关键词: 并行计算机系统 容错 可靠性 故障诊断

Abstract:

Fault-tolerant design is an effective method to improve the reliability of computer systems. This paper proposes a fault-tolerant architecture for par  allel computer systems, analyzes the fault diagnosis techniques employed in this architecture and presents the configuration optimization strategy for s  tand-by nodes.

Key words: （parallel computer system, fault-tolerance, reliability, fault diagnosis）