Analysis of on-chip interconnection network interface reliability in multicore systems

In Networks-on-Chip (NoC), with ever-increasing complexity and technology scaling, transient single-event upsets (SEUs) have become a key design challenge. In this work, we extend the concept of architectural vulnerability factor (AVF) from the microprocessor domain and propose a network vulnerability factor (NVF) to characterize the susceptibility of NoC components such as the Network Interface (NI) to transient faults. Our studies reveal that different NI buffers behave quite differently on transient faults and each buffer can have different levels of inherent fault-tolerant capability. Our analysis also considers the impact of thermal hotspot mitigation techniques such as frequency throttling on the NVF estimation.