Near-optimal energy-efficient partial-duplication task mapping of real-time parallel applications

Minimizing energy consumption, as well as meeting real-time and reliability constraints, are major goals during system deployment. When complex platforms, such as multicore architectures with DVFS, and parallel applications are considered, these goals are significantly impacted by task mapping. To minimize energy consumption, while meeting real-time and reliability constraints, this work proposes a task mapping approach to jointly solve the problem of task allocation, task scheduling, frequency assignment, and task duplication. A novel heuristic algorithm is proposed to cope with this NP-hard problem, consisting of a pruning phase, which maintains only the task configurations that satisfy reliability constraints, and a mapping phase, which minimizes total energy consumption under real-time and precedence constraints. The obtained results show that the proposed heuristic obtains near-optimal results, with low computation time, compared to optimal solvers, while it achieves better energy consumption and finds slightly more solutions compared to other heuristic approaches.