Energy-aware application scheduling on a heterogeneous multi-core system

Abstract

Heterogeneous multi-core processors are attractive for power efficient computing because of their ability to meet varied resource requirements of diverse applications in a workload. However, one of the challenges of using a heterogeneous multi-core processor is to schedule different programs in a workload to matching cores that can deliver the most efficient program execution. This paper presents an energy-aware scheduling mechanism that employs fuzzy logic to calculate the suitability between programs and cores by analyzing important inherent program characteristics such as instruction dependency distance and branch transition rate. The obtained suitability is then used to guide the program scheduling in the heterogeneous multi-core system. The experimental results show that the proposed suitability-guided program scheduling mechanism achieves up to 15.0% average reduction in energy-delay product compared with that of the random scheduling approach. To the best of our knowledge, this study is the first to apply fuzzy logic to schedule programs in heterogeneous multi-core systems.