Contention and Reliability-Aware Energy Efficiency Task Mapping on NoC-Based MPSoCs
Résumé
Recently, Network-on-Chip (NoC)-based Multi-Processor System-on-Chips (MPSoCs) have become popular computing platforms for real-time applications due to high communication performance and energy efficiency over traditional bus-based MPSoCs. Due to the nature of network structures, network congestion along with transient faults, can significantly affect communication efficiency and system reliability. Most existing works have rarely focused on the concurrent optimization of network contention, reliability, and energy consumption. Here, we study the problem of contention and reliability-aware task mapping under real-time constraints for dynamic voltage and frequency scaling-enabled NoC. The problem entails optimizing voltage/frequency on cores and links to reduce energy consumption and ensure system reliability, while task mapping and slack time are adopted to alleviate network contention and reduce latency. We aim to minimize computation and communication energy and balance workload. This problem is formulated as a mixed-integer nonlinear programming, and we present an effective linearization scheme that equivalently transforms it into a mixed-integer linear programming to find the optimal solution. To reduce computation time, we propose a three-step heuristic, including task allocation, frequency scaling and edge scheduling, and communication contention management. Finally, we perform extensive simulations to evaluate the proposed method. The results show we can achieve 31:6% and 21:7% energy savings, with 95:5% and 98:6% less contention than the existing methods.
Domaines
Systèmes embarquésOrigine | Fichiers produits par l'(les) auteur(s) |
---|