updated Nvidia is developing a new inventory management service that could be used by customers to verify the location of their existing GPU stockpiles.

The existence of the service, which has yet to be officially announced, was first reported on by Reuters on Wednesday. However, location verification isn’t the platform’s intended purpose but rather a secondary benefit, and customers would need to opt in to use it, El Reg has since learned.

Instead, the software platform, which would be offered by Nvidia as a managed service, is designed to provide streaming telemetry on the health of customers’ GPU fleets in order to minimize failures and maximize uptime.

The mechanism for verifying the location of the accelerators isn’t particularly sophisticated. From what we understand, it’s essentially the equivalent of running a ping and comparing the response time to a lookup table to see whether it’s within the expected range. 

This kind of infrastructure monitoring and management service isn’t uncommon in modern datacenters. For example, this class of software might use telemetry to identify a failing component and flag the system or contain it for replacement.

Nvidia already provides some of this functionality through its Datacenter GPU management suite. It’s also important to note that the offering wouldn’t rely on baking new functionality into its GPUs. Instead, it would rely on existing security functionality present in GPUs going back to the Hopper generation.

Nvidia has previously denied allegations of backdoors, kill switches, or spyware in its chips and services raised by Chinese authorities. 

In a statement following publication, an Nvidia spokesperson reiterated these points. “There is no feature within Nvidia GPUs that allow Nvidia or a remote actor to disable the Nvidia GPU. There is no kill switch. For GPU health there are no features that allow Nvidia to remotely control or take action on registered systems. It is read -nly telemetry sent to Nvidia.”

We’re told development of the new Nvidia inventory platform was driven by demand from customers for a managed

 » …
Read More