|
Peter Boyle
|
cc220abd1d
|
inline for HIP
|
2020-09-16 00:35:38 +01:00 |
|
Peter Boyle
|
d1c0c0197e
|
HipCC requires inline on definition
|
2020-09-16 00:35:06 +01:00 |
|
Peter Boyle
|
fd9424ef27
|
innlines required to make HIP happy
|
2020-09-16 00:34:32 +01:00 |
|
Peter Boyle
|
a5c35c4024
|
Make HIP / Vega happy
|
2020-09-16 00:33:53 +01:00 |
|
Peter Boyle
|
e03b64dc06
|
HIP default flaags to work on ROCM
|
2020-09-16 00:33:09 +01:00 |
|
Peter Boyle
|
4677c40195
|
HIP improvements
|
2020-09-16 00:32:27 +01:00 |
|
Peter Boyle
|
288c615782
|
Hip improvements
|
2020-09-16 00:31:50 +01:00 |
|
Peter Boyle
|
48e81cf6f8
|
Hip Pragmas
|
2020-09-16 00:31:03 +01:00 |
|
Peter Boyle
|
65b724bb5f
|
2 level hddcr
|
2020-09-03 21:46:43 -04:00 |
|
Peter Boyle
|
6dbd117aa5
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2020-09-03 20:30:49 -04:00 |
|
Peter Boyle
|
198b29f618
|
Merge branch 'develop' of https://github.com/paboyle/Grid into develop
|
2020-09-03 20:29:54 -04:00 |
|
Peter Boyle
|
a8309638d4
|
UVM check in MPI calls
|
2020-09-03 20:29:26 -04:00 |
|
Peter Boyle
|
f98a4e880e
|
Merge pull request #310 from kostrzewa/accelerator_vector_stream_op_no_backspace
do not use backspace in AcceleratorVector (Coordinate) output stream operator
|
2020-09-03 20:24:59 -04:00 |
|
Peter Boyle
|
8244caff25
|
Remove the asynchronous non-Stencil calls.
|
2020-09-03 18:52:55 -04:00 |
|
Peter Boyle
|
bcd7895362
|
Include cuda.h
|
2020-09-03 15:49:13 -04:00 |
|
Peter Boyle
|
85b1c5df39
|
A never hit case that is not 100% confident is asserted for safety
|
2020-09-03 15:48:16 -04:00 |
|
Peter Boyle
|
b4255140d6
|
Stale data member eliminated
|
2020-09-03 15:47:46 -04:00 |
|
Peter Boyle
|
0c3095e173
|
Comms buffers to device memory
|
2020-09-03 15:45:35 -04:00 |
|
Peter Boyle
|
d3ce60713d
|
UVM, Device and Lattice/aligned allocators
|
2020-09-03 15:44:13 -04:00 |
|
Peter Boyle
|
eac1f08b7b
|
Close expressions passed as an argument
|
2020-09-01 15:30:33 -04:00 |
|
Peter Boyle
|
1654c4f3c0
|
Closure improved
|
2020-09-01 15:29:45 -04:00 |
|
Peter Boyle
|
8807d998bc
|
closure improved
|
2020-09-01 15:29:11 -04:00 |
|
Peter Boyle
|
5791021dcd
|
Speed up Cshift more with coalesced
|
2020-09-01 15:28:15 -04:00 |
|