01646nas a2200145 4500008004100000245006300041210006300104260001000167300001200177520120600189100002001395700002301415700001901438856004301457 2011 eng d00aModeling of Data Adaptable Reconfigurable Embedded Systems0 aModeling of Data Adaptable Reconfigurable Embedded Systems cApril a276-2853 a
Many applications require high flexibility, high configurability and high processing speeds. The physical constraints of a highly flexible system’s hardware implementation preclude a hardware solution that satisfies all configuration options. Similarly for pure software implementations, even if configurability is satisfied, process efficiency will be sacrificed. Thus for applications of any significant size, there can be no single hardware or software configuration that can efficiently support all the configurability options of the applications. The Data-Adaptable Reconfigurable Embedded System (DARES) approach tackles this problem through combination of the hardware-software co-design and reconfigurable computing methodologies. Data-adaptability means that as data streams change, the system is reconfigured along the baselines defined within the system’s specifications. In this project we use the concepts of Model-Integrated Computing to implement a domain-specific modeling language for the DARES approach. The language captures all the configurability options of the application task(s), performs design-space exploration, and provides a template for source code generation.
1 aGopinath, Vijay1 aSprinkle, Jonathan1 aLysecky, Roman uhttp://dx.doi.org/10.1109/ECBS.2011.31