A distributed real-time programming model is presented. It consists of a set of tasks whose segments require processor time and devices, and which is run on a dedicated network of microcomputers. A task is started upon receipt of an external signal or the completion of other tasks. Segments communicate via message passing, and there may be a limited number of transient communication errors. A heuristic algorithm is developed to determine an upper bound on the response time of each task. This algorithm is useful in a hard-real-time environment for determining if response times will always be met.

Resource sharing problems can be described in three basically independent modular components. • The constraints the resource places upon sharing because of physcal limitations and consistency requirements. • The desired ordering of resource requests to achieve efficiency-either efficiency of resource utilization or efficiency of processes making the requests. • Modifications to the ordering to prevent starvation of processes waiting for requests which might otherwise never receive service. A high-level nonprocedural language to specify these components of resource sharing problems is described. General deadlock and starvation properties of selectors are proven. Solutions to several classic resource sharing problems are shown to illustrate the expressiveness of this language. Proof techniques for this high-level language are introduced to show how to prove particular selectors are or are not deadlock and starvation free.

This paper describes a scheduling algorithm for a set of tasks that guarantees the time within which a task, once started, will complete. A task is started upon receipt of an external signal or the completion of other tasks. Each task has a rxed set of requirements in processor time, resources, and device operations needed for completion of its various segments. A worst case analysis of task performance is carried out. An algorithm is developed for determining the response times that can be guaranteed for a set of tasks. Operating system overhead is also accounted for.

A simulator is presented that allows a student to quickly write a demand paging memory management system. The simulator provides a job stream, support routines (such as read a page into memory), extensive error checking and debugging, and performance evaluation.