Summary
Overview
This filing enables scheduler-driven suspend and resume of GPU workloads without requiring application-level checkpoint logic.
Abstract
Technical Abstract
The system identifies safe points, snapshots device memory and reconstruction metadata, releases GPU resources for higher-priority work, and later restores the workload deterministically. Scheduler-visible telemetry such as snapshot size and restore latency supports policy decisions in responsive GPU clusters.
Search Context
SEO Keywords
GPU preemption patent, suspend resume patent, context quiescence patent, GPU scheduler patent, transparent checkpoint patent
Related Patents
More Patents in accelerator architecture, compiler control, and cluster systems
These filings sit nearby in the portfolio and strengthen internal linking across related patent topics.