Thermal Sensors

NVIDIA BlueField BF1600 InfiniBand/Ethernet Controller Card User Manual

The BlueField BF1600 Controller Card incorporates the BlueField SoC which operates in the range of temperatures between 0C and 120C.

There are three thermal threshold definitions for the BlueField SoC which impact the overall system operation state:

  • Warning – 105°C: On managed systems only: When the device crosses the 100°C threshold, a Warning Threshold message will be issued by the management SW, indicating to system administration that the Controller Card has crossed the Warning threshold. Note that this temperature threshold does not require nor lead to any action by hardware (such as BlueField Controller Card shutdown).

  • Critical – 120°C: When the device crosses this temperature, the firmware will automatically shut down the device.

  • Emergency – 130°C: In case the firmware fails to shut down the device upon crossing the Critical threshold, the device will auto-shutdown upon crossing the Emergency (130°C) threshold.

The BlueField thermal sensors can be read through the system’s SMBus. The user can read these thermal sensors and adapt the system airflow in accordance with the readouts and the needs of the above-mentioned SoC thermal requirements.

© Copyright 2023, NVIDIA. Last updated on May 22, 2023.