Implications of Reliability Enhancement Achieved by Fault Avoidance on Dynamically Reconfigurable Architectures

Abstract

Fault avoidance methods on dynamically reconfigurable devices have been proposed to extend device life-time, while their quantitative comparison has not been sufficiently presented. This paper shows results of quantitative life-time evaluation by simulating fault avoidance procedures of representative five methods under the same conditions of wearout scenario, application and device architecture. Experimental results reveal 1) MTTF is highly correlated with the number of avoided faults, 2) there is the efficiency difference of spare usage in five fault avoidance methods, and 3) spares should be prevented from wear-out not to spoil lifetime enhancement.

Field Slack Assessment for Predictive Fault Avoidance on Coarse-Grained Reconfigurable Devices

“…For coping with aging-induced delay increase, two approaches are studied; suppressing aging effects [1], [2] and eliminating faulty modules [3], [4]. Though aging suppression is effective for extending device life-time, it cannot stop the aging effects completely and its efficacy is limited.…”

“…This paper focuses on the second approach of faulty module elimination with module replacement, especially in reconfigurable devices that are compatible with module replacement. Using the reconfiguration capability, a faulty BE is replaced with a healthy unused BE [3], [4]. On the other hand, the delays of BEs are different due to manufacturing variability and different environmental conditions for aging.…”

A predictive delay fault avoidance scheme for coarse-grained reconfigurable architecture

“…Therefore, the number of possible pairs is limited. Besides, a problem on how much spares are necessary to succeed BE replacement is beyond this paper, and we will study that in the near future extending [2].…”

“…[1]) and eliminating faulty modules [2,3]. Though aging suppression is effective for extending device life-time, it cannot stop the aging effects completely and its efficacy is limited.…”

“…This paper focuses on the second approach of faulty module elimination with module replacement, especially in reconfigurable devices that are compatible with module replacement. Using the reconfiguration capability, a faulty BE is replaced with a healthy BE [2,3], where BE is basic element composing a reconfigurable device. To ensure the successful replacement, we need to identify which BE should be eliminated and which BE should substitute.…”