Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Graphics Processing Units, Parallel Processing, Real-time, Scheduling, Time Division Multiplexing |
Field | DocType | ISSN |
Middleware,Kernel (linear algebra),Graphics,Computer vision,Scheduling (computing),Computer science,Server,Image processing,Artificial intelligence,Time-division multiplexing,Matrix multiplication,Embedded system | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vladislav Golyanik | 1 | 22 | 12.55 |
Mitra Nasri | 2 | 67 | 10.09 |
Didier Stricker | 3 | 1266 | 138.03 |