RISC Workstations Research Articles

A program for performing exact quantum dynamics calculations using cylindrical polar coordinates: A nanotube application

A program that uses the time-dependent wavepacket method to study the motion of structureless particles in a force field of quasi-cylindrical symmetry is presented here. The program utilises cylindrical polar coordinates to express the wavepacket, which is subsequently propagated using a Chebyshev expansion of the Schrödinger propagator. Time-dependent exit flux as well as energy-dependent S matrix elements can be obtained for all states of the particle (describing its angular momentum component along the nanotube axis and the excitation of the radial degree of freedom in the cylinder). The program has been used to study the motion of an H atom across a carbon nanotube. Program summary Program title: CYLWAVE Catalogue identifier: AECL_v1_0 Program summary URL: http://cpc.cs.qub.ac.uk/summaries/AECL_v1_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.html No. of lines in distributed program, including test data, etc.: 3673 No. of bytes in distributed program, including test data, etc.: 35 237 Distribution format: tar.gz Programming language: Fortran 77 Computer: RISC workstations Operating system: UNIX RAM: 120 MBytes Classification: 16.7, 16.10 External routines: SUNSOFT performance library (not essential) TFFT2D.F (Temperton Fast Fourier Transform), BESSJ.F (from Numerical Recipes, for the calculation of Bessel functions) (included in the distribution file). Nature of problem: Time evolution of the state of a structureless particle in a quasicylindrical potential. Solution method: Time dependent wavepacket propagation. Running time: 50000 secs. The test run supplied with the distribution takes about 10 minutes to complete.

Parallel FEM Software for CFD Problems

The present paper describes the development and the performance of parallel FEM software for solving various CFD problems. Domain decomposition strategy and parallel iterative GMRES solver have been adapted to the universal space-time FEM code FEMTOOL, which allows implementation of any partial differential equation with minor expenses. The developed data structures, the static load balancing and the inter-processor communication algorithms have been particularly suited for homogeneous distributed memory PC clusters. The universality of the considered parallel algorithms has been validated solving applications described by the Poisson equation, by the convective transport equation and by the Navier-Stokes equations. Three typical benchmark problems have been solved in order to perform the efficiency study. The performance of parallel computations, the speed-up and the efficiency have been measured on three BEOWULF PC clusters as well as on the cluster of IBM RISC workstations and on the IBM SP2 supercomputer.

The Java Management Extensions (JMX): Is Your Cluster Ready for Evolution?

The arrival of commodity hardware configurations with performance rivaling that offered by RISC workstations is resulting in important advances in the state of the art of building and running very large scalable clusters at “mass market” pricing levels. However, cluster middleware layers are still considered as static infrastructures which are not ready for evolution. In this paper, we claim that middleware layers based on both agent and Java technologies offer new opportunities to support clusters where services can be dynamically added, removed, and reconfigured. To support this claim, we present the Java management extensions, a new Java agent-based technology, and its application to implement two disjoint cluster management middleware services (a remote reboot service and a distributed infrastructure for collecting Log events) which share a unique agent-based infrastructure.

CAD techniques for microwave circuits

In little more than 10 years computer-aided design (CAD) of microwave circuits has moved from dumb terminals on mainframe computers to PCs, and now to powerful RISC workstations. Commercial CAD software now integrates the various stages of microwave circuit design: schematic capture, simulation and layout. This paper reviews the different CAD packages that are available for microwave circuit design. The basic principles employed in the modelling of microstrip circuits are introduced and the reasons for the extensive use of frequency-domain simulations are explored. The developments in nonlinear, electromagnetic and system-level simulation methods are described.

Risc workstations as a platform for radiation dose planning in stereotactic radiosurgery

Risc workstations as a platform for radiation dose planning in stereotactic radiosurgery

Super efficient decoding of color JPEG images on RISC machines

An efficient method for decoding a color JPEG image coded as luminance and chrominance data and converting the output to red, green and blue data on RISC workstations is presented. Timing results are presented which show that these algorithms can be used in a software package to decompress and display images of size 352 × 240 at about 9 frames per second on the IBM RISC System/6000 Model 530 (a 25 MHz machine).

Transitioning desktops to set tops

Video provides the greatest realism in multimedia and also demands the most from computer systems. Innovations already enable conventional desktops, such as RISC workstations, to handle compressed audio and low-resolution video signals. Similarly, interactive, real-time, 3D animation graphics produce data processing and transmission challenges. Meeting these challenges will transition desktop systems to televisions with set-top boxes, linking broadcast quality video and audio to the interactivity of a computer.

High precision interpolation algorithm for 3D parametric curve generation

The paper presents an algorithm for general 3D and 2D parametric curve interpolation. This is an incremental step algorithm, and it uses two simple principles; firstly, each selected step has to follow a given direction along the curve, and, secondly, each selected step has to be at the closest distance from the curve. The mathematical formulation of the algorithm permits the interpolation of any kind of parametric curve, which is an important aspect of modern cad/cam systems. Its software implementation on risc workstations and the in-house academic tests to date have shown promising results, and it is hoped that it can be applied in the next generation of computerized numerical control systems.

Domain decomposition methods for circuit simulation

In this paper we discuss the application of domain decomposition methods to circuit simulation. This coarse grain parallelization guarantees a minimum of communication and thus achieves good speedup results on a workstation cluster. Our results show that with a cluster of ten powerful RISC workstations comparable turn around times to a supercomputer can be achieved. Furthermore a workstation cluster offers the possibility to simulate electric circuits with a size of new magnitude. On a cluster of 27 workstations we succeeded in simulating a circuit with 135000 transistors, while we failed to simulate the same circuit on our supercomputer because of a lack of memory.

An efficient implementation of BP on RISC-based workstations

A method for efficient implementation of a batch BP algorithm on current generation RISC workstations is presented. We show that with careful programming and slight modification to the algorithm, it is possible to achieve a performance gain up to 50 times when compared with conventional implementation. Experimental results show performances of 17.6 Mcups (Million of connection upates per second) through level 3 BLAS routines and 15.5 Mcups through standard FORTRAN77 programming on a IBM RISC/6000 550.

MECDAS/spl minus/a distributed data acquisition system for experiments at MAMI

For coincidence experiments with the three-spectrometer setup at MAMI an experiment control and data acquisition system has been built and was put successfully into final operation in 1992. MECDAS is designed as a distributed system using communication via Ethernet and optical links. At the front end, VMEbus systems are used for real time purposes and direct hardware access via CAMAC, Fastbus or VMEbus. RISC workstations running UNIX are used for monitoring, data archiving and online and offline analysis of the experiment. MECDAS consists of several fixed programs and libraries, but large parts of readout and analysis can be configured by the user. Experiment specific configuration files are used to generate efficient and powerful code well adapted to special problems without additional programming. The experiment description is added to the raw or partially analyzed data to get self-descriptive data files. >

Computer Networks and Advanced Communications: Weighing the Pros and Cons

Summary One main method for optimizing computer usage is networking. However, for those who are contemplating a change from standalone computers to a network system, investigation of actual networks in use presents a paradox: network systems can be highly productive and beneficial, but they can create many complex, frustrating problems. The issue becomes a question of whether the benefits of networking are worth the extra effort and cost. Here we review the implementation and management of an actual network in the Louisiana State U. (LSU) Petroleum Engineering Dept. The network, which has been in operation 4 years, is large and diverse (50 computers, 2 sites, PC's, UNIX RISC workstations, etc.). The benefits, costs, and method of operation of this network are described, and an effort is made to weigh these elements objectively from the viewpoint of the average computer user. Our intent is to provide those who may be considering the change to a network system with the benefit of experience gained in the actual operation of such a system.

A new off-lattice Monte Carlo model for polymers: A comparison of static and dynamic properties with the bond-fluctuation model and application to random media

A model for a multichain polymer system in three-dimensional continuous space is studied by link cell Monte Carlo methods, using systems up to chain length N=64 and up to 16 384 monomers. The chains consist of beads with a hard core connected by rather stiff harmonic bonds, with a repulsive Lennard-Jones-type interaction between beads chosen such that chains cannot cross each other during their random motions. On RISC workstations the model performs only about a factor of 4 slower than the bond fluctuation lattice model, the qualitative behavior of the time-dependent mean-square displacements and relaxation functions being rather similar to the latter. For the model without obstacles, it is shown that the present continuum model can be approximately mapped on the lattice bond fluctuation model by a suitable rescaling of chain length and volume fraction. But the distinctive advantage of the present model is that it can be applied easily to random media (described by randomly placed rigid obstacles), without the severe ergodicity problems (locked-in configurations) arising in lattice models for such systems. It is shown that static properties of the chains stay nearly unaffected by the obstacles, while the chain motions are considerably slowed down in this frozen environment.

Recent developments in SHADOW

SHADOW is the ray-tracing program of choice for the synchrotron radiation community. The program can raytrace essentially any x-ray optical system and predict image shapes and intensities with great accuracy. Several new extensions have been included. The optical database has been extended to the 10-eV region by inclusion of the new data from the Center for X-ray Optics, Lawrence Berkeley Lab. Two major physical models have been added to the code; the first being a surface roughness model to add to the error surface option. The second addition is to the crystal model. It now includes an asymmetric crystal, a model of a mosaic crystal, and a model for the Johannson case of a figured, bent crystal. Until now, SHADOW has operated under Digital Equipment Corporation’s (DEC) VMS operating system (VMS). The advent of powerful RISC workstations has prompted a porting to the UNIX environment, opening a multiplatform operability. So far, the code has been validated for Ultrix (DEC) and is undergoing beta testing for Sun operating system and IBM Corporation’s AIX operating system. Porting to a 386/486 platform is also considered. Finally, an optimization algorithm based on a combination of the Simplex and simulated annealing is being implemented.

Preface

The IBM Journal of Research and Development has committed this issue to a description of the architecture and machine designo f the IBM RISC System/6000* processor, along with some of the innovations in the implementation of the AIX* operating system, Version 3, that is used with that processor. Written by the system designers, the articles presented here explain in detail many of the advances in architecture, machine organization, hardware design, and the management of instructions, programs, and storage facilities that characterize this new family of superscalar RISC workstations and servers.

The IBM RISC System/6000 processor: Hardware overview

A highly concurrent superscalar second-generation family of RISC workstations and servers is described. The RISC System/6000 family is based on the new IBM POWER (performance optimization with enhanced RISC) architecture; the hardware implementation takes advantage of this powerful RISC architecture and employs sophisticated design techniques to achieve a short cycle time and a low cycles-per-instruction (CPI) ratio. The RS/6000 CPU features multiple-instruction dispatch, multiple functional units that operate concurrently, separate instruction and data caches, and zero-cycle branches. In this superscalar implementation, at a given cycle the equivalent of five operations can be executed simultaneously ( a branch, a condition-register operation, and a floating-point multiply-add).

DMA considerations on RISC workstations

article DMA considerations on RISC workstations Share on Author: R. Cousins Department Manager, Workstation Development, Data General Corporation Department Manager, Workstation Development, Data General CorporationView Profile Authors Info & Claims ACM SIGARCH Computer Architecture NewsVolume 17Issue 5Sep. 1989 pp 16–23https://doi.org/10.1145/71302.71304Online:01 September 1989Publication History 0citation205DownloadsMetricsTotal Citations0Total Downloads205Last 12 Months2Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access