* Changes:
- Updates to DRM renderD* / card* pathing for partition devices
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated several ROCm SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Added a new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
Change-Id: If844f27ffc595942272abe9c8167ed90a0b0e225
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
rocm-smi is not working in mGPU, Blocking DLM tests
Updates include:
- Creating check_runtime_status function to check for device status of active.
- Added warning to users that No AMD GPUs are available, check power status/control.
- Added check for empty string coming from HWMON, if emtpy returns unexpected data.
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
* SWDEV-518214: GPU Metrics 1.8 (#31)
- Updates:
- Adding the following metrics to allow new calculations for violation status:
- Per XCP metrics gfx_below_host_limit_ppt_acc
- Per XCP metrics gfx_below_host_limit_thm_acc
- Per XCP metrics gfx_low_utilization_acc
- Per XCP metrics gfx_below_host_limit_total_acc
- Increasing available JPEG engines to 40. Current ASICs may not support all 40. These will be indicated as UINT16_MAX or N/A in CLI.
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Co-authored-by: Charis Poag <Charis.Poag@amd.com>
Memory partition test was changing original compute partiton based
on default compute mode. Corrected this to set back to original
compute partition.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Guest: Tests needed to account for not supporting changing compute
partitions.
BM: Tests need to account for invalid responses from Driver (due to
static CPX config).
Changes: - Fixed Device Name (market name)
- Added new API rsmi_dev_market_name_get()
- Updated tests
- Updated amdgpu_drm.h to match latest mainline kernel
- Fixed subsystem ID to only show hex value (not subsystem name)
- rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).
2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```
3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```
4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```
Closes#210.
Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
- Fixes the broken links in rocm_smi.h
- Uses automodule instead of autofunction in docs/reference/python_api.rst
- Fixes some warnings during docs build
- Update some of the versions in requirements.txt
The target_graphics_version was not formatted properly and was
showing incorrect Target Name. Corrected this by fomatting
major, minor and revision numbers.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
- To address https://github.com/ROCm/rocm_smi_lib/issues/208
where use of fake BDFs for partitions can cause confusion. This note
is already in the comments of the function definition, but was not
updated in the function declaration.
- Fix broken formatting for the location table for PCIE coordinate fields
- Tracked in SWDEV-501108
Change-Id: Ic85439866cb836bb43acc52314a7f1d026c3215d
Changes:
- Added new GPU metrics:
1) XGMI link status - Up/Down; 1 = up; 0 = down
2) Graphics clocks below host limit (per XCP)
accumulators -> used to help calculate a violation status
3) VRAM max bandwidth at max memory clock
- Updated rocm-smi --showmetrics to include new metrics.
Units/values reflect as indicated by driver, may differ
from AMD SMI or other ROCm SMI interfaces which
use these fields.
- N/A fields means the device does not support providing this
data.
Change-Id: I17b313345f15070a76b3a30dd8d5645d212d601b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Guest: Tests needed to account for not supporting changing compute
partitions.
BM: Tests need to account for invalid responses from Driver (due to
static CPX config).
Change-Id: I09ccee981c6b73684b64e5053068920a6c1b6439
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
* Revert - this reverts commit a73e47591c7ea0ed5a7fc217211872d74be64206.
* Revert "[SWDEV-514998/SWDEV-511662] Fix tests for Guest and BM with static CPX config"
This reverts commit 5a71fd9d75d4d6a9bdd7fa3e652eeb12336a1d6a.
Memory partition test was changing original compute partiton based
on default compute mode. Corrected this to set back to original
compute partition.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Guest: Tests needed to account for not supporting changing compute
partitions.
BM: Tests need to account for invalid responses from Driver (due to
static CPX config).
Changes: - Fixed Device Name (market name)
- Added new API rsmi_dev_market_name_get()
- Updated tests
- Updated amdgpu_drm.h to match latest mainline kernel
- Fixed subsystem ID to only show hex value (not subsystem name)
- rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).
2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```
3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```
4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```
Closes#210.
Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
- Fixes the broken links in rocm_smi.h
- Uses automodule instead of autofunction in docs/reference/python_api.rst
- Fixes some warnings during docs build
- Update some of the versions in requirements.txt
The target_graphics_version was not formatted properly and was
showing incorrect Target Name. Corrected this by fomatting
major, minor and revision numbers.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
- To address https://github.com/ROCm/rocm_smi_lib/issues/208
where use of fake BDFs for partitions can cause confusion. This note
is already in the comments of the function definition, but was not
updated in the function declaration.
- Fix broken formatting for the location table for PCIE coordinate fields
- Tracked in SWDEV-501108
Change-Id: Ic85439866cb836bb43acc52314a7f1d026c3215d
Changes:
- Added new GPU metrics:
1) XGMI link status - Up/Down; 1 = up; 0 = down
2) Graphics clocks below host limit (per XCP)
accumulators -> used to help calculate a violation status
3) VRAM max bandwidth at max memory clock
- Updated rocm-smi --showmetrics to include new metrics.
Units/values reflect as indicated by driver, may differ
from AMD SMI or other ROCm SMI interfaces which
use these fields.
- N/A fields means the device does not support providing this
data.
Change-Id: I17b313345f15070a76b3a30dd8d5645d212d601b
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Changes:
* [API] Removed checking board name, fixes for other MI ASICs
* [CLI] Increased progress bar to change memory partition modes
to 140 seconds, since driver reload is variable per system
Change-Id: Ifcaf40d28b4adf5eaa800c9e3748d33749dc414a
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Charis Poag
Castillo, Juan
Mallya, Ameya Keshava
Arif, Maisam
Su, Daniel
Zhang, Ava
Kanangot Balakrishnan, Bindhiya
Galantsev, Dmitrii
Johar, Adel
James Xu
Choudhary, Rahul
gabrpham