As an initial demonstration of the parallelobject-orientedenvironment and toolkit (POET) the authors have investigated a probability density function (PDF) code for a jet flame diffusion problem. The PDF algorithm i...
详细信息
As an initial demonstration of the parallelobject-orientedenvironment and toolkit (POET) the authors have investigated a probability density function (PDF) code for a jet flame diffusion problem. The PDF algorithm involves mostly Monte Carlo calculations and is highly amenable to an efficient parallel implementation. POET is used to partition the algorithmic portions of the code from the application-specific code. POET was designed to provide a mechanism that permits both the computational and the physical scientist to contribute their expertise to an integrated scalable application through the use of a well-defined object-oriented interface. Through this interface, direct integration of existing application codes is implemented without affecting the parallel computation algorithms. Thus, the combustion scientist need only be concerned with application-specific code. The results of interfacing a PDF jet flame diffusion model with POET have generated the first investigation of a turbulent nonpremixed flame with a full chemical mechanism.< >
The proceedings contain 32 papers. The special focus in this conference is on Design and Implementation of Symbolic Computation Systems. The topics include: Proving the correctness of algebraic implementations by the ...
ISBN:
(纸本)9783540572350
The proceedings contain 32 papers. The special focus in this conference is on Design and Implementation of Symbolic Computation Systems. The topics include: Proving the correctness of algebraic implementations by the ISAR system;sketching concepts and computational model of TROLL light;analogical type theory;improving the multiprecision euclidean algorithm;storage allocation for the karatsuba integer multiplication algorithm;process scheduling in DSC and the large sparse linear systems challenge;a parameterized domain of computation system with support for signature functions;on coherence in computer algebra;subtyping inheritance in languages for symbolic computation systems;a unified-algebra-based specification language for symbolic computing;an order-sorted approach to algebraic computation;variant handling, inheritance and composition in the objectmath computer algebra environment;matching and unification for the object-oriented symbolic computation system algbench;a type system for computer algebra;decision procedures for set/hyperset contexts;reasoning with contexts;a graphic framework for combining theorem provers and editing proofs for different logics;dynamic term rewriting calculus and its application to inductive equational reasoning;the aquarius prover;the design of the SACLIB/PACLIB kernels;the weyl computer algebra substrate;on the uniform representation of mathematical data structures;compact delivery support for REDUCE;a portable language-driven tool for mathematical surfaces visualization;computing in construction-defined domains;extending algbench with a type system;modeling finite fields with mathematica and an enhanced sequent calculus for reasoning in a given domain.
In today's workstation based environment, applications such as design databases, multimedia databases, and knowledge bases do not fit well into the relational data processing framework. The object-oriented data mo...
详细信息
In today's workstation based environment, applications such as design databases, multimedia databases, and knowledge bases do not fit well into the relational data processing framework. The object-oriented data model has been proposed to model and process such complex databases. Due to the nature of the supported applications, object-oriented database systems need efficient mechanisms for the retrieval of complex objects and the navigation along the semantic links among objects. object clustering and buffering have been suggested as efficient mechanisms for the retrieval of complex objects. However, to improve the efficiency of the aforementioned operations, one has to look at the recent advances in storage technology. This paper is an attempt to investigate the feasibility of using parallel disks for object-oriented databases. It analyzes the conceptual changes needed to map the clustering and buffering schemes proposed on the new underlying architecture. The simulation and performance evaluation of the proposed leveled-clustering and mapping schemes utilizing parallel I/O disks are presented and analyzed.< >
The interpretation of remote sensing images challenges the image processing community not only by a variety of difficulties which are to be solved during the creation of an application but also by the computational ef...
详细信息
The interpretation of remote sensing images challenges the image processing community not only by a variety of difficulties which are to be solved during the creation of an application but also by the computational effort required to run it. The solution to overcome the latter restriction is the use of parallel computers. However, programming such machines is another challenge. The present paper aims towards the design and implementation of powerful tools allowing the user to generate a remote sensing application even on images obtained from a variety of sensors, by icon manipulation. A graph of icons is parsed and a source code free of errors is produced in objective C for an AIS-3500 massively parallel computer. The environment was used to generate an "Automated Road Detection" system running on the above parallel computer. The system was tested on images from Ottawa area.< >
Most distributed computing systems are required to be reliable, adaptable, and expandable to dynamically changing environments. A type of system with online maintainability, expandability, and testability and fault to...
详细信息
Most distributed computing systems are required to be reliable, adaptable, and expandable to dynamically changing environments. A type of system with online maintainability, expandability, and testability and fault tolerant capability, called an autonomous decentralized system (ADS), is discussed. Although the hardware and system software of ADSs support the online properties, systematic development methodologies for ADSs are needed. An object-oriented approach to application software development for ADSs is presented. Achieving online expandability of the application software and the software design phase are emphasized.< >
In programming massively parallel computers, it is often necessary to have sets of processes cooperate in performing certain computations and communications. Most run-time libraries require that such sets of processes...
详细信息
In programming massively parallel computers, it is often necessary to have sets of processes cooperate in performing certain computations and communications. Most run-time libraries require that such sets of processes be explicitly specified in the program. In the Venus run-time communication library however, a Process Group abstraction is used to enable implicit coordination of and communication over dynamically determined sets of processes. The Process Groups mechanism in Venus offers an object-oriented approach for handling sets of processes and enhances the debugging and monitoring of programs. The authors describe the Process Groups mechanism in Venus, illustrate its use on the class of N-body problems, and outline some of the data structures and algorithms used to implement this mechanism in Venus.< >
The purpose of this research was to implement the simulation of specific queuing systems on the Encore Multimax computer system. The environment partitioning approach to distributed simulation was used to implement pa...
详细信息
The purpose of this research was to implement the simulation of specific queuing systems on the Encore Multimax computer system. The environment partitioning approach to distributed simulation was used to implement parallel simulations of three benchmark queuing models to show performance improvement. The execution times obtained for the queuing systems were better with environment partitioning than without. However, this only occurred when the objects to implement the simulation were tightly coupled and were not hiding a lot of information. objectoriented techniques were not completely applicable because the time spent in message passing between processors was large compared to the time spent in a processor's local computation. While speedups of up to 2.0 were obtained, this is far smaller than prior simulation studies have suggested are possible for a computer with faster inter-processor communication. Thus, the Multimax was not a suitable machine for distributed simulation employing objectoriented design and environment partitioning.
The proceedings contain 25 papers. The special focus in this conference is on management, real-time, and compiler validation. The topics include: Progress of Ada as an international standard: ISO/IEC JTC1/SC22 WG9 Ada...
ISBN:
(纸本)9783540568025
The proceedings contain 25 papers. The special focus in this conference is on management, real-time, and compiler validation. The topics include: Progress of Ada as an international standard: ISO/IEC JTC1/SC22 WG9 Ada status);graphics development in Ada;the olympus attitude and orbital control system: a case study in hard real-time system design and implementation;information systems support in Ada 9X;the impact of Ada on mis applications;SAMeDL - a pilot project;applying Ada 9X to two real-time applications: a case study;an efficient compiler validation method for Ada 9x;avoiding anomalies in inheritance schemes;object-oriented design of an air defence simulator;use and abuse of exceptions - 12 guidelines for proper exception handling;error-prone exception handling in large Ada systems;structuring iterators to encourage reuse;tool for computing cohesion and coupling in Ada programs: DIANA dependent part;data compatibility in a heterogeneous processor environment;an operational computer aided software environment: ILIADE;performance expectations on Ada programs;impact of an Ada run-time system's performance characteristics on scheduling models;distributed run-time systems, a protocol for Ada;certification of Ada real-time executives for safety critical applications;performance evaluation of parallel Ada programs using an experimental multiprocessor;adam, an Ada simulation toolkit;real and virtual interrupt support: the mapping of a carts feature to two different architectures;toward a secondary standard for hard real-time Ada: the real-time rapporteur group (ISO/JTC1/SC22/WG9/RRG) JTC 1.22.35.
A new kind of distributed system service called availability management service is introduced. It is responsible for ensuring that the critical services of a distributed system remain continuously available to users d...
详细信息
A new kind of distributed system service called availability management service is introduced. It is responsible for ensuring that the critical services of a distributed system remain continuously available to users despite arbitrary numbers of concurrent node removals and node restarts caused by failures, maintenance, and growth. The description of many details involved in a realistic design is sacrificed to make the underlying concepts easily understandable. To this end, the availability management service is designed on top of an easy-to-understand synchronous communication environment, and only one kind of service availability policy is considered. It is indicated how the initial specification and design can be extended to deal with asynchronous systems subject to partitioning as well as with other kinds of service availability policies.< >
暂无评论