Commit Graph

76348 Commits

Author SHA1 Message Date
Pengda Xie 29c2ca8cbc SWDEV-559867 - Fix CU mask printing (#1328) 2025-10-20 09:47:17 -07:00
Mythreya Kuricheti ef1ed44e93 [rocprofiler-sdk] Update codeowner for api-trace.h (#1974)
Feedback from #1933

[ROCm/rccl commit: 9ae5956ca5]
2025-10-20 10:43:42 -06:00
Mythreya Kuricheti 9ae5956ca5 [rocprofiler-sdk] Update codeowner for api-trace.h (#1974)
Feedback from #1933
2025-10-20 10:43:42 -06:00
Ioannis Assiouras 30a14a8a05 SWDEV-559166 - Fix potential data race in ReferenceCountedObject::release() (#1388)
Use fetch_sub(std::memory_order_acq_rel) on release
so the destroying thread acquires prior writes.
2025-10-20 17:15:56 +01:00
systems-assistant[bot] ad3cb435ee SWDEV-507874 - Psdb perf: reduce test iterations (#618)
Change-Id: Ia9af40ecfb2ea121388a3c7a932805b49cef7669

Co-authored-by: agunashe <ajay.gunashekar@amd.com>
2025-10-20 09:00:05 -07:00
Nilesh M Negi ab1bd9d87f [FORMAT] Add .clang-format for C++ code (#1404)
[ROCm/rccl commit: 34d469864b]
2025-10-20 10:54:03 -05:00
Nilesh M Negi 34d469864b [FORMAT] Add .clang-format for C++ code (#1404) 2025-10-20 10:54:03 -05:00
JC 08d93e763e [CI] Enable ccache w/ namespace for external use (#1966)
* Enable ccache w/ namespace for external use

* Remove TheRock from setup_tools.py command line

* Bump TheRock commit to use health_status.py

Resolves https://github.com/ROCm/rccl/pull/1966/files/f9d6d76440b88ecf67d08765ee0e9bac00b55b40#r2420734710

* Bump TheRock to older commit with health_status.py

* Add git safe directory for working directory

* Move install python deps

* Remove pip freeze

[ROCm/rccl commit: b1589a5786]
2025-10-20 08:44:42 -07:00
JC b1589a5786 [CI] Enable ccache w/ namespace for external use (#1966)
* Enable ccache w/ namespace for external use

* Remove TheRock from setup_tools.py command line

* Bump TheRock commit to use health_status.py

Resolves https://github.com/ROCm/rccl/pull/1966/files/c6d2e8ce5c14a2c94bfb47e21d3e2d466f25c9b4#r2420734710

* Bump TheRock to older commit with health_status.py

* Add git safe directory for working directory

* Move install python deps

* Remove pip freeze
2025-10-20 08:44:42 -07:00
Yiltan 92a7904656 Implement rocshmem_pe_quiet() (#282)
Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>

[ROCm/rocshmem commit: c3eeae473b]
2025-10-20 11:42:39 -04:00
Yiltan c3eeae473b Implement rocshmem_pe_quiet() (#282)
Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
2025-10-20 11:42:39 -04:00
Julia Jiang ee4021d6c5 SWDEV-556212 - Update changelog for HIP 7.1 in develop (#1326)
* SWDEV-556212 - Update changelog for HIP 7.1 in develop

* Update CHANGELOG.md

* Update CHANGELOG.md
2025-10-20 11:41:58 -04:00
Edgar Gabriel 6bc1cc63ae update tester for RO (#281)
update the tester script to only tests the amo functions on RO that are
expected to pass. We can revisit the non-passing tests later, but this
prevents us from having passing CIs at the moment, while RO is simply
lower priority than other asks.

[ROCm/rocshmem commit: 6f74cdfd75]
2025-10-20 09:03:17 -05:00
Edgar Gabriel 6f74cdfd75 update tester for RO (#281)
update the tester script to only tests the amo functions on RO that are
expected to pass. We can revisit the non-passing tests later, but this
prevents us from having passing CIs at the moment, while RO is simply
lower priority than other asks.
2025-10-20 09:03:17 -05:00
Danylo Lytovchenko 61fc256db9 Fix memsetD2XX tests (#1405)
* Fix memsetD2XX tests

* Remove redundant interpret_cast
2025-10-20 11:55:17 +02:00
randyh62 fd5ad25615 Add note for setting the HSA_SCRATCH_SINGLE_LIMIT (#1391) 2025-10-19 17:38:06 -07:00
mberenjk abf0605823 Fixing the AR_Bias issue for FP8 (#155)
Authored-by: Marzieh Berenjkoub <146776561+mberenjk@users.noreply.github.com>
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>
Co-authored-by: Nilesh M Negi <Nilesh.Negi@amd.com>

[ROCm/rccl-tests commit: 33cc4df1e4]
2025-10-18 14:46:31 -05:00
mberenjk 33cc4df1e4 Fixing the AR_Bias issue for FP8 (#155)
Authored-by: Marzieh Berenjkoub <146776561+mberenjk@users.noreply.github.com>
Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>
Co-authored-by: Nilesh M Negi <Nilesh.Negi@amd.com>
2025-10-18 14:46:31 -05:00
systems-assistant[bot] ffb380a710 SWDEV-491279 - add stream capture test for ExternalMemory APIs (#570)
Co-authored-by: Li, Todd tiantuo <Toddtiantuo.Li@amd.com>
2025-10-17 16:32:00 -07:00
itrowbri e7a26594b7 [rocprofiler-sdk] Fix Stream ID Error for Attachment (#1142)
* Changed stream error warning, remove regex search from attach execute test

* Formatting

* Revert accidental change

* Fix stream hang error due to grabbing same lock twice

* Updated add stream code, need to update tests

* Update attachment tests to use streams, threads, and multiple devices

* Update tests and fix stream issues

* Updated error messages to be more explicit, updated json to csv code in conftest to include streams and threads

* Formatting

* Add attachment label to attachment tests and update validation to fix errors

* Fix attach twice conftest

* Disabled thread san tests for attachment since they no longer work with bin file changes

* Updated for comment

* Added null check for getting attach status
2025-10-17 16:34:05 -05:00
ajanicijamd 620ccbeb82 Reducing the number of iterations for lulesh tests (#1233) 2025-10-17 17:32:27 -04:00
Ammar ELWazir 3eb01da28d [ROCProfiler-SDK] [ROCProfiler-Register] Adding Correct Installation steps (#1150)
* Adding Correct Installation steps

* Update projects/rocprofiler-sdk/source/docs/install/installation.rst

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update projects/rocprofiler-sdk/source/docs/install/installation.rst

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-10-17 15:48:48 -05:00
Pryor, Adam b2b0815b37 Add cache for user/group checking (#780)
* Add cache for user/group checking
* Fix self

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
2025-10-17 15:46:19 -05:00
Pryor, Adam 428bded17a Add cache for user/group checking (#780)
* Add cache for user/group checking
* Fix self

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: b2b0815b37]
2025-10-17 15:46:19 -05:00
Saeed, Oosman f7c9fe3011 [SWDEV-551318] Update readme doc: amdsmi_get_afids_from_cper() input arguments (#766)
* Update readme doc: amdsmi_get_afids_from_cper() input argument is only bytes, not a list of dicts each with keys “bytes” (List[int]) and “size” (int)

---------

Signed-off-by: Oosman Saeed <oossaeed@amd.com>
2025-10-17 15:42:17 -05:00
Saeed, Oosman 7d39749a08 [SWDEV-551318] Update readme doc: amdsmi_get_afids_from_cper() input arguments (#766)
* Update readme doc: amdsmi_get_afids_from_cper() input argument is only bytes, not a list of dicts each with keys “bytes” (List[int]) and “size” (int)

---------

Signed-off-by: Oosman Saeed <oossaeed@amd.com>

[ROCm/amdsmi commit: f7c9fe3011]
2025-10-17 15:42:17 -05:00
alexxu-amd 55baf27627 [CI] Copy over docs update workflow from rocm-libraries (#1400)
* migrate docs update workflow from rocm-libraries

* add test branch to the trigger condition

* modify docs to test workflow

* temporarily rename project folder name to match the test project

* add more content for testing

* test successful, restore test modifications
2025-10-17 13:47:28 -04:00
Yiltan c269577b89 Updated docs for ROCm 7.x.x (#239)
Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
Co-authored-by: yugang-amd <yugang.wang@amd.com>

[ROCm/rocshmem commit: 9338c84480]
2025-10-17 12:10:37 -04:00
Yiltan 9338c84480 Updated docs for ROCm 7.x.x (#239)
Co-authored-by: Aurelien Bouteiller <aurelien.bouteiller@amd.com>
Co-authored-by: yugang-amd <yugang.wang@amd.com>
2025-10-17 12:10:37 -04:00
cfreeamd 911a2f42c1 Revert "rocr: Don't assert in hsa_shut_down when no agents (#1115)" (#1312)
This reverts commit fb8ab442b6.
2025-10-17 08:36:06 -07:00
systems-assistant[bot] 6b109c11c4 [rocprofv3] Reorganize rocprofv3.avail python package (#175)
* Reorganize rocprofv3 python package

adding Python version candidates

review fix

fix test

fix

remove extra line

fix the exception handle

fix Lint fail

fix installation

adding checks to check version format

disable test for address sanitizer

* review comments

* Removing extra lines

* fix format

* Add lib/python3/site-packages to PYTHONPATH in setup-env.sh

* rocprof-compute update rocprofv3 avail lib path

* Make rocprofv3 python binding build commands consistent with other python bindings

* fix cmake

* fix rocprof-compute

* revert cmake changes

* fix rocprofv3 avail python library

* fix cmake

* fix cmake

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Sriraksha Nagaraj <Sriraksha.Nagaraj@amd.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
Co-authored-by: Jonathan R. Madsen <jrmadsen@users.noreply.github.com>
Co-authored-by: SrirakshaNag <104580803+SrirakshaNag@users.noreply.github.com>
Co-authored-by: Vignesh Edithal <Vignesh.Edithal@amd.com>
2025-10-17 08:27:17 -07:00
David Bélanger 02294e3852 kfdtest: Fix ExtendedCuMasking on GPUs with inactive CUs (#726)
Modify the code that computes the adjusted CU mask array to take
into account of additional cases for inactive CUs.

Signed-off-by: David Belanger <david.belanger@amd.com>
2025-10-17 08:26:12 -07:00
cfreeamd 9df655088f thunk: Correct kfd_ioctl_create_queue_args comment (#1235) 2025-10-17 08:25:51 -07:00
Julia Jiang 5919671102 SWDEV-560097 - Fix math API doc for __frcp_rn and __drcp_rn (#1393) 2025-10-17 11:20:39 -04:00
systems-assistant[bot] dae5b30a1a SWDEV-534207 - Solve more phoenix mem test failures (#545)
* SWDEV-534207 - fix 'Unit_hipFreeMipmappedArrayImplicitSyncArray - float' out of memory error with extent (1024, 1024, 1024) and 1 levels on 740M iGPUs. totalGlobalMem is not really the amount of device memory available for compute

* SWDEV-534207 - compare expected available memory within a range in Unit_hipMalloc3D_Basic; to take into account some bookkeeping overhead (instead of in exact 64MB chunks)

* SWDEV-534207 - fix missing setting of SvmGpuMemoryCreateInfo::interprocess in the 'fine' and 'fine uncached' memory and 'MemorySubAllocator' cases. Coarse allocation was added first; the flag was missed when the other three cases were added

* SWDEV-534207 - allow more room for the check of available memory after hipFree() in Unit_hipMalloc3D_Basic; it was till failing on 740M

---------

Co-authored-by: Gerardo Hernandez <gerardo.hernandez@amd.com>
Co-authored-by: systems-assistant[bot] <systems-assistant[bot]@users.noreply.github.com>
2025-10-17 15:49:57 +01:00
Aurelien Bouteiller bba611d702 Add ROCSHMEM_GDA_PROVIDER envvar (#280)
* Add ROCHSMEM_GDA_PROVIDER env control

* Single name for a single concept: vendor->provider

[ROCm/rocshmem commit: aef74812ae]
2025-10-17 10:46:05 -04:00
Aurelien Bouteiller aef74812ae Add ROCSHMEM_GDA_PROVIDER envvar (#280)
* Add ROCHSMEM_GDA_PROVIDER env control

* Single name for a single concept: vendor->provider
2025-10-17 10:46:05 -04:00
Nilesh M Negi 0aa56fb0a5 Fix ncclDevFuncId for AllReduceWithBias (#1980)
[ROCm/rccl commit: c35bc721ad]
2025-10-17 09:28:57 -05:00
Nilesh M Negi c35bc721ad Fix ncclDevFuncId for AllReduceWithBias (#1980) 2025-10-17 09:28:57 -05:00
Jason Bonnell 9664f1dc91 [rocprofiler-systems] Add retries to RHEL install steps (#1384)
* Add GHCR retry logic

* Add retries to Install ROCm Packages step in rocprofiler-systems-redhat.yml

* Update containers-ci.yml file to use latest RHEL9/10 releases

* Use build-docker-ci script in rocprofiler-systems-containers

* Remove working-directory from step in rocprofiler-systems-redhat.yml

* Remove shell bash from Install ROCm Packages step

* Revert RHEL version change in rocprofiler-systems-redhat.yml
2025-10-17 10:20:54 -04:00
Arm Patinyasakdikul fca120343f Disable graph mode memory registration and UBR as unsupported feature. (#1977)
[ROCm/rccl commit: 58eca5d7f8]
2025-10-17 09:18:39 -05:00
Arm Patinyasakdikul 58eca5d7f8 Disable graph mode memory registration and UBR as unsupported feature. (#1977) 2025-10-17 09:18:39 -05:00
Arm Patinyasakdikul b14fec8dbc Fix git version fetching logic. (#1981)
[ROCm/rccl commit: 9806f5e9dd]
2025-10-17 09:17:49 -05:00
Arm Patinyasakdikul 9806f5e9dd Fix git version fetching logic. (#1981) 2025-10-17 09:17:49 -05:00
Narlo, Joseph 460cfcba1f [SWDEV-555807] TestCudaMallocAsync test power draw failing (#755)
* Clarified comments regarding power limit retrieval and its support on virtualized systems.
* Change unsupported comment to UINT32_MAX

---------

Signed-off-by: josnarlo <Joseph.Narlo@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
2025-10-17 08:57:57 -05:00
Narlo, Joseph 5ec7b213e4 [SWDEV-555807] TestCudaMallocAsync test power draw failing (#755)
* Clarified comments regarding power limit retrieval and its support on virtualized systems.
* Change unsupported comment to UINT32_MAX

---------

Signed-off-by: josnarlo <Joseph.Narlo@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 460cfcba1f]
2025-10-17 08:57:57 -05:00
Sunday Clement b9b8b6110b rocrtst: Add SVM Prefetch test (#360)
this test will prefetch SVM memory, and then verify the memory is sourced
from the expected numa node.

Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
2025-10-17 09:43:46 -04:00
Milan Radosavljevic 00faa48ac2 Add flushing of perfetto buffer (#1417)
- Add flushing of perfetto buffer
- Add `ROCPROFSYS_PERFETTO_FLUSH_PERIOD_MS` config setting.
- Update CHANGELOG.sh
- Resolves SWDEV-518817

---------

Co-authored-by: David Galiffi <David.Galiffi@amd.com>
2025-10-17 09:30:29 -04:00
Edgar Gabriel feab645795 update to build system: (#277)
- make adding PMIx library to compile time based on the result of
  finding PMIx support. This is required eg if compiling rocSHMEM with ompi
  4.0/4.1, which do not have a built-in PMIx version.
- when setting USE_EXTERNAL_MPI=OFF  which ensures that we do not
  check for external MPI libraries (even if one would be available).

[ROCm/rocshmem commit: ed957302d4]
2025-10-17 07:42:11 -05:00
Edgar Gabriel ed957302d4 update to build system: (#277)
- make adding PMIx library to compile time based on the result of
  finding PMIx support. This is required eg if compiling rocSHMEM with ompi
  4.0/4.1, which do not have a built-in PMIx version.
- when setting USE_EXTERNAL_MPI=OFF  which ensures that we do not
  check for external MPI libraries (even if one would be available).
2025-10-17 07:42:11 -05:00