Parametric Design Synthesis of Distributed Embedded Systems

This paper presents a design synthesis method for distributed embedded systems In such systems computations can ow through long pipelines of interacting software components hosted on a variety of resources each of which is managed by a local scheduler Our method automatically calibrates the local resource schedulers to achieve the system s global end to end performance requirements A system is modeled as a set of distributed task chains or pipelines where each task represents an activity requiring nonzero load from some CPU or network resource Task load requirements can vary stochastically due to second order e ects like cache memory behavior DMA interference pipeline stalls bus arbitration delays transient head of line blocking etc We aggregate these e ects along with a task s per service load demand and model them via a single random variable ranging over an arbitrary discrete probability distribution Load models can be obtained via pro ling tasks in isolation or simply by using an engineer s hypothesis about the system s projected behavior The end to end performance requirements are posited in terms of throughput and delay con straints Speci cally a pipeline s delay constraint is an upper bound on the total latency a compu tatation can accumulate from input to output The corresponding throughput constraint mandates the pipeline s minimum acceptable output rate counting only outputs which meet their delay con straints Since per component loads can be generally distributed and since resources host stages from multiple pipelines meeting all of the system s end to end constraints is a nontrivial problem Our approach involves solving two sub problems in tandem A nding an optimal proportion of load to allocate each task and channel and B deriving the best combination of service intervals over which all load proportions can be guaranteed The design algorithms use analytic approximations to quickly estimate output rates and propagation delays for candidate solutions When all parameters are synthesized the estimated end to end performance metrics are re checked by simulation The per component load reservations can then be increased with the synthe sis algorithms re run to improve performance At that point the system can be con gured according to the synthesized scheduling parameters and then re validated via on line pro ling In this paper we demonstrate our technique on an example system and compare the estimated performance to its simulated on line behavior This research is supported in part by ONR grant N NSF Young Investigator Award CCR ARL Cooperative Agreement DAAL and NSERC Operating Grant OGPO A preliminary version of this work was reported in Performance Based Design of Distributed Real Time Systems at the Proceedings of IEEE Real Time Technology and Applications Symposium June