bae2b2aece
Merge pull request #45 from Yiltan/to_all_reduce
...
Fixed Function Signature for `to_all` APIs
[ROCm/rocshmem commit: 958575d8a4
2024-11-06 10:54:36 -05:00
8df27a93be
updated examples to use new APIs
...
[ROCm/rocshmem commit: 799d9d5ed7
2024-11-06 09:49:06 -06:00
f887e9b886
removed external access to non-team based reduce
...
[ROCm/rocshmem commit: 9aa9aea7e6
2024-11-06 09:46:47 -06:00
7f3dd33144
modified team based to_all -> reduce
...
[ROCm/rocshmem commit: 997eb69b5a
2024-11-06 09:46:43 -06:00
b43ef2b45b
Merge pull request #46 from avinashkethineedi/active_set_APIs
...
Remove device-side active-set-based APIs
[ROCm/rocshmem commit: 75ece02048
2024-11-05 18:43:40 -06:00
832dda25e6
Merge branch 'ROCm:develop' into active_set_APIs
...
[ROCm/rocshmem commit: b2b0d559cb
2024-11-05 23:02:44 +00:00
d1b3b30f76
Merge pull request #47 from Yiltan/revert-pr36-coopgroups
...
Remove Cooperative Groups (Partially Revert #PR36)
[ROCm/rocshmem commit: b141f354cf
2024-11-04 09:35:15 -05:00
9ae2320ac3
remove cooperative groups
...
[ROCm/rocshmem commit: fe767d9abf
2024-10-30 20:10:21 +00:00
f682dcee3f
Add example code demonstrating team-based broadcast and alltoall API usage
...
* Update all_reduce test to keep the naming convention uniform across the examples
[ROCm/rocshmem commit: 68c893d790
2024-10-30 19:09:17 +00:00
b1a52b906b
Update broadcast function to use stride calculations instead of log_stride
...
[ROCm/rocshmem commit: 5975b8c621
2024-10-29 19:10:05 +00:00
058aa3ccf3
Remove device-side active-set-based broadcast API interface from rocSHMEM
...
[ROCm/rocshmem commit: e1ff06913c
2024-10-29 19:04:49 +00:00
daae6f4d60
Remove active-set-based broadcast test from the functional tests suite
...
[ROCm/rocshmem commit: 9a524046fe
2024-10-29 16:18:46 +00:00
5869709dac
Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays
...
* Change log_stride calcualtions to stride calculations
* Update all_reduce example code to use team based interface
[ROCm/rocshmem commit: abec29bd6a
2024-10-28 22:10:18 +00:00
9f9ecd9a38
Remove the device-side active-set-based reduction API interface from rocSHMEM
...
[ROCm/rocshmem commit: c22048112e
2024-10-28 21:35:14 +00:00
4e71fa5d22
Remove active-set-based reduction test from the functional tests suite
...
[ROCm/rocshmem commit: e9484bbb86
2024-10-28 21:22:46 +00:00
da9466f7cc
Merge pull request #44 from ROCm/fix-printing
...
Clean up functional tests output
[ROCm/rocshmem commit: 9885f984f6
2024-10-28 15:45:28 -04:00
bd3a07d28b
Merge pull request #43 from ROCm/LWPRHMEM-75-API-differences-bug-fix
...
Lwprhmem 75 api differences bug fix
[ROCm/rocshmem commit: 794b888d69
2024-10-28 15:45:15 -04:00
0ed689439b
Cleaned up how we print the output
...
[ROCm/rocshmem commit: 9576ff6440
2024-10-28 13:37:33 -05:00
e21e9a8fb6
Merge pull request #32 from edgargabriel/topic/to_all_first_version
...
ipc/to_all: add direct allreduce algorithm
[ROCm/rocshmem commit: 7ae0a54550
2024-10-24 15:59:24 -05:00
bc315d1c8b
API bug fix in IB conduit
...
[ROCm/rocshmem commit: 98afb41263
2024-10-24 11:52:03 -05:00
2da1f4e925
API change bug fix
...
[ROCm/rocshmem commit: e210020e9b
2024-10-24 11:52:03 -05:00
95c01c67af
add ascii art for ring allredude
...
[ROCm/rocshmem commit: 11df5427a6
2024-10-24 15:08:32 +00:00
2836240906
fix odd-case allreduce scenarios
...
if the number of elements to be used in the allreduce operation is not
exact multiple of the work-array buffer size and number of pe's, we need
to adjust the algorithm to:
- initially perform a ring_allreduce on n_segments * chunk_size (which
is the integer division of the number of elements and the work-buffer
size, i.e. will not cover the entire buffer)
- perform another ring_allreduce where chunk_size is reduced to match
the remaining elements
- if the remaining elements from the previous step cannot evenly be
divded by the number of pe's, we need to perform a direct_allreduce on
the outstanding number of elements.
[ROCm/rocshmem commit: a4b4281f50
2024-10-24 15:08:32 +00:00
7b760bb023
fix barrier synchronization on gfx90a
...
[ROCm/rocshmem commit: 87db7f7d38
2024-10-24 15:08:28 +00:00
777401ae29
add some example code
...
first examples include a getmem testcase and an allreduce (to_all)
example.
[ROCm/rocshmem commit: a0ac7b2d60
2024-10-24 15:07:17 +00:00
c9b5f03548
ipc: add ring_allreduce algorithms
...
add the ring allreduce algorithm to the ipc conduit in order to be able
to execute slightly largers reductions.
[ROCm/rocshmem commit: 1fbb89bc73
2024-10-24 15:07:17 +00:00
5f0f2f6e85
ipc/to_all: add direct allreduce algorithm
...
add a simple version of an allreduce algorithm as a starting point.
[ROCm/rocshmem commit: ba21cb7b85
2024-10-24 15:07:14 +00:00
a032b41c20
Merge pull request #34 from BKP/ipc_parameterized_simple_tests_10-01-24
...
IPC Parameterized Simple Tests
[ROCm/rocshmem commit: 416dffa129
2024-10-24 08:23:26 -05:00
6979677ec5
Merge pull request #41 from avinashkethineedi/collective_routine_buffers
...
Fine grained memory buffers for work/sync arrays
[ROCm/rocshmem commit: 8a16968cf2
2024-10-23 23:33:48 -05:00
2356d407f0
Merge pull request #42 from avinashkethineedi/fix_quiet/fence
...
Fix quiet and fence of default context
[ROCm/rocshmem commit: e594a9cb85
2024-10-22 12:56:43 -05:00
82d296db73
Fix quiet and fence of default context
...
* Update tinfo of default context
[ROCm/rocshmem commit: d5ea5868e3
2024-10-22 16:18:05 +00:00
fbcba80cd3
Add fine grained memory buffers for work/sync arrays
...
* Add interanl put_mem/get_mem{_wave, _wg} functions to read/write to work/sync arrays
* Add condition check to ensure all MPI processes are on the same compute node for IPC conduit
[ROCm/rocshmem commit: 6685d0ab60
2024-10-21 15:28:39 +00:00
08ab0b4a41
Merge pull request #39 from Yiltan/LWPRHMEM-75-API-differences
...
LWPRHMEM-75 API Differences
[ROCm/rocshmem commit: b922bdcf4c
2024-10-18 15:27:34 -04:00
012532791f
Merge pull request #40 from avinashkethineedi/functional_tests/puts_gets
...
Functional tests {wave, wg} puts and gets
[ROCm/rocshmem commit: 892b4e2436
2024-10-17 17:23:05 -05:00
10eb11c1d5
Use C++ iota function to reset buffers and use its values for verification
...
* Update functional test script to include new tests
[ROCm/rocshmem commit: 18a1bdd0ac
2024-10-15 20:23:25 +00:00
1a5536bfaa
Merge branch 'ROCm:develop' into functional_tests/puts_gets
...
[ROCm/rocshmem commit: e981f61693
2024-10-14 10:27:54 -05:00
31fe937259
updated atomic_fetch() parameters
...
[ROCm/rocshmem commit: 8b3854b252
2024-10-11 13:34:28 -07:00
3d0fca0387
updated *_wait* APIs to use int rather than roc_shmem_cmps
...
[ROCm/rocshmem commit: 722a5f0731
2024-10-11 13:34:28 -07:00
496f06dd2b
*_wait* routines changed parameter from ptr to ivars to match OpenSHMEM
...
[ROCm/rocshmem commit: bcf3fdff10
2024-10-11 13:34:28 -07:00
7f19a42778
Merge branch 'ROCm:develop' into ipc_parameterized_simple_tests_10-01-24
...
[ROCm/rocshmem commit: ce0ca36d37
2024-10-11 12:49:56 -05:00
5b47cf482d
Merge pull request #29 from ROCm/improve-ib-latency
...
Vectorize WQE segments writes
[ROCm/rocshmem commit: e419a8b963
2024-10-11 11:55:48 -05:00
9eb928d520
Merge pull request #36 from Yiltan/LWPRHMEM-71-add-coop-groups
...
Add cooperative groups for sync collective
[ROCm/rocshmem commit: 8015a453ff
2024-10-11 12:55:33 -04:00
17323323f8
fixed notifier bug
...
[ROCm/rocshmem commit: 509277c034
2024-10-10 06:45:43 -07:00
8334214b98
added notifier->sync() when we are not using cooperative groups
...
updated scope bug
[ROCm/rocshmem commit: b1134e8633
2024-10-09 13:11:28 -07:00
caa6d356c0
Added Cooperative Groups configure option and header
...
[ROCm/rocshmem commit: 63667a3167
2024-10-09 13:11:12 -07:00
45976b23ae
Fix initialization order bug
...
[ROCm/rocshmem commit: 1baa071edf
2024-10-09 13:11:12 -07:00
ef571f5863
fixed barrier issue on MI250X
...
[ROCm/rocshmem commit: e2f6a65284
2024-10-08 13:18:04 -07:00
3cba9ccd42
added .gitignore, we do not want to include the build directory in our commits
...
[ROCm/rocshmem commit: 120453c75c
2024-10-08 13:18:04 -07:00
380f07749f
Merge pull request #37 from avinashkethineedi/unit_test_script
...
Unit tests script
[ROCm/rocshmem commit: d4bcd11262
2024-10-08 15:05:58 -05:00
7eec77ea17
Add script to run unit tests
...
[ROCm/rocshmem commit: c1bcf336b4
2024-10-08 18:12:07 +00:00
Yiltan
Yiltan Temucin
Yiltan Hassan Temucin
Avinash Kethineedi
Edgar Gabriel
Edgar Gabriel
Brandon Potter