Loopback strategy for in-vehicle network processing in automotive gateway network on chip

Abstract

In this work, authors introduce an innovative loopback strategy for In-Vehicle Network (IVN) processing in automotive gateway (GW) Network on Chip. The new proposed architecture is fully HW centric, and allows performing any IVN processing algorithms without intervention from the CPU. In essence, the loopback strategy allows for adapting the number of stages in the pipeline of the processing stage by betting on the centralization of the processing resources and recirculating frames from output to input when further stages are needed. It permits even to select to which stage to send them depending on the processing required, optimizing thus the number of stages traversed by frames and consequently reducing latency. The processing unit is built as a stack of parallel tasks with the required interconnection resources that allow performing any processing over any frame, and to handle several frames in parallel. With this architecture, the GW data path is fully adaptable per frame, optimizing latency and Quality of Service, allowing for fulfilling the high demanding requirements of future IVNs.