[$] A parallel path for GPU restore in CRIU

The fundamental concept of checkpoint/restore is elegant: capture aprocess's state and resurrect it later, perhaps elsewhere. Checkpointingmeticulously records a process's memory, open files, CPU state, and more into asnapshot. Restoration then reconstructs the process from this state. Thisestablished technique faces new challenges with GPU-accelerated applications,where low-latency restoration is crucial forfaulttolerance, live migration, andfast startups. Recently, the restore process for AMD GPUs has been redesigned toeliminate substantial bottlenecks.