GPUSync: A framework for real-time GPU management

This paper describes GPUSync, which is a framework for managing graphics processing units (GPUs) in multi-GPU multicore real-time systems. GPUSync was designed with flexibility, predictability, and parallelism in mind. Specif-ically, it can be applied under either static- or dynamic-priority CPU scheduling; can allocate CPUs/GPUs on a partitioned, clustered, or global basis; provides flexible mechanisms for allocating GPUs to tasks; enables task state to be migrated among different GPUs, with the potential of breaking such state into smaller “chunks”; provides migra-tion cost predictors that determine when migrations can be effective; enables a single GPU’s different engines to be ac-cessed in parallel; properly supports GPU-related interrupt and worker threads according to the sporadic task model, even when GPU drivers are closed-source; and provides budget policing to the extent possible, given that GPU ac-cess is non-preemptive. No prior real-time GPU manage-ment framework provides a comparable range of features.