检索结果-内蒙古大学图书馆

THE SUPRENUM SUPERcomputer - GOALS, ACHIEVEMENTS, AND LESSONS LEARNED

PARALLEL COMPUTING 1994年第10-11期20卷 1407-1425页

作者： GILOI, WK GMD Institute for Computer Architecture and Software Technology Rudower Chausses 5 D-12489 Berlin Germany

SUPRENUM is a highly parallel supercomputer for numerical applications. The 5-GFLOPS peak performance of the 256-node system made it the most powerful MIMD architecture of the 'first generation.' Each node is a complete, single-board vector machine with 20 Mflops peak performance (IEEE double precision). SUPRENUM is a distributed memory architecture, resulting in a highly scalable system that can be made fault-tolerant. Message passing is accelerated by dedicated communication hardware in each node. Array access is performed by an 'intelligent' DMA address generator. The SUPRENUM architecture was the first to be based on two-level interconnection structure, consisting of a number of clusters with each cluster consisting of a number of nodes. At the cluster level the nodes are interconnected by two very fast parallel buses. At the system level the clusters are interconnected by a torus structure consisting of serial ring buses. The nodes run under the proprietary, distributed PEACE operating system. Significant efforts were undertaken to make the system programmable, by providing a host of software tools, libraries, and application software packages. The paper discusses the rationale for the SUPRENUM architecture, the goals achieved, and the lessons learned.

关键词： DISTRIBUTED MEMORY architecture VECTOR NODES HIERARCHICAL INTERCONNECTION STRUCTURE DISTRIBUTED OPERATING SYSTEM PROGRAMMING PARADIGMS AND TOOLS

来源：评论

学校读者我要写书评

暂无评论

DSPNEXPRESS - A software PACKAGE FOR THE EFFICIENT SOLUTION OF DETERMINISTIC AND STOCHASTIC PETRI NETS

引用

PERFORMANCE EVALUATION 1995年第1期22卷 3-21页

作者： LINDEMANN, C GMD Institute for Computer Architecture and Software Technology (GMD-FIRST) Technical University of Berlin Rudower Chaussee 5 12489 Berlin Germany

This paper describes the analysis tool DSPNexpress which has been developed at the Technische Universitat Berlin since 1991. The development of DSPNexpress has been motivated by the lack of a powerful software package for the numerical solution of deterministic and stochastic Petri nets (DSPNs) and the complexity requirements imposed by evaluating memory consistency models for multicomputer systems. The development of DSPNexpress has gained by the author's experience with the version 1.4 of the software package GreatSPN. However, opposed to GreatSPN, the software architecture of DSPNexpress is particularly tailored to the numerical evaluation of DSPNs. Furthermore, DSPNexpress contains a graphical interface running under the X11 window system. To the best of the author's knowledge, DSPNexpress is the first software package which contains an efficient numerical algorithm for computing steady-state solutions of DSPns.

关键词： software PACKAGES FOR STOCHASTIC PETRI NETS NUMERICAL METHODS FOR TRANSIENT ANALYSIS OF MARKOV CHAINS PERFORMANCE AND DEPENDABILITY MODELING

来源：评论

学校读者我要写书评

暂无评论

Simulation of traffic-induced air pollution for mesoscale applications

引用

MATHEMATICS AND computerS IN SIMULATION 1997年第3-6期43卷 285-290页

作者： Sydow, A Lux, T Mieth, P Schafer, RP GMD Research Institute for Computer Architecture and Software Technology (GMD FIRST) Rudower Chaussee 5 D-12489 Berlin Germany

Recent investigations have shown that vehicular traffic is the main source for emissions leading to summer smog. A study of the impact of traffic emission on urban air quality requires a complex air-pollution simulation system. This paper presents results of the development and application of an air-pollution simulation system at gmd FIRST which aims at supporting users in government administration and industry with forecasting and operative decision-making as well as short- to long-term regional planning. The components of the simulation system are parallelly implemented simulation models for meteorology, transport and air chemistry, data bases for model input and simulation results, as well as a graphic user interface for spatial data visualization. In order to study the influence of traffic emissions, a traffic-flow and a traffic-emission model have been added to the simulation system. Results presented are from two recent applications in the regions of Berlin/Brandenburg and Munich (Germany). Further applications are in preparation.

关键词： computer simulation

来源：评论

学校读者我要写书评

暂无评论

PARALLEL SUPERcomputer architectureS AND THEIR PROGRAMMING-MODELS

引用

PARALLEL COMPUTING 1994年第10-11期20卷 1443-1470页

作者： GILOI, WK GMD Research Institute for Computer Architecture and Software Engineering (FIRST) Rudower Chaussee 5 12489 Berlin Germany

The paper presents a taxonomy of the existing forms of parallel computer architectures, based on the characteristics of the hardware architecture and the abstract machine layered upon it. The abstract machine reflects the programming models provided. The main classes of hardware architectures are: physically shared memory systems and distributed memory systems. Distributed memory systems may be remote memory access architectures or message passing architectures. The major forms of abstract machine architecture are: message passing systems and logically shared memory architectures. Three solutions for logically shared memory architectures are known (1) distributed shared memory architectures, (2) multi-threaded architectures, and (3) virtual shared memory architectures. All three types are discussed in detail under the aspects of performance, programmability, and scalability, and their corresponding programming paradigms are characterized. The implications of the three concepts on node architecture and the requirements of latency minimization or latency hiding are discussed and illustrated by examples taken from pioneering realizations of the three kinds of architecture such as DASH, *T, and MANNA.

关键词： MASSIVELY PARALLEL DISTRIBUTED MEMORY architectureS SHARED-MEMORY AND MESSAGE-PASSING PROGRAMMING MODELS DISTRIBUTED SHARED MEMORY architectureS VIRTUAL SHARED MEMORY architectureS DATA CONSISTENCY AND SYNCHRONIZATION PARALLELIZATION TOOLS, PARALLELIZING COMPILERS MORE ABSTRACT PROGRAMMING MODELS

来源：评论

学校读者我要写书评

暂无评论

Reducing domains for search in clp(Fd) and its application to job-shop scheduling 1st

Reducing domains for search in clp(Fd) and its application t...

引用

1st International Conference on Principles and Practice of Constraint Programming, CP 1995

作者： Goltz, Hans-Joachim Research Institute for Computer Architecture and Software Technology GMD-FIRST Rudower Chaussee 5 BerlinD-12489 Germany

ISBN: (纸本)3540602992

This paper describes a generalization of the "labelling" search strategy and its application to scheduling problems. The assignment of a value to the selected variable is replaced by reduction of the domain of the variable. This strategy can be applied for solving problems modelled in CLP(FD). We discuss the application of this domain-reducing strategy to the well-known problem of 10 x 10 job-shop scheduling. The computation results obtained using this strategy show its advantages. A good solution, coming to within 3% of the optimal solution, is generated in less than 1 second, using only a simple heuristics for variable selection and domain reduction. Compared with the standard strategy, the domain-reducing strategy exhibits more robustness with respect to the given planning horizon. Assuming that there is a choice of machines, a good solution can be generated with the same strategy, deviating from the optimal solution by less than 4%. Our experience has shown that the domain-reducing strategy is suitable as a basic search strategy for solving job-shop problems by means of CLP, allowing good (near-to-optimum) solutions to be computed fast. © Springer-Verlag Berlin Heidelberg 1995.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Lowering HPF procedure interface to a canonical representation 10th

引用

10th Annual International Workshop on Languages and Compilers for Parallel Computing, LCPC 1997

作者： Borowiec, Jan Veen, Arthur GMD FIRST Research Institute For Computer Architecture and Software Technology Rudower Chaussee 5 Berlin12489 Germany Parallel Computing Amsterdam Netherlands

ISBN: (纸本)3540644725

Handling the procedure interface in an HPF compiler is complex due to the many possible combinations of Fortran 90/HPF properties of an actual array argument and its associated dummy argument. This paper describes an algorithm that reduces this complexity by mapping all the combinations of properties to a small set of canonical Internal Representations. These internal representations as well as the necessary run-time descriptors are also described. The algorithm has been implemented in the commercial HPF compiler produced by the Prepare project. © 1998, Springer-Verlag. All rights reserved.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Parallel Simulation of Air Pollution Transport for Urban Decision Making

引用

IFAC Proceedings Volumes 1993年第2期26卷 391-394页

作者： A. Sydow M. Schmidt S. Unger T. Lux P. Mieth R.-P. Schäfer GMD - Research Institute for Computer Architecture and Software Technology Rudower Chaussee 5 (13.7) D-1199 Berlin Germany

A concept for an air pollution simulation environment to predict and manage smog situations is presented consisting of the necessary data bases, a mesoscale meteorological model, an air chemistry model, and decision support tools including result visualization. Simulation runs and scenario analyses of such numerically complex models take hours of computing time, even on today's supercomputers. Therefore a strategy for model decomposition and implementation on massively parallel computers is described. Simulation results are shown for an ozone smog situation in Berlin.

关键词： Modeling computer simulation air pollution parallel processing urban systems environmental engineering

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：