检索结果-内蒙古大学图书馆

9th Workshop on parallel/High-Performance Object-Oriented Scientific Computing, POOSC'10, at the ACM conference on Systems, programming, Languages and Applications: Software for Humanity, SPLASH

作者： Ostlund, Per Stavaker, Kristian Fritzson, Peter Department of Computer and Information Science Linkoping University SE-58183 Linkoping Sweden

ISBN: (纸本)9781450305464

Our contributions with this work are methods and a prototype implementation for compiling and executing a limited set of equation-based mathematical models (written in the object-oriented equation-based modeling language Modelica) on CUDA-enabled GPUs. We look at methods of finding parallelism in Modelica models, that can be used on the massively parallel CUDA architecture. The methods have been implemented in a new back-end module of the OpenModelica compiler (an open-source Modelica compiler). This paper shows that it is possible to automatically generate simulation code for pure continuous-time models that can be reduced to an ordinary differential equation system without algebraic loops and where the initial values of all variables and parameters are known at compile time. It is possible to get some speedup compared with simulation on a single CPU core, a (approximated) relative speedup of 4.6 was for instance obtained for one model. © 2010 ACM.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Compiler Techniques for massively Scalable Implicit Task parallelism 14

Compiler Techniques for Massively Scalable Implicit Task Par...

引用

International conference on High Performance Computing, Networking, Storage and Analysis

作者： Armstrong, Timothy G. Wozniak, Justin M. Wilde, Michael Foster, Ian T. Univ Chicago Dept Comp Sci Chicago IL 60637 USA Argonne Natl Lab Math & Comp Sci Div Argonne IL 60439 USA Univ Chicago Computat Inst Chicago IL 60637 USA Argonne Natl Lab Chicago IL USA

ISBN: (纸本)9781479955008

Swift/T is a high-level language for writing concise, deterministic scripts that compose serial or parallel codes implemented in lower-level programming models into large-scale parallel applications. It executes using a data-driven task parallel execution model that is capable of orchestrating millions of concurrently executing asynchronous tasks on homogeneous or heterogeneous resources. Producing code that executes efficiently at this scale requires sophisticated compiler transformations: poorly optimized code inhibits scaling with excessive synchronization and communication. We present a comprehensive set of compiler techniques for data-driven task parallelism, including novel compiler optimizations and intermediate representations. We report application benchmark studies, including unbalanced tree search and simulated annealing, and demonstrate that our techniques greatly reduce communication overhead and enable extreme scalability, distributing up to 612 million dynamically load balanced tasks per second at scales of up to 262,144 cores without explicit parallelism, synchronization, or load balancing in application code.

关键词： parallel scripting Swift High-performance computing Compiler optimization Data-flow Execution models programming models

来源：评论

学校读者我要写书评

暂无评论

MODELING INTERMEDIATE TESTS FOR FAULT-TOLERANT MULTICHIP-MODULE SYSTEMS

引用

IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY PART B-ADVANCED PACKAGING 1995年第3期18卷 448-455页

作者： KIM, S LOMBARDI, F Department of Computer Science Texas A and M University College Station TX USA

This paper presents analytical models for evaluating intermediate tests for yield enhancement and quality assurance of systems manufactured using fault-tolerant multichip modules (MCM's) for massively parallel computing (MPG), In the proposed approaches, we employ both a novel Markov model and a so called working-test-set to compute the yield, Unlike a previous method [1] which utilizes a binomial distribution, our scheme can employ intermediate tests to meet MCM quality requirements effectively. Several strategies for appropriately testing fault-tolerant MCM's have been proposed, but little analytical evaluation has been performed, In this paper, it is shown that an efficient test strategy with a modest level of redundancy may exist to achieve virtually 100% first-pass MCM yield for a particular system, We note that a yield-analysis model employing the LRTWS (Least Recently Tested in WS) test strategy proposed in this paper may provide a very good figure of merit due to its cost, delivery, number of tests and reliability benefits for current technology, Extensive parametric results for the analysis are provided to show that our approach can be applied to calculate the overall yield for fault-tolerant MCM's more accurately and efficiently, thereby improving upon the reliability and quality of the entire system.

关键词： Fault tolerance Multichip modules System testing Fault tolerant systems Analytical models Quality assurance Pulp manufacturing Virtual manufacturing parallel processing Performance analysis

来源：评论

学校读者我要写书评

暂无评论

MPI-2: standards beyond the message-passing model

MPI-2: standards beyond the message-passing model

引用

working conference on massively parallel programming models

作者： E. Lusk Mathematics and Computer Science Division Argonne National Laboratory Argonne IL USA

The MPI (Message-Passing Interface) Standard has been successful in its goal of promoting portable parallel programming for both application writers and library implementors. MPI-I confined itself to the well-known and understood message-passing model, in which a fixed number of processes with separate address spaces communicate only though cooperative operations such as send/receive or collective operations such as broadcast and reduce. In a second round of activity, the MPI Forum has recently concluded work on the MPI-2 Standard, which extends MPI beyond the message-passing programming model in a number of ways, including dynamic process management, one-sided operations, and some shared-memory operations. The message-passing model has also been used in MPI-2 as a model for parallel I/O. This paper describes the salient features of the MPI-2 Standard with special emphasis on the programming model that results from these extensions to the message-passing model.

关键词： Dynamic programming parallel programming Standardization Application software Libraries Mathematics Computer science Laboratories Broadcasting Communication standards

来源：评论

学校读者我要写书评

暂无评论

Aspects of the compilation of nested parallel imperative languages

Aspects of the compilation of nested parallel imperative lan...

引用

working conference on massively parallel programming models

作者： W. Pfannenstiel M. Dahm M.M.T. Chakravarty S. Jahnichen G. Keller F.-W. Schroer M. Simons Technical University Berlin Berlin Germany Fu Berlin Germany University of Tsukuba Japan GMD FIRST Germany

We report on our experiences with the implementation of the imperative nested parallel language V. We give an overview of the compiler and a description of its building blocks and their interplay. We show how functional and imperative constructs such as control structures and pointers are handled by transformation rules. We justify additional restrictions that had to be placed on side effects and imperative constructs and were not initially thought to be necessary.

关键词： parallel languages Data structures Concurrent computing Automatic control

来源：评论

学校读者我要写书评

暂无评论

Finite Element based Structural Optimization using Object-Oriented parallel programming

Finite Element based Structural Optimization using Object-Or...

引用

2nd International conference on parallel, Distributed, Grid and Cloud Computing for Engineering

作者： Masching, H. Fischer, M. Firl, M. Bletzinger, K. -U. Tech Univ Munich Chair Struct Anal D-80290 Munich Germany

ISBN: (纸本)9781905088423

This contribution presents an MPI-based parallel computational framework for simulation and gradient-based structural optimization of geometrically nonlinear and large-scale structural finite element models. The field of computational structural analysis is gaining more and more importance in product design. In order to obtain an impression about possible approaches of design improvement already in an early planning phase, an efficient optimization tool is desired that requires only few modelling effort. This demand can be satisfied by a combined analysis and optimization tool working on the same model. To this purpose the finite element based optimization method is an excellent approach, leading to the highest possible diversity within the optimization process.

关键词： structural optimization finite element based optimization parameter-free optimization parallel programming object-oriented programming finite element method C plus

来源：评论

学校读者我要写书评

暂无评论

The challenges of efficient code-generation for massively parallel architectures

The challenges of efficient code-generation for massively pa...

引用

11th Asia-Pacific conference on Advances in Computer Systems Architecture

作者： McGuiness, Jason M. Egan, Colin Christianson, Bruce Gao, Guang Univ Hertfordshire Dept Compiler Technol & Comp Architecture Hatfield AL10 9AB Herts England Univ Delaware CAPSL Newark DE 19716 USA

ISBN: (纸本)3540400567

Overcoming the memory wall [15] may be achieved by increasing the bandwidth and reducing the latency of the processor to memory connection, for example by implementing Cellular architectures, such as the IBM Cyclops. Such massively parallel architectures have sophisticated memory models. In this paper we used DIMES (the Delaware Iterative Multiprocessor Emulation System), developed by CAPSL at the University of Delaware, as a hardware evaluation tool for cellular architectures. The authors contend that there is an open question regarding the potential, ideal approach to parallelism from the programmer's perspective. For example, at language-level such as UPC or HPF, or using trace-scheduling, or at a library-level, for example OpenMP or POSIX-threads. To investigate this, we have chosen to use a threaded Mandelbrot-set generator with a work-stealing algorithm to evaluate the DIMES cthread programming model for writing a simple multi-threaded program.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

A parallel programming model for irregular dynamic neural networks

A parallel programming model for irregular dynamic neural ne...

引用

working conference on massively parallel programming models

作者： L. Prechelt Fakultat fur Informatik Universitat Karlsruhe Karlsruhe Germany

The compilation of high-level programming languages for parallel machines faces two challenges: maximizing data/process locality and balancing load. No solutions for the general case are known that solve both problems at once. The present paper describes a programming model that allows to solve both problems for the special case of neural network learning algorithms, even for irregular networks with dynamically changing topology (constructive neural algorithms). The model is based on the observation that such algorithms predominantly execute local operations (on nodes and connections of the network), reductions, and broadcasts. The model is concretized in an object-centered procedural language called CuPit. The language is completely abstract: No aspects of the parallel implementation such as number of processors, data distribution, process distribution, execution model etc. are visible in user programs. The compiler can derive most information relevant for the generation of efficient code from unannotated source code. Therefore, CuPit programs are efficiently portable. A compiler for CuPit has been built for the MasPar MP-1/MP-2 using compilation techniques that can also be applied to most other parallel machines. The paper shortly presents the main ideas of the techniques used and results obtained by the various optimizations.

关键词： parallel programming Dynamic programming Neural networks Network topology Computer networks Computer languages parallel machines Broadcasting Program processors Yarn

来源：评论

学校读者我要写书评

暂无评论

A parallel program execution model supporting modular software construction

A parallel program execution model supporting modular softwa...

引用

working conference on massively parallel programming models

作者： J.B. Dennis Laboratory for Computer Science Massachusetts Institute of Technology Cambridge MA USA

A watershed is near in the architecture of computer systems. There is overwhelming demand for systems that support a universal format for computer programs and software components so users may benefit from their use on a wide variety of computing platforms. At present this demand is being met by commodity microprocessors together with standard operating system interfaces. However current systems do not offer a standard API (application program interface) for parallel programming, and the popular interfaces for parallel computing violate essential principles of modular or component-based software construction. Moreover microprocessor architecture is reaching the limit of what can be done usefully within the framework of superscalar and VLIW processor models. The next step is to put several processors (or the equivalent) on a single chip. This paper presents a set of principles for modular software construction and describes a program execution model based on functional programming that satisfies the set of principles. The implications of the principles for computer system architecture are discussed together with a sketch of the architecture of a multithread processing chip which promises to provide efficient execution of parallel computations while providing a sound base for modular software construction.

关键词： Computer architecture Modular construction Microprocessors Concurrent computing Operating systems Software standards Application software parallel programming parallel processing VLIW

来源：评论

学校读者我要写书评

暂无评论

Market-based massively parallel Internet computing

Market-based massively parallel Internet computing

引用

working conference on massively parallel programming models

作者： P. Cappello B.O. Christiansen M.O. Neary K.E. Schauser Department of Computer Science University of California슠Santa Barbara Santa Barbara CA USA

Recent advances in Internet connectivity and implementations of safer distributed computing through languages such as Java provide the foundation for transforming computing resources into tradable commodities. We have developed Javelin, a Java-based prototype of a globally distributed heterogeneous, high-performance computational infrastructure that conveniently enables rapid execution of massively parallel applications. Our infrastructure consists of three entities: Hosts, clients, and brokers. Our goal is to allow users to buy and sell computational power using supply and demand, and market mechanisms to marshal computational power far beyond what can be achieved via conventional techniques. Several research issues must be worked out to make this vision a reality: allocating resources between computational objects via market mechanisms; expressing and enforcing scheduling and quality of service constraints; modeling programming in a global computing ecosystem; supporting heterogeneous execution without sacrificing computational speed; ensuring host security; global naming and communication; and client privacy.

关键词： Internet Concurrent computing Distributed computing Computer vision Java Prototypes Supply and demand Resource management Processor scheduling Quality of service

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：