08-17-2017, 12:17 AM
Power consumption, physical size, and architecture design of sensor node processors have been the focus of sensor network research in the architecture community. What lies at the foundation for these research is the hardware- level design which determines the boundaries for achievable utility and performance. Architecture design and evaluation, however, cannot be accomplished independent of the applications and software that run on these sensor nodes. On one hand, some researchers have proposed architectures that can cater to a variety of application classes while trading off on some performance improvements. On the other hand, a set of application-specific architectures have been proposed which perform certain operations extremely well but are not versatile enough to run a variety of applications. This paper provides a design space exploration and optimizations platform to characterize the processor and ISA design tailored for a particular application or a class of applications. We collect a wide variety of sensor network applications to create a comprehensive benchmark suite called the WiSeNBench. We then present a careful profiling of these benchmark applications using an ARM simulator to identify some of the key characteristic behaviors. This also opens up avenue for a possible re-look at the classes of applications that could be supported on next-generation sensor networks and efficient architectural designs to enable these applications.