High performance computing clusters operating in shared and batch mode pose challenges for processing sensitive data. In the meantime, the need for secure processing of sensitive data on HPC system is growing. In this work we present a novel method for creating secure computing environments on traditional multi-tenant high-performance computing clusters. Our platform as a service provides a customizable, virtualized solution using PCOCC and SLURM to meet strict security requirements without modifying the exist-ing HPC infrastructure. We show how this platform has been used in real-world research applications from different research domains. The solution is scalable by design with low performance overhead and can be generalized for processing sensitive data on shared HPC systems imposing high security criteria
翻译:以共享和分批方式运行的高性能计算集群对处理敏感数据构成挑战;同时,对高频PC系统敏感数据进行安全处理的需要正在增加;在这项工作中,我们提出了一个在传统的多租多租高性能计算集群中创造安全计算环境的新颖方法;我们的平台作为一个服务平台提供了一种可定制的、虚拟化的解决方案,利用PCOCC和SLURM满足严格的安全要求,而不改变现有的高频PC基础设施。我们展示了该平台如何在不同研究领域的现实世界研究应用中被使用。这个解决方案可以通过低性能间接费用的设计加以缩放,并可以普遍用于处理关于高安全标准的共享高电动计算机系统的敏感数据。