Evaluating the Energy Efficiency of Reconfigurable Computing Toward Heterogeneous Multi-Core Computing

Abstract

Future exascale systems need to have a much better performance-to-power ratio than today’s systems. Accelerators are a promising approach to pave this path by more energy-efficient computing. We show some early results of our investigations toward energy efficiency of reconfigurable and heterogeneous computing against multi-core processors for special applications. The results are supported by a general framework and toolchain for early evaluation of potential benefits of reconfigurable hardware. As a result, heterogeneous systems based on reconfigurable hardware, efficient data exchange mechanisms, data-driven and component-based programming, and task-parallel execution can help achieve power-efficient exascale systems in future.