commit 775199d2599981d2c4460c7c1e91a607829e9f0c
author Harshit Aghera <haghera@nvidia.com> Tue May 27 14:20:24 2025 +0530
committer Ed Tanous <ed@tanous.net> Thu Jul 10 15:01:22 2025 +0000
tree df57e4f6a84ed5c663a072a553bdd970d7a0bed1
parent 902c649b631ada141ee5910f7ee2a45026d5b084

nvidia-gpu: add energy sensor

This commit introduces a energy sensor for the GPU.

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/energy_NVIDIA_GB200_GPU_0_Energy_0
{
  "@odata.id": "/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/energy_NVIDIA_GB200_GPU_0_Energy_0",
  "@odata.type": "#Sensor.v1_2_0.Sensor",
  "Id": "energy_NVIDIA_GB200_GPU_0_Energy_0",
  "Name": "NVIDIA GB200 GPU 0 Energy 0",
  "Reading": 269947.856,
  "ReadingRangeMax": 1.8446744073709552e+16,
  "ReadingRangeMin": 0.0,
  "ReadingType": "EnergyJoules",
  "ReadingUnits": "J",
  "Status": {
    "Health": "OK",
    "State": "Enabled"
  }
}%
```

Change-Id: I6f53ab2a83eedd54005bbdcd781dc8d320d7f26a
Signed-off-by: Harshit Aghera <haghera@nvidia.com>

src/nvidia-gpu/NvidiaGpuDevice.cpp

diff --git a/src/nvidia-gpu/NvidiaGpuDevice.cpp b/src/nvidia-gpu/NvidiaGpuDevice.cpp
index dc30788..082fbbe 100644
--- a/src/nvidia-gpu/NvidiaGpuDevice.cpp
+++ b/src/nvidia-gpu/NvidiaGpuDevice.cpp
@@ -14,6 +14,7 @@
 #include <bits/basic_string.h>
 
 #include <MctpRequester.hpp>
+#include <NvidiaGpuEnergySensor.hpp>
 #include <NvidiaGpuPowerSensor.hpp>
 #include <NvidiaGpuThresholds.hpp>
 #include <boost/asio/io_context.hpp>
@@ -61,6 +62,10 @@
         conn, mctpRequester, name + "_Power_0", path, eid, gpuPowerSensorId,
         objectServer, std::vector<thresholds::Threshold>{});
 
+    energySensor = std::make_shared<NvidiaGpuEnergySensor>(
+        conn, mctpRequester, name + "_Energy_0", path, eid, gpuEnergySensorId,
+        objectServer, std::vector<thresholds::Threshold>{});
+
     lg2::info("Added GPU {NAME} Sensors with chassis path: {PATH}.", "NAME",
               name, "PATH", path);
 
@@ -98,6 +103,7 @@
         tLimitSensor->update();
     }
     powerSensor->update();
+    energySensor->update();
 
     waitTimer.expires_after(std::chrono::milliseconds(sensorPollMs));
     waitTimer.async_wait([this](const boost::system::error_code& ec) {