Towards Scheduling Hard Real-Time Image Processing Tasks on a Single GPU

Vladislav Golyanik, Mitra Nasri, Didier Stricker

In: International Conference on Image Processing. IEEE International Conference on Image Processing (ICIP-17) September 17-20 Beijing China online 9/2017.


Graphics Processing Units (GPU) are becoming the key hardware accelerators in the emerging image processing applications such as self-driving cars and mobile augmented reality systems. As GPUs execute launched workloads non-preemptively, their usage in safety-critical systems with hard real-time constraints is impeded. The existing solutions for scheduling real-time tasks on a single GPU focus on soft real-time systems. In this paper, we consider real-time systems with a single dedicated GPU handling sporadic tasks with hard deadlines and propose a scheduling approach based on time division multiplexing called the GPU-TDMh — a lightweight middleware framework located between the application and the GPU driver layers. We evaluate the proposed approach on a matrix multiplication benchmark on a heterogeneous platform. The experiments demonstrate the effectiveness of our method as well as superiority over the non-preemptive online scheduling policies.


GPU-TDMh.pdf (pdf, 668 KB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz