- Updated VCLK and DCLK min/max clock logic to populate N/A values.
- Updated VCLK and DCLK to show all available clocks.
- Updated deep_sleep logic using sys/fs clk_deep_sleep true/false.
- Added clarifying comments.
- Updated error output using e.get_error_info() instead of just error.
- Updated changelog
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
[ROCm/amdsmi commit: e123e986f9]
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]
Changes:
- Removed libdrm/libdrm_amdgpu dependencies
- Added/updated new internal libdrm/libdrm_amdgpu/xf86drm APIs
to allow our APIs to reference before dynamic loading
the libdrm/libdrm_amdgpu libraries:
1. amdgpu_drm.h to what's seen in mainline
2. Added xf86drm.h to whats seen in mainline
- Modified internal DRM capabilities:
1. Require each API to independently connect to libdrm/libdrm_amdgpu
+ validate API handles reponses accordingly
2. Initialization of AMD SMI no longer has as strong of a tie to
libdrm
- Updated internal implementations of several APIs which have
connections to libdrm/libdrm_amdgpu or APIs which have conflicts
with open libdrm/libdrm_amdgpu connections:
1. amdsmi_init()
2. amdsmi_get_gpu_vram_usage()
3. amdsmi_get_gpu_asic_info()
4. amdsmi_get_gpu_vram_info()
5. amdsmi_get_gpu_vbios_info()
6. amdsmi_get_gpu_driver_info()
7. amdsmi_get_gpu_virtualization_mode()
8. amdsmi_set_gpu_memory_partition()
9. amdsmi_set_gpu_memory_partition_mode()
- Cleaned up effected tests/APIs
Change-Id: I96e2cf1b06b0cfee1b01a5e991ccc6116c4245a8
[ROCm/amdsmi commit: b5a43b7744]
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* use partition id and skip if non-zero
* reverting un-needed change
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* use partition id and skip if non-zero
---------
Co-authored-by: Oosman Saeed <oossaeed@amd.com>
[ROCm/amdsmi commit: 9c297639f3]
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]
* Small Fixes
* CLI Help text and parser formatting updates
* Changed metavar for set partition
---------
Change-Id: Ia8809665f6fac670452cd4db4e5e8f9c7270faba
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Pham, Gabriel <Gabriel.Pham@amd.com>
Co-authored-by: Pham, Gabriel <Gabriel.Pham@amd.com>
[ROCm/amdsmi commit: 53dbb7bf58]
* Reduced Load times for CLI in partition mode
* Change rsmi_dev_id_get() to use KFD, if KGD interface does not exist
* Make gpu_device_uuid fallback to rsmi_wrapper
* Moved Enumeration info calls in list for more speed
* Moved made group check excluded from recursion
---------
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
[ROCm/amdsmi commit: 63b13ecb05]
(#280)
- Fixed potential issue with min/max values when only one frequency is available
- Improve error handling in GPU frequency range detection
- Refactor clock frequency range detection for better readability
- Added special handling for current frequency indicator (*) in DPM output
- Added comments explaining special case handling for current frequency
- Cleaned up incorrect definitions in hsmp metric table definition
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 4d92dea079]
* Changes:
- Updates to DRM renderD* / card* pathing for partition
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated serveral AMD SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Tests are updated to handle not supported features
- Added new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
- Renamed device->get_card_id() & device->get_drm_render_minor()
These can now be used on internal AMD SMI calls.
- Removed warnings shown in build
Change-Id: Ice882fd9b97fb625a5bd4ef327f3ceaf247dc570
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 4782528770]
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]
When argparse parses multiple invalid arguments, the error
message displays only the last argument and this leads to
confusion. To avoid the scenario, added valid command check
before argparse and in case of invalid first command, added
new exception.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 3681f900ee]
* [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]
Added enumeration mapping for
- drm render
- drm card
- hsa id
- hip id
- hip uuid (rocminfo uuid)
Signed-off-by: AL Musaffar, Yazen <Yazen.ALMusaffar@amd.com>
Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
Co-authored-by: Maisam Arif <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 2936e00fed]
To execute set and reset commands, amd-smi needs sudo
privileges. Updated the subcommand help text to show
'sudo' requirement for these commands.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Co-authored-by: Arif, Maisam <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 2141e0336c]
Change Versioning Scheme to match https://semver.org/
Dropping the year enum and API fields in a future release.
Should not impact library versioning since we are now starting from 25.2.0
---------
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>
Co-authored-by: Arif, Maisam <Maisam.Arif@amd.com>
Change-Id: Id090e23f156926d08f9c0b781447388adf268cf6
[ROCm/amdsmi commit: d7c3ad0886]
Changed amdsmi_get_rocm_version() to be an API in the python library only.
Updated usage and version detection
Updated path detection of librocm-core.so
Updated docs to reflect both amdsmi_get_rocm_version and amdsmi_get_lib_version() do not require initialization.
Signed-off-by: Arif, Maisam <Maisam.Arif@amd.com>
[ROCm/amdsmi commit: 52b3ee2dc6]
Castillo, Juan
Arif, Maisam
Galantsev, Dmitrii
Bindhiya Kanangot Balakrishnan
Poag, Charis
Saeed, Oosman
Pham, Gabriel
AL Musaffar, Yazen
Pryor, Adam
Narlo, Joseph
Mewar, Deepak