AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность
1 346 коммитов 3 Ветки 0 Теги
01c11ef123a5a8b7a48b7aee115bba680e80d67c
Граф коммитов

1346 Коммитов

This Branch
This Branch
Все ветки
Автор SHA1 Сообщение Дата
Maisam Arif 01c11ef123 Merge amd-dev into amd-master 20240823 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ibb71d60b3fc87b2fa268f8a95b2fba4e9019ecba


[ROCm/amdsmi commit: 89cbecd0b6]
 2024-08-23 19:22:15 -05:00
Maisam Arif 2e92791192 Removed extra print statement 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I0043567f4cc17d69860b0c77f42fa77fd41e354d


[ROCm/amdsmi commit: 7ac0a49470]
 2024-08-23 19:22:05 -05:00
Charis Poag bc357f1500 [SWDEV-478807] Add leading 0s to amdsmi_get_fw_info() 
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Change-Id: Ie535dcb8cb44138c115e29a4bc41db3cc488097f


[ROCm/amdsmi commit: c46eab4e9e]
 2024-08-23 19:37:32 -04:00
Charis Poag ee66b03dc8 [SWDEV-478807] Fix incorrect firmware versions and names 
- Fix updates API to have correct enum names (PM->SMU)
 - Python API/CLI now reports correct versions and names for
    SMC/TA_XGMI/TA_RAS

Change-Id: Icbe115b3070b9f252ef15b09b781b9b3f5861e50
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: d7c583d422]
 2024-08-23 18:03:13 -05:00
Charis Poag 4b308c8d48 Fix amdsmi_reg_type_t not defined 
Latest updates need to use a wrapper defined value. Breaks basic CLI
functionality.

$ /opt/rocm/bin/amd-smi list
Traceback (most recent call last):
  File "/opt/rocm/bin/amd-smi", line 44, in <module>
    from amdsmi_commands import AMDSMICommands
  File "/opt/rocm/libexec/amdsmi_cli/amdsmi_commands.py", line 30, in <module>
    from amdsmi_helpers import AMDSMIHelpers
  File "/opt/rocm/libexec/amdsmi_cli/amdsmi_helpers.py", line 35, in <module>
    from amdsmi_init import *
  File "/opt/rocm/libexec/amdsmi_cli/amdsmi_init.py", line 35, in <module>
    from amdsmi import amdsmi_interface
  File "/usr/local/lib/python3.8/dist-packages/amdsmi/__init__.py", line 26, in <module>
    from .amdsmi_interface import amdsmi_init
  File "/usr/local/lib/python3.8/dist-packages/amdsmi/amdsmi_interface.py", line 1725, in <module>
    reg_type: amdsmi_reg_type_t,
NameError: name 'amdsmi_reg_type_t' is not defined

Change-Id: I628c811c137f57f3177a718c9bce859bc553bf7d
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: a2dc934b05]
 2024-08-22 21:57:36 -05:00
Zhang Ava f214b54d8f Merge amd-dev into amd-master 20240821 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I9e5be746557fc7e3c7fdee2d91d0b3981945a75f


[ROCm/amdsmi commit: 8c5942db3a]
 2024-08-23 09:45:42 +08:00
Tom St Denis c59f7b7705 Add amdsmi_get_gpu_pm_metrics_info and amdsmi_get_gpu_reg_table_info to py-interface (v3) 
v2: drop depend on libc
v3: whitespace

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Change-Id: I2eff7aa9d4f0ca8635796f82b106ac0d36176346


[ROCm/amdsmi commit: f4506cfd65]
 2024-08-21 08:38:14 -04:00
Bill(Shuzhou) Liu ef78459f75 Set soft min or max clock 
Add the API to support set soft min or max clock.

Change-Id: Ia34381a721ef3c3d894d5a89d25afa757be46a79


[ROCm/amdsmi commit: 97e70d44cf]
 2024-08-20 13:22:32 -04:00
Maisam Arif 4523b20652 Merge amd-dev into amd-master 20240820 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I33f3e9c430c039131a4e81224eb561269aecbe32


[ROCm/amdsmi commit: 2a11d82ab9]
 2024-08-20 03:17:30 -05:00
Maisam Arif 77e3035cf5 [SWDEV-479989] - Fixed if statement for filtering ecc blocks 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I4d0c7579257c98be8a4ba8e5a31b5d9db4305844


[ROCm/amdsmi commit: 78373cb5f7]
 2024-08-20 03:16:49 -05:00
Maisam Arif f0bfe32f29 Merge amd-dev into amd-master 20240819 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I124d1e5d0896ae539636f72dcc8cc2182cac6954


[ROCm/amdsmi commit: 9253a941ca]
 2024-08-19 17:21:24 -05:00
Maisam Arif 5013af7398 Revert "Do not automatically download kernel header amd_hsmp.h" 
This reverts commit 18bb65a5cd.

Change-Id: I48ef2a6df69e7b8bc4e66009e6ee2987af8448fc
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>


[ROCm/amdsmi commit: c934291940]
 2024-08-19 17:20:20 -05:00
Zhang Ava 1a709688b7 Merge amd-dev into amd-master 20240814 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I377d25c7fbabe9d177303f0efe077f75be1be29b


[ROCm/amdsmi commit: 0d6cb91a1d]
 2024-08-15 18:48:41 +08:00
Tom Rix 18bb65a5cd Do not automatically download kernel header amd_hsmp.h 
First look locally following these heuristics
Either as a user specified option -DBUILD_KERNEL_ASM_DIR=<PATH>
or from the running kernel's src
and then from hints at where it could be.

When these fail, download from the upstream kernel

Change-Id: If8d62a4f84a929f550e4a83cda93e4d671e92d02
Signed-off-by: Tom Rix <Tom.Rix@amd.com>


[ROCm/amdsmi commit: f3cb51c08e]
 2024-08-13 15:42:20 -05:00
Maisam Arif 4b2c3c9e50 Merge amd-dev into amd-master 20240813 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ic744285e2203fad663a2f4a9f722c2bad1e623c8


[ROCm/amdsmi commit: 1a8462f364]
 2024-08-13 15:35:06 -05:00
Maisam Arif 83dfd814c3 [SWDEV-478576] Adjusted Disclaimer 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I0dbdcd1c8ff200336e7ee0e8ca88a5eba1b41057


[ROCm/amdsmi commit: b49c5596b5]
 2024-08-09 18:50:55 -04:00
Maisam Arif 0a28df87c8 Fixed Guest VM registering as Passthrough VM 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I0edc36e1a114166647dc10ebc646665b62c5d88e


[ROCm/amdsmi commit: 037f8689fe]
 2024-08-09 18:44:44 -04:00
Maisam Arif 1eaf218f2f Removed metric --ecc & --ecc-blocks commands from VM 
ecc is not supported on VM
	Added static --ras because ras features are still detectable

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ied4132b863989dfd67897e00904f04d140fd2773


[ROCm/amdsmi commit: 210680b570]
 2024-08-09 18:44:44 -04:00
Maisam Arif b0c05aa04d [SWDEV-478576] Added Disclaimer for CLI Tool 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3d432ac3f8c9663365921591d183a5d1f35c4707


[ROCm/amdsmi commit: cec3e4c2a0]
 2024-08-09 14:14:50 -04:00
Galantsev, Dmitrii e3c9bb9613 Merge amd-dev into amd-master 20240808 
Change-Id: I353b1f5219dd67d1d066fcc51d27677447726776
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: d0ff27181b]
 2024-08-08 16:42:06 -05:00
Maisam Arif a3a8a0cfa8 Bump Version to 24.6.3.0 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I902da5e5e9e7441002420afaaef01ca9c6c9666f


[ROCm/amdsmi commit: 40112f5b17]
 2024-08-08 01:30:51 -05:00
Ranjith Ramakrishnan 8ce27d8bc7 SWDEV-469004 - Append additonal path to system path 
amd-smi is installed in /opt/rocm-ver/bin, but not as a soft link in wheel package
For amd-smi to work from bin directory, it need the extra path to find the dependent python scripts in /opt/rocm-ver/libexec/amd_smi

Change-Id: I4ff63a8f55949aaac51d85eae849ecc890f4c694


[ROCm/amdsmi commit: 7591eec971]
 2024-08-08 02:15:04 -04:00
Ranjith Ramakrishnan 0cd04cdefb SWDEV-476075 - Prevent the modification of interpreter directives 
CPACK is converting /usr/bin/env python3 to /usr/libexec/platform-python in RHEL8.
Undefining __brp_mangle_shebangs will prevent the same

Change-Id: I5120274b90aeaf783b62414ac2aeba9e84029205


[ROCm/amdsmi commit: 92a4093256]
 2024-08-08 02:04:37 -04:00
Maisam Arif 7130dc9f04 Fixed handling in GPU/CPU/CORE select functions 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I83d78a8d6cdcbd54e5c79330be577b3a06a00985


[ROCm/amdsmi commit: 574712386f]
 2024-08-05 18:27:30 -04:00
gabrpham 6975697b56 Fixed cli issue with empty cpu/core parameter 
Change-Id: Id0fee74357a56baaec59ca5359eb00a65cfd6185
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 0143041262]
 2024-08-05 16:37:36 -05:00
gabrpham 0df83ddf94 Fixed 'amd-smi process -G' 
Issue linked here: https://github.com/ROCm/amdsmi/issues/23

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I73c2dede8634b21a5dfe0245a202e883fa856de2


[ROCm/amdsmi commit: fe1dc23ade]
 2024-08-02 16:42:08 -04:00
Galantsev, Dmitrii c44abfcd08 Cleanup convert_SI_unit and misc linter warnings 
Change-Id: I000ba548b79a7023aabad653125842064fa2e7cb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 3784f37a3a]
 2024-08-02 10:29:06 -04:00
Zhang Ava 5a4d59efaa Merge amd-dev into amd-master 20240731 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: Iad8ae44b4d92afc76ecb5afdd4ee57e9c981b6a8


[ROCm/amdsmi commit: ce0c45ebca]
 2024-08-02 13:07:51 +08:00
gabrpham 5b44997728 [SWDEV-439701] Additional GPU error handling 
Change-Id: Ieb35e9712f2a78acef8961d865dba1d824969ef3
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: de8145387d]
 2024-07-30 16:19:10 -05:00
Zhang Ava ce99e615e3 Merge amd-dev into amd-master 20240724 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I0f646a946999682c2128c5322447a64ae40286b2


[ROCm/amdsmi commit: 813ed1bf92]
 2024-07-26 13:42:16 +08:00
Galantsev, Dmitrii 4799537b20 Docs - Switch to amd-staging branch 
Change-Id: I1a26542b3a7831c1f5efea6d6b4084f77b0a7cdb
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: f3426ced06]
 2024-07-23 17:10:34 -05:00
Galantsev, Dmitrii 7ec65d7e57 Azure - Switch to amd-staging branch 
Change-Id: I5cc2316427631fc17990506c4234163302febd3d
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: ceac87ef5a]
 2024-07-23 17:04:37 -05:00
Maisam Arif 225595d643 Merge amd-dev into amd-master 20240719 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Id47efb0e83a5bfcf2fdc996ab2d0e4e20bc0ab9b


[ROCm/amdsmi commit: 23fc9e4ea5]
 2024-07-19 18:14:33 -05:00
Galantsev, Dmitrii 815e607285 Fix missing c_str() introduced in c63ea0e 
Change-Id: Ife778276aaebd109a413efb3db703de36b730613
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 47c8cd10cf]
 2024-07-19 19:12:17 -04:00
Charis Poag e536831413 Fix TypeError: 'type' object is not subscriptable 
Python 3.8 requires typing import to specify.
Python 3.10, no longer requires typing import.

Change-Id: I5d9844c91932bc3af53acc6dd56eb258f4d18d9b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: ac40e963d3]
 2024-07-19 16:33:41 -05:00
Maisam Arif 0bc127a846 Merge amd-dev into amd-master 20240719 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: If86d0b42820c0faf1a6ea4525aec6d11bf57a510


[ROCm/amdsmi commit: c9a113eecf]
 2024-07-19 12:47:11 -05:00
Maisam Arif c63ea0e5e0 [SWDEV-474450] Removed DEVICE_MUTEX from gpu_reset 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I706fb47288738bfbde94b56fee66bbf807b3c0cb


[ROCm/amdsmi commit: 8bc8307c60]
 2024-07-19 11:47:52 -04:00
Maisam Arif 49e4e8f234 Updated Changelog with Mutex Fix 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I0aee284ce7600efc66b0ad5392c11bb6a502a929


[ROCm/amdsmi commit: 3a9c93bfa6]
 2024-07-19 11:18:09 -04:00
Galantsev, Dmitrii 12143a4ec8 [SWDEV-471523] - Replace lspci and lscpu with sysfs reads 
Change-Id: Ia5a12c04d3064787a0f36a961e68533b79e17ed0
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: baaa1cc4b6]
 2024-07-19 00:29:36 -05:00
Galantsev, Dmitrii 8f04a0f91e Merge branch 'dgalants/fix_mutex' into amd-dev 
This change imports changes done to shared_mutex in rocm_smi_lib repo

Change-Id: I1412440b52a3419127b03003df3cc36fa71875d4
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 0f6224cbe6]
 2024-07-18 21:14:34 -05:00
Bill(Shuzhou) Liu 39f37c5d33 Remove thread safe only mutex warning message 
In multiple GPUs environment, too many warning messages generated,
and then need to be removed.

Change-Id: I275de2397eb0e6b189e2e17e94335cb1e8f97815


[ROCm/amdsmi commit: 78ee3f5e5a]
 2024-07-18 20:43:57 -05:00
Bill(Shuzhou) Liu a1aec9c971 Support thread only mutex 
The environment variable RSMI_MUTEX_THREAD_ONLY=1 to enable thread only mutex.
The RSMI_INIT_FLAG_THRAD_ONLY_MUTEX can also be pass to rsmi_init()
to enable thread only mutex.

Change-Id: I2d9844039b774e386f03bb9bb130d8c342504ea6


[ROCm/amdsmi commit: dbba33d3f5]
 2024-07-18 20:43:38 -05:00
Bill(Shuzhou) Liu eb04dbc1c9 Unlock the mutex when process is dead 
After the dead process is detected, pthread_mutex_consistent() will
be called. After that, the pthread_mutex_unlock() should also be
called to unlock it: "It is the responsibility of the application to
recover the state so it can be reused."

Change-Id: I45d3e2e68c3b06779f3acb1e908dbec0c6a39297


[ROCm/amdsmi commit: 06b9232a56]
 2024-07-18 20:43:21 -05:00
Bill(Shuzhou) Liu 3fc94657d9 Remove const to avoid compile error 
Fix the compile error

Change-Id: I422b606b2b969b418c2e77b47a3afad0cfc732a1


[ROCm/amdsmi commit: 33dab0c232]
 2024-07-18 18:15:43 -04:00
Maisam Arif df6b8386cf Fix amd-smi event from reading NONE event type 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I7acf91eb682b3f0873ca34a98191eafd3925a344


[ROCm/amdsmi commit: 8f15c22606]
 2024-07-18 17:54:08 -04:00
Maisam Arif 244587525a Corrected passthrough platform logic 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ibbc4f5dd6300efd16f26efe17bc68eb8c22ed8be


[ROCm/amdsmi commit: b5f9e6a91d]
 2024-07-18 17:54:02 -04:00
Maisam Arif ad3ba88ba5 [SWDEV-474474] - Changed Monitor PCIE_REPLAY count to use gpu_metrics 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I4351a23e8412875bb4b23b30747ac6d0bf3d3c56


[ROCm/amdsmi commit: 5b7be3bf99]
 2024-07-18 17:53:49 -04:00
Maisam Arif a7ea536524 [SWDEV-439701] Add missing parameter CLI error cases 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I8a6623ccdd7b16be320ea0f6f48b7b6cb3511983


[ROCm/amdsmi commit: 0fc779b14f]
 2024-07-18 14:24:00 -04:00
Maisam Arif 0865293d27 [SWDEV-472641] Set file opening and writing encoding to utf-8 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ic5cdca41b588341f7894de72dfe3d949378f9a61


[ROCm/amdsmi commit: c83bcb7ac9]
 2024-07-12 09:46:44 -04:00
Zhang Ava 5385e1d325 Merge amd-dev into amd-master 20240711 
Signed-off-by: Zhang Ava <niandong.zhang@amd.com>
Change-Id: I2d8f9c634d4f3d5427a59b230691722da99f6c01


[ROCm/amdsmi commit: b64603e552]
 2024-07-11 19:38:42 +08:00