ClusterSs: a task-based programming model for clusters

IEEE International Symposium on High-Performance Parallel Distributed Computing Pub Date : 2011-06-08 DOI:10.1145/1996130.1996168

E. Tejedor, Montse Farreras, D. Grove, Rosa M. Badia, G. Almási, Jesús Labarta

{"title":"ClusterSs: a task-based programming model for clusters","authors":"E. Tejedor, Montse Farreras, D. Grove, Rosa M. Badia, G. Almási, Jesús Labarta","doi":"10.1145/1996130.1996168","DOIUrl":null,"url":null,"abstract":"Programming for large-scale, multicore-based architectures requires adequate tools that offer ease of programming while not hindering application performance. StarSs is a family of parallel programming models based on automatic function level parallelism that targets productivity. StarSs deploys a data-flow model: it analyses dependencies between tasks and manages their execution, exploiting their concurrency as much as possible. We introduce Cluster Superscalar (ClusterSs), a new StarSs member designed to execute on clusters of SMPs. ClusterSs tasks are asynchronously created and assigned to the available resources with the support of the IBM APGAS runtime, which provides an efficient and portable communication layer based on one-sided communication.\n This short paper gives an overview of the ClusterSs design on top of APGAS, as well as the conclusions of a productivity study; in this study, ClusterSs was compared to the IBM X10 language, both in terms of programmability and performance. A technical report is available with the details.","PeriodicalId":330072,"journal":{"name":"IEEE International Symposium on High-Performance Parallel Distributed Computing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE International Symposium on High-Performance Parallel Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1996130.1996168","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 29

Abstract

Programming for large-scale, multicore-based architectures requires adequate tools that offer ease of programming while not hindering application performance. StarSs is a family of parallel programming models based on automatic function level parallelism that targets productivity. StarSs deploys a data-flow model: it analyses dependencies between tasks and manages their execution, exploiting their concurrency as much as possible. We introduce Cluster Superscalar (ClusterSs), a new StarSs member designed to execute on clusters of SMPs. ClusterSs tasks are asynchronously created and assigned to the available resources with the support of the IBM APGAS runtime, which provides an efficient and portable communication layer based on one-sided communication. This short paper gives an overview of the ClusterSs design on top of APGAS, as well as the conclusions of a productivity study; in this study, ClusterSs was compared to the IBM X10 language, both in terms of programmability and performance. A technical report is available with the details.

查看原文本刊更多论文

clusters:用于集群的基于任务的编程模型

为大规模、基于多核的体系结构编程需要适当的工具，这些工具既能提供编程的便利性，又不会影响应用程序的性能。stars是一组基于自动功能级并行性的并行编程模型，其目标是提高生产率。stars部署了一个数据流模型:它分析任务之间的依赖关系并管理它们的执行，尽可能地利用它们的并发性。我们引入了集群超标量(clusters)，这是一个新的stars成员，设计用于在smp集群上执行。在IBM APGAS运行时的支持下，集群任务异步创建并分配给可用资源，该运行时提供了基于单侧通信的高效且可移植的通信层。这篇短文概述了基于APGAS的集群设计，以及生产力研究的结论;在本研究中，在可编程性和性能方面，将clusters与IBM X10语言进行了比较。一份技术报告提供了详细信息。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE International Symposium on High-Performance Parallel Distributed Computing

自引率

0.00%

发文量