Adaptive router architecture based on traffic behavior observability
Proceedings of the 2nd International Workshop on Network on Chip Architectures
Leveraging partially faulty links usage for enhancing yield and performance in networks-on-chip
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Transient and Permanent Error Co-management Method for Reliable Networks-on-Chip
NOCS '10 Proceedings of the 2010 Fourth ACM/IEEE International Symposium on Networks-on-Chip
Self-adaptive system for addressing permanent errors in on-chip interconnects
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A methodology for the characterization of process variation in NoC links
Proceedings of the Conference on Design, Automation and Test in Europe
Addressing link degradation in noc-based ULSI designs
Euro-Par'12 Proceedings of the 18th international conference on Parallel processing workshops
Methods for fault tolerance in networks-on-chip
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
Systems-on-chip integrate increasingly larger numbers of pre-designed cores interconnected through complex communication fabrics. For nanometer-scale VLSI processes (45 nm and below), it is difficult to guarantee correct fabrication with an acceptable yield without employing design techniques that take into account the intrinsic existence of manufacturing defects. In order to improve the yield and reliability of multi-core SoCs, their interconnect infrastructures must be designed such that fabrication and life-time faults can be tolerated. In this work we present a self-repair method for the interconnect fabrics of integrated multi-core systems. Our method is based on the use of redundant links and crosspoints, and improves both post-manufacturing yield and life-time reliability of on-chip communication fabrics. Our method can provide a significant interconnect yield improvement (up to 72% in our experiments), and allows fine-tuning of yield versus redundant components.