Commit Graph

330 Commits

Author SHA1 Message Date
Narlo, Joseph c26da62fc7 [SWDEV-513651] Sync Unified And Linux Header (#98)
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>

[ROCm/amdsmi commit: dc4a16da6f]
2025-02-06 22:25:50 -06:00
Arif, Maisam e8a8122111 [SWDEV-494072] Added Fallback to metric command to for pcie replay_counter (#99)
Change-Id: I5392e8f881b1e69d9a76b01813a66b08fb70e006

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

[ROCm/amdsmi commit: 548ed781c7]
2025-02-06 19:33:49 -06:00
Maisam Arif 3550702604 [SWDEV-513127] - Fixed spelling in amdsmi_parser.py
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Id15b7e1e15d8719c36d508db6cf2667234928b92


[ROCm/amdsmi commit: 08be2db720]
2025-02-04 17:57:16 -06:00
Poag, Charis 020d194100 [SWDEV-513127] Fix AttributeError: 'AMDSMILogger' object has no attribute 'clear_multiple_devices_output' (#92)
Full output:
$ amd-smi metric:
 AttributeError: 'AMDSMILogger' object has no attribute 'clear_multiple_devices_output'. Did you mean: 'clear_multiple_devices_ouput'?

Changes:
* Changed CLI function definition clear_multiple_devices_ouput(self) ->
clear_multiple_devices_output(self)
* Updated all references to clear_multiple_devices_ouput() to use
  clear_multiple_devices_ouput()

Change-Id: Ibd4e210ea30c9dd51fba17981a524b823f2db054

[ROCm/amdsmi commit: 1d2272490e]
2025-02-04 09:30:12 -06:00
Pham, Gabriel 5c1f610cc1 [SWDEV-462952] Updated passthrough to use virtualization mode struct
Signed-off-by: gabrpham <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: e663bed7d6]
2025-01-31 17:34:01 -06:00
Poag, Charis 76a1641800 Fix AttributeError: 'Namespace' object has no attribute 'cpu_pwr_svi_telemetry_rails'
Updated missing references to cpu_pwr_svi_telemetry_rails

Change-Id: I1828ad3122a602dc5c4253500f83c3910b682cb3
Signed-off-by: Poag, Charis <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 3a94f5a880]
2025-01-31 08:12:42 -06:00
Pham, Gabriel c735f77be1 [SWDEV-462952] Options enabled for GPU passthrough scenarios
Added Dynamic Passthrough detection

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

[ROCm/amdsmi commit: 0f79efac78]
2025-01-30 18:12:03 -06:00
Pham, Gabriel d2067e7d56 [SWDEV-493207] Made fixes to enable hsmp version
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: 5b2c271eff]
2025-01-30 16:14:21 -06:00
Kanangot Balakrishnan, Bindhiya c9ba59f49a [SWDEV-511961] Wrap BM specific set help text
BM specific help text contained functions that required the driver to be loaded.
this was causing amd-smi not supported error on Linux guests.
Fixed this by wrapping the help text in the proper checks

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

[ROCm/amdsmi commit: 51c705fd43]
2025-01-30 03:25:48 -06:00
Pham, Gabriel 634bacfdf6 [SWDEV-493207] Added amd_hsmp version to version command
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: 0326c52ce9]
2025-01-30 03:12:08 -06:00
Arif, Maisam da7e32834b Updated Import Error Logging
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ief4a5f100f54668c5bce001ea051136738fbc468

[ROCm/amdsmi commit: 703415cb1f]
2025-01-28 15:56:49 -06:00
Kanangot Balakrishnan, Bindhiya a725ae078c [SWDEV-508042] Fix TypeError in specific clocks csv logging (#57)
Logging specific clocks in csv format was causing TypeError as the levels were int.
Fixed this by appending Level string at the beginning.

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

[ROCm/amdsmi commit: e3e11835e4]
2025-01-22 18:06:13 -06:00
Pham, Gabriel 9617b9c269 [SWDEV-493207] Added amdgpu version to version command
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: b779ce2831]
2025-01-22 18:05:25 -06:00
Kanangot Balakrishnan, Bindhiya d31107d110 SWDEV-457845: Fix Linux VM clean_local_data error on set
Corrected clean_local_data error in Linux VM's while doing
amd-smi set without args.

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

[ROCm/amdsmi commit: 834993e1c3]
2025-01-20 14:45:27 -06:00
Poag, Charis fa81bcb513 [SWDEV-488276] Add partition 2.0 functionality (#44)
Changes:
* CLI:
  - Updated amd-smi partition
  - Updated amd-smi partition -c
  - Updated amd-smi partition -m
  - Updated amd-smi partition -a
  - Updated amd-smi set -M <NPS1/NPS2/NPS4/NPS8>
  - Updated amd-smi set -C <SPX/DPX/QPX/TPX/CPX>
  - Updated amd-smi set -C <ACCELERATOR_TYPE> or <PROFILE_INDEX>
    Where PROFILE_INDEX = available ACCELERATOR_TYPES
  - Updated amd-smi set --help, now includes more detail for
    amd-smi set -C <ACCELERATOR_TYPE> or <PROFILE_INDEX>

* API:
  - Added amdsmi_get_gpu_memory_partition_config
  - Added amdsmi_set_gpu_memory_partition_mode
  - Added amdsmi_get_gpu_accelerator_partition_profile_config
  - Updated amdsmi_get_gpu_accelerator_partition_profile_config
  - Added amdsmi_set_gpu_accelerator_partition_profile

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

[ROCm/amdsmi commit: c1cd2b46ef]
2025-01-16 00:53:46 -06:00
Scaffidi, Salvatore 6eeb06927d [SWDEV-463406] Update API with fields for gfx_clock_below_host_limit and low_utilization violations
Updated API with fields for gfx_clock_below_host_limit and low_utilization violations
Change-Id: I25647bae6e7b785f44dab024272767658688bcad

---------
Signed-off-by: Scaffidi, Salvatore <Salvatore.Scaffidi@amd.com>
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 3793be7735]
2025-01-08 22:07:23 -06:00
Kanangot Balakrishnan, Bindhiya 67d5b8568a SWDEV-504130 Add temperature violation status to amd-smi monitor (#2)
Added boolean temperature violation status to amd-smi monitor.

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

[ROCm/amdsmi commit: d0e770ffbc]
2025-01-08 16:35:53 -06:00
Pham, Gabriel 9e4aa3a2e1 [SWDEV-502523] Made amd-smi reset command arguments mutually exclusive
Made reset arguments mutually exclusive so that users can only 
select one option at a time to prevent throwing of errors.

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

[ROCm/amdsmi commit: 129ad8ffad]
2025-01-08 16:24:05 -06:00
Kanangot Balakrishnan, Bindhiya a1d60ef088 [SWDEV-439701] Fix wrong error handling in MissingParameterValue (#32)
Error handling was not displaying the missing parameter details in
argument type validator functions. Fixed this by passing param name to
AmdSmiMissingParameterValueException.

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

[ROCm/amdsmi commit: 3897670757]
2025-01-07 17:13:00 -06:00
Pham, Gabriel e9fbe5bc66 [SWDEV-502523] made set gpu arguments mutually exclusive (#31)
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>

[ROCm/amdsmi commit: 5ed340c08b]
2025-01-07 16:48:01 -06:00
Pham, Gabriel 0c4db04140 [SWDEV-476303] Exposed valid values for set command (#8)
Updated amd-smi set help text
---------

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

[ROCm/amdsmi commit: 93a027ec95]
2024-12-20 15:32:10 -06:00
gabrpham 11d7fb9508 Additional fixes for amd-smi static --clock
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>


[ROCm/amdsmi commit: 23da950ef0]
2024-12-20 14:45:20 -06:00
Charis Poag bf4bbef085 [SWDEV-484382] Fix VCLK/DCLK outputs for monitor, static, metric
Units were off and VCLK/DCLK outputs were not coming in
properly through amdsmi_get_clk_freq()

Now we match units sent back through rsmi_dev_gpu_clk_freq_get (MHz).

CLI now shows maximum of 2 VCLK/DCLKs otherwise shows N/A if there
is no current_freq listed.

Change-Id: I8a7b66cbb5263e8d396f8568c104e1ce3512923d
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 3226a1d0ea]
2024-12-20 14:11:08 -06:00
Juan Castillo 2ddb2ef032 [SWDEV-496693]GPU Metrics 1.7
Features added:
- [SWDEV-475244] Add new interface to get max memory bandwidth
Updated API: amdsmi_get_gpu_vram_info
Updated: struct amdsmi_vram_info_t to include vram_max_bandwidth
CLI: amd-smi static --vram

- [SWDEV-488349] Add new interface for XGMI link status
New API: amdsmi_get_gpu_xgmi_link_status
CLI: amd-smi xgmi --link-status

Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Change-Id: I1aa35b741136eb4f02f7ea9a95b865886273eb72


[ROCm/amdsmi commit: f8b8347627]
2024-12-18 10:57:06 -06:00
gabrpham d71dac9766 [SWDEV-484382] Added fclk and socclk to amd-smi metric -c
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ie7e19c757b05455693c0d26eeb5e8b6c1e238375


[ROCm/amdsmi commit: fe290a2056]
2024-12-13 00:33:12 -05:00
gabrpham 49a0904903 [SWDEV-484382] Added new command amd-smi set -c/--clk-level
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: If45152e3a3c94f65b6a8a960601b9ed16fa3d0d7


[ROCm/amdsmi commit: 5f9c2db6f3]
2024-12-13 00:32:19 -05:00
gabrpham cb42e8e444 [SWDEV-484382] Added new command amd-smi static --clock
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I49e1aa2e699734d81c40c76c62da1cecc5bd3c0e


[ROCm/amdsmi commit: bc16e1a5da]
2024-12-13 00:30:29 -05:00
Charis Poag 323ebacde0 Fix amd-smi firmware not printing YAML-like dictionary correctly
List string should take into account dictionary value types

Change-Id: Icc08288cb0007d43eacd1aff6d44c40a84ea9448
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 57f45954b7]
2024-12-11 10:48:43 -05:00
Maisam Arif 6447baeedd Fixed spacing in amd-smi --xgmi
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I9fbd20c50a25aa3be80c8aa68eea37b81a74dc67


[ROCm/amdsmi commit: 554203c13a]
2024-12-10 15:45:06 -05:00
Charis Poag 95cc962509 [SWDEV-488288] Remove GFX_BUSY_ACC from amd-smi metric --usage
Output is not helpful to users.

Change-Id: I12a60e28b8eab2fc3ffca4ea88f03018bf0ef3ce
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: bc0015fd36]
2024-12-10 13:37:36 -05:00
Bindhiya Kanangot Balakrishnan efa7286410 [SWDEV-496639] Align amd-smi xgmi statistics
The xgmi read and write values were displayed in KB. The numbers became
unreadable due to misalignment. So, converted read and write values to
readable units using helper function. Updated Changelog.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Change-Id: I4c90a1de8a58c29cbdf43fe3480a1546f3946673


[ROCm/amdsmi commit: 288b11df37]
2024-12-09 12:57:45 -05:00
Charis Poag 44adc457b2 [SWDEV-502744] Fix "amd-smi monitor" shows VCN ENC utilization & clock but not VCN DEC
Reason for this fix:
Navi products use vclk and dclk for both encode and decode.
On MI products, only decode is supported.
Navi products cannot support displaying ENC_UTIL % at this time.

Change-Id: I107bb761794ae4724949ac21c110b23a4f616700
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: d323ecff97]
2024-12-07 12:11:10 -05:00
gabrpham cdecce3658 Fixed post reset and ring_hang issues
Issues include:
	SWDEV-480250
	SWDEV-480255
	SWDEV-480248
Known issue:
	`amd-smi event` has threads taking events from the same device
which, in the case of resetting gpus, makes it seem like some gpus have
reset mulitple times and other have not reset at all.

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ic7dcc214e0366fc1532ece579d915d34d35d5407


[ROCm/amdsmi commit: bd01cfc203]
2024-12-06 17:46:00 -05:00
Bindhiya Kanangot Balakrishnan 3794b3796c [SWDEV-457845] Error code unification for amd-smi set
Earlier amd-smi set was returning different outputs in Linux
and Windows. In Linux it was returning ValueError. As part of
Error Code unification, corrected this output message.

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Change-Id: Iba9ddd9c5b2bed0456f303e4373f6771c93608be


[ROCm/amdsmi commit: 1586005a5b]
2024-12-06 14:21:31 -05:00
Maisam Arif f707990d49 Added gpu_metrics table debug logs in monitor
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I8aa96629a65df7a2d52ef9ed42a884732d097a54


[ROCm/amdsmi commit: bc3ac61641]
2024-12-05 15:18:13 -06:00
Justin Williams 8c9cb42a58 [SWDEV-469278] Removed PyYAML Dependency
Signed-off-by: Justin Williams <Justin.Williams@amd.com>
Change-Id: Idec32cfb0de84cc255b506d7f972e2750992745e


[ROCm/amdsmi commit: 2370aa1b40]
2024-12-03 15:40:44 -05:00
Bindhiya Kanangot Balakrishnan bfd480c6ba [SWDEV-498507] Tool amd-smi could be more case insensitive
Modified amdsmi_cli to accept case insensitive arguments if
the argument does not start with a single dash(-).

Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Change-Id: I1b6320db0afaad0900d5a2049206002c3899fa71


[ROCm/amdsmi commit: fc7e1ddb4a]
2024-12-02 18:09:45 -05:00
Charis Poag e3793942de [SWDEV-499029] Fix unable to change memory partition modes
Changes:
  * [API] Removed checking board name, fixes for other MI ASICs
  * [API] Fixed unable to restart AMD GPU, libdrm blocked
    doing this operation
  * [API] Added ability to unload/reload libdrm
    from within AMD SMI APIs
  * [CLI] Increased progress bar to change memory partition modes
    to 140 seconds, since driver reload is variable per system

Change-Id: I52f227f2ab850c4a6332ff3ecdc899903b1080f1
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 7d061f9ae4]
2024-11-25 09:28:02 -05:00
Joe Narlo bad2cc9c23 SWDEV-495787 [AMDSMI] Different license headers
Change copyrights to MIT and remove date

Signed-off-by: Joe Narlo <Joseph.Narlo@amd.com>
Change-Id: I16f5b412f2b9ddefaaa1771aa714cc18829a1be4


[ROCm/amdsmi commit: 3052ad4220]
2024-11-22 08:55:28 -05:00
gabrpham f963f24d63 [SWDEV-498453] Enabled 'amd-smi set --clk-limit' for virtual environments
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I23e994502d4abc1a602d2341e77ad9c50fcf4839


[ROCm/amdsmi commit: 50eaf14b9e]
2024-11-19 16:17:29 -06:00
gabrpham f7a77c2539 [SWDEV-498453] Enabled for virtual environments
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ic7b274cf8e579b733515efe84fc0f325256ef8b1


[ROCm/amdsmi commit: fc9d18dd3e]
2024-11-18 11:57:04 -05:00
Maisam Arif 48da4536c7 Updated CLI exceptions
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I5c68eed7719c093727afa434e25ba2560dde894a


[ROCm/amdsmi commit: f1c3fbf226]
2024-11-15 11:44:51 -05:00
Charis Poag f01eea6077 [SWDEV-488276/SWDEV-497613] Update memory partition set functionality
Changes:
  - [CLI] Added warning screen to AMD SMI users
    setting memory partition
  - [CLI] Added a progress bar time-bar for CLI sets display to 40 seconds
  - [API] Updated to wait until the driver reloads with SYSFS files active
  - [CLI] Now users can set or reset without providing:
    amd-smi set -g all <set arguments>
    or amd-smi reset -g all <set arguments>
    now can directly call -> sudo amd-smi set <set arguments>
    or sudo amd-smi reset <set arguments>
  - [SWDEV-475712][CLI/API] Fixed target_graphics_version field
    not properly displaying for older MI or Navi ASICs.
  - [All APIs] Added a catch for the driver to report invalid arguments
    now these APIs will show AMDSMI_STATUS_INVAL
    (ex. changing to NPS8 if the device does not support it)
  - [Install] Modified paths for Python install commands to support
    multi-ROCm installs

Change-Id: Id11f25d68a82d23c6b2d77ccb30b51e860dd0ca7
Signed-off-by: Charis Poag <Charis.Poag@amd.com>


[ROCm/amdsmi commit: 3ea4a42a6e]
2024-11-12 16:50:32 -04:00
gabrpham 194c33852f [SWDEV-492739] Partial fix for sclk min/max out of bounds
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I1f0230955c890c11a735c8cb352c8a9ee4cebe27


[ROCm/amdsmi commit: 2273d95a6c]
2024-11-11 20:45:37 -05:00
gabrpham f9bfce707d updated cli tool examples doc to reflect current CLI
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Iab78a412464ba6d7919aeb7da04a031b063a7d09


[ROCm/amdsmi commit: 0f067488e1]
2024-11-11 17:12:40 -05:00
Maisam Arif 43efe1c39a Updated parser help text
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I8cc65edb1e629a55e0efbfc1109b1c549ed81101


[ROCm/amdsmi commit: 7932de967a]
2024-11-11 15:07:21 -06:00
Peter Park a003e50130 docs: Remove redundant/stale docs
bump rocm-docs-core to 1.8.2

rm unused files

rm stale docs

fix sphinx conf

reorg docs

SWDEV-482203 -- add note to usage guides

update readmes

Change-Id: I9e0111ac8fe2a691ac964b27436ba47747c27904
Signed-off-by: Peter Park <Peter.Park@amd.com>


[ROCm/amdsmi commit: e196f98dba]
2024-11-11 16:49:17 -04:00
Maisam Arif 27d81891be Adjusted private helper variables
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: I0590b9ee5a1b4d5e6d4ae71c9587550c8d95033b


[ROCm/amdsmi commit: 5449d78cc4]
2024-11-08 11:25:50 -06:00
Maisam Arif e9f43bc3dd Added ras and ecc counting back to Linux VMs
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Change-Id: Ie981f7fe8f481f2137e95dda2e200d00ab4d92c8


[ROCm/amdsmi commit: abee26d4ab]
2024-11-08 11:05:15 -06:00
gabrpham f162de9efd [SWDEV-495985] Changed ACCELERATOR_TYPE default value.
Default value changed from 0 to "N/A".
	Actual values for all fields will be filled out in later API
update.

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I69b08fff894a032ef79301754807ed4b5c85257f


[ROCm/amdsmi commit: 27996aef18]
2024-11-07 21:22:28 -05:00