76333 Коммитов

Автор SHA1 Сообщение Дата
AL Musaffar, Yazen 678972b8ec [SWDEV-549789] Removed incorrect CPER AFID references (#619)
* Fix for afid help
* Update amdsmi_parser.py

Signed-off-by: AL Musaffar, Yazen <Yazen.ALMusaffar@amd.com>

[ROCm/amdsmi commit: e84e364b35]
2025-08-19 18:55:33 -05:00
Pryor, Adam b62900c372 [SWDEV-544620] Add kfd fallback for GPU Processes (#631)
Signed-off-by: adapryor <Adam.pryor@amd.com>
2025-08-19 18:53:16 -05:00
Pryor, Adam 96a28009fc [SWDEV-544620] Add kfd fallback for GPU Processes (#631)
Signed-off-by: adapryor <Adam.pryor@amd.com>

[ROCm/amdsmi commit: b62900c372]
2025-08-19 18:53:16 -05:00
Pham, Gabriel c0ea186d47 [SWDEV-446394] Updated error message for setting clock limit (#633)
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
2025-08-19 18:51:49 -05:00
Pham, Gabriel 729b7beddf [SWDEV-446394] Updated error message for setting clock limit (#633)
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: c0ea186d47]
2025-08-19 18:51:49 -05:00
Poag, Charis 1b2edd70bd [SWDEV-550355] Fix process + violation output when in partitions (#623)
Changes:
  - Fixes amd-smi monitor such as:
    amd-smi monitor -Vqt, amd-smi monitor -g 0 -Vqt -w 1
    amd-smi monitor -Vqt --file /tmp/test1, ...
  - Required moving around when process is called, since xcp
    information is gathered in right format expected by monitor
  - Requires process to be appended first with the gpu data -> xcp
    info to be gathered + added after 1st device

Change-Id: I76356a4610944f633a9530970fac66556d65bf11
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-08-19 18:50:51 -05:00
Poag, Charis 35b4b0df38 [SWDEV-550355] Fix process + violation output when in partitions (#623)
Changes:
  - Fixes amd-smi monitor such as:
    amd-smi monitor -Vqt, amd-smi monitor -g 0 -Vqt -w 1
    amd-smi monitor -Vqt --file /tmp/test1, ...
  - Required moving around when process is called, since xcp
    information is gathered in right format expected by monitor
  - Requires process to be appended first with the gpu data -> xcp
    info to be gathered + added after 1st device

Change-Id: I76356a4610944f633a9530970fac66556d65bf11
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

[ROCm/amdsmi commit: 1b2edd70bd]
2025-08-19 18:50:51 -05:00
Charis Poag 5fe58a8e38 [SWDEV-550679] Fix amd-smi monitor AttributeError
Impacts only Guest systems

Fixes following error:
$ amd-smi monitor
AttributeError: 'Namespace' object has no attribute 'violation'

Change-Id: If501819be3f8e2d2dfd75775dc776873a92465a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-08-19 17:58:44 -05:00
Charis Poag b239e5be60 [SWDEV-550679] Fix amd-smi monitor AttributeError
Impacts only Guest systems

Fixes following error:
$ amd-smi monitor
AttributeError: 'Namespace' object has no attribute 'violation'

Change-Id: If501819be3f8e2d2dfd75775dc776873a92465a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 5fe58a8e38]
2025-08-19 17:58:44 -05:00
Maisam Arif 6de6290dc1 Removed kfd_ioctl.h from rocm include install
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I7948eb050f79a8a0f71e0b8a8e4e08187ac0bb84
2025-08-19 17:18:14 -05:00
Maisam Arif 2851f80253 Removed kfd_ioctl.h from rocm include install
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I7948eb050f79a8a0f71e0b8a8e4e08187ac0bb84


[ROCm/amdsmi commit: 6de6290dc1]
2025-08-19 17:18:14 -05:00
Atul Kulkarni 8c5095dd94 Added new code owners (#1869)
[ROCm/rccl commit: 231449c896]
2025-08-19 16:32:25 -05:00
Atul Kulkarni 231449c896 Added new code owners (#1869) 2025-08-19 16:32:25 -05:00
Mustafa Abduljabbar 5025a9aab9 Have ncclDevFuncId use 64-Bit keyed map with field packing (#1857)
- Updated ncclDevFuncId to use a hash-based lookup with std::unordered_map.
- Keys are now 64-bit integers, which pack coll, algo, proto, devRedOp, and type fields.
- Improved flexibility and maintainability by moving away from row-based indexing.
- Added error handling for missing keys in the hash map.
- Aligned key generation logic with generate.py and updated generate.py.

[ROCm/rccl commit: c1b3cd8911]
2025-08-19 16:41:19 -04:00
Mustafa Abduljabbar c1b3cd8911 Have ncclDevFuncId use 64-Bit keyed map with field packing (#1857)
- Updated ncclDevFuncId to use a hash-based lookup with std::unordered_map.
- Keys are now 64-bit integers, which pack coll, algo, proto, devRedOp, and type fields.
- Improved flexibility and maintainability by moving away from row-based indexing.
- Added error handling for missing keys in the hash map.
- Aligned key generation logic with generate.py and updated generate.py.
2025-08-19 16:41:19 -04:00
Galantsev, Dmitrii cd33b75540 [SWDEV-545751] CMAKE - Enable fPIC (#629)
Change-Id: Iaade10e70b3a39d6bca23ae98f9f501339ffd76d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
2025-08-19 11:39:39 -05:00
Galantsev, Dmitrii beaffa2c84 [SWDEV-545751] CMAKE - Enable fPIC (#629)
Change-Id: Iaade10e70b3a39d6bca23ae98f9f501339ffd76d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>

[ROCm/amdsmi commit: cd33b75540]
2025-08-19 11:39:39 -05:00
Poag, Charis e12d270693 [SWDEV-546220] Fix mVF xcd check within tests (#628)
Adding a check to see if we're in guest -> allowing equal XCD values.
This is because in mVF configurations, we may not be able to read the gfx clock values.

Change-Id: I8e5d9627e061e98ec854734a91624c8077644a2a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
2025-08-19 11:13:18 -05:00
Poag, Charis 61c817a2d3 [SWDEV-546220] Fix mVF xcd check within tests (#628)
Adding a check to see if we're in guest -> allowing equal XCD values.
This is because in mVF configurations, we may not be able to read the gfx clock values.

Change-Id: I8e5d9627e061e98ec854734a91624c8077644a2a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

[ROCm/amdsmi commit: e12d270693]
2025-08-19 11:13:18 -05:00
systems-assistant[bot] 351d598869 [Docs] Adding AQLprofile info (#150)
* Adding AQLprofile info

* update aqlprofile text

---------

Co-authored-by: Matt Williams <Matt.Williams+amdeng@amd.com>
2025-08-19 08:44:25 -07:00
systems-assistant[bot] c746ba6d31 Fix compilation with libc++ (#148)
`interop.cpp` uses `std::find_if` without a relevant include file, breaking compilation with Clang/libc++.

Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
2025-08-19 08:42:03 -07:00
Giovanni Lenzi Baraldi ff43893902 Fix decoder description (#513) 2025-08-19 08:35:22 -07:00
Joseph Macaranas 894cfbc02c Language runtime codeowner updates (#628) 2025-08-19 11:03:42 -04:00
Joseph Macaranas 669cea4570 Migration status update Aug 18 2025-08-18 20:55:31 -04:00
Joseph Macaranas c912ff5051 Source of truth update Aug 18 (#623) 2025-08-18 20:05:55 -04:00
Joseph Macaranas f81d90623d Preserved file-path commit history for hip-tests. 2025-08-18 19:43:53 -04:00
Joseph Macaranas 966fc5319d Preserve file-path commit history for hipother. 2025-08-18 19:07:27 -04:00
Joseph Macaranas a8f48a100d Preserve file-path commit history for hip. 2025-08-18 19:04:49 -04:00
Joseph Macaranas a2cedb7fe5 Preserve file-path commit history of clr. 2025-08-18 19:01:36 -04:00
Bindhiya Kanangot Balakrishnan 41488f0c18 [SWDEV-547160] Fix VRAM percentage calculation
The vram_percent calculation was missing
multiplication by 100.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
2025-08-18 17:28:30 -05:00
Bindhiya Kanangot Balakrishnan 8e645a6da7 [SWDEV-547160] Fix VRAM percentage calculation
The vram_percent calculation was missing
multiplication by 100.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>


[ROCm/amdsmi commit: 41488f0c18]
2025-08-18 17:28:30 -05:00
Joseph Macaranas a22b6f3aca Merge commit 'ed7fae51d884a17cd3bd96c7973d1f1f78b5f3a5' into develop 2025-08-18 16:23:12 -04:00
ammallya 32634d809f Adding merge conflicts bypass 2025-08-18 13:11:15 -07:00
ammallya 53ae4f13db Fix for commits 2025-08-18 13:00:02 -07:00
Arif, Maisam 2d5accd000 [SWDEV-540665] Add power_cap set to Linux Guest (#626)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3c8d707681c141390b40521231e0d638c81cdeaf
2025-08-18 14:59:14 -05:00
Arif, Maisam 4e568b2eea [SWDEV-540665] Add power_cap set to Linux Guest (#626)
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3c8d707681c141390b40521231e0d638c81cdeaf

[ROCm/amdsmi commit: 2d5accd000]
2025-08-18 14:59:14 -05:00
ammallya cc67092904 Adding git user settings 2025-08-18 12:54:51 -07:00
ammallya 8110a5d38c Adding pr logic to python file 2025-08-18 12:51:12 -07:00
ammallya 03d4c5c1fd Changing the logic to invoke python script 2025-08-18 12:50:03 -07:00
ammallya b8ea251fc5 Continue on error 2025-08-18 12:31:03 -07:00
nileshnegi 74b03fe00e Merge pull request #147 from nileshnegi/sync/nccl-tests_v2.16.7
[SYNC] NCCL-Tests v2.16.7


[ROCm/rccl-tests commit: 690f97c119]
2025-08-18 15:28:34 -04:00
nileshnegi 690f97c119 Merge pull request #147 from nileshnegi/sync/nccl-tests_v2.16.7
[SYNC] NCCL-Tests v2.16.7
2025-08-18 15:28:34 -04:00
ammallya 1d19aa0dd5 Escaping /r 2025-08-18 12:17:31 -07:00
Manocha, Rahul 13d54a3ec1 Fix typo in hipBatchMemOpParamsTocudaBatchMemOpParams (#38)
Co-authored-by: Rahul Manocha <rmanocha@amd.com>

[ROCm/hipother commit: ed7fae51d8]
2025-08-18 12:09:09 -07:00
Manocha, Rahul ed7fae51d8 Fix typo in hipBatchMemOpParamsTocudaBatchMemOpParams (#38)
Co-authored-by: Rahul Manocha <rmanocha@amd.com>
2025-08-18 12:09:09 -07:00
ammallya 9ceb4b8fb8 Fix logic 2025-08-18 11:57:26 -07:00
ammallya 948ce50ec8 Remove from json 2025-08-18 11:55:40 -07:00
ammallya 95ef34ce41 Fix multiline matrix error 2025-08-18 11:50:27 -07:00
systems-assistant[bot] bc455989d9 Merge commit 'b0519e8441273e20bbcbe1bb7b56cdf55369f514' into develop 2025-08-18 18:08:07 +00:00
systems-assistant[bot] c95526c57e Merge commit '55b54866fb50f264b064b20814679385ffd2847c' into develop 2025-08-18 18:08:05 +00:00