Fast Crown Scheduling Heuristics for Energy-Efficient Mapping and Scaling of Moldable Streaming Tasks on Many-Core Systems

Exploiting effectively massively parallel architectures is a major challenge that stream programming can help to face. We investigate the problem of generating energy-optimal code for a collection of streaming tasks that include parallelizable or moldable tasks on a generic manycore processor with dynamic discrete frequency scaling. In this paper we consider crown scheduling, a novel technique for the combined optimization of resource allocation, mapping and discrete voltage/frequency scaling for moldable streaming task collections in order to optimize energy efficiency given a throughput constraint. We present optimal off-line algorithms for separate and integrated crown scheduling based on integer linear programming (ILP) and heuristics able to compute solution faster and for bigger problems. We make no restricting assumption about speedup behavior. Our experimental evaluation of the ILP models for a generic manycore architecture shows that at least for small and medium sized streaming task collections even the integrated variant of crown scheduling can be solved to optimality by a state-of-the-art ILP solver within a few seconds. Our heuristics produce makespan and energy consumption close to optimality within the limits of the phase-separated crown scheduling technique and the crown structure. Their optimization time is longer than the one of other algorithms we test, but our heuristics consistently produce better solutions. This is an extended abstract of Melot et al., ACM Trans. Arch. Code Opt. 11(4) 2015.