Microprocessing and Microprogramming最新文献_第2页

Deriving structured parallel implementations for numerical methods 推导数值方法的结构化并行实现

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00007-5

Thomas Rauber, Gudula Rünger

{"title":"Deriving structured parallel implementations for numerical methods","authors":"Thomas Rauber, Gudula Rünger","doi":"10.1016/0165-6074(96)00007-5","DOIUrl":"10.1016/0165-6074(96)00007-5","url":null,"abstract":"<div><p>The numerical solution of differential equations is an important problem in the natural sciences and engineering. But the computational effort to find a solution with the desired accuracy is usually quite large. This suggests the use of powerful parallel machines which often use a distributed memory organization. In this article, we present a parallel programming methodology to derive structured parallel implementations of numerical methods that exhibit two levels of potential parallelism, a coarse-grain method parallelism and a medium grain parallelism on data or systems. The derivation process is subdivided into three stages: The first stage identifies the potential for parallelism in the numerical method, the second stage fixes the implementation decisions for a parallel program and the third stage derives the parallel implementation for a specific parallel machine. The derivation process is supported by a group-SPMD computational model that allows the prediction of runtimes for a specific parallel machine. This enables the programmer to test different alternatives and to implement only the most promising one. We give several examples for the derivation of parallel implementations and of the performance prediction. Experiments on an Intel iPSC/860 confirm the accuracy of the runtime predictions. The parallel programming methodology separates the software issues from the architectural details, enables the design of well-structured, reusable and portable software and supplies a formal basis for automatic support.</p></div>","PeriodicalId":100927,"journal":{"name":"Microprocessing and Microprogramming","volume":"41 8","pages":"Pages 589-608"},"PeriodicalIF":0.0,"publicationDate":"1996-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0165-6074(96)00007-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132860160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 23

Performance evaluation and optimization in low-cost cellular SIMD systems 低成本蜂窝SIMD系统的性能评估与优化

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00008-7

Alberto Broggi , Francesco Gregoretti

引用次数: 5

Scope: An extensible interactive environment for the performance evaluation of parallel systems 范围:用于并行系统性能评估的可扩展交互环境

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00003-8

Yves Arrouye

引用次数: 3

Calendar79 Calendar79

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/S0165-6074(96)90001-0

引用次数: 0

Modeling of optimal load balancing strategy using queueing theory 基于排队理论的最优负载均衡策略建模

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(95)00006-2

François Spies

引用次数: 30

Designing parallel programs by the graphical language GRAPNEL 用图形语言GRAPNEL设计并行程序

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00005-1

Péter Kacsuk, Gábor Dózsa, Tibor Fadgyas

引用次数: 56

Exploiting partial replication in unbalanced parallel loop scheduling on multicomputer 利用多机不平衡并行循环调度中的部分复制

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00002-6

Salvatore Orlando , Raffaele Perego

{"title":"Exploiting partial replication in unbalanced parallel loop scheduling on multicomputer","authors":"Salvatore Orlando , Raffaele Perego","doi":"10.1016/0165-6074(96)00002-6","DOIUrl":"10.1016/0165-6074(96)00002-6","url":null,"abstract":"<div><p>We consider the problem of scheduling parallel loops whose iterations operate on large array data structures and are characterized by highly varying execution times (<em>unbalanced or non-uniform</em> parallel loops). A general parallel loop implementation template for message-passing distributed-memory multiprocessors (<em>multicomputers</em>) is presented. Assuming that it is impossible to statically determine the distribution of the computational load on the data accessed, the template exploits a hybrid scheduling strategy. The data are partially replicated on the processor's local memories and iterations are statically scheduled until first load imbalances are detected. At this point an effective dynamic scheduling technique is adopted to move iterations among nodes holding the same data. Most of the communications needed to implement dynamic load balancing are overlapped with computations, as a very effective prefetching policy is adopted. The template scales very well, since knowing where data are replicated makes it possible to balance the load without introducing high overheads.</p><p>In the paper a formal characterization of load imbalance related to a generic problem instance is also proposed. This characterization is used to derive an analytical cost model for the template, and in particular, to tune those parameters of the template that depend on the costs related to the specific features of the target machine and the specific problem.</p><p>The template and the related cost model are validated by experiments conducted on a 128-node nCUBE 2, whose results are reported and discussed.</p></div>","PeriodicalId":100927,"journal":{"name":"Microprocessing and Microprogramming","volume":"41 8","pages":"Pages 645-658"},"PeriodicalIF":0.0,"publicationDate":"1996-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0165-6074(96)00002-6","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125448052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Parallel systems engineering 并行系统工程

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/S0165-6074(96)90000-9

Peter Milligan, Stephen Winter

引用次数: 0

A two-level programming strategy for distributed systems 分布式系统的两级编程策略

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(95)00032-1

D. Conde, R. Menéndez, M. González Harbour, J.A. Gregorio

{"title":"A two-level programming strategy for distributed systems","authors":"D. Conde, R. Menéndez, M. González Harbour, J.A. Gregorio","doi":"10.1016/0165-6074(95)00032-1","DOIUrl":"10.1016/0165-6074(95)00032-1","url":null,"abstract":"<div><p>In this paper we present a global approach for programming distributed multiprocessor systems. In this approach, applications are developed as a global parallel program that is independent of the particular hardware architecture, and is represented through an extended Petri net model. The building blocks for the global program are tasks that are implemented using standard programming languages. A highly automated tool is used to allocate the different tasks to processing nodes in a near-optimum way, minimizing message traffic in the interconnection network and balancing the execution workload in the different nodes. The combined use of this tool with analysis and simulation tools for Petri nets allows us to obtain information about the performance and behavior of the global program. The tool divides the original extended Petri net into several subnets that are distributed among the different nodes, and provides for the installation, execution, and monitoring of the program. An example is presented in which our programming strategy is compared to PVM, which is a widely extended software tool for the distribution of programs in a network of computers.</p></div>","PeriodicalId":100927,"journal":{"name":"Microprocessing and Microprogramming","volume":"41 8","pages":"Pages 541-554"},"PeriodicalIF":0.0,"publicationDate":"1996-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/0165-6074(95)00032-1","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134071098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From transformations to methodology in parallel program development: A case study 从并行程序开发中的转换到方法论:一个案例研究

Microprocessing and Microprogramming Pub Date : 1996-04-01 DOI: 10.1016/0165-6074(96)00004-X

Sergei Gorlatch

引用次数: 5