Limits on interconnection network performance

“…Thus, the average number of hops traversing each dimension, f k , is calculating by weighting average of average number of hops taken in each case. Therefore, using the method proposed in [7], f k is calculated by ( )…”

Section: Calculation Of the Mean Network Latency ( L )mentioning

confidence: 99%

“…The model is based on the following assumptions that have been widely employed in similar networks analysis studies [4][5][6][7][8][9].…”

Section: Assumptionsmentioning

confidence: 99%

A Performance Model of Fault-Tolerant Routing Algorithm in Interconnect Networks

Safaei

Khonsari

Ould‐Khaoua

2006

Computational Science – ICCS 2006

View full text Add to dashboard Cite

Abstract. The Software-Based fault-tolerant routing [1] has been proposed as an efficient routing algorithm to preserve both performance and fault-tolerant demands in large-scale parallel computers and current multiprocessor systemson-chip (Mp-SoCs). A number of different analytical models for fault-free routing algorithms have been suggested in the past literature. However, there has not been reported any similar analytical model of fault-tolerant routing in the presence of faulty components. This paper presents a new analytical model to capture the effects of failures in wormhole-switched k-ary n-cubes using Software-Based fault-tolerant routing algorithm. The validity of the model is demonstrated by comparing analytical results with those obtained through simulation experiments.

show abstract

“…This feature is a valid alternative to solve the main problem associated to multicomputers: the communication bottleneck. By means of using a dynamic topology, the principle of locality in communications is exploited, leading to a substantial improvement in network latency [2].…”

Section: Discussionmentioning

confidence: 99%