Minimizing Memory Utilization of Real-Time Task Sets in Single and Multi-Processor Systems-on-a-Chip

The research on real-time software systems hasproduced algorithms that allow to effectively schedulesystem resources while guaranteeing the deadlines ofthe application and to group tasks in a very shortnumber of non-preemptive sets which require muchless RAM memory for stack.Unfortunately, up tonow the research focus has been on time guaranteesrather than the optimization of RAM usage.Furthermore,these techniques do not apply to multiprocessor architectures whichare likely to be widely used in futuremicrocontrollers.This paper presents a fast and simple algorithmfor sharing resources in multiprocessor systems, to-gether with an innovative procedure for assigningpreemption thresholds to tasks.This allows toguarantee the schedulability of hard real-time tasksets while minimizing RAM usage.The experimentalpart shows the effectiveness of a simulatedannealing-based tool that allows to and a nearoptimal task allocation.When use d in conjunctionwith our preemption threshold assignment algorithm, our tool further reduces the RAM usage in multiprocessorsystems.