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

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