SafeMPI -并行机群上扩展MPI的拜占庭错误检测
SafeMPI - Extending MPI for Byzantine Error Detection on Parallel Clusters
摘要：
现代高性能计算在很大程度上依赖于使用以集群形式排列在一起的商用处理器。这些集群由通过高速互连连接在一起的各个节点（通常是现成的单处理器或双处理器机器）组成。使用集群计算有很多好处，但由于涉及的组件数量太多，也容易出现故障。已经提出了许多有效的解决方案来帮助集群中的故障恢复，它们的一个显著缺点是它们支持的故障模型。该领域的大部分工作都集中在检测和纠正故障停止错误上。我们提出了一个系统，也将检测更一般的错误模型，如拜占庭错误，从而允许现有的故障恢复方法来正确处理它们。
英文摘要：
Modern high-performance computing relies heavily on the use of commodity processors arranged together in clusters. These clusters consist of individual nodes (typically off-the-shelf single or dual processor machines) connected together with a high speed interconnect. Using cluster computation has many benefits, but also carries the liability of being failure prone due to the sheer number of components involved. Many effective solutions have been proposed to aid failure recovery in clusters, their one significant downside being the failure models they support. Most of the work in the area has focused on detecting and correcting fail-stop errors. We propose a system that will also detect more general error models, such as Byzantine errors, thus allowing existing failure recovery methods to handle them correctly.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
