The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We address the problem of estimating the average switching activity in combinational digital CMOS circuits under random input sequences. We have used a probabilistic approach and have given a distributed implementation using PVM. We make use of the Parker-McCluskey heuristic and use bit-vector representation of Signal Probability Expressions to arrive at an efficient implementation. Experimental results...
The advent of distributed computer systems with hundreds of processors has created the need for software tools for monitoring their resource usage and system status. In this paper, we describe the design, implementation, and performance of the BVIEW software tool for monitoring distributed systems. Our tool has been tested on a 64 node PC cluster running the Linux operating system. However, it could...
This paper describes a system that supports the specification of a large set of simulations and their organization and distributes execution over a PC's network under Windows 95 and NT. Our objective is two faced: maximize resources utilization of IBERDROLA and the possibility of starting experiments that require a high compute power. As an example, we will describe the work done in the ESPRIT project...
The project PROGRESS being under development at the Institute of Informatics Systems in Novosibirsk is outlined. The information subsystem TRANSFORM aimed at accumulating and processing of knowledge about optimizing and restructuring program transformations is considered. A three-phase networked query interface for information retrieval is discussed. The subsystem SFP intended to support supercomputing...
A COOL system based on superconductor Rapid Single-Flux-Quantum (RSFQ) technology is being developed at SUNY (Stony Brook, USA) within the framework of the Hybrid Technology MultiThreaded architecture (HTMT) project. The objective of the second phase of the project is the design study of a petaflops scale computer. We have found that a 0.8-μm RSFQ technology would make possible the implementation...
High performance computing increasingly utilizes loosely coupled clusters of commodity computers. Performance monitoring data on such platforms is traditionally performed by invasive message passing taps, and examined only after the run is complete. We present an alternative, designed to capitalize on the scalable nature of the platform. Lilith Lights is a non-invasive network and processor monitoring...
The high-performance algorithm of two-level parallelization for direct simulation Monte Carlo of unsteady flows has been described. The algorithm of parallel statistically independent runs is used on the first level of parallelization. The data parallelization corresponds to the second one. The problem of simulation of the inner atmosphere of a comet was used to study the speedup of the algorithm...
Staff scheduling is a complex problem encountered in almost all large businesses. Available manpower and skills must be deployed as effectively as possible, while being flexible enough to cope with the unexpected. This paper shows how high end PC technology in data-mining and simulation, as opposed to super-computing techniques, were applied to staff-scheduling in a large commercial organisation,...
A neural network based program has been developed to unfold lifetimes and amplitudes as well as lifetime distributions from positron spectra. The program is written in Fortran 90 and ported to two different shared memory systems, a Cray Origin 2000 using OpenMP, and a Cray 90 using autotasking. The performance has been examined by profiling tools and the program has been optimized. The achieved speedup...
The paper describes MPVisualizer (Message Passing Visualizer) a general purpose tool for the debugging of message passing parallel applications; its three components are the trace/replay mechanism, the graphical user interface and the central component, called visualization engine. The engine, which plays the main role during the replay phase, can be used with different message passing environments...
Dynamically trace scheduled VLIW (DTSVLIW) architectures can be used to implement machines that execute code of current RISC or CISC instruction set architectures in a VLIW fashion, delivering instruction level parallelism (ILP) with backward code compatibility. This paper presents the effect of multicycle instructions on the performance of a DTSVLIW architecture running the SPECint95 benchmarks.
The MAD environment is a toolset for debugging parallel message passing programs. In contrast to other existing tools and prototypes, where error detection facilities are implemented by combining sequential debuggers, MAD is designed as a top-down approach. The main interface for program analysis is the event graph display, a state-time diagram that shows process interaction. Based on this program...
The european ESPRIT project STRETCH is dedicated to the management of documents by their content. We present in this paper the high-performance developments and the programming support required by STRETCH indexing and retrieval processes.
Recent advances in hardware and networking have fueled the interest in distributed computing in general and in metacomputing frameworks in particular. Harness is an experimental metacomputing system based upon the principle of dynamic reconfigurability both in terms of the computers and networks that comprise the virtual machine, and in the services offered by the virtual machine itself. In this paper...
A new coordination model is constructed for distributed shared memory parallel programs. It exploits typing of shared resources and formal specification of a priori known synchonization constraints.
This paper addresses the problem of estimating the total execution time of a parallel program based on a domain decomposition strategy. We consider the situation where a single iteration on each processor can take two different execution times. We show that the total time depends on the topology of the interconnection network and provide a lower bound for the ring and the grid. The analysis...
This paper reports a study on the use of reflection as a methodology for expressing concurrent objects, i.e. actors, scheduling strategies. Reflection allows to separate at design time and compose at runtime the applicative program and the placement program, thus providing modularity, portability of applicative programs and reusability of scheduling ones.
In this paper we present a simplified version of heterogeneous metacomputing environments for specific applications, allowing ability to run jobs on remote systems without administration overhead connected with maintaining user accounts, and transparently for the real user. We present problems with developing distributed computing environments, the idea of the Virtual User Account on specialised application...
In this paper, we propose a data partitioning scheme for contentbased retrieval from a multimedia database using a heterogeneous cluster system. The proposed parallel unified model [6] was used to represent multimedia data. All types of multimedia data in the unified model are represented by k-dimensional(k-d) signals. Each dimension of k-d data is separated into small blocks and then formed into...
The main objective of the paper is to highlight the specific characteristics of an industrial supercomputing center, which would be established in Hungary (Budapest). The presented results and conclusions are based on the performed research-in the framework of a pre-feasibility study—required and supported by the National Committe for Technological Development Hungary (OMFB). The paper will describe...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.