Fault detection in parallel hardware
AssigneeNVIDIA Corporation
InventorsSaurabh Hukerikar, Nirmal Saxena, Atieh Lotfi, Samuel H. Duncan, Yanxiang Huang, Jason Campbell, Paul Racunas
Life of this patent
Estimating the term…
Abstract
In various examples, faults are detected based at least in part on result value(s) generated by hardware component(s) by performing one or more diagnostic tests in accordance with a diagnostic test pattern. The diagnostic test pattern may be used to perform an assessment of functionality of the hardware component(s) by causing the hardware component(s) to generate the result value(s), which may be used to identify one or more hardware faults (e.g., by comparing the result value(s) to expected value(s)).
Claims20
A method comprising:
- causing one or more hardware components to generate at least one result value based at least on performing one or more diagnostic tests in accordance with at least one diagnostic test pattern;
- and
- using the at least one result value to detect one or more hardware faults associated with the one or more hardware components.
A system for use with one or more hardware components and at least one network, the system comprising:
- one or more processing units;
- and
- a network interface to connect the one or more processing units to the one or more hardware components over the at least one network, the one or more processing units to:
- communicate diagnostic information to the one or more hardware components, via the network interface, to cause the one or more hardware components to generate at least one result value based at least on performing one or more diagnostic tests in accordance with at least one diagnostic test pattern,
- receive, via the network interface, result information based at least in part on the at least one result value from the one or more hardware components, and
- use the result information to detect one or more hardware faults associated with the one or more hardware components.
A processor comprising:
- one or more processing units to perform operations comprising:
- causing one or more hardware components to generate at least one result value by performing one or more diagnostic tests in accordance with at least one diagnostic test pattern;
- and
- using the at least one result value to detect one or more hardware faults associated with the one or more hardware components.
Dependencies are inferred from the claim text.