Updated changelog to provide options to users on how to fix.
Change-Id: I4fd04b1e65ff9d678b2d13109599f57a03c84d41
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: b911a0606a]
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]
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]
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]
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]
Change struct to a typedef struct
Signed-off-by: Joe Narlo <Joseph.Narlo@amd.com>
Change-Id: I6f3b22a5219c0db0aab2c308b71213ae75334476
[ROCm/amdsmi commit: 547db10384]
The FRU_ID was truncated because the string copied from sysfs
was limited to 32 characters. This limit has been increased to
AMDSMI_MAX_STRING_LENGTH to accommodate longer FRU_IDs. Also
updated the deprecated string length macros.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Change-Id: I8becaf9f37609b2e5aecdf92b6ae60f4419ad8ef
[ROCm/amdsmi commit: bc77330a74]
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]
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]
Change copyrights to MIT and remove date
Signed-off-by: Joe Narlo <Joseph.Narlo@amd.com>
Change-Id: I16f5b412f2b9ddefaaa1771aa714cc18829a1be4
[ROCm/amdsmi commit: 3052ad4220]
This reverts commit a33cdd7da6.
Reason for revert: Because the gtest of amdsmi is different to other components so it was installed in a share/amdsmi/lib folder. It cannot be installed in a common folder such as /usr/local/bin or /usr/bin because all other components try to search those folder first.
This is breaking ROCmValidationSuite and other tools. Per Wang, Yanyao this should be reverted.
Change-Id: Id61bc6056fe41800e738616f39293e9b8762a377
[ROCm/amdsmi commit: b7789d4699]
black format docs/conf.py
add seealso to python api reference
Change-Id: I60fa754f0af662669282dc90eea4b7dc5c5030cc
Signed-off-by: Peter Park <peter.park@amd.com>
[ROCm/amdsmi commit: cbfe403b1d]
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]
* amdsmi_get_gpu_pm_metrics_info and amdsmi_get_gpu_reg_table_info
were added to python api documentation
* AmdSmiRegType added as enum
* amdsmi_get_gpu_reg_table_info reg_type changed to AmdSmiRegType
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I57239ecf048e82226151db071e8d9299e9182647
[ROCm/amdsmi commit: 4d26db84ca]
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]
Move memory_caps defintion and correct the number in reserved to match Confluence
Signed-off-by: Joe Narlo <Joseph.Narlo@amd.com>
Change-Id: Id94144f4b3d2d3d7b4d7327211ffc1957ffd0a93
[ROCm/amdsmi commit: 54462ab447]
Changes:
- Corrected max speed users can sample from FW/driver
is 100 ms
- Added warning to amdsmi_get_violation_status()
call on delay required 100ms to sample
- Removed guest support, this API will not be supported
- Updated CLI `amd-smi metric --throttle` outputs from
XXX_active -> XXX_status
XXX_percent -> XXX_activity
to align with host
- Changelog updated
Change-Id: Ib30dd35dcc04ff67904ca82c86a55a16689df226
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 0ceca28f41]
TEST FAILURE message for `amdsmi_get_gpu_cpi_throughput` and
`amdsmi_get_gpu_pci_bandwidth` changed to WARNING to indicate that
pcie_bw and/or pp_dpm_pcie sysfs files may not be supported on respetive
devices.
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: I1ad6e15eceacb5a00b022458ee5fb21df9d845c7
[ROCm/amdsmi commit: 00b3184e9f]
The reset gpu partition support for both compute and memory were removed
Code changes related to the following:
* amdsmi_reset_gpu_compute_partition()
* amdsmi_reset_gpu_memory_partition()
* CLI
Change-Id: I372589074b4da172bedd39223edde18939e373ae
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/amdsmi commit: f5b7761ac7]
Implements DiscoverIOLinkPerNodeDirection() based on KFD Node infrastructure;
'/kfd/topology/nodes/*/io_links'
Code changes related to the following:
* Internal implementation
Change-Id: Iccd84d1d69234dbeae4d4925f657e7e3bd801106
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
[ROCm/amdsmi commit: 25bcf6af2a]
Charis Poag
Maisam Arif
Bindhiya Kanangot Balakrishnan
gabrpham
Justin Williams
Joe Narlo
Adam Pryor
Peter Park
Jorge López
Oliveira, Daniel