Cell-neighbor-bridging defects between logic and filler cells were detected on an automotive design after a highly resistive short defect was activated during an internal reliability assessment, having previously passed all wafer probe and package Final Test stresses and screens. The impacted cell’s nodes were confirmed to be stressed and tested as intended at the wafer probe insertion, but not sufficiently enough to activate and observe the effect of the highly resistive defect’s impact on the circuit behavior. The paper discusses a new methodology that identified and located all instantiations of the affected cell combinations in the sea of gates, and development of new stress and test stimuli using User Define Fault Models (UDFM) to target only the affected cell combinations. Limiting the reach of the enhanced stress and test in this way enabled a cost effective and high-quality solution to accelerate activation and improve detectability of the latent defect during silicon test flows.

Distributed storage systems for large clusters typically use replication to provide reliability. Recently, erasure codes have been used to reduce the large storage overhead of three-replicated systems. Reed-Solomon codes are the standard design choice and their high repair cost is often considered an unavoidable price to pay for high storage efficiency and high reliability. This paper shows how to overcome this limitation. We present a novel family of erasure codes that are efficiently repairable and offer higher reliability compared to Reed-Solomon codes. We show analytically that our codes are optimal on a recently identified tradeoff between locality and minimum distance. We implement our new codes in Hadoop HDFS and compare to a currently deployed HDFS module that uses Reed-Solomon codes. Our modified HDFS implementation shows a reduction of approximately 2× on the repair disk I/O and repair network traffic. The disadvantage of the new coding scheme is that it requires 14% more storage compared to Reed-Solomon codes, an overhead shown to be information theoretically optimal to obtain locality. Because the new codes repair failures faster, this provides higher reliability, which is orders of magnitude higher compared to replication.