A scalable built-in self-recovery (BISR) VLSI architecture and design methodology for 2D-mesh based on-chip networks

Kun Chih Chen*, Shu Yen Lin, Wen Chung Shen, An Yeu Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


On-Chip Networks (OCNs) have been proposed to solve the complex on-chip communication problems. In Very Deep-Submicron era, OCN will also be affected by faults in chip due to technologies shrinking. Many researches focused on fault detection and diagnosis in OCN systems. However, these approaches didn't consider faulty OCN system recovery. This paper proposes a scalable built-in self-recovery (BISR) design methodology and corresponding Surrounding Test Ring (STR) architecture for 2D-mesh based OCNs to extend the work of diagnosis. The BISR design methodology consists of STR architecture generation, faulty system recovery, and system correctness maintenance. For an n×n mesh, STR architecture contains one controller and 4n test modules which are formed as a ring-like connection surrounding the OCN. Moreover, these test modules generate test patterns for fault diagnosis during warm-up time. According to these diagnosis results, the faulty system is recovered. Finally, this paper proposes a fault-tolerant routing algorithm, Through-Path Fault-Tolerant (TP-FT) routing, to maintain the correctness of this faulty system. In our experiments, the proposed approach can reduce 68.33~79.31% unreachable packets and 4.86~23.6% latency in comparison with traditional approach with 8.48~13.3% area overhead.

Original languageEnglish
Pages (from-to)111-132
Number of pages22
JournalDesign Automation for Embedded Systems
Issue number2
StatePublished - Jun 2011


  • Built-in self-recovery (BISR)
  • Design-for-testability (DfT)
  • On-chip networks (OCN)
  • Surrounding test ring (STR)
  • Through-path fault-tolerant (TP-FT) routing


Dive into the research topics of 'A scalable built-in self-recovery (BISR) VLSI architecture and design methodology for 2D-mesh based on-chip networks'. Together they form a unique fingerprint.

Cite this