提交線圖

22 次程式碼提交

作者 SHA1 備註 日期
Avinash Kethineedi baca5fd7a1 Fix/RO Backend Hang Issue (#53)
* Update HIP version check for compatibility with versions >= 5.5

* Update memory allocator for context BlockHandle
   - Replaced `HIPAllocator` with `HIPDefaultFinegrainedAllocator` for context `BlockHandle`.

* Update run commands for `rocshmem_g` and `rocshmem_p` functional tests

[ROCm/rocshmem commit: c16b0d6952]
2025-03-24 22:54:07 -05:00
Edgar Gabriel 1ee9b72449 add rocshmem_barrier() (#61)
* add team-barrier implementation

add a team-barrier API and implementation in the IPC and RO conduit.
Clean up some of the logic in the RO Conduit to distinguish between
sync, sync_all, barrier, and barrier_all.

* add team_barrier_tests to functional tests

[ROCm/rocshmem commit: bcbc42e78f]
2025-03-24 11:23:03 -05:00
Yiltan 1ed4512106 Removed GPU_IB (#59)
[ROCm/rocshmem commit: 658bf2a3b5]
2025-03-24 09:04:52 -04:00
Avinash Kethineedi e16bb62767 Update RMA functional tests (#50)
* Update primitive tests for multi-workgroup support

* Update workgroup primitive tests for multi-workgroup support

* Update workfront primitive tests for multi-workgroup support

* Update team based primitive tests for multi-workgroup support

* Update RMA functional tests to capture timing after quiet call
   - Modified RMA functional tests to record the time after a `quiet` call in thread, wavefront, and workgroup RMA calls.

* Improve error handling and memory management
   - Replaced `cout` with `cerr` for improved error reporting.
   - Ensured all allocated memory is freed when `rocshmem_malloc` fails.

* Update start time in primitive tests and latency calculations
   - Modified primitive tests to capture the earliest start time.
   - Updated latency calculations in functional tests.

* Remove `GetSwarmTester`

* Update start time in team primitive tests

* Invoke quiet call from a single thread within a block on a rocshmem context

[ROCm/rocshmem commit: aa3121a967]
2025-03-18 14:39:57 -05:00
Avinash Kethineedi 7f3879ff31 Refactor RO backend data structures (#49)
- Remove hdp and ipc pointers from BlockHandle, align RO stats with RO contexts

- Add run commands for `rocshmem_g` and `rocshmem_p` API tests in driver.sh

- Allocate rocshmem API return buffers based on number of device contexts.

- Associate status flag address with blocking calls and remove threadId dependency
   - Associated the status flag address with each blocking call request to notify the GPU thread.
   - Removed dependency on threadId for determining the appropriate status flag index.

- Move status flag buffer allocation to backend.

- Initialize allocated memeory to zero

[ROCm/rocshmem commit: df4ad2c04d]
2025-03-14 10:49:44 -05:00
Yiltan a16492cdf9 Added option to build only tests and link to an external rocshmem library (#43)
* Rearrange CMakefile

* Enable linking to external rocshmem library

* Minor fix for the functional test driver

* ROCSHMEM_HOME detection fixed

[ROCm/rocshmem commit: 96424a59a8]
2025-03-13 15:49:50 -04:00
Yiltan Hassan Temucin e50460af83 Use the precalculated num_warps variable
[ROCm/rocshmem commit: b83ff2fa84]
2025-02-06 13:21:25 -06:00
Yiltan Hassan Temucin 257610bdc5 Validate signal after put signal operations
[ROCm/rocshmem commit: 8d74c7b73e]
2025-02-06 08:17:22 -06:00
Yiltan Hassan Temucin adf66d04f4 Updated RO builds script and functional test driver for multi-node support
[ROCm/rocshmem commit: 3a8b0d4647]
2025-01-23 16:46:19 -06:00
avinashkethineedi 7a0bf44b83 Updated driver.sh and tester.hpp with sequential numbering for test identification
* Enabled Ping Pong tests
* Removed test commands for multi-workgroup collective tests


[ROCm/rocshmem commit: 23172c9150]
2024-12-26 21:28:21 +00:00
avinashkethineedi 04daad3625 Merge branch PR #55 into naming_scheme
[ROCm/rocshmem commit: d8ce066adc]
2024-12-04 21:46:38 +00:00
Brandon Potter 913ce47ef1 Use new naming scheme
[ROCm/rocshmem commit: fd8dbc7fb6]
2024-11-25 14:25:29 -06:00
Yiltan Temucin fe7fb26f50 Added functional tests
[ROCm/rocshmem commit: f710a301fe]
2024-11-22 15:36:17 -06:00
Yiltan Temucin 97bac1004f Fixed bug in functional and unit tests driver.sh
- The driver previously did not propagate errors correctly
- Adjusted gtest filters

driver edit


[ROCm/rocshmem commit: 3f857718fd]
2024-11-15 10:50:31 -06:00
avinashkethineedi 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
Avinash Kethineedi 1a5536bfaa Merge branch 'ROCm:develop' into functional_tests/puts_gets
[ROCm/rocshmem commit: e981f61693]
2024-10-14 10:27:54 -05:00
avinashkethineedi 9532e084fc Add tilled version of puts and gets at wavefront level to the functional test suite
* Implemented tiled version of put*_wave and get*_wave functions
* Maintain single kernel that supports both tiled and untiled versions
* Disable IPC in the default RO build script


[ROCm/rocshmem commit: b6d31ac7ef]
2024-09-07 16:06:36 -07:00
avinashkethineedi 3d26792831 Add tilled version of puts and gets at the workgroup level to the functional test suite
[ROCm/rocshmem commit: d226922733]
2024-09-07 15:58:14 -07:00
avinashkethineedi 31c43bd58d add functional tests for puts and gets at wavefront level
* These functional tests are simple puts and gets, where every wave will get/put the same amount of data
* Enabled workgroup level puts and gets tests


[ROCm/rocshmem commit: ff954237dd]
2024-09-05 14:52:48 -07:00
avinashkethineedi 46176eeeff Comment out ping pong test
* ping pong test fails sporadically
* issues with roc_shmem_wait_until


[ROCm/rocshmem commit: 9c9ef4ffd3]
2024-08-28 12:40:51 -07:00
Brandon Potter 98b26a763e Update functional_tests driver.sh script
[ROCm/rocshmem commit: 06e51a8132]
2024-07-12 15:08:46 -07:00
Brandon Potter ad4ab69c19 Transfer files from RAD repository
[ROCm/rocshmem commit: ea8f264a11]
2024-07-01 09:57:08 -05:00