Evolvable systems on reconfigurable architecture via self-aware adaptive applications

Self-adaptive applications are capable of changing their behavior thousands of times per second to autonomically find a way to accomplish given goals despite working in an unpredictable environment whose conditions can vary continuously. In this work we propose an evolvable system that runs self-adaptive applications on top of a heterogeneous system consisting of a general purpose processor and a reconfigurable device. Self-adaptive techniques enable an effective runtime exploration of a rich design space at the intersection of hardware and software and prove how their adoption can improve applications´ ability to meet given performance goals. The operating system running on top of the heterogeneous system is responsible for providing self-adaptive capabilities. It answers applications´ requests for functionality by choosing at runtime the best suiting implementation with respect to the given constraints and the environment. We designed and developed an evolvable system exploiting self-adaptive techniques by running a customized version of GNU/Linux and a set of self-adaptive applications on top of a heterogeneous system featuring a multi-core processor, i.e., an Intel Core i7, and a reconfigurable device, i.e., a Xilinx Virtex-5 FPGA-based board.