- **Added evicted_time metric for kfd processes**.
- Time that queues are evicted on a GPU in milliseconds
- Added to CLI in `amd-smi monitor -q` and `amd-smi process`
- Added to C API and Python API:
- amdsmi_get_gpu_process_list()
- amdsmi_get_gpu_compute_process_info()
- amdsmi_get_gpu_compute_process_info_by_pid()
---------
Signed-off-by: Pryor, Adam <Adam.Pryor@amd.com>
[ROCm/amdsmi commit: 2144cfbba4]
Changes:
- Update violation status logic and metric naming for XCP/XCC metrics (thrm/thm consistency)
- Added XCP identifier in monitor to allow partition metrics to be shown with applicable APIs
(Violation Status is the first example of this in monitor)
- Improve CLI monitor output:
support multiple GPU lines per GPU, add new columns, and better formatting
- Refactor helpers and logger for flexible unit formatting and table rendering
- Add examples for amdsmi_get_gpu_pm_metrics_info()/amdsmi_get_gpu_reg_table_info()
new metrics APIs in C++ example
- Sync Python/C++ interface and structures for new metrics fields and naming
- Remove deprecated/unused RSMI activity APIs, documentation not needed since
the APIs no longer exist in ROCm SMI either.
- Cleanup metric violations + fix handle watch arguments
- Provide better handling/doc for average_flattened_ints()
- Group xcp metrics with brackets in human readable + adjust output size
Signed-off-by: Poag, Charis <Charis.Poag@amd.com>
[ROCm/amdsmi commit: e2e4fc65c1]
The amd-smi command will will show only executable
name of a process by stripping absolute path. This
cause "N/A" process names incorrectly display as
"A" in the output. Corrected the same.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: b16a66b2c5]
Modified the file used to fetch process name so that complete name with path can be displayed.
Changes:
amd-smi monitor -q
- human readable format will output only the process name
- csv and json formats will print the full path
amd-smi process
- name will always be the full path to the process
amd-smi (default output)
- name will always be truncated.
---------
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 514517e536]
* [SWDEV-537852] Update process name help text
Currently process name displays N/A if that need elevated
permissions. Updated the default amd-smi, process and monitor
commands help texts to display elevated permission requirement.
---------
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: ce230efaaa]
The custom_dump function was not printing list's key
and so static numa was not displaying list keys
CPU affinity and Socket affinity. Updated custom_dump
to print the keys.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 6fbda16098]
The amd-smi partition --json output was not in valid json
format. Changes are done to get the output in valid
json format.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 872c58b7a3]
The amd-smi xgmi --json output was not in valid json
format. Changes are done to get the output in valid
json format.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 8f943b03e1]
* Added degree symbol and fixed power usage
* Added degree symbol and fixed power usage
* fixed default command
---------
Signed-off-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
[ROCm/amdsmi commit: bc158d2b51]
When all clocks are N/A's, it will be filtered. To
avoid confusion, single N/A is added.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 62294df49a]
The N/A leaves filering was removing clock in static.
To avoid this, removed N/A filtering from single tier.
Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: e26e26e308]
The 'amd-smi metric --clock' was listing values with N/A. Filtered these outputs to show only available values.
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 797e4fba07]
Earlier, the amd-smi metric and static json output
was not in valid json format. Changes are done to
get the output in valid json format.
---------
Change-Id: I5576333269509f63b3c800f225c3d73127ce80cf
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 8e5f6b1a8d]
Added power cap to display on amd-smi monitor -p.
Updated help and Changelog as well.
Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 7d109001ac]
Earlier amd-smi monitor was showing VRAM usage as used and total.
Modified it to display free VRAM and VRAM percentage. Updated
Changelog.
Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 3ddfbcc0a3]
* [SWDEV-513807] Fix amd-smi partition --accelerator not returning AMDSMI_STATUS_NO_PERM
Changes:
- Fixed amdsmi_get_gpu_accelerator_partition_profile_config() from not
returning AMDSMI_STATUS_NO_PERM
- Changed amd-smi partition --accelerator to provide user with a warning
if users does not use sudo or root permissions.
- Updated changelog for fixes planned for 6.4.1 release
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 0402bb4d75]
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]
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]
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]
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]
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]
Change copyrights to MIT and remove date
Signed-off-by: Joe Narlo <Joseph.Narlo@amd.com>
Change-Id: I16f5b412f2b9ddefaaa1771aa714cc18829a1be4
[ROCm/amdsmi commit: 3052ad4220]
new command includes following arguments:
- current - display the current partition information for the selected
gpu(s)
- memory - display memory partition information for the selected
gpu(s)
- accelerator - display accelerator partition information for the
selected gpu(s)
additional functionality will be added as more partition APIs are added.
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ica86160139002ef5213d6d4b0e390670aeef01c8
[ROCm/amdsmi commit: 4e2fc2d604]
Revert submission 1125402
Reason for revert: Packaging a tar archive of 3rd party sources
Reverted Changes:
I8908451c0:[SWDEV-482058] Updated Packaging for offline insta...
I764c8bf01:[SWDEV-469278] Lowered PyYAML post install script ...
Change-Id: I3886b5370e352fc33a249c4657d7ed0c1ee75baf
[ROCm/amdsmi commit: 6beec5f3ec]
Revert submission 1125402
Reason for revert: Packaging a tar archive of 3rd party sources
Reverted Changes:
I8908451c0:[SWDEV-482058] Updated Packaging for offline insta...
I764c8bf01:[SWDEV-469278] Lowered PyYAML post install script ...
Change-Id: Ib32fa5b9351b1cfc2a8d453e744c0d00209359eb
[ROCm/amdsmi commit: 9924574cbe]
adapryor
Bindhiya Kanangot Balakrishnan
gabrpham_amdeng
Maisam Arif
Poag, Charis
Scaffidi, Salvatore
Juan Castillo
Justin Williams
Joe Narlo
Dmitrii Galantsev