GPU Operational Events (Preview)

Warning

GPU Operational Events are a preview feature and remain under active development. Category values, module signatures, module event codes, severities, context payloads, and the set of published events may change before the interface is declared stable. Treat the identifiers in this document as valid for the driver release documented here, and re-validate consumers against each driver release. Legacy Xid reporting remains supported for production monitoring during the preview period. See Release Notes for compatibility changes.

This document explains what GPU Operational Events are, how to monitor them, the formats they are published in, and the published event categories and codes. It is intended to assist system administrators, developers, and FAEs who consume structured GPU health and error data from the NVIDIA driver.

This edition documents R620. See Release Notes for changes from R615.

• Analyzing GPU Operational Events
• GPU Operational Event Formats
• GPU Operational Event Catalog
• Release Notes
• Notices