Modelling real-time applications based on resource reservations

This paper presents a strategy for the design of real-time applications relying on the resource-reservation paradigm, based on a new modelling element that describes the schedulable entities of the applications during the whole design cycle. A virtual view of this element is used first for evaluating a set of constraints that guarantee the application schedulability independently of the execution platform. Then, the element is viewed as a thread that receives the particular scheduling parameters required for a schedulable execution of the application in a specific platform. The purpose of the design process is to make both views compatible.     

MMM: a Web-based system for sharing statistical computing modules

This prototype method management system (MMM), implemented with Web technologies, supports distributed authoring and execution of computational software modules among an interdisciplinary group of developers and users. Heterogeneous data formats, programming languages, and computing platforms pose various challenges whenever researchers are sharing and combining software modules, especially when the collaboration occurs across different traditions of scientific computing. To meet these challenges, we designed and implemented MMM. MMM is a collection of middleware services to support the interaction between software users and developers, and to facilitate the sharing of software modules across heterogeneous networks. The system design follows the World Wide Web paradigm: developers (providers) install their modules on the network in a way that allows users (consumers) to access and execute them. A prototype is available on the Web     

A characterization of workflow management systems for extreme-scale applications

Automation of the execution of computational tasks is at the heart of improving scientific productivity. Over the last years, scientific workflows have been established as an important abstraction that captures data processing and computation of large and complex scientific applications. By allowing scientists to model and express entire data processing steps and their dependencies, workflow management systems relieve scientists from the details of an application and manage its execution on a computational infrastructure. As the resource requirements of today’s computational and data science applications that process vast amounts of data keep increasing, there is a compelling case for a new generation of advances in high-performance computing, commonly termed as extreme-scale computing, which will bring forth multiple challenges for the design of workflow applications and management systems. This paper presents a novel characterization of workflow management systems using features commonly associated with extreme-scale computing applications. We classify 15 popular workflow management systems in terms of workflow execution models, heterogeneous computing environments, and data access methods. The paper also surveys workflow applications and identifies gaps for future research on the road to extreme-scale workflows and management systems.     

A new intelligent system for senior executives to maintain remote control of their company

The mobile-enterprise concept has emerged as an innovation with the increasing use of personal digital assistant (PDA) on wireless data networks. To realize the concept, simply use the PDA to search for information is not enough, where an intelligent paradigm is required to deal with the request for information as well as the command execution in a distributed information system. This paper proposes a mobile-enterprise multi-agent paradigm (MMAP) which is an agent-based intelligent solution provider developed for small to medium enterprises (SMEs) in order to increase their flexibility and competitiveness in the market. The system is driven by intelligent software agents. Their design and prototype implementation are demonstrated in this paper.     

Four kinds of design thinking: From ideating to making,engaging, and criticizing

Design thinking is spreading extremely rapidly among organizations in terms of interest and practices. Far from being linked to the “form” of products, design thinking is accepted as a formal creative problem‐solving method with the intent to foster innovation. However, the spread of design thinking in practice has not been coupled with a similarly rapid and robust diffusion of its theoretical underpinnings. This paper aims to clarify the theoretical contribution of design thinking by identifying the practices that connote different interpretations of the paradigm. Moreover, we investigate the innovation challenges that the adoption of the design thinking paradigm aims to address. From an empirical perspective, through 47 case studies of consulting organizations that provide advisory services based on the design thinking paradigm in Italy, we identify four different interpretations of the paradigm characterized by different practices: creative problem solving, sprint execution, creative confidence, and innovation of meaning.     

B2B集成技术的体系结构

介绍了B2B集成技术的体系结构和概念上的模型，用来支持统一概念集成模型中并发的A2A和B2B集成。概念集成模型通过设计时仓库完成，集成模型作为元数据存储在设计时仓库。B2B集成技术的执行时范例完成实际的应用和贸易伙伴商务交易遵循编译的方法，根据存储在设计时仓库中的集成模型，执行器完成实际的集成实例。     

用于Hadoop2.x的MapReduce性能评估模型

基于MapReduce的程序被越来越多地应用于大型数据分析的应用中.Apache Hadoop是最常用的开源MapReduce模型之一.程序运行时间的缩短对于MapReduce程序以及所有数据处理应用而言至关重要,而能够准确估算MapReduce程序的执行时间是优化程序的重要环节.本文定义了一个在Hadoop2.x版本...     

Implementation of GAMMA on a Massively Parallel Computer

The GAMMA paradigm is recently proposed by Banatre and Metayer to describe the systematic construction of parallel programs without introducing artificial sequentiality.This paper presents two synchronous execution models for GAMMA and discusses how to implement them on MasPar MP-1,a massively data parallel computer.The results show that GAMMA paradign can be implemented very naturally on data parallel machines,and very high level language,such as GAMMA in which parallelism is left implicit,is suitable for specifying massively parallel applications.     

Distributed process creation within a shared data space framework

This paper describes the design and implementation of a remote process instantiation mechanism which is consistent with the Linda paradigm and semantics of the EVAL operation, and which uses shared data space as the medium for passing process and environment parameters. The motivation for such an implementation stems from our effort to rehost a uniprocessor version of the Linda computational system to a network of workstations. The baseline version of the Linda system relies on the semantics of the UNIX fork() system call to create processes and to pass the proper execution parameters to them. In creating a distributed version of the Linda environment, two major issues are addressed: (1) how to instantiate a remote process that knows where, among several possibilities, to begin its execution, and (2) how to communicate the proper run-time values of relevant variables to each new remote Linda process. Guiding our implementation was a desire to employ existing interprocess communication facilities, i.e. shared data space, to pass process creation and execution parameters.     

COMPLEX: an object-oriented logic programming system

The design and a prototypical implementation of COMPLEX, which is a logic-based system extended with concepts from the object-oriented paradigm and is intended as a tool for the development of knowledge-based applications, are described. The system supports a logic language, called Complex-Datalog (C-Datalog), enhanced by semantic constructs to provide facility for data abstraction. Its implementation is based on a bottom-up computational model that guarantees a fully declarative style of programming. However, the user is also given the possibility of running a query using a top-down model of computation. Efficiency of execution is the result of the integration of different novel technologies for the compilation and the execution of queries     

Execution system for distributed business processes in a virtual enterprise

New cooperative approaches for manufacturing and service industries, as represented by the virtual enterprise paradigm, are enabled by the recent advances in communication technologies, computer networks, and logistics. The implantation of this paradigm requires the design and development of a flexible execution environment to support the distributed business processes that materialize the cooperation in a network of enterprises. A configurable architecture for such execution system is proposed focusing the support for multi-level process coordination. A set of examples to illustrate the adopted concepts and developed tools are discussed.     

Metadata for Managing Grid Resources in Data Mining Applications

The Grid is an infrastructure for resource sharing and coordinated use of those resources in dynamic heterogeneous distributed environments. The effective use of a Grid requires the definition of metadata for managing the heterogeneity of involved resources that include computers, data, network facilities, and software tools provided by different organizations. Metadata management becomes a key issue when complex applications, such as data-intensive simulations and data mining applications, are executed on a Grid. This paper discusses metadata models for heterogeneous resource management in Grid-based data mining applications. In particular, it discusses how resources are represented and managed in the Knowledge Grid, a framework for Grid-enabled distributed data mining. The paper illustrates how XML-based metadata is used to describe data mining tools, data sources, mining models, and execution plans, and how metadata is used for the design and execution of distributed knowledge discovery applications on Grids.     

Distributed control parallelism in multidisciplinary aircraft design

Multidisciplinary design optimization (MDO) for large-scale engineering problems poses many challenges (e.g. the design of an efficient concurrent paradigm for global optimization based on disciplinary analyses, expensive computations over vast data sets, etc.). This work focuses on the application of distributed schemes for massively parallel architectures to MDO problems, as a tool for reducing computation time and solving larger problems. The specific problem considered here is configuration optimization of a high speed civil transport (HSCT), and the efficient parallelization of the embedded paradigm for reasonable design space identification. Two distributed dynamic load balancing techniques (random polling and global round robin with message combining) and two necessary termination detection schemes (global task count and token passing) were implemented and evaluated in terms of effectiveness and scalability to large problem sizes and a thousand processors. The effect of certain parameters on execution time was also inspected. Empirical results demonstrated stable performance and effectiveness for all schemes, and the parametric study showed that the selected algorithmic parameters have a negligible effect on performance. Copyright © 1999 John Wiley & Sons, Ltd.     

A Partitioning-Independent Paradigm for Nested Data Parallelism

A generalization of the data parallel model has been proposed by Blelloch which permits the nesting of data parallel operators to specify parallel computation across nested and irregular data structures. In this paper we consider the costs of supporting the general model of nested data parallelism, analyzing the requirements such a model places upon an underlying model of execution. We propose a new multi-node execution model which meets the needs of the paradigm and is additionally generic in the partitioning of data aggregates within the system. The basis for our execution model is an abstract machine based upon elementary notions of nodal multi-threading. We demonstrate the utility of our proposal by providing a full definition for a simple nestable one-dimensional data parallel operator. We discuss the applicability of our design to existing multi-processor machines, illustrating performance statistics gathered from a prototype system we have constructed on the Thinking Machines CM-5.     

RTC: Language support for real-time concurrency

This paper presents a model and language constructs for expressing timing and concurrency requirements in distributed real-time programs. Our approach combines an abstract data type paradigm for the specification of shared resources and a distributed transaction-based paradigm for the specification of application processes. Resources provide abstract views of shared system entities, such as devices and data structures. Each resource has a state and defines a set ofactions that can be invoked by processes to examine or change its state. A resource also specifies scheduling constraints on the execution of its actions to ensure its consistency. Processes access resources by invoking actions and by expressing precedence, execution and timing constraints on action invocations. The implementation of our language constructs and the use of this system to control the simulation of a distributed robotics application is also described.This work is supported in part by the following grants: ARO DAAG-29-84-k-0061, ONR N000014-89-J-1131, and NSF CCR90-14621.     

CAD Framework中基于知识的设计流管理

设计流管理是ＣＡＤ Ｆｒａｍｅｗｏｒｋ（框架结构）中一个新的研究领域。本文在给出与设计流有关的基本概念的基础上，采用结构约束和数据约束的方法实现对设计流的知识表示，并通过设计经验的获取途径，进一步的知识生成以及设计流的执行，一致性的处理和设计流的评估，详细讨论ＣＡＤ Ｆｒａｍｅｗｏｒｋ中基于知识的设计流管理。文中还给出了相应的设计流管理系统的总体设计。     

GAMESH: A grid architecture for scalable monitoring and enhanced dependable job scheduling

Grid computing is a largely adopted paradigm to federate geographically distributed data centers. Due to their size and complexity, grid systems are often affected by failures that may hinder the correct and timely execution of jobs, thus causing a non-negligible waste of computing resources. Despite the relevance of the problem, state-of-the-art management solutions for grid systems usually neglect the identification and handling of failures at runtime. Among the primary goals to be considered, we claim the need for novel approaches capable to achieve the objectives of scalable integration with efficient monitoring solutions and of fitting large and geographically distributed systems, where dynamic and configurable tradeoffs between overhead and targeted granularity are necessary. This paper proposes GAMESH, a Grid Architecture for scalable Monitoring and Enhanced dependable job ScHeduling. GAMESH is conceived as a completely distributed and highly efficient management infrastructure, concentrating on two crucial aspects for large-scale and multi-domain grid environments: (i) the scalable dissemination of monitoring data and (ii) the troubleshooting of job execution failures. GAMESH has been implemented and tested in a real deployment encompassing geographically distributed data centers across Europe. Experimental results show that GAMESH (i) enables the collection of measurements of both computing resources and conditions of task scheduling at geographically sparse sites, while imposing a limited overhead on the entire infrastructure, and (ii) provides a failure-aware scheduler able to improve the overall system performance, even in the presence of failures, by coordinating local job schedulers at multiple domains.     

面向资源管理的DFMS模型研究

针对大规模协同设计流程管理系统的需求，提出一种面向资源管理的DFMS模型。该模型以资源的优化调度、任务执行的动态监控、全局目标的强制实施、冲突的先期避免和后期消解、类单机协同工作环境的构造来获得设计效率和设计质量的提高，从而更容易拟合设计活动的特点，使设计流程管理系统和CAD系统相对独立，具有通用性、健壮性、交互性、灵活性等特点。     

Improving communication latency with the write-only architecture

This paper introduces a novel execution paradigm called the Write-Only Architecture (WOA) that reduces communication latency overheads by up to a factor of five over previous methods. The WOA writes data through distributed control flow logic rather than using a read–write paradigm or a centralised message hub which allows tasks to be partitioned at a fine-grained level without suffering from excessive communication overheads on distributed systems. In this paper we provide formal assignment results for software benchmarks partitioned using the WOA and previous execution paradigms for distributed heterogeneous architectures along with bounds and complexity information to demonstrate the robust performance improvements possible with the WOA.     

MPI for Big Data: New tricks for an old dog

The processing of massive amounts of data on clusters with finite amount of memory has become an important problem facing the parallel/distributed computing community. While MapReduce-style technologies provide an effective means for addressing various problems that fit within the MapReduce paradigm, there are many classes of problems for which this paradigm is ill-suited. In this paper we present a runtime system for traditional MPI programs that enables the efficient and transparent out-of-core execution of distributed-memory parallel programs. This system, called BDMPI,¹ leverages the semantics of MPI’s API to orchestrate the execution of a large number of MPI processes on much fewer compute nodes, so that the running processes maximize the amount of computation that they perform with the data fetched from the disk. BDMPI enables the development of efficient out-of-core parallel distributed memory codes without the high engineering and algorithmic complexities associated with multiple levels of blocking. BDMPI achieves significantly better performance than existing technologies on a single node as well as on a small cluster, and performs within 30% of optimized out-of-core implementations.