For ASICs NAVI10 and above setting display clock [DCEFCLK] is not supported and the sysfs entry is
read-only. As a result, the test falsely fails for these ASICs. ROCm SMI Lib is ASIC independent.
So Display clock set cannot be selectively disabled for these ASICs.
As a compromise if the set (write to sysfs entry) fails due to permission error and euid is root,
assume that set feature is not supported and skip the test.
Change-Id: I7a273878cbf1465b01728705323e8a92a42378dd
[ROCm/amdsmi commit: c6f695f5a9]
Implement default GPU power cap functionality in rsmitst.
It is available in the "rsmitstReadOnly.TestPowerRead" test, and
is displayed as: "Default Power Cap: #uW" (where uW is microwatts).
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: I564ea3785f1a93dfd30587634057516549fa762c
[ROCm/amdsmi commit: 5b42cdf780]
The rsmi_dev_temp_metric_get() can also support the HBM
temperatures which is retrieved from gpu_metrics.
Change-Id: I96b979296e90cf881523627b41b1a02849676416
[ROCm/amdsmi commit: da480b4589]
static-libasan doesn't exist, so use the easier-to-remember
shared-libsan and change static-libasan to static-libsan
Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: Ieef480aacdd770f3bb40673a2e8f8306b308b1c9
[ROCm/amdsmi commit: ef7f99a7e2]
Enums referenced in the test did not match what's in rocm_smi.h.
Added static assert to try to catch this. Also moved enum string
map to test_common.cc/h where other such maps are.
Also, fixed some cpplint issues.
Change-Id: I683553248ceb2fabb28ce1a1208bc9744aaf88d6
[ROCm/amdsmi commit: 7e17684532]
Previously, when a process holding a shared mutex was killed,
the next time an RSMI application was started, it would not be
able to obtain the mutex--the application would have to exit.
This fix uses pthread_mutexattr_setrobust() to detect this
situation and act accordingingly.
Also, add some missing, needed mutexes and move mutexes
closer to where the protect resource is used.
Change-Id: Icfdc3a246f4cfa3fd008e3f13472199abd76fd35
[ROCm/amdsmi commit: f4938b0ac9]
A special mode of operation to achieve minimal performance variation by letting
the user have the ability to provide the desired frequency to be set as the soft limit.
The user can control the entry and exit to the mode via rocm-smi a mechanism to
enter / exit performance determinism mode as below.
Enter performance determinism mode:
- hold a lock
- write performance_determinism to power_dpm_force_performance_level
- write input clk_freq to pp_dpm_sclk
- release lock
Exit performance determinism_mode:
- hold a lock
- write auto to power_dpm_force_performance_level
- release lock
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: Ia24e27954cdf1c4337ffc83d8948fbdfaf4552d2
[ROCm/amdsmi commit: 60d0f3052f]
Update the event notification tests to handle both GPU pre reset
and GPU post reset events. GPU post reset event takes sometime to
be generated after the pre reset event, so issue another
notification read to wait for post reset event.
Change-Id: I2812760b184d5357130e478cc35d27b14592abb3
[ROCm/amdsmi commit: 446ab5c8c7]
This reverts commit dc48f149f0.
Temporarily reverting until the driver side of this is upstream
Change-Id: I2d8243208c1271ebad90bc2ee0fda2dfefb0831b
[ROCm/amdsmi commit: ae6d3fbdd0]
Add handling for both pre GPU reset and post GPU reset SMI
events.
Change-Id: I64d5e006bef58cb28b1c580c75f482a4590427da
[ROCm/amdsmi commit: 8b95705e6f]
Add handling for receiving thermal throttling SMI event from the
kernel.
Also, update the event notification test to work with the new event.
Change-Id: Ib89c12b244f90998ccbae0a38b37f25705d156e0
[ROCm/amdsmi commit: aff75c955f]
Event bitmask in KFD SMI event is now replaced with event index in
the SMI event message. Sending a event bitmask, which was a 64-bit
field with only 1 bit set, was quite wasteful of memory and also
potentially limiting to 64 events. Instead the kernel would send
event index in the SMI event message. As a result, update the
KFD SMI event handling to expect the event index in the message.
Change-Id: I3e74620788d3c1f7c0bdaa69e9d9ab3d1aba2c92
[ROCm/amdsmi commit: 406859ca8a]
Use unsigned number for left shift operation. If not specificed as
unsigned, compiler throws warning about left shift of negative
number.
Change-Id: I05948073b0c40700bee69399b08df6031fc49d70
[ROCm/amdsmi commit: 9d24fc9175]
Some systems have kfd sysfs properties entries that
are unreadable--for example, when a multi-gpu system is
dividing the gpus among containers, each container may
only be able to access certain gpus.
Previously, all kfd topology node properties entries were
assumed to be valid. Now, we check for readability before
declaring them "valid".
Fixes SWDEV-240169
Also:
* remove an assertion that would happen when no pcie
device identifier files are found on the system.
* fix cpplint issues
Change-Id: I74321b685159dd2628c890b33c39ad82988cb9dd
[ROCm/amdsmi commit: 68155baed5]
Also, fix TestMutualExclusion and TestEvtNofifReadWrite.
Previously, some of the normal SetUp function was not
being done for this test. In some cases, no DRM
devices are being found on the test machine. Skip
those.
Change-Id: Iaa5a257841eb459aa57491ae9680c34a60d5ac2b
[ROCm/amdsmi commit: 59394f3354]
Also, support --iterations flag for certain functions that will
likely be repeated frequently.
Change-Id: I7ed76835001b5cbca30042d6bf26484258c7b9a6
[ROCm/amdsmi commit: efc9b7658c]
Also:
* When destroying a counter, make sure to stop the counter first
* In the test, do not stop (disable) the counter before
reading it.
* Clean up some whitespace in other tests
* Re-add manual pdf file
Change-Id: I0786ef3a994ca568299c77e44f092af8943ac33d
[ROCm/amdsmi commit: f946ea37ef]
This isn't supported on all models, so just comment out on failure
instead of fully failing
Change-Id: Id36d5df7c87abbb41f7b6be43abfea82004703a6
[ROCm/amdsmi commit: 8cf44548c0]
When getting process information for a process, it's possible
that between the time the process ID was discovered and when
we attempt to collect data for that process, that the process
ended. This change is meant to handle that in the test case.
* Also, fix compile warning by removing unused variable.
Change-Id: I62f9a84a63548c856f0661fef15b7d248a330c05
[ROCm/amdsmi commit: 1c9ef44398]
* Added a new test to verify mutual exclusion of access to device
resources
* Added some missing acquiring of mutexes to some RSMI calls, as
well as try-catch blocks.
Change-Id: I87aac009878a0b2d1f975e1d5b794d887bb23ff9
[ROCm/amdsmi commit: f8b57c3b16]
Given a device index, return the corresponding NUMA node for the
device.
Also, add NUMA node tests to Sys Info Read test.
Change-Id: I0df4937470e6362e6737ccea568d4b3e5890c91a
[ROCm/amdsmi commit: fd79e5c161]
Sreekant Somasekharan
Divya Shikre
Bill(Shuzhou) Liu
Ori Messinger
Harish Kasiviswanathan
Chris Freehill
Kent Russell
Mukul Joshi
Ramesh Errabolu
Mike Li