高性能计算与虚拟桌面基础设施融合使用研究

Research on fusion use of HPC and VDI

随着机器学习、神经网络、深度学习相关研究的广泛开展,以及近年来人工智能、大数据相关专业的增设,很多高校的高性能计算系统存在算力紧张的情况;同时,高校中的很多信息设施由于负载的时段性波动,也存在计算资源闲置浪费的情况,因而对这些闲置资源如何有效利用进行研究意义重大。虚拟桌面基础设施计算力可观,负载空闲时间段较长且具有规律性,基于此,文中提出一种通过在虚拟桌面基础设施中创建虚拟机形式的高性能计算节点进而组成计算队列,通过错时启动虚拟桌面池和高性能计算队列融合使用的方法,来解决高性能计算算力紧张的问题。文中方法既不影响虚拟桌面基础设施原有的提供桌面池的功能,同时又能够提供额外的高性能计算算力,使得既有信息设备发挥更大的功效。

With the extensive development of research related to machine learning,neural networks and deep learning,as well as the addition of artificial intelligence and big data related majors in recent years,HPC(high-performance computing)systems in many colleges and universities are facing computational stress. Many information facilities in colleges and universities also have idle and wasted computing resources due to the periodical fluctuation of load. Therefore,it is of great significance to study how to effectively use these idle resources. The computing power of VDI(virtual desktop infrastructure)is considerable,and the load idle time period is long and regular. On this basis,a method of creating HPC nodes in the form of virtual machines in the VDI is proposed to form a computing queue,and start the fusion use of virtual desktop pool and HPC queue at staggered hours,so as to solve the problem of HPC stress in calculation. The method in this paper is not only does not affect the original function of providing desktop pool in VDI,but also can provide additional HPC power,so that the existing information equipment can play a greater role.