Towards resource sharing under multiprocessor semi-partitioned scheduling

Integrating independently developed real-time applications on a shared multi-core architecture

“…Inspired by our previous work on supporting resource sharing under semi-partitioned scheduling [23,24], and based on the subsystem abstraction presented in [1], we propose a new approach to abstract independently-developed applications running on a multicore platform where the applications are potentially requiring more than one core to be schedulable.…”

“…The reason of selecting the highest priority task to be split is that it has a great impact on the schedulability of all lower priority tasks within the systems. As it can be seen in Figure 3, τ i is the task that is split on P k and P r such that τ 1 i fills the capacity of P k up to the allowed limit and τ 2 i , which has the remainder execution of τ i , is located on P r , [23,24].…”

“…However, we want to prevent this case to keep the same analysis as the analysis of the partitioned scheduling presented in this paper to find applications interfaces. This is done by letting the split tasks to overrun until they release the global resource then they are allowed to migrate to the next core [23,24]. The overrun part should be considered in Equation 13.…”

A Correlation Framework for different Resource Access Protocol in Real Time System

“…Second, Sporadic task, recurs at random instants and third one is Aperiodic task, it is similar to the sporadic task. A whole system resource is divided into two types: Processors and Resources [2,7]. Computers, Database servers are example of processor.…”

“…A job may need some resources through the processor during make progress. Each job is characterized by its parameters like, execution time, response time, release time, deadline [2]. Execution time is defined as how long the time it takes to run the given task.…”