Efficient Scheduling of DAGs and Sets of Chains on a Simple Asymmetric Multicore Model

In this work we model multicore platforms as chip multiprocessors made up from two different types cores; each type of cores has different computation capabilities. In this simple asymmetric multicore model we study the problem of executing parallel programs that are represented as DAGs or chains of tasks. We assume 2 (essential) speeds in our proposed platform. We relax this assumption and consider many speeds in our energy considerations. This problem has been considered previously in the field of parallel computing and scheduling theory for the general case where multiprocessor platforms have $K$ distinct speeds. Our model is a bridge between the assumptions in these fields and recent advances in multicore processors technology. We provide a refined analysis of a recent scheduling method. Based on this analysis, we specialize the scheduling policy and provide an algorithm of $(3 o(1))$ expected approximation factor. Note that this improves the previous best factor (6 for two speeds).