nvidia-gpu: add dram temperature sensor
This commit introduces a dram temperature sensor for the GPU, enhancing
the existing temperature monitoring capabilities.
Tested: Build an image for gb200nvl-obmc machine with the following
patches cherry picked. This patches are needed to enable the mctp stack.
https://gerrit.openbmc.org/c/openbmc/openbmc/+/79422
```
$ curl -s -k -u 'root:0penBmc' https://10.137.203.137/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/temperature_NVIDIA_GB200_GPU_0_DRAM_0_TEMP_0
{
"@odata.id": "/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/temperature_NVIDIA_GB200_GPU_0_DRAM_0_TEMP_0",
"@odata.type": "#Sensor.v1_2_0.Sensor",
"Id": "temperature_NVIDIA_GB200_GPU_0_DRAM_0_TEMP_0",
"Name": "NVIDIA GB200 GPU 0 DRAM 0 TEMP 0",
"Reading": 30.0,
"ReadingRangeMax": 127.0,
"ReadingRangeMin": -128.0,
"ReadingType": "Temperature",
"ReadingUnits": "Cel",
"Status": {
"Health": "OK",
"State": "Enabled"
},
"Thresholds": {
"UpperCritical": {
"Reading": 95.0
}
}
}%
```
Change-Id: I914bb94f85e2d4163397b71a08b4ddd8b171e7d7
Signed-off-by: Harshit Aghera <haghera@nvidia.com>
diff --git a/src/nvidia-gpu/NvidiaGpuDevice.hpp b/src/nvidia-gpu/NvidiaGpuDevice.hpp
index 2c81287..5357121 100644
--- a/src/nvidia-gpu/NvidiaGpuDevice.hpp
+++ b/src/nvidia-gpu/NvidiaGpuDevice.hpp
@@ -61,6 +61,7 @@
std::shared_ptr<NvidiaGpuTempSensor> tempSensor;
std::shared_ptr<NvidiaGpuTempSensor> tLimitSensor;
+ std::shared_ptr<NvidiaGpuTempSensor> dramTempSensor;
std::shared_ptr<NvidiaGpuPowerSensor> powerSensor;
std::shared_ptr<NvidiaGpuEnergySensor> energySensor;
std::shared_ptr<NvidiaGpuVoltageSensor> voltageSensor;