Card Thermal and Electrical Protections

Built-in shutdown logic protects the card from damage by removing power to the device when either electrical or thermal limits (given in the following table) reach or exceed their respective card shutdown thresholds. Thermal management is implemented in the RPU which monitors the external inlet, outlet, and FPGA temperature sensors while the voltage regulator module (VRM) monitors the VCCINT current and temperature. When any of the thresholds are exceeded, card power is removed. A cold reboot of the server hosting the card is subsequently necessary to reload the device configuration and re-enumerate the card in the server.

Note: When card shutdown occurs, the card is pulled off the PCIe bus and consequently is not seen by the host. No AXI firewall trip is issued. A cold reboot of the server is required to recover.

The following table lists the card shutdown thermal and electrical thresholds. The thresholds apply equally with and without AUX power connected.

Table 1. Thermal and Electrical Protection Thresholds
Sensor Description	Card Shutdown Threshold
VCCINT Current	60A (no PCIe AUX power) 180A (2x3 PCIe AUX power)
VCCINT Temperature	125°C
FPGA Temperature	100°C

Card Thermal and Electrical Protections - DS1014

Alveo U45N Data Center Accelerator Card Data Sheet (DS1014)