Network-on-chip-based heterogeneous multiprocessor system-on-a chip (NoC-HMPSoC) a single board computer is extensively utilized in many real-time applications such as mobile edge computing (MEC), cyber-physical systems, smart phones, driverless vehicles, and real-time embedded systems due to its flexible communication architecture, switching network, excellent performance, and energy efficiency. Despite its benefits, task scheduling and appropriate resource allocation is still an non-polynomial hard problem. NoC-HMPSoC includes heterogeneous processors along with interconnected communication routing structure which creates more complexity in task and resource scheduling. In this paper, a new task classification and low-complex resource mapping heuristics are developed to deal with mixed-critical workloads execution targeted on NoC-HMPSoC architecture. MethodologyTo minimize runtime scheduling cost, the deadline-based task classification (DBTC) heuristic divides the workload into three distinct classes depending on their deadline and inter-arrival limitations. The mixed-integer linear programming (MILP) statistical model, which improved task miss ratio with greater time complexity, is used to schedule the categorized task sets. Static resource mapping (SRM) and load-based dynamic resource mapping (LBDRM) heuristics are created to allocate mixed-critical activities into NoC-HMPSoC in order to overcome this. The suggested framework is a list-based scheduler that processes tasks on an unchanging processor using the SRM algorithm and prioritizes them depending on the tasks' earliest finish times. The LBDRM technique is then used to dynamically reallocate mixed-critical task groups among heterogeneous processors based on the load factor and task utilization factor. The time complexity of DBTC algorithm is O(log n) where 'n' is the task nodes, and the time complexity of the proposed scheduling heuristics are O(n2 * m) for larger graphs. The proposed framework performs classification, mapping, and scheduling in an integrated manner that is experimentally evaluated on the Samsung Exynos 5422 NoC-HMPSoC and Intel Xeon cloud server for E3S sysmark mobile benchmark workloads. Averagely 65%, 33%, is improved in execution time reduction and 45%, 36% reduction in energy consumption and 56%, 32% than JRFS-HRFS and ARSH-FATI methods.
Read full abstract