Abstract: Scheduling models can be used to evaluate whether a particular system is able to meet its timing constrains. In many-core processors, with tens to hundreds of processors in the same chip, the analysis of the timing behavior needs to include the communications network used to exchange messages between the different processors. This paper presents a schedulability model for many-core systems based on a 2D mesh network-on-chip and store-and-forward switching with a limitation on the maximum link utilization rate that makes the analysis tractable. The model has been applied to the Epiphany many-core processor which has 16 cores connected by a 4 × 4 2D mesh. The analysis results have been tested on the real hardware by executing examples with synthetic task workloads. Those tasks are executed in a micro-kernel RTOS that we have developed. We also describe synchronization mechanisms to send messages between the tasks, and we analyze their timing behavior, so that they can be included in the analysis model.

Authorship

Download reference