A reconfigurable fault-tolerant deflection routing algorithm based on reinforcement learning for network-on-chip

Author(s):  
Chaochao Feng ◽  
Zhonghai Lu ◽  
Axel Jantsch ◽  
Jinwen Li ◽  
Minxuan Zhang
2017 ◽  
Vol 28 (3) ◽  
pp. 838-849 ◽  
Author(s):  
Yu-Yin Chen ◽  
En-Jui Chang ◽  
Hsien-Kai Hsin ◽  
Kun-Chih Chen ◽  
An-Yeu Andy Wu

2016 ◽  
Vol 26 (03) ◽  
pp. 1750037 ◽  
Author(s):  
Xiaofeng Zhou ◽  
Lu Liu ◽  
Zhangming Zhu

Network-on-Chip (NoC) has become a promising design methodology for the modern on-chip communication infrastructure of many-core system. To guarantee the reliability of traffic, effective fault-tolerant scheme is critical to NoC systems. In this paper, we propose a fault-tolerant deflection routing (FTDR) to address faults on links and router by redundancy technique. The proposed FTDR employs backup links and a redundant fault-tolerant unit (FTU) at router-level to sustain the traffic reliability of NoC. Experimental results show that the proposed FTDR yields an improvement of routing performance and fault-tolerant capability over the reported fault-tolerant routing schemes in average flit deflection rate, average packet latency, saturation throughput and reliability by up to 13.5%, 9.8%, 10.6% and 17.5%, respectively. The layout area and power consumption are increased merely 3.5% and 2.6%.


2017 ◽  
Vol 27 (02) ◽  
pp. 1850022 ◽  
Author(s):  
Ling Wang ◽  
Terrence Mak

In 2D mesh Network on Chips (NoCs), fault-tolerant algorithms usually deactivate healthy nodes to form rectangular or convex fault blocks. However, the deactivated nodes can possibly form an available tunnel in a faulty block. We propose a method to discover these tunnels, and propose a fault-tolerant routing algorithm to route messages through such paths such that the overall communication performance is improved. In addition, the algorithm is deadlock-free by prohibiting some turns. Simulation results demonstrate that the reuse of the sacrificed nodes in fault blocks can significantly reduce the average message latency.


Author(s):  
Chaochao Feng ◽  
Minxuan Zhang ◽  
Jinwen Li ◽  
Jiang Jiang ◽  
Zhonghai Lu ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document