高性能计算机系统

虚拟化技术在高性能计算机系统中的应用研究

The Application Research of Virtualization Techniques for High Performance Computer Systems

门户是访问高性能计算机系统上的服务的用户界面。

Portal is a user interface to access services on high performance computer systems .

气象模式应用门户，以Web方式来共享使用承载于高性能计算机系统上的气象模式。

The meteorological model application portal realizes the shared use of meteorological applications hosted in high performance computers by means of Web .

高性能计算机系统是现代SAR地面处理系统中的重要组成部分。

High Performance Computing ( HPC ) system is an important part of a modern SAR processing system .

HPS在IBM高性能计算机系统中的应用

Application of HPS to IBM High Performance Computer System

而在目前高性能计算机系统中，最广泛使用的一种标准是MPI，它已成为一种并行程序的标准。

MPI , which is a standard , is the most extensive usage in high performance computing system .

随着叠前偏移处理技术的进一步推广应用，大规模PC集群已取代传统并行机成为地震资料处理的高性能计算机系统。

As the popularization of prestack migration processing technique , large scale PC group has replaced traditional parallel cluster and become a high performance computer system for seismic data processing .

高性能计算机系统MGH串行背板设计

The Design of Mlti-GigaHertz Serial-Link Backplane in High Performance Computer System

本文描述了高性能计算机系统对RAS的需求，介绍了当前RAS技术的现状，并对其发展趋势进行了分析。

This paper describes the requirements of RAS in high performance computers , and introduces the current RAS situation and analyzes its trend in the future .

高性能计算机系统的可扩展性是系统设计的一大难题，NUMA（non-uniformmemoryarchitecture）结构正是为了解决共享存储体系的可扩展性问题而提出来的。

The scalability of system is a puzzle to design high performance computers . NUMA ( non - uniform memory architecture ) architecture is proposed for scalable system underlying a shared memory pattern .

文章在对高性能计算机系统中的Cache结构研究基础上，将Cache的三种组织方式作了分析和比较，并对各自的优缺点和使用场合提出了重要见解。

This paper analyses and compares three organization fashions of Cache based on research for Cache architectures of high property computer system , and besides , it suggests important opinion for their advantage , defect , and use occasion .

本文以Chirpscaling算法为例，从分析SAR成像处理的典型运算入手，以NUMA架构为主要对象，研究了现代高性能计算机系统中对SAR成像处理有较大影响的环节。

With an example for Chirp Scaling algorithm , this paper focuses on typical operations in SAR imaging and analyzes the elements of a HPC system , especially of a NUMA system , which greatly impact SAR imaging performance .

高性能计算机系统中可视化负载信息的获取及性能分析工具：THPTii

THPTii : A Visualization Tool for Load Information Collecting and Performance Analyse in High Performance Computing System

高性能计算机系统接口通信机制的研究

Research for communication mechanism of a high performance computer system

高性能计算机系统中影响通信因素分析和优化策略的研究

Analysis for Factors Affecting Communication and Research for Optimizing in High Performance Cluster Computer System

互连系统是构成高性能计算机系统和决定系统通信性能的关键部分。

The interconnection system is the critical part of high performance computer system ( HPCS ) .

获得高度的并行性，仍然是开发高性能计算机系统的基本途径，而可以获得的并行效率，也越来越与程序的内在特性相关联。

Exploiting as much parallelism as possible is still the base to implement high performance computer systems .

在多机系统中，处理器之间的高效通信对于提高系统的性能十分重要，于是，研究多机系统结构上的路由技术成为高性能计算机系统应用的实际需要。

In multicomputer system , the efficient communication between computers is very important to improve the system 's performance .

提出基于异步光分组交换及组播技术的新型高性能计算机系统架构。

A novel high performance computing system ( HPCS ) based on asynchronous OPS and optical multicast is presented .

这种算法采用数据划分技术，利用高性能计算机系统，如集群式系统，有效地提高了双序列比对的时间空间效率。

It reduces time and space complexity by introducing data dividing technique , using High Performance computer system such as group system .

目前的高性能计算机系统由大量的处理结点构成，处理结点之间通过互连网络进行通信和协作。

Currently the high performance computer system is consisted by plenty of nodes , between which are communicated and coordinated by interconnection network .

该文主要介绍了神威高性能计算机系统的作业管理系统及其批式作业调度模块的设计思路和实现。

This paper mainly introduces the job management system and the design and implementation of its batch job management system scheduling module in sunway .

随着高性能计算机系统的快速发展，并行计算已经成为科学和工程计算的基本支撑技术。

With the rapid development of high performance computer systems , parallel computing has become a basic supporting technology for scientific and engineering computing .

在计算机体系结构的发展过程中，并行结构的出现与不断发展将高性能计算机系统的峰值速度一次又一次推向新的高峰。

The peak speeds of high performance computer are pushed to new pinnacle with the use and innovations of parallel architectures again and again .

虚拟现实是模拟仿真在高性能计算机系统和信息处理环境下的一种拓展。

Virtual Reality ( VR ) is a kind of extension of simulation in the background of computer systems with high capacity and information processing .

计算机系统总线及其体系结构是影响高性能计算机系统性能的关键因素。

Two of the most important factors , which impact on the performance of high-performance computer system , are the system bus and the structure of the computer system .

本文研究了高性能计算机系统的性能度量和提升途径，分析并找出了影响系统加速比的关键因素。

We study the performance measurement of the HPCS as the starting point The characteristic of the HPCS 's speedup and the crucial factors to influence the HPCS 's speedup are studied .

高性能计算机系统内部高速互连网络是制约系统整体性能的关键因素，高带宽低延迟的互连和交换是系统最为重要的性能指标。

The internal high-speed interconnection network of High-performance computer systems is the key factor which constraints the overall performance of the system . high-bandwidth , low-latency interconnection and exchange are the most important performance indicators of the system .

数据分析表明，在许多大规模并行程序中，聚合通信的开销甚至占到全部通信开销的80%、总执行时间的60%以上，成为高性能计算机系统的性能瓶颈。

According to the data analyzing , the cost of the collective communication accounts for 80 % of the cost of whole communication and 60 % of the executing time in some large-scale paral-lel programs . Collective Communication has become a performance bottleneck for high performance computing system .

高性能并行计算机系统中由于CPU速度不断提高，通信机制成了影响系统性能的首要因素。

In the high performance cluster computer system , the speed of CPU raises continually , so the communication mechanism becomes the first factor affecting performance of the system .