16:10 - 17:58 | Wed 28 Jun | | WeDPl
Historically, automotive test systems were designed for a single core architecture. This, however, limited the utilization of shared resources. In this paper we present a redesign of an automotive test system that is based on a multicore architecture and capable of managing mixed-criticality data. As part of the redesign, we implemented a Connectivity Manager (CM) that is in charge of multiplexing several data streams from multiple cores across a shared network. Due to the increased complexity of our system, a more flexible scheduling approach is required. Our solution to this problem is a novel dynamic priority communication scheduling approach that adapts to bandwidth changes on the shared communication network. Through simulations with realistic workloads, we prove the proper functioning of our algorithm with the result that higher critical data streams are favoured over less critical data streams in case of an overloaded system caused by a bottleneck on the CAN bus.
No information added