Skip to main content

Fujitsu

Global

Archived content

NOTE: this is an archived page and the content is likely to be out of date.

High Performance Computing


FSTJ 1997-06 Cover Image

1997-06(Vol.33, No.1)



1997-6(Vol.33, No.1) Contents

1. Preface (179 KB)
---[Yoshihiro Kosaka General Manager HPC Division. ]
2.Hardware of VX/VPP300/VPP700 Series of Vector-Parallel Supercomputer Systems (571 KB)
This paper introduces the hardware of Fujitsu's VX/VPP300/VPP700 series of vector-parallel supercomputer systems for high-speed scientific calculations. The series can be configured with up to 512 processing elements ( PEs ) to achieve a performance of from 2.2 GFLOPS to 1.1 TFLOPS ( the maximum performance of each PE is 2.2 GFLOPS ). By using advanced CMOS technology, the series has been greatly improved in terms of cost-performance and physical characteristics such as power consumption and installation space. The series supports standard interfaces such as SCSI, ATM, FDDI, and HIPPI, making them very open machines. ---[Nobuo Uchida ]
3. Operating System of the VX/VPP300/VPP700 Series of Vector-Parallel Supercomputer Systems (222 KB)
The computers used in science and technology are generally either low-end, high cost-performance machines owned by individual research and development sections, or high-end ultra high-speed machines. This paper describes the features of the UXP/V operating system of the VX/VPP300/VPP700 series of vector parallel supercomputers, which were developed to flexibly cover the requirements for science and technology computing. It also looks at the following important topics regarding vector parallel supercomputers : - The method of allocating resources such as the CPU and memory - The scheduling technique for batch processing - The technology used to achieve high-speed I/O processing and network processing This paper also describes a function for easy installation and administration and a strengthened operational management function for the computer center. ---[Yuji Koeda ]
4. Hardware of AP3000 Scalar Parallel Server (288 KB)
The AP3000 is a distributed-memory parallel server consisting of multiple workstations connected via a high-speed communication network. Each workstation ( node ) uses the advanced UltraSPARC CPU and the Solaris operating system. By combining the AP3000 with a remote memory copy function and by performing inter-node communication using Fujitsu newly developed AP-Net high-speed message communication network, the AP3000 can be used as a high-performance parallel computer and a workstation cluster. The system has hardware to support single-system-image operation of a multi-node system. ---[Hiroaki Ishihata, Masanori Takahashi, Hiroyuki Sato ]
5. Operating System of AP3000 Series Scalar-Type Parallel Servers (272 KB)
This paper outlines the control software for the AP3000 series of scalar-type parallel servers. The series provides high-performance computing power in many fields, for example, R&D, database processing, decision making support, and multimedia processing. Each AP3000 series machine is a scalar-type parallel computer system consisting of four or more node computers that are interconnected by a high-speed communication network called AP-Net. The AP3000 series has a high processing performance to cover the higher-level models of equipment ranging from Symmetrical Multiprocessors ( SMPs ) to Massively Parallel Processors ( MPPs ). The AP3000 series contains an SMP as a node computer and has the same scalability as that of an MPP. The series has the characteristics of a cluster-type computer and has all the characteristics of typical parallel computers. Solaris is used as the control software of the AP3000 series. By combining Solaris with operation management software products, all node computers connected to AP-Net can be operated as one system. The set of node computers can also be divided into various groups as required. ---[Hiroyuki Oyake, Yuji Iguchi, Tsunemi Yamane ]
6. Parallel Language Processing System for High-Performance Computing (469 KB)
Fujitsu has developed a common parallel language processing system for the VPP and AP distributed memory parallel computers. The parallel language processing system includes a parallelizing compiler, libraries, and parallelizing support tools. The systems were developed to satisfy the following requirements : 1) To provide a language processing system that is common to the VPP and AP, 2) to provide multi-paradigms for parallel programming, and 3) to realize functions to achieve high performance. The following have also been developed : A Fortran parallelizing compiler that processes VPP Fortran. The compiler provides parallelizing notations for manual tuning and makes programming easy. The MPI and PVM message passing libraries, which can be custom tuned to suit a machine's architecture. The SSL II library of popular numerical calculation algorithms, which are parallelized to achieve high performance. A GUI programming support tool called Workbench that provides users with several options for parallel programming. ---[Eiji Yamanaka, Tatsuya Shindo ]
7. Development and Application of MASPHYC Computational Material Design System "Application Package in HPC" (417 KB)
Although high performance is one of the main criteria when considering whether to introduce a supercomputer, users are paying much more attention to the quantity and quality of application packages available for a candidate machine. In response, Fujitsu has developed original packages and ported de facto standard packages for supercomputers. This paper describes the status of application packages available for Fujitsu VX/VPP series computers. Also, this paper introduces Fujitsu's MASPHYC computational material design system and describes its performance on a VPP500. ---[Munetaka Takechi, Takahiro Ishigai, Katashi Ishibashi ]
8. Examples of Using the VPP500 in JRCAT (2.58 MB )
We have been using calculation techniques based on first-principles ( or quantum ) molecular dynamics to analyze physical phenomena at the atomic level. Some examples of the phenomena that have been analyzed are molecule dissociative adsorption reactions on semiconductor and metal surfaces, and metal-insulator phase transitions of organic solids. It is certain that such analyses will be more widely and frequently performed in the future. The VPP500 vector parallel computer is very compatible with these calculation techniques. When programs written for vector computers are run on the VPP500, the parallel acceleration rate can be improved considerably without reducing the vectorization factor. The VPP500 can handle large-scale calculations because it separates calculations from data and allows calculations to be assigned to processor elements appropriately. This paper describes our experience of changing first-principles molecular dynamics programs so that they can be parallel-executed on the VPP500, and describes the operation management of a computer group centered around the VPP500. This paper also looks at some simulation results. ---[Takahiro Yamasaki, Koichi Sato, Kiyoyuki Terakura]
9. VPP300 Series in National Astronomical Observatory (1.24 MB )
In astronomy we cannot perform any experiments of realistic time scale and spatial scale because those of the universe are too large for human being. That is the reason why we make very much of the numerical experiments by large computers. In this paper, we introduce the supercomputer system VPP300/16R, VX/4R, VX/1R and many small computers around them which were installed in National Astronomical Observatory Mitaka, Tokyo in 1996. We also introduce the history, the way of administration, and some of the scientific results produced by the system for now. In this system main memory of 32 Gbyte and parallel computation up to 16PE is available, and it is expected to become a central platform for large scale numerical experiments to progress the astronomy worldwide. ---[Takashi Ito ]
10. Use of the Fujitsu VPP700 for Weather Forecasting at ECMWF (2.10 MB )
On 18 September 1996 the operational numerical weather forecasting activities of the European Centre for Medium-Range Weather Forecasts (ECMWF) were transferred to run on a Fujitsu VPP700/46 computer system, after many years of use of shared-memory Cray systems. The range of current forecasting activities is described, and further information is given on the computational design and performance of the atmospheric forecast model, and on the operation of the VPP700. Developments which will utilize planned enhancements of the Fujitsu computer system at ECMWF are summarized. ---[D.Dent, G-R.Hoffmann, P.A.E.M.Janssen, Adrian Simmons ]