Exploring the design space of IMA system architectures

In systems such as integrated modular avionics (IMA), there is a substantial benefit from maintaining significant portions of a product family's architecture unchanged from one system to the next. When there are tight constraints on resources such as bandwidth and processor capacity, however, certain seemingly small changes in a few components have the potential to create a cascade of timing problems. The ability to rapidly analyze and quantify the impact of these changes prior to implementation and system integration provides the engineering team with early validation of the changes, which can prevent substantially increased costs for design, integration, and verification, as well as delays in the development schedule. However, detailed early evaluation of architecture performance involves analysis of many complex interrelated variables and is therefore challenging. Consider the case of moving a task from a processor's IMA partition to another processor's partition. The tasks sets need to be updated. The I/O and network traffic must be rerouted. The schedulability equations of processor, I/O and network need to be recreated, and the analysis needs to be propagated end to end. Last but not least, all the architecture specification documents have to be updated. In order to reduce the detailed architecture evaluation effort, we have automated the performance analysis process with a system integration tool prototype called ASIIST (Application-Specific I/O Integration Support Tool). To move a task, we can now use a graphical interface to drag and drop a task from one processor's IMA partition to another. All the steps described above are done automatically, including the updating of the architecture specification in AADL (Architecture Analysis and Description Language). In this paper, we show how to use this tool to explore the design space of an IMA system architecture, so as to derive designs with specified performance properties.