Automatic error prediction in data centers
AssigneeNVIDIA Corporation
InventorsTamar Viclizki, Fay Wang, Divyansh Jain, Avighan Majumder, Vadim Gechman, Vibhor Agrawal
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to predict a probability of an error or anomay in processing units, such as those of a data center. In at least one embodiment, the probability of an error occuring in a proccessing unit is identified using multiple trained machine learning models, in which the trained machine learning models each outputs, for example, the probability of an error occuring within a different predetermined time period.
Claims20
A method comprising:
- obtaining, from one or more machine learning models and based on telemetry data corresponding to a device, a plurality of error predictions, wherein one or more of the plurality of error predictions comprises a probability of a type of potential error occurring within a unique future time period;
- identifying, based on the plurality of error predictions, at least one preventative action corresponding to the device;
- and
- performing the preventative action for the device in response to identifying the at least one preventative action.
A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:
- processing telemetry data for a device by a first machine learning model that outputs a first error prediction comprising a first probability of a first type of potential error occurring within a first future time period;
- processing the telemetry data for the device by a second machine learning model that outputs a second error prediction comprising a second probability of a second type of potential error occurring within a second future time period;
- identifying, based on the first error prediction and the second error predictions, at least one preventative action corresponding to the device;
- and
- performing the preventative action for the device in response to identifying the at least one preventative action.
A system comprising:
- a memory device;
- and
- a processing device coupled to the memory device, wherein the processing device is to perform operations comprising:
- receiving, by a plurality of machine learning models, telemetry data for a processor;
- process the telemetry data to generate a plurality of error predictions, wherein one or more error predictions of the plurality of error predictions comprises a probability of the processor experiencing a type of error within a unique future time period;
- and
- performing, based on the plurality of error predictions, a preventative action for the processor.
Dependencies are inferred from the claim text.