Dynamic Placement Optimization for Bio-Inspired Self-Repairing Hardware

Abstract

Bio-inspired self-repairing hardware is a distributed self-adaptive system, characterized by powerful fault-tolerant ability and environment adaptivity. However, it suffers from some difficulties such as large resource consumption and degraded circuit performances. From the viewpoint of cybernetics and computer science, the cellular differentiation and substitution process of bio-inspired self-repairing hardware can be converted into dynamic placement problems on a reconfigurable system. Current systems can only generate some predefined fault-free placements from a finite number of initial placements. The aim of this paper was to achieve high-quality placements from arbitrary initial placements. Based on P systems, an analysis has been made on the limitations of current systems and an improved computing system has been developed to achieve the ergodic property. Its computational power has been verified by a constructive proof. Moreover, centering on the problem how to improve the placement quality on a distributed platform, the optimization model, task allocation, optimization strategy, and membrane optimization algorithm have been designed and developed. The optimization performances were verified and the calculation amount was exhibited by experiments. Finally, it indicated by comparison that the proposed approach would reduce the resource consumption and maintain good circuit performances. INDEX TERMS Bio-inspired self-repairing hardware, dynamic placement optimization, P systems, computing model, membrane optimization algorithms.

A Dynamical Evolution Approach to High Placement Performance and Low Fault-Tolerant Cost for Bio-Inspired Self-Repairing Hardware

“…Then the FRL value and the PPL value will be calculated by Eq. 3and (6). There are 100 experiments in one method and every experiment corresponds to one FRL value and one PPL value.…”

“…During this phase, all the PLs are deactivated. ECells automatically change their states or renew function blocks according to the environment information and the placement keeps changing by local rules without any central control [6]. By contrast, the placement interval is in a stable state without any faulty eCell.…”

“…In order to avoid the combination explosion problem, researchers mimicked the behavioral pattern of multicellular organisms and developed bio-inspired selfrepairing hardware to solve complex computational tasks by local rules without any central control [4], [5]. As a reconfigurable, fault-tolerant system, bio-inspired self-repairing hardware is characterized by decentered architecture, distributed computing, and dynamic partial reconfiguration [6]. It uses multiple processing elements to increase the computing power and relocate configuration information segments (or function blocks) instead of generating the entire bitstreams to reduce the calculation amount.…”

Computer Hardware Fault Detection based on Machine Learning

“…Computer hardware fault detection based on machine learning is shown in Figure 2.1. Liu, et al said that the scale of the system continues to grow and the complexity of hardware and software continues to increase, these make the mean time between failures of supercomputers getting shorter and shorter [8]. Yuan, et al said that when the scale of the supercomputer system reaches a certain scale, continuing to expand the scale of the system will not only fail to shorten the running time of the job, on the contrary, the execution time of the job will become longer and longer due to the constraints of fault tolerance overhead, that is, reliability, it restricts the expansion of the system scale [9].…”