AI/rocm-systems
2
0
Çatalla 0
Kod Konular Değişiklik İstekleri İşlemler Paketler Projeler Sürüm Viki Aktivite
1.894 İşleme 3 Dal 0 Etiketler
c8698c87ef7cbce11324028ed0d2b7c2b0b02c99
İşleme Grafiği

499 İşleme

Yazar SHA1 Mesaj Tarih
Poag, Charis bf8bbd99c6 [SWDEV-518561] Separate Driver Reload from Memory Partition Sets (#582) 
Description:
  - Added a new API `amdsmi_gpu_driver_reload()` to reload the AMD GPU driver independently.
  - Updated CLI (`sudo amd-smi reset -r`) and Python bindings to support driver reload functionality.
  - Removed automatic driver reload from `amdsmi_set_gpu_memory_partition()` and `amdsmi_set_gpu_memory_partition_mode()`.
  - Enhanced CLI and test cases to allow users to control when the driver reload occurs.
  - Updated documentation and changelog to reflect the new driver reload process.
  - Improved error handling and logging for driver reload operations.
  - Added progress bar and user confirmation prompts for driver reload commands.

* Update build/test strategy to only allow one test execution at a time
* Modify API verbage + modify systemctl error output
  - Systemctl is typically not enabled on docker.
  - And is an edge case for gpu being active process/etc for display devices.
* Remove AMDSMI_STATUS_AMDGPU_RESTART_ERR from the return values
* Move driver reload to after we save original compute partitions

---------

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

[ROCm/amdsmi commit: d24dc7ef89]
 2025-08-05 20:44:28 -05:00
Liu, Shuzhou (Bill) 7ec0a1a7dd Query UBB/OAM temperature API (#581) 
Add support to Query UBB/OAM temperature.
* Updated Python API with new temperature metrics enum

---------

Co-authored-by: Bill Liu <shuzhliu@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: abd3c02a3c]
 2025-08-05 20:37:45 -05:00
Arif, Maisam e5d03d099a Revert "[SWDEV-505176] Submodule Unified Header in AMDSMI" 
This reverts commit 0e895cf235.


[ROCm/amdsmi commit: 240a607904]
 2025-07-30 14:08:24 -05:00
Narlo, Joseph 0e895cf235 [SWDEV-505176] Submodule Unified Header in AMDSMI 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: a315b62e37]
 2025-07-30 13:37:01 -05:00
Pham, Gabriel 6369febcbd [SWDEV-545342] Fixed amdsmi_link_type_t enumeration (#560) 
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: e2eac98496]
 2025-07-22 18:22:49 -05:00
Bindhiya Kanangot Balakrishnan c2bc3ca72e [SWDEV-543308] Revert amdsmi_link_metrics structure change 
Moved the bit_rate and max_bandwidth back into links in the
amdsmi_link_metrics_t struct as this change was impacting
other teams. Modified the C and python API's, wrapper, and
CLI accordingly.

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


[ROCm/amdsmi commit: 645c313f00]
 2025-07-14 13:56:26 -05:00
Narlo, Joseph 540ecd41bd [SWDEV-541675] Remove Unnecessary API from amdsmi.h (#530) 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: 2cf6272b53]
 2025-07-07 11:14:27 -05:00
Galantsev, Dmitrii 44986cfbd4 DRM - Remove FD usage 
Change-Id: I77dfa778ccd0d39a03289c2e11cf10357566ff16
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 9b5bbf555a]
 2025-06-20 11:00:42 -05:00
Galantsev, Dmitrii 40228106b5 DRM - Remove caching 
Change-Id: I21716cc953462e385e981024f75a9a7c2d76a466
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: 202b46d96f]
 2025-06-20 11:00:42 -05:00
Galantsev, Dmitrii ccdd52e9c0 DRM - Update to latest public 
Change-Id: I9f7b46acbae654c377702a599c4b094fd621f101
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>


[ROCm/amdsmi commit: cb2f152205]
 2025-06-20 11:00:42 -05:00
josnarlo ed9086505d [SWDEV-538604] Sync Unified Header and AMDSMI Comments 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>


[ROCm/amdsmi commit: 5ed9fba9be]
 2025-06-18 09:13:01 -05:00
josnarlo 48ed5787a6 [SWDEV-537983] Fix comments about temperature units for amdsmi_get_temp_metric 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>


[ROCm/amdsmi commit: d4a946717b]
 2025-06-13 16:51:59 -05:00
josnarlo 986a2dd0b5 [SWDEV-537983] Fix comments about temperature units for amdsmi_get_temp_metric 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>


[ROCm/amdsmi commit: 4aee30f49b]
 2025-06-13 16:51:59 -05:00
Maisam Arif 6e37490e87 [SWDEV-529665] PLDM Bundle naming 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Id7f652ddc4e790027869683a4aaa3226ffc05c83


[ROCm/amdsmi commit: 6da33b8ded]
 2025-06-12 02:19:37 -05:00
Maisam Arif 7be2218717 [SWDEV-537491] Updated Copyright to aca-decode files 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I9621e4c54f3b490c6eb4cfc3e9bdfb4d489f0052


[ROCm/amdsmi commit: 5763412f7d]
 2025-06-11 20:51:51 -05:00
Saeed, Oosman cc2b4b4067 [SWDEV-536417] AFID & addc decode fixes (#449) 
* fix endian problem
* use hw_revision and flags_mask from cper section instead of hardcoded values

---------

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

[ROCm/amdsmi commit: 815e0252b1]
 2025-06-06 13:41:16 -05:00
Charis Poag df6de25624 [SWDEV-529030/SWDEV-531217] Fix tests & output for partitioned configurations (CPX, DPX, QPX, etc.) 
Changes:
  - Updated AMD SMI firmware to display "N/A" for unavailable firmware in partitioned environments, improving clarity.
    Example (in DPX):
    $ amd-smi firmware
    GPU: 0
        FW_LIST:
            ...
            FW 12:
                FW_ID: PM
                FW_VERSION: 00.86.39.00
    GPU: 1
        FW_LIST: N/A
  - Fixed amd-smi partition not showing current partition information on
    asics with inablity to set memory or accelerator partitions.
    $ amd-smi partition -c -m
    CURRENT_PARTITION:
    GPU_ID  MEMORY  ACCELERATOR_TYPE  ACCELERATOR_PROFILE_INDEX  PARTITION_ID
    0       NPS1    CPX               2                          0
    1       N/A     N/A               N/A                        1
    2       N/A     N/A               N/A                        2
    3       N/A     N/A               N/A                        3
    4       N/A     N/A               N/A                        4
    5       N/A     N/A               N/A                        5
    6       NPS1    SPX               0                          0
    7       NPS1    SPX               0                          0
    8       NPS1    SPX               0                          0

    MEMORY_PARTITION:
    GPU_ID  MEMORY_PARTITION_CAPS  CURRENT_MEMORY_PARTITION
    0       N/A                    NPS1
    1       N/A                    N/A
    2       N/A                    N/A
    3       N/A                    N/A
    4       N/A                    N/A
    5       N/A                    N/A
    6       N/A                    NPS1
    7       N/A                    NPS1
    8       N/A                    NPS1

  - Refactored amd_smi_drm_example.cc:
    - Grouped partition changes and restores original partition settings.
    - Now handles partitioned environments allowing example to continue even if some APIs are not supported in partitioned configurations.
  - Modified amdsmi_asic_info_t (see amdsmi_get_gpu_asic_info()) to report OAM ID as N/A if 0xFFFFFFFF (was 0xFFFF).
    Allows for better handling of OAM IDs in partitioned environments (DNE for non-primary nodes,
    since its a physical identifier). Easier to handle in tests and example code (ie. now consistent w/ max size of the structure's value).
  - Introduced amdsmi_RAII_open_FD() (internal API) to manage file descriptors using RAII, ensuring proper closure and preventing resource leaks.
    Updated the following APIs to use this function:
      - amdsmi_get_gpu_asic_info(), amdsmi_get_gpu_vram_usage(),
        amdsmi_get_gpu_vram_info(), amdsmi_get_gpu_vbios_info(),
        amdsmi_get_gpu_driver_info(), amdsmi_get_gpu_virtualization_mode()
  - Updated AMD SMI test_base.cc/.h:
    - Improved output and handling for partitioned environments.
    - Added detailed ASIC information logging to align with structure changes.
    - Enhanced error messages for better context before ASSERT checks.
  - Resolved test failures in partitioned environments by updating
    logic and handling for partition-specific configurations.
    Fixed tests include:
      - computepartition_read_write.cc, frequencies_read_write.cc,
        gpu_metrics_read.cc, mem_util_read.cc, memorypartition_read_write.cc,
        perf_level_read.cc, perf_level_read_write.cc, power_cap_read_write.cc,
        power_read.cc, sys_info_read.cc, gpu_busy_read.cc

Change-Id: I36e903f8fddd714c74c719459c71aba8bbb77e6f
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

Resetting head + adding fixes for tests ran in partitions

Change-Id: I0c1e9ac07488b50c95f3bc6d8a724e67d2c715dc
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 391451752b]
 2025-06-05 19:24:49 -05:00
Saeed, Oosman 99df131155 [SWDEV-530385] Update aca-decode with parsing fixes (#435) 
*Update aca-decode to #4cd539d that fixes some errors in parsing cper files for afid extraction
*Without this fix, we get garbage value for some cper input files relating GFX_poison_cpers

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

[ROCm/amdsmi commit: 2c3fa591b5]
 2025-06-04 18:49:05 -05:00
Arif, Maisam e38de3932f Add Directory Not Found Status code to map to ENOTDIR (#238) 
* Corrected ecc count error return
* Added directory not found error code
* Added ENOTDIR mapping to RSMI_STATUS_DIRECTORY_NOT_FOUND in ErrnoToRsmiStatus

---------

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: e2692ab533]
 2025-06-03 17:53:33 -05:00
Narlo, Joseph ba8d2f0d84 [SWDEV-532069] Doxygen Not Picking Non-Documented Values (#362) 
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Signed-off-by: Deepak Mewar <deepak.mewar@amd.com>
Co-authored-by: Arif, Maisam <Maisam.Arif@amd.com>
Co-authored-by: Deepak Mewar <deepak.mewar@amd.com>

[ROCm/amdsmi commit: c0c4e021ea]
 2025-06-03 17:24:44 -05:00
Narlo, Joseph 4eb6d34df0 [SWDEV-532769] amd-smi APIs mismatch with documentation (#428) 
* Populated socket_power to get power info
---------

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

[ROCm/amdsmi commit: ce7d6dfe61]
 2025-06-03 17:12:13 -05:00
Joseph Narlo 3d0f98c16d [SWDEV-522996] Syncing Unified Header and AMDSMI 
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>


[ROCm/amdsmi commit: ee43ec71e8]
 2025-06-02 13:44:33 -05:00
Maisam Arif 00ad72baf9 Deprecated PASID 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ib008f80f3d736172079358c0ceb3ebca87340d28


[ROCm/amdsmi commit: c89b5db09d]
 2025-05-30 20:48:29 -05:00
Maisam Arif 16d60f3411 [SWDEV-488303] Fixed process list information source 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Iec3416cb5ca1bdd806c3225b514bbf3dbf8c0d2e


[ROCm/amdsmi commit: cebb0799cb]
 2025-05-30 20:48:29 -05:00
Maisam Arif 5324134708 Version Bump 26.0.0 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I29ea6fa781dfc338a60b390ff498c46b4a1efe52


[ROCm/amdsmi commit: cc4dfd834f]
 2025-05-30 20:48:29 -05:00
Kanangot Balakrishnan, Bindhiya f12c72a4e2 [SWDEV-530633] Use gpu_metric speed and BW for xgmi (#366) 
The xgmi command was showing pcie bit rate and bandwidth instead of xgmi. Corrected the API to get xgmi data from gpu metric.
Added python API for amdsmi_get_link_metrics. Modified the amdsmi_link_metrics struct.
Added check to confirm non zero partition got xgmi command.

---------

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

[ROCm/amdsmi commit: 2eff0b3764]
 2025-05-30 16:51:11 -05:00
Arif, Maisam da430dec05 [SWDEV-488303] Adjusted process vram_mem data source (#411) 
* [SWDEV-488303] Adjusted process vram_mem data source
* Standardized sscanf format strings

---------

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: 42441c78ea]
 2025-05-29 23:26:12 -05:00
Arif, Maisam 465f2e6a41 [SWDEV-488303] Updated CU occupancy for per-process retrieval (#243) 
Change-Id: I2990597c6dd4b2e8cf3e11ce60f72049ebdd9a8c
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>

[ROCm/amdsmi commit: 0fdaebdbaa]
 2025-05-29 20:35:27 -05:00
Maisam Arif 418ec78c21 [SWDEV-534707] Adjust power value documentation 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I1c4516e403715b9a1fe9c78fae94848c89daa920


[ROCm/amdsmi commit: fba62e2270]
 2025-05-29 18:55:44 -05:00
Liu, Shuzhou (Bill) ff2e230a34 [SWDEV-520665] Add support for board voltage (#303) 
* Add the API and CLI to show the board voltage. 

---------

Change-Id: Icb25bd653bb1d004704b5a21b378ca31b2b242c7
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Signed-off-by: AL Musaffar, Yazen <Yazen.ALMusaffar@amd.com>

[ROCm/amdsmi commit: 970560fc7c]
 2025-05-29 18:55:08 -05:00
Kanangot Balakrishnan, Bindhiya 2155c96c9e [SWDEV-463406] ViolationStatus Changes (#288) 
* Expanded Violation Status tracking for GPU metrics 1.8
* Added new fields to `amdsmi_violation_status_t` and related interfaces for enhanced violation statuses
---------

Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>

[ROCm/amdsmi commit: e7f19b36f0]
 2025-05-29 13:26:21 -05:00
Mewar, Deepak 4b0397fd80 [SWDEV-512393] Fix for incorrect cpu set size input (#399) 
Signed-off-by: Deepak Mewar <deepak.mewar@amd.com>

[ROCm/amdsmi commit: 9a49e454fd]
 2025-05-29 12:14:03 -05:00
Pryor, Adam 69fde31369 Remove ring hang (#391) 
Change-Id: I856cd0949d3661911ab9302148aa1bc6e72abeed

Signed-off-by: adapryor <Adam.pryor@amd.com>

[ROCm/amdsmi commit: d0a89393df]
 2025-05-29 11:58:46 -05:00
Maisam Arif 3db6b8b36c Removed leftover AMDSMI_MAX_DRIVER_VERSION_LENGTH 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Iee95728e6eb6d7962ed658b9a77feccb88e24e92


[ROCm/amdsmi commit: 2481573184]
 2025-05-29 10:34:21 -05:00
Narlo, Joseph cd3128f997 [SWDEV-522996] Syncing Unified Header and AMDSMI (#355) 
* Update doxygen help text and formatting

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

[ROCm/amdsmi commit: 4cd0f3391e]
 2025-05-28 19:06:10 -05:00
Narlo, Joseph 8d6253d772 [SWDEV-532125] Remove_Unused_Definitions (#385) 
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: b6d638d942]
 2025-05-28 18:49:08 -05:00
Narlo, Joseph 41522f665f [SWDEV-532131] Update String Lengths (#383) 
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: 7c29b4eab8]
 2025-05-28 18:31:30 -05:00
Narlo, Joseph d2bf77401e [SWDEV-532129] Update amdsmi asic info (#369) 
* Added `subsystem_id` to `amdsmi_get_gpu_asic_info`
---------
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: 9862db63dd]
 2025-05-28 18:26:58 -05:00
Narlo, Joseph 1fbddb6dcc [SWDEV-533941] Align P2P input struct (#395) 
* Removed `amdsmi_io_link_type_t` and replaced with alredy implemented amdsmi_link_type_t
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: f3a5cc9cd5]
 2025-05-28 18:22:19 -05:00
Narlo, Joseph 59f5827164 [SWDEV-535200] Remove deprecated function amdsmi_get_power_info_v2 (#397) 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: 38a1fadf44]
 2025-05-28 18:09:13 -05:00
Narlo, Joseph 268c4e59ed [SWDEV-534438] Update structure amdsmi_bdf_t (#388) 
Signed-off-by: josnarlo <Joseph.Narlo@amd.com>
Signed-off-by: Narlo, Joseph <Joseph.Narlo@amd.com>

[ROCm/amdsmi commit: 7b3c85e970]
 2025-05-28 18:05:43 -05:00
Narlo, Joseph cd71942678 [SWDEV-529483] Get Vram Vendor Name from Driver (#323) 
* Update to remove vram enum and instead use the string directly from the driver.

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

[ROCm/amdsmi commit: f71ae88956]
 2025-05-28 17:57:49 -05:00
Maisam Arif 28d1aaf066 Spellcheck 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I3842ca7552c8d3525ac7fee8c94b15cfdd7defdd


[ROCm/amdsmi commit: cebc512b1a]
 2025-05-27 13:59:23 -05:00
Pham, Gabriel 24f25b4133 Updated docs with new KFD events (#382) 
* Updated docs with new KFD events

---------

Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: c40d4291f6]
 2025-05-27 12:21:38 -05:00
Daniel Oliveira 806c3c62ed [SWDEV-529665] Add PLDM Bundle version 
feat: Report PLDM Bundle from SMC to IB

Code changes related to the following:
  * APIs
  * CLI
  * Unit tests

Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
Change-Id: I35ccf01eb612ca80e3ae6b72039085c18c989222


[ROCm/amdsmi commit: fe9b6eeb49]
 2025-05-20 01:37:00 -05:00
Mewar, Deepak 9a3c59c63c [SWDEV-512393] Added amdsmi_get_cpu_affinity_with_scope (#198) 
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Deepak Mewar <deepak.mewar@amd.com>

[ROCm/amdsmi commit: b999f86611]
 2025-05-20 01:06:09 -05:00
Pryor, Adam 36f8565856 [SWDEV-527092] - Fix ringhang event removal (#372) 
Signed-off-by: adapryor <Adam.pryor@amd.com>

[ROCm/amdsmi commit: 51e99965b3]
 2025-05-16 16:41:31 -05:00
Pryor, Adam 8f6cde2376 [SWDEV-527092] - Process Start/Stop event addition (#368) 
- Added more events to `amdsmi_evt_notification_type_t`

Change-Id: I6a256fe828e4bec3197c7fecbed374ab17c6f850
Signed-off-by: Adam Pryor <Adam.Pryor@amd.com>

[ROCm/amdsmi commit: 8713305f80]
 2025-05-16 11:01:15 -05:00
Saeed, Oosman ffc8b09056 [SWDEV-522623] Add afid functionality to API and CLI (#330) 
Change-Id: I015bde926491d54e09da8f39b05650515711e09f

[SWDEV-522623] Add afid functionality to API and CLI


Change-Id: I015bde926491d54e09da8f39b05650515711e09f

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

[ROCm/amdsmi commit: 1bb1f8acc2]
 2025-05-16 10:49:56 +08:00
Arif, Maisam 7ded6504b8 Version & Doc update (#343) 
Change-Id: Ibf8e1809913e30aba4b21ba889b72e5db7205736

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

[ROCm/amdsmi commit: ace3b0901a]
 2025-05-08 12:19:04 -05:00