检索结果-内蒙古大学图书馆

A semi-automatic multiple-strategy approach to mapping tree-structured symbolic processing programs

JOURNAL OF SYMBOLIC COMPUTATION 1996年第4-6期21卷 615-634页

作者： Sodan, A GMD Institute for Computer Architecture and Software Technology Germany

Symbolic applications such as expert systems, theorem provers, and computer algebra exhibit dynamic, tree-structured behavior with respect to control and data structures. This is why it is difficult to parallelize a program and get it running efficiently on a parallel computer, especially one with distributed memory. This paper introduces a semi-automatic mapping environment providing a set of support tools, intended for application to large, real-life programs. Mapping can perform adaptive granularity control, dynamic load balancing, and scheduling on parallel programs with dynamic data and control behavior, providing a set of strategies for all components. A set of mapping rules are extracted, describing when which strategy is appropriate. The approach systematically selects and configures its strategies to suit the characteristics of the application and is thus superior to a universal heuristic. (C) 1996 Academic Press Limited

关键词：

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

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

THE SUPRENUM SUPERcomputer - GOALS, ACHIEVEMENTS, AND LESSONS LEARNED

引用

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

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

Formalization of autonomous dynamic reconfiguration in distributed constraint satisfaction

引用

Fundamenta Informaticae 2000年第1期43卷 129-151页

作者： Hannebauer, Markus Planning and Optimization Laboratory Research Institute for Computer Architecture and Software Technology (FIRST) GMD — German National Research Center for Information Technology eMail: hannebau@first.gmd.de

Several interesting practical problems in process control, planning and scheduling can be expressed and solved using the model of constraint satisfaction problems. At least four drawbacks of this classical model directly relate to areas of distribution: complexity, scalability, privacy and robustness. Hence, research on distributed constraint satisfaction problems is a new direction in the area of multi-agent systems. A typical engineering task in distributed constraint satisfaction is the design of the distribution itself. A careful look at this task reveals that the design of distribution is critical to the quality and efficiency of the problem solving process and is itself an optimization problem. In this article we formalize different variants of this configuration problem and prove them to be all at least N P-complete. For solving these problems, we present two local operators, agent melting and agent splitting, that can be combined to allow for an autonomous and dynamic reconfiguration of the organizational structure of the problem-solving agents. We prove sequences of these operators to be sufficient for solving any given configuration problem. We also briefly describe what practical steps are necessary to exploit the rather theoretical result of the proof in realistic applications.

关键词： multi-agent systems distributed constraint satisfaction autonomous dynamic reconfiguration partitioning agent melting agent splitting

来源：评论

学校读者我要写书评

暂无评论

ParLisp - Parallel symbolic processing with lisp on the distributed memory machine MANNA

ParLisp - Parallel symbolic processing with lisp on the dist...

引用

International Conference and Exhibition on High-Performance Computing and Networking, HPCN 1994

作者： Sedan, Angela Bi, Hua GMD Institute for Computer Architecture and Software Technology Germany

ISBN: (纸本)9783540579816

The parLisp system consists of a parallel run-time system and a set of tools for parallel symbolic processing with Lisp on the distributed memory parallel machine MANNA. The parallel run-time system provides and implements efficiently language features and mechanisms for expressing parallelism appropriately and for handling the data access problem by either explicit copying or by Virtual Shared Memory. A set of tools for detection of parallelism, mapping, profiling and visualization supports the process of getting efficient parallel symbolic applications. © 1994, Springer Verlag. All rights reserved.

关键词： Memory architecture

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

H2-MARL: Multi-Agent Reinforcement Learning for Pareto Optimality in Hospital Capacity Strain and Human Mobility during Epidemic

arXiv

引用

arXiv 2025年

作者： Luo, Xueting Deng, Hao Yang, Jihong Shen, Yao Guo, Huanhuan Sun, Zhiyuan Liu, Mingqing Wei, Jiming Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai201804 China China Land Surveying and Planning Institute Beijing100035 China College of Architecture and Urban Planning Tongji University Shanghai200092 China Chongqing Institute of Planning and Natural Resources Investigation and Monitoring Chongqing401121 China Li-Fi Research and Development Centre University of Cambridge CambridgeCB3 0FA United Kingdom Guangdong Urban-rural Planning and Design Research Institute Technology Group Co. Ltd. Guangzhou510290 China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai201804 China

The necessity of achieving an effective balance between minimizing the losses associated with restricting human mobility and ensuring hospital capacity has gained significant attention in the aftermath of COVID-19. Reinforcement learning (RL)-based strategies for human mobility management have recently advanced in addressing the dynamic evolution of cities and epidemics;however, they still face challenges in achieving coordinated control at the township level and adapting to cities of varying scales. To address the above issues, we propose a multi-agent RL approach that achieves Pareto optimality in managing hospital capacity and human mobility (H2-MARL), applicable across cities of different scales. We first develop a township-level infection model with online-updatable parameters to simulate disease transmission and construct a city-wide dynamic spatiotemporal epidemic simulator. On this basis, H2-MARL is designed to treat each division as an agent, with a trade-off dual-objective reward function formulated and an experience replay buffer enriched with expert knowledge built. To evaluate the effectiveness of the model, we construct a township-level human mobility dataset containing over one billion records from four representative cities of varying scales. Extensive experiments demonstrate that H2-MARL has the optimal dual-objective trade-off capability, which can minimize hospital capacity strain while minimizing human mobility restriction loss. Meanwhile, the applicability of the proposed model to epidemic control in cities of varying scales is verified, which showcases its feasibility and versatility in practical applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

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

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：